CN109686447A - A kind of employee status's monitoring system based on artificial intelligence - Google Patents
A kind of employee status's monitoring system based on artificial intelligence Download PDFInfo
- Publication number
- CN109686447A CN109686447A CN201910081688.3A CN201910081688A CN109686447A CN 109686447 A CN109686447 A CN 109686447A CN 201910081688 A CN201910081688 A CN 201910081688A CN 109686447 A CN109686447 A CN 109686447A
- Authority
- CN
- China
- Prior art keywords
- employee
- work
- physiological
- data
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
- A61B5/02055—Simultaneously evaluating both cardiovascular condition and temperature
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06398—Performance of employee with respect to a job function
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/174—Facial expression recognition
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Cardiology (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Surgery (AREA)
- Veterinary Medicine (AREA)
- Strategic Management (AREA)
- Physiology (AREA)
- Human Computer Interaction (AREA)
- Animal Behavior & Ethology (AREA)
- Multimedia (AREA)
- Molecular Biology (AREA)
- Psychiatry (AREA)
- Development Economics (AREA)
- Heart & Thoracic Surgery (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Biophysics (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Social Psychology (AREA)
- Educational Technology (AREA)
- Developmental Disabilities (AREA)
- Child & Adolescent Psychology (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Hospice & Palliative Care (AREA)
- Psychology (AREA)
- Oral & Maxillofacial Surgery (AREA)
Abstract
The present invention relates to a kind of, and the employee status based on artificial intelligence monitors system, belongs to Condition Monitoring Technology field, solves the problems, such as that the prior art is subjective, real-time is poor, judging result accuracy is lower, is unable to satisfy safety in production and require.The system includes: to be set to the helmet, the Multifunction Sensor on wrist strap, the message handler being set on the safety working clothes of employee's wearing.Multifunction Sensor for acquiring work on the spot environment audio/video information, the individual physiological data information of the employee, and transmits it to message handler;Message handler, for work on the spot environment audio/video information, the individual physiological data information according to employee, identify the working condition and real-time physiological health condition of the employee, and then whether physiological status meets job position request before judging its hilllock, or can physiological status be competent at work at present in its work, and show judging result.The system can in real time, automatically, accurately analyze the physiology and psychologic situation of employee.
Description
Technical field
The present invention relates to Condition Monitoring Technology fields more particularly to a kind of employee status based on artificial intelligence to monitor system
System.
Background technique
The production activity of modern enterprise is often continuous, repetition pipeline system, and enterprise's production is frequently in high temperature, height
Under wet, dusty and big noise circumstance, such as building, electric power, flow line production place etc..Employee is grasped in modern enterprise production
It is more demanding to make qualification, refinement requirement is also higher, and production activity is to state in state before the hilllock of employee and work
More demanding, the psychology and physiological status of employee will directly influence work quality.
It is monitored currently, most enterprises are still artificial passive type to the management of employee, but some half newly also occurs
Active monitoring method, i.e. administrator monitor the working condition of employee by monitoring method, but this management method is generally deposited
In following problems:
1) monitoring room administrator is needed to judge the working condition of employee, the judgement is subjective, is easy to appear erroneous judgement
With fail to judge;
2) real-time is poor, and cost of labor is higher, and administrator needs persistently to watch monitored picture;
3) for safety in production, it cannot accomplish that active prevents in advance, monitoring and subsequent feedback in thing.
Summary of the invention
In view of above-mentioned analysis, the embodiment of the present invention is intended to provide a kind of employee status's monitoring system based on artificial intelligence
System, to solve, the prior art is subjective, real-time is poor, judging result accuracy is lower, is unable to satisfy safety in production
It is required that the problem of.
On the one hand, the embodiment of the invention provides a kind of, and the employee status based on artificial intelligence monitors system, including is placed in
Multifunction Sensor on the helmet, wrist strap, the message handler being set on the safety working clothes of employee's wearing.
The Multifunction Sensor, for acquiring work on the spot environment audio/video information, the individual physiological data of the employee
Information, and transmit it to message handler;
The message handler, for according to the work on the spot environment audio/video information of the employee, individual physiological data
Information, identifies the working condition and real-time physiological health condition of the employee, and then whether physiological status meets hilllock before judging its hilllock
Can physiological status be competent at work at present in position requirement or its work, show judging result.
Above-mentioned technical proposal has the beneficial effect that: employee status is monitored system preparation in the helmet, wrist strap and safety
When on work clothes, dressing, working before work convenient for each employee using, work after change clothes.The life of single employee can be also directed to
Reason and psychological condition, customize different Multifunction Sensors, obtain the working condition and specific real-time physiological health of specific employee
Situation has functional expansionary.Pass through the real-time employee work site environment audio/video information of acquisition, individual physiological data
Information, judges automatically the instantaneous operating conditions (psychology) and real-time physiological health condition of employee, and further judges its hilllock previous existence
Can whether reason state meets physiological status in job position request or its work be competent at work at present, accomplish in advance actively prevention, thing
Middle monitoring and subsequent feedback, remind and replace in time the employee for not meeting job position request, guarantee safety in production.It is demonstrate,proved through a large number of experiments
Bright, the judging result accuracy of the system is high, can satisfy most of manufacturing requirements.
In another embodiment based on the above method, the Multifunction Sensor, comprising:
The miniature audio-video acquisition equipment being set on the helmet, the work on the spot environment audio-video for acquiring the employee are believed
Breath, and transmit it to message handler;
The physiological data sensor being set on wrist strap, for acquiring the non-real time physiological data information of the employee, and by its
It is transmitted to message handler.
The beneficial effect of above-mentioned technical proposal is: being defined, passes through to the component and installation site of Multifunction Sensor
The miniature audio-video acquisition equipment being set on the helmet can acquire the real-time live working environment audio/video information of the employee, packet
The operation information for including relevant field devices can acquire the real-time life of employee by the physiological data sensor being set on wrist strap
Manage data, including body temperature, breathing, palmic rate and alcohol content etc..
Further, the miniature audio-video acquisition equipment, including high-definition camera, camera base, bracing means;Its
In,
It is designed using card slot protrusion at the back side of the high-definition camera;The front of the camera base uses and the card
Slot protrusion designs the groove design that matches, the back side by bracing means be fixed on the helmet it is default connect fastly base position or
Add the interim base position matched.
The beneficial effect of above-mentioned further scheme is: being defined to the composition of miniature audio-video acquisition equipment, passes through card
Slot cooperation and Design of Reinforcement, make high-definition camera be secured firmly to the predetermined position of the helmet, to work on the spot environment audio-video
Information carries out stable, effective acquisition.
Further, the bracing means includes double-sided adhesive, velcro elastic band;Wherein,
The camera base through the sticking double faced adhesive tape on the helmet, and passes through the velcro elastic band
The high-definition camera is bundled on employee's helmet.
The beneficial effect of above-mentioned further scheme is: being defined to the composition of bracing means, passes through double-sided adhesive, velcro
Camera base can be firmly secured at employee's helmet predetermined position by elastic band, and method is simple, practical.
Further, the non-real time physiological data information of the employee, including body temperature, breathing, palmic rate and alcohol content number
At least one of according to.
The beneficial effect of above-mentioned further scheme is: medically, the body temperature of human body, breathing (rhythm), palmic rate and
The physiological datas such as alcohol content have specific range of normal value, can be convenient by acquiring these data, effectively judgement person
Whether the physiological status of work meets work position requirement.And the physiological data of the employee can pass through the multifunctional sensing of setting
Device is acquired in real time, is carried out additional physical examination without taking a significant amount of time again, is saved time and cost.
Further, the message handler, comprising:
Data processing module is known for work on the spot environment audio/video information, the individual physiological data information according to employee
The working condition of relevant device, the working condition of the employee and real-time physiological health in other working environment, and then judge the employee
Whether physiological status meets job position request before hilllock, and can physiological status be competent at work at present in work, and show judging result and
Correlation alarm;
Data memory module, for storing the work on the spot environment audio/video information, individual physiological data information, and
Whether meet physiological status before hilllock that job position request, can physiological status be competent at the judging result of work at present in work accordingly
It is alerted with correlation;Its data terminal is connect with the data terminal of above-mentioned data processing module;
Power supply module, for powering for the data processing module, data memory module, Multifunction Sensor;It is exported
End is connect with the feeder ear of data processing module, data memory module, Multifunction Sensor respectively.
The beneficial effect of above-mentioned further scheme is: message handler assembly module, nuclear interface standardizing, for different hilllocks
Position requires employee's physiology and the different of psychological condition, may customize different Multifunction Sensors, obtains the work of specific employee
State and specific real-time physiological health condition have functional expansionary.The data of data memory module storage can not only be made
For the input of data processing module, and it can be used as historical data and provided for later period system (data processing module) parameter optimization
Feedback.
It further, further include live video acquisition equipment;
The live video acquires equipment, for the facial expression of all employees, eye in real-time collection site working environment
Mind and limb action information, and transmit it to message handler.
The beneficial effect of above-mentioned further scheme is: equipment is acquired by live video, it can real-time collection site building ring
The facial expression, expression in the eyes and limb action information of all employees in border, and then judge whether the psychological condition of every employee is in
The employee for not meeting job position request is reminded and replace in time to fatigue and degree of fatigue, is conducive to improve production efficiency.
It further, further include the communication module being connect with the data processing module and miniature headset;
The communication module, for by work on the spot environment audio/video information, the individual physiological data information of employee, and
Whether meet physiological status before hilllock that job position request, can physiological status be competent at the judging result of work at present in work accordingly
It is alerted with correlation, is transmitted to external server, meanwhile, the instruction that external server issues is transmitted to data processing module and is carried out
Display;
The miniature headset, for by communication module carry out employee between work cooperate information exchange, employee to
Grade carries out field condition report, higher level and issues instruction information to employee.
The beneficial effect of above-mentioned further scheme is: by communication module and miniature headset, can carry out between employee, employee
With the information exchange between higher level (including administrator), be conducive to the working efficiency for improving each employee, improve user experience and use
Family satisfaction.
Further, the data processing module, including sequentially connected pretreatment submodule, classification are predicted submodule, are shown
Show submodule;Wherein,
The pretreatment submodule, the audio, video data information for obtaining to Multifunction Sensor carry out target identification,
The signal lamp opening and closing information and audio-video prompt information for obtaining the field device of current time employee operation, as scene
The distinguishing indexes of equipment operation condition;Human body and four limbs positioning are carried out to the collected before and after frames picture of live video acquisition equipment
And recognition of face, certain period employee's limb action will be characterized in human body and four limbs positioning result, and whether there is or not the differences of aggressive behavior
Data information will be in face recognition result when difference as the distinguishing indexes of the limb action of the employee in work on the spot environment
Nozzle type, the eyes size and shape of employee are carved, the identification as the facial expression, expression in the eyes of the employee in work on the spot environment refers to
Mark;And noise reduction process is carried out to the individual physiological data information that Multifunction Sensor obtains;Then, respectively by above-mentioned distinguishing indexes
The classification prediction submodule is transmitted to noise reduction process result;
Submodule is predicted in the classification, is made the following judgment by the good 3 classes classification prediction model of precondition: firstly,
The distinguishing indexes for the field device operating condition that the employee in work on the spot environment is operated, the good first kind of input precondition
Classification prediction model, obtains the judging result whether relevant field devices open;Secondly, by the noise reduction of individual physiological data information
Processing result, the good two classification prediction model of input precondition, show that can the real-time physiological health of the employee be competent at
The judging result to work on issues not competent alarm if not competent work;Then, it will be somebody's turn to do in work on the spot environment
The distinguishing indexes of the facial expression of employee, expression in the eyes and limb action information input the good third class classification prediction of precondition respectively
Model, show whether employee's psychological condition is in the judging result of fatigue and degree of fatigue, and issues the tired of appropriate level
Labor alarm;Finally, whether physiological status meets job position request before judging the employee hilllock in conjunction with monitoring time, in work physiology and
Can psychological condition be competent at work at present;
The display module, for the above-mentioned judging result of real-time display and related alarm.
The beneficial effect of above-mentioned further scheme is: being defined to the composition of data processing module, makes it have data
The function of pretreatment, classification prediction and display.Also, 3 classes classification prediction model is established in classification prediction submodule, it is instructed
After white silk, can accurately obtain judging result, the real-time physiological health of employee whether relevant field devices open can be competent at after
Whether judging result, the employee's psychological condition of continuous work are in the judging result of fatigue, and issue related alarm, are conducive in time
Replacement does not meet the employee of job position request, improves production efficiency and user satisfaction.
Further, submodule is predicted in the classification, is trained using following steps to 3 classes classification prediction model:
Acquiring multiple groups includes the distinguishing indexes of field device operating condition, corresponding field device open and close result
Training data input first kind classification prediction model is obtained the parameter of first kind classification prediction model by training data, complete
The training of pairs of first kind classification prediction model;
Can multiple groups be acquired competent result comprising employee's individual physiological data, the real-time physiological health of corresponding employee
Training data, by the training data input two classification prediction model, obtain two classification prediction model parameter,
Complete the training to two classification prediction model;
Acquisition multiple groups include that facial expression, expression in the eyes and the limb action under the frightened different mental state of employee's happiness, anger, grief and joy refer to
Mark, corresponding employee real-time mental health can competent result training data, by the training data input third
Class classification prediction model, obtains the parameter of third class classification prediction model, completes the training to third class classification prediction model.
The beneficial effect of above-mentioned further scheme is: the method being trained to 3 classes classification prediction model is defined, and is led to
Above-mentioned training is crossed, can accurately can obtain judging result, the real-time physiological health of employee that whether relevant field devices open
Whether competent judging result, the employee's psychological condition to work on is in the judging result of fatigue.
It in the present invention, can also be combined with each other between above-mentioned each technical solution, to realize more preferred assembled schemes.This
Other feature and advantage of invention will illustrate in the following description, also, certain advantages can become from specification it is aobvious and
It is clear to, or understand through the implementation of the invention.The objectives and other advantages of the invention can by specification, claims with
And it is achieved and obtained in specifically noted content in attached drawing.
Detailed description of the invention
Attached drawing is only used for showing the purpose of specific embodiment, and is not to be construed as limiting the invention, in entire attached drawing
In, identical reference symbol indicates identical component.
Fig. 1 is that 1 employee status of the embodiment of the present invention monitors system layout diagram;
Fig. 2 is that 2 employee status of the embodiment of the present invention monitors system layout diagram.
Appended drawing reference:
A1- Multifunction Sensor;A2- Multifunction Sensor;B- message handler;1- camera connecting line;2- data line;
3- wrist strap (including Multifunction Sensor);The miniature headset of 4-;5- tone frequency channel wire;6- audio jack;The closing waist pine of 7- safety working clothes
Taut band (including message handler);8- message handler audio interface;9- message handler data-interface.
Specific embodiment
Specifically describing the preferred embodiment of the present invention with reference to the accompanying drawing, wherein attached drawing constitutes the application a part, and
Together with embodiments of the present invention for illustrating the principle of the present invention, it is not intended to limit the scope of the present invention.
Embodiment 1
A specific embodiment of the invention discloses a kind of employee status's monitoring system based on artificial intelligence, such as Fig. 1
It is shown, including being set to the helmet, Multifunction Sensor A1, A2 on wrist strap, it is set on the safety working clothes of employee's wearing
Message handler B.
Multifunction Sensor A1, A2, for acquiring work on the spot environment audio/video information, the individual physiological data of the employee
Information, and transmit it to message handler B.
Message handler B, for being believed according to the work on the spot environment audio/video information of the employee, individual physiological data
Breath, identifies the working condition and real-time physiological health condition of the employee, and then whether physiological status meets post before judging its hilllock
It is required that or can physiological status be competent at work at present, display judging result in its work.
The data of Multifunction Sensor acquisition can be transmitted to information by data transfer modes such as data line or wireless networks
Processor.
When implementation, by Multifunction Sensor, the work on the spot environment audio/video information of the employee, a life can be acquired
Data information is managed, and then obtains the working condition of the employee and real-time physiological health condition in conjunction with monitoring time can determine whether employee
Can whether pre-job physiological status meets physiological status in job position request or its work be competent at work at present, if not, to not
Satisfactory employee issues alarm in time, and suspends it and be on duty.In conventional Workplace, only to key link and weight can be played
The employee to be acted on is equipped with the condition monitoring system.
Compared with prior art, the employee status provided in this embodiment based on artificial intelligence monitors system, prepares in head
On helmet, wrist strap and safety working clothes, convenient for before each employee work dress, work when using, work after change clothes.It can also be directed to
The physiology and psychological condition of single employee, customizes different Multifunction Sensors, obtains the working condition of specific employee and specific
Real-time physiological health condition is further analyzed, and has functional expansionary.The real-time employee work scene that the system passes through acquisition
Environment audio/video information, individual physiological data information, instantaneous operating conditions (psychology) and the real-time physiological for judging automatically employee are strong
Health situation, and further judge before its hilllock whether physiological status meets physiological status in job position request or its work and can be competent at
Work at present.The systematic difference enables existing production activity to accomplish in advance actively prevention, monitors in thing and subsequent anti-
Feedback can remind and replace in time the employee for not meeting job position request, guarantee safety in production.It is proved through a large number of experiments, the system
Accuracy of judgement degree it is high, can satisfy manufacturing requirement.
Embodiment 2
It optimizes on the basis of embodiment 1, as shown in Fig. 2, the Multifunction Sensor, including miniature audio-video collection
Equipment and physiological data sensor.
Miniature audio-video acquisition equipment for acquiring the work on the spot environment audio/video information of the employee, and is transmitted
To message handler.In use, the miniature audio-video acquisition equipment can be placed in the helmet it is default connect fastly base position or
Add the interim base position matched, suitable position can be selected according to the actual situation.
Physiological data sensor for acquiring the non-real time physiological data information of the employee, and transmits it to information processing
Device.In use, the physiological data sensor to be placed on wrist strap 3 to the position for being not easy to collide with.The non-real time physiological data information
Including body temperature, breathing, palmic rate and alcohol content data.The physiological data sensor can be used existing body temperature, breathing,
Palmic rate and alcohol content detection sensor, repeat no more.
Preferably, miniature audio-video acquisition equipment further comprises high-definition camera, camera base, bracing means.Its
In, the back side of high-definition camera is designed using card slot protrusion;Phase is designed using with the card slot protrusion in the front of camera base
The groove design of cooperation, the back side are fixed on the default of the helmet by bracing means and connect base position fastly or add the interim bottom matched
At seat.Bracing means includes double-sided adhesive, velcro elastic band.Camera base, through the sticking double faced adhesive tape on the helmet, and
High-definition camera is bundled on employee's helmet by the velcro elastic band.
Preferably, message handler, including data processing module, data memory module and power supply module.Wherein, data are deposited
The data terminal of the data terminal and data processing module that store up module connects, and carries out bidirectional data transfers;The output end of power supply module point
Do not connect with the feeder ear of data processing module, data memory module, Multifunction Sensor.
Data processing module is known for work on the spot environment audio/video information, the individual physiological data information according to employee
The working condition of relevant device, the working condition of the employee and real-time physiological health in other working environment, and then judge hilllock previous existence
Can whether reason state meets physiological status in job position request, or work be competent at work at present, and show judging result and correlation
Alarm.
Data memory module, for storing work on the spot environment audio/video information, the individual physiological data information of employee, with
And whether meet physiological status before hilllock that job position request, can physiological status be competent at the judgement knot of work at present in work accordingly
Fruit and warning information;The connection of the data segment of its data terminal and data processing module.
Power supply module, for powering for data processing module, data memory module, Multifunction Sensor;Its output end point
It is not connect with the feeder ear of data processing module, data memory module, Multifunction Sensor.
The employee status for being preferably based on artificial intelligence monitors system, further includes live video acquisition equipment, communication module
With miniature headset, wherein the communication ends and headset end (audio that communication module and miniature headset are connect with data processing module respectively
Interface 8) connection.
Live video acquire equipment, for all employees in real-time collection site working environment facial expression, expression in the eyes and
Limb action information, and transmit it to the psychological condition identification that message handler carries out every employee.
Communication module, for by work on the spot environment audio/video information, the individual physiological data information of employee, and it is corresponding
Whether meet physiological status before hilllock that job position request, can physiological status be competent at the judging result and announcement of work at present in work
Alert information, is transmitted to external server, meanwhile, the instruction that external server issues is transmitted to data processing module and is shown
Show.
Miniature headset, for carrying out the work cooperation interaction between employee by communication module, employee shows higher level
Field situation report-back, higher level give employee to issue instruction information.
Preferably, message handler is sewed by velcro in the waist location of safety working clothes, or is stitched by velcro
It is formed on the closing waist elastic band 7 of safety working clothes.
Preferably, data processing module, including sequentially connected pretreatment submodule, classification prediction submodule, display
Module.
Pre-process submodule, for identification in work on the spot environment every employee facial expression, expression in the eyes and limb action,
It identifies the field device operating condition of employee operation in work on the spot environment, and individual physiological data information is carried out at noise reduction
Then recognition result and noise reduction process result are transmitted to the classification respectively and predict submodule by reason.Specifically, to micro-sound
The audio, video data that video capture device obtains carries out single frames target identification, obtains the field device of current time employee operation
Signal lamp opening and closing information and other special prompt informations (audio-video prompt information), as the operating condition of field device
Distinguishing indexes;Human body and four limbs positioning are carried out to the collected video before and after frames picture of live video acquisition equipment and face is known
Not, certain period employee's limb action will be characterized in human body and four limbs positioning result whether there is or not the distinguishes data of aggressive behavior letters
Breath, as the limb action of the employee in work on the spot environment distinguishing indexes (for example, can by actual act amplitude size with
Threshold value comparison judges that whether there is or not aggressive behaviors for certain period employee's limb action), by different moments employee in face recognition result
Nozzle type, eyes size and shape, the distinguishing indexes as the facial expression, expression in the eyes of the employee in work on the spot environment;And to more
The individual physiological data information that function sensor obtains carries out noise reduction process;It then, respectively will be at above-mentioned distinguishing indexes and noise reduction
Reason result is transmitted to the classification prediction submodule.Other above-mentioned special prompt informations include the alarm sound of field device, scene
The screen display content of equipment, the other equipment signal lamp opening and closing information to cooperate with field device etc..
Above-mentioned noise reduction process, including by carrying out curve fitting to collected individual physiological Data Data information, remove
Discrete noise point and burr, to achieve the purpose that remove dryness collected initial data.Optionally, micro-sound can also be regarded
The audio, video data and the collected video of live video acquisition equipment that frequency acquisition equipment obtains carry out denoising.
Classification prediction submodule is made the following judgment by the good 3 classes classification prediction model of precondition: firstly, will show
The distinguishing indexes of the field device operating condition of employee operation in the working environment of field, the good first kind classification of input precondition
Prediction model obtains the judging result whether relevant field devices open;Secondly, by the noise reduction process of individual physiological data information
As a result, the two classification prediction model that input precondition is good, show that can the real-time physiological health of the employee be competent at continuation
The judging result of work issues not competent alarm if not competent work;Then, by the employee in work on the spot environment
Facial expression, expression in the eyes and limb action information distinguishing indexes input the good third class classification prediction mould of precondition respectively
Type, show whether employee's psychological condition is in the judging result of fatigue and degree of fatigue, and issues the fatigue of appropriate level
Alarm;Finally, whether physiological status meets job position request before judging the employee hilllock, physiology and the heart in work in conjunction with monitoring time
Can reason state be competent at work at present.
Display module, for the above-mentioned judging result of real-time display and related alarm.
Optionally, supporting vector machine model or existing neural network model can be used in above-mentioned 3 class classification prediction model.
Preferably, classification prediction submodule is trained 3 classes classification prediction model using following steps:
S1. acquisition multiple groups include the distinguishing indexes of field device operating condition, corresponding field device open and close knot
The training data of fruit, classification storage establish training dataset, the training data input first kind point that the training data is concentrated
Class prediction model obtains the parameter of first kind classification prediction model, completes the training to first kind classification prediction model.
S2. can acquisition multiple groups competent comprising employee's individual physiological data, the real-time physiological health of corresponding employee
As a result training data, classification storage establish training dataset, and the training data that the training data is concentrated inputs the second class
Classification prediction model, obtains the parameter of two classification prediction model, completes the training to two classification prediction model;
S3. acquisition multiple groups include facial expression, expression in the eyes and the limb action under the frightened different mental state of employee's happiness, anger, grief and joy
Index, the real-time mental health of corresponding employee can competent result training data, by training data input the
Three classes classification prediction model, obtains the parameter of third class classification prediction model, completes the training to third class classification prediction model.
It will be understood by those skilled in the art that realizing all or part of the process of above-described embodiment method, meter can be passed through
Calculation machine program is completed to instruct relevant hardware, and the program can be stored in computer readable storage medium.Wherein, institute
Stating computer readable storage medium is disk, CD, read-only memory or random access memory etc..
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
In the technical scope disclosed by the present invention, any changes or substitutions that can be easily thought of by anyone skilled in the art,
It should be covered by the protection scope of the present invention.
Claims (10)
1. a kind of employee status based on artificial intelligence monitors system characterized by comprising be set to the helmet, on wrist strap
Multifunction Sensor, the message handler being set on the safety working clothes of employee's wearing;
The Multifunction Sensor, for acquiring work on the spot environment audio/video information, the individual physiological data information of the employee,
And transmit it to message handler;
The message handler, for work on the spot environment audio/video information, the individual physiological data information according to the employee,
It identifies the working condition and real-time physiological health condition of the employee, and then judges before its hilllock whether physiological status meets post and want
Ask or its work in physiological status can be competent at work at present, show judging result.
2. the employee status according to claim 1 based on artificial intelligence monitors system, which is characterized in that described multi-functional
Sensor, comprising:
The miniature audio-video acquisition equipment being set on the helmet, for acquiring the work on the spot environment audio/video information of the employee,
And transmit it to message handler;
The physiological data sensor being set on wrist strap for acquiring the non-real time physiological data information of the employee, and is transmitted
To message handler.
3. the employee status according to claim 2 based on artificial intelligence monitors system, which is characterized in that the micro-sound
Video capture device, including high-definition camera, camera base, bracing means;Wherein,
It is designed using card slot protrusion at the back side of the high-definition camera;The front of the camera base is using prominent with the card slot
Play the groove design that matches of design, the back side is fixed on the default of the helmet by bracing means and connects base position fastly or plus match
Interim base position.
4. the employee status according to claim 3 based on artificial intelligence monitors system, which is characterized in that the reinforcing dress
It sets including double-sided adhesive, velcro elastic band;Wherein,
The camera base, through the sticking double faced adhesive tape on the helmet, and by the velcro elastic band by institute
High-definition camera is stated to be bundled on employee's helmet.
5. the employee status according to one of claim 2-4 based on artificial intelligence monitors system, which is characterized in that described
At least one of non-real time physiological data information of employee, including body temperature, breathing, palmic rate and alcohol content data.
6. the employee status described in one of -4 based on artificial intelligence monitors system according to claim 1, which is characterized in that described
Message handler, comprising:
Data processing module identifies work for work on the spot environment audio/video information, the individual physiological data information according to employee
Make the working condition of relevant device in environment, the working condition of the employee and real-time physiological health, and then before judging the employee hilllock
Whether physiological status meets job position request, and can physiological status be competent at work at present in work, and show judging result and correlation
Alarm;
Data memory module, for storing the work on the spot environment audio/video information, individual physiological data information, and it is corresponding
Whether meet physiological status before hilllock that job position request, can physiological status be competent at the judging result and phase of work at present in work
Close alarm;Its data terminal is connect with the data terminal of above-mentioned data processing module;
Power supply module, for powering for the data processing module, data memory module, Multifunction Sensor;Its output end point
It is not connect with the feeder ear of data processing module, data memory module, Multifunction Sensor.
7. the employee status according to claim 6 based on artificial intelligence monitors system, which is characterized in that further include scene
Video capture device;
The live video acquires equipment, for all employees in real-time collection site working environment facial expression, expression in the eyes and
Limb action information, and transmit it to message handler.
8. employee status according to claim 7 based on artificial intelligence monitors system, which is characterized in that further include and institute
State the communication module and miniature headset that data processing module connects;
The communication module, for by work on the spot environment audio/video information, the individual physiological data information of employee, and it is corresponding
Whether meet physiological status before hilllock that job position request, can physiological status be competent at the judging result and phase of work at present in work
Alarm is closed, external server is transmitted to, meanwhile, the instruction that external server issues is transmitted to data processing module and is shown
Show;
The miniature headset, the work for being carried out between employee by communication module cooperate information exchange, employee to upper grading
Row field condition is reported, higher level issues to employee and indicates information.
9. the employee status according to claim 7 or 8 based on artificial intelligence monitors system, which is characterized in that the number
According to processing module, including sequentially connected pretreatment submodule, classification prediction submodule, display sub-module;Wherein,
The pretreatment submodule, the audio, video data information for obtaining to Multifunction Sensor carry out target identification, obtain
The signal lamp opening and closing information and audio-video prompt information of the field device of current time employee operation, as field device
The distinguishing indexes of operating condition;Human body and four limbs positioning and people are carried out to the collected before and after frames picture of live video acquisition equipment
Face identification, certain period employee's limb action will be characterized in human body and four limbs positioning result, and whether there is or not the distinguishes datas of aggressive behavior
Information, as the distinguishing indexes of the limb action of the employee in work on the spot environment, by different moments person in face recognition result
Nozzle type, the eyes size and shape of work, the distinguishing indexes as the facial expression, expression in the eyes of the employee in work on the spot environment;And
Noise reduction process is carried out to the individual physiological data information that Multifunction Sensor obtains;Then, respectively by above-mentioned distinguishing indexes and drop
Processing result of making an uproar is transmitted to the classification prediction submodule;
Submodule is predicted in the classification, is made the following judgment by the good 3 classes classification prediction model of precondition: firstly, will show
The distinguishing indexes of the field device operating condition of employee operation in the working environment of field, the good first kind classification of input precondition
Prediction model obtains the judging result whether relevant field devices open;Secondly, by the noise reduction process of individual physiological data information
As a result, the two classification prediction model that input precondition is good, show that can the real-time physiological health of the employee be competent at continuation
The judging result of work issues not competent alarm if not competent work;Then, by the employee in work on the spot environment
Facial expression, expression in the eyes and limb action information distinguishing indexes input the good third class classification prediction mould of precondition respectively
Type, show whether employee's psychological condition is in the judging result of fatigue and degree of fatigue, and issues the fatigue of appropriate level
Alarm;Finally, whether physiological status meets job position request before judging the employee hilllock, physiology and the heart in work in conjunction with monitoring time
Can reason state be competent at work at present;
The display module, for the above-mentioned judging result of real-time display and related alarm.
10. the employee status according to claim 9 based on artificial intelligence monitors system, which is characterized in that the classification
It predicts submodule, 3 class classification prediction model is trained using following steps:
Acquire the training that multiple groups include the distinguishing indexes of field device operating condition, corresponding field device opens and closes result
Training data input first kind classification prediction model is obtained the parameter of first kind classification prediction model, completion pair by data
The training of first kind classification prediction model;
Acquire multiple groups include employee's individual physiological data, the real-time physiological health of corresponding employee can competent result instruction
Practice data, the training data is inputted into two classification prediction model, obtains the parameter of two classification prediction model, is completed
Training to two classification prediction model;
Acquiring multiple groups includes that employee's happiness, anger, grief and joy shy facial expression, expression in the eyes and limb action index, right under different mental state
The real-time mental health of the employee answered can competent result training data, by the training data input third class classification
Prediction model obtains the parameter of third class classification prediction model, completes the training to third class classification prediction model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910081688.3A CN109686447B (en) | 2019-01-28 | 2019-01-28 | Staff state monitoring system based on artificial intelligence |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910081688.3A CN109686447B (en) | 2019-01-28 | 2019-01-28 | Staff state monitoring system based on artificial intelligence |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109686447A true CN109686447A (en) | 2019-04-26 |
CN109686447B CN109686447B (en) | 2021-09-14 |
Family
ID=66195011
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910081688.3A Active CN109686447B (en) | 2019-01-28 | 2019-01-28 | Staff state monitoring system based on artificial intelligence |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109686447B (en) |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110232506A (en) * | 2019-05-24 | 2019-09-13 | 中国人民解放军总医院 | A kind of pharmacist deploys the real time evaluating method and system of state |
CN110276589A (en) * | 2019-05-23 | 2019-09-24 | 珠海纳奥智能装备有限公司 | A kind of enterprise is health management system arranged and method |
CN110348340A (en) * | 2019-06-26 | 2019-10-18 | 秒针信息技术有限公司 | The sending method and device of information warning, storage medium and electronic device |
CN110507297A (en) * | 2019-08-30 | 2019-11-29 | 深圳市汇健医疗工程有限公司 | Surgicenter wisdom surgical intervention platform based on 5G network |
CN110522426A (en) * | 2019-09-05 | 2019-12-03 | 大连海事大学 | A kind of ship personnel behavior intelligent monitor system based on multisensor |
CN110738120A (en) * | 2019-09-17 | 2020-01-31 | 平安科技(深圳)有限公司 | Environment data adjusting method and device, electronic equipment and medium |
CN111368737A (en) * | 2020-03-04 | 2020-07-03 | 开放智能机器(上海)有限公司 | System and method for automatically analyzing working behaviors of staff |
CN111696673A (en) * | 2020-05-08 | 2020-09-22 | 吕小民 | Mental health management model system and method |
CN112185191A (en) * | 2020-09-21 | 2021-01-05 | 信阳职业技术学院 | Intelligent digital teaching model |
CN112633615A (en) * | 2021-03-15 | 2021-04-09 | 北京孵家科技股份有限公司 | Operation decision method, device and system based on artificial neural network |
CN112766576A (en) * | 2021-01-22 | 2021-05-07 | 无锡市第五人民医院 | Parameter result prediction method and system based on database |
CN113240396A (en) * | 2021-05-20 | 2021-08-10 | 北京明略昭辉科技有限公司 | Method, device and equipment for analyzing working state of employee and storage medium |
CN113491510A (en) * | 2021-07-09 | 2021-10-12 | 国家电网公司华中分部 | Dispatcher training result evaluation method and system based on intelligent wearable equipment |
CN113509156A (en) * | 2021-05-28 | 2021-10-19 | 郑州轻工业大学 | Adaptive information processing method, system and storage medium based on behavior characteristics of old user |
CN113520308A (en) * | 2020-04-21 | 2021-10-22 | 动联国际股份有限公司 | Health management system and health management method |
WO2022019826A1 (en) * | 2020-07-20 | 2022-01-27 | Hitachi, Ltd. | Scheduling system, methods of operating and forming the same |
CN116884649A (en) * | 2023-09-06 | 2023-10-13 | 山西数字政府建设运营有限公司 | Control system for monitoring user safety |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101753743A (en) * | 2009-12-23 | 2010-06-23 | 中国安全生产科学研究院 | Major accident mobile monitoring and commanding platform system and working method thereof |
CN104992280A (en) * | 2015-06-29 | 2015-10-21 | 中国民用航空厦门空中交通管理站 | Air traffic controller security ability automatic monitoring system based on intelligent headset |
CN105342557A (en) * | 2015-09-30 | 2016-02-24 | 上海建工二建集团有限公司 | Personnel status monitoring system for inverse construction method |
CN106725536A (en) * | 2017-03-17 | 2017-05-31 | 珠海博翔科技有限公司 | The high-risk work health monitor on duty of intelligence |
CN107370986A (en) * | 2017-06-29 | 2017-11-21 | 北京天泰怡和科技有限公司 | Intelligent distribution network field operation Safety system |
CN207909307U (en) * | 2018-02-07 | 2018-09-25 | 中国石油化工股份有限公司 | A kind of driller operating personnel's fatigue monitoring and prior-warning device |
CN108596792A (en) * | 2018-05-09 | 2018-09-28 | 安徽老乡鸡餐饮有限公司 | Improve the device of Customer Experience |
CN207992779U (en) * | 2017-12-22 | 2018-10-19 | 深圳市前海公共安全科学研究院有限公司 | A kind of construction personnel's behavior intelligent monitoring system |
CN208225253U (en) * | 2018-01-30 | 2018-12-11 | 国网陕西省电力公司安康水力发电公司 | A kind of anti-fall visualizing monitor early warning system of high altitude operation |
CN109044266A (en) * | 2018-09-10 | 2018-12-21 | 中国矿业大学(北京) | Based on wearable device to the intelligent recognition and control device of coal mine staff safe condition |
-
2019
- 2019-01-28 CN CN201910081688.3A patent/CN109686447B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101753743A (en) * | 2009-12-23 | 2010-06-23 | 中国安全生产科学研究院 | Major accident mobile monitoring and commanding platform system and working method thereof |
CN104992280A (en) * | 2015-06-29 | 2015-10-21 | 中国民用航空厦门空中交通管理站 | Air traffic controller security ability automatic monitoring system based on intelligent headset |
CN105342557A (en) * | 2015-09-30 | 2016-02-24 | 上海建工二建集团有限公司 | Personnel status monitoring system for inverse construction method |
CN106725536A (en) * | 2017-03-17 | 2017-05-31 | 珠海博翔科技有限公司 | The high-risk work health monitor on duty of intelligence |
CN107370986A (en) * | 2017-06-29 | 2017-11-21 | 北京天泰怡和科技有限公司 | Intelligent distribution network field operation Safety system |
CN207992779U (en) * | 2017-12-22 | 2018-10-19 | 深圳市前海公共安全科学研究院有限公司 | A kind of construction personnel's behavior intelligent monitoring system |
CN208225253U (en) * | 2018-01-30 | 2018-12-11 | 国网陕西省电力公司安康水力发电公司 | A kind of anti-fall visualizing monitor early warning system of high altitude operation |
CN207909307U (en) * | 2018-02-07 | 2018-09-25 | 中国石油化工股份有限公司 | A kind of driller operating personnel's fatigue monitoring and prior-warning device |
CN108596792A (en) * | 2018-05-09 | 2018-09-28 | 安徽老乡鸡餐饮有限公司 | Improve the device of Customer Experience |
CN109044266A (en) * | 2018-09-10 | 2018-12-21 | 中国矿业大学(北京) | Based on wearable device to the intelligent recognition and control device of coal mine staff safe condition |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110276589A (en) * | 2019-05-23 | 2019-09-24 | 珠海纳奥智能装备有限公司 | A kind of enterprise is health management system arranged and method |
CN110232506A (en) * | 2019-05-24 | 2019-09-13 | 中国人民解放军总医院 | A kind of pharmacist deploys the real time evaluating method and system of state |
CN110348340A (en) * | 2019-06-26 | 2019-10-18 | 秒针信息技术有限公司 | The sending method and device of information warning, storage medium and electronic device |
CN110507297A (en) * | 2019-08-30 | 2019-11-29 | 深圳市汇健医疗工程有限公司 | Surgicenter wisdom surgical intervention platform based on 5G network |
CN110522426A (en) * | 2019-09-05 | 2019-12-03 | 大连海事大学 | A kind of ship personnel behavior intelligent monitor system based on multisensor |
CN110738120A (en) * | 2019-09-17 | 2020-01-31 | 平安科技(深圳)有限公司 | Environment data adjusting method and device, electronic equipment and medium |
CN110738120B (en) * | 2019-09-17 | 2024-02-09 | 平安科技(深圳)有限公司 | Environment data adjustment method and device, electronic equipment and medium |
CN111368737A (en) * | 2020-03-04 | 2020-07-03 | 开放智能机器(上海)有限公司 | System and method for automatically analyzing working behaviors of staff |
CN113520308A (en) * | 2020-04-21 | 2021-10-22 | 动联国际股份有限公司 | Health management system and health management method |
CN111696673A (en) * | 2020-05-08 | 2020-09-22 | 吕小民 | Mental health management model system and method |
WO2022019826A1 (en) * | 2020-07-20 | 2022-01-27 | Hitachi, Ltd. | Scheduling system, methods of operating and forming the same |
CN112185191A (en) * | 2020-09-21 | 2021-01-05 | 信阳职业技术学院 | Intelligent digital teaching model |
CN112766576A (en) * | 2021-01-22 | 2021-05-07 | 无锡市第五人民医院 | Parameter result prediction method and system based on database |
CN112633615A (en) * | 2021-03-15 | 2021-04-09 | 北京孵家科技股份有限公司 | Operation decision method, device and system based on artificial neural network |
CN113240396A (en) * | 2021-05-20 | 2021-08-10 | 北京明略昭辉科技有限公司 | Method, device and equipment for analyzing working state of employee and storage medium |
CN113509156A (en) * | 2021-05-28 | 2021-10-19 | 郑州轻工业大学 | Adaptive information processing method, system and storage medium based on behavior characteristics of old user |
CN113509156B (en) * | 2021-05-28 | 2023-12-15 | 郑州轻工业大学 | Self-adaptive information processing method, system and storage medium based on behavioral characteristics of old users |
CN113491510A (en) * | 2021-07-09 | 2021-10-12 | 国家电网公司华中分部 | Dispatcher training result evaluation method and system based on intelligent wearable equipment |
CN116884649A (en) * | 2023-09-06 | 2023-10-13 | 山西数字政府建设运营有限公司 | Control system for monitoring user safety |
CN116884649B (en) * | 2023-09-06 | 2023-11-17 | 山西数字政府建设运营有限公司 | Control system for monitoring user safety |
Also Published As
Publication number | Publication date |
---|---|
CN109686447B (en) | 2021-09-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109686447A (en) | A kind of employee status's monitoring system based on artificial intelligence | |
US10092236B2 (en) | Emergency medical services smart watch | |
CN103179897B (en) | A method and a system for monitoring of sleep and other physiological conditions | |
JP2008503268A (en) | System and method for real-time physiological monitoring | |
CN207024470U (en) | A kind of rope skipping system | |
CN106264500A (en) | A kind of telemedicine method and system | |
CN204813800U (en) | Intelligent intervention system of full -automatic health | |
CN105852840A (en) | Heart rhythm monitoring device | |
CN104825143A (en) | Remote health monitoring system | |
CN107393042A (en) | Child intelligence peace system and its method of work under big data background | |
WO2019047428A1 (en) | Pulse monitoring device and system | |
CN207992779U (en) | A kind of construction personnel's behavior intelligent monitoring system | |
CN106485877A (en) | The monitoring method of intelligence and system | |
CN107495947A (en) | Blood pressure dynamic analysis method and blood pressure measuring device | |
CN206542449U (en) | A kind of intelligent health terminal system | |
CN108044634A (en) | A kind of intelligent robot of health physical therapy service | |
CN209299531U (en) | A kind of police monitoring system based on Intelligent bracelet | |
CN211381321U (en) | Portable heart rate monitoring feedback system | |
CN111544720A (en) | Method and system for identifying false positive alarm of breathing machine | |
CN106236043A (en) | A kind of interactive intelligent Medical hand loop systems | |
CN106073061A (en) | A kind of Intelligent bracelet of adjustable temperature | |
CN206462986U (en) | A kind of bracelet for being used to guard | |
CN205612465U (en) | Wearing formula electrocardio at night monitoring system | |
CN208607701U (en) | A kind of internet of things intelligent household educational system | |
CN208354799U (en) | A kind of management bracelet applied to supervision place |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |