CN109886378A - Method and apparatus for pushed information - Google Patents
Method and apparatus for pushed information Download PDFInfo
- Publication number
- CN109886378A CN109886378A CN201910164581.5A CN201910164581A CN109886378A CN 109886378 A CN109886378 A CN 109886378A CN 201910164581 A CN201910164581 A CN 201910164581A CN 109886378 A CN109886378 A CN 109886378A
- Authority
- CN
- China
- Prior art keywords
- test state
- sample
- image
- neural network
- testing result
- 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
Abstract
The embodiment of the present application discloses the method, apparatus for pushed information, electronic equipment and computer-readable medium.One specific embodiment of this method includes: to obtain the target image including human face image；The target image is input to test state detection model trained in advance, obtain the test state testing result of the target image, wherein, which is used to characterize the corresponding relationship between the test state testing result of the image and image including human face image；In response to determining that the test state of test state testing result characterization belongs to the first test state, the corresponding user information of human body predetermined position image is determined；The prompt information that characterization belongs to the first test state is pushed to destination client, wherein the prompt information includes identified user information.The embodiment enriches the flexibility of information push.
Description
Technical field
The invention relates to field of computer technology, and in particular to Internet technical field more particularly, to pushes away
It delivers letters the method and apparatus of breath.
Background technique
Existing Invigilating method is usually artificial invigilator, and human cost is higher.
Relevant invigilator's system generallys use the authentications mode such as recognition of face and fingerprint recognition, can replace to avoid other people
The case where examining, but it is limited to be applicable in scene.The state that examinee oneself takes an examination in violation of rules and regulations can not effectively be detected.
Summary of the invention
The embodiment of the present application proposes the method and apparatus for pushed information.
In a first aspect, the embodiment of the present application provides a kind of method for pushed information, this method comprises: acquisition includes
The target image of human face image；Above-mentioned target image is input to test state detection model trained in advance, is obtained
State the test state testing result of target image, wherein above-mentioned test state detection model includes human face figure for characterizing
Corresponding relationship between the image of picture and the test state testing result of image；In response to the above-mentioned test state testing result of determination
The test state of characterization belongs to the first test state, determines the corresponding user information of above-mentioned human body predetermined position image；It will characterization
The prompt information for belonging to the first test state is pushed to destination client, wherein above-mentioned prompt information includes identified user
Information.
In some embodiments, above-mentioned test state further includes cheating state, and above-mentioned cheating state is by detecting examinee
Eye focus whether be detached from examination paper and obtained more than preset duration, the above method further include: in response to detecting the eye of examinee
It is more than preset duration that eyeball focus, which is detached from examination paper, and the prompt information for characterizing the examinee and belonging to cheating state is sent to invigilator client
End, wherein above-mentioned prompt information further includes the identity information of the examinee.
In some embodiments, training obtains above-mentioned test state detection model as follows: sample set is obtained,
In, sample includes the sample image of human body predetermined position image, and sample test state corresponding with sample image detection knot
Fruit；Following training step is executed based on sample set: the sample image of at least one sample in sample set is separately input into just
Beginning neural network obtains the corresponding test state testing result of each sample at least one above-mentioned sample；By it is above-mentioned at least
The corresponding test state testing result of each sample in one sample is compared with corresponding sample test state testing result
Compared with, determine whether above-mentioned initial neural network reaches preset optimization aim according to comparison result, it is above-mentioned initial in response to determination
Neural network reaches above-mentioned optimization aim, the test state detection model that above-mentioned initial neural network is completed as training.
In some embodiments, the step of training obtains above-mentioned test state detection model further include: in response to determining just
Beginning neural network is not up to above-mentioned optimization aim, adjusts the network parameter of initial neural network, and use unworn sample
Sample set is formed, uses initial neural network adjusted as initial neural network, continues to execute above-mentioned training step.
Second aspect, the embodiment of the present application provide a kind of device for pushed information, which includes: to obtain list
Member is configured to obtain the target image including human face image；Input unit is configured to input above-mentioned target image
To test state detection model trained in advance, the test state testing result of above-mentioned target image is obtained, wherein above-mentioned examination
State-detection model is used to characterize corresponding between image and the test state testing result of image including human face image
Relationship；Determination unit is configured in response to determine that the test state of above-mentioned test state testing result characterization belongs to first and examines
Examination state determines the corresponding user information of above-mentioned human body predetermined position image；Push unit, is configured to characterize and belongs to first
The prompt information of test state is pushed to destination client, wherein above-mentioned prompt information includes identified user information.
In some embodiments, above-mentioned test state further includes cheating state, and above-mentioned cheating state is by detecting examinee
Eye focus whether be detached from examination paper and obtained more than preset duration, above-mentioned apparatus further include: transmission unit is configured to respond to
It is more than preset duration in detecting that the eye focus of examinee is detached from examination paper, the examinee will be characterized belongs to the prompt information of cheating state
It is sent to invigilator's client, wherein above-mentioned prompt information further includes the identity information of the examinee.
In some embodiments, training obtains above-mentioned test state detection model as follows: sample set is obtained,
In, sample includes the sample image of human body predetermined position image, and sample test state corresponding with sample image detection knot
Fruit；Following training step is executed based on sample set: the sample image of at least one sample in sample set is separately input into just
Beginning neural network obtains the corresponding test state testing result of each sample at least one above-mentioned sample；By it is above-mentioned at least
The corresponding test state testing result of each sample in one sample is compared with corresponding sample test state testing result
Compared with, determine whether above-mentioned initial neural network reaches preset optimization aim according to comparison result, it is above-mentioned initial in response to determination
Neural network reaches above-mentioned optimization aim, the test state detection model that above-mentioned initial neural network is completed as training.
In some embodiments, the step of training obtains above-mentioned test state detection model further include: in response to determining just
Beginning neural network is not up to above-mentioned optimization aim, adjusts the network parameter of initial neural network, and use unworn sample
Sample set is formed, uses initial neural network adjusted as initial neural network, continues to execute above-mentioned training step.
The third aspect, the embodiment of the present application provide a kind of electronic equipment, which includes: one or more processing
Device；Storage device, for storing one or more programs；When one or more programs are executed by one or more processors, make
Obtain method of the one or more processors realization as described in implementation any in first aspect.
Fourth aspect, the embodiment of the present application provide a kind of computer readable storage medium, are stored thereon with computer journey
Sequence realizes the method as described in implementation any in first aspect when the computer program is executed by processor.
Method and apparatus provided by the embodiments of the present application for pushed information, firstly, obtaining includes human face image
Target image.Then, above-mentioned target image is input to test state detection model trained in advance, obtains above-mentioned target figure
The test state testing result of picture, wherein above-mentioned test state detection model is for characterizing the image including human face image
Corresponding relationship between the test state testing result of image.Later, in response to the above-mentioned test state testing result table of determination
The test state of sign belongs to the first test state, determines the corresponding user information of above-mentioned human body predetermined position image.Finally, by table
The prompt information that sign belongs to the first test state is pushed to destination client, wherein above-mentioned prompt information includes identified use
Family information.Method and apparatus provided by the embodiments of the present application for pushed information can obtain the use in the first test state
The corresponding user information in family.Such as first test state be examinee's violation test state, then can obtain in violation of rules and regulations examination shape
The corresponding identity information of the examinee of state.The available wider application by the way of image detection, and will not be with number
Increase lead to the increase of cost.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application's is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is that the embodiment of the present application can be applied to exemplary system architecture figure therein；
Fig. 2 is the flow chart according to one embodiment of the method for pushed information of the application；
Fig. 3 is the schematic diagram according to an application scenarios of the method for pushed information of the application；
Fig. 4 is the structural schematic diagram according to one embodiment of the device for pushed information of the application；
Fig. 5 is adapted for the structural schematic diagram for the computer system for realizing the electronic equipment of the embodiment of the present application.
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to
Convenient for description, part relevant to related invention is illustrated only in attached drawing.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 is shown can the method for pushed information using the embodiment of the present application or the device for pushed information
Exemplary system architecture 100.
As shown in Figure 1, system architecture 100 may include image collecting device 101,102,103, network 104 and server
105.Network 104 between image collecting device 101,102,103 and server 105 to provide the medium of communication link.Net
Network 104 may include various connection types, such as wired, wireless communication link or fiber optic cables etc..
Image collecting device 101,102,103 can be interacted by network 104 with server 105, to receive instruction or hair
Send message etc..Image collecting device 101,102,103 may include camera and depth camera.
Server 105 can be to provide the server of various services, such as be sent out image collecting device 101,102,103
The information sent parse etc. the background server of processing.Background server can use image collecting device 101,102,103
It is monitored, to obtain target image, acquired target image can also be stored.Server 105 can be to obtaining
The data such as the target image including human body predetermined position image got carry out the processing such as analyzing, and determine in above-mentioned target image
The corresponding user information of human body predetermined position.
It should be noted that server can be hardware, it is also possible to software.When server is hardware, may be implemented
At the distributed server cluster that multiple servers form, individual server also may be implemented into.It, can when server is software
To be implemented as multiple softwares or software module (such as providing Distributed Services), single software or software also may be implemented into
Module.It is not specifically limited herein.
It should be noted that the method provided by the embodiment of the present application for pushed information is generally held by server 105
Row, correspondingly, the device for pushed information is generally positioned in server 105.
It may also be noted that also can have image processing function in image collecting device 101,102,103.At this point,
Server 105 and network 104 can be not present in exemplary system architecture 100.At this point, for pushing away provided by the embodiment of the present application
Deliver letters breath method by image collecting device 101,102,103 execute, correspondingly, the device for pushed information is set to image
In acquisition device 101,102,103.
It should be understood that the number of terminal device, network and server in Fig. 1 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.
With continued reference to Fig. 2, it illustrates the processes according to one embodiment of the method for pushed information of the application
200.This is used for the method for pushed information, comprising the following steps:
Step 201, the target image including human face image is obtained.
It in the present embodiment, can be with for the executing subject of the method for pushed information (such as server 105 shown in FIG. 1)
Obtain the target image including human face image.Above-mentioned target image usually can be including the arbitrary of human face image
Human body image, such as examinee's image etc..One or more electronics that above-mentioned image collecting device can be for acquiring image are set
It is standby, such as camera, depth camera head etc..
It should be noted that above-mentioned executing subject, which can use various modes, obtains target image.As an example, can lead to
The camera collection image being mounted in examination hall is crossed, and the camera and above-mentioned executing subject communicate to connect.Above-mentioned executing subject
The examinee in examination hall can be monitored by the camera.Camera can be with face examinee position, in order to acquire examinee
Examination process video.Here, camera can acquire the video of examination process of the examinee in current slot in real time, and
The collected video of institute is sent to executing subject in real time.
Step 202, target image is input to test state detection model trained in advance, obtains the examination of target image
State-detection result.
In the present embodiment, above-mentioned test state detection model is for characterizing image and image including human face image
Test state testing result between corresponding relationship.Based on target image acquired in step 201, executing subject can be by mesh
Logo image is input to test state detection model trained in advance, to obtain the test state testing result of target image.It examines
Examination state-detection result may include taking an examination in violation of rules and regulations, also may include normally taking an examination.For example, if examinee occurs in examination process
It is more than that preset duration then indicates that examinee is in violation test state that eye focus, which is detached from examination paper,.
In the present embodiment, test state detection model can be artificial neural network, it is from information processing angle to people
Brain neuron network is abstracted, certain naive model is established, and different networks is formed by different connection types.Usually by big
Composition is coupled to each other between the node (or neuron) of amount, a kind of each specific output function of node on behalf referred to as motivates
Function.Connection between every two node all represents a weighted value for passing through the connection signal, and referred to as weight (is called and does
Parameter), the output of network is then different according to the difference of the connection type of network, weighted value and excitation function.Test state detection
Model generally includes multiple layers, and each layer includes multiple nodes, in general, the weight of the node of same layer can be identical, different layers
The weight of node can be different, therefore multiple layers of test state detection model of parameter can also be different.Here, executing subject
Target image can be inputted from the input side of test state detection model, successively by each layer in test state detection model
Parameter processing (such as product, convolution etc.), and from the outlet side of test state detection model export, outlet side output letter
Breath is the test state testing result of target image.
In the present embodiment, test state detection model is for characterizing image and image including human body predetermined position image
Test state testing result between corresponding relationship.Executing subject can be trained in several ways and can be characterized including people
The test state detection model of corresponding relationship between the image of body predetermined position image and the test state testing result of image.
As an example, executing subject can be based on to a large amount of images including examinee's face image and examinee's examination shape
State is counted and generates pair for being stored with the corresponding relationship of multiple images including examinee's face image and examinee's test state
Relation table is answered, and using the mapping table as test state detection model.In this way, executing subject can be by target image and this
Multiple emotional states including examinee's face image in mapping table are successively compared, if one in the mapping table
The emotional state of face image in the emotional state and target image of a image is same or similar, then will be in the mapping table
The image corresponding to test state of examinee's test state as target image.
As another example, executing subject can obtain multiple sample images including examinee's face image and more first
The test state result of sample examinee corresponding to each sample image in a sample image；It then will be in multiple sample images
At least one sample image as input, by sample examinee corresponding at least one sample image in multiple sample images
Test state result as desired output, training obtains test state detection model.Here, executing subject is available multiple
Sample image including examinee's face image, and technical staff is showed, technical staff can be rule of thumb to multiple sample graphs
The test state result of each sample image mark sample examinee as in.Executing subject training can be initialization examination shape
State detection model, initialization test state detection model can be unbred test state detection model or not training completion
Test state detection model, initial parameter has can be set in each layer of the test state detection model of initialization, and parameter is being examined
It tries to be continuously adjusted in the training process of state-detection model.Initialization test state detection model can be various types of
The indiscipline of type or the artificial neural network that training is not completed or the artificial mind that a variety of indisciplines or training is completed
It is combined obtained model through network, for example, initialization test state detection model can be unbred convolution mind
Through network, it is also possible to unbred Recognition with Recurrent Neural Network, can also be to unbred convolutional neural networks, without instruction
Experienced Recognition with Recurrent Neural Network and unbred full articulamentum are combined obtained model.In this way, executing subject can incite somebody to action
Target video is inputted from the input side of test state detection model, successively by the parameter of each layer in test state detection model
Processing, and from the outlet side of test state detection model export, outlet side output information be target examinee examination shape
State result.
In some optional implementations, above-mentioned test state detection model can be above-mentioned executing subject or other
Training is obtained executing subject for training above-mentioned test state detection model in the following manner:
Step S1, available sample set, wherein sample may include the sample image of human body predetermined position image, with
And sample test state testing result corresponding with sample image.
Step S2 can execute following training step based on sample set: it is possible, firstly, to by least one sample in sample set
This sample image is separately input into initial neural network, obtains the corresponding examination of each sample at least one above-mentioned sample
State-detection result.Wherein, above-mentioned initial neural network, which can be, to obtain according to the image for including human body predetermined position image
To the various neural networks of test state testing result, for example, convolutional neural networks, deep neural network etc..Secondly, can be with
The corresponding test state testing result of each sample at least one above-mentioned sample is detected with corresponding sample test state
As a result it is compared.Then, determine whether above-mentioned initial neural network reaches preset optimization aim according to comparison result.As
Example, when the corresponding test state testing result of a sample and the difference between corresponding sample test state testing result are small
When default discrepancy threshold, it is believed that the test state testing result is accurate.At this point, above-mentioned optimization aim can refer to it is above-mentioned
The accuracy rate for the test state testing result that initial neural network generates is greater than preset accuracy rate threshold value.Finally, in response to true
Fixed above-mentioned initial neural network reaches above-mentioned optimization aim, the examination shape that above-mentioned initial neural network can be completed as training
State detection model.
Optionally, training the step of obtaining above-mentioned test state detection model can with the following steps are included:
Step S3, in response to determining, above-mentioned initial neural network is not up to above-mentioned optimization aim, adjustable above-mentioned first
The network parameter of beginning neural network, and sample set is formed using unworn sample, continue to execute above-mentioned training step.As
Example, can using back-propagation algorithm (Back Propgation Algorithm, BP algorithm) and gradient descent method (such as
Small lot gradient descent algorithm) network parameter of above-mentioned initial neural network is adjusted.It should be noted that backpropagation
Algorithm and gradient descent method are the well-known techniques studied and applied extensively at present, and details are not described herein.
Step 203, it in response to determining that the test state of test state testing result characterization belongs to the first test state, determines
The corresponding user information of human body predetermined position image.
In the present embodiment, it is based on the obtained test state testing result of step 202, determines above-mentioned test state detection
Whether the test state as a result characterized belongs to the first test state.Above-mentioned first test state typically refers to violation test state.
For example, occurring indicating that examinee is in examination in violation of rules and regulations if eye focus disengaging examination paper is more than preset duration in examination process if examinee
State.Above-mentioned human body predetermined position image typically refers to face image.By being examined with first above-mentioned test state testing result
Examination state, which is compared, can determine whether the test state of test state testing result characterization belongs to the first test state.Pass through
Recognition of face is carried out to above-mentioned face image, is then searched and face recognition result phase from preset User Information Database
The user information matched may thereby determine that the corresponding user information of face image.User information typically refers to the identity letter of user
Breath, such as the name of examinee, the number etc. of examinee.
Step 204, the prompt information that characterization belongs to the first test state is pushed to destination client, wherein prompt letter
Breath includes identified user information.
In the present embodiment, destination client can be client used in invigilator personnel.Such as first test state
It is the state that examinee takes an examination in violation of rules and regulations, then can reminds invigilator personnel or be responsible for the contact staff of invigilator, to avoids examining in violation of rules and regulations
It is lost caused by examination.
In some optional implementations of the present embodiment, test state can also include cheating state, state of practising fraud
It is whether to be detached from examination paper by the eye focus of detection examinee to obtain more than preset duration, this method can also include: response
It is more than preset duration in detecting that the eye focus of examinee is detached from examination paper, the examinee will be characterized belongs to the prompt information of cheating state
It is sent to invigilator's client.Wherein, prompt information further includes the identity information of the examinee.Above-mentioned preset duration can be according to reality
It is set, this is not restricted.Above-mentioned invigilator's client is usually used by supervisor.By reminding teacher that should examine
Life belongs to cheating state, helps that teacher is assisted to invigilate, invigilator is avoided to omit, and improves invigilator's efficiency, reduces supervisor
Number demand, to reduce the human cost of invigilator.
Method provided by the embodiments of the present application for pushed information, by the target that will include human body predetermined position image
Image is input to test state detection model trained in advance, to obtain the test state testing result of target image.Then
Belong to the first test state in response to the test state of the above-mentioned test state testing result characterization of determination, determines that above-mentioned human body is predetermined
The corresponding user information of position image.Invigilator personnel can be reminded.Such as first test state be examinee in violation of rules and regulations examination state,
Invigilator personnel can then be reminded or be responsible for the contact staff of invigilator, to avoid loss caused by taking an examination in violation of rules and regulations.
With continued reference to the signal that Fig. 3, Fig. 3 are according to the application scenarios of the method for pushed information of the present embodiment
Figure.In the application scenarios of Fig. 3, terminal device 301 obtains the face image 302 of examinee first.Later, terminal device 301 can
Face image 302 is inputted test state detection model 303, the test state testing result for obtaining face image (is examined in violation of rules and regulations
Examination state, for example, cheating state) 304.Finally, terminal device 301 can be in response to determining 304 table of test state testing result
The test state of sign belongs to violation test state, determines the identity information 305 of the corresponding examinee of facial image.Finally, will characterization
The prompt information that the examinee belongs to violation test state is pushed to invigilator's client 306.Wherein, which includes examinee's
Identity information 305.
The method provided by the above embodiment of the application, which realizes, detects the target image for including face image, if
The test state of above-mentioned face image characterization belongs to violation test state, it is determined that the identity of the corresponding examinee of above-mentioned face image
Then information will be prompted to information and be pushed to invigilator's client, can remind invigilator personnel or be responsible for the contact staff of monitoring, from
And avoid loss caused by taking an examination in violation of rules and regulations.
With further reference to Fig. 4, as the realization to method shown in above-mentioned each figure, this application provides one kind for pushing letter
One embodiment of the device of breath, the Installation practice is corresponding with embodiment of the method shown in Fig. 2, which can specifically answer
For in various electronic equipments.
As shown in figure 5, the device 400 for pushed information of the present embodiment includes: acquiring unit 401, input unit
402, determination unit 403 and push unit 404.Wherein, it includes human face that acquiring unit 401, which is configured to obtain,
The target image of image.Input unit 402 is configured to for above-mentioned target image being input to test state detection trained in advance
Model obtains the test state testing result of above-mentioned target image, wherein above-mentioned test state detection model, which is used to characterize, includes
Corresponding relationship between the image of human face image and the test state testing result of image.Determination unit 403 is configured to
Belong to the first test state in response to the test state of the above-mentioned test state testing result characterization of determination, determines that above-mentioned human body is predetermined
The corresponding user information of position image.Push unit 404, the prompt information for being configured to belong to characterization the first test state push away
Give destination client, wherein above-mentioned prompt information includes identified user information.
In the present embodiment, for the acquiring unit 401 of the device of pushed information 400, input unit 402, determination unit
403 and push unit 404 specific processing and its brought technical effect can be respectively with reference to step in Fig. 2 corresponding embodiment
201, the related description of step 202, step 203 and step 204, details are not described herein.
In some optional implementations of the present embodiment, above-mentioned apparatus can also include that transmission unit (does not show in figure
Out), it is configured in response to detect that the eye focus of examinee is detached from examination paper to be more than preset duration, the examinee will be characterized and belong to work
The prompt information of disadvantage state is sent to invigilator's client.Wherein, above-mentioned prompt information further includes the identity information of the examinee.It is above-mentioned
Test state further includes cheating state, and it is more than pre- that above-mentioned cheating state, which is by detecting the eye focus of examinee whether to be detached from examination paper,
What if duration obtained.
In some optional implementations of the present embodiment, above-mentioned test state detection model is trained as follows
It obtains: obtaining sample set, wherein sample includes the sample image of human body predetermined position image, and corresponding with sample image
Sample test state testing result；Following training step is executed based on sample set: by the sample of at least one sample in sample set
This image is separately input into initial neural network, obtains the corresponding test state inspection of each sample at least one above-mentioned sample
Survey result；The corresponding test state testing result of each sample and corresponding sample at least one above-mentioned sample is taken an examination shape
State testing result is compared, and determines whether above-mentioned initial neural network reaches preset optimization aim according to comparison result, is rung
Above-mentioned optimization aim should be reached in determining above-mentioned initial neural network, the examination that above-mentioned initial neural network is completed as training
State-detection model.
In some optional implementations of the present embodiment, the step of obtaining above-mentioned test state detection model is trained also
Include: to be not up to above-mentioned optimization aim in response to the initial neural network of determination, adjusts the network parameter of initial neural network, and
Sample set is formed using unworn sample, uses initial neural network adjusted as initial neural network, continues to execute
Above-mentioned training step.
Below with reference to Fig. 5, it illustrates the computer systems 500 for the server for being suitable for being used to realize the embodiment of the present application
Structural schematic diagram.Server shown in Fig. 5 is only an example, should not function and use scope band to the embodiment of the present application
Carry out any restrictions.
As shown in figure 5, computer system 500 includes central processing unit (CPU) 501, it can be read-only according to being stored in
Program in memory (ROM) 502 or be loaded into the program in random access storage device (RAM) 503 from storage section 508 and
Execute various movements appropriate and processing.In RAM 503, also it is stored with system 500 and operates required various programs and data.
CPU 501, ROM 502 and RAM 503 are connected with each other by bus 504.Input/output (I/O) interface 505 is also connected to always
Line 504.
I/O interface 505 is connected to lower component: the importation 506 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 507 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage section 508 including hard disk etc.；
And the communications portion 509 of the network interface card including LAN card, modem etc..Communications portion 509 via such as because
The network of spy's net executes communication process.Driver 510 is also connected to I/O interface 505 as needed.Detachable media 511, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 510, in order to read from thereon
Computer program be mounted into storage section 508 as needed.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed from network by communications portion 509, and/or from detachable media
511 are mounted.When the computer program is executed by central processing unit (CPU) 501, limited in execution the present processes
Above-mentioned function.
It should be noted that the computer-readable medium of the application can be computer-readable signal media or computer
Readable storage medium storing program for executing either the two any combination.Computer readable storage medium for example can be --- but it is unlimited
In system, device or the device of --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, or any above combination.It calculates
The more specific example of machine readable storage medium storing program for executing can include but is not limited to: have the electrical connection, portable of one or more conducting wires
Formula computer disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable programmable read only memory
(EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device or
The above-mentioned any appropriate combination of person.In this application, computer readable storage medium can be it is any include or storage program
Tangible medium, which can be commanded execution system, device or device use or in connection.And in this Shen
Please in, computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
In carry computer-readable program code.The data-signal of this propagation can take various forms, including but not limited to
Electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer-readable
Any computer-readable medium other than storage medium, the computer-readable medium can send, propagate or transmit for by
Instruction execution system, device or device use or program in connection.The journey for including on computer-readable medium
Sequence code can transmit with any suitable medium, including but not limited to: wireless, electric wire, optical cable, RF etc. are above-mentioned
Any appropriate combination.
The calculating of the operation for executing the application can be write with one or more programming languages or combinations thereof
Machine program code, above procedure design language include object-oriented programming language-such as Java, Smalltalk, C+
+, further include conventional procedural programming language-such as " C " language or similar programming language.Program code can
Fully to execute, partly execute on the user computer on the user computer, be executed as an independent software package,
Part executes on the remote computer or executes on a remote computer or server completely on the user computer for part.
In situations involving remote computers, remote computer can pass through the network of any kind --- including local area network (LAN)
Or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as utilize Internet service
Provider is connected by internet).
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the application, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of the module, program segment or code include one or more use
The executable instruction of the logic function as defined in realizing.It should also be noted that in some implementations as replacements, being marked in box
The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually
It can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it to infuse
Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding
The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in the embodiment of the present application can be realized by way of software, can also be by hard
The mode of part is realized.Described unit also can be set in the processor, for example, can be described as: a kind of processor, packet
Include acquiring unit, input unit, determination unit and push unit.Wherein, the title of these units not structure under certain conditions
The restriction of the pairs of unit itself, for example, acquiring unit is also described as " obtaining the target figure including human face image
The unit of picture ".
As on the other hand, present invention also provides a kind of computer-readable medium, which be can be
Included in device described in above-described embodiment；It is also possible to individualism, and without in the supplying device.Above-mentioned calculating
Machine readable medium carries one or more program, when said one or multiple programs are executed by the device, so that should
Device: the target image including human face image is obtained；The target image is input to test state detection trained in advance
Model obtains the test state testing result of the target image, wherein the test state detection model includes human body for characterizing
Corresponding relationship between the image of face image and the test state testing result of image；In response to determining test state detection
As a result the test state characterized belongs to the first test state, determines the corresponding user information of human body predetermined position image；By table
The prompt information that sign belongs to the first test state is pushed to destination client, wherein the prompt information includes identified user
Information.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.Those skilled in the art
Member is it should be appreciated that invention scope involved in the application, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from foregoing invention design, it is carried out by above-mentioned technical characteristic or its equivalent feature
Any combination and the other technical solutions formed.Such as features described above has similar function with (but being not limited to) disclosed herein
Can technical characteristic replaced mutually and the technical solution that is formed.
Claims (10)
1. a kind of method for pushed information, comprising:
Obtain the target image including human face image；
The target image is input to test state detection model trained in advance, obtains the test state of the target image
Testing result, wherein the test state detection model is used to characterize the examination of image and image including human face image
Corresponding relationship between state-detection result；
Belong to the first test state in response to the test state of the determination test state testing result characterization, determines the human body
The corresponding user information of predetermined position image；
The prompt information that characterization belongs to the first test state is pushed to destination client, wherein the prompt information includes institute
Determining user information.
2. the cheating state is according to the method described in claim 1, wherein, the test state further includes cheating state
Whether the eye focus by detecting examinee is detached from what examination paper was obtained more than preset duration, the method also includes:
It is more than preset duration in response to detecting that the eye focus of examinee is detached from examination paper, the examinee will be characterized and belong to cheating state
Prompt information is sent to invigilator's client, wherein the prompt information further includes the identity information of the examinee.
3. method described in one of -2 according to claim 1, wherein the test state detection model is trained as follows
It obtains:
Obtain sample set, wherein sample includes the sample image of human body predetermined position image, and sample corresponding with sample image
This test state testing result；
Following training step is executed based on sample set: the sample image of at least one sample in sample set is separately input into just
Beginning neural network obtains the corresponding test state testing result of each sample at least one described sample；By described at least
The corresponding test state testing result of each sample in one sample is compared with corresponding sample test state testing result
Compared with determining whether initial neural network reaches preset optimization aim according to comparison result, in response to the initial neural network of determination
Reach the optimization aim, the test state detection model that initial neural network is completed as training.
4. according to the method described in claim 3, wherein, training the step of obtaining the test state detection model further include:
It is not up to the optimization aim in response to the initial neural network of determination, adjusts the network parameter of initial neural network, and
Sample set is formed using unworn sample, uses initial neural network adjusted as initial neural network, continues to execute
The training step.
5. a kind of device for pushed information, comprising:
Acquiring unit is configured to obtain the target image including human face image；
Input unit is configured to for the target image being input to test state detection model trained in advance, obtains described
The test state testing result of target image, wherein the test state detection model includes human face image for characterizing
Image and image test state testing result between corresponding relationship；
Determination unit is configured in response to determine that the test state of the test state testing result characterization belongs to the first examination
State determines the corresponding user information of the human body predetermined position image；
Push unit, the prompt information for being configured to belong to characterization the first test state are pushed to destination client, wherein institute
Stating prompt information includes identified user information.
6. device according to claim 5, wherein the test state further includes cheating state, and the cheating state is
Whether the eye focus by detecting examinee is detached from what examination paper was obtained more than preset duration, described device further include:
Transmission unit is configured in response to detect that the eye focus of examinee is detached from examination paper to be more than preset duration, should by characterization
The prompt information that examinee belongs to cheating state is sent to invigilator's client, wherein the prompt information further includes the body of the examinee
Part information.
7. the device according to one of claim 5-6, wherein the test state detection model is trained as follows
It obtains:
Obtain sample set, wherein sample includes the sample image of human body predetermined position image, and sample corresponding with sample image
This test state testing result；
Following training step is executed based on sample set: the sample image of at least one sample in sample set is separately input into just
Beginning neural network obtains the corresponding test state testing result of each sample at least one described sample；By described at least
The corresponding test state testing result of each sample in one sample is compared with corresponding sample test state testing result
Compared with determining whether initial neural network reaches preset optimization aim according to comparison result, in response to the initial neural network of determination
Reach the optimization aim, the test state detection model that initial neural network is completed as training.
8. device according to claim 7, wherein the step of training obtains the test state detection model further include:
It is not up to the optimization aim in response to the initial neural network of determination, adjusts the network parameter of initial neural network, and
Sample set is formed using unworn sample, uses initial neural network adjusted as initial neural network, continues to execute
The training step.
9. a kind of electronic equipment, comprising:
One or more processors；
Storage device, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The now method as described in any in claim 1-4.
10. a kind of computer readable storage medium, is stored thereon with computer program, wherein the computer program is processed
The method as described in any in claim 1-4 is realized when device executes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910164581.5A CN109886378A (en) | 2019-03-05 | 2019-03-05 | Method and apparatus for pushed information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910164581.5A CN109886378A (en) | 2019-03-05 | 2019-03-05 | Method and apparatus for pushed information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109886378A true CN109886378A (en) | 2019-06-14 |
Family
ID=66930759
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910164581.5A Pending CN109886378A (en) | 2019-03-05 | 2019-03-05 | Method and apparatus for pushed information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109886378A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110942033A (en) * | 2019-11-28 | 2020-03-31 | 重庆中星微人工智能芯片技术有限公司 | Method, apparatus, electronic device and computer medium for pushing information |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102799893A (en) * | 2012-06-15 | 2012-11-28 | 北京理工大学 | Method for processing monitoring video in examination room |
| CN108304794A (en) * | 2018-01-26 | 2018-07-20 | 安徽爱学堂教育科技有限公司 | cheating automatic identifying method and device |
-
2019
- 2019-03-05 CN CN201910164581.5A patent/CN109886378A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102799893A (en) * | 2012-06-15 | 2012-11-28 | 北京理工大学 | Method for processing monitoring video in examination room |
| CN108304794A (en) * | 2018-01-26 | 2018-07-20 | 安徽爱学堂教育科技有限公司 | cheating automatic identifying method and device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110942033A (en) * | 2019-11-28 | 2020-03-31 | 重庆中星微人工智能芯片技术有限公司 | Method, apparatus, electronic device and computer medium for pushing information |
| CN110942033B (en) * | 2019-11-28 | 2023-05-26 | 重庆中星微人工智能芯片技术有限公司 | Method, device, electronic equipment and computer medium for pushing information |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109919079A (en) | Method and apparatus for detecting learning state | |
| CN108509941B (en) | Emotion information generation method and device | |
| CN109145781B (en) | Method and apparatus for processing image | |
| CN108197532B (en) | The method, apparatus and computer installation of recognition of face | |
| CN109002842A (en) | Image-recognizing method and device | |
| CN108985208A (en) | The method and apparatus for generating image detection model | |
| CN108446651A (en) | Face identification method and device | |
| CN111241883B (en) | Method and device for preventing cheating of remote tested personnel | |
| CN108875546A (en) | Face auth method, system and storage medium | |
| CN109086719A (en) | Method and apparatus for output data | |
| CN109308490A (en) | Method and apparatus for generating information | |
| CN109492128A (en) | Method and apparatus for generating model | |
| CN109887077B (en) | Method and apparatus for generating three-dimensional model | |
| CN109446990A (en) | Method and apparatus for generating information | |
| CN110363067A (en) | Auth method and device, electronic equipment and storage medium | |
| CN109086780A (en) | Method and apparatus for detecting electrode piece burr | |
| JP6930277B2 (en) | Presentation device, presentation method, communication control device, communication control method and communication control system | |
| CN108509888B (en) | Method and apparatus for generating information | |
| CN108511066A (en) | information generating method and device | |
| CN110060441A (en) | Method and apparatus for terminal anti-theft | |
| CN110263748A (en) | Method and apparatus for sending information | |
| CN108171208A (en) | Information acquisition method and device | |
| CN108449514A (en) | Information processing method and device | |
| CN108133197A (en) | For generating the method and apparatus of information | |
| CN108399401B (en) | Method and device for detecting face image |
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 |
Application publication date: 20190614 |
|
| RJ01 | Rejection of invention patent application after publication |