CN108198265A - Attendance checking system based on voice and face composite identification - Google Patents
Attendance checking system based on voice and face composite identification Download PDFInfo
- Publication number
- CN108198265A CN108198265A CN201810204478.4A CN201810204478A CN108198265A CN 108198265 A CN108198265 A CN 108198265A CN 201810204478 A CN201810204478 A CN 201810204478A CN 108198265 A CN108198265 A CN 108198265A
- Authority
- CN
- China
- Prior art keywords
- attendance
- voice
- signal
- main equipment
- recognition
- 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
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
- G07C1/10—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people together with the recording, indicating or registering of other data, e.g. of signs of identity
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a kind of attendance checking system based on voice and face composite identification, including Time Attendance Device, Cloud Server and mobile terminal;Time Attendance Device includes main equipment and the photographic device, microphone array and the door lock device that are connected respectively with the main equipment, further includes the human body detection sensor being connected respectively with the main equipment, optical sensor, lighting device and public address system.The present invention uses the attendance mode of " zero carries, is contactless ", and checked-in person person does not need to carry card, without brush finger line etc., significantly improves the convenience of system, user can be accessed by APP, easy to use.
Description
Technical field
The invention belongs to attendance technical field more particularly to a kind of attendance checking systems based on voice and face composite identification.
Background technology
Many enterprises and institutions are by swiping the card or fingerprint recognition is come attendance at present.Attendance of swiping the card is each employee equipped with only
One personal information card, existence information card leaves behind or Loss, and safety is not high, while there is also generations to check card phenomenon,
It can not ensure the accuracy and fairness of attendance;Fingerprint recognition for attendance checking, due to the attendance mode of its contact, user experience is not
It is good, it needs often to clean fingerprint extracting device, cost of equipment maintenance is high;In addition, above two attendance mode is due to being contact
Attendance, attendance position are fixed, and easily attendance congestion phenomenon occur in peak time on and off duty.With the hair of artificial intelligence technology
Exhibition, the Work attendance method based on recognition of face starts landing application, but this method is used for the face of authentication easily by environment
The variation of illumination causes attendance to fail, and " emotion zero interacts " also largely affects user's between attendance checking system and people
Experience.
Invention content
The present invention goal of the invention be:In order to solve problem above in the prior art, the present invention proposes one kind
Attendance checking system based on voice and face composite identification.
The technical scheme is that:A kind of attendance checking system based on voice and face composite identification, including
Time Attendance Device for acquiring video signal and voice signal, downloads multiple classification of training in Cloud Server
Device model is identified to obtain attendance record and be uploaded to cloud to take using sorter model to video signal and voice signal
Business device, while export the opening and closing of control signal control door lock device;
Cloud Server, for generating recognition of face, Application on Voiceprint Recognition sorter model using log-on data and algorithms library training,
Preserve the attendance record that the Time Attendance Device uploads;
Mobile terminal obtains attendance record for accessing Cloud Server.
Further, the Time Attendance Device includes main equipment and the photographic device being connected respectively with the main equipment, wheat
Gram wind array and door lock device;The photographic device is used to acquire video signal and is transmitted to main equipment;The microphone
Array is for collected sound signal and is transmitted to main equipment;The main equipment for respectively with the Cloud Server and mobile terminal into
Row data communication.
Further, the Time Attendance Device be additionally operable to acquisition setting human-computer interaction sentence voice signal and multiple do not share the same light
Face image signal according under the conditions of downloads the speech recognition of training, Expression Recognition, emotion recognition grader mould in Cloud Server
Type;Human-computer interaction sentence voice signal is identified using sorter model, Checking on Work Attendance Mode is switched according to recognition result;It utilizes
Sorter model, which is identified face image signal and combines voice signal recognition result, carries out sentiment analysis, and output voice carries
Show signal to public address system.
Further, the Time Attendance Device further includes the human body detection sensor being connected respectively with the main equipment, light
According to sensor, lighting device and public address system;The human body detection sensor is used to acquire human perceptual signal;The illumination passes
Sensor is used to acquire ambient lighting perceptual signal;The lighting device is used to provide ambient lighting;The public address system is used for root
Voice prompt is played according to the voice prompt signal that the Time Attendance Device is sent.
Further, the log-on data is specifically using the human-computer interaction sentence voice and a variety of of Time Attendance Device acquisition setting
Face image under illumination condition, and obtain userspersonal information using mobile terminal.
The invention has the advantages that:(1) the attendance mode of " zero carries, is contactless ", checked-in person person are used
It does not need to carry card, without brush finger line etc., significantly improves the convenience of system;
(2) it can be organically combined with safety-protection system, attendance data is stored in high in the clouds, convenient for tether management;
(3) user can be accessed by APP, easy to use;
(4) attendance mode more hommization, emotional culture, user experience are good.
Description of the drawings
Fig. 1 is the structure diagram of the attendance checking system based on voice and face composite identification of the present invention.
Specific embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, with reference to the accompanying drawings and embodiments, it is right
The present invention is further elaborated.It should be appreciated that specific embodiment described herein is only to explain the present invention, not
For limiting the present invention.
As shown in Figure 1, the structure diagram of the attendance checking system based on voice and face composite identification for the present invention.It is a kind of
Attendance checking system based on voice and face composite identification, including
Time Attendance Device for acquiring video signal and voice signal, downloads multiple classification of training in Cloud Server
Device model is identified to obtain attendance record and be uploaded to cloud to take using sorter model to video signal and voice signal
Business device, while export the opening and closing of control signal control door lock device;
Cloud Server, for generating recognition of face, Application on Voiceprint Recognition sorter model using log-on data and algorithms library training,
Preserve the attendance record that the Time Attendance Device uploads;
Mobile terminal obtains attendance record for accessing Cloud Server.
In an alternate embodiment of the present invention where, above-mentioned Time Attendance Device is additionally operable to the human-computer interaction sentence language of acquisition setting
Face image signal under sound signal and multiple different illumination conditions downloads the speech recognition of training in Cloud Server, expression is known
Not, emotion recognition sorter model;Human-computer interaction sentence voice signal is identified using sorter model, is tied according to identification
Fruit switches Checking on Work Attendance Mode;Face image signal is identified using sorter model and combines the progress of voice signal recognition result
Sentiment analysis, output voice prompt signal to public address system.Time Attendance Device specifically include main equipment and respectively with the main equipment
Photographic device, microphone array and the door lock device being connected, further include the human testing being connected respectively with the main equipment
Sensor, optical sensor, lighting device and public address system.
In an alternate embodiment of the present invention where, above-mentioned photographic device is used to acquire video signal and is transmitted to master
Kinco bright eyes XP2S binocular cameras may be used in equipment, the realization of the function.
In an alternate embodiment of the present invention where, above-mentioned microphone array for collected sound signal and is transmitted to main set
Standby, hundred degree of DuerOS intelligent sounds control 6 microphone arrays of development board of SoundPi- may be used in the realization of the function.
In an alternate embodiment of the present invention where, above-mentioned door lock device is used for according to control signal control door lock device
It opens and closes.
In an alternate embodiment of the present invention where, above-mentioned human body detection sensor, should for acquiring human perceptual signal
Risym human body infrared induction modules, HC-SR501 may be used in the realization of function.
In an alternate embodiment of the present invention where, above-mentioned optical sensor, should for acquiring ambient lighting perceptual signal
GY-485-44009 high-precision RS485 illuminance luminous intensity brightness module sensors modules may be used in the realization of function.
In an alternate embodiment of the present invention where, above-mentioned lighting device is used to provide ambient lighting.
In an alternate embodiment of the present invention where, above-mentioned public address system is used for the voice sent according to the Time Attendance Device
Standby signal plays voice prompt.
In an alternate embodiment of the present invention where, above-mentioned mobile terminal can be with cloud by cell phone application for attendance user
Server and the communication of intelligent Checking on Work Attendance equipment, check personal attendance information, also can submit and change part individual's essential information.
In an alternate embodiment of the present invention where, above-mentioned Cloud Server is believed substantially for the individual of storing user's registered
Breath, face information, voice messaging and attendance record;Using log-on data and algorithms library training generation recognition of face, Expression Recognition,
The Intelligence Classifiers model such as speech recognition, Application on Voiceprint Recognition and emotion recognition.
In an alternate embodiment of the present invention where, above-mentioned main equipment realizes human body for connecting various external collecting devices
It is perceived with illumination, acquisition video and sound, control lighting device light filling, control door lock device switch and control public address system are broadcast
It puts;It is additionally operable to communicate with Cloud Server, uploads attendance information, download new grader or program carries out module update or work(
It can upgrade, communicate in LAN with APP, realize that data double-way transmits.
In an alternate embodiment of the present invention where, above-mentioned Time Attendance Device include algorithm maintenance module, speech processing module,
Face recognition module, memory module and other common modules;Algorithm maintenance module is used to add, delete, update speech recognition, sound
Line identification, Expression Recognition, recognition of face and emotion recognition algorithm classification model;Speech processing module is used to acquiring and exporting language
Sound, registered user's vocal print and voice, vocal print to input and voice carry out feature extraction and identification, and can according to input voice into
The sentiment analysis of row speaker and judgement;Face recognition module monitors face and is identified in real time for acquisition and registered face
Attendance judges the expression of attendance people, and combines voice and carry out sentiment analysis, then carries out corresponding interactive voice;Memory module
Comprising storage medium, for data such as storaged voice, vocal print, face, expression, algorithm, personnel and attendances;Other common module packets
Include the functions such as Web system, system maintenance, system communication, equipment management and personal management.
User needs first to carry out user's registration, be as follows when carrying out the attendance checking system using the present invention:
A1, acquisition user voice to be registered (the human-computer interaction sentence voice specified, each sentence need acquisition 3 times with
On);
A2, acquisition user's facial image to be registered (face image 5 under various illumination open more than);
A3, input registered user information (containing information such as number, name, phones);
A4, the voice and vocal print feature that voice is acquired by corresponding deep learning model learning;
A5, the face characteristic and expressive features that face is acquired by corresponding deep learning model learning;
A6, speech recognition modeling training is carried out according to the phonetic feature extracted;
A7, Application on Voiceprint Recognition model training is carried out according to the vocal print feature extracted;
A8, human face recognition model training is carried out according to the face characteristic learnt;
A9, Expression Recognition model training is carried out according to the expressive features learnt;
After the completion of user's registration, attendance operation is carried out, is as follows:
B1, acquisition user attendance wake up sound;
Attendance facial image is treated in B2, acquisition;
B3, the voice and vocal print feature that voice is acquired by corresponding deep learning model learning;
B4, the face characteristic and expressive features that face is acquired by corresponding deep learning model learning;
B5, speech recognition is carried out according to the phonetic feature extracted;
B6, Application on Voiceprint Recognition is carried out according to the vocal print feature extracted;
B7, recognition of face is carried out according to the face characteristic learnt;
B8, Expression Recognition is carried out according to the expressive features learnt;
B9, user identity is verified, and record attendance record according to recognition of face and vocal print recognition result, it is defeated on a monitor
Go out the prompt message of attendance success or not;
B10, sentiment analysis is carried out according to facial expression recognition result and voice recognition result;
B11, the voice prompt that corresponding mood is played according to sentiment analysis result, help employee to put down worried and negative feelings
Thread easily works, so as to improve working efficiency.
The attendance checking system of the present invention can be waken up attendance recorder by voice and enter checking-in state, can perform under non-checking-in state
General security monitoring function, and using the attendance interactive mode of " emotional culture ", in addition to traditional attendance, this intelligent Checking on Work Attendance machine
Can also the affective state of employee be judged by the interactive voice and Expression Recognition with employee, and the prompt tones such as play love, inflate
Employee simply dredge at heart, employee is made to start one day Wonderful Job, depth is introduced in intelligent Checking on Work Attendance equipment
Model and method are practised, effectively improves attendance accuracy.
Those of ordinary skill in the art will understand that the embodiments described herein, which is to help reader, understands this hair
Bright principle, it should be understood that protection scope of the present invention is not limited to such specific embodiments and embodiments.This field
Those of ordinary skill can make according to these technical inspirations disclosed by the invention various does not depart from the other each of essence of the invention
The specific deformation of kind and combination, these deform and combine still within the scope of the present invention.
Claims (5)
1. a kind of attendance checking system based on voice and face composite identification, which is characterized in that including
Time Attendance Device for acquiring video signal and voice signal, downloads multiple grader moulds of training in Cloud Server
Type is identified to obtain attendance record and is uploaded to cloud service using sorter model to video signal and voice signal
Device, while export the opening and closing of control signal control door lock device;
Cloud Server, for using log-on data and algorithms library training generation recognition of face, Application on Voiceprint Recognition sorter model, preserving
The attendance record that the Time Attendance Device uploads;
Mobile terminal obtains attendance record for accessing Cloud Server.
2. the attendance checking system based on voice and face composite identification as described in claim 1, which is characterized in that the attendance is set
Standby photographic device, microphone array and the door lock device for including main equipment and being connected respectively with the main equipment;The camera shooting
Device is used to acquire video signal and is transmitted to main equipment;The microphone array is for collected sound signal and is transmitted to
Main equipment;The main equipment is for respectively with the Cloud Server and mobile terminal into row data communication.
3. the attendance checking system based on voice and face composite identification as claimed in claim 2, which is characterized in that the attendance is set
The standby face image signal being additionally operable under the human-computer interaction sentence voice signal and multiple different illumination conditions of acquisition setting, is downloaded
The speech recognition of training, Expression Recognition, emotion recognition sorter model in Cloud Server;Using sorter model to human-computer interaction
Sentence voice signal is identified, and switches Checking on Work Attendance Mode according to recognition result;Using sorter model to face image signal into
Row, which identifies and combines voice signal recognition result, carries out sentiment analysis, output voice prompt signal to public address system.
4. the attendance checking system based on voice and face composite identification as claimed in claim 3, which is characterized in that the attendance is set
It is standby to further include the human body detection sensor being connected respectively with the main equipment, optical sensor, lighting device and public address system;
The human body detection sensor is used to acquire human perceptual signal;The optical sensor perceives letter for acquiring ambient lighting
Number;The lighting device is used to provide ambient lighting;The voice that the public address system is used to be sent according to the Time Attendance Device carries
Show that signal plays voice prompt.
5. the attendance checking system based on voice and face composite identification as claimed in claim 4, which is characterized in that the registration number
According to the face image under specific human-computer interaction sentence voice and a variety of illumination conditions using Time Attendance Device acquisition setting, and utilize
Mobile terminal obtains userspersonal information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810204478.4A CN108198265A (en) | 2018-03-13 | 2018-03-13 | Attendance checking system based on voice and face composite identification |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810204478.4A CN108198265A (en) | 2018-03-13 | 2018-03-13 | Attendance checking system based on voice and face composite identification |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108198265A true CN108198265A (en) | 2018-06-22 |
Family
ID=62595555
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810204478.4A Pending CN108198265A (en) | 2018-03-13 | 2018-03-13 | Attendance checking system based on voice and face composite identification |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108198265A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109447563A (en) * | 2018-09-05 | 2019-03-08 | 平安科技(深圳)有限公司 | Voice Work attendance method, device, computer equipment and storage medium |
CN109887115A (en) * | 2018-12-30 | 2019-06-14 | 重庆智荟数创科技有限公司 | A kind of business administration fingerprint attendance system |
CN113225364A (en) * | 2020-10-29 | 2021-08-06 | 深圳市芯中芯科技有限公司 | AI intelligent monitoring attendance system and method |
CN116071842A (en) * | 2022-11-21 | 2023-05-05 | 深聪半导体(江苏)有限公司 | Voiceprint-based card punching method and system |
CN117314478A (en) * | 2023-11-30 | 2023-12-29 | 深圳市天兴诚科技有限公司 | RFID-based product full life cycle management and control system and method |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2003030706A (en) * | 2001-07-10 | 2003-01-31 | Sharp Corp | Method for managing information, method for managing attendance, attendance managing device, display screen, information management program and attendance management program |
CN102819744A (en) * | 2012-06-29 | 2012-12-12 | 北京理工大学 | Emotion recognition method with information of two channels fused |
CN103400145A (en) * | 2013-07-19 | 2013-11-20 | 北京理工大学 | Voice-vision fusion emotion recognition method based on hint nerve networks |
CN103530912A (en) * | 2013-09-27 | 2014-01-22 | 深圳市迈瑞思智能技术有限公司 | Attendance recording system having emotion identification function, and method thereof |
CN105354986A (en) * | 2015-11-12 | 2016-02-24 | 熊强 | Driving state monitoring system and method for automobile driver |
CN106446753A (en) * | 2015-08-06 | 2017-02-22 | 南京普爱医疗设备股份有限公司 | Negative expression identifying and encouraging system |
CN106709402A (en) * | 2015-11-16 | 2017-05-24 | 优化科技(苏州)有限公司 | Living person identity authentication method based on voice pattern and image features |
CN206711176U (en) * | 2017-04-11 | 2017-12-05 | 广州市贺氏办公设备有限公司 | A kind of cloud attendance recorder with gate function |
-
2018
- 2018-03-13 CN CN201810204478.4A patent/CN108198265A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2003030706A (en) * | 2001-07-10 | 2003-01-31 | Sharp Corp | Method for managing information, method for managing attendance, attendance managing device, display screen, information management program and attendance management program |
CN102819744A (en) * | 2012-06-29 | 2012-12-12 | 北京理工大学 | Emotion recognition method with information of two channels fused |
CN103400145A (en) * | 2013-07-19 | 2013-11-20 | 北京理工大学 | Voice-vision fusion emotion recognition method based on hint nerve networks |
CN103530912A (en) * | 2013-09-27 | 2014-01-22 | 深圳市迈瑞思智能技术有限公司 | Attendance recording system having emotion identification function, and method thereof |
CN106446753A (en) * | 2015-08-06 | 2017-02-22 | 南京普爱医疗设备股份有限公司 | Negative expression identifying and encouraging system |
CN105354986A (en) * | 2015-11-12 | 2016-02-24 | 熊强 | Driving state monitoring system and method for automobile driver |
CN106709402A (en) * | 2015-11-16 | 2017-05-24 | 优化科技(苏州)有限公司 | Living person identity authentication method based on voice pattern and image features |
CN206711176U (en) * | 2017-04-11 | 2017-12-05 | 广州市贺氏办公设备有限公司 | A kind of cloud attendance recorder with gate function |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109447563A (en) * | 2018-09-05 | 2019-03-08 | 平安科技(深圳)有限公司 | Voice Work attendance method, device, computer equipment and storage medium |
CN109887115A (en) * | 2018-12-30 | 2019-06-14 | 重庆智荟数创科技有限公司 | A kind of business administration fingerprint attendance system |
CN113225364A (en) * | 2020-10-29 | 2021-08-06 | 深圳市芯中芯科技有限公司 | AI intelligent monitoring attendance system and method |
CN113225364B (en) * | 2020-10-29 | 2022-05-27 | 深圳市芯中芯科技有限公司 | AI intelligent monitoring attendance system and method |
CN116071842A (en) * | 2022-11-21 | 2023-05-05 | 深聪半导体(江苏)有限公司 | Voiceprint-based card punching method and system |
CN117314478A (en) * | 2023-11-30 | 2023-12-29 | 深圳市天兴诚科技有限公司 | RFID-based product full life cycle management and control system and method |
CN117314478B (en) * | 2023-11-30 | 2024-03-19 | 深圳市天兴诚科技有限公司 | RFID-based product full life cycle management and control system and method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108198265A (en) | Attendance checking system based on voice and face composite identification | |
CN108470169A (en) | Face identification system and method | |
CN105654952B (en) | Electronic device, server and method for outputting voice | |
CN108537017B (en) | Method and equipment for managing game users | |
CN109769099B (en) | Method and device for detecting abnormality of call person | |
CN108098767A (en) | A kind of robot awakening method and device | |
WO2016172872A1 (en) | Method and device for verifying real human face, and computer program product | |
WO2021135685A1 (en) | Identity authentication method and device | |
CN109766759A (en) | Emotion identification method and Related product | |
CN109658923A (en) | Voice quality detecting method, equipment, storage medium and device based on artificial intelligence | |
CN108573202A (en) | Identity identifying method, device and system and terminal, server and storage medium | |
CN108039988A (en) | Equipment control processing method and device | |
CN105426723A (en) | Voiceprint identification, face identification and synchronous in-vivo detection-based identity authentication method and system | |
CN104361276A (en) | Multi-mode biometric authentication method and multi-mode biometric authentication system | |
TW201937344A (en) | Smart robot and man-machine interaction method | |
CN103530912A (en) | Attendance recording system having emotion identification function, and method thereof | |
CN208351494U (en) | Face identification system | |
CN109941231A (en) | Vehicle-mounted terminal equipment, vehicle-mounted interactive system and exchange method | |
EP3890342A1 (en) | Method and apparatus for awakening wearable device | |
CN112016367A (en) | Emotion recognition system and method and electronic equipment | |
CN110348409A (en) | A kind of method and apparatus that facial image is generated based on vocal print | |
CN109241924A (en) | Multi-platform information interaction system Internet-based | |
CN114242037A (en) | Virtual character generation method and device | |
CN107491757A (en) | A kind of antifraud system and control method based on living body characteristics | |
CN112087309A (en) | Management and education conversation integrated terminal equipment |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180622 |