CN102880781A - On-line examination intelligent monitoring system - Google Patents
On-line examination intelligent monitoring system Download PDFInfo
- Publication number
- CN102880781A CN102880781A CN2012102015341A CN201210201534A CN102880781A CN 102880781 A CN102880781 A CN 102880781A CN 2012102015341 A CN2012102015341 A CN 2012102015341A CN 201210201534 A CN201210201534 A CN 201210201534A CN 102880781 A CN102880781 A CN 102880781A
- Authority
- CN
- China
- Prior art keywords
- data
- examinee
- examination
- station
- sample
- 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.)
- Granted
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an on-line examination intelligent monitoring system. The on-line examination intelligent monitoring system comprises a central station, one or more examination stations which can communicate with the central station, and an examinee supervisory data processing module which is positioned in the central station or each examination station, wherein the central station comprises a data storage device and a data processor; the data processor comprises a biometrical data comparison module which is used for comparing biometrical data of an examinee with stored and verified biometrical data; each examination station comprises a data processor, a biometrical measuring device, an examinee supervisory data recording device and a data storage device; the data processor also comprises a process monitoring module which is used for monitoring and managing the process of the data processor; and the examinee supervisory data processing module judges whether the examinee has an abnormal examination behavior. By adoption of the on-line examination intelligent monitoring system, the examinee identity verification, examination paper issuing, examination room supervision and examination system monitoring processes are automated, and reliable and special examination environment is provided, so a reliable examination can be managed with minimum cost.
Description
Technical field
The present invention relates to a kind of online testing supervisory system, the particularly a kind of online testing intelligent monitor system that can realize intelligent monitoring and unmanned invigilator, and a kind of method of using this system to realize the intelligence invigilator.
Background technology
In recent years, along with the development of computing machine and internet, be developed based on the online testing system of computing machine and Internet technology, such as in the examinations such as large-scale GRE, GMAT, having obtained applying.The online testing system generally includes a testing server, and one or more exam station, and examination paper sends to exam station by network from server, and exam station is collected candidate's reply data, and sends it back testing server.When carrying out such online testing, particularly very strict to the examination hall requirement of discipline in examination, when perhaps examination result is very high for reliability requirement, need cost plenty of time and energy to guarantee the integrality of taking an examination.At first, the examinee must register, and guarantees titular people's enroll oneself for examination.Secondly, need to guarantee that the talent who registers is allowed to take an examination.In the examination process, need to be equipped with the professional and to supervise examination and do not occur to practise fraud guaranteeing.And, very important aspect is to guarantee the safety of examination problem information on the computing machine and computer run environment in the online testing, to guarantee that the candidate can not utilize the machine cheating of examination, perhaps exam information can be not stolen, reveal, by unauthorized access and be modified.All these safety practices all need a large amount of funds and manpower.
Both at home and abroad online testing being invigilated at present mainly is the mode of taking to concentrate machine room, artificial invigilator.This mode need to be prepared special-purpose examination hall, and adopts traditional artificial invigilator's mode.Compare with traditional standard papery examination, this online testing mode is just being made improvement aspect paper generation and the collection, is still applying mechanically traditional method fully aspect invigilator's mode.The increase that part online testing system is tentative video monitoring function.U.S. Prometric (Prometric) examination company is exactly maximum in the world computerize education and the company of examination authentication service, computerize examination technology and administrative standard have been started, the machine test system that is used for the examinations such as GRE and TOFEL, just has the examination hall video monitoring function, but this technology has just realized the videograph of examination surroundings, can not realize the synchronization monitoring of and computing machine individual for each examination, in addition, this supervisory system also needs a large amount of manpowers to participate in analyzing video information, can not realize the automatic analysis to the magnanimity video information, prediction and utilization.The watch-dog of simultaneously this Technology Need special use, equipment price is expensive, and installing, debug and safeguarding needs the professional person to carry out, high cost, very flexible.
In addition, very important aspect is to guarantee the safety of examination problem information on the computing machine and computer run environment in the online testing, guaranteeing that the examinee can't utilize local computer cheating, and exam information can be not stolen, reveal, by unauthorized access and be modified.The way that present online testing system adopts is to prepare the computer examination environment of " totally " for examination.This mode need to be prepared special-purpose device for examining, concentrates before examination and carries out system's refitting and Software deployment, and workload is large, takes time and effort, and dirigibility is looked into, and can not be applied to the examinee and use the situation that computer takes an exam of providing for oneself.
Summary of the invention
The object of the invention is to develop a kind of intelligent monitor system for online testing, compile necessary software and hardware so that complete unattended intelligence invigilator's remote examination hall to be provided.
Another object of the present invention is to make whole examination process automation, thereby makes can automatically take an exam authentication and finish examination of examinee, and without any need for personnel at the scene.
Another object of the present invention is to provide a kind of supervisory system of the computer run environment that uses for taking an examination, can be used for common computing machine, so that the application program operation of only having system to allow on the computing machine, prevent that the examinee from using the computing machine cheating, perhaps revise, copy the exam information in the computing machine, thereby need not prepare special device for examining for examination, even the computer that examination is provided for oneself the candidate carries out.
The objective of the invention is to realize by following basic technical scheme:
The invention provides a kind of online testing intelligent monitor system, comprise a central station and the one or more exam stations that can communicate by letter with central station;
Central station comprises: data storage device, and store examination problem data, examination reply data, the biometric data of examining and unusually supervise sample data; Data processor, exercisable being connected on the memory storage can electronization send the examination problem data to exam station and from exam station reception examination reply data, can also receive biometric data and examinee's monitoring data from exam station; Data processor comprises the biometric data comparison module, is used for comparison examinee's biometric data and biometric data storage, that examine;
Exam station comprises: data processor, can communicate by letter with central station, and receive the examination problem data and be shown to the examinee from central station, receive examinee's examination reply data, biometric data and examinee's monitoring data and send to central station; Biometric measurement device is used for examinee's biometric data is input to processor; Examinee's monitoring data pen recorder is used for recording the examinee's monitoring data when taking an examination, and examinee's monitoring data is input to processor; The exercisable data processor that is connected to of data storage device is used for keeping in the examination process and begins data required and that produce in the examination process; Data processor also comprises the process monitoring module, is used for the process of data processor is carried out monitoring management;
In addition, system also comprises the examinee's monitoring data processing module that is positioned at central station or exam station, and examinee's monitoring data processing module is used for examinee's monitoring data and unusual supervision sample data are compared, and judges whether the examinee exists the behavior of unusual examination hall.
Beneficial effect
The present invention makes that examinee's identity verification, examination paper send, examination hall supervision and the robotization of examination system monitor procedure, and a reliable and special-purpose examination surroundings is provided, and when and where takes an exam to make the candidate of online testing can select easily.For the organization and management person of examination, the present invention has eliminated the needs to the field staff of back-up system, so that online testing need not depend on special-purpose examination equipment again, takes an examination reliably with minimum overhead management.
Description of drawings
Fig. 1 is system construction drawing according to an embodiment of the invention;
Fig. 2 is central station structural representation according to an embodiment of the invention;
Fig. 3 is exam station structural representation according to an embodiment of the invention;
Fig. 4 is system module structural drawing according to an embodiment of the invention;
Fig. 5 is system module structural drawing in accordance with another embodiment of the present invention;
Fig. 6 is the process flow diagram of according to an embodiment of the invention examination and supervision and management process.
Among the figure, 1 is central station, 2 is exam station, 10 is the central station data processor, 11 is the central station display, 12 is the central station input media, and 13 is the central station data storage device, and 14 is biometric data comparison module 14,15 is examinee's monitoring data processing module, 20 is the exam station data processor, and 21 is the exam station display, and 22 is the exam station input media, 23 is biometric measurement device, 24 is examinee's monitoring data pen recorder, and 25 is the exam station data storage device, and 26 is exam station process monitoring module.
Embodiment
Below in conjunction with accompanying drawing, specify preferred implementation of the present invention.
Fig. 1, Fig. 2, Fig. 3 are the structural drawing according to system of the present invention, the hardware of expression a system in accordance with the present invention, and this system is used for the secure examination of control and management robotization supervision.System comprises a central station 1 and one or more Test Centre.Test Centre is provided with Relay Server, and the configuration camera provides the examination process video record of whole Test Centre in the examination process.In each Test Centre, one or more exam stations 2 are set.
Central station 1 is a master server, comprise a data processor 10, data processor 10 has a display 11 and the input media 12 such as keyboard coupled, is used for allowing the mutual of keeper and system, and system is controlled, upgrades and manages.The a data memory storage 13 exercisable data processors 10 that are connected to are arranged, in data storage device 13, store examination problem data, examination reply data, the biometric data of examining and unusually supervise sample data.
Exam station 2 is a concrete examination equipment, comprise a data processor 20, can communicate by letter with central station, communication mode can be by modulator-demodular unit, telephone wire, ISDN connect, other proper data link of a kind of satellite link or certain.Data processor 20 has a display 21 and one coupled such as touch-screen, keyboard, paintbrush device or other input media 22, be used for allowing the mutual of examinee and system, the problem data of will taking an examination is shown to the examinee, and receives examinee's examination reply data.Data processor 20 is connected with a biometric measurement device 23, with the record such as the geometric configuration of candidate's fingerprint image, retinal images, voiceprint, hand, the biometric data candidate's photo digital picture, or other can identify individual biometric data.Data processor 20 also is connected with examinee's monitoring data pen recorder 24, is used for recording the examinee's monitoring data when taking an examination, and examinee's monitoring data is input to processor 20.In most preferred embodiment, monitoring data is a kind of audio/video record, and particularly the examinee inputs the record of data overall process during the examination process.The memory storage 25 exercisable data processors 20 that are connected to are used for keeping in the data that the examination process begins required data and produces in the examination process.
Fig. 4 is system module structural drawing according to an embodiment of the invention.Store examination problem data, examination reply data, the biometric data of examining in the data storage device 13 of central station 1 and unusually supervise sample data.Accordingly, data processor 10 can electronization send the examination problem data to exam station 2 and from exam station 2 reception examination reply datas, can also receive biometric data and examinee's monitoring data from exam station 2.And, data processor 10 also comprises biometric data comparison module 14 and examinee's monitoring data processing module 15, wherein biometric data comparison module 14 is used for comparison examinee's biometric data and biometric data storage, that examine, examinee's monitoring data processing module 15 is used for examinee's monitoring data of comparison examinee and the unusual supervision sample data of storage, and judges whether the examinee exists the behavior of unusual examination hall.
The data storage device 25 of exam station 2 is used for keeping in the examination process and begins the part examination problem data that required data for example receive from central station processor 10, and the examinee's monitoring data that produces in the data that produce in the examination process biometric data, examination reply data and the examination process that for example the examinee inputs.Accordingly, data processor 20 receives the examination problem data and is shown to the examinee from central station 1, receives examinee's examination reply data, biometric data and examinee's monitoring data and sends to central station 1.In addition, data processor 20 also comprises process monitoring module 26, is used for the process of data processor is carried out monitoring management, only has specific process just to allow operation in the examination stage.
Fig. 5 is system module structural drawing in accordance with another embodiment of the present invention.In the situation that a large amount of examinee's examinations, examinee's monitoring data of a plurality of exam stations is transferred to central station simultaneously may cause network congestion.Therefore, in the data storage device of exam station, store the unusual supervision sample data synchronous with central station before the examination beginning, and in exam station configuration examination monitoring data processing module, be used in the exam station unusual supervision sample data of examinee's monitoring data and storage relatively, and judge whether the examinee exists the behavior of unusual examination hall.Only in the situation that be judged as the behavior of unusual examination hall, exam station just uploads to central station with examinee's monitoring data.
In one embodiment, system is configured to comprise that the large machine room of a master server and a centralized configuration is as the examination hall.In the machine room each machine links to each other with server by netting twine.Owing to being special-purpose examination place and examination machine, therefore every examination machine can carry out pre-configuredly before beginning examination, machines configurations was become the computer examination environment of " totally ".Can several video cameras of concentrated setting in the examination hall, to obtain the videograph of examination overall process.This is the system architecture that present online testing is adopted usually.
In the present embodiment, every examination machine is connected with a biometric measurement device.When the examinee registers, need my biometric data of registration, as stay my information such as fingerprint, digital picture.In one embodiment, exam station also can be used as the logging station in when registration, and examinee's biometric measurement device that machine connects that gets through the examinations stays my biometric data through examining, and uploads to master server, and is stored in the storer of master server.In the test time that the examinee selects, the examinee begins before the examination, the biometric measurement device of examination machine by connecting, and record examinee's biometric data, and be transferred to master server.Master server is by the biometric data comparison module, with the examinee take an examination front input biometric data and reservation examine biometric data relatively, carry out authentication, take an examination in the situation that just permission is passed through in authentication.Further, in the process of examination, biometric measurement device is whenever extracted examinee's biometric data at regular intervals, compares with the biometric data of examining in the server.If the examinee's biometric data that extracts in the test period has greatly changed, the generation that the examinee impersonates phenomenon in the test period may appear.
As a kind of optional prioritization scheme, every examination machine is connected with a camera, and this camera is double biometric measurement device and the examinee's monitoring data pen recorder done simultaneously.When being used as for biometric measurement device, can before examination, record examinee's digital picture, with master server in the digital picture of examining reserved compare.When as examinee's monitoring data pen recorder, can in the examination process, record the take an examination video information of overall process of examinee.
In the present embodiment, after master server receives the examination supervision video data that exam station uploads, the examination hall that prestores by examinee's monitoring data processing module and master server is unusually supervised sample data and is compared, and judge whether the examinee exists cheating, for example leave the examination seat, perhaps used reference or electronic equipment.Further, examinee's monitoring data processing module is obtained examinee's facial image that camera is caught, and face posture is identified in the process of examination, judges whether to exist the situation of cheating from face posture, and for example the behavior of other people answer is stolen a glance in rotary head.In the situation that judge examinee's cheating, will unusually take an examination the supervision Video Data Storage in the storer of master server.As further optimization, master server also comprises examination hall abnormal behaviour update module, sets up the mechanism of a cover self study, carries out analytic learning for the cheating of new affirmation, and upgrades pre-stored unusual supervision sample data in the master server.
Under the situation of the device for examining of preparing in advance " totally " for examination, the examination surroundings software that is configured on the examination machine comprises the process monitoring software that operates on the examination machine, this software is memory-resident behind os starting, the monitor system process guarantees to only have specific process just to allow operation in the examination stage.
Further, in one embodiment, also configured the system action control module on the examination machine.This module is monitoring and is recording user's input such as keyboard, mouse action in the test period, and judges whether user's input is the illegal operation of systemic presupposition, if user's operation is then forbidden in illegal operation.For example, if the examinee inputs the keyboard combination of ALT+TAB, can triggering system the program operation of switching, can destroy the exclusivity of examination program, exist certain dangerous; If the examinee inputs the TSKILL order, this order meeting deletion system process is relatively more dangerous operation; If the user attempts closing the examination window, perhaps attempt at the swap data between software and any other application program of taking an examination, also be unallowed.For the operation of these danger, it is pre-defined for illegal operation, and when detecting the examinee and carried out these operations, system can warn or forbids according to harmful grade.)
Further, in one embodiment, the examination machine also is connected with a supervisory screen device.Along with the development of computer technology, the examinee might utilize the monitoring of the technological breakthrough process monitoring modules such as system vulnerability and virtual machine and system action control module.As optional invigilator's measure, can be for supervisory screen device of every examination machines configurations, to record in the test period examinee's on-screen data.This supervisory screen device can be one provides the in the test period camera of screen video record, or the on-screen data that obtains of the interface by operating system, perhaps for safer purpose, get around operating system, directly obtain display data on the screen from the video card data buffer.Direct access video memory data, according to the video memory data screen message that the active user shows of painting out, the height of can real realization grabbing screen data and display data on the screen is consistent, and is very effective for the screen deception that prevents the operating system aspect.
The data processor of master server or examination machine comprises and the corresponding screen analysis module of supervisory screen device, the on-screen data that examinee's on-screen data of obtaining should be occurred during with examination is compared, in the situation that be not the software of taking an examination such as examinee's screen display, judge examinee's cheating.As further optimization, the on-screen data that should occur when the screen analysis module does not need to obtain to take an examination in advance, but extract the current whole examinees' that take an examination simultaneously screen message, obtain the current on-screen data that should occur, and the examinee's on-screen data that differs greatly is analyzed.For example, if the interface of the software that all should occur on all examinees' the screen taking an examination, what occur on some examinee's screens is the interface of other application program, and then there are larger difference in this examinee's screen and other examinee's screens, can be extracted and analyze.
Be different among the embodiment of special-purpose examination hall and special-purpose device for examining at another, system is configured to comprise a master server and one or more non-special-purpose exam station, for example candidate's oneself computer.Exam station can pass through that modulator-demodular unit, telephone wire, ISDN connect, other proper data link connection of a kind of satellite link or certain is to master server.The examinee installed from master server down loading mounting software bag and in exam station before beginning examination.The software of installing in exam station comprises the support software of biometric measurement device and examinee's monitoring data pen recorder, also comprises process supervision module, system action control module, examinee's monitoring data processing module and the unusual supervision sample data synchronous with master server.After installing software, system at first reminds the examinee to connect corresponding biometric measurement device and examinee's monitoring data pen recorder, and carries out authentication by the input biometric data, begins examination in authentication by rear examinee.In the examination process, the software that is installed in exam station carries out short range monitoring and examinee's behavior monitoring to exam station, record examinee's monitoring data is also compared to examinee's monitoring data and unusual supervision sample data, when cheating appears in judgement, carry out the operation of warning examinee or termination examination according to behavior character, and corresponding examinee's monitoring data is uploaded to master server.If the examination machine is connected with the supervisory screen device, and is then corresponding, also the screen analysis module can be installed on the exam station, the supervisory screen data are processed, judge whether to occur cheating, and when cheating appears in judgement, corresponding supervisory screen data upload is arrived master server.
The present embodiment also provides a kind of compares examinee's monitoring data and unusual supervision sample data, judges whether it is the method for cheating by face posture, may further comprise the steps:
Step 1, preparation sample image, sample image is divided into positive sample and negative sample, namely is judged to be the image and the image that is judged to be non-front face of front face, generates sorter according to sample image;
Step 2, receive the examination monitor video, the interval gathers a width of cloth examinee camera and catches image from video at regular intervals, and the sorter that uses step 1 to obtain classifies, and whether image is caught in judgement is front face image;
Surpass certain hour if step 3 detects non-front face image continued presence, judge that then may there be cheating in the examinee, system for prompting the keeper note, perhaps the examinee taked the treatment measures such as warning, termination examination;
Wherein, the method according to sample image generation sorter is in the step 1:
One, samples pictures is designated as (x
1, y
1) ... (x
n, y
n), y
i=1 this sample of expression is the image that positive example namely is judged to be front face, y
i=0 this example of expression namely is judged to be the image of non-front face for negative example;
Two, all sample images are normalized to the image of normal size, and all samples are carried out gray processing;
Three, initialization sample weight:
W
T, iThe error weight that represents i sample in the t time circulation is during initialization, if i sample is negative example, order
M is the number of samples of negative example; If i sample is positive example, then order
L is the number of samples of positive example;
Four, the strong classifier of training system, concrete grammar is:
A. specify the number T of the Weak Classifier that comprises in the strong classifier, to t=1 ... T, following steps are carried out in circulation:
1) normalized weight:
T=1 wherein ... T, T is the number of times of training;
2) to each Haar feature f, train a Weak Classifier h (x, f, p, θ); Calculate the error in classification of the Weak Classifier of corresponding this feature; The Haar feature is exactly the feature that forms with two adjacent rectangles, one of them represents with white rectangle, one represents with black rectangle, the Haar feature templates comprises edge feature, linear feature, central feature and diagonal line feature, adularescent and two kinds of rectangles of black in each feature templates, feature templates can be placed on any placement and can convergent-divergent in the piece image subwindow, any convergent-divergent of any one form is put and is called a kind of feature, the eigenwert that defines this template be the white rectangle pixel and deduct the black rectangle pixel and, for gray level image, pixel and be each grey scale pixel value sum;
3) choose the best minimal error rate ε that namely has
tWeak Classifier h
t(x)=h (x, f
t, p
t, θ
t), f wherein
t, p
t, θ
tTo make ε
tValue for minimum;
4) adjust weight according to best Weak Classifier obtained in the previous step:
Wherein, if x
iCorrectly classified e
i=0, if x
iClassified mistakenly e
i=1,
B. the strong classifier that finally obtains is:
Wherein
Step 2) in, the method for training Weak Classifier and calculating weighting error rate is:
To each feature f, train a Weak Classifier h (x, f, p, θ)
Wherein f is feature, and θ is threshold value, and the direction of the p indication sign of inequality is exactly 1 and-1, and what be used for the judgement system appointment is to meet standard or meet standard less than threshold value greater than threshold value, and x represents one and detects subwindow, and f (x) represents the eigenwert of this feature templates;
To each feature f, train a Weak Classifier h (x, f, p, θ), be exactly the optimal threshold of determining f, so that this Weak Classifier h (x, f, p, θ) is minimum to the error in classification of all training samples;
The process of each feature being carried out the Weak Classifier training is:
(1) to each feature f, obtains the eigenwert of all training samples;
(2) eigenwert is sorted;
(3) to sorted each element:
(i) calculate all just weight and the T of sample
+
(ii) weight and the T of the whole negative samples of calculating
-
(iii) calculate this element front just weight and the S of sample
+
(iv) calculate weight and the S of negative sample before this element
-
(v) choose the eigenwert of currentElement
An eigenwert with its front
Between number as threshold value, and the error in classification of calculating this threshold value is:
e=min(S
++(T
--S
-)，S
-+(T
+-S
+))；
(4) all errors in classification relatively obtain making the threshold value of error in classification minimum, as the Weak Classifier for feature f.
Fig. 6 shows the method that the present invention carries out the online testing intelligent monitoring, may further comprise the steps:
(a) the storage of biometric data to of examining a central station place;
(b) unusual supervision sample data is stored into described central station;
(c) the examination problem data is stored into described central station;
(d) at remote exam station input examinee biometric data, to begin the examination process;
(e) described examinee's biometric data is sent to central station, and the biometric data that compares examinee's biometric data and examine, described examinee's biometric data examined thus;
(f) the examination problem data of central station storage can be obtained in exam station;
(g) store the examination reply data of replying described examination problem data and storing;
(h) in the examination process, the examinee's monitoring data the during examination of exam station record also is sent to central station, at central station examinee's monitoring data and unusual supervision sample data is compared, and judges whether the examinee exists the behavior of unusual examination hall; The unusual supervision sample data of central station storage can be obtained in exam station, and in exam station examinee's monitoring data and unusual supervision sample data are compared, and judge whether the examinee exists the behavior of unusual examination hall; If have the behavior of unusual examination hall, take corresponding measure;
(i) in the examination process, exam station is carried out monitoring management to the process of moving on the exam station, if there is illegal process, takes corresponding measure;
(j) finish the examination process.
In the embodiment of centralized machine room, when the examinee arrives exam station 2, require the examinee to be confirmed whether to take an examination, and begin the examination process.When the examinee confirms to prepare to begin to take an examination, examinee's monitoring data pen recorder of examination machine is started working, point out simultaneously the examinee to pass through biometric data measurement mechanism input biometric data, for example, for the still photo of taking the examinee requires the examinee facing to video camera, perhaps require the examinee that his hand or finger are put into suitable pen recorder.
If when measuring biometric data, invalid event is arranged, make so the examination process invalid, and stop examination.For example, invalid event may be to have occurred two people in the exam station camera, perhaps attempts illegally or the input biological data of deception.
If the process of input biometric data is effective, exam station uploads to central station with biometric data.Central station is examined biometric data with the examinee's biometric data that transmits with the examinee who prestores and is compared, if data are not mated, then stops examination, begins to take an examination otherwise the problem data of will take an examination is sent to exam station.
In the examination process, the examinee replys the problem that occurs on the display device.In this process, exam station continues record examinee's monitoring data and also uploads to central station, carries out simultaneously process monitoring and examinee's behavior control, and whether the supervision examinee has moved illegal process or illegal operation occurred, if having then stops taking an examination.Central station is processed the examinee's monitoring data that receives, and the feature of the cheating that prestores with system compares, and judges whether to exist cheating, also stops examination if exist.
The method that non-special-purpose exam station embodiment according to the present invention is carried out the online testing intelligent monitoring is: before beginning examination, the examinee is connected to central station and downloads and at examination machine operation exam software bag by modes such as http, ftp.In the installation process, software package can at the support software of examination machine deploy biometric measurement device and examinee's monitoring data pen recorder, also comprise process supervision module, system action control module, examinee's monitoring data processing module and the unusual supervision sample data synchronous with master server.After software package installed, system at first required the examinee to be confirmed whether to take an examination, and begins the examination process.When the examinee confirmed to prepare to begin to take an examination, system prompt connected biometric measurement device and examinee's monitoring data pen recorder, and the prompting examinee is by biometric data measurement mechanism input biometric data.If the process of input biometric data is effective, exam station uploads to central station with biometric data.Central station is examined biometric data with the examinee's biometric data that transmits with the examinee who prestores and is compared, if data are not mated, then stops examination, begins to take an examination otherwise the problem data of will take an examination is sent to exam station.In the examination process, the examinee replys the problem that occurs on the display device.In this process, exam station continues record examinee's monitoring data and the feature of the cheating that prestores with system compares, and carries out simultaneously process monitoring and examinee's behavior control, and whether the supervision examinee has moved illegal process or illegal operation occurred.If exam station is judged the user and had cheating, then stop examination, and be that the system action data upload is to central station with corresponding examinee's monitoring data or illegal process.
In one embodiment, for each exam station connects a supervisory screen device, and dispose corresponding screen analysis module in exam station.In the examination process, exam station record examinee screen, and the on-screen data that examinee's on-screen data of obtaining should be occurred during with examination compares, and judges whether to occur invalid event.This comparison also can be carried out between the current whole examinees' that take an examination simultaneously on-screen data, extracts the examinee's on-screen data that differs greatly and analyzes.
The present invention is not limited only to above embodiment, everyly utilizes mentality of designing of the present invention, does the design of some simple change, all should count within protection scope of the present invention.
Claims (10)
1. an online testing intelligent monitor system comprises a central station (1) and the one or more exam stations (2) that can communicate by letter with central station, it is characterized in that:
Central station comprises: data storage device (13), and store examination problem data, examination reply data, the biometric data of examining and unusually supervise sample data; Data processor (10), exercisable being connected on the memory storage can electronization send the examination problem data to exam station and from exam station reception examination reply data, can also receive biometric data and examinee's monitoring data from exam station; Data processor comprises biometric data comparison module (14), is used for comparison examinee's biometric data and biometric data storage, that examine;
Exam station comprises: data processor (20), can communicate by letter with central station, and receive the examination problem data and be shown to the examinee from central station, receive examinee's examination reply data, biometric data and examinee's monitoring data and send to central station; Biometric measurement device (23) is used for examinee's biometric data is input to processor; Examinee's monitoring data pen recorder (24) is used for recording the examinee's monitoring data when taking an examination, and examinee's monitoring data is input to processor; The exercisable data processor that is connected to of data storage device (25) is used for keeping in the examination process and begins data required and that produce in the examination process; Data processor also comprises process monitoring module (26), is used for the process of data processor is carried out monitoring management;
In addition, system also comprises the examinee's monitoring data processing module that is positioned at central station or exam station, and examinee's monitoring data processing module is used for examinee's monitoring data and unusual supervision sample data are compared, and judges whether the examinee exists the behavior of unusual examination hall.
2. a kind of online testing intelligent monitor system according to claim 1, it is characterized in that, each exam station is connected with a camera, and this camera is double biometric measurement device (23) and the examinee's monitoring data pen recorder (24) of doing this exam station simultaneously.
3. a kind of online testing intelligent monitor system according to claim 1 and 2, it is characterized in that, in the process of examination, biometric measurement device (23) is whenever extracted examinee's biometric data at regular intervals, compares with the biometric data of examining of central station.
4. a kind of online testing intelligent monitor system according to claim 1 and 2, it is characterized in that, exam station also comprises the system action control module, this module is in the test period supervision and recording user input, and whether the input of judging the user be the illegal operation of systemic presupposition, if user's operation is then forbidden in illegal operation.
5. a kind of online testing intelligent monitor system according to claim 1 and 2 is characterized in that, exam station also comprises a supervisory screen device, to record in the test period examinee's on-screen data.
6. a kind of online testing intelligent monitor system according to claim 5, it is characterized in that, this supervisory screen device is one provides the in the test period camera of screen video record, or the on-screen data that obtains of the interface by operating system, perhaps be directly from the display data on the screen of video card data buffer acquisition.
7. a kind of online testing intelligent monitor system according to claim 5, it is characterized in that, central station or exam station also comprise and the corresponding screen analysis module of supervisory screen device, the on-screen data that examinee's on-screen data of obtaining should be occurred during with examination is compared, and judges examinee's cheating.
8. a kind of online testing intelligent monitor system according to claim 7, it is characterized in that, the on-screen data that should occur when the screen analysis module does not need to obtain to take an examination in advance, but extract the current whole examinees' that take an examination simultaneously screen message, obtain the current on-screen data that should occur, and the examinee's on-screen data that differs greatly is analyzed.
9. a kind of online testing intelligent monitor system according to claim 1 and 2, it is characterized in that, the software of installing on the exam station, by the examinee begin the examination before, install from central station down loading mounting software bag and in exam station, described software comprises the support software of biometric measurement device and examinee's monitoring data pen recorder, also comprises process supervision module, system action control module, examinee's monitoring data processing module and the unusual supervision sample data synchronous with master server.
10. a kind of online testing intelligent monitor system according to claim 1 and 2, it is characterized in that, examinee's monitoring data processing module is in the process of examination, obtain examinee's facial image that camera is caught, and face posture identified, judge whether to exist the situation of cheating from face posture, concrete grammar is:
Step 1, preparation sample image, sample image is divided into positive sample and negative sample, namely is judged to be the image and the image that is judged to be non-front face of front face, generates sorter according to sample image;
Step 2, receive the examination monitor video, the interval gathers a width of cloth examinee camera and catches image from video at regular intervals, and the sorter that uses step 1 to obtain classifies, and whether image is caught in judgement is front face image;
Surpass certain hour if step 3 detects non-front face image continued presence, judge that then may there be cheating in the examinee, system for prompting the keeper note, perhaps the examinee taked the treatment measures such as warning, termination examination;
Wherein, the method according to sample image generation sorter is in the step 1:
One, samples pictures is designated as (x
1, y
1) ... (x
n, y
n), y
i=1 this sample of expression is the image that positive example namely is judged to be front face, y
i=0 this example of expression namely is judged to be the image of non-front face for negative example;
Two, all sample images are normalized to the image of normal size, and all samples are carried out gray processing;
Three, initialization sample weight:
W
T, iThe error weight that represents i sample in the t time circulation is during initialization, if i sample is negative example, order
M is the number of samples of negative example; If i sample is positive example, then order
L is the number of samples of positive example;
Four, the strong classifier of training system, concrete grammar is:
A. specify the number T of the Weak Classifier that comprises in the strong classifier, to t=1 ... T, following steps are carried out in circulation:
1) normalized weight:
T=1 wherein ... T, T is the number of times of training;
2) to each Haar feature f, train a Weak Classifier h (x, f, p, θ); Calculate the error in classification of the Weak Classifier of corresponding this feature; The Haar feature is exactly the feature that forms with two adjacent rectangles, one of them represents with white rectangle, one represents with black rectangle, the Haar feature templates comprises edge feature, linear feature, central feature and diagonal line feature, adularescent and two kinds of rectangles of black in each feature templates, feature templates can be placed on any placement and can convergent-divergent in the piece image subwindow, any convergent-divergent of any one form is put and is called a kind of feature, the eigenwert that defines this template be the white rectangle pixel and deduct the black rectangle pixel and, for gray level image, pixel and be each grey scale pixel value sum;
3) choose the best minimal error rate ε that namely has
tWeak Classifier h
t(x)=h (x, f
t, p
t, θ
t), f wherein
t, p
t, θ
tTo make ε
tValue for minimum;
4) adjust weight according to best Weak Classifier obtained in the previous step:
Wherein, if x
iCorrectly classified e
i=0, if x
iClassified mistakenly e
i=1,
B. the strong classifier that finally obtains is:
Wherein
Step 2) in, the method for training Weak Classifier and calculating weighting error rate is:
To each feature f, train a Weak Classifier h (x, f, p, θ)
Wherein f is feature, and θ is threshold value, and the direction of the p indication sign of inequality is exactly 1 and-1, and what be used for the judgement system appointment is to meet standard or meet standard less than threshold value greater than threshold value, and x represents one and detects subwindow, and f (x) represents the eigenwert of this feature templates;
To each feature f, train a Weak Classifier h (x, f, p, θ), be exactly the optimal threshold of determining f, so that this Weak Classifier h (x, f, p, θ) is minimum to the error in classification of all training samples;
The process of each feature being carried out the Weak Classifier training is:
(1) to each feature f, obtains the eigenwert of all training samples;
(2) eigenwert is sorted;
(3) to sorted each element:
(i) calculate all just weight and the T of sample
+
(ii) weight and the T of the whole negative samples of calculating
-
(iii) calculate this element front just weight and the S of sample
+
(iv) calculate weight and the S of negative sample before this element
-
(v) choose the eigenwert of currentElement
An eigenwert with its front
Between number as threshold value, and the error in classification of calculating this threshold value is:
e=min(S
++(T
--S
-)，S
-+(T
+-S
+))；
(4) all errors in classification relatively obtain making the threshold value of error in classification minimum, as the Weak Classifier for feature f.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210201534.1A CN102880781B (en) | 2012-06-15 | 2012-06-15 | On-line examination intelligent monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210201534.1A CN102880781B (en) | 2012-06-15 | 2012-06-15 | On-line examination intelligent monitoring system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102880781A true CN102880781A (en) | 2013-01-16 |
| CN102880781B CN102880781B (en) | 2015-04-22 |
Family
ID=47482103
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210201534.1A Expired - Fee Related CN102880781B (en) | 2012-06-15 | 2012-06-15 | On-line examination intelligent monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102880781B (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102724394A (en) * | 2012-06-20 | 2012-10-10 | 蒋耘晨 | Surveillance camera for examination halls |
| CN104794665A (en) * | 2015-04-07 | 2015-07-22 | 宋阳 | Examination and evaluation system and control method thereof |
| CN105262998A (en) * | 2015-10-15 | 2016-01-20 | 于璐菁 | Examination monitoring system and examination monitoring method |
| CN105654404A (en) * | 2016-01-20 | 2016-06-08 | 国网福建省电力有限公司 | Computer examination anti-cheating method in electric power system |
| CN106462725A (en) * | 2014-01-07 | 2017-02-22 | Arb实验室公司 | Systems and methods of monitoring activities at a gaming venue |
| CN106919940A (en) * | 2017-03-29 | 2017-07-04 | 安徽大鸿智能科技有限公司 | The monitoring system in the examination hall of vehicle driver subject one |
| CN107393364A (en) * | 2017-09-05 | 2017-11-24 | 艾牛（北京）科技有限公司 | A kind of the classroom method of examination and system |
| CN107818531A (en) * | 2017-11-22 | 2018-03-20 | 浙江中医药大学 | A kind of safe examination system |
| CN107845300A (en) * | 2017-11-22 | 2018-03-27 | 浙江中医药大学 | A kind of safe examination system monitored in real time |
| CN108470255A (en) * | 2018-04-12 | 2018-08-31 | 上海小蚁科技有限公司 | Workload Account method and device, storage medium, computing device |
| CN108897423A (en) * | 2018-06-27 | 2018-11-27 | 武汉华工智云科技有限公司 | A kind of VR glasses and its online testing anti-cheating method |
| CN110135282A (en) * | 2019-04-25 | 2019-08-16 | 沈阳航空航天大学 | A kind of examinee based on depth convolutional neural networks model later plagiarizes cheat detection method |
| US10666667B2 (en) | 2017-11-02 | 2020-05-26 | Tata Consultancy Services Limited | System and method for conducting a secured computer based candidate assessment |
| CN111640342A (en) * | 2018-09-04 | 2020-09-08 | 北京猿力教育科技有限公司 | Online examination method and device, computing device and storage medium |
| CN111666785A (en) * | 2019-03-06 | 2020-09-15 | 阿里巴巴集团控股有限公司 | Behavior recognition method, system, apparatus, computing device, and medium |
| CN112600884A (en) * | 2020-12-02 | 2021-04-02 | 武汉育知联信息科技有限公司 | Cloud inspection management system |
| CN112741437A (en) * | 2021-01-13 | 2021-05-04 | 淄博职业学院 | Psychological health degree evaluation test auxiliary device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2003079314A2 (en) * | 2002-03-15 | 2003-09-25 | The University Of Newcastle Research Associates Limited | Remote examination supervision |
| CN101916365A (en) * | 2010-07-06 | 2010-12-15 | 北京竞业达数码科技有限公司 | Intelligent video identifying method for cheat in test |
| CN102348101A (en) * | 2010-07-30 | 2012-02-08 | 深圳市先进智能技术研究所 | Examination room intelligence monitoring system and method thereof |
-
2012
- 2012-06-15 CN CN201210201534.1A patent/CN102880781B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2003079314A2 (en) * | 2002-03-15 | 2003-09-25 | The University Of Newcastle Research Associates Limited | Remote examination supervision |
| WO2003079314A3 (en) * | 2002-03-15 | 2007-11-29 | Univ Newcastle Res Ass | Remote examination supervision |
| CN101916365A (en) * | 2010-07-06 | 2010-12-15 | 北京竞业达数码科技有限公司 | Intelligent video identifying method for cheat in test |
| CN102348101A (en) * | 2010-07-30 | 2012-02-08 | 深圳市先进智能技术研究所 | Examination room intelligence monitoring system and method thereof |
Non-Patent Citations (3)
| Title |
|---|
| 冯磊: "基于图像分析的智能考试监控系统", 《中国优秀硕士学位论文全文数据库信息科技辑》, no. 9, 15 September 2011 (2011-09-15), pages 6 - 27 * |
| 张道想: "基于图像的在线考试实时监控系统的设计与实现", 《中国优秀硕士学位论文全文数据库信息科技辑》, no. 5, 15 May 2007 (2007-05-15), pages 1 - 49 * |
| 段珊珊: "基于PC摄像头的考试监控系统研究与设计", 《中国优秀硕士学位论文全文数据库信息科技辑》, no. 5, 15 May 2007 (2007-05-15), pages 6 - 15 * |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102724394A (en) * | 2012-06-20 | 2012-10-10 | 蒋耘晨 | Surveillance camera for examination halls |
| CN106462725A (en) * | 2014-01-07 | 2017-02-22 | Arb实验室公司 | Systems and methods of monitoring activities at a gaming venue |
| CN104794665A (en) * | 2015-04-07 | 2015-07-22 | 宋阳 | Examination and evaluation system and control method thereof |
| CN105262998A (en) * | 2015-10-15 | 2016-01-20 | 于璐菁 | Examination monitoring system and examination monitoring method |
| CN105654404A (en) * | 2016-01-20 | 2016-06-08 | 国网福建省电力有限公司 | Computer examination anti-cheating method in electric power system |
| CN106919940A (en) * | 2017-03-29 | 2017-07-04 | 安徽大鸿智能科技有限公司 | The monitoring system in the examination hall of vehicle driver subject one |
| CN107393364A (en) * | 2017-09-05 | 2017-11-24 | 艾牛（北京）科技有限公司 | A kind of the classroom method of examination and system |
| US10666667B2 (en) | 2017-11-02 | 2020-05-26 | Tata Consultancy Services Limited | System and method for conducting a secured computer based candidate assessment |
| CN107818531A (en) * | 2017-11-22 | 2018-03-20 | 浙江中医药大学 | A kind of safe examination system |
| CN107845300A (en) * | 2017-11-22 | 2018-03-27 | 浙江中医药大学 | A kind of safe examination system monitored in real time |
| CN107818531B (en) * | 2017-11-22 | 2020-10-27 | 浙江中医药大学 | Safety examination system |
| CN107845300B (en) * | 2017-11-22 | 2020-07-07 | 浙江中医药大学 | Real-time monitoring safety examination system |
| CN108470255A (en) * | 2018-04-12 | 2018-08-31 | 上海小蚁科技有限公司 | Workload Account method and device, storage medium, computing device |
| CN108470255B (en) * | 2018-04-12 | 2021-02-02 | 上海小蚁科技有限公司 | Workload statistical method and device, storage medium and computing equipment |
| CN108897423A (en) * | 2018-06-27 | 2018-11-27 | 武汉华工智云科技有限公司 | A kind of VR glasses and its online testing anti-cheating method |
| CN111640342A (en) * | 2018-09-04 | 2020-09-08 | 北京猿力教育科技有限公司 | Online examination method and device, computing device and storage medium |
| CN111666785A (en) * | 2019-03-06 | 2020-09-15 | 阿里巴巴集团控股有限公司 | Behavior recognition method, system, apparatus, computing device, and medium |
| CN110135282A (en) * | 2019-04-25 | 2019-08-16 | 沈阳航空航天大学 | A kind of examinee based on depth convolutional neural networks model later plagiarizes cheat detection method |
| CN110135282B (en) * | 2019-04-25 | 2021-06-04 | 沈阳图为科技有限公司 | Examinee return plagiarism cheating detection method based on deep convolutional neural network model |
| CN112600884A (en) * | 2020-12-02 | 2021-04-02 | 武汉育知联信息科技有限公司 | Cloud inspection management system |
| CN112600884B (en) * | 2020-12-02 | 2022-08-02 | 武汉育知联信息科技有限公司 | Cloud inspection management system |
| CN112741437A (en) * | 2021-01-13 | 2021-05-04 | 淄博职业学院 | Psychological health degree evaluation test auxiliary device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102880781B (en) | 2015-04-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102890747B (en) | Intelligent monitoring method for on-line examination | |
| CN102880781B (en) | On-line examination intelligent monitoring system | |
| CN109145789A (en) | Power supply system safety work support method and system | |
| CN102799893B (en) | Method for processing monitoring video in examination room | |
| CN105791299A (en) | Unattended monitoring type intelligent on-line examination system | |
| CN207216700U (en) | A kind of system that speeds passage through customs based on recognition of face | |
| CN110533811A (en) | The method and device and system and storage medium of safety cap inspection are realized based on SSD | |
| CN104700094B (en) | A kind of face identification method for intelligent robot and system | |
| Fuzail et al. | Face detection system for attendance of class’ students | |
| CN106850648A (en) | Auth method, client and service platform | |
| CN102724394A (en) | Surveillance camera for examination halls | |
| CN110543811B (en) | Deep learning-based non-cooperative examination personnel management method and system | |
| CN107833328B (en) | Access control verification method and device based on face recognition and computing equipment | |
| CN109326009A (en) | A kind of system and method that speeds passage through customs based on recognition of face | |
| CN105933190A (en) | Communication method and apparatus applied to intelligent household platform | |
| KR100998617B1 (en) | Central control type cbt system and method thereof | |
| CN112087603B (en) | Intelligent examination room supervision method | |
| Labati et al. | Advanced design of automated border control gates: biometric system techniques and research trends | |
| CN110930566A (en) | Safe rechecking method, system and device for vehicles to and from prisons and storable medium | |
| MacLeod et al. | Methodology for the evaluation of an international airport automated border control processing system | |
| CN105184236A (en) | Robot-based face identification system | |
| CA3114954A1 (en) | Express tracking for patient flow management in a distributed environment | |
| CN102456129B (en) | A kind of security inspection image correction method and system | |
| CN110211266A (en) | A kind of gate inhibition's face identification system and method | |
| CN116580432A (en) | Online examination monitoring method, system, computing device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20150422 Termination date: 20160615 |