CN110399362A - Screening technique, device, computer equipment and the storage medium of abnormal attendance data - Google Patents
Screening technique, device, computer equipment and the storage medium of abnormal attendance data Download PDFInfo
- Publication number
- CN110399362A CN110399362A CN201910533062.1A CN201910533062A CN110399362A CN 110399362 A CN110399362 A CN 110399362A CN 201910533062 A CN201910533062 A CN 201910533062A CN 110399362 A CN110399362 A CN 110399362A
- Authority
- CN
- China
- Prior art keywords
- data
- attendance
- history
- screening
- target
- 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.)
- Pending
Links
- 238000012216 screening Methods 0.000 title claims abstract description 137
- 238000000034 method Methods 0.000 title claims abstract description 97
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 58
- 238000003860 storage Methods 0.000 title claims abstract description 28
- 238000012544 monitoring process Methods 0.000 claims abstract description 27
- 239000012141 concentrate Substances 0.000 claims abstract description 8
- 230000008569 process Effects 0.000 claims description 45
- 238000004590 computer program Methods 0.000 claims description 14
- 238000001914 filtration Methods 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 7
- 238000000354 decomposition reaction Methods 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 5
- 238000013480 data collection Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 16
- 238000012545 processing Methods 0.000 description 13
- 238000007781 pre-processing Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 5
- 230000001815 facial effect Effects 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 238000012795 verification Methods 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 238000013450 outlier detection Methods 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000014759 maintenance of location Effects 0.000 description 2
- 238000013508 migration Methods 0.000 description 2
- 230000005012 migration Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000009412 basement excavation Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
- G07C1/10—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people together with the recording, indicating or registering of other data, e.g. of signs of identity
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses the screening technique of abnormal attendance data, device, computer equipment and storage mediums.This method comprises: positioning obtains attendance data set, corresponding history attendance data set is obtained according to data screening condition in attendance data set；According to data screening strategy, each history attendance data subset obtains corresponding target data from history attendance data set, to obtain target data subset；It obtains and concentrates the attendance time point of each target data corresponding monitor video with target data, according to target user present in recognition of face acquisition monitor video；If there is the user corresponding with each target data of target user present in monitoring data not identical, corresponding target data is subjected to suspicious data mark.The method achieve accurately excavating the target data for meeting data screening strategy from attendance data set, and the suspicious data in target data is further determined that in conjunction with face recognition technology, checked card the effective monitoring of situation with realizing to generation.
Description
Technical field
The present invention relates to technical field of data processing more particularly to a kind of screening technique, device, the meters of abnormal attendance data
Calculate machine equipment and storage medium.
Background technique
Currently, the common attendance mode of enterprise staff has fingerprint to check card, recognition of face is checked card, the scraps of paper are checked card (specifically such as to
The insertion attendance scraps of paper printing attendance time is checked card with realizing in attendance record terminal), brush employee job card checks card (by employee job card and attendance end
End in contact realization of swiping the card is checked card), attendance APP positioning is checked card (nail of such as Ali is followed closely) mode.Due to some large enterprises employee
Number is more, and the more commonly used mode of checking card is that brush employee job card is checked card.But by this attendance mode, stored in server
Attendance data is only when the employee job card of each employee swipes the card on attendance record terminal, can not know each attendance data whether be
It really checks card attendance data, namely can not judge the case where each attendance data is checked card in generation with the presence or absence of employee, it more can not be with
The suspicious attendance data being directed to for situation of checking card is excavated based on actual attendance data.
Summary of the invention
The embodiment of the invention provides screening technique, device, computer equipment and the storages of a kind of abnormal attendance data to be situated between
Matter, it is intended to solve the excavation that can not carry out suspicious attendance data for the attendance data being stored in server in the prior art
Problem.
In a first aspect, the embodiment of the invention provides a kind of screening techniques of abnormal attendance data comprising:
If the difference of the time of present system time and upper data screening time are equal to pre-set timing cycle, positioning
Attendance data set is obtained, is obtained in the attendance data set according to the data screening condition generated by present system time
Corresponding history attendance data set；
According to pre-set data screening strategy from the history attendance data set each history attendance data subset
Corresponding target data is obtained, to obtain target data subset corresponding with each history attendance data subset；
It obtains and concentrates the attendance time point of each target data corresponding monitor video with the target data, according to face
Identification obtains target user present in monitor video；
If having the user corresponding with each target data of target user present in monitoring data not identical, by corresponding target
Data carry out suspicious data mark；And
Suspicious data respectively with suspicious data mark is stored to pre-set tables of data, abnormal attendance data is obtained
Table.
Second aspect, the embodiment of the invention provides a kind of screening plants of abnormal attendance data comprising:
Data screening unit is set in advance if being equal to for the difference of present system time and the time of upper data screening time
The timing cycle set, positioning obtain attendance data set, and basis is generated by present system time in the attendance data set
Data screening condition obtain corresponding history attendance data set；
Target data acquiring unit, for according to pre-set data screening strategy from the history attendance data set
In each history attendance data subset obtain corresponding target data, to obtain number of targets corresponding with each history attendance data subset
According to subset；
Target user's acquiring unit, for obtaining the attendance time point pair for concentrating each target data with the target data
The monitor video answered, according to target user present in recognition of face acquisition monitor video；
Suspicious mark unit, if for having the user corresponding with each target data of target user present in monitoring data not
It is identical, corresponding target data is subjected to suspicious data mark；And
Tables of data acquiring unit, for storing the suspicious data respectively with suspicious data mark to pre-set data
Table obtains abnormal attendance data table.
The third aspect, the embodiment of the present invention provide a kind of computer equipment again comprising memory, processor and storage
On the memory and the computer program that can run on the processor, the processor execute the computer program
The screening technique of abnormal attendance data described in the above-mentioned first aspect of Shi Shixian.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, wherein the computer can
It reads storage medium and is stored with computer program, it is above-mentioned that the computer program when being executed by a processor executes the processor
The screening technique of abnormal attendance data described in first aspect.
The embodiment of the invention provides screening technique, device, computer equipment and the storages of a kind of abnormal attendance data to be situated between
Matter.If this method included that present system time and the difference of the time of upper data screening time are equal to pre-set timing week
Phase, positioning obtain attendance data set, according to the data screening generated by present system time in the attendance data set
Condition obtains corresponding history attendance data set；According to pre-set data screening strategy from the history attendance data collection
Each history attendance data subset obtains corresponding target data in conjunction, to obtain target corresponding with each history attendance data subset
Data subset；It obtains and concentrates the attendance time point of each target data corresponding monitor video with the target data, according to people
Face identification obtains target user present in monitor video；If having target user present in monitoring data and each target data pair
The user answered is not identical, and corresponding target data is carried out suspicious data mark；And by respectively with suspicious data mark can
Doubtful data are stored to pre-set tables of data, obtain abnormal attendance data table.The method achieve quasi- from attendance data set
True excavates the target data for meeting data screening strategy, and further determines that in target data in conjunction with face recognition technology
Suspicious data, to realize to the effective monitoring for situation of checking card.
Detailed description of the invention
Technical solution in order to illustrate the embodiments of the present invention more clearly, below will be to needed in embodiment description
Attached drawing is briefly described, it should be apparent that, drawings in the following description are some embodiments of the invention, general for this field
For logical technical staff, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is the application scenarios schematic diagram of the screening technique of abnormal attendance data provided in an embodiment of the present invention；
Fig. 2 is the flow diagram of the screening technique of abnormal attendance data provided in an embodiment of the present invention；
Fig. 3 is the sub-process schematic diagram of the screening technique of abnormal attendance data provided in an embodiment of the present invention；
Fig. 4 is another sub-process schematic diagram of the screening technique of abnormal attendance data provided in an embodiment of the present invention；
Fig. 5 is another sub-process schematic diagram of the screening technique of abnormal attendance data provided in an embodiment of the present invention；
Fig. 6 is the schematic block diagram of the screening plant of abnormal attendance data provided in an embodiment of the present invention；
Fig. 7 is the subelement schematic block diagram of the screening plant of abnormal attendance data provided in an embodiment of the present invention；
Fig. 8 is another subelement schematic block diagram of the screening plant of abnormal attendance data provided in an embodiment of the present invention；
Fig. 9 is another subelement schematic block diagram of the screening plant of abnormal attendance data provided in an embodiment of the present invention；
Figure 10 is the schematic block diagram of computer equipment provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
It should be appreciated that ought use in this specification and in the appended claims, term " includes " and "comprising" instruction
Described feature, entirety, step, operation, the presence of element and/or component, but one or more of the other feature, whole is not precluded
Body, step, operation, the presence or addition of element, component and/or its set.
It is also understood that mesh of the term used in this description of the invention merely for the sake of description specific embodiment
And be not intended to limit the present invention.As description of the invention and it is used in the attached claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singular, "one" and "the" are intended to include plural form.
It will be further appreciated that the term "and/or" used in description of the invention and the appended claims is
Refer to any combination and all possible combinations of one or more of associated item listed, and including these combinations.
Fig. 1 and Fig. 2 are please referred to, Fig. 1 is the applied field of the screening technique of abnormal attendance data provided in an embodiment of the present invention
Scape schematic diagram, Fig. 2 are the flow diagram of the screening technique of abnormal attendance data provided in an embodiment of the present invention, the exception attendance
The screening technique of data is applied in server, and this method is executed by the application software being installed in server.
As shown in Fig. 2, the method comprising the steps of S110~S150.
If the difference of the time of S110, present system time and upper data screening time are equal to pre-set timing week
Phase, positioning obtain attendance data set, according to the data screening generated by present system time in the attendance data set
Condition obtains corresponding history attendance data set.
It, can be by pre- when in the present embodiment, in order to periodically carry out the analysis of suspicious data to history attendance data
If timing cycle the time is corresponded to according to the data screening conditional filtering that automatically generates from the attendance data table of each attendance record terminal
The history attendance data of section, to obtain history attendance data set.
For example, the office space of certain enterprise A is divided into M layers, each layer of N number of inlet is each provided with 1 attendance record terminal, on
It states each attendance record terminal of M*N attendance record terminal and is provided with only one attendance record terminal number, the attendance that each attendance record terminal obtains
Data have subdatasheet corresponding with the attendance record terminal to be stored in the server.After above-mentioned setting, user (such as look forward to
Industry is responsible for the administrative personnel of attendance verification) the week-night 9:00 in settable each week is in the corresponding subdatasheet of each attendance record terminal
Workaday history attendance data is (at this point, the evening of current week-night 9:00 and a upper Sunday in this week of middle screening
The difference of the time of 9:00 is 7 days, wherein being within 7 days pre-set timing cycle), it obtains history corresponding with each attendance record terminal and examines
Diligent data subset, to form history attendance data set.
In one embodiment, as shown in figure 3, step S110 includes:
The subdatasheet for the attendance record terminal that S111, positioning and server connect, by the corresponding subdatasheet of each attendance record terminal
Form attendance data set；
S112, data screening condition is generated according to present system time；
S113, data screening is carried out in each subdatasheet according to the data screening condition, it is whole with each attendance to obtain
Hold corresponding history attendance data subset；
S114, the corresponding history attendance data subset of each attendance record terminal is combined, obtains history attendance data collection
It closes.
In the present embodiment, since the attendance record terminal attendance data set collected respectively connected with server can be corresponding
Corresponding subdatasheet is stored into the storage region of server.It, need to be by each attendance record terminal pair in order to obtain attendance data set
The subdatasheet answered, which is combined, to be obtained.Wherein, need each attendance whole to know the source of each subdatasheet in the server
It holds when sending stored subdatasheet, need to number that form equipment unique according to the device number and attendance record terminal of each attendance record terminal
Identification code carries out the name of table name with subdata table.For example, the device number of attendance record terminal 1 is ABCDEF, attendance record terminal is compiled
Number be 1, can successively by device number and attendance record terminal number concatenation, obtain equipment unique identifier.When server receives attendance
When subdatasheet transmitted by terminal 1, the subdatasheet is ordered with the equipment unique identifier ABCDEF1 of attendance record terminal 1
Name.
Later, data screening condition is automatically generated according to current system time and preset data screening period.Example
Such as, current system time is X1 month X2 day 21:00 in 2019, it is assumed that the same day is Sunday, at this time data screening generated
Condition is that the date intervals before current system time and between the date corresponding to current system time are less than 7
It.
After having obtained data screening condition, according to the data screening condition in the corresponding subdata of each attendance record terminal
Data screening is carried out in table, to obtain the history attendance data subset corresponding with each attendance record terminal, thus by each attendance record terminal
Corresponding history attendance data subset forms history attendance data set.In order to reduce in the corresponding subdatasheet of each attendance record terminal
The amount of storage of attendance data, evening at the end of month 11:30 of settable every month by the attendance data of current month in subdatasheet into
Row Data Migration stores the historical data sublist being correspondingly arranged into server or other databases with the attendance record terminal.Pass through
Aforesaid way, so that the attendance data in subdatasheet corresponding with each attendance record terminal is only current month in the server
Attendance data greatly reduces the data volume of subdatasheet, so that subsequent data screening process is more efficient.
In one embodiment, after step S110 further include:
Obtain the corresponding attendance record terminal number of each history attendance data subset；
The corresponding attendance record terminal number of each history attendance data subset is remmed divided by preset apportioning cost, to obtain
Sequence number corresponding with each attendance record terminal number；
Judge whether the number of each sequence number is greater than 1；
If there is the number of sequence number to be greater than 1, by the corresponding corresponding history attendance data of attendance record terminal number institute of sequence number
Subset presses the lexcographical order of attendance record terminal number, is sequentially sent to and sequence number corresponding process.
It in the present embodiment,, can in order to improve data screening efficiency after server obtains history attendance data set
The corresponding history attendance data subset in attendance end each in the history attendance data set is distributed to a correspondence respectively
Process carry out data screening, in each process on be pre-configured with data screening strategy, complete number when each process end is corresponding
After obtaining target data subset according to screening, carried out in the storage region of server centrally stored.Wherein, in the server of multicore
In, multiple processes can be concurrently carried out to realize the concurrent processing of data processing.Moreover, including multiple threads in each process to control
Make the execution of corresponding process.By multithreading, data screening efficiency is effectively improved.
Such as assume to start 10 processes in server, and the history attendance data subset in history attendance data set
Total number be 30, can be assigned in each process at this time processing 3 history attendance data subsets data screening task (example
The attendance record terminal number for each attendance record terminal such as connecting with server is respectively 1-30, and preset apportioning cost is 10, by above-mentioned 30
After a attendance record terminal number rems divided by 10 respectively, it is known that the corresponding 3 attendance record terminals number of each remainder, due to remainder
It is the sequence number as each attendance record terminal, then each sequence number has corresponded to 3 attendance record terminal numbers), at this time due to sequence number
Number be greater than 1, will the corresponding history attendance data subset of sequence number corresponding attendance record terminal number institute by attendance record terminal number
Lexcographical order, be sequentially sent to number corresponding with sequence process (wherein lexcographical order is it can be appreciated that ASCII character sequence, such as
The attendance record terminal that attendance record terminal number is 1,11 and 21, respective attendance record terminal number is except Yuing 1 after 10, then according to attendance record terminal
Attendance record terminal is successively numbered corresponding history attendance data subset and is sent to and sorts by the sequencing that number is 1,11 and 21
Number corresponding process).If the number without sequence number is greater than 1, then it represents that current each process at most receives a history attendance number
According to subset, handled without multiple parallel multi-thread.By way of multithreading, data screening efficiency is effectively promoted.
In one embodiment, described to press the corresponding corresponding history attendance data subset of attendance record terminal number institute of sequence number
The lexcographical order of attendance record terminal number, be sequentially sent to the step of number corresponding process of sequence after, further includes:
Each attendance data of history attendance data subset corresponding working attendance time is obtained respectively by each attendance date,
Obtain data subset corresponding with each attendance date；
The corresponding working attendance of an attendance data is randomly selected in corresponding data subset of selected attendance date
Time is as initial cluster center；
According to preset minimum comprising points, obtain spacing between initial cluster center preset sweep radius it
Interior attendance data, to form initial clustering group；
Regard the working attendance time of attendance data each in initial clustering group as cluster centre, obtain in data subset with
The attendance data that the direct density of cluster centre is reachable, density is reachable or density is connected, with obtain with corresponding to the data subset
Multiple cluster groups；
It obtains the target that attendance data sum in multiple cluster groups corresponding to data subset is minimum value and clusters group, with
To the corresponding value set that peels off.
In the present embodiment, after process has received corresponding history attendance data subset, data prediction can be carried out,
Such as history attendance is filtered out by DBSCAN clustering method (DBSCAN clustering method is a kind of density-based algorithms)
(such as a certain employee's absence from duty is not checked card, then this attendance data generally peels off for abnormal point or outlier in data subset
Point).Wherein, each data is an attendance data in history attendance data subset, and each attendance data includes attendance
People's identity identification information (such as work number), current attendance date, working attendance time and next attendance time, generally respectively to working
Attendance time and next attendance time carry out outlier detection.For example, identifying the detailed process of outlier in the working attendance time
It is as follows:
1) each attendance data of history attendance data subset corresponding working attendance time is obtained respectively by the attendance date, obtain
Data subset corresponding with each attendance date；Also history attendance data subset will be taken to carry out according to the attendance date further thin
Point, each day data carry out outlier detection for corresponding subset of each attendance date later as a subset respectively；
2) the corresponding upper bancor of an attendance data is randomly selected in corresponding data subset of selected attendance date
The diligent time is as initial cluster center；For example, the working attendance time randomly selected is 8:25；
3) points are included according to preset minimum, obtains the spacing between initial cluster center in preset sweep radius
Within attendance data, to form initial clustering group；
4) it regard the working attendance time of attendance data each in initial clustering group as cluster centre, obtains in data subset
With the attendance data that the direct density of cluster centre is reachable, density is reachable or density is connected, with obtain with corresponding to the data subset
Multiple cluster groups；
In order to it is clearer understand DBSCAN cluster detailed process, below to DBSCAN cluster involved in define into
Row is introduced.
Eps indicates sweep radius；
MinPts indicates minimum comprising points；
Epsilon neighborhood, indicates centered on given object, the region within the scope of the sweep radius for giving object；
Kernel object, if indicating, object number included in the epsilon neighborhood of given object includes more than or equal to minimum
Points, then the given object is referred to as kernel object；
Direct density is reachable, indicates for sample set D, if sample point q, in the epsilon neighborhood of p, and p is kernel object,
So object q is reachable from the direct density of object p；
Density is reachable, indicates for sample set D, give a string of sample point p1, p2 ..., pn, if p1=q and pn=
P, if object pi is reachable from the direct density of pi-1, then object q is reachable from object p density；
Density is connected, and indicates that there are the point o in sample set D, if object o to object p and object q are that density can
It reaches, then p with q density is connected.
The principle generally to be occupied the minority according to outlier, can choose attendance data sum in multiple cluster groups is minimum value
Target clusters group, to obtain the corresponding value set that peels off.Completing the number to each each attendance data of history attendance data subset
After Data preprocess, suspicious data further can be obtained according to data screening strategy.
In one embodiment, after step S110 further include:
If there is the subdatasheet of attendance record terminal not to be uploaded to server, request of data for obtaining data is sent to correspondence
Attendance record terminal；
If receiving the attendance record terminal of the request of data not sent corresponding subdatasheet in pre-set time threshold
To server, corresponding attendance record terminal number will be filled in pre-stored notification information template to obtain abnormal notification information；
The abnormal notification information is sent to receiving end corresponding with attendance record terminal number.
In the present embodiment, after server has received the subdatasheet that each attendance record terminal uploads, in order to ensure each
It is uploaded to server with the subdatasheet of the attendance record terminal of server communication connection, server is needed periodically to have received attendance record terminal
After the subdatasheet of upload, multiple received subdatasheets are carried out with the wheel continuous query of table name, to judge whether there is attendance
The subdatasheet of terminal is not uploaded to server.
For example, all attendance record terminal 1- attendance record terminals 30 being connect with server known to server, in multiple attendance record terminals
After uploading corresponding subdatasheet, server summarizes the table name of received subdatasheet, has been uploaded number
According to terminal list.Since the terminal including all equipment unique identifiers connecting with server has been stored in server in advance
Total list will upload data terminal list at this time and be compared with the total list of terminal, obtain difference value you can learn that whether having
The subdatasheet of attendance record terminal is not uploaded to server.If such as difference value be null value when indicate uploaded data terminal list with
The total list of terminal is identical, and all attendance record terminals with server connection have uploaded corresponding subdatasheet；If difference value is non-
Null value then obtains attendance record terminal corresponding to the corresponding equipment unique identifier of difference value.At this point, server is sent for obtaining
The request of data of data is to corresponding attendance record terminal；If receiving the attendance record terminal of request of data in pre-set time threshold
Not sent corresponding subdatasheet will fill corresponding attendance record terminal number to server in pre-stored notification information template
To obtain abnormal notification information；The abnormal notification information is sent to receiving end corresponding with attendance record terminal number.By upper
Advice method is stated, energy effective monitoring is uploaded the attendance record terminal of subdatasheet not in time, transported with the equipment for notifying attendance record terminal in time
The data upload function failure of the attendance record terminal is overhauled in time dimension side, it is ensured that the normal transmission of data.
S120, according to pre-set data screening strategy from the history attendance data set each history attendance data
Subset obtains corresponding target data, to obtain target data subset corresponding with each history attendance data subset.
In one embodiment, as shown in figure 4, step S120 includes:
S121, in each history attendance data subset obtain attendance data between adjacent frequency of occurrence exceed the preset frequency
The attendance subsequence of threshold value, using as attendance subsequence set corresponding with each history attendance data subset；
If being examined included by each attendance subsequence in S122, the corresponding attendance subsequence set of each history attendance data subset
Attendance time interval between diligent data is in preset time interval section, using corresponding attendance subsequence as attendance
The corresponding target data subset of arrangement set.
It in the present embodiment,, can in order to improve data screening efficiency after server obtains history attendance data set
The corresponding history attendance data subset in attendance end each in the history attendance data set is distributed to a correspondence respectively
Process carry out data screening, be pre-configured with data screening strategy in each process, completed data sieve when each process is corresponding
After choosing, carries out concentrating in the storage region of server and summarize.Wherein, pre-set data screening strategy is that each history is examined
Diligent data subset corresponds to attendance time interval there are each attendance data in similar attendance subsequence and the attendance subsequence and exists
In 2-10 seconds.
For example, the attendance recorder 11 at 1 layer of entrance 1 of the office space of certain enterprise A, in 4 days-December 8 December in 2017
In five working days in this week in corresponding history attendance data subset, and it can per diem be divided into multiple sublists, if after dividing
Multiple sublists in the adjacent number of employee A1 and A2 occur be 5 times, and attendance time of employee A1 and A2 is spaced in 2-
In 10 seconds, then it represents that be likely to be that employee A1 helps employee A2 generation to check card or employee A2 helps employee A1 generation checks card, employee A1 at this time
Attendance data corresponding with A2 is then that target data is screened out.
S130, it obtains and concentrates the attendance time point of each target data corresponding monitor video, root with the target data
Target user present in monitor video is obtained according to recognition of face.
In the present embodiment, it is concentrated to further verify target data corresponding with each history attendance data subset
Each target data can transfer the attendance time point corresponding prison of each target data with the presence or absence of the case where really generation checks card at this time
Video is controlled, according to target user present in recognition of face acquisition monitor video.If user and target data in monitor video
Corresponding user is identical, and it is on and off duty together to indicate that the two users only often make an appointment, and excludes the suspicion that band is checked card；If monitoring view
User user corresponding with target data in frequency is not identical, and (number of users usually in monitor video is less than target data pair
The user's number answered, for example, target data be employee A1 and A2 data of checking card, and only occur in monitor video employee A1 or
A2), then employee A1 or A2 has occurred for situation of checking card at this time.
Due to directly can not directly carrying out recognition of face to monitor video, need monitor video carrying out video decomposition at this time,
Obtain corresponding multiframe user monitoring picture.The use of target present in monitor video is obtained by multiframe user monitoring picture
Family.
In one embodiment, as shown in figure 5, step S130 includes:
S131, by the monitor video carry out video decomposition, obtain corresponding multiframe user monitoring picture；
S132, gray correction and noise filtering are successively carried out to the user monitoring picture, picture after being pre-processed；
S133, picture feature vector corresponding with picture after the pretreatment is obtained by convolutional neural networks model；
S134, the picture feature vector is compared with feature templates stored in face database, judges people
It is identical with the presence or absence of picture feature vector corresponding with picture after the pretreatment in stored feature templates in face database
Feature templates；
If there is picture corresponding with picture after the pretreatment in S135, face database in stored feature templates
The identical feature templates of feature vector, obtain corresponding user identification information, to obtain target user's set.
In the present embodiment, if being not present and picture after the pretreatment in stored feature templates in face database
The identical feature templates of corresponding picture feature vector, then it represents that the feature templates that user is also lacked in face database need
Immediately the feature templates in face database are updated.Image preprocessing for face be based on Face datection as a result,
Processing is carried out to image and finally serves the process of feature extraction.The original image that server obtains is due to by various conditions
Limitation and random disturbances, tend not to directly use, it is necessary to image procossing early stage to it carry out gray correction, make an uproar
The image preprocessings such as sound filtering.For facial image, preprocessing process mainly includes the light compensation of facial image, ash
Spend transformation, histogram equalization, normalization, geometric correction, filtering and sharpening etc..
When obtaining the feature vector of picture, picture element matrix corresponding with picture after the pretreatment of each frame is first obtained, then
Using the corresponding picture element matrix of picture after the pretreatment of each frame as the input of input layer in convolutional neural networks model, obtain multiple
Characteristic pattern is inputted pond layer later, obtains one-dimensional row vector corresponding to the corresponding maximum value of each characteristic pattern, finally by characteristic pattern
One-dimensional row vector corresponding to the corresponding maximum value of each characteristic pattern is input to full articulamentum, obtains scheming after pre-processing with each frame
The corresponding picture feature vector of piece.
Since the face picture for storing the magnanimity acquired in feature templates stored in face database is corresponding
Feature vector namely everyone face correspond to unique feature vector, and the feature templates for having these magnanimity are data
Behind basis, it may be used to determine the corresponding one or more people of picture after pretreatment, to realize recognition of face.
Finally, obtained user identification information can be the identification card number of user, due to the identity of each citizen
Card number is uniquely, to can be used as its unique identifier.When completing the identification to the target user in the presence of monitor video
Afterwards, i.e., concentrate whether each target data comprehensive descision has generation in combination with the target user and the target data that identify
The case where checking card exists.
If S140, having the user corresponding with each target data of target user present in monitoring data not identical, will correspond to
Target data carry out suspicious data mark.
In the present embodiment, the user corresponding with target data of the user in monitor video is not identical, usually monitoring view
Number of users in frequency is less than the corresponding user's number of target data, such as target data is the data of checking card of employee A1 and A2,
And only occurring employee A1 or A2 in monitor video, corresponding target data, which is carried out suspicious data mark, at this time can be realized generation
It checks card the screening of user.
S150, the suspicious data respectively with suspicious data mark is stored to pre-set tables of data, obtains abnormal examine
Diligent tables of data.
In the present embodiment, it completes when in conjunction with monitor video to all target datas concentration attendance data authenticity
It is if having obtained suspicious data set corresponding with each target data subset, each target data subset is right respectively after verification
The suspicious data set answered will be stored and be summarized in pre-set tables of data, and abnormal attendance data table is obtained.At this time will
Abnormal attendance data table by server be sent to pre-set data receiver (usually administrative personnel use intelligence eventually
End, such as tablet computer), data receiver can be facilitated to check suspicious attendance data.
The method achieve accurately excavating the target data for meeting data screening strategy from attendance data set, and tie
It closes face recognition technology and further determines that the suspicious data in target data, to realize to the effective monitoring for situation of checking card.
The embodiment of the present invention also provides a kind of screening plant of abnormal attendance data, the screening plant of the exception attendance data
For executing any embodiment of the screening technique of aforementioned abnormal attendance data.Specifically, referring to Fig. 6, Fig. 6 is of the invention real
The schematic block diagram of the screening plant of the abnormal attendance data of example offer is provided.The screening plant 100 of the exception attendance data can be with
It is configured in server.
As shown in fig. 6, the screening plant 100 of abnormal attendance data includes data screening unit 110, target data acquisition list
Member 120, target user's acquiring unit 130, suspicious mark unit 140 and tables of data acquiring unit 150.
Data screening unit 110, if being equal to for the difference of present system time and the time of upper data screening time pre-
The timing cycle being first arranged, positioning obtain attendance data set, according to by present system time in the attendance data set
The data screening condition of generation obtains corresponding history attendance data set.
It, can be by pre- when in the present embodiment, in order to periodically carry out the analysis of suspicious data to history attendance data
If timing cycle the time is corresponded to according to the data screening conditional filtering that automatically generates from the attendance data table of each attendance record terminal
The history attendance data of section, to obtain history attendance data set.
For example, the office space of certain enterprise A is divided into M layers, each layer of N number of inlet is each provided with 1 attendance record terminal, on
It states each attendance record terminal of M*N attendance record terminal and is provided with only one attendance record terminal number, the attendance that each attendance record terminal obtains
Data have subdatasheet corresponding with the attendance record terminal to be stored in the server.After above-mentioned setting, user (such as look forward to
Industry is responsible for the administrative personnel of attendance verification) the week-night 9:00 in settable each week is in the corresponding subdatasheet of each attendance record terminal
Workaday history attendance data is (at this point, the evening of current week-night 9:00 and a upper Sunday in this week of middle screening
The difference of the time of 9:00 is 7 days, wherein being within 7 days pre-set timing cycle), it obtains history corresponding with each attendance record terminal and examines
Diligent data subset, to form history attendance data set.
In one embodiment, as shown in fig. 7, data screening unit 110 includes:
Attendance data set acquiring unit 111, for positioning the subdatasheet for the attendance record terminal connecting with server, by each
The corresponding subdatasheet of attendance record terminal forms attendance data set；
Screening conditions generation unit 112, for generating data screening condition according to present system time；
History attendance data subset acquiring unit 113, for according to the data screening condition in each subdatasheet into
Row data screening, to obtain the history attendance data subset corresponding with each attendance record terminal；
Data combination unit 114 is obtained for the corresponding history attendance data subset of each attendance record terminal to be combined
History attendance data set.
In the present embodiment, since the attendance record terminal attendance data set collected respectively connected with server can be corresponding
Corresponding subdatasheet is stored into the storage region of server.It, need to be by each attendance record terminal pair in order to obtain attendance data set
The subdatasheet answered, which is combined, to be obtained.Wherein, need each attendance whole to know the source of each subdatasheet in the server
It holds when sending stored subdatasheet, need to number that form equipment unique according to the device number and attendance record terminal of each attendance record terminal
Identification code carries out the name of table name with subdata table.For example, the device number of attendance record terminal 1 is ABCDEF, attendance record terminal is compiled
Number be 1, can successively by device number and attendance record terminal number concatenation, obtain equipment unique identifier.When server receives attendance
When subdatasheet transmitted by terminal 1, the subdatasheet is ordered with the equipment unique identifier ABCDEF1 of attendance record terminal 1
Name.
Later, data screening condition is automatically generated according to current system time and preset data screening period.Example
Such as, current system time is X1 month X2 day 21:00 in 2019, it is assumed that the same day is Sunday, at this time data screening generated
Condition is that the date intervals before current system time and between the date corresponding to current system time are less than 7
It.
After having obtained data screening condition, according to the data screening condition in the corresponding subdata of each attendance record terminal
Data screening is carried out in table, to obtain the history attendance data subset corresponding with each attendance record terminal, thus by each attendance record terminal
Corresponding history attendance data subset forms history attendance data set.In order to reduce in the corresponding subdatasheet of each attendance record terminal
The amount of storage of attendance data, evening at the end of month 11:30 of settable every month by the attendance data of current month in subdatasheet into
Row Data Migration stores the historical data sublist being correspondingly arranged into server or other databases with the attendance record terminal.Pass through
Aforesaid way, so that the attendance data in subdatasheet corresponding with each attendance record terminal is only current month in the server
Attendance data greatly reduces the data volume of subdatasheet, so that subsequent data screening process is more efficient.
In one embodiment, the screening plant 100 of abnormal attendance data further include:
Number acquiring unit, for obtaining the corresponding attendance record terminal number of each history attendance data subset；
Sequence acquiring unit, for numbering the corresponding attendance record terminal of each history attendance data subset divided by preset
Apportioning cost rems, to obtain sequence number corresponding with each attendance record terminal number；
Number judging unit, for judging whether the number of each sequence number is greater than 1；
Allocation unit, if for there is the number of sequence number to be greater than 1, the corresponding attendance record terminal number institute of sequence number is corresponding
History attendance data subset presses the lexcographical order of attendance record terminal number, is sequentially sent to and sequence number corresponding process.
It in the present embodiment,, can in order to improve data screening efficiency after server obtains history attendance data set
The corresponding history attendance data subset in attendance end each in the history attendance data set is distributed to a correspondence respectively
Process carry out data screening, in each process on be pre-configured with data screening strategy, complete number when each process end is corresponding
After obtaining target data subset according to screening, carried out in the storage region of server centrally stored.Wherein, in the server of multicore
In, multiple processes can be concurrently carried out to realize the concurrent processing of data processing.Moreover, including multiple threads in each process to control
Make the execution of corresponding process.By multithreading, data screening efficiency is effectively improved.
Such as assume to start 10 processes in server, and the history attendance data subset in history attendance data set
Total number be 30, can be assigned in each process at this time processing 3 history attendance data subsets data screening task (example
The attendance record terminal number for each attendance record terminal such as connecting with server is respectively 1-30, and preset apportioning cost is 10, by above-mentioned 30
After a attendance record terminal number rems divided by 10 respectively, it is known that the corresponding 3 attendance record terminals number of each remainder, due to remainder
It is the sequence number as each attendance record terminal, then each sequence number has corresponded to 3 attendance record terminal numbers), at this time due to sequence number
Number be greater than 1, will the corresponding history attendance data subset of sequence number corresponding attendance record terminal number institute by attendance record terminal number
Lexcographical order, be sequentially sent to number corresponding with sequence process (wherein lexcographical order is it can be appreciated that ASCII character sequence, such as
The attendance record terminal that attendance record terminal number is 1,11 and 21, respective attendance record terminal number is except Yuing 1 after 10, then according to attendance record terminal
Attendance record terminal is successively numbered corresponding history attendance data subset and is sent to and sorts by the sequencing that number is 1,11 and 21
Number corresponding process).If the number without sequence number is greater than 1, then it represents that current each process at most receives a history attendance number
According to subset, handled without multiple parallel multi-thread.By way of multithreading, data screening efficiency is effectively promoted.
In one embodiment, the screening plant 100 of the abnormal attendance data further include:
Data subset acquiring unit, for obtaining each attendance number of history attendance data subset respectively by each attendance date
According to the corresponding working attendance time, data subset corresponding with each attendance date is obtained；
Initial center setting unit is examined for randomly selecting one in corresponding data subset of selected attendance date
The diligent data corresponding working attendance time is as initial cluster center；
Initial clustering unit, for according to the preset minimum spacing comprising points, between acquisition and initial cluster center
Attendance data within preset sweep radius, to form initial clustering group；
Group's acquiring unit is clustered, for the working attendance time of attendance data each in initial clustering group to be used as in cluster
The heart, obtain in data subset with the attendance data that the direct density of cluster centre is reachable, density is reachable or density is connected, to obtain and
Multiple cluster groups corresponding to the data subset；
Peel off value set acquiring unit, is for obtaining attendance data sum in multiple cluster groups corresponding to data subset
The target of minimum value clusters group, to obtain the corresponding value set that peels off.
In the present embodiment, after process has received corresponding history attendance data subset, data prediction can be carried out,
Such as history attendance is filtered out by DBSCAN clustering method (DBSCAN clustering method is a kind of density-based algorithms)
(such as a certain employee's absence from duty is not checked card, then this attendance data generally peels off for abnormal point or outlier in data subset
Point).Wherein, each data is an attendance data in history attendance data subset, and each attendance data includes attendance
People's identity identification information (such as work number), current attendance date, working attendance time and next attendance time, generally respectively to working
Attendance time and next attendance time carry out outlier detection.The principle generally to be occupied the minority according to outlier can be chosen multiple
It clusters the target that attendance data sum in group is minimum value and clusters group, to obtain the corresponding value set that peels off.It is completing to each
After the data prediction of each attendance data of history attendance data subset, suspicious number further can be obtained according to data screening strategy
According to.
In one embodiment, the screening plant 100 of abnormal attendance data further include:
Request of data transmission unit, if sending for there is the subdatasheet of attendance record terminal not to be uploaded to server for obtaining
The request of data for evidence of fetching is to corresponding attendance record terminal；
Abnormal notification information generation unit, if the attendance record terminal for receiving request of data is in pre-set time threshold
Not sent corresponding subdatasheet will fill corresponding attendance record terminal in pre-stored notification information template to server in being worth
Number is to obtain abnormal notification information；
Abnormal notification information transmission unit, it is corresponding with attendance record terminal number for being sent to the abnormal notification information
Receiving end.
In the present embodiment, after server has received the subdatasheet that each attendance record terminal uploads, in order to ensure each
It is uploaded to server with the subdatasheet of the attendance record terminal of server communication connection, server is needed periodically to have received attendance record terminal
After the subdatasheet of upload, multiple received subdatasheets are carried out with the wheel continuous query of table name, to judge whether there is attendance
The subdatasheet of terminal is not uploaded to server.
For example, all attendance record terminal 1- attendance record terminals 30 being connect with server known to server, in multiple attendance record terminals
After uploading corresponding subdatasheet, server summarizes the table name of received subdatasheet, has been uploaded number
According to terminal list.Since the terminal including all equipment unique identifiers connecting with server has been stored in server in advance
Total list will upload data terminal list at this time and be compared with the total list of terminal, obtain difference value you can learn that whether having
The subdatasheet of attendance record terminal is not uploaded to server.If such as difference value be null value when indicate uploaded data terminal list with
The total list of terminal is identical, and all attendance record terminals with server connection have uploaded corresponding subdatasheet；If difference value is non-
Null value then obtains attendance record terminal corresponding to the corresponding equipment unique identifier of difference value.At this point, server is sent for obtaining
The request of data of data is to corresponding attendance record terminal；If receiving the attendance record terminal of request of data in pre-set time threshold
Not sent corresponding subdatasheet will fill corresponding attendance record terminal number to server in pre-stored notification information template
To obtain abnormal notification information；The abnormal notification information is sent to receiving end corresponding with attendance record terminal number.By upper
Advice method is stated, energy effective monitoring is uploaded the attendance record terminal of subdatasheet not in time, transported with the equipment for notifying attendance record terminal in time
The data upload function failure of the attendance record terminal is overhauled in time dimension side, it is ensured that the normal transmission of data.
Target data acquiring unit 120, for according to pre-set data screening strategy from the history attendance data
Each history attendance data subset obtains corresponding target data in set, to obtain mesh corresponding with each history attendance data subset
Mark data subset.
In one embodiment, as shown in figure 8, target data acquiring unit 120 includes:
Attendance subsequence acquiring unit 121 is obtaining adjacent appearance between attendance data in each history attendance data subset
The frequency exceeds the attendance subsequence of preset frequency threshold value, using as attendance subsequence corresponding with each history attendance data subset
Set；
If each in target data subset acquiring unit 122, the corresponding attendance subsequence set of each history attendance data subset
Attendance time interval between attendance data included by attendance subsequence is examined in preset time interval section by corresponding
Diligent subsequence is as the corresponding target data subset of attendance subsequence set.
It in the present embodiment,, can in order to improve data screening efficiency after server obtains history attendance data set
The corresponding history attendance data subset in attendance end each in the history attendance data set is distributed to a correspondence respectively
Process carry out data screening, be pre-configured with data screening strategy in each process, completed data sieve when each process is corresponding
After choosing, carries out concentrating in the storage region of server and summarize.Wherein, pre-set data screening strategy is that each history is examined
Diligent data subset corresponds to attendance time interval there are each attendance data in similar attendance subsequence and the attendance subsequence and exists
In 2-10 seconds.
For example, the attendance recorder 11 at 1 layer of entrance 1 of the office space of certain enterprise A, in 4 days-December 8 December in 2017
In five working days in this week in corresponding history attendance data subset, and it can per diem be divided into multiple sublists, if after dividing
Multiple sublists in the adjacent number of employee A1 and A2 occur be 5 times, and attendance time of employee A1 and A2 is spaced in 2-
In 10 seconds, then it represents that be likely to be that employee A1 helps employee A2 generation to check card or employee A2 helps employee A1 generation checks card, employee A1 at this time
Attendance data corresponding with A2 is then that target data is screened out.
Target user's acquiring unit 130, for obtaining the attendance time for concentrating each target data with the target data
The corresponding monitor video of point, according to target user present in recognition of face acquisition monitor video.
In the present embodiment, it is concentrated to further verify target data corresponding with each history attendance data subset
Each target data can transfer the attendance time point corresponding prison of each target data with the presence or absence of the case where really generation checks card at this time
Video is controlled, according to target user present in recognition of face acquisition monitor video.If user and target data in monitor video
Corresponding user is identical, and it is on and off duty together to indicate that the two users only often make an appointment, and excludes the suspicion that band is checked card；If monitoring view
User user corresponding with target data in frequency is not identical, and (number of users usually in monitor video is less than target data pair
The user's number answered, for example, target data be employee A1 and A2 data of checking card, and only occur in monitor video employee A1 or
A2), then employee A1 or A2 has occurred for situation of checking card at this time.
Due to directly can not directly carrying out recognition of face to monitor video, need monitor video carrying out video decomposition at this time,
Obtain corresponding multiframe user monitoring picture.The use of target present in monitor video is obtained by multiframe user monitoring picture
Family.
In one embodiment, as shown in figure 9, target user's acquiring unit 130 includes:
Video decomposition unit 131, for obtaining corresponding multiframe user by carrying out video decomposition to the monitor video
Monitor picture；
Pretreatment unit 132 obtains pre- for successively carrying out gray correction and noise filtering to the user monitoring picture
Picture after processing；
Feature vector acquiring unit 133, for being obtained and picture pair after the pretreatment by convolutional neural networks model
The picture feature vector answered；
Feature comparing unit 134 is used for stored feature templates in the picture feature vector and face database
It is compared, judges to whether there is figure corresponding with picture after the pretreatment in face database in stored feature templates
The identical feature templates of piece feature vector；
Target user gathers acquiring unit 135, if for existing and institute in stored feature templates in face database
The identical feature templates of the corresponding picture feature vector of picture after pre-processing are stated, corresponding user identification information is obtained, with
Obtain target user's set.
In the present embodiment, if being not present and picture after the pretreatment in stored feature templates in face database
The identical feature templates of corresponding picture feature vector, then it represents that the feature templates that user is also lacked in face database need
Immediately the feature templates in face database are updated.Image preprocessing for face be based on Face datection as a result,
Processing is carried out to image and finally serves the process of feature extraction.The original image that server obtains is due to by various conditions
Limitation and random disturbances, tend not to directly use, it is necessary to image procossing early stage to it carry out gray correction, make an uproar
The image preprocessings such as sound filtering.For facial image, preprocessing process mainly includes the light compensation of facial image, ash
Spend transformation, histogram equalization, normalization, geometric correction, filtering and sharpening etc..
When obtaining the feature vector of picture, picture element matrix corresponding with picture after the pretreatment of each frame is first obtained, then
Using the corresponding picture element matrix of picture after the pretreatment of each frame as the input of input layer in convolutional neural networks model, obtain multiple
Characteristic pattern is inputted pond layer later, obtains one-dimensional row vector corresponding to the corresponding maximum value of each characteristic pattern, finally by characteristic pattern
One-dimensional row vector corresponding to the corresponding maximum value of each characteristic pattern is input to full articulamentum, obtains scheming after pre-processing with each frame
The corresponding picture feature vector of piece.
Since the face picture for storing the magnanimity acquired in feature templates stored in face database is corresponding
Feature vector namely everyone face correspond to unique feature vector, and the feature templates for having these magnanimity are data
Behind basis, it may be used to determine the corresponding one or more people of picture after pretreatment, to realize recognition of face.
Finally, obtained user identification information can be the identification card number of user, due to the identity of each citizen
Card number is uniquely, to can be used as its unique identifier.When completing the identification to the target user in the presence of monitor video
Afterwards, i.e., concentrate whether each target data comprehensive descision has generation in combination with the target user and the target data that identify
The case where checking card exists.
Suspicious mark unit 140, if for there is the use corresponding with each target data of target user present in monitoring data
Family is not identical, and corresponding target data is carried out suspicious data mark.
In the present embodiment, the user corresponding with target data of the user in monitor video is not identical, usually monitoring view
Number of users in frequency is less than the corresponding user's number of target data, such as target data is the data of checking card of employee A1 and A2,
And only occurring employee A1 or A2 in monitor video, corresponding target data, which is carried out suspicious data mark, at this time can be realized generation
It checks card the screening of user.
Tables of data acquiring unit 150, for storing the suspicious data respectively with suspicious data mark to pre-set
Tables of data obtains abnormal attendance data table.
In the present embodiment, it completes when in conjunction with monitor video to all target datas concentration attendance data authenticity
It is if having obtained suspicious data set corresponding with each target data subset, each target data subset is right respectively after verification
The suspicious data set answered will be stored and be summarized in pre-set tables of data, and abnormal attendance data table is obtained.At this time will
Abnormal attendance data table by server be sent to pre-set data receiver (usually administrative personnel use intelligence eventually
End, such as tablet computer), data receiver can be facilitated to check suspicious attendance data.
The arrangement achieves accurately excavating the target data for meeting data screening strategy from attendance data set, and tie
It closes face recognition technology and further determines that the suspicious data in target data, to realize to the effective monitoring for situation of checking card.
The screening plant of above-mentioned exception attendance data can be implemented as the form of computer program, which can be with
It is run in computer equipment as shown in Figure 10.
Referring to Fig. 10, Figure 10 is the schematic block diagram of computer equipment provided in an embodiment of the present invention.The computer is set
Standby 500 be server, and server can be independent server, is also possible to the server cluster of multiple server compositions.
Refering to fig. 10, which includes processor 502, memory and the net connected by system bus 501
Network interface 505, wherein memory may include non-volatile memory medium 503 and built-in storage 504.
The non-volatile memory medium 503 can storage program area 5031 and computer program 5032.The computer program
5032 are performed, and processor 502 may make to execute the screening technique of abnormal attendance data.
The processor 502 supports the operation of entire computer equipment 500 for providing calculating and control ability.
The built-in storage 504 provides environment for the operation of the computer program 5032 in non-volatile memory medium 503, should
When computer program 5032 is executed by processor 502, processor 502 may make to execute the screening technique of abnormal attendance data.
The network interface 505 is for carrying out network communication, such as the transmission of offer data information.Those skilled in the art can
To understand, structure shown in Figure 10, only the block diagram of part-structure relevant to the present invention program, is not constituted to this hair
The restriction for the computer equipment 500 that bright scheme is applied thereon, specific computer equipment 500 may include than as shown in the figure
More or fewer components perhaps combine certain components or with different component layouts.
Wherein, the processor 502 is for running computer program 5032 stored in memory, to realize such as this hair
The screening technique for the abnormal attendance data that bright embodiment provides.
It will be understood by those skilled in the art that the embodiment of computer equipment shown in Figure 10 is not constituted to computer
The restriction of equipment specific composition, in other embodiments, computer equipment may include components more more or fewer than diagram, or
Person combines certain components or different component layouts.For example, in some embodiments, computer equipment can only include depositing
Reservoir and processor, in such embodiments, the structure and function of memory and processor are consistent with embodiment illustrated in fig. 10,
Details are not described herein.
It should be appreciated that in embodiments of the present invention, processor 502 can be central processing unit (Central
Processing Unit, CPU), which can also be other general processors, digital signal processor (Digital
Signal Processor, DSP), specific integrated circuit (Application Specific Integrated Circuit,
ASIC), ready-made programmable gate array (Field-Programmable GateArray, FPGA) or other programmable logic devices
Part, discrete gate or transistor logic, discrete hardware components etc..Wherein, general processor can be microprocessor or
The processor is also possible to any conventional processor etc..
Computer readable storage medium is provided in another embodiment of the invention.The computer readable storage medium can be with
For non-volatile computer readable storage medium.The computer-readable recording medium storage has computer program, wherein calculating
The screening technique such as abnormal attendance data provided in an embodiment of the present invention is realized when machine program is executed by processor.
It is apparent to those skilled in the art that for convenience of description and succinctly, foregoing description is set
The specific work process of standby, device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
Those of ordinary skill in the art may be aware that unit described in conjunction with the examples disclosed in the embodiments of the present disclosure and algorithm
Step can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware and software
Interchangeability generally describes each exemplary composition and step according to function in the above description.These functions are studied carefully
Unexpectedly the specific application and design constraint depending on technical solution are implemented in hardware or software.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
In several embodiments provided by the present invention, it should be understood that disclosed unit and method, it can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only logical function partition, there may be another division manner in actual implementation, can also will be with the same function
Unit set is at a unit, such as multiple units or components can be combined or can be integrated into another system or some
Feature can be ignored, or not execute.In addition, shown or discussed mutual coupling, direct-coupling or communication connection can
Be through some interfaces, the indirect coupling or communication connection of device or unit, be also possible to electricity, mechanical or other shapes
Formula connection.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.Some or all of unit therein can be selected to realize the embodiment of the present invention according to the actual needs
Purpose.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, is also possible to two or more units and is integrated in one unit.It is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in one storage medium.Based on this understanding, technical solution of the present invention is substantially in other words to existing
The all or part of part or the technical solution that technology contributes can be embodied in the form of software products, should
Computer software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be
Personal computer, server or network equipment etc.) execute all or part of step of each embodiment the method for the present invention
Suddenly.And storage medium above-mentioned include: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), magnetic disk or
The various media that can store program code such as person's CD.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can readily occur in various equivalent modifications or replace
It changes, these modifications or substitutions should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with right
It is required that protection scope subject to.
Claims (10)
1. a kind of screening technique of exception attendance data characterized by comprising
If the difference of the time of present system time and upper data screening time are equal to pre-set timing cycle, positioning is obtained
Attendance data set is obtained according to the data screening condition generated by present system time in the attendance data set and is corresponded to
History attendance data set；
According to pre-set data screening strategy, each history attendance data subset is obtained from the history attendance data set
Corresponding target data, to obtain target data subset corresponding with each history attendance data subset；
It obtains and concentrates the attendance time point of each target data corresponding monitor video with the target data, according to recognition of face
Obtain target user present in monitor video；
If having the user corresponding with each target data of target user present in monitoring data not identical, by corresponding target data
Carry out suspicious data mark；And
Suspicious data respectively with suspicious data mark is stored to pre-set tables of data, abnormal attendance data table is obtained.
2. the screening technique of exception attendance data according to claim 1, which is characterized in that if the present system time
And the difference of the time of upper data screening time is equal to pre-set timing cycle, and positioning obtains attendance data set, in institute
It states in attendance data set and corresponding history attendance data collection is obtained according to the data screening condition generated by present system time
It closes, comprising:
The subdatasheet for positioning the attendance record terminal connecting with server, forms attendance number by the corresponding subdatasheet of each attendance record terminal
According to set；
Data screening condition is generated according to present system time；
Data screening is carried out in each subdatasheet according to the data screening condition, it is corresponding with each attendance record terminal to obtain
History attendance data subset；
The corresponding history attendance data subset of each attendance record terminal is combined, history attendance data set is obtained.
3. the screening technique of exception attendance data according to claim 1, which is characterized in that if the present system time
And the difference of the time of upper data screening time is equal to pre-set timing cycle, and positioning obtains attendance data set, in institute
It states in attendance data set and corresponding history attendance data collection is obtained according to the data screening condition generated by present system time
After conjunction, further includes:
Obtain the corresponding attendance record terminal number of each history attendance data subset；
Each history attendance data subset corresponding attendance record terminal number is remmed divided by preset apportioning cost, with obtain with respectively
The corresponding sequence number of attendance record terminal number；
Judge whether the number of each sequence number is greater than 1；
If there is the number of sequence number to be greater than 1, by the corresponding corresponding history attendance data subset of attendance record terminal number institute of sequence number
By the lexcographical order that attendance record terminal is numbered, sequentially it is sent to and sequence number corresponding process.
4. the screening technique of exception attendance data according to claim 3, which is characterized in that described that sequence number is corresponding
The corresponding history attendance data subset of attendance record terminal number institute presses the lexcographical order of attendance record terminal number, is sequentially sent to and sorts number
After corresponding process, further includes:
Each attendance data of history attendance data subset corresponding working attendance time is obtained respectively by each attendance date, is obtained
Data subset corresponding with each attendance date；
An attendance data corresponding working attendance time is randomly selected in corresponding data subset of selected attendance date
As initial cluster center；
Include points according to preset minimum, obtains the spacing between initial cluster center within preset sweep radius
Attendance data, to form initial clustering group；
Regard the working attendance time of attendance data each in initial clustering group as cluster centre, obtain in data subset with cluster
The attendance data that the direct density in center is reachable, density is reachable or density is connected, with obtain with it is multiple corresponding to the data subset
Cluster group；
Obtain corresponding to data subset that attendance data sum is that the target of minimum value clusters group in multiple cluster groups, to obtain pair
The value set that peels off answered.
5. the screening technique of exception attendance data according to claim 1, which is characterized in that the positioning connects with server
The subdatasheet of the attendance record terminal connect, after forming attendance data set by the corresponding subdatasheet of each attendance record terminal, further includes:
If there is the subdatasheet of attendance record terminal not to be uploaded to server, request of data for obtaining data is sent to corresponding attendance
Terminal；
If receive the attendance record terminal of request of data in pre-set time threshold not sent corresponding subdatasheet to taking
Business device will fill corresponding attendance record terminal number to obtain abnormal notification information in pre-stored notification information template；
The abnormal notification information is sent to receiving end corresponding with attendance record terminal number.
6. the screening technique of exception attendance data according to claim 1, which is characterized in that described according to pre-set
Data screening strategy each history attendance data subset from the history attendance data set obtains corresponding target data, with
To target data subset corresponding with each history attendance data subset, comprising:
Adjacent frequency of occurrence examining beyond preset frequency threshold value between attendance data is being obtained in each history attendance data subset
Diligent subsequence, using as attendance subsequence set corresponding with each history attendance data subset；
If in the corresponding attendance subsequence set of each history attendance data subset attendance data included by each attendance subsequence it
Between attendance time interval in preset time interval section, using corresponding attendance subsequence as the attendance subsequence set
Corresponding target data subset.
7. the screening technique of exception attendance data according to claim 1, which is characterized in that described to be obtained according to recognition of face
Take target user present in monitor video, comprising:
By carrying out video decomposition to the monitor video, corresponding multiframe user monitoring picture is obtained；
Gray correction and noise filtering are successively carried out to the user monitoring picture, picture after being pre-processed；
Picture feature vector corresponding with picture after the pretreatment is obtained by convolutional neural networks model；
The picture feature vector is compared with feature templates stored in face database, is judged in face database
It whether there is the identical feature templates of picture feature vector corresponding with picture after the pretreatment in stored feature templates；
If there is picture feature vector corresponding with picture after the pretreatment in face database in stored feature templates
Identical feature templates obtain corresponding user identification information, to obtain target user's set.
8. a kind of screening plant of exception attendance data characterized by comprising
Data screening unit, if being equal to for the difference of present system time and the time of upper data screening time pre-set
Timing cycle, positioning obtain attendance data set, according to the number generated by present system time in the attendance data set
Corresponding history attendance data set is obtained according to screening conditions；
Target data acquiring unit, for each from the history attendance data set according to pre-set data screening strategy
History attendance data subset obtains corresponding target data, to obtain target data corresponding with each history attendance data subset
Collection；
Target user's acquiring unit concentrates the attendance time point of each target data corresponding for obtaining with the target data
Monitor video, according to target user present in recognition of face acquisition monitor video；
Suspicious mark unit, if for there is the user corresponding with each target data of target user present in monitoring data not phase
Together, corresponding target data is subjected to suspicious data mark；And
Tables of data acquiring unit, for storing the suspicious data respectively with suspicious data mark to pre-set tables of data,
Obtain abnormal attendance data table.
9. a kind of computer equipment, including memory, processor and it is stored on the memory and can be on the processor
The computer program of operation, which is characterized in that the processor realizes such as claim 1 to 7 when executing the computer program
Any one of described in abnormal attendance data screening technique.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has computer journey
Sequence, it is as described in any one of claim 1 to 7 different that the computer program when being executed by a processor executes the processor
The screening technique of normal attendance data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910533062.1A CN110399362A (en) | 2019-06-19 | 2019-06-19 | Screening technique, device, computer equipment and the storage medium of abnormal attendance data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910533062.1A CN110399362A (en) | 2019-06-19 | 2019-06-19 | Screening technique, device, computer equipment and the storage medium of abnormal attendance data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110399362A true CN110399362A (en) | 2019-11-01 |
Family
ID=68323289
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910533062.1A Pending CN110399362A (en) | 2019-06-19 | 2019-06-19 | Screening technique, device, computer equipment and the storage medium of abnormal attendance data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110399362A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111143350A (en) * | 2019-11-27 | 2020-05-12 | 深圳壹账通智能科技有限公司 | Enterprise data monitoring method and device, computer equipment and storage medium |
| CN111696222A (en) * | 2020-06-19 | 2020-09-22 | 打工快线网络科技(苏州)有限责任公司 | Intelligent attendance system based on comprehensive identification |
| CN112380217A (en) * | 2020-11-17 | 2021-02-19 | 安徽鸿程光电有限公司 | Data processing method, device, equipment and medium |
| CN112883073A (en) * | 2021-03-22 | 2021-06-01 | 北京同邦卓益科技有限公司 | Data screening method, device, equipment, readable storage medium and product |
| CN117078139A (en) * | 2023-10-16 | 2023-11-17 | 国家邮政局邮政业安全中心 | Cross-border express supervision method, system, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030167193A1 (en) * | 2002-01-08 | 2003-09-04 | Jones Wallace R. | Attendance monitoring system |
| CN107609330A (en) * | 2017-08-31 | 2018-01-19 | 中国人民解放军国防科技大学 | Access log mining-based internal threat abnormal behavior analysis method |
| CN107767477A (en) * | 2017-09-05 | 2018-03-06 | 深圳市盛路物联通讯技术有限公司 | A kind of information processing method and relevant device |
| CN108664375A (en) * | 2017-03-28 | 2018-10-16 | 瀚思安信（北京）软件技术有限公司 | Method for the abnormal behaviour for detecting computer network system user |
| CN109285234A (en) * | 2018-09-29 | 2019-01-29 | 中国平安人寿保险股份有限公司 | Human face identification work-attendance checking method, device, computer installation and storage medium |
| WO2019062620A1 (en) * | 2017-09-28 | 2019-04-04 | 钉钉控股（开曼）有限公司 | Attendance check method and apparatus, and attendance check device |
| CN109697595A (en) * | 2017-10-20 | 2019-04-30 | 杭州海康威视系统技术有限公司 | The recognition methods of cheating attendance data and device, storage medium, computer equipment |
-
2019
- 2019-06-19 CN CN201910533062.1A patent/CN110399362A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030167193A1 (en) * | 2002-01-08 | 2003-09-04 | Jones Wallace R. | Attendance monitoring system |
| CN108664375A (en) * | 2017-03-28 | 2018-10-16 | 瀚思安信（北京）软件技术有限公司 | Method for the abnormal behaviour for detecting computer network system user |
| CN107609330A (en) * | 2017-08-31 | 2018-01-19 | 中国人民解放军国防科技大学 | Access log mining-based internal threat abnormal behavior analysis method |
| CN107767477A (en) * | 2017-09-05 | 2018-03-06 | 深圳市盛路物联通讯技术有限公司 | A kind of information processing method and relevant device |
| WO2019062620A1 (en) * | 2017-09-28 | 2019-04-04 | 钉钉控股（开曼）有限公司 | Attendance check method and apparatus, and attendance check device |
| CN109697595A (en) * | 2017-10-20 | 2019-04-30 | 杭州海康威视系统技术有限公司 | The recognition methods of cheating attendance data and device, storage medium, computer equipment |
| CN109285234A (en) * | 2018-09-29 | 2019-01-29 | 中国平安人寿保险股份有限公司 | Human face identification work-attendance checking method, device, computer installation and storage medium |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111143350A (en) * | 2019-11-27 | 2020-05-12 | 深圳壹账通智能科技有限公司 | Enterprise data monitoring method and device, computer equipment and storage medium |
| CN111696222A (en) * | 2020-06-19 | 2020-09-22 | 打工快线网络科技(苏州)有限责任公司 | Intelligent attendance system based on comprehensive identification |
| CN112380217A (en) * | 2020-11-17 | 2021-02-19 | 安徽鸿程光电有限公司 | Data processing method, device, equipment and medium |
| CN112380217B (en) * | 2020-11-17 | 2024-04-12 | 安徽鸿程光电有限公司 | Data processing method, device, equipment and medium |
| CN112883073A (en) * | 2021-03-22 | 2021-06-01 | 北京同邦卓益科技有限公司 | Data screening method, device, equipment, readable storage medium and product |
| CN112883073B (en) * | 2021-03-22 | 2024-04-05 | 北京同邦卓益科技有限公司 | Data screening method, device, equipment, readable storage medium and product |
| CN117078139A (en) * | 2023-10-16 | 2023-11-17 | 国家邮政局邮政业安全中心 | Cross-border express supervision method, system, electronic equipment and storage medium |
| CN117078139B (en) * | 2023-10-16 | 2024-02-09 | 国家邮政局邮政业安全中心 | Cross-border express supervision method, system, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110399362A (en) | Screening technique, device, computer equipment and the storage medium of abnormal attendance data | |
| CN110309706A (en) | Face critical point detection method, apparatus, computer equipment and storage medium | |
| CN110096410A (en) | Alarm information processing method, system, computer installation and readable storage medium storing program for executing | |
| US10885461B2 (en) | Unsupervised method for classifying seasonal patterns | |
| CN108875522A (en) | Face cluster methods, devices and systems and storage medium | |
| CN108353149A (en) | CCTV sorts monitoring system CCTV and sorts monitoring management server and management method automatically automatically | |
| US20170249562A1 (en) | Supervised method for classifying seasonal patterns | |
| CN103363751B (en) | Refrigerator and inventory management method thereof | |
| US11496493B2 (en) | Dynamic transaction graph analysis | |
| CN108597605A (en) | A kind of life big data acquisition of personal health and analysis system | |
| US11169865B2 (en) | Anomalous account detection from transaction data | |
| CN111652280A (en) | Behavior-based target object data analysis method and device and storage medium | |
| CN105208325A (en) | Territorial resource monitoring and early warning method based on image fixed-point snapshot and comparative analysis | |
| CN105892994B (en) | A kind of mobile robot mission planning is with performing abnormal conditions processing method and processing device | |
| CN110471945A (en) | Processing method, system, computer equipment and the storage medium of alive data | |
| CN109033165A (en) | A kind of method for exhibiting data, computer readable storage medium and terminal device | |
| CN107203464A (en) | The localization method and device of traffic issues | |
| CN103336800B (en) | The method of the fingerprint storage comparison that Behavior-based control is analyzed | |
| CN114880312A (en) | Flexibly-set application system service data auditing method | |
| CN113342939B (en) | Data quality monitoring method and device and related equipment | |
| CN110164541A (en) | Working condition in the Medical Devices period determines method and system | |
| CN114118832A (en) | Bank scheduling method and system based on historical data prediction | |
| CN109686429A (en) | Physician visits period recommended method and device | |
| CN116308679A (en) | Supply chain abnormal order processing method, device, equipment and storage medium | |
| CN109801394A (en) | A kind of staff's Work attendance method and device, electronic equipment and readable storage medium storing program for executing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Xu Fu Inventor before: Li Rimei |
|
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |