CN109766766A - Employee work condition monitoring method, device, computer equipment and storage medium - Google Patents
Employee work condition monitoring method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109766766A CN109766766A CN201811546642.6A CN201811546642A CN109766766A CN 109766766 A CN109766766 A CN 109766766A CN 201811546642 A CN201811546642 A CN 201811546642A CN 109766766 A CN109766766 A CN 109766766A
- Authority
- CN
- China
- Prior art keywords
- employee
- micro
- obtains
- history
- training set
- 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
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000012544 monitoring process Methods 0.000 title claims abstract description 15
- 230000001815 facial effect Effects 0.000 claims abstract description 126
- 239000013598 vector Substances 0.000 claims abstract description 109
- 230000008451 emotion Effects 0.000 claims abstract description 103
- 238000012549 training Methods 0.000 claims description 124
- 238000003066 decision tree Methods 0.000 claims description 26
- 238000004590 computer program Methods 0.000 claims description 25
- 238000005070 sampling Methods 0.000 claims description 16
- 239000003086 colorant Substances 0.000 claims description 13
- 238000012806 monitoring device Methods 0.000 claims description 8
- 238000013473 artificial intelligence Methods 0.000 abstract 1
- 238000010801 machine learning Methods 0.000 abstract 1
- 230000002996 emotional effect Effects 0.000 description 10
- 238000004422 calculation algorithm Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 230000008859 change Effects 0.000 description 6
- 238000001514 detection method Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000007637 random forest analysis Methods 0.000 description 4
- 210000004709 eyebrow Anatomy 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000036651 mood Effects 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 235000015096 spirit Nutrition 0.000 description 2
- 206010054196 Affect lability Diseases 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
This application involves the machine learning in artificial intelligence, a kind of employee work condition monitoring method, device, computer equipment and storage medium are provided.This method comprises: employee work video is obtained, every preset duration from employee work video intercepting video pictures；Employee's facial image is obtained according to video pictures, corresponding employee identification is determined according to employee's facial image；Micro- expressive features are obtained according to employee's facial image, micro- expressive features are inputted in the micro- Expression Recognition model trained and are identified, micro- expression output feature is obtained, feature is exported according to micro- expression and obtains corresponding micro- expression；The corresponding Employees'Emotions state of employee identification is determined according to micro- expression, Employees'Emotions state vector is obtained according to Employees'Emotions state, in the risk warning model that the input of Employees'Emotions state vector has been trained, obtains risk output vector；The Risk-warning grade of employee identification is obtained according to risk output vector.Efficiency and accuracy can be improved using this method.
Description
Technical field
This application involves Internet technical fields, more particularly to a kind of employee work condition monitoring method, device, calculating
Machine equipment and storage medium.
Background technique
In the staff's benefits of current enterprise, it is less able to be concerned about the emotional change of each employee.Enterprise staff is often
Because operating pressure leads to emotional change, so that labor turnover or other accidents be made to occur, make talent drain in corporations, shadow
Ring the normal production and operation of enterprise.Usual enterprise links up to understand employee work merely by interval time for a long time face-to-face
Situation, can not recognize the working condition of employee in real time, inefficiency, and also can not be accurate by linking up face-to-face
The emotional change of employee is solved, accuracy is low.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of employee work that can be improved efficiency and accuracy
Condition monitoring method, device, computer equipment and storage medium.
A kind of employee work condition monitoring method, which comprises
Employee work video is obtained, every preset duration from the employee work video intercepting video pictures；
Employee's facial image is obtained according to the video pictures, determines that corresponding employee marks according to employee's facial image
Know；
Micro- expressive features are obtained according to employee's facial image, micro- expressive features are inputted into the micro- expression trained
It is identified in identification model, obtains micro- expression output feature, corresponding micro- expression is obtained according to micro- expression output feature；
The corresponding Employees'Emotions state of the employee identification is determined according to micro- expression, according to the Employees'Emotions state
Employees'Emotions state vector is obtained, in the risk warning model that Employees'Emotions state vector input has been trained, obtains wind
Dangerous output vector；
The Risk-warning grade of the employee identification is obtained according to the risk output vector.
It is described in one of the embodiments, to obtain employee's facial image according to the video pictures, according to the employee
Facial image determines corresponding employee identification, comprising:
Facial image in the video pictures is detected, employee's facial image is obtained；
Employee's face characteristic information is determined according to employee's facial image, calculates employee's face characteristic information and pre-
If the similarity of employee's facial image；
When the similarity is greater than preset threshold, the corresponding employee identification of default employee's facial image is obtained.
It is described in one of the embodiments, that employee's face characteristic information is determined according to employee's facial image, it calculates
The similarity of employee's face characteristic information and default employee's facial image, comprising:
Employee's facial image is divided, target facial image is obtained, is corresponded to according to the target facial image
Features of skin colors information, contour feature information, texture feature information and area features information；
Calculate the features of skin colors information, contour feature information, texture feature information and area features information and default member
The similarity of worker's face image.
The generation step of micro- Expression Recognition model in one of the embodiments, comprising:
History interviewee video and the corresponding micro- expression label of history interviewee's video are obtained, original training set is obtained；
It puts back to sampling at random from the original training set, obtains target training set；
The corresponding micro- expressive features collection of history is obtained according to the target training set, according to the micro- expressive features collection of the history
Obtain the micro- expressive features collection of target；
It is obtained dividing expressive features according to the micro- expressive features collection of the target, using the division expressive features to the mesh
Mark training set is divided, and sub- training set is obtained, using the sub- training set as target training set；
It returns and the corresponding micro- expressive features collection of history is obtained according to the target training set, it is special according to the micro- expression of the history
Collection obtains the execution of the step of target micro- expressive features collection and obtains objective decision tree when reaching preset condition；
Return the step of putting back to sampling at random from the original training set, obtaining target training set execution, when reaching
When the objective decision tree of preset number, micro- Expression Recognition model is obtained.
The generation step of the risk warning model in one of the embodiments, comprising:
History Employees'Emotions state and corresponding historical risk warning grade are obtained, according to the history Employees'Emotions state
History Employees'Emotions state vector is obtained, historical risk output vector is obtained according to the historical risk warning grade；
Using the historical risk output vector as label, patrolled the history Employees'Emotions state vector as input
It collects and is trained in regression model, when reaching preset condition, obtain the risk warning model.
A kind of employee work condition monitoring device, described device include:
Picture interception module, for obtaining employee work video, every preset duration from the employee work video intercepting
Video pictures；
Determining module is identified, for obtaining employee's facial image according to the video pictures, according to employee's face figure
As determining corresponding employee identification；
Micro- Expression Recognition module, it is for obtaining micro- expressive features according to employee's facial image, micro- expression is special
It is identified in micro- Expression Recognition model that sign input has been trained, obtains micro- expression output feature, exported according to micro- expression
Feature obtains corresponding micro- expression；
Output obtains module, for determining the corresponding Employees'Emotions state of the employee identification, root according to micro- expression
Employees'Emotions state vector is obtained according to the Employees'Emotions state, the Employees'Emotions state vector is inputted to the risk trained
In Early-warning Model, risk output vector is obtained；
Grade obtains module, for obtaining the Risk-warning grade of the employee identification according to the risk output vector.
Described device in one of the embodiments, further include:
Initial sample obtains module, for obtaining history interviewee video and the corresponding micro- expression mark of history interviewee's video
Label, obtain original training set；
Training set obtains module, for putting back to sampling at random from the original training set, obtains target training set；
Feature set obtains module, for obtaining the corresponding micro- expressive features collection of history according to the target training set, according to
The micro- expressive features collection of history obtains the micro- expressive features collection of target；
Sub- training set obtains module, divides expressive features for obtaining according to the micro- expressive features collection of the target, uses institute
It states division expressive features to divide the target training set, obtains sub- training set, instructed the sub- training set as target
Practice collection；
Decision tree obtains module, obtains the corresponding micro- expressive features collection of history according to the target training set for returning,
The step of obtaining target micro- expressive features collection according to the micro- expressive features collection of history execution is obtained when reaching preset condition
Objective decision tree；
Model obtains module, puts back to sampling at random from the original training set for returning, obtains target training set
The step of execute, when reaching the objective decision tree of preset number, obtain micro- Expression Recognition model.
Described device in one of the embodiments, further include:
History vectors obtain module, for obtaining history Employees'Emotions state and corresponding historical risk warning grade, root
History Employees'Emotions state vector is obtained according to the history Employees'Emotions state, is gone through according to the historical risk warning grade
History risk output vector；
Model training module is used for using the historical risk output vector as label, by the history Employees'Emotions shape
State vector is trained in Logic Regression Models as input, when reaching preset condition, obtains the risk warning model.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device performs the steps of when executing the computer program
Employee work video is obtained, every preset duration from the employee work video intercepting video pictures；
Employee's facial image is obtained according to the video pictures, determines that corresponding employee marks according to employee's facial image
Know；
Micro- expressive features are obtained according to employee's facial image, micro- expressive features are inputted into the micro- expression trained
It is identified in identification model, obtains micro- expression output feature, corresponding micro- expression is obtained according to micro- expression output feature；
The corresponding Employees'Emotions state of the employee identification is determined according to micro- expression, according to the Employees'Emotions state
Employees'Emotions state vector is obtained, in the risk warning model that Employees'Emotions state vector input has been trained, obtains wind
Dangerous output vector；
The Risk-warning grade of the employee identification is obtained according to the risk output vector.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
It is performed the steps of when row
Employee work video is obtained, every preset duration from the employee work video intercepting video pictures；
Employee's facial image is obtained according to the video pictures, determines that corresponding employee marks according to employee's facial image
Know；
Micro- expressive features are obtained according to employee's facial image, micro- expressive features are inputted into the micro- expression trained
It is identified in identification model, obtains micro- expression output feature, corresponding micro- expression is obtained according to micro- expression output feature；
The corresponding Employees'Emotions state of the employee identification is determined according to micro- expression, according to the Employees'Emotions state
Employees'Emotions state vector is obtained, in the risk warning model that Employees'Emotions state vector input has been trained, obtains wind
Dangerous output vector；
The Risk-warning grade of the employee identification is obtained according to the risk output vector.
Above-mentioned employee work condition monitoring method, device, computer equipment and storage medium obtain employee work video,
Every preset duration from the employee work video intercepting video pictures；Employee's facial image is obtained according to the video pictures,
Corresponding employee identification is determined according to employee's facial image；Micro- expressive features are obtained according to employee's facial image, it will
It is identified in micro- Expression Recognition model that micro- expressive features input has been trained, micro- expression output feature is obtained, according to institute
It states micro- expression output feature and obtains corresponding micro- expression；The corresponding Employees'Emotions of the employee identification are determined according to micro- expression
State obtains Employees'Emotions state vector according to the Employees'Emotions state, and Employees'Emotions state vector input has been instructed
In experienced risk warning model, risk output vector is obtained；The wind of the employee identification is obtained according to the risk output vector
Dangerous warning grade.Micro- expression is identified by employee's facial image, the corresponding Employees'Emotions state of micro- expression is obtained, according to employee's feelings
Not-ready status obtains the Risk-warning grade of employee, can monitor employee work situation in real time and obtain Risk-warning grade, improves
Efficiency and accuracy.
Detailed description of the invention
Fig. 1 is the application scenario diagram of employee work condition monitoring method in one embodiment；
Fig. 2 is the flow diagram of employee work condition monitoring method in one embodiment；
Fig. 3 is to obtain the flow diagram of employee identification in one embodiment；
Fig. 4 is the flow diagram of similarity calculation in one embodiment；
Fig. 5 is to obtain the flow diagram of micro- Expression Recognition model in one embodiment；
Fig. 6 is to obtain the flow diagram of risk warning model in one embodiment；
Fig. 7 is the structural block diagram of employee work condition monitoring device in one embodiment；
Fig. 8 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.
Employee work condition monitoring method provided by the present application, can be applied in application environment as shown in Figure 1.Its
In, video acquisition device 102 is communicated by network with server 104.It is real that server 104 obtains video acquisition device 102
When the employee work video that acquires, every preset duration from employee work video intercepting video pictures；Server 104 is according to video
Picture obtains employee's facial image, determines corresponding employee identification according to employee's facial image；Server 104 is according to employee's face
Image obtains micro- expressive features, and micro- expressive features are inputted in the micro- Expression Recognition model trained and are identified, micro- table is obtained
Feelings export feature, export feature according to micro- expression and obtain corresponding micro- expression；Server 104 determines employee identification according to micro- expression
Corresponding Employees'Emotions state obtains Employees'Emotions state vector according to Employees'Emotions state, and Employees'Emotions state vector is defeated
Enter in the risk warning model trained, obtains risk output vector；Server 104 obtains employee's mark according to risk output vector
The Risk-warning grade of knowledge.Wherein, video acquisition device 102 can be, but not limited to be various personal computers, laptop,
Smart phone, tablet computer and camera, server 104 can use the clothes of the either multiple server compositions of independent server
Device cluster be engaged in realize.
In one embodiment, it as shown in Fig. 2, providing a kind of employee work condition monitoring method, applies in this way
It is illustrated for server in Fig. 1, comprising the following steps:
S202 obtains employee work video, every preset duration from employee work video intercepting video pictures.
Specifically, video acquisition device acquires employee work video, and sends the employee work video collected to
Server, server get employee work video, every preset duration from the employee work video intercepting video frame, depending on
Frequency picture.Wherein, video acquisition device for acquiring video in real time.Preset time can be the time span pre-set,
For example video pictures were obtained from the employee work video intercepting video frame every 5 seconds.
S204, obtains employee's facial image according to video pictures, determines corresponding employee identification according to employee's facial image.
Wherein, employee identification is for identifying employee.
Specifically, server obtains employee's face figure according to video pictures user face detection algorithm from the video pictures
Picture, server determine corresponding employee identification according to employee's facial image, i.e., carry out recognition of face, root according to employee's facial image
The corresponding employee identification of employee's facial image is obtained according to recognition result.
S206 obtains micro- expressive features according to employee's facial image, and micro- expression that the input of micro- expressive features has been trained is known
It is identified in other model, obtains micro- expression output feature, feature is exported according to micro- expression and obtains corresponding micro- expression.
Wherein, micro- Expression Recognition model is according to the video pictures and the video pictures intercepted in history employee work video
What the corresponding micro- expression of history was trained using random forests algorithm.
Specifically, server obtains micro- expressive features according to employee's facial image, and micro- expressive features are input to and have been trained
Micro- Expression Recognition model in identified to obtain micro- expression output feature, feature is exported according to micro- expression and presets micro- expression
Corresponding relationship obtains micro- expression and exports the corresponding micro- expression of feature.
S208 determines the corresponding Employees'Emotions state of employee identification according to micro- expression, according to the Employees'Emotions state person of obtaining
Employees'Emotions state vector is inputted in the risk warning model trained, obtains risk output vector by work emotional state vector.
Wherein, risk warning model is to be returned according to history Employees'Emotions state and corresponding Risk-warning grade using logic
Reduction method is trained, and is also possible to be trained using neural network algorithm.
Specifically, server determines the corresponding Employees'Emotions state of employee identification according to micro- expression, at available one section
Between content Employees'Emotions state change, such as the Employees'Emotions state change in one day or in three days.According to Employees'Emotions
State obtains Employees'Emotions state vector, can be obtained according to the variation of Employees'Emotions state Employees'Emotions state change to
Employees'Emotions state vector is inputted in the risk warning model trained, obtains risk output vector by amount.Such as: in one day
The Employees'Emotions state in morning be that No. 12 moods are brightened up, noon when, is steady and calm for No. 14 moods, afternoon when
Waiting is that No. 16 moods are in high spirits, then obtains the emotional state vector [12,14,16] of employee in this day.By the emotional state
Vector is input in the risk warning model trained, and obtained risk output vector is [0,0,0,0,1].
S210 obtains the Risk-warning grade of employee identification according to risk output vector.
Wherein, Risk-warning grade is can be divided into 5 grades for reflecting that the risk class of employee work situation carries out early warning
Including it is normal, compared with low-risk, low-risk, risk and high risk.
Specifically, the corresponding relationship between risk output vector and Risk-warning grade is pre-set, then server
The Risk-warning grade of the corresponding employee identification of risk output vector is obtained according to corresponding relationship.When Risk-warning grade is height
When risk class, start advanced early warning, server sends the prompt such as early warning mail messaging phone to management terminal immediately, so that enterprise
Industry administrative staff are handled in time.When Risk-warning grade is risk, e-mail alert is sent to management terminal.For example,
When it is pre- to obtain risk according to the corresponding relationship pre-set for [0,0,0,0,1] for the risk output vector for obtaining an employee
Alert grade is high-risk grade, illustrates that the staff pressure is too big, emotional instability, it should carry out communication guidance immediately, avoid sending out
The accidents such as raw leaving office.
In above-mentioned employee work condition monitoring method, by obtaining employee work video, every preset duration from employee's work
Make video intercepting video pictures.Employee's facial image is obtained according to video pictures, corresponding member is determined according to employee's facial image
Work mark.Micro- expressive features are obtained according to employee's facial image, micro- expressive features are inputted to the micro- Expression Recognition model trained
In identified, obtain micro- expression output feature, feature exported according to micro- expression and obtains corresponding micro- expression.It is true according to micro- expression
Determine the corresponding Employees'Emotions state of employee identification, Employees'Emotions state vector is obtained according to Employees'Emotions state, by Employees'Emotions
In the risk warning model that state vector input has been trained, risk output vector is obtained.Employee is obtained according to risk output vector
The Risk-warning grade of mark can monitor employee work situation in real time and obtain Risk-warning grade, improve efficiency and standard
True property.
In one embodiment, as shown in figure 3, step S204, obtains employee's facial image according to video pictures, according to member
Worker's face image determines corresponding employee identification, comprising steps of
S302 detects facial image in video pictures, obtains employee's facial image.
Specifically, server carries out face inspection using AdaBoost (Adaptive Boosting, adaptive to enhance) algorithm
It surveys, obtains employee's facial image.Wherein, AdaBoost algorithm is a kind of iterative algorithm, and core concept is for the same instruction
Practice the different classifier of collection training, then these weak classifier sets are got up, constitute a stronger final classification device, most
Afterwards, Face datection is carried out using final classifier.
S304 determines employee's face characteristic information according to employee's facial image, counter's work face characteristic information and default
The similarity of employee's facial image.
Wherein, employee's face characteristic information is used to reflect the specifying information of employee's facial image.
Specifically, server determines employee's face characteristic information, counter's work face characteristic letter according to employee's facial image
The similarity of breath and default employee's facial image.Wherein, employee's facial image, the member of the preservation have been pre-saved in the server
Worker's face image is corresponding with employee identification.
S306 obtains the corresponding employee identification of employee's facial image when similarity is greater than preset threshold.
Specifically, it when employee's face characteristic information and the similarity of default employee's facial image are greater than preset threshold, says
It is bright to have identified the corresponding default employee's facial image of employee's facial image, at this point, corresponding according to default employee's facial image
Employee identification.
In the above-described embodiments, by facial image in detection video pictures, employee's facial image is obtained, according to employee people
Face image determines employee's face characteristic information, the similarity of counter's work face characteristic information and default employee's facial image, when
When similarity is greater than preset threshold, the default corresponding employee identification of employee's facial image is obtained.It is intercepted by recognition of face
Image in the corresponding employee identification of facial image, meet demand improves efficiency.
In one embodiment, as shown in figure 4, step S304, i.e., determine employee's face characteristic according to employee's facial image
Information, the similarity of counter's work face characteristic information and default employee's facial image, comprising steps of
S402 divides employee's facial image, obtains target facial image, obtains corresponding skin according to target facial image
Color characteristic information, contour feature information, texture feature information and area features information.
Wherein, target facial image refers to the partial face image obtained after division.
Specifically, server divides employee's facial image, it is divided into multiple localized masses interconnected, Mei Geju
Portion's block.Obtain the corresponding features of skin colors information of each localized mass, contour feature information, texture feature information and area features letter
Breath.
S404 calculates features of skin colors information, contour feature information, texture feature information and area features information and default member
The similarity of worker's face image.
Specifically, server according to the features of skin colors information of each localized mass, contour feature information, texture feature information and
Area features information calculates the similarity with default employee's facial image, obtains the similarity with default employee's facial image.Its
In, similarity calculation can be used Euclidean distance algorithm,
By dividing employee's facial image, target facial image is obtained, corresponding skin is obtained according to target facial image
Color characteristic information, contour feature information, texture feature information and area features information calculate features of skin colors information, contour feature
The similarity of information, texture feature information and area features information and default employee's facial image, by calculating target face figure
As the similarity with employee's facial image, the accuracy for the similarity that energy ditch improves.
In one embodiment, as shown in figure 5, the generation step of micro- Expression Recognition model, comprising steps of
S502 obtains history interviewee video and the corresponding micro- expression label of history interviewee's video, obtains initial sample
Collection.
Micro- expression label refers to the mark of the corresponding micro- expression of video frame in history interviewee's video at interval of preset duration
Label.
Specifically, server gets micro- expression label in history interviewee video and history interviewee's video, will go through
The corresponding video pictures of video frame micro- expression label corresponding with the video pictures in history interviewee's video is as initial sample
Collection.
S504 puts back to sampling at random from original training set, obtains target training set.
S506 obtains the corresponding micro- expressive features collection of history according to target training set, is obtained according to the micro- expressive features collection of history
To the micro- expressive features collection of target.
Wherein, target training set refers to the set that the sample randomly selected from original training set obtains.Micro- expressive features
Collection refers to the set being made of micro- expressive features, is extracted by the video pictures in history video.
Specifically, server first puts back to sampling at random from original training set, obtains target training set.Server according to
At interval of the video pictures of preset duration in history employee work video in target training set, the member that Face datection obtains is carried out
Work face picture obtains the micro- expressive features of history according to employee's face picture, is gone through according to the micro- expressive features of obtained history
Then the micro- expressive features collection of history chooses any number of feature from the micro- expressive features concentration of history in one's power and obtains the micro- expression spy of target
Collection.
S508 obtains dividing expressive features according to the micro- expressive features collection of target, is trained using expressive features are divided to target
Collection is divided, and sub- training set is obtained, using sub- training set as target training set.
Wherein, dividing expressive features is the feature for dividing the sample in target training set.For example, dividing expressive features
It raises up for eyebrow exterior angle, then the sample that the eyebrow exterior angle in target training set raises up is divided into a sub- training set, by target
The sample that eyebrow exterior angle in training set does not raise up is divided into another sub- training set.
Specifically, server is special using the optimal division expression of gini index algorithm picks according to the micro- expressive features collection of target
Sign, divides target training set using obtained division expressive features, obtains sub- training set.Using sub- training set as target
Training set, when the target training set is first node, which is root node, then a left side can be obtained after being divided
Training set and right training set all regard left training set and right training set as target training set.
S510 is returned and is obtained the corresponding micro- expressive features collection of history according to target training set, according to the micro- expressive features of history
Collection obtains the execution of the step of target micro- expressive features collection and obtains objective decision tree when reaching preset condition.
Wherein, preset condition refers to that micro- expression label of sample in target training set is identical.
Specifically, server judges whether to have reached preset condition, when not up to preset condition, i.e., in target training set
Micro- expression label of sample is not identical, and server return step S706 is executed at this time, until micro- table in target training set
When feelings label is all identical, i.e. when micro- expression label in each sub- training set is all identical, objective decision tree is just obtained.For example,
Obtained micro- expression label in a sub- training set is all uneasiness, then illustrates that the sub- training set label is identical, then son training
Collection has just reached preset condition, at this time, it is also necessary to judge whether other sub- training sets have reached preset condition, when all sons
Training set has all reached preset condition, has just obtained an objective decision tree at this time.
S512, return the step of putting back to sampling at random from original training set, obtaining target training set execution, when reaching
When the objective decision tree of preset number, micro- Expression Recognition model is obtained.
Specifically, when obtaining objective decision tree, whether the quantity that server judges objective decision tree has reached default
Number just obtained micro- expression Random Forest model when the quantity of objective decision tree has reached preset number.Micro- expression
Random Forest model is just used as micro- Expression Recognition model.When the quantity of objective decision tree is not up to preset number, server is returned
It returns step S704 to be executed, until the quantity of objective decision tree has reached preset number.
In the above-described embodiments, it is trained to obtain micro- Expression Recognition model, Ke Yizhi by using random forests algorithm
It taps into enforcement to use, improves micro- Expression Recognition efficiency.
In one embodiment, as shown in fig. 6, the generation step of risk warning model, comprising:
S602 obtains history Employees'Emotions state and corresponding historical risk warning grade, according to history Employees'Emotions shape
State obtains history Employees'Emotions state vector, obtains historical risk output vector according to historical risk warning grade.
Specifically, server gets history Employees'Emotions state and corresponding historical risk warning grade, according to history
Employees'Emotions state obtains history Employees'Emotions state vector, according to historical risk warning grade obtain historical risk export to
Amount.Such as: history Employees'Emotions state includes: beaming with smiles, calm calm and in high spirits in intraday variation.It is corresponding
Historical risk warning grade is normal level.The vector then obtained according to history Employees'Emotions state is [12,14,16], then root
It is the obtained historical risk output vector of normal level according to corresponding historical risk warning grade is [0,0,0,0,1].
S604, using historical risk output vector as label, using history Employees'Emotions state vector as input in logic
It is trained in regression model, when reaching preset condition, obtains risk warning model.
Specifically, using historical risk output vector as label, using history Employees'Emotions state vector as logistic regression
The input of model is trained, and when the value of cost function reaches preset threshold or reaches maximum number of iterations, which is returned
Return the training of model to complete, obtains risk warning model.Wherein, the linear regression analysis model of a kind of broad sense of logistic regression.
Activation primitive uses S type functionSum of squared errors function is as cost function.
In the above-described embodiments, by obtaining history Employees'Emotions state and corresponding historical risk warning grade, according to
History Employees'Emotions state obtains history Employees'Emotions state vector, obtains historical risk output according to historical risk warning grade
Vector, using historical risk output vector as label, using history Employees'Emotions state vector as input in Logic Regression Models
In be trained, when reaching preset condition, obtain risk warning model.It is pre- that risk is trained by preparatory usage history data
Alert model can be carried out directly using facilitating subsequent processing, improve efficiency.
It should be understood that although each step in the flow chart of Fig. 2-6 is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 2-6
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can be at least part of the sub-step or stage of other steps or other steps in turn or alternately
It executes.
In one embodiment, as shown in fig. 7, providing a kind of employee work condition monitoring device 700, comprising: picture
Interception module 702, mark determining module 704, micro- Expression Recognition module 706, output obtains module 708 and grade obtains module
710, in which:
Picture interception module 702 is regarded every preset duration from employee work video intercepting for obtaining employee work video
Frequency picture；
Determining module 704 is identified, for obtaining employee's facial image according to video pictures, is determined according to employee's facial image
Corresponding employee identification；
Micro- Expression Recognition module 706 inputs micro- expressive features for obtaining micro- expressive features according to employee's facial image
It is identified in the micro- Expression Recognition model trained, obtains micro- expression output feature, feature is exported according to micro- expression and is obtained pair
The micro- expression answered；
Output obtains module 708, for determining the corresponding Employees'Emotions state of employee identification according to micro- expression, according to employee
Emotional state obtains Employees'Emotions state vector, in the risk warning model that the input of Employees'Emotions state vector has been trained, obtains
To risk output vector；
Grade obtains module 710, for obtaining the Risk-warning grade of employee identification according to risk output vector.
In one embodiment, determining module 704 is identified, comprising:
Face detection module obtains employee's facial image for detecting facial image in video pictures；
Similarity calculation module, for determining employee's face characteristic information, counter worker's face according to employee's facial image
The similarity of characteristic information and default employee's facial image；
Judgment module, for when similarity is greater than preset threshold, obtaining the corresponding employee's mark of default employee's facial image
Know.
Similarity calculation module in one of the embodiments, comprising:
Face division module obtains target facial image, according to target facial image for dividing employee's facial image
Obtain corresponding features of skin colors information, contour feature information, texture feature information and area features information；
Computing module, for calculating features of skin colors information, contour feature information, texture feature information and area features information
With the similarity of default employee's facial image.
In one embodiment, employee work condition monitoring device 700, further includes:
Initial sample obtains module, obtains history interviewee video and the corresponding micro- expression label of history interviewee's video,
Obtain original training set；
Training set obtains module, puts back to sampling at random from original training set, obtains target training set；
Feature set obtains module, the corresponding micro- expressive features collection of history is obtained according to target training set, according to the micro- table of history
Feelings feature set obtains the micro- expressive features collection of target；
Sub- training set obtains module, is obtained dividing expressive features according to the micro- expressive features collection of target, special using expression is divided
Sign divides target training set, sub- training set is obtained, using sub- training set as target training set；
Decision tree obtains module, returns and obtains the corresponding micro- expressive features collection of history according to target training set, according to history
Micro- expressive features collection obtains the execution of the step of target micro- expressive features collection and obtains objective decision tree when reaching preset condition；
The step of model obtains module, and return puts back to sampling at random from original training set, obtains target training set is held
Row, when reaching the objective decision tree of preset number, obtains micro- Expression Recognition model.
In one embodiment, employee work condition monitoring device 700, further includes:
History vectors obtain module.Module is obtained for history vectors, obtains history Employees'Emotions state and corresponding is gone through
History Risk-warning grade obtains history Employees'Emotions state vector according to history Employees'Emotions state, according to historical risk early warning
Grade obtains historical risk output vector；
Model training module, for using historical risk output vector as label, history Employees'Emotions state vector to be made
It is trained in Logic Regression Models for input, when reaching preset condition, obtains risk warning model.
Specific restriction about employee work condition monitoring device may refer to above for employee work condition monitoring
The restriction of method, details are not described herein.Modules in above-mentioned employee work condition monitoring device can be fully or partially through
Software, hardware and combinations thereof are realized.Above-mentioned each module can be embedded in the form of hardware or independently of the place in computer equipment
It manages in device, can also be stored in a software form in the memory in computer equipment, in order to which processor calls execution or more
The corresponding operation of modules.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 8.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is for storing employee's video data.The network interface of the computer equipment is used to pass through with external terminal
Network connection communication.To realize a kind of employee work condition 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. 8, 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, which is stored with
Computer program, which performs the steps of when executing computer program obtains employee work video, every preset duration
From employee work video intercepting video pictures；Employee's facial image is obtained according to video pictures, is determined according to employee's facial image
Corresponding employee identification；Micro- expressive features are obtained according to employee's facial image, micro- expressive features are inputted to the micro- expression trained
It is identified in identification model, obtains micro- expression output feature, feature is exported according to micro- expression and obtains corresponding micro- expression；According to
Micro- expression determines the corresponding Employees'Emotions state of employee identification, obtains Employees'Emotions state vector according to Employees'Emotions state, will
In the risk warning model that the input of Employees'Emotions state vector has been trained, risk output vector is obtained；According to risk output vector
Obtain the Risk-warning grade of employee identification.
In one embodiment, people in detection video pictures is also performed the steps of when processor executes computer program
Face image obtains employee's facial image；Employee's face characteristic information, counter's work face characteristic are determined according to employee's facial image
The similarity of information and default employee's facial image；When similarity is greater than preset threshold, it is corresponding to obtain employee's facial image
Employee identification.
In one embodiment, it is also performed the steps of when processor executes computer program and draws employee's facial image
Point, target facial image is obtained, corresponding features of skin colors information, contour feature information, texture are obtained according to target facial image
Characteristic information and area features information；Calculate features of skin colors information, contour feature information, texture feature information and area features letter
The similarity of breath and default employee's facial image.
In one embodiment, it is also performed the steps of when processor executes computer program and obtains history interviewee view
Frequency micro- expression label corresponding with history interviewee's video, obtains original training set；It puts back to and adopts at random from original training set
Sample obtains target training set；The corresponding micro- expressive features collection of history is obtained according to target training set, according to the micro- expressive features of history
Collection obtains the micro- expressive features collection of target；It is obtained dividing expressive features according to the micro- expressive features collection of target, uses division expressive features
Target training set is divided, sub- training set is obtained, using sub- training set as target training set；It returns according to target training set
The step of obtaining the corresponding micro- expressive features collection of history, obtaining target micro- expressive features collection according to the micro- expressive features collection of history is held
Row, when reaching preset condition, obtains objective decision tree；Sampling is put back in return at random from original training set, obtains target
The step of training set, executes, and when reaching the objective decision tree of preset number, obtains micro- Expression Recognition model.
In one embodiment, it is also performed the steps of when processor executes computer program and obtains history Employees'Emotions
State and corresponding historical risk warning grade obtain history Employees'Emotions state vector, root according to history Employees'Emotions state
Historical risk output vector is obtained according to historical risk warning grade；Using historical risk output vector as label, by history employee
Emotional state vector is trained in Logic Regression Models as input, when reaching preset condition, obtains Risk-warning mould
Type
In one embodiment, it is also performed the steps of when computer program is executed by processor and obtains employee work view
Frequently, every preset duration from employee work video intercepting video pictures；Employee's facial image is obtained according to video pictures, according to member
Worker's face image determines corresponding employee identification；Micro- expressive features are obtained according to employee's facial image, micro- expressive features are inputted
It is identified in the micro- Expression Recognition model trained, obtains micro- expression output feature, feature is exported according to micro- expression and is obtained pair
The micro- expression answered；The corresponding Employees'Emotions state of employee identification is determined according to micro- expression, and employee is obtained according to Employees'Emotions state
Employees'Emotions state vector is inputted in the risk warning model trained, obtains risk output vector by emotional state vector；Root
The Risk-warning grade of employee identification is obtained according to risk output vector.
In one embodiment, it is also performed the steps of when computer program is executed by processor in detection video pictures
Facial image obtains employee's facial image；Employee's face characteristic information is determined according to employee's facial image, and counter worker's face is special
The similarity of reference breath and default employee's facial image；When similarity is greater than preset threshold, default employee's facial image is obtained
Corresponding employee identification.
In one embodiment, it is also performed the steps of when computer program is executed by processor by employee's facial image
It divides, obtains target facial image, corresponding features of skin colors information, contour feature information, line are obtained according to target facial image
Manage characteristic information and area features information；Calculate features of skin colors information, contour feature information, texture feature information and area features
The similarity of information and default employee's facial image.
In one embodiment, it is also performed the steps of when computer program is executed by processor and obtains history interviewee
Video and the corresponding micro- expression label of history interviewee's video, obtain original training set；It is put back at random from original training set
Sampling, obtains target training set；The corresponding micro- expressive features collection of history is obtained according to target training set, it is special according to the micro- expression of history
Collection obtains the micro- expressive features collection of target；It is obtained dividing expressive features according to the micro- expressive features collection of target, it is special using expression is divided
Sign divides target training set, sub- training set is obtained, using sub- training set as target training set；It returns according to target training
The step of collection obtains the corresponding micro- expressive features collection of history, obtains target micro- expressive features collection according to the micro- expressive features collection of history is held
Row, when reaching preset condition, obtains objective decision tree；Sampling is put back in return at random from original training set, obtains target
The step of training set, executes, and when reaching the objective decision tree of preset number, obtains micro- Expression Recognition model.
In one embodiment, it is also performed the steps of when computer program is executed by processor and obtains history employee feelings
Not-ready status and corresponding historical risk warning grade obtain history Employees'Emotions state vector according to history Employees'Emotions state,
Historical risk output vector is obtained according to historical risk warning grade；Using historical risk output vector as label, by history person
Work emotional state vector is trained in Logic Regression Models as input, when reaching preset condition, obtains Risk-warning
Model.
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 above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, 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 concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of employee work condition monitoring method, which comprises
Employee work video is obtained, every preset duration from the employee work video intercepting video pictures；
Employee's facial image is obtained according to the video pictures, corresponding employee identification is determined according to employee's facial image；
Micro- expressive features are obtained according to employee's facial image, micro- expressive features are inputted into the micro- Expression Recognition trained
It is identified in model, obtains micro- expression output feature, corresponding micro- expression is obtained according to micro- expression output feature；
The corresponding Employees'Emotions state of the employee identification is determined according to micro- expression, is obtained according to the Employees'Emotions state
The Employees'Emotions state vector is inputted in the risk warning model trained, it is defeated to obtain risk by Employees'Emotions state vector
Outgoing vector；
The Risk-warning grade of the employee identification is obtained according to the risk output vector.
2. the method according to claim 1, wherein described obtain employee's face figure according to the video pictures
Picture determines corresponding employee identification according to employee's facial image, comprising:
Facial image in the video pictures is detected, employee's facial image is obtained；
Employee's face characteristic information is determined according to employee's facial image, calculates employee's face characteristic information and default member
The similarity of worker's face image；
When the similarity is greater than preset threshold, the corresponding employee identification of default employee's facial image is obtained.
3. according to the method described in claim 2, it is characterized in that, described determine employee's face according to employee's facial image
Characteristic information calculates the similarity of employee's face characteristic information Yu default employee's facial image, comprising:
Employee's facial image is divided, target facial image is obtained, corresponding skin is obtained according to the target facial image
Color characteristic information, contour feature information, texture feature information and area features information；
Calculate the features of skin colors information, contour feature information, texture feature information and area features information and default employee people
The similarity of face image.
4. the method according to claim 1, wherein the generation step of micro- Expression Recognition model, comprising:
History interviewee video and the corresponding micro- expression label of history interviewee's video are obtained, original training set is obtained；
It puts back to sampling at random from the original training set, obtains target training set；
The corresponding micro- expressive features collection of history is obtained according to the target training set, is obtained according to the micro- expressive features collection of the history
The micro- expressive features collection of target；
It is obtained dividing expressive features according to the micro- expressive features collection of the target, the target is instructed using the division expressive features
Practice collection to be divided, sub- training set is obtained, using the sub- training set as target training set；
It returns and the corresponding micro- expressive features collection of history is obtained according to the target training set, according to the micro- expressive features collection of the history
The step of obtaining target micro- expressive features collection execution obtains objective decision tree when reaching preset condition；
The step of return puts back to sampling at random from the original training set, obtains target training set execution, it is default when reaching
When the objective decision tree of number, micro- Expression Recognition model is obtained.
5. the method according to claim 1, wherein the generation step of the risk warning model, comprising:
History Employees'Emotions state and corresponding historical risk warning grade are obtained, is obtained according to the history Employees'Emotions state
History Employees'Emotions state vector obtains historical risk output vector according to the historical risk warning grade；
Using the historical risk output vector as label, returned using the history Employees'Emotions state vector as input in logic
Return in model and be trained, when reaching preset condition, obtains the risk warning model.
6. a kind of employee work condition monitoring device, which is characterized in that described device includes:
Picture interception module, for obtaining employee work video, every preset duration from the employee work video intercepting video
Picture；
Determining module is identified, it is true according to employee's facial image for obtaining employee's facial image according to the video pictures
Fixed corresponding employee identification；
Micro- Expression Recognition module, it is for obtaining micro- expressive features according to employee's facial image, micro- expressive features are defeated
Enter and identified in the micro- Expression Recognition model trained, obtain micro- expression output feature, feature is exported according to micro- expression
Obtain corresponding micro- expression；
Output obtains module, for determining the corresponding Employees'Emotions state of the employee identification according to micro- expression, according to institute
It states Employees'Emotions state and obtains Employees'Emotions state vector, the Employees'Emotions state vector is inputted to the Risk-warning trained
In model, risk output vector is obtained；
Grade obtains module, for obtaining the Risk-warning grade of the employee identification according to the risk output vector.
7. device according to claim 6, which is characterized in that described device further include:
Initial sample obtains module, for obtaining history interviewee video and the corresponding micro- expression label of history interviewee's video,
Obtain original training set；
Training set obtains module, for putting back to sampling at random from the original training set, obtains target training set；
Feature set obtains module, for obtaining the corresponding micro- expressive features collection of history according to the target training set, according to described
The micro- expressive features collection of history obtains the micro- expressive features collection of target；
Sub- training set obtains module, divides expressive features for obtaining according to the micro- expressive features collection of the target, uses described stroke
Point expressive features divide the target training set, sub- training set are obtained, using the sub- training set as target training set；
Decision tree obtains module, obtains the corresponding micro- expressive features collection of history according to the target training set for returning, according to
The micro- expressive features collection of history obtains the execution of the step of target micro- expressive features collection and obtains target when reaching preset condition
Decision tree；
Model obtains module, puts back to sampling at random from the original training set for returning, obtains the step of target training set
It is rapid to execute, when reaching the objective decision tree of preset number, obtain micro- Expression Recognition model.
8. device according to claim 6, which is characterized in that described device further include:
History vectors obtain module, for obtaining history Employees'Emotions state and corresponding historical risk warning grade, according to institute
It states history Employees'Emotions state and obtains history Employees'Emotions state vector, history wind is obtained according to the historical risk warning grade
Dangerous output vector；
Model training module, for using the historical risk output vector as label, by the history Employees'Emotions state to
Amount is trained in Logic Regression Models as input, when reaching preset condition, obtains the risk warning model.
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 5 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 5 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811546642.6A CN109766766A (en) | 2018-12-18 | 2018-12-18 | Employee work condition monitoring method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811546642.6A CN109766766A (en) | 2018-12-18 | 2018-12-18 | Employee work condition monitoring method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109766766A true CN109766766A (en) | 2019-05-17 |
Family
ID=66451479
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811546642.6A Pending CN109766766A (en) | 2018-12-18 | 2018-12-18 | Employee work condition monitoring method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109766766A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110222623A (en) * | 2019-05-31 | 2019-09-10 | 深圳市恩钛控股有限公司 | Micro- expression analysis method and system |
| CN110414806A (en) * | 2019-07-10 | 2019-11-05 | 平安科技（深圳）有限公司 | Employee's method for prewarning risk and relevant apparatus |
| CN110458008A (en) * | 2019-07-04 | 2019-11-15 | 深圳壹账通智能科技有限公司 | Method for processing video frequency, device, computer equipment and storage medium |
| CN110555374A (en) * | 2019-07-25 | 2019-12-10 | 深圳壹账通智能科技有限公司 | resource sharing method and device, computer equipment and storage medium |
| CN110620905A (en) * | 2019-09-06 | 2019-12-27 | 平安医疗健康管理股份有限公司 | Video monitoring method and device, computer equipment and storage medium |
| CN112183197A (en) * | 2020-08-21 | 2021-01-05 | 深圳追一科技有限公司 | Method and device for determining working state based on digital person and storage medium |
| CN112348342A (en) * | 2020-10-30 | 2021-02-09 | 中核核电运行管理有限公司 | Employee behavior analysis method and device |
| WO2021047185A1 (en) * | 2019-09-12 | 2021-03-18 | 深圳壹账通智能科技有限公司 | Monitoring method and apparatus based on facial recognition, and storage medium and computer device |
| CN112668833A (en) * | 2020-11-26 | 2021-04-16 | 平安普惠企业管理有限公司 | Staff work arrangement method, device, equipment and medium based on artificial intelligence |
| CN112766145A (en) * | 2021-01-15 | 2021-05-07 | 深圳信息职业技术学院 | Method and device for identifying dynamic facial expressions of artificial neural network |
| CN112950174A (en) * | 2021-04-12 | 2021-06-11 | 上海应用技术大学 | Staff pressure attribution early warning prevention system based on differentiated employment mode |
| CN113052146A (en) * | 2021-04-30 | 2021-06-29 | 中国银行股份有限公司 | Emotion early warning method and device |
| CN113256904A (en) * | 2020-06-08 | 2021-08-13 | 深圳怡化电脑股份有限公司 | Self-service financial terminal control method and device, terminal and readable medium |
| CN113837578A (en) * | 2021-09-15 | 2021-12-24 | 江苏兴力工程管理有限公司 | Gridding supervision and management evaluation method for power supervision enterprise |
| CN114022944A (en) * | 2022-01-05 | 2022-02-08 | 北京国信网联科技有限公司 | Intelligent monitoring system |
| CN116029287A (en) * | 2023-03-29 | 2023-04-28 | 北京万理软件开发有限公司 | Method, device and storage medium for determining working state based on self-correcting operation |
| CN116433029A (en) * | 2023-04-23 | 2023-07-14 | 国网四川省电力公司巴中供电公司 | Power operation risk assessment method, system, equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130281798A1 (en) * | 2012-04-23 | 2013-10-24 | Sackett Solutions & Innovations, LLC | Cognitive biometric systems to monitor emotions and stress |
| US20130300900A1 (en) * | 2012-05-08 | 2013-11-14 | Tomas Pfister | Automated Recognition Algorithm For Detecting Facial Expressions |
| US20140163960A1 (en) * | 2012-12-12 | 2014-06-12 | At&T Intellectual Property I, L.P. | Real - time emotion tracking system |
| US20160241500A1 (en) * | 2015-02-13 | 2016-08-18 | International Business Machines Corporation | Point in time expression of emotion data gathered from a chat session |
| CN106361356A (en) * | 2016-08-24 | 2017-02-01 | 北京光年无限科技有限公司 | Emotion monitoring and early warning method and system |
| CN106650621A (en) * | 2016-11-18 | 2017-05-10 | 广东技术师范学院 | Deep learning-based emotion recognition method and system |
| CN108234956A (en) * | 2018-02-05 | 2018-06-29 | 龙马智芯（珠海横琴）科技有限公司 | Medical care monitoring method, device and system, equipment |
| CN108460324A (en) * | 2018-01-04 | 2018-08-28 | 上海孩子通信息科技有限公司 | A method of child's mood for identification |
-
2018
- 2018-12-18 CN CN201811546642.6A patent/CN109766766A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130281798A1 (en) * | 2012-04-23 | 2013-10-24 | Sackett Solutions & Innovations, LLC | Cognitive biometric systems to monitor emotions and stress |
| US20130300900A1 (en) * | 2012-05-08 | 2013-11-14 | Tomas Pfister | Automated Recognition Algorithm For Detecting Facial Expressions |
| US20140163960A1 (en) * | 2012-12-12 | 2014-06-12 | At&T Intellectual Property I, L.P. | Real - time emotion tracking system |
| US20160241500A1 (en) * | 2015-02-13 | 2016-08-18 | International Business Machines Corporation | Point in time expression of emotion data gathered from a chat session |
| CN106361356A (en) * | 2016-08-24 | 2017-02-01 | 北京光年无限科技有限公司 | Emotion monitoring and early warning method and system |
| CN106650621A (en) * | 2016-11-18 | 2017-05-10 | 广东技术师范学院 | Deep learning-based emotion recognition method and system |
| CN108460324A (en) * | 2018-01-04 | 2018-08-28 | 上海孩子通信息科技有限公司 | A method of child's mood for identification |
| CN108234956A (en) * | 2018-02-05 | 2018-06-29 | 龙马智芯（珠海横琴）科技有限公司 | Medical care monitoring method, device and system, equipment |
Non-Patent Citations (2)
| Title |
|---|
| ANTONIO FERNANDEZ-CABALLERO等: "Smart environment architecture for emotion detection and regulation", 《ELSEVIER》 * |
| 刘迪兆: "基于深度学习的老年人情绪关怀系统的研究与设计", 《中国优秀硕士学位论文全文数据库（电子期刊）信息科技辑》, vol. 2018, no. 07 * |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110222623A (en) * | 2019-05-31 | 2019-09-10 | 深圳市恩钛控股有限公司 | Micro- expression analysis method and system |
| CN110458008A (en) * | 2019-07-04 | 2019-11-15 | 深圳壹账通智能科技有限公司 | Method for processing video frequency, device, computer equipment and storage medium |
| CN110414806A (en) * | 2019-07-10 | 2019-11-05 | 平安科技（深圳）有限公司 | Employee's method for prewarning risk and relevant apparatus |
| CN110414806B (en) * | 2019-07-10 | 2024-05-14 | 平安科技（深圳）有限公司 | Employee risk early warning method and related device |
| CN110555374A (en) * | 2019-07-25 | 2019-12-10 | 深圳壹账通智能科技有限公司 | resource sharing method and device, computer equipment and storage medium |
| CN110620905A (en) * | 2019-09-06 | 2019-12-27 | 平安医疗健康管理股份有限公司 | Video monitoring method and device, computer equipment and storage medium |
| WO2021047185A1 (en) * | 2019-09-12 | 2021-03-18 | 深圳壹账通智能科技有限公司 | Monitoring method and apparatus based on facial recognition, and storage medium and computer device |
| CN113256904B (en) * | 2020-06-08 | 2024-04-02 | 深圳怡化电脑股份有限公司 | Self-service financial terminal control method, device, terminal and readable medium |
| CN113256904A (en) * | 2020-06-08 | 2021-08-13 | 深圳怡化电脑股份有限公司 | Self-service financial terminal control method and device, terminal and readable medium |
| CN112183197A (en) * | 2020-08-21 | 2021-01-05 | 深圳追一科技有限公司 | Method and device for determining working state based on digital person and storage medium |
| CN112348342A (en) * | 2020-10-30 | 2021-02-09 | 中核核电运行管理有限公司 | Employee behavior analysis method and device |
| CN112668833A (en) * | 2020-11-26 | 2021-04-16 | 平安普惠企业管理有限公司 | Staff work arrangement method, device, equipment and medium based on artificial intelligence |
| CN112766145A (en) * | 2021-01-15 | 2021-05-07 | 深圳信息职业技术学院 | Method and device for identifying dynamic facial expressions of artificial neural network |
| CN112766145B (en) * | 2021-01-15 | 2021-11-26 | 深圳信息职业技术学院 | Method and device for identifying dynamic facial expressions of artificial neural network |
| CN112950174A (en) * | 2021-04-12 | 2021-06-11 | 上海应用技术大学 | Staff pressure attribution early warning prevention system based on differentiated employment mode |
| CN113052146A (en) * | 2021-04-30 | 2021-06-29 | 中国银行股份有限公司 | Emotion early warning method and device |
| CN113837578B (en) * | 2021-09-15 | 2024-02-06 | 江苏兴力工程管理有限公司 | Grid supervision, management and evaluation method for power supervision enterprise |
| CN113837578A (en) * | 2021-09-15 | 2021-12-24 | 江苏兴力工程管理有限公司 | Gridding supervision and management evaluation method for power supervision enterprise |
| CN114022944A (en) * | 2022-01-05 | 2022-02-08 | 北京国信网联科技有限公司 | Intelligent monitoring system |
| CN116029287A (en) * | 2023-03-29 | 2023-04-28 | 北京万理软件开发有限公司 | Method, device and storage medium for determining working state based on self-correcting operation |
| CN116433029A (en) * | 2023-04-23 | 2023-07-14 | 国网四川省电力公司巴中供电公司 | Power operation risk assessment method, system, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109766766A (en) | Employee work condition monitoring method, device, computer equipment and storage medium | |
| CN109767261A (en) | Products Show method, apparatus, computer equipment and storage medium | |
| CN109729383B (en) | Double-recording video quality detection method and device, computer equipment and storage medium | |
| EP3852003A1 (en) | Feature point locating method, storage medium and computer device | |
| CN107463888B (en) | Face emotion analysis method and system based on multi-task learning and deep learning | |
| WO2021000644A1 (en) | Video processing method and apparatus, computer device and storage medium | |
| CN109543627A (en) | A kind of method, apparatus and computer equipment judging driving behavior classification | |
| CN111028305A (en) | Expression generation method, device, equipment and storage medium | |
| CN109766917A (en) | Interview video data handling procedure, device, computer equipment and storage medium | |
| CN111160275B (en) | Pedestrian re-recognition model training method, device, computer equipment and storage medium | |
| CN109815489A (en) | Collection information generating method, device, computer equipment and storage medium | |
| CN109886554B (en) | Illegal behavior discrimination method, device, computer equipment and storage medium | |
| CN110046577B (en) | Pedestrian attribute prediction method, device, computer equipment and storage medium | |
| CN110009003A (en) | Training method, the device and system of image procossing and image comparison model | |
| WO2021114612A1 (en) | Target re-identification method and apparatus, computer device, and storage medium | |
| CN109886110A (en) | Micro- expression methods of marking, device, computer equipment and storage medium | |
| CN109766474A (en) | Inquest signal auditing method, device, computer equipment and storage medium | |
| Mousavi | A new way to age estimation for rgb-d images, based on a new face detection and extraction method for depth images | |
| CN114119460A (en) | Semiconductor image defect identification method, semiconductor image defect identification device, computer equipment and storage medium | |
| Murtaza et al. | PMHI: Proposals from motion history images for temporal segmentation of long uncut videos | |
| CN109711301A (en) | Driver's checking method, device, computer equipment and storage medium | |
| CN109271957A (en) | Face gender identification method and device | |
| Diyasa et al. | Multi-face Recognition for the Detection of Prisoners in Jail using a Modified Cascade Classifier and CNN | |
| CN111985340A (en) | Face recognition method and device based on neural network model and computer equipment | |
| Lian et al. | Region based robust facial expression analysis |
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 |