CN117495329B - Attendance machine data information management method based on Internet of things - Google Patents
Attendance machine data information management method based on Internet of things Download PDFInfo
- Publication number
- CN117495329B CN117495329B CN202410004437.6A CN202410004437A CN117495329B CN 117495329 B CN117495329 B CN 117495329B CN 202410004437 A CN202410004437 A CN 202410004437A CN 117495329 B CN117495329 B CN 117495329B
- Authority
- CN
- China
- Prior art keywords
- attendance
- absences
- employee
- staff
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000007726 management method Methods 0.000 title claims abstract description 13
- 238000000034 method Methods 0.000 claims abstract description 55
- 238000012937 correction Methods 0.000 claims abstract description 29
- 238000000926 separation method Methods 0.000 claims abstract description 3
- 238000010586 diagram Methods 0.000 claims description 22
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 238000005259 measurement Methods 0.000 claims description 6
- 238000003064 k means clustering Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 239000000758 substrate Substances 0.000 description 3
- 238000004080 punching Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/109—Time management, e.g. calendars, reminders, meetings or time accounting
- G06Q10/1091—Recording time for administrative or management purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2323—Non-hierarchical techniques based on graph theory, e.g. minimum spanning trees [MST] or graph cuts
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Resources & Organizations (AREA)
- Probability & Statistics with Applications (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Discrete Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to an attendance machine data information management method based on the Internet of things, which comprises the following steps: the method comprises the steps of obtaining attendance data of all staff, obtaining a working time characteristic value and a working time characteristic value of the staff according to working time and working time of the staff, obtaining an attendance characteristic sequence of the staff according to the working time characteristic value, working time characteristic value and attendance missing days of the staff, obtaining correction degree of attendance missing days of the staff according to a number value of an attendance missing reason of the staff and the number of separation days of two adjacent attendance missing days, correcting the attendance missing days of the staff according to the correction degree, obtaining a corrected attendance characteristic sequence, and clustering and storing the corrected attendance characteristic sequence. According to the method and the device for correcting the original data, the original data are corrected according to the characteristics of the attendance data of the staff, the data redundancy is reduced, the accuracy of the characteristics of the attendance data of each staff is improved, and the aim of better managing and storing the attendance data is achieved.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an attendance machine data information management method based on the Internet of things.
Background
With the development of technologies such as the internet of things, big data, artificial intelligence and the like, the data information management method of the attendance machine is continuously innovated and improved, and the working time of most companies at present implements an elastic working system, wherein the elastic working system refers to a system that staff can flexibly and autonomously select specific time schedule of work to replace uniform and fixed working time on the premise of completing a specified working task or fixed working time length. The system mainly aims to solve the contradiction between working time and personal living needs which possibly occur in the traditional fixed working time system, so that staff can find a better balance point between work and living, and enterprises can find problems of working rules, working efficiency and the like of the staff through deep analysis of attendance data, thereby providing basis for decision making of the enterprises.
Iterative self-organizing clustering is a common clustering method that calculates the distance between two data by calculating the Euclidean distance between the data during the clustering of the data. For the attendance data of each employee counted by the attendance machine, the card punching data which is not available in a certain day can be caused by reasons such as forgetting card punching, leave requesting, work absence and the like, and the abnormal degrees corresponding to different reasons are different. If the Euclidean distance between the attendance data of different staff is only calculated to determine that the distance between the two data cannot accurately represent the abnormal degree between the data, the difference between the data after clustering is overlarge, and the data management and the subsequent analysis are not facilitated.
Disclosure of Invention
In order to solve the problems, the invention provides an attendance machine data information management method based on the Internet of things.
The attendance machine data information management method based on the Internet of things adopts the following technical scheme:
the embodiment of the invention provides an attendance machine data information management method based on the Internet of things, which comprises the following steps:
Obtaining attendance data of all staff, wherein the attendance data comprises: the number value of the last two months of working time, attendance days and attendance reasons of each employee;
obtaining a plurality of working time characteristic values of each employee according to the working time of each employee in the attendance data for two months, obtaining a plurality of working time characteristic values of each employee according to the working time and the working time characteristic values of each employee in the attendance data for two months, and obtaining an attendance characteristic sequence of each employee according to the working time characteristic values, the working time characteristic values and the attendance days of each employee;
Obtaining a plurality of absences of each employee and days corresponding to each absences according to the attendance data, obtaining the absences of each employee according to the number value of the absences of each employee in the attendance data and the number of the separation days of adjacent two absences, obtaining the absences of each employee according to the absences of each employee and the difference of the absences of all employees, obtaining the absences of each employee and the difference of the absences of all employees according to the number value of the absences of each employee in the attendance data, and obtaining the correction of the absences of each employee according to the absences of each employee and the difference of the absences of all employees;
correcting the absenteeism days in the attendance feature sequence of each employee according to the correction degree of the absenteeism days of each employee to obtain a corrected attendance feature sequence of each employee, clustering the corrected attendance feature sequences, and storing the clustering result.
Further, according to the last two months of working hours of each employee in the attendance data, a plurality of working time characteristic values of each employee are obtained, and the method comprises the following specific steps:
Recording any staff as a target staff, acquiring all working hours of the target staff in the last two months according to attendance data, carrying out K-means clustering on all working hours, and obtaining a plurality of clusters by using a time interval value between working hours in distance measurement; for any cluster, constructing a shift time distribution diagram of the cluster, wherein the horizontal axis of the shift time distribution diagram is shift time arranged from the morning to the evening, the vertical axis of the shift time distribution diagram is the number of times corresponding to the shift time, and the shift time corresponding to the maximum number of times in the shift time distribution diagram is used as a shift time characteristic value of a target employee; and acquiring a working time characteristic value for each class cluster.
Further, according to the characteristic values of the time to work and the time to work of each employee in the last two months in the attendance data, a plurality of characteristic values of the time to work of each employee are obtained, and the method comprises the following specific steps:
For any on-duty time characteristic value of a target employee, acquiring all off-duty times of the on-duty time characteristic value of the target employee according to attendance data, recording the off-duty times as characteristic off-duty times of the on-duty time characteristic value, and constructing an off-duty time distribution diagram according to all characteristic off-duty times, wherein the horizontal axis of the off-duty time distribution diagram is the off-duty times arranged from the early to the late, and the vertical axis is the times corresponding to the characteristic off-duty times; and arranging all times corresponding to different characteristic off-hours in the off-hours time distribution diagram from large to small to obtain a time sequence, taking the characteristic off-hours time corresponding to the first times and the characteristic off-hours time corresponding to the second times in the time sequence as two initial off-hours time characteristic values corresponding to the off-hours time characteristic values of the target staff, obtaining a plurality of initial off-hours time characteristic values corresponding to other off-hours time characteristic values of the target staff, arranging all initial off-hours time characteristic values of the target staff from large to small according to the times corresponding to the initial off-hours time characteristic values to obtain a first time sequence, marking the number of all off-hours time characteristic values of the target staff as N, and taking the initial off-hours time characteristic values corresponding to the first N times in the first time sequence as the off-hours time characteristic values.
Further, the attendance characteristic sequence of each employee is obtained according to the working time characteristic value, the working time characteristic value and the absences days of each employee, and the specific steps are as follows:
Arranging all working time characteristic values of the target staff in an early-to-late order to obtain a first sequence, and arranging working time characteristic values of the target staff in an order from big to small according to corresponding times to obtain a second sequence; an empty initial attendance characteristic sequence is constructed, the length of the initial attendance characteristic sequence is 2 multiplied by N+1, N is the number of all attendance time characteristic values of a target employee, the first attendance time characteristic value in the first sequence is used as the first element of the initial attendance characteristic sequence, the first attendance time characteristic value in the second sequence is used as the second element of the initial attendance characteristic sequence, the second attendance time characteristic value in the first sequence is used as the third element of the initial attendance characteristic sequence, the second attendance time characteristic value in the second sequence is used as the fourth element of the initial attendance characteristic sequence, and so on until all attendance time characteristic values and all attendance time characteristic values of the target employee are added into the initial attendance characteristic sequence, the absences of the target employee are used as the last element of the initial attendance characteristic sequence, and finally the attendance characteristic sequence of the target employee is obtained.
Further, the step of obtaining a plurality of absences of each employee and days corresponding to each absences according to the attendance data, and obtaining the absences anomaly of each employee according to the number value of the absences reason of each employee and the number of days between two adjacent absences in the attendance data, includes the following specific steps:
recording each absent day of the target staff as one absent day, and obtaining a plurality of absent days and corresponding days of each absent day;
；
In the method, in the process of the invention, For the number value of the absences reason of the first absences of the target staff,/>For the total number of number values of the absences corresponding to the absences of the target staff, the number value of the absences corresponding to the absences of the target staff is/areFor the number of days apart of the kth absences and the kth-1 absences of the target employee,/>For the number value of the absences reason for the kth absences of the target staff,/>Minimum number value for absences of duty reasons of target staff,/>For the absences of target staff, abnormal degree,/>To avoid super parameters with denominator 0.
Further, the step of obtaining the difference between the absences of each employee and the absences of all employees according to the absences comprises the following specific steps:
；
In the method, in the process of the invention, For the absences of target staff, abnormal degree,/>For average absences of attendance anomaly for all employees,/>For the absenteeism degree parameter of target staff/>The specific acquisition method of (1) is as follows: if/>，/>If/>，/>，For the difference between the absences of target staff and the absences of all staff,/>Representing absolute values.
Further, according to the number value of the absenteeism reason of each employee in the attendance data, the difference degree between the absenteeism reason of each employee and the absenteeism reason of all employees is obtained, which comprises the following specific steps:
；
In the method, in the process of the invention, Average number value of absence reason corresponding to absence days of target staff,/>, of absence reasonFor the average number value of the absences corresponding to the i-th employee absences days,/>, the number value of the absences corresponding to the i-th employee absences daysFor the number of all employees,/>For the number value parameter of the target employee,/>The specific acquisition method of (1) is as follows: if/>，/>If/>，/>，/>For the difference degree of the absences of target staff and the absences of all staff,/>To avoid hyper-parameters with denominators 0,/>Representing absolute values.
Further, the step of obtaining the correction of the absences of each employee according to the difference between the absences of each employee and the absences of all employees and the difference between the absences of each employee and the absences of all employees comprises the following specific steps:
；
In the method, in the process of the invention, For the difference between the absences of target staff and the absences of all staff,/>For the difference degree of the absences of target staff and the absences of all staff,/>Initial correction for the absences of duty days of the target employee;
and linearly normalizing the initial correction degree of the absenteeism days of all the staff, wherein the obtained result is used as the correction degree of the absenteeism days of each staff.
Further, the correction of the absenteeism days in the attendance feature sequence of each employee according to the correction of the absenteeism days of each employee, obtaining the corrected attendance feature sequence of each employee, clustering the corrected attendance feature sequences and storing the clustering result, comprising the following specific steps:
Multiplying the attendance checking feature sequence of each employee by the correction degree of the corresponding attendance checking number, replacing the attendance checking number in the attendance checking feature sequence by the obtained product to obtain an attendance checking feature sequence corrected by each employee, carrying out iterative self-organizing clustering on the attendance checking feature sequences corrected by all employees, obtaining a plurality of final class clusters by adopting Euclidean distance between the corrected attendance checking feature sequences in distance measurement, and storing all the final class clusters respectively.
Further, the specific acquisition method of the number value of the absences cause is as follows:
The reasons of absence corresponding to false loss, false year and wedding holidays are uniformly numbered as 1, the reasons of absence corresponding to false event and false illness are uniformly numbered as 2, and the reasons of absence corresponding to open work are numbered as 3.
The technical scheme of the invention has the beneficial effects that: in the conventional ISODATA clustering method, in the process of clustering, the Euclidean distance between two data is directly used as the distance characteristic between the data, then the data is clustered according to the distance characteristic,
For attendance data based on the Internet of things, the working time and the working time of each employee per day are not necessarily the same, and partially repeated data exists in the attendance data. The reasons for the absences of each employee are different, and the abnormal degrees corresponding to the different absences are different, so that the distance between the attendance data of the two employees can not be accurately calculated only by calculating the Euclidean distance between the attendance data of the two employees.
Therefore, the invention calculates the characteristic value of the time to work in the attendance data of each employee according to the distribution condition of the dimension data of the time to work in the attendance data of each employee, and then calculates the characteristic value of the time to work out based on the characteristic value of the time to work in the attendance data of each employee. And finally, combining the characteristic values of the working time and the working time, namely the number of times of absence, to form an attendance characteristic sequence of each employee. And correcting the data of the absences of the attendance feature sequence of each employee according to the absences of each employee. And finally obtaining corrected data, and then clustering by using ISODATA through the corrected data.
Compared with the traditional ISODATA method for directly calculating the Euclidean distance to the data, the method and the device for correcting the data based on the characteristics of the attendance data of each employee correct the original data, reduce the redundancy of the data and improve the accuracy of the characteristics of the attendance data of each employee. Therefore, the accuracy of the clustering result is improved, the influence of inaccuracy of the original data characteristic representation on the clustering result is avoided, and the aim of better managing and storing the attendance data is fulfilled.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of steps of a method for managing data information of an attendance machine based on internet of things according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description is given below of the specific implementation, structure, characteristics and effects of the attendance machine data information management method based on the internet of things according to the invention by combining the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, 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 belongs.
The specific scheme of the attendance machine data information management method based on the Internet of things provided by the invention is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of steps of a method for managing data information of an attendance machine based on internet of things according to an embodiment of the present invention is shown, the method includes the following steps:
And S001, acquiring attendance data of all staff.
It should be noted that, the purpose of this embodiment is to analyze the attendance data of the staff in the past two months, calculate the characteristic value of each staff attendance data, correct the absenteeism day data in each staff attendance data, and finally use the corrected data to perform ISODATA clustering, i.e. iterative self-organizing clustering, to optimize the storage management of the attendance data, and before starting analysis, first need to collect the data and perform preprocessing.
Specifically, attendance data of all employees of any one company in the last two months are obtained through attendance management software, wherein the attendance data comprises the time of work on the last two months of each employee, the time of work off, the number of absences of service and the reason of absences of service; note that, in this embodiment, the working hours and the working hours only include hours and minutes, for example, a certain working time is 8:40.
It should be noted that, in order to facilitate the subsequent analysis, the attendance data needs to be quantified for the reasons of absences, which generally include false, loss of attendance, annual false, wedding holidays, absenteeism and sick false, and the reasons of absences are quantified by artificial division, and the embodiment is not limited to these reasons of absences and can be adjusted according to specific situations when implemented.
Specifically, the loss of duty, the annual false and wedding holidays all belong to normal absences, the absences reasons corresponding to the loss of duty, the annual false and wedding holidays are uniformly numbered as 1, the absences corresponding to the cases of false and sick false belong to the absences of personal reasons, the absences corresponding to the cases of false and sick false are uniformly numbered as 2, the absences corresponding to the absences of open workers are numbered as 3, and finally the number value of the absences is obtained.
So far, the attendance data of staff is obtained.
Step S002, obtaining a plurality of on-duty time characteristic values of each employee according to the last two months of on-duty time of each employee in the attendance data, obtaining a plurality of off-duty time characteristic values of each employee according to the last two months of off-duty time and on-duty time characteristic values of each employee in the attendance data, and obtaining an on-duty characteristic sequence of each employee according to the on-duty time characteristic values, the off-duty time characteristic values and the absences of duty days of each employee.
When the attendance data of all employees of the company are clustered, the time of the same employee to work and the time of the same employee to work are different each day due to the elastic work system, and the time of the same employee to work is different due to the fact that the same employee to work is available in the case of overtime. And where there may be a large number of repeated attendance data. The fact that all data are directly involved in the calculation of the distance between the attendance data of two staff can cause excessive redundancy of calculation. And there may be a situation that the attendance data of two employees are similar in a staggered manner in a daily unit, for example, the attendance data of employee 1 on day 1 is similar to the attendance data of employee 2 on day 2, and direct calculation may result in a larger distance deviation between the calculated attendance data of the two employees. It is therefore necessary to calculate characteristic data that determine the attendance of each employee.
Specifically, according to the last two months of working time of each employee in the attendance data, a plurality of working time characteristic values of each employee are obtained, and the method specifically comprises the following steps:
recording any staff as a target staff, acquiring all working hours of the target staff in the last two months according to attendance data, and carrying out K-means clustering on all working hours, wherein in the embodiment, the K value of the K-means clustering is described as 5, and the distance measurement adopts a time interval value between the working hours to obtain a plurality of clusters, namely 5 clusters; for any cluster, constructing a shift time distribution diagram of the cluster, wherein the horizontal axis of the shift time distribution diagram is shift time arranged from the morning to the evening, the vertical axis of the shift time distribution diagram is the number of times corresponding to the shift time, and the shift time corresponding to the maximum number of times in the shift time distribution diagram is used as a shift time characteristic value of a target employee; and acquiring a working time characteristic value for each class cluster.
Further, according to the characteristic values of the off-duty time and the on-duty time of each employee in the last two months in the attendance data, a plurality of characteristic values of the off-duty time of each employee are obtained, and the characteristic values are as follows:
For any on-duty time characteristic value of a target employee, acquiring all off-duty times of the on-duty time characteristic value of the target employee according to attendance data, recording the off-duty times as characteristic off-duty times of the on-duty time characteristic value, and constructing an off-duty time distribution diagram according to all characteristic off-duty times, wherein the horizontal axis of the off-duty time distribution diagram is the off-duty times arranged from the early to the late, and the vertical axis is the times corresponding to the characteristic off-duty times; it should be noted that, because there are multiple higher peaks in the time distribution diagram of the next shift, it is not very accurate to determine the characteristic value of the time of the next shift only according to the highest peak, and multiple characteristic values of the time of the next shift need to be selected; and arranging all times corresponding to different characteristic off-hours in the off-hours time distribution diagram from large to small to obtain a time sequence, taking the characteristic off-hours time corresponding to the first times and the characteristic off-hours time corresponding to the second times in the time sequence as two initial off-hours time characteristic values corresponding to the off-hours time characteristic values of the target staff, obtaining a plurality of initial off-hours time characteristic values corresponding to other off-hours time characteristic values of the target staff, arranging all initial off-hours time characteristic values of the target staff from large to small according to the times corresponding to the initial off-hours time characteristic values to obtain a first time sequence, marking the number of all off-hours time characteristic values of the target staff as N, and taking the initial off-hours time characteristic values corresponding to the first N times in the first time sequence as the off-hours time characteristic values.
Further, according to the working time characteristic value, the working time characteristic value and the absenteeism days of each employee, an attendance characteristic sequence of each employee is obtained, and the method specifically comprises the following steps:
arranging all working time characteristic values of the target staff in an early-to-late order to obtain a first sequence, and arranging working time characteristic values of the target staff in an order from big to small according to corresponding times to obtain a second sequence; an empty initial attendance characteristic sequence is constructed, the length of the initial attendance characteristic sequence is 2 multiplied by N+1, a first on-duty time characteristic value in the first sequence is taken as a first element of the initial attendance characteristic sequence, a first off-duty time characteristic value in the second sequence is taken as a second element of the initial attendance characteristic sequence, a second on-duty time characteristic value in the first sequence is taken as a third element of the initial attendance characteristic sequence, a second off-duty time characteristic value in the second sequence is taken as a fourth element of the initial attendance characteristic sequence, and so on until all on-duty time characteristic values and all off-duty time characteristic values of a target employee are added into the initial attendance characteristic sequence, the absent days of the target employee is taken as a last element of the initial attendance characteristic sequence, and finally the attendance characteristic sequence of the target employee is obtained.
So far, the attendance characteristic sequence of each employee is obtained.
Step S003, obtaining a plurality of absences of each employee and days corresponding to each absences according to the attendance data, obtaining the absences of each employee according to the number value of the absences of each employee and the number of days of the adjacent two absences in the attendance data, obtaining the differences of the absences of each employee and the absences of all employees according to the absences of each employee, obtaining the differences of the absences of each employee and the absences of all employees according to the number value of the absences of each employee in the attendance data, and obtaining the correction of the absences of each employee according to the differences of the absences of each employee and the absences of all employees and the differences of the absences of each employee and the absences of all employees.
It should be noted that, when the attendance feature sequences of each employee are obtained and the ISODATA clustering is performed on the attendance feature sequences of all employees, the difference between the attendance days cannot be accurately represented by the distance between the Euclidean distance calculated amount data, so that the clustering result is inaccurate, and therefore, the attendance days in the attendance feature sequences of each employee need to be corrected.
Specifically, a plurality of absences of each employee and days corresponding to each absences are obtained according to the attendance data, and the absences anomaly degree of each employee is obtained according to the number value of the absences reason of each employee and the number of the days of the adjacent two absences in the attendance data, specifically as follows:
And recording each absent day of the target staff as one absent day, and obtaining a plurality of absent days and corresponding days of each absent day.
；
In the method, in the process of the invention,For the number value of the absences reason of the first absences of the target staff,/>For the total number of number values of the absences corresponding to the absences of the target staff, the number value of the absences corresponding to the absences of the target staff is/areThe number of days apart for the kth absences and the kth-1 absences of the target employee, wherein the number of days apart refers to: if the target staff has two continuous absences, the number of days between the first absences and the second absences is 0 days, otherwise, the number of days between the two absences is/(>For the number value of the absences reason for the kth absences of the target staff,/>Minimum number value for absences of duty reasons of target staff,/>For the absences of target staff, abnormal degree,/>To avoid superparameters with denominators of 0, this embodiment uses/>Description will be made. If the target employee is not absent, the target employee does not participate in the absent abnormality calculation.
It should be noted that the number of the substrates,The smaller the value of (c) is, the more serious the condition that the target staff is suffering from continuity absences,Representing the difference degree between the number value corresponding to the kth absences of the target staff and the minimum number value,/>The smaller the value of/>The larger the value of (2), the greater the absences of the target employee from attendance anomaly.
Further, obtaining the absences anomaly of each employee and the difference of the absences anomaly of all employees according to the absences anomaly, wherein the difference is specifically as follows:
；
In the method, in the process of the invention, For the absences of target staff, abnormal degree,/>For average absences of attendance anomaly for all employees,/>For the absenteeism degree parameter of target staff/>The specific acquisition method of (1) is as follows: if/>，/>If/>，/>，For the difference between the absences of target staff and the absences of all staff,/>To avoid superparameters with denominators of 0, this embodiment uses/>To describe,/>Representing absolute values.
It should be noted that the number of the substrates,At this time, it indicates that the absences of the target employee are greater than or equal to the average absences of all employees, at this time/>The larger the difference between the absent degree of the target employee and the average absent degree is, namely the larger the difference between the absent degree of the target employee and the absent degree of all employees is, and conversely the smaller the difference between the absent degree of the target employee and the absent degree of all employees is.
It should be noted that, the difference of the absences of each employee and all employees is analyzed, but the actual difference of the absences of each employee cannot be represented only by calculating the difference of the absences, and due to the difference of the absences, there are a plurality of absences of a certain employee, but the number of the absences is smaller, or the number of the absences is smaller, but the number of the absences is larger. These conditions can lead to large deviations in the subsequent clustering results. It is necessary to correct the absences anomaly difference according to the absences cause.
Specifically, according to the number value of the absenteeism reason of each employee in the attendance data, the difference degree between the absenteeism reason of each employee and the absenteeism reason of all employees is obtained, specifically as follows:
；
In the method, in the process of the invention, Average number value of absence reason corresponding to absence days of target staff,/>, of absence reasonFor the average number value of the absences corresponding to the i-th employee absences days,/>, the number value of the absences corresponding to the i-th employee absences daysFor the number of all employees (including target employee),/>For the number value parameter of the target employee,/>The specific acquisition method of (1) is as follows: if/>，/>If/>，，/>For the difference degree of the absences of target staff and the absences of all staff,/>To avoid superparameters with denominators of 0, this embodiment uses/>To describe,/>Representing absolute values.
It should be noted that the number of the substrates,When the average number value of the absences of the target staff is greater than or equal to the average number value of the absences of all staff, the/>The larger the difference between the absences of the target staff and the absences of all staff is, the smaller the difference between the absences of the target staff and the absences of all staff is, on the contrary.
Further, according to the difference between the absences of each employee and the absences of all employees and the difference between the absences of each employee and the absences of all employees, the correction of the absences of each employee is obtained, specifically as follows:
；
In the method, in the process of the invention, For the difference between the absences of target staff and the absences of all staff,/>For the difference degree of the absences of target staff and the absences of all staff,/>Initial correction for the number of absences of the target employee.
And linearly normalizing the initial correction degree of the absenteeism days of all the staff, wherein the obtained result is used as the correction degree of the absenteeism days of each staff.
Thus, the correction degree of the absenteeism days of each employee is obtained.
And S004, correcting the absenteeism days in the attendance feature sequence of each employee according to the correction degree of the absenteeism days of each employee to obtain a corrected attendance feature sequence of each employee, clustering the corrected attendance feature sequences, and storing the clustering result.
The attendance feature sequence of each employee and the correction degree of the absenteeism days of each employee are obtained respectively, the absenteeism days in the attendance feature sequence are corrected according to the correction degree of the absenteeism days to obtain a corrected attendance feature sequence, and the corrected attendance feature sequence is clustered and the clustering result is stored.
Specifically, multiplying the absenteeism days in the attendance feature sequences of each employee by the correction degree of the corresponding absenteeism days, replacing the absenteeism days in the attendance feature sequences by the obtained product to obtain the corrected attendance feature sequences of each employee, performing iterative self-organizing clustering on the corrected attendance feature sequences of all employees, obtaining a plurality of final class clusters by adopting Euclidean distances among the corrected attendance feature sequences in distance measurement, and storing all the final class clusters respectively; the clustering results are conveniently analyzed by the company, for example, the working time of corresponding staff in a certain final class cluster is biased to afternoon, the working time is long, namely the working time is late, the overtime condition usually exists, and the number of absences is large. The company can optimize the working time or the working content of the staff corresponding to the final class cluster, distribute the working tasks suitable for afternoon to the cluster staff, and manage the absent state of the staff corresponding to the class cluster. Therefore, work tasks are reasonably distributed according to the working time and the working state of each employee, the manpower resource allocation is optimized, and the effect of improving the working efficiency is achieved.
Through the steps, the attendance machine data information management method based on the Internet of things is completed.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (9)
1. The attendance machine data information management method based on the Internet of things is characterized by comprising the following steps of:
Obtaining attendance data of all staff, wherein the attendance data comprises: the number value of the last two months of working time, attendance days and attendance reasons of each employee;
obtaining a plurality of working time characteristic values of each employee according to the working time of each employee in the attendance data for two months, obtaining a plurality of working time characteristic values of each employee according to the working time and the working time characteristic values of each employee in the attendance data for two months, and obtaining an attendance characteristic sequence of each employee according to the working time characteristic values, the working time characteristic values and the attendance days of each employee;
Obtaining a plurality of absences of each employee and days corresponding to each absences according to the attendance data, obtaining the absences of each employee according to the number value of the absences of each employee in the attendance data and the number of the separation days of adjacent two absences, obtaining the absences of each employee according to the absences of each employee and the difference of the absences of all employees, obtaining the absences of each employee and the difference of the absences of all employees according to the number value of the absences of each employee in the attendance data, and obtaining the correction of the absences of each employee according to the absences of each employee and the difference of the absences of all employees;
correcting the absenteeism days in the attendance feature sequence of each employee according to the correction degree of the absenteeism days of each employee to obtain a corrected attendance feature sequence of each employee, clustering the corrected attendance feature sequences, and storing a clustering result;
the method comprises the following specific steps of obtaining the attendance anomaly of each employee according to the number value of the attendance reason of each employee in the attendance data and the number of the interval days of the adjacent two absences, wherein the number of absences of each employee and the days corresponding to each absences are obtained according to the attendance data:
marking any staff as target staff, marking each absent day of the target staff as one absent, and obtaining a plurality of absent and days corresponding to each absent;
；
In the method, in the process of the invention, For the number value of the absences reason of the first absences of the target staff,/>For the total number of number values of the absences corresponding to the absences of the target staff, the number value of the absences corresponding to the absences of the target staff is/areFor the number of days apart of the kth absences and the kth-1 absences of the target employee,/>For the number value of the absences reason for the kth absences of the target staff,/>Minimum number value for absences of duty reasons of target staff,/>For the absences of target staff, abnormal degree,/>To avoid super parameters with denominator 0.
2. The method for managing data information of the attendance machine based on the internet of things according to claim 1, wherein the step of obtaining a plurality of time feature values of each employee according to the last two months of time of work of each employee in the attendance data comprises the following specific steps:
Obtaining all working times of a target employee in the last two months according to the attendance data, carrying out K-means clustering on all working times, and obtaining a plurality of clusters by using a time interval value between the working times in distance measurement; for any cluster, constructing a shift time distribution diagram of the cluster, wherein the horizontal axis of the shift time distribution diagram is shift time arranged from the morning to the evening, the vertical axis of the shift time distribution diagram is the number of times corresponding to the shift time, and the shift time corresponding to the maximum number of times in the shift time distribution diagram is used as a shift time characteristic value of a target employee; and acquiring a working time characteristic value for each class cluster.
3. The method for managing data information of the attendance machine based on the internet of things according to claim 2, wherein the step of obtaining a plurality of time feature values of each employee for work hours according to the time feature values of work hours and work hours of each employee in the attendance data for two months comprises the following specific steps:
For any on-duty time characteristic value of a target employee, acquiring all off-duty times of the on-duty time characteristic value of the target employee according to attendance data, recording the off-duty times as characteristic off-duty times of the on-duty time characteristic value, and constructing an off-duty time distribution diagram according to all characteristic off-duty times, wherein the horizontal axis of the off-duty time distribution diagram is the off-duty times arranged from the early to the late, and the vertical axis is the times corresponding to the characteristic off-duty times; and arranging all times corresponding to different characteristic off-hours in the off-hours time distribution diagram from large to small to obtain a time sequence, taking the characteristic off-hours time corresponding to the first times and the characteristic off-hours time corresponding to the second times in the time sequence as two initial off-hours time characteristic values corresponding to the off-hours time characteristic values of the target staff, obtaining a plurality of initial off-hours time characteristic values corresponding to other off-hours time characteristic values of the target staff, arranging all initial off-hours time characteristic values of the target staff from large to small according to the times corresponding to the initial off-hours time characteristic values to obtain a first time sequence, marking the number of all off-hours time characteristic values of the target staff as N, and taking the initial off-hours time characteristic values corresponding to the first N times in the first time sequence as the off-hours time characteristic values.
4. The method for managing data information of an attendance machine based on the internet of things according to claim 3, wherein the step of obtaining the attendance feature sequence of each employee according to the on-duty time feature value, the off-duty time feature value and the absences days of each employee comprises the following specific steps:
Arranging all working time characteristic values of the target staff in an early-to-late order to obtain a first sequence, and arranging working time characteristic values of the target staff in an order from big to small according to corresponding times to obtain a second sequence; an empty initial attendance characteristic sequence is constructed, the length of the initial attendance characteristic sequence is 2 multiplied by N+1, N is the number of all attendance time characteristic values of a target employee, the first attendance time characteristic value in the first sequence is used as the first element of the initial attendance characteristic sequence, the first attendance time characteristic value in the second sequence is used as the second element of the initial attendance characteristic sequence, the second attendance time characteristic value in the first sequence is used as the third element of the initial attendance characteristic sequence, the second attendance time characteristic value in the second sequence is used as the fourth element of the initial attendance characteristic sequence, and so on until all attendance time characteristic values and all attendance time characteristic values of the target employee are added into the initial attendance characteristic sequence, the absences of the target employee are used as the last element of the initial attendance characteristic sequence, and finally the attendance characteristic sequence of the target employee is obtained.
5. The method for managing data information of an attendance machine based on the internet of things according to claim 1, wherein the step of obtaining the absences of each employee and the differences of the absences of all employees according to the absences comprises the following specific steps:
；
In the method, in the process of the invention, For the absences of target staff, abnormal degree,/>For average absences of attendance anomaly for all employees,/>For the absenteeism degree parameter of target staff/>The specific acquisition method of (1) is as follows: if/>，/>If/>，/>，/>For the difference between the absences of target staff and the absences of all staff,/>Representing absolute values.
6. The method for managing data information of an attendance machine based on the internet of things according to claim 1, wherein the step of obtaining the difference between the absences of each employee and the absences of all employees according to the number value of the absences of each employee in the attendance data comprises the following specific steps:
；
In the method, in the process of the invention, Average number value of absence reason corresponding to absence days of target staff,/>, of absence reasonFor the average number value of the absences corresponding to the i-th employee absences days,/>, the number value of the absences corresponding to the i-th employee absences daysFor the number of all employees,/>For the number value parameter of the target employee,/>The specific acquisition method of (1) is as follows: if/>，/>If/>，/>，/>For the difference degree of the absences of target staff and the absences of all staff,/>To avoid hyper-parameters with denominators 0,/>Representing absolute values.
7. The method for managing data information of an attendance machine based on the internet of things according to claim 1, wherein the obtaining the correction of the absenteeism days of each employee according to the difference between the absenteeism of each employee and the absenteeism of all employees and the difference between the absenteeism reasons of each employee and the absenteeism reasons of all employees comprises the following specific steps:
；
In the method, in the process of the invention, For the difference between the absences of target staff and the absences of all staff,/>For the difference degree of the absences of target staff and the absences of all staff,/>Initial correction for the absences of duty days of the target employee;
and linearly normalizing the initial correction degree of the absenteeism days of all the staff, wherein the obtained result is used as the correction degree of the absenteeism days of each staff.
8. The method for managing data information of attendance machine based on internet of things according to claim 1, wherein the correcting the absenteeism days in the attendance feature sequence of each employee according to the correction degree of the absenteeism days of each employee to obtain the corrected attendance feature sequence of each employee, clustering the corrected attendance feature sequences and storing the clustering result comprises the following specific steps:
Multiplying the attendance checking feature sequence of each employee by the correction degree of the corresponding attendance checking number, replacing the attendance checking number in the attendance checking feature sequence by the obtained product to obtain an attendance checking feature sequence corrected by each employee, carrying out iterative self-organizing clustering on the attendance checking feature sequences corrected by all employees, obtaining a plurality of final class clusters by adopting Euclidean distance between the corrected attendance checking feature sequences in distance measurement, and storing all the final class clusters respectively.
9. The method for managing data information of the attendance machine based on the internet of things according to claim 1, wherein the specific method for acquiring the number value of the absenteeism reason is as follows:
The reasons of absence corresponding to false loss, false year and wedding holidays are uniformly numbered as 1, the reasons of absence corresponding to false event and false illness are uniformly numbered as 2, and the reasons of absence corresponding to open work are numbered as 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410004437.6A CN117495329B (en) | 2024-01-03 | 2024-01-03 | Attendance machine data information management method based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410004437.6A CN117495329B (en) | 2024-01-03 | 2024-01-03 | Attendance machine data information management method based on Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117495329A CN117495329A (en) | 2024-02-02 |
| CN117495329B true CN117495329B (en) | 2024-05-07 |
Family
ID=89673075
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410004437.6A Active CN117495329B (en) | 2024-01-03 | 2024-01-03 | Attendance machine data information management method based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117495329B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108921496A (en) * | 2018-06-04 | 2018-11-30 | 熊猫电子集团有限公司 | A kind of attendance data statistical analysis technique and system |
| CN109416846A (en) * | 2017-11-27 | 2019-03-01 | 齐心商用设备(深圳)有限公司 | The implementation method and device of staff attendance |
| CN111160779A (en) * | 2019-12-30 | 2020-05-15 | 厦门中控智慧信息技术有限公司 | Priority-based scheduling and attendance management method, system and equipment |
| CN111258585A (en) * | 2020-01-07 | 2020-06-09 | 厦门中控智慧信息技术有限公司 | Attendance calculation method, system and equipment |
| CN114757639A (en) * | 2022-03-28 | 2022-07-15 | 中国银行股份有限公司 | Data processing method, device, equipment and storage medium |
| CN114862339A (en) * | 2022-04-11 | 2022-08-05 | 无锡喔趣信息科技有限公司 | Attendance information automatic management system and method for human resources |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11501107B2 (en) * | 2020-05-07 | 2022-11-15 | Adobe Inc. | Key-value memory network for predicting time-series metrics of target entities |
-
2024
- 2024-01-03 CN CN202410004437.6A patent/CN117495329B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109416846A (en) * | 2017-11-27 | 2019-03-01 | 齐心商用设备(深圳)有限公司 | The implementation method and device of staff attendance |
| CN108921496A (en) * | 2018-06-04 | 2018-11-30 | 熊猫电子集团有限公司 | A kind of attendance data statistical analysis technique and system |
| CN111160779A (en) * | 2019-12-30 | 2020-05-15 | 厦门中控智慧信息技术有限公司 | Priority-based scheduling and attendance management method, system and equipment |
| CN111258585A (en) * | 2020-01-07 | 2020-06-09 | 厦门中控智慧信息技术有限公司 | Attendance calculation method, system and equipment |
| CN114757639A (en) * | 2022-03-28 | 2022-07-15 | 中国银行股份有限公司 | Data processing method, device, equipment and storage medium |
| CN114862339A (en) * | 2022-04-11 | 2022-08-05 | 无锡喔趣信息科技有限公司 | Attendance information automatic management system and method for human resources |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117495329A (en) | 2024-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021052031A1 (en) | Statistical interquartile range-based commodity inventory risk early warning method and system, and computer readable storage medium | |
| CN116523262B (en) | Intelligent planning method, system and medium for production plan based on big data | |
| CN113126019B (en) | Remote estimation method, system, terminal and storage medium for error of intelligent ammeter | |
| CN116579590B (en) | Demand response evaluation method and system in virtual power plant | |
| CN110689190A (en) | Power grid load prediction method and device and related equipment | |
| CN108428055B (en) | Load clustering method considering load longitudinal characteristics | |
| CN110390563A (en) | Quantization method, device, computer equipment and the storage medium of user's value | |
| CN117495329B (en) | Attendance machine data information management method based on Internet of things | |
| CN116385210B (en) | Power supply energy consumption monitoring system based on Internet of things | |
| CN112464165A (en) | Method for improving measuring point statistical efficiency, storage medium and computing device | |
| CN114676931B (en) | Electric quantity prediction system based on data center technology | |
| CN112016765A (en) | Asset allocation method and device based on quantitative investment risk preference and terminal | |
| CN111325433A (en) | Scheduling method, device, equipment and storage medium in logistics field | |
| CN111613312B (en) | Equipment operation condition comparison analysis method and device | |
| CN112348220A (en) | Credit risk assessment prediction method and system based on enterprise behavior pattern | |
| CN116629714B (en) | Power plant performance management method and system | |
| CN117742975B (en) | Resource data processing method and device, storage medium and electronic equipment | |
| CN117786370A (en) | Information intelligent analysis system for gridding service terminal | |
| CN114900443B (en) | Method and device for establishing incoming line traffic prediction model | |
| CN117541200B (en) | Project management method and system based on LTC flow | |
| CN112801333B (en) | XGBoost-based power distribution network line summer peak load prediction method | |
| CN114596667A (en) | Data sharing method, system and computer storage medium | |
| CN117742975A (en) | Resource data processing method and device, storage medium and electronic equipment | |
| CN116720322A (en) | Intelligent recommendation model design method for demand response potential users, industries and lines | |
| CN117131043A (en) | Real-time storage and display system using voltage drop load |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |