CN109726663A - Online testing monitoring method, device, computer equipment and storage medium - Google Patents
Online testing monitoring method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109726663A CN109726663A CN201811582155.5A CN201811582155A CN109726663A CN 109726663 A CN109726663 A CN 109726663A CN 201811582155 A CN201811582155 A CN 201811582155A CN 109726663 A CN109726663 A CN 109726663A
- Authority
- CN
- China
- Prior art keywords
- examinee
- information
- data
- image information
- cheating
- 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
Landscapes
- Collating Specific Patterns (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
This application involves a kind of online testing monitoring method, device, computer equipment and storage mediums, and by obtaining examinee information, examinee information includes image information and voice messaging；Authentication is carried out according to image information and voice messaging；When authentication passes through, push examination task data；Examinee's behavior dynamic data is obtained, and examinee's behavioural characteristic data are obtained based on bone tracking principle；According to examinee's behavioural characteristic data, examinee's cheating probability is analyzed；According to cheating probability analysis as a result, pushing default alarm information.During entire monitoring, after examinee's authentication passes through, push examination task data, when examinee takes an exam, the behavioural characteristic data in examinee's behavior are obtained according to based on bone tracking principle, examinee's cheating probability is analyzed, send alarm information, realize that automation invigilator is not required to artificial concern monitoring in real time, monitored results are accurate, improve invigilator's efficiency.
Description
Technical field
This application involves monitoring technology fields, more particularly to a kind of online testing monitoring method, device, computer equipment
And storage medium.
Background technique
With the raising of the level of cultural life, people increasingly pay attention to Training and Learning, and education activities are also under traditional line
Teaching, becomes and carries out distance learning training on line by network, and examination also becomes gradually moving on line under line with no paper at all.
Traditional online testing monitoring is to pay close attention to student's state in real time by supervisor and invigilate, but examine with no paper at all
Equipment of taking an examination in examination causes invigilator's sight to block, and can not intuitively observe each examinee dynamic.
Existing people has used camera to be monitored, and can be concerned about the behavior state of each examinee, but camera
Monitoring needs the person of invigilator to pay close attention to monitoring in real time, goes through examinee's abnormality, be easy to cause visual fatigue, misses in monitoring
Cheating causes to invigilate low efficiency.
Summary of the invention
Based on this, it is necessary to aiming at the problem that invigilating low efficiency, provide a kind of online testing monitoring for improving invigilator's efficiency
Method, apparatus, computer equipment and storage medium.
A kind of online testing monitoring method, comprising:
Examinee information is obtained, examinee information includes image information and voice messaging；
Authentication is carried out according to image information and voice messaging；
When authentication passes through, push examination task data；
Examinee's behavior dynamic data is obtained, and examinee's behavioural characteristic data are obtained based on bone tracking principle；
According to examinee's behavioural characteristic data, examinee's cheating probability is analyzed；
According to cheating probability analysis as a result, pushing default alarm information.
In one of the embodiments, before acquisition examinee information further include:
Obtain examinee's history image information and examinee's history voice messaging.
Carrying out authentication according to image information and voice messaging in one of the embodiments, includes:
Obtain examinee's current sound information, to examinee's current sound information carry out preemphasis processing, framing window processing with
And after Fourier transformation, discrete cosine transform is carried out, identifiable audio data is obtained；
Speech recognition verifying is carried out to audio data according to examinee's history voice messaging；
When speech recognition is verified, examinee's present image information is obtained, face recognition technology is based on, is gone through according to examinee
History image information carries out similarity verifying to examinee's present image information.
In one of the embodiments, when authentication passes through, push examination task data further include:
When the matching similarity of examinee's history image information and examinee's present image information is lower than preset threshold, adopt again
Collect examinee's image information, carries out similarity mode；
When acquiring examinee information number arrival preset upper limit number, stop push examination task data.
Examinee's behavior dynamic data is obtained in one of the embodiments, and examinee's row is obtained based on bone tracking principle
Being characterized data includes:
Obtain the infrared dynamic data of examinee's behavior；
According to the infrared dynamic data of examinee's behavior, depth of field data is obtained；
According to depth of field data, examinee's bone is matched based on bone tracking principle, establishes examinee's joint coordinates；
According to examinee's joint coordinates, the rotational angle of each skeletal joint is calculated, obtains examinee's behavioural characteristic data.
In one of the embodiments, according to examinee's behavioural characteristic data, carrying out analysis to examinee's cheating probability includes:
Articulation angle in examinee's behavioural characteristic data is compared with default security standpoint, acquisition is greater than or small
In the angle-data of default security standpoint；
Examinee's cheating probability is analyzed according to angle-data, examinee's cheating probability and angle-data are positively correlated.
It is also wrapped after practising fraud probability analysis as a result, pushing default alarm information according to examinee in one of the embodiments,
It includes:
Reception invigilator's terminal responds examinee's cheating detection message that default alarm information is sent；
It is practised fraud according to examinee and detects message, extract the answering information with all examinees in examination hall same where examinee to be detected；
Examinee's answering information to be detected and the answering information of other examinees in examination hall are compared and analyzed, similarity number is obtained
According to；
When set of metadata of similar data is greater than preset threshold, sends and suspect examinee's cheating message.
A kind of online testing monitoring device, comprising:
Information acquisition module, for obtaining examinee information, examinee information includes image information and voice messaging；
Authentication module, for carrying out authentication according to image information and voice messaging；
Task data pushing module, for when authentication passes through, pushing examination task data；
Characteristic obtains module, obtains examinee for obtaining examinee's behavior dynamic data, and based on bone tracking principle
Behavioural characteristic data；
Analysis module, for analyzing examinee's cheating probability according to examinee's behavioural characteristic data；
Alarm information sending module, for presetting alarm information as a result, pushing according to cheating probability analysis.
A kind of computer equipment, including memory and processor, memory are stored with computer program, and processor executes meter
It is performed the steps of when calculation machine program
Examinee information is obtained, examinee information includes image information and voice messaging；
Authentication is carried out according to image information and voice messaging；
When authentication passes through, push examination task data；
Examinee's behavior dynamic data is obtained, and examinee's behavioural characteristic data are obtained based on bone tracking principle；
According to examinee's behavioural characteristic data, examinee's cheating probability is analyzed；
According to cheating probability analysis as a result, pushing default alarm information.
A kind of computer readable storage medium is stored thereon with computer program, when computer program is executed by processor
It performs the steps of
Examinee information is obtained, examinee information includes image information and voice messaging；
Authentication is carried out according to image information and voice messaging；
When authentication passes through, push examination task data；
Examinee's behavior dynamic data is obtained, and examinee's behavioural characteristic data are obtained based on bone tracking principle；
According to examinee's behavioural characteristic data, examinee's cheating probability is analyzed；
According to cheating probability analysis as a result, pushing default alarm information.
Above-mentioned online testing monitoring method, device, computer equipment and storage medium, by obtaining examinee information, examinee
Information includes image information and voice messaging；Authentication is carried out according to image information and voice messaging；When authentication passes through
When, push examination task data；Examinee's behavior dynamic data is obtained, and examinee's behavioural characteristic number is obtained based on bone tracking principle
According to；According to examinee's behavioural characteristic data, examinee's cheating probability is analyzed；According to cheating probability analysis as a result, push is default
Alarm information.During entire monitoring, after examinee's authentication passes through, push examination task data, when examinee takes an exam, root
The behavioural characteristic data in examinee's behavior are obtained according to based on bone tracking principle, examinee's cheating probability is analyzed, sends and accuses
Alert message realizes that automation invigilator is not required to artificial concern monitoring in real time, and monitored results are accurate, improve invigilator's efficiency.
Detailed description of the invention
Fig. 1 is the one of embodiment flow diagram of above-mentioned online testing monitoring method；
Fig. 2 is another embodiment flow diagram of above-mentioned online testing monitoring method；
Fig. 3 is the above-mentioned one of example structure schematic diagram of online testing monitoring device；
Fig. 4 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
In one of the embodiments, as shown in Figure 1, providing a kind of online testing monitoring method, comprising the following steps:
S110: examinee information is obtained, examinee information includes image information and voice messaging.
When carrying out online testing, need first to obtain examinee's identity information, wherein examinee information may include admission card for entrance examination
Number, identification card number, finger print information, image information and voice messaging etc., log in letter by be able to carry out identity unique authentication
Breath just can enter corresponding examination stage after being logged in.In the present embodiment, before examination, examinee is acquired by taking pictures
Image information, and typing is carried out by sound of the microphone apparatus to examinee, obtain voice messaging.
S120: authentication is carried out according to image information and voice messaging.
Before examinee logs in examination, according to the examinee's image information and voice messaging of acquisition, examinee's identity is verified.
In the present embodiment, according to the historical data in the image information and voice messaging that acquire on the spot and default examinee's identity information library into
Row compares, and realizes to certification of exam inee's identity.It is non-essential, can according to the comparison of finger print information and preset fingerprint information, or
The verifying of identification card number and admission card for entrance examination number etc., detects examinee's identity information.
S130: when authentication passes through, push examination task data.
After examinee inputs exam information, the information that server inputs examinee is verified, when the information of examinee's input
When presetting the historical information recorded in examinee's identity information database with server and reaching certain consistent degree, authentication success,
Server pushes the corresponding examination task data of identity unique identification according to identity unique identification.In the present embodiment, work as scene
The examinee's image information recorded in the examinee's image information and examinee's voice messaging and default examinee's identity information database of acquisition
When reaching a certain similarity with examinee's voice messaging, authentication passes through, the corresponding examination content of server push examinee's identity
To examination terminal, examinee starts to take an examination data.
S140: examinee's behavior dynamic data is obtained, and examinee's behavioural characteristic data are obtained based on bone tracking principle.
Dynamic data refers to the data for changing over time and changing in system application.In the present embodiment, examinee's behavior
Dynamic data, which refers to, is monitored examinee's behavior, and examinee acts the data irregularly changed at any time.Bone tracks principle, can
By kinect (body-sensing periphery peripheral hardware), to carry out dynamically capturing immediately and influencing identification etc., acquisition and recording action behavior dynamic
Data, wherein kinect bone tracking are not influenced by ambient lighting, and mainly infrared information generates 3D depth map, to human body into
Row tracking is distinguished human body using strategy is separated from complicated background, by depth characteristic classifier, identifies object
Body determines the joint part of body.It when examinee, which acts, to change, can be tracked, be known according to the angular transition to examinee's skeletal joint
Other examinee's behavior act obtains examinee's behavioural characteristic data.
S150: according to examinee's behavioural characteristic data, examinee's cheating probability is analyzed.
Examinee's behavioural characteristic data that skeletal joint rotational angle obtains are calculated according to tracking examinee's skeletal joint, to examinee
Cheating probability is analyzed.Wherein, " national education examinations violation treating method " issued according to the Ministry of Education, by tester
The unlawful practice that may occur of member is divided into 9 kinds of " undisciplined " and 14 kinds of " cheating ", but because practise fraud and it is undisciplined between be difficult to define, can be with
Using normal read-write mode as normal behaviour, it in addition to this will all be used as abnormal behaviour.It, can just correctly in the present embodiment
Head turns forward, left and right rotary head and stretches out one's hand these three situations and be defined in read-write mode, for example, the angle that head turns forward is 30
It spends to 45 degree and is considered as normally, the angle of head rotated right is to be considered as between 60 degree to 90 degree normally, and the angle that head is turned left is less than 90
Degree is considered as normally, and elbow rotational angle is considered as normally less than 135 degree when stretching out one's hand.It is understood that for just in the present embodiment
The angle definition of Chang Hangwei be not it is unique limit angle, can according to characteristics of human body's behavior research or manager voluntarily
Define the definition of standard implementation normal behaviour.It is right according to the normal bone rotational angle deviation of examinee's behavioural characteristic data and definition
Examinee's cheating probability is analyzed.
S160: according to cheating probability analysis as a result, pushing default alarm information.
According to the definition to examinee's skeletal joint motion tracking, and to examinee's examination normal behaviour, examinee's cheating is obtained
Probability.For example, when definition normal behaviour in, examinee head turn forward normal angled be 30 degree to 45 degree, according to examinee's bone
Tracking when detecting that examinee's head forward leaning angle is 65 degree, beyond default 20 degree of normal header forward leaning angle, then analyzes examinee cheating
Probability is 20%.Further, presetting alarm information includes alarm grade, examinee's abnormal behaviour image, examinee's abnormal behaviour hair
Raw time etc., can preset when cheating probability is 10%-20% is lower priority alarm, and 21%-30% is low middle rank alarm, 31-%-
40% is middle rank alarm, and 41-%-50% is middle-and-high-ranking alarm.50% the above are advanced alarms, it is to be understood that human body head
The active range of portion's rotation varies with each individual, can be also different beyond the range for presetting articulation normal angled, therefore, root
Cheating probability is set according to head gyration, sends predetermined level alarm information to invigilator's terminal further according to probability, warning information can be with
The 2 seconds behavior act images in front and back occur including examinee's abnormal behaviour image, abnormal behaviour duration and abnormal behaviour,
Terminal is invigilated according to alarm information, abnormal behavior examinee's cheating is further confirmed that.
Above-mentioned online testing monitoring method, by obtaining examinee information, examinee information includes image information and voice messaging；
Authentication is carried out according to image information and voice messaging；When authentication passes through, push examination task data；Obtain examinee
Behavior dynamic data, and examinee's behavioural characteristic data are obtained based on bone tracking principle；According to examinee's behavioural characteristic data, to examining
Raw cheating probability is analyzed；According to cheating probability analysis as a result, pushing default alarm information.During entire monitoring, examinee
After authentication passes through, push examination task data when examinee takes an exam, obtains examinee's row according to based on bone tracking principle
For the behavioural characteristic data in dynamic data, examinee's cheating probability is analyzed, alarm information is sent, realizes automation invigilator
It is not required to artificial concern monitoring in real time, monitored results are accurate, improve invigilator's efficiency.
In one of the embodiments, before acquisition examinee information further include: obtain examinee's history image information and examinee
History voice messaging.Wherein, before examinee takes an exam, need to take an exam reservation or examination registration, in registration or in advance
When about, the input personally identifiable information needed, personally identifiable information may include identification card number, student's identity card number, photographic intelligence, refer to
Line information and voice messaging etc. can play the information of unique identification to examinee's identity, reserve test item.Further,
Server obtains the identity information of examinee's input, wherein voice messaging, which can be, carries out sound collection, and voice by microphone
Information can be one section of phonetic order, for example, identification card number sound instruction, name sound instruction etc.；Image information can be tune
The image information temporarily taken pictures with camera or uploaded by examinee, and image information need to be with ID Card Image information one
It causes.Examinee's identity information of acquisition and the corresponding test item information of examinee are stored, carry out identity when as examination
The history identity information of verifying.Verifying foundation can be provided examinee's authentication, guarantee that examinee's identity is errorless, avoid work of praticing fraud
Disadvantage behavior.
Carrying out authentication according to image information and voice messaging in one of the embodiments, includes: to obtain examinee to work as
Preceding acoustic information carries out after carrying out preemphasis processing, the processing of framing window and Fourier transformation to examinee's current sound information
Discrete cosine transform obtains identifiable audio data；Speech recognition is carried out to audio data according to examinee's history voice messaging
Verifying；When speech recognition is verified, examinee's present image information is obtained, face recognition technology is based on, according to examinee's history
Image information carries out similarity verifying to examinee's present image information.Wherein, preemphasis processing is to the high frequency division of the signal of input
Measure the signal processing mode compensated.Framing refers to that voice signal has time variation, but in the range of the short time, generally
Thinking within the of short duration time of 10-30ms, characteristic is held essentially constant, thus can be regarded as a steady quasi- state process,
I.e. voice signal has short-term stationarity, so the analysis processing of any voice signal must be set up on the basis of in short-term, it will
Voice is segmented to analyze its characteristic parameter, wherein each section is known as frame, generally, what is analyzed is to have each frame feature
The characteristic parameter time series of parameter composition.Windowing process refers to, calculates the signal that can only handle finite length, need to be to original letter
Number XT is truncated with sampling time t, becomes XT (t) time series.In the present embodiment, using Hamming window (hamming window), again
Claim improved remaining liter porthole, secondary lobe can be made to reach smaller, lower the rate of decay, voice data is analyzed.In the present embodiment,
Preemphasis treated acoustic information input Hamming window is subjected to frame choosing first, the data by the choosing of Hamming window frame carry out
Fourier transformation, then the data after Fourier transformation are exported in the form of filtering group energy and carry out discrete cosine transform, it obtains
Identifiable audio data code is compared with history audio data code in history voice messaging.Further, work as examinee
After speech verification passes through, double verifying is carried out, camera is called, takes pictures immediately to examinee, obtains examinee's image information, base
In face recognition technology, examinee's identity is verified.In the present embodiment, Ali's cloud recognition of face interface can be called, is based on
Face recognition technology carries out pair facial feature information in the examinee's image information and examinee's history image information acquired on the spot
Than illustrating currently to examine when the similarity of current examinee's image information and examinee's history image information is greater than preset threshold 90%
The raw examinee with history registry examination is same people, is verified, pushes the corresponding examination task data of the examinee, start to examine
Examination.It is understood that preset threshold is not limited in 90% similarity, can be carried out according to invigilator's quality and examination hall demand
Setting.Dual identity verifying is compared by voice messaging identification and human face image information, examination is effectively controlled and pratices fraud cheating
Behavior effectively increases invigilator's efficiency.
In one of the embodiments, when authentication passes through, push examination task data further include: when examinee's history
When the matching similarity of image information and examinee's present image information is lower than preset threshold, examinee's image information is resurveyed, into
Row similarity mode；When acquiring examinee information number arrival preset upper limit number, stop push examination task data.Wherein,
Before examination, takes pictures on the spot to examinee and typing is carried out to examinee's sound by microphone, obtain examinee's image information
And acoustic information, when the examinee's image information and acoustic information obtained on the spot, with examinee's image information of history storage and
When voice history information similarity is greater than 80%, authentication passes through, into examination.After voice messaging is verified, carry out
When image information and examinee's history image information similarity are lower than preset threshold authentication failed, it can take pictures again to examinee,
Image information is acquired, continues to verify, when the number to examinee's image information collecting reaches 8 times, is stopped to the examinee information
Acquisition, and stop push examination task data.It is understood that preset threshold and preset upper limit number are not uniquely to limit
It is fixed, it can be modified according to demand.Further, when acquiring image information number arrival upper limit number, abnormal mentions is sent
Show that message to terminal is invigilated, is verified examinee's situation by supervisor.It is non-essential, when examinee is favorite in examination process
When exiting outside, server records the examination content on timing node and timing node when exiting, when the examinee is again introduced into
When, timing node when exiting into the last time continues to complete examination task, also, within the remaining test time, random shooting
Examinee's facial image obtains examinee's human face image information and carries out authentication.Facial change can be effectively avoided in the present embodiment
Change causes authentication failed that can also identify to the examinee that pratices fraud, and improves invigilator's efficiency.
In one of the embodiments, as shown in Fig. 2, obtaining examinee's behavior dynamic data, and principle is tracked based on bone
Obtaining examinee's behavioural characteristic data includes:
S210: the infrared dynamic data of examinee's behavior is obtained.
S220 obtains depth of field data according to the infrared dynamic data of examinee's behavior.
S230: according to depth of field data, examinee's bone is matched based on bone tracking principle, establishes examinee joint seat
Mark.
S240: according to examinee's joint coordinates, the rotational angle of each skeletal joint is calculated, obtains examinee's behavioural characteristic data.
Wherein, obtain the infrared dynamic data of examinee's behavior can by call kinect (body-sensing periphery peripheral hardware) interface,
Middle kinect has infrared transmitter and camera, by the monitoring to examinee's behavior act and ambient enviroment, generates three dimensions
According to obtaining the infrared dynamic data of examinee's behavior, contain environmental background dynamic data in the infrared dynamic data of examinee's behavior.The depth of field
Data refer to, through kinect at a distance from environment personage, calculate the image pixel depth value of environment personage within the vision,
Kinect is remoter at a distance from environment personage, and depth value is smaller, and color is more shallow, and kinect is closer at a distance from environment personage, deep
Angle value is bigger, and color is deeper.According to depth of field data, strategy is separated by kinect, by human body from complicated background environment area
It branches away, depth image data is assessed based on bone tracking principle, match the different parts of human body, for example, head, shoulder,
It the skeletal joints such as elbow joint, wrist, ankle and knee position in the present embodiment can be using half body mode to examinee
Behavior is monitored, and only the upper part of the body skeletal joint such as enemy, shoulder, elbow and wrist is tracked, and establishes upper part of the body skeletal joint
The coordinate system of point.Examinee's behavioural characteristic data can be the angle of examinee's agenda movement in a coordinate system.Further, exist
In rectangular coordinate system, with head for C point, left shoulder joint node is A point, and right shoulder joint node is B point, and shoulder joint center is O point, same
In plane, using shoulder joint central point as origin, the line of two shoulders is controlled as X-axis, the line at head and shoulder center is Y-axis, and head is to the left
Turn: the angle between detection OA vector and OC vector；Head rotated right: the angle between detection OC vector and OB vector；Stretch left hand:
With left hand elbow joint be M point, left hand wrist joint be P point, using left hand elbow joint point M as origin, detection MP vector and MA vector it
Between angle；Stretch the right hand: with left hand elbow joint for N point, left hand wrist joint is Q point, using left hand elbow joint point N as origin, detection
Angle between NA vector and NQ vector.In a coordinate system, detect that examinee's head is turned right, the angle between OC vector and OA vector
When being 50 degree, i.e., examinee's behavioural characteristic data are that head is turned right 50 degree.By establishing skeletal joint coordinate system, tracking examinee's behavior is dynamic
Make, as a result precisely, improves invigilator's efficiency.
Specifically, being analyzed in one of the embodiments, according to examinee's behavioural characteristic data examinee's cheating probability
It include: to compare the articulation angle in examinee's behavioural characteristic data with default security standpoint, acquisition is more than or less than
The angle-data of default security standpoint；Examinee's cheating probability is analyzed according to angle-data, examinee's cheating probability and angle-data are just
It is related.Wherein, by examinee's skeletal joint coordinate system of foundation, in the same plane, using shoulder joint central point as origin, left and right
The line of two shoulders is X-axis, and the line at head and shoulder center is Y-axis, and it is between 30 degree to 45 degree that default head, which turns security standpoint range Theta,；
Head is turned left: presetting the angle between OA vector and OC vector at 60 degree to 90 degree is security standpoint；Head rotated right: default OC to
Angle between amount and OB vector is security standpoint between 60 degree and 90 degree；Stretch left hand: with left hand elbow joint for M point, left hand
Wrist joint is P point, using left hand elbow joint point M as origin, presets 60 degree to 130 degree of angle between MP vector and MA vector as peace
Full angle；Stretch the right hand: with left hand elbow joint for N point, left hand wrist joint is Q point, using left hand elbow joint point N as origin, presets NA
60 degree to 130 degree of angle between vector and NQ vector are security standpoint.It is and default when examinee's head rotated right angle is 50 degree
Head right-hand rotation security standpoint comparison, the angle-data for obtaining being less than default security standpoint is 10 degree.When inclined with default security standpoint
Poor angle-data is bigger, and examinee's cheating probability is bigger, in the present embodiment, since human body executes the articulation angle of a movement
Degree varies with each individual, and cannot treat different things as the same, and therefore, when angle-data is 10 degree, analysis examinee's cheating probability is 10%, by true
Real angular deviation carries out cheating probability analysis.In the present embodiment, pass through detection examinee's actual act angle and default security standpoint
Deviation, cheating probability is analyzed, true to reflect examinee's behavior act, monitoring is accurate, improves invigilator's efficiency.
It is also wrapped after practising fraud probability analysis as a result, pushing default alarm information according to examinee in one of the embodiments,
Include: reception invigilator's terminal responds examinee's cheating detection message that default alarm information is sent；It is practised fraud according to examinee and detects message, mentioned
Take the answering information with all examinees in examination hall same where examinee to be detected；By in examinee's answering information to be detected and examination hall other
The answering information of examinee compares and analyzes, and obtains set of metadata of similar data；When set of metadata of similar data is greater than preset threshold, sends and suspect examinee
Cheating message.Wherein, according to probability analysis as a result, the corresponding alarm grade message of push probability analysis result is to invigilating terminal,
Warning information may include that the 2 seconds rows in front and back occur for examinee's abnormal behaviour image, abnormal behaviour duration and abnormal behaviour
For motion images, terminal is invigilated according to alarm information, fore-aft motion is acted to examinee's abnormal behaviour movement and abnormal behaviour
It is observed, when examinee's behavior act is there is no when cheating risk, releasing to practise fraud to alert, when invigilator person carries out examinee's behavior
Observation when finding that examinee's behavior act is suspicious, sends cheating detection message to server, server response cheating detection disappears
Breath extracts and answers information with all examinees in examination hall same where examinee to be detected, examinee's answering information quantified, and to amount
Examinee's answering information after change carries out similarity analysis, defines examinee's answering information Ci (Ci to be detected1、Ci2...Cin), n table
Show the topic number of examination, defines the answering information 0JD (OJD of other examinees in examination hall1、OJD2..OJDN),OJDNIndicate that j-th is examined
The road the N answering information of raw examination, analyzes examinee to be detected and other examinee's answering information similarity data are as follows:
Wherein Z is examination hall number, and H indicates examinee's number to be measured, and X indicates that the admission card for entrance examination of examinee to be measured and other examinees are numbered
Difference sends when Q is greater than preset threshold and suspects examinee's cheating message to monitor terminal.Supervisor disappears according to suspection cheating
Breath carries out final judgement of practising fraud to the examinee.In the present embodiment, the answer by analyzing examinee and all examinees of examinee to be measured is believed
Breath is analyzed, and is sent and is suspected examinee's cheating message, enables the cheating of supervisor's intuitive judgment examinee, be not required to people
To pay close attention in real time, and testing result is accurate, improves invigilator's efficiency.
In one of the embodiments, as shown in figure 3, providing a kind of online testing monitoring device, comprise the following modules:
Information acquisition module 310, for obtaining examinee information, examinee information includes image information and voice messaging；
Authentication module 320, for carrying out authentication according to image information and voice messaging；
Task data pushing module 330, for when authentication passes through, pushing examination task data；
Characteristic obtains module 340, examines for obtaining examinee's behavior dynamic data, and based on bone tracking principle acquisition
Raw behavioural characteristic data；
Analysis module 350, for analyzing examinee's cheating probability according to examinee's behavioural characteristic data；
Alarm information sending module 360, for presetting alarm information as a result, pushing according to cheating probability analysis.
Information acquisition module 310 in one of the embodiments, are also used to obtain examinee's history image information and examinee goes through
History voice messaging.
Authentication module 320 in one of the embodiments, are also used to obtain examinee's current sound information, to examinee
After current sound information carries out preemphasis processing, the processing of framing window and Fourier transformation, discrete cosine transform is carried out, is obtained
Identifiable audio data；Speech recognition verifying is carried out to audio data according to examinee's history voice messaging；When speech recognition is tested
When card passes through, examinee's present image information is obtained, is based on face recognition technology, it is current to examinee according to examinee's history image information
Image information carries out similarity verifying.
Task data pushing module 330 in one of the embodiments, is also used to as examinee's history image information and examinee
When the matching similarity of present image information is lower than preset threshold, examinee's image information is resurveyed, carries out similarity mode；When
When acquiring examinee information number arrival preset upper limit number, stop push examination task data.
Characteristic obtains module 340 in one of the embodiments, is also used to obtain the infrared dynamic number of examinee's behavior
According to；According to the infrared dynamic data of examinee's behavior, depth of field data is obtained；According to depth of field data, based on bone tracking principle to examinee
Bone is matched, and examinee's joint coordinates are established；According to examinee's joint coordinates, the rotational angle of each skeletal joint is calculated, is obtained
Examinee's behavioural characteristic data.
Analysis module 350 in one of the embodiments, are also used to the articulation angle in examinee's behavioural characteristic data
Degree is compared with default security standpoint, obtains the angle-data for being more than or less than default security standpoint；According to angle-data point
Examinee's cheating probability is analysed, examinee's cheating probability and angle-data are positively correlated.
Above-mentioned online testing monitoring device in one of the embodiments, further includes detection module, for receiving invigilator eventually
End responds examinee's cheating detection message that default alarm information is sent；It is practised fraud according to examinee and detects message, extraction is compared with to be checked
The answering information of the same all examinees in examination hall where raw；The answer of other examinees in examinee's answering information to be detected and examination hall is believed
Breath compares and analyzes, and obtains set of metadata of similar data；When set of metadata of similar data is greater than preset threshold, sends and suspect examinee's cheating message.
Specific about online testing monitoring device limits the limit that may refer to above for online testing monitoring method
Fixed, details are not described herein.Modules in above-mentioned online testing monitoring device can fully or partially through software, hardware and its
Combination is to realize.Above-mentioned each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also be with
Software form is stored in the memory in computer equipment, executes the corresponding behaviour of the above modules in order to which processor calls
Make.
A kind of computer equipment is provided in one of the embodiments, which can be server, in
Portion's structure chart can be as shown in Figure 4.The computer equipment includes that the processor, memory, network connected by system bus connects
Mouth and database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The storage of the computer equipment
Device includes non-volatile memory medium, built-in storage.The non-volatile memory medium be stored with operating system, computer program and
Database.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.It should
The database of computer equipment is for storing online testing monitoring data.The network interface of the computer equipment is used for and outside
Terminal passes through network connection communication.To realize a kind of online testing monitoring method when the computer program is executed by processor.
It will be understood by those skilled in the art that structure shown in Fig. 4, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, is stored in memory
Computer program, the processor perform the steps of acquisition examinee information when executing computer program, and examinee information includes image
Information and voice messaging；Authentication is carried out according to image information and voice messaging；When authentication passes through, push examination is appointed
Business data；Examinee's behavior dynamic data is obtained, and examinee's behavioural characteristic data are obtained based on bone tracking principle；According to examinee's row
Data are characterized, examinee's cheating probability is analyzed；According to cheating probability analysis as a result, pushing default alarm information.
It is also performed the steps of when processor executes computer program in one of the embodiments, and obtains examinee's history
Image information and examinee's history voice messaging.
It is current that acquisition examinee is also performed the steps of when processor executes computer program in one of the embodiments,
Acoustic information, to examinee's current sound information carry out preemphasis processing, framing window processing and Fourier transformation after, carry out from
Cosine transform is dissipated, identifiable audio data is obtained；Speech recognition is carried out to audio data according to examinee's history voice messaging to test
Card；When speech recognition is verified, examinee's present image information is obtained, face recognition technology is based on, according to examinee's history figure
As information carries out similarity verifying to examinee's present image information.
It also performs the steps of when processor executes computer program in one of the embodiments, when examinee's history figure
When being lower than preset threshold as the matching similarity of information and examinee's present image information, examinee's image information is resurveyed, is carried out
Similarity mode；When acquiring examinee information number arrival preset upper limit number, stop push examination task data.
It is also performed the steps of when processor executes computer program in one of the embodiments, and obtains examinee's behavior
Infrared dynamic data；According to the infrared dynamic data of examinee's behavior, depth of field data is obtained；According to depth of field data, tracked based on bone
Principle matches examinee's bone, establishes examinee's joint coordinates；According to examinee's joint coordinates, the rotation of each skeletal joint is calculated
Angle obtains examinee's behavioural characteristic data.
It is also performed the steps of when processor executes computer program in one of the embodiments, examinee's behavior is special
Articulation angle in sign data is compared with default security standpoint, obtains the angle for being more than or less than default security standpoint
Data；Examinee's cheating probability is analyzed according to angle-data, examinee's cheating probability and angle-data are positively correlated.
Reception invigilator's terminal is also performed the steps of when processor executes computer program in one of the embodiments,
Respond examinee's cheating detection message that default alarm information is sent；It is practised fraud according to examinee and detects message, extracted and examinee to be detected
The answering information of all examinees in the same examination hall in place；By the answering information of other examinees in examinee's answering information to be detected and examination hall
It compares and analyzes, obtains set of metadata of similar data；When set of metadata of similar data is greater than preset threshold, sends and suspect examinee's cheating message.
A kind of computer readable storage medium is provided in one of the embodiments, is stored thereon with computer program,
Acquisition examinee information is performed the steps of when computer program execution processed, examinee information includes image information and voice letter
Breath；Authentication is carried out according to image information and voice messaging；When authentication passes through, push examination task data；It obtains
Examinee's behavior dynamic data, and examinee's behavioural characteristic data are obtained based on bone tracking principle；According to examinee's behavioural characteristic data,
Examinee's cheating probability is analyzed；According to cheating probability analysis as a result, pushing default alarm information.
Acquisition examinee is also performed the steps of when computer program is executed by processor in one of the embodiments, to go through
History image information and examinee's history voice messaging.
Acquisition examinee is also performed the steps of when computer program is executed by processor in one of the embodiments, to work as
Preceding acoustic information carries out after carrying out preemphasis processing, the processing of framing window and Fourier transformation to examinee's current sound information
Discrete cosine transform obtains identifiable audio data；Speech recognition is carried out to audio data according to examinee's history voice messaging
Verifying；When speech recognition is verified, examinee's present image information is obtained, face recognition technology is based on, according to examinee's history
Image information carries out similarity verifying to examinee's present image information.
It also performs the steps of when computer program is executed by processor in one of the embodiments, when examinee's history
When the matching similarity of image information and examinee's present image information is lower than preset threshold, examinee's image information is resurveyed, into
Row similarity mode；When acquiring examinee information number arrival preset upper limit number, stop push examination task data.
It is also performed the steps of when computer program is executed by processor in one of the embodiments, and obtains examinee's row
For infrared dynamic data；According to the infrared dynamic data of examinee's behavior, depth of field data is obtained；According to depth of field data, chased after based on bone
Track principle matches examinee's bone, establishes examinee's joint coordinates；According to examinee's joint coordinates, turning for each skeletal joint is calculated
Dynamic angle, obtains examinee's behavioural characteristic data.
It is also performed the steps of when computer program is executed by processor in one of the embodiments, by examinee's behavior
Articulation angle in characteristic is compared with default security standpoint, obtains the angle for being more than or less than default security standpoint
Degree evidence；Examinee's cheating probability is analyzed according to angle-data, examinee's cheating probability and angle-data are positively correlated.
Reception invigilator is also performed the steps of when computer program is executed by processor in one of the embodiments, eventually
End responds examinee's cheating detection message that default alarm information is sent；It is practised fraud according to examinee and detects message, extraction is compared with to be checked
The answering information of the same all examinees in examination hall where raw；The answer of other examinees in examinee's answering information to be detected and examination hall is believed
Breath compares and analyzes, and obtains set of metadata of similar data；When set of metadata of similar data is greater than preset threshold, sends and suspect examinee's cheating message.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of embodiment described above can be combined arbitrarily, for simplicity of description, not to above-mentioned reality
It applies all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, all should be considered as described in this specification.
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to protection of the invention
Range.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.
Claims (10)
1. a kind of online testing monitoring method characterized by comprising
Examinee information is obtained, the examinee information includes image information and voice messaging；
Authentication is carried out according to described image information and the voice messaging；
When authentication passes through, push examination task data；
Examinee's behavior dynamic data is obtained, and examinee's behavioural characteristic data are obtained based on bone tracking principle；
According to examinee's behavioural characteristic data, examinee's cheating probability is analyzed；
According to cheating probability analysis as a result, pushing default alarm information.
2. online testing monitoring method according to claim 1, which is characterized in that also wrapped before the acquisition examinee information
It includes:
Obtain examinee's history image information and examinee's history voice messaging.
3. online testing monitoring method according to claim 2, which is characterized in that described according to described image information and described
Voice messaging carries out authentication
Obtain examinee's current sound information, to examinee's current sound information carry out preemphasis processing, framing window processing with
And after Fourier transformation, discrete cosine transform is carried out, identifiable audio data is obtained；
Speech recognition verifying is carried out to the audio data according to examinee's history voice messaging；
When speech recognition is verified, examinee's present image information is obtained, face recognition technology is based on, is gone through according to the examinee
History image information carries out similarity verifying to examinee's present image information.
4. online testing monitoring method according to claim 1, which is characterized in that described when authentication passes through, push
Examination task data further include:
When the matching similarity of examinee's history image information and examinee's present image information is lower than preset threshold, weight
New acquisition examinee's image information, carries out similarity mode；
When acquiring examinee information number arrival preset upper limit number, stop push examination task data.
5. online testing monitoring method according to claim 1, which is characterized in that the acquisition examinee behavior dynamic data,
And examinee's behavioural characteristic data are obtained based on bone tracking principle and include:
Obtain the infrared dynamic data of examinee's behavior；
According to the infrared dynamic data of examinee's behavior, depth of field data is obtained；
According to the depth of field data, examinee's bone is matched based on bone tracking principle, establishes examinee's joint coordinates；
According to examinee's joint coordinates, the rotational angle of each skeletal joint is calculated, obtains examinee's behavioural characteristic data.
6. online testing monitoring method according to claim 5, which is characterized in that described according to examinee's behavioural characteristic number
According to carrying out analysis to examinee's cheating probability includes:
Articulation angle in examinee's behavioural characteristic data is compared with default security standpoint, acquisition is greater than or small
In the angle-data of default security standpoint；
Examinee's cheating probability is analyzed according to the angle-data, examinee's cheating probability and the angle-data are positively correlated.
7. online testing monitoring method according to claim 1, which is characterized in that it is described according to cheating probability analysis as a result,
It pushes after presetting alarm information further include:
It receives invigilator's terminal and responds examinee's cheating detection message that the default alarm information is sent；
It is practised fraud according to the examinee and detects message, extract the answering information with all examinees in examination hall same where examinee to be detected；
Examinee's answering information to be detected and the answering information of other examinees in examination hall are compared and analyzed, similarity number is obtained
According to；
When the set of metadata of similar data is greater than preset threshold, sends and suspect examinee's cheating message.
8. a kind of online testing monitoring device, which is characterized in that described device includes:
Information acquisition module, for obtaining examinee information, the examinee information includes image information and voice messaging；
Authentication module, for carrying out authentication according to described image information and the voice messaging；
Task data pushing module, for when authentication passes through, pushing examination task data；
Characteristic obtains module, obtains examinee's behavior for obtaining examinee's behavior dynamic data, and based on bone tracking principle
Characteristic；
Analysis module, for analyzing examinee's cheating probability according to examinee's behavioural characteristic data；
Alarm information sending module, for presetting alarm information as a result, pushing according to cheating probability analysis.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 7 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 7 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811582155.5A CN109726663A (en) | 2018-12-24 | 2018-12-24 | Online testing monitoring method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811582155.5A CN109726663A (en) | 2018-12-24 | 2018-12-24 | Online testing monitoring method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109726663A true CN109726663A (en) | 2019-05-07 |
Family
ID=66296402
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811582155.5A Pending CN109726663A (en) | 2018-12-24 | 2018-12-24 | Online testing monitoring method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109726663A (en) |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110189239A (en) * | 2019-05-30 | 2019-08-30 | 北京金和网络股份有限公司 | Five fixed online testing method and system |
| CN110458735A (en) * | 2019-07-05 | 2019-11-15 | 黄河水利职业技术学院 | A kind of intelligence examination hall management system and method |
| CN110705270A (en) * | 2019-09-18 | 2020-01-17 | 北京金和网络股份有限公司 | Voice monitoring online examination method and device based on five-determination technology |
| CN111192173A (en) * | 2019-12-27 | 2020-05-22 | 广东德诚科教有限公司 | Examination invigilating system and method, server, computer readable storage medium |
| CN111274956A (en) * | 2020-01-20 | 2020-06-12 | 北京明略软件系统有限公司 | Method and device for monitoring driving test |
| CN111311455A (en) * | 2020-01-17 | 2020-06-19 | 广东德诚科教有限公司 | Examination information matching method and device, computer equipment and storage medium |
| CN111539313A (en) * | 2020-04-21 | 2020-08-14 | 成都佳发安泰教育科技股份有限公司 | Examination cheating behavior detection method and system |
| CN111553203A (en) * | 2020-04-10 | 2020-08-18 | 北京明略软件系统有限公司 | Method and device for monitoring examination fraud behaviors |
| CN111583732A (en) * | 2020-06-03 | 2020-08-25 | 广州市南方人力资源评价中心有限公司 | Evaluation state monitoring method, device and equipment based on head-mounted display equipment |
| CN111640150A (en) * | 2019-09-20 | 2020-09-08 | 于贵庆 | Video data source analysis system and method |
| CN111951629A (en) * | 2019-05-16 | 2020-11-17 | 上海流利说信息技术有限公司 | Pronunciation correction system, method, medium and computing device |
| CN112101215A (en) * | 2020-09-15 | 2020-12-18 | Oppo广东移动通信有限公司 | Face input method, terminal equipment and computer readable storage medium |
| CN112818796A (en) * | 2021-01-26 | 2021-05-18 | 厦门大学 | Intelligent posture discrimination method and storage device suitable for online invigilation scene |
| CN113010868A (en) * | 2021-04-14 | 2021-06-22 | 苏州智行众维智能科技有限公司 | On-line test authentication examination management system |
| CN113468488A (en) * | 2020-03-30 | 2021-10-01 | 广东虚拟现实科技有限公司 | Remote examination system and method |
| CN113743901A (en) * | 2021-09-07 | 2021-12-03 | 广州网才信息技术有限公司 | Cloud online invigilation method, system, equipment and storage medium |
| CN114360085A (en) * | 2021-11-25 | 2022-04-15 | 中国人民人寿保险股份有限公司 | Method for identifying attendance cheating behaviors, service system and terminal equipment thereof |
| CN110321852B (en) * | 2019-07-05 | 2022-06-14 | 创优数字科技(广东)有限公司 | Action type identification method and device, storage medium and computer equipment |
| CN114882533A (en) * | 2022-05-30 | 2022-08-09 | 北京百度网讯科技有限公司 | Examination room abnormal behavior detection method, device, equipment and storage medium |
| WO2022191798A1 (en) * | 2021-03-12 | 2022-09-15 | Bahcesehir Universitesi | Online exam security system and a method thereof |
| CN115146243A (en) * | 2022-07-08 | 2022-10-04 | 武汉全英教育咨询有限公司 | Online VR examination examinee information checking management system based on data analysis |
| CN116153312A (en) * | 2023-03-05 | 2023-05-23 | 广州网才信息技术有限公司 | Online pen test method and device using voice recognition |
| CN116580354A (en) * | 2023-05-11 | 2023-08-11 | 泰州市元根体育器材有限公司 | Remote education invigilation system with application mode switching |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101763459A (en) * | 2009-09-01 | 2010-06-30 | 周荣华 | Method for remotely invigilating individual |
| CN104299178A (en) * | 2014-07-11 | 2015-01-21 | 北京神州智联科技有限公司 | Facial-recognition-based network teaching method and system |
| CN106023516A (en) * | 2016-05-18 | 2016-10-12 | 广西瀚特信息产业股份有限公司 | Examination monitoring method and system and examination room monitor |
| CN107077796A (en) * | 2016-03-11 | 2017-08-18 | 深圳市大疆创新科技有限公司 | Method, system and the equipment of the anti-cheating of storage medium, network test |
| CN107491717A (en) * | 2016-06-13 | 2017-12-19 | 科大讯飞股份有限公司 | The detection method that cheats at one's exam and device |
| CN107895336A (en) * | 2017-12-01 | 2018-04-10 | 合肥亚慕信息科技有限公司 | A kind of online testing invigilator's system and method for work caught based on multi-faceted dynamic |
| CN107895036A (en) * | 2017-11-27 | 2018-04-10 | 合肥亚慕信息科技有限公司 | One kind is based on the online analysis and processing method that cheats at one's exam of safety encryption |
| US10147184B2 (en) * | 2016-12-30 | 2018-12-04 | Cerner Innovation, Inc. | Seizure detection |
-
2018
- 2018-12-24 CN CN201811582155.5A patent/CN109726663A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101763459A (en) * | 2009-09-01 | 2010-06-30 | 周荣华 | Method for remotely invigilating individual |
| CN104299178A (en) * | 2014-07-11 | 2015-01-21 | 北京神州智联科技有限公司 | Facial-recognition-based network teaching method and system |
| CN107077796A (en) * | 2016-03-11 | 2017-08-18 | 深圳市大疆创新科技有限公司 | Method, system and the equipment of the anti-cheating of storage medium, network test |
| CN106023516A (en) * | 2016-05-18 | 2016-10-12 | 广西瀚特信息产业股份有限公司 | Examination monitoring method and system and examination room monitor |
| CN107491717A (en) * | 2016-06-13 | 2017-12-19 | 科大讯飞股份有限公司 | The detection method that cheats at one's exam and device |
| US10147184B2 (en) * | 2016-12-30 | 2018-12-04 | Cerner Innovation, Inc. | Seizure detection |
| CN107895036A (en) * | 2017-11-27 | 2018-04-10 | 合肥亚慕信息科技有限公司 | One kind is based on the online analysis and processing method that cheats at one's exam of safety encryption |
| CN107895336A (en) * | 2017-12-01 | 2018-04-10 | 合肥亚慕信息科技有限公司 | A kind of online testing invigilator's system and method for work caught based on multi-faceted dynamic |
Non-Patent Citations (4)
| Title |
|---|
| 刘静等: "基于kinect的考试异常行为识别与研究", 《计算机光盘软件与应用》 * |
| 李恒: "基于Kinect骨骼跟踪功能的骨骼识别系统研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 董万里: "面向货物分拣的地名语音识别系统", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 钱美伶: "基于Kinect的室内异常行为检测", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111951629A (en) * | 2019-05-16 | 2020-11-17 | 上海流利说信息技术有限公司 | Pronunciation correction system, method, medium and computing device |
| CN110189239A (en) * | 2019-05-30 | 2019-08-30 | 北京金和网络股份有限公司 | Five fixed online testing method and system |
| CN110458735A (en) * | 2019-07-05 | 2019-11-15 | 黄河水利职业技术学院 | A kind of intelligence examination hall management system and method |
| CN110321852B (en) * | 2019-07-05 | 2022-06-14 | 创优数字科技(广东)有限公司 | Action type identification method and device, storage medium and computer equipment |
| CN110705270A (en) * | 2019-09-18 | 2020-01-17 | 北京金和网络股份有限公司 | Voice monitoring online examination method and device based on five-determination technology |
| CN111640150A (en) * | 2019-09-20 | 2020-09-08 | 于贵庆 | Video data source analysis system and method |
| CN111192173A (en) * | 2019-12-27 | 2020-05-22 | 广东德诚科教有限公司 | Examination invigilating system and method, server, computer readable storage medium |
| CN111311455B (en) * | 2020-01-17 | 2024-02-06 | 广东德诚科教有限公司 | Examination information matching method, examination information matching device, computer equipment and storage medium |
| CN111311455A (en) * | 2020-01-17 | 2020-06-19 | 广东德诚科教有限公司 | Examination information matching method and device, computer equipment and storage medium |
| CN111274956A (en) * | 2020-01-20 | 2020-06-12 | 北京明略软件系统有限公司 | Method and device for monitoring driving test |
| CN113468488A (en) * | 2020-03-30 | 2021-10-01 | 广东虚拟现实科技有限公司 | Remote examination system and method |
| CN111553203A (en) * | 2020-04-10 | 2020-08-18 | 北京明略软件系统有限公司 | Method and device for monitoring examination fraud behaviors |
| CN111539313A (en) * | 2020-04-21 | 2020-08-14 | 成都佳发安泰教育科技股份有限公司 | Examination cheating behavior detection method and system |
| CN111583732B (en) * | 2020-06-03 | 2021-09-03 | 广州市南方人力资源评价中心有限公司 | Evaluation state monitoring method, device and equipment based on head-mounted display equipment |
| CN111583732A (en) * | 2020-06-03 | 2020-08-25 | 广州市南方人力资源评价中心有限公司 | Evaluation state monitoring method, device and equipment based on head-mounted display equipment |
| CN112101215A (en) * | 2020-09-15 | 2020-12-18 | Oppo广东移动通信有限公司 | Face input method, terminal equipment and computer readable storage medium |
| CN112818796B (en) * | 2021-01-26 | 2023-10-24 | 厦门大学 | Intelligent gesture distinguishing method and storage device suitable for online prison scene |
| CN112818796A (en) * | 2021-01-26 | 2021-05-18 | 厦门大学 | Intelligent posture discrimination method and storage device suitable for online invigilation scene |
| WO2022191798A1 (en) * | 2021-03-12 | 2022-09-15 | Bahcesehir Universitesi | Online exam security system and a method thereof |
| CN113010868B (en) * | 2021-04-14 | 2022-02-01 | 苏州智行众维智能科技有限公司 | On-line test authentication examination management system |
| CN113010868A (en) * | 2021-04-14 | 2021-06-22 | 苏州智行众维智能科技有限公司 | On-line test authentication examination management system |
| CN113743901A (en) * | 2021-09-07 | 2021-12-03 | 广州网才信息技术有限公司 | Cloud online invigilation method, system, equipment and storage medium |
| CN114360085A (en) * | 2021-11-25 | 2022-04-15 | 中国人民人寿保险股份有限公司 | Method for identifying attendance cheating behaviors, service system and terminal equipment thereof |
| CN114882533A (en) * | 2022-05-30 | 2022-08-09 | 北京百度网讯科技有限公司 | Examination room abnormal behavior detection method, device, equipment and storage medium |
| CN115146243B (en) * | 2022-07-08 | 2023-09-15 | 北京布局未来教育科技有限公司 | Online VR examination examinee information checking and managing system based on data analysis |
| CN115146243A (en) * | 2022-07-08 | 2022-10-04 | 武汉全英教育咨询有限公司 | Online VR examination examinee information checking management system based on data analysis |
| CN116153312A (en) * | 2023-03-05 | 2023-05-23 | 广州网才信息技术有限公司 | Online pen test method and device using voice recognition |
| CN116580354A (en) * | 2023-05-11 | 2023-08-11 | 泰州市元根体育器材有限公司 | Remote education invigilation system with application mode switching |
| CN116580354B (en) * | 2023-05-11 | 2023-11-03 | 北京优思安科技有限公司 | Remote education invigilation system with application mode switching |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109726663A (en) | Online testing monitoring method, device, computer equipment and storage medium | |
| US10740465B2 (en) | Detection of print-based spoofing attacks | |
| EP3373202B1 (en) | Verification method and system | |
| US9082011B2 (en) | Person identification using ocular biometrics with liveness detection | |
| CN104966070B (en) | Biopsy method and device based on recognition of face | |
| Hu et al. | Research on abnormal behavior detection of online examination based on image information | |
| US9892315B2 (en) | Systems and methods for detection of behavior correlated with outside distractions in examinations | |
| CN106156578A (en) | Auth method and device | |
| CN110909722A (en) | Anti-cheating camera based on target action detection | |
| CN115205764B (en) | Online learning concentration monitoring method, system and medium based on machine vision | |
| CN110647807A (en) | Abnormal behavior determination method and device, computer equipment and storage medium | |
| Rigas et al. | Gaze estimation as a framework for iris liveness detection | |
| CN112633189A (en) | Method and device for preventing examination cheating, electronic equipment and computer readable medium | |
| CN113794759B (en) | Examination cloud platform system based on block chain | |
| CN113743901A (en) | Cloud online invigilation method, system, equipment and storage medium | |
| CN106920194A (en) | A kind of anti-cheating remote test method | |
| US20200110954A1 (en) | System for characterization of biometric station metrics | |
| Iwasokun et al. | Design of e-invigilation framework using multi-modal biometrics | |
| CN109302413A (en) | A kind of mobile terminal authentication system and method for Behavior-based control feature | |
| CN115174857A (en) | Intelligent examination room monitoring method, system, equipment and storage medium for experimental examination | |
| CN114299569A (en) | Safe face authentication method based on eyeball motion | |
| Rathgeb et al. | Face morphing attacks: a threat to eLearning? | |
| CN113920563A (en) | Online examination cheating identification method and device, computer equipment and storage medium | |
| KR20220009287A (en) | Online test fraud prevention system and method thereof | |
| KR20230017454A (en) | Method, Device and Computer Program For Preventing Cheating In Non-face-to-face Evaluation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190507 |