CN117476234A - AI intelligent judging system for pre-post health detection - Google Patents
AI intelligent judging system for pre-post health detection Download PDFInfo
- Publication number
- CN117476234A CN117476234A CN202311691035.XA CN202311691035A CN117476234A CN 117476234 A CN117476234 A CN 117476234A CN 202311691035 A CN202311691035 A CN 202311691035A CN 117476234 A CN117476234 A CN 117476234A
- Authority
- CN
- China
- Prior art keywords
- data
- health
- identity
- evaluation
- state
- 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
- 230000036541 health Effects 0.000 title claims abstract description 118
- 238000001514 detection method Methods 0.000 title claims abstract description 76
- 238000000034 method Methods 0.000 claims abstract description 73
- 238000004080 punching Methods 0.000 claims abstract description 72
- 238000011156 evaluation Methods 0.000 claims description 90
- 230000007246 mechanism Effects 0.000 claims description 36
- 230000004044 response Effects 0.000 claims description 35
- 230000006870 function Effects 0.000 claims description 22
- 230000008569 process Effects 0.000 claims description 17
- 238000000605 extraction Methods 0.000 claims description 15
- 230000006996 mental state Effects 0.000 claims description 13
- 201000010099 disease Diseases 0.000 claims description 10
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 10
- 230000003862 health status Effects 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 10
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 9
- 239000008280 blood Substances 0.000 claims description 9
- 210000004369 blood Anatomy 0.000 claims description 9
- 230000036772 blood pressure Effects 0.000 claims description 9
- 229910052760 oxygen Inorganic materials 0.000 claims description 9
- 239000001301 oxygen Substances 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 230000036651 mood Effects 0.000 claims description 7
- 208000019901 Anxiety disease Diseases 0.000 claims description 6
- 206010003658 Atrial Fibrillation Diseases 0.000 claims description 6
- 206010062519 Poor quality sleep Diseases 0.000 claims description 6
- 230000036506 anxiety Effects 0.000 claims description 6
- 208000011775 arteriosclerosis disease Diseases 0.000 claims description 6
- 206010012601 diabetes mellitus Diseases 0.000 claims description 6
- 238000012854 evaluation process Methods 0.000 claims description 6
- 230000006698 induction Effects 0.000 claims description 6
- 230000029058 respiratory gaseous exchange Effects 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 5
- 230000001960 triggered effect Effects 0.000 claims description 4
- 238000013075 data extraction Methods 0.000 claims description 3
- 230000002526 effect on cardiovascular system Effects 0.000 claims description 3
- 238000002513 implantation Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000012790 confirmation Methods 0.000 claims 1
- 238000000638 solvent extraction Methods 0.000 claims 1
- 230000008451 emotion Effects 0.000 description 21
- 230000002159 abnormal effect Effects 0.000 description 14
- 230000009286 beneficial effect Effects 0.000 description 8
- 230000008859 change Effects 0.000 description 8
- 230000003340 mental effect Effects 0.000 description 8
- 238000013515 script Methods 0.000 description 8
- 230000035945 sensitivity Effects 0.000 description 6
- 208000024172 Cardiovascular disease Diseases 0.000 description 3
- 206010041349 Somnolence Diseases 0.000 description 3
- 230000001815 facial effect Effects 0.000 description 3
- 206010016256 fatigue Diseases 0.000 description 3
- 230000005714 functional activity Effects 0.000 description 3
- 238000011084 recovery Methods 0.000 description 3
- 238000013475 authorization Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000019771 cognition Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000008621 organismal health Effects 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 206010003210 Arteriosclerosis Diseases 0.000 description 1
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008909 emotion recognition Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 230000036449 good health Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
-
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063114—Status monitoring or status determination for a person or group
-
- 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
- G06Q10/10—Office automation; Time management
- G06Q10/105—Human resources
-
- 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
- G07C9/00—Individual registration on entry or exit
- G07C9/20—Individual registration on entry or exit involving the use of a pass
- G07C9/22—Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder
- G07C9/25—Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder using biometric data, e.g. fingerprints, iris scans or voice recognition
-
- 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
- G07C9/00—Individual registration on entry or exit
- G07C9/20—Individual registration on entry or exit involving the use of a pass
- G07C9/29—Individual registration on entry or exit involving the use of a pass the pass containing active electronic elements, e.g. smartcards
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Public Health (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Medical Informatics (AREA)
- Marketing (AREA)
- Databases & Information Systems (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Pathology (AREA)
- Development Economics (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Primary Health Care (AREA)
- Human Computer Interaction (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention provides an AI intelligent judging system for pre-post health detection, which comprises an identity judging module: acquiring biological characteristic information of a card punching person through an attendance checking and card punching device, and judging whether the person is an authorized worker or not; identity dividing module: the system is used for carrying out identity division when a card punching person is an authorized staff, and generating an identity identification pre-post acquisition module: the method comprises the steps of extracting identity information data of corresponding identity mark personnel according to the identity mark; health judgment module: the health state estimation module is used for estimating the health state according to the physical state data; and a result uploading module: and the health state estimation result is used for obtaining the health state estimation result and uploading the health state estimation result to the user side.
Description
Technical Field
The invention relates to the technical field of pre-post physical state detection, in particular to an AI intelligent judgment system for pre-post health detection.
Background
At present, all groups and institutions such as enterprises, public institutions, government institutions, organizations, individual organizations, individuals and the like work under the good and healthy state in management, control and monitoring, so that the work of the staff is a very important matter for all groups and institutions such as each enterprise, public institutions, government institutions, organizations, individual organizations, individuals and the like, and is more important for special and important posts and professions, for example, pilots, high-altitude operators, drivers, operators of vehicles and mechanical equipment facilities and the like, and when the staff with no good health state works, the staff not only brings potential safety hazards to the staff, but also can cause bad results to other people and society;
in the method, the device, the equipment and the storage medium for managing the health information of the patent 202010897849.9, a method for acquiring the physical examination report of the staff to judge the health state of the staff is proposed, however, the method only has an effect on the staff detected by physical examination, and cannot realize the detection of the state of the staff at the current moment.
Disclosure of Invention
The invention provides an AI intelligent judging system for pre-post health detection, which is used for solving the situation in the background technology.
The invention provides an AI intelligent judging system for pre-post health detection, comprising:
identity judging module: acquiring biological characteristic information of a card punching person through an attendance checking and card punching device, and judging whether the person is an authorized worker or not;
identity dividing module: the method is used for carrying out identity division when the card punching personnel is an authorized staff, and generating an identity mark
Front post acquisition module: the method comprises the steps of extracting identity information data of corresponding identity mark personnel according to the identity mark;
health judgment module: the health state estimation module is used for estimating the health state according to the physical state data;
and a result uploading module: and the health state estimation result is used for obtaining the health state estimation result and uploading the health state estimation result to the user side.
Preferably, the identity determination module includes:
sensing unit: the method comprises the steps of setting an induction area of an attendance card punching device, and starting a biological characteristic extraction mechanism when face information appears in the induction area;
face extraction unit: the face extraction method is used for extracting face data according to a biological feature extraction mechanism to obtain face features;
a matching identification unit: the method is used for carrying out feature matching in a preset identity database according to the face features and judging whether corresponding identification data exist or not;
a determination unit: and when the corresponding identification data exists, identifying the card punching personnel as authorized staff and extracting the identity data of the card punching personnel.
Preferably, the identity dividing module includes:
a work model unit: the method is used for constructing an work model for checking work attendance and punching cards and implanting identity information of workers of different work types;
and a response unit: the method comprises the steps of receiving a card punching response, and calling an identity recognition mechanism of a corresponding work class when receiving card punching information of authorized staff; wherein,
the identity recognition mechanism comprises a name extraction mechanism, a face comparison mechanism and a work content judgment mechanism;
a work pattern unit: the method comprises the steps of constructing a first work type requirement identification model according to the body health state requirements of different work types, and constructing a second work type requirement identification model according to the historical body state information of staff of different work types;
a mapping construction unit: the body detection atlas is used for constructing body detection atlas of different work types according to the identity recognition mechanism, the first work type requirement recognition model and the second work type requirement recognition model;
identity dividing unit: the method is used for carrying out identity division on different authorized staff according to the post detection map, and generating identity division information.
Preferably, the construction of the engineering model includes:
pre-building a punching template based on different industrial types, and setting implantation punching response on the punching template; wherein,
the card punching response comprises the following steps: a card punching time response, a card punching place response, a physical state analysis response, a report pushing response and an identity information identification response;
and when the card punching responses are triggered, outputting a calling instruction of the identity recognition mechanism.
Preferably, the body state map includes the following generation steps:
determining physical state standards of different work types through the work types, and generating a physical state judgment matrix;
analyzing the body state judgment matrix through a preset big data platform, and determining body state parameter intervals corresponding to different kinds of work;
according to the body state fixed matrix and the body state parameter interval, an initial body state model is generated, and state judgment modes and state judgment standards of different positions of the body are determined;
the method is used for dividing the state judgment modes and the state judgment standards of different work types and performing sparse coding on each divided body judgment position;
and generating a judging map of the physical state according to the sparse coding.
Preferably, the pre-post acquisition module comprises:
detection element judgment unit: the detection element is used for determining the corresponding work type according to the identity;
a table generation unit: the method is used for constructing a detection table according to the detection elements;
a data extraction unit: and the system is used for extracting the physical state data according to the detection table.
Preferably, the physical state data includes: mental state data, disease risk data and physiological detection data; wherein,
the mental state data includes: wakefulness data, stress index, anxiety index, match index, physical health data, and mood data; the method comprises the steps of carrying out a first treatment on the surface of the
Disease risk data includes: diabetes risk data, cardiovascular risk data, vascular sclerosis risk data, atrial fibrillation detection data;
the physiological test data includes: heart rate data, respiration data, blood pressure data, and blood oxygen data.
Preferably, the health determination module includes:
setting corresponding identity mark personnel, evaluation items and evaluation intervals corresponding to the evaluation items according to the identity information data;
processing the physical state data and determining key information in the physical state data;
according to the key information and the evaluation items, invoking evaluation source codes corresponding to each item of key information in an evaluation database; wherein,
program source codes for judging different health states are configured in the evaluation database;
compiling the evaluation source codes according to the evaluation source codes and the evaluation interval to generate an evaluation process file;
carrying out evaluation processing on the physical state data through an evaluation process file to obtain corresponding evaluation health state estimated parameters;
traversing all health state estimation items of the corresponding identity label personnel to generate a health state estimation parameter set;
and setting the evaluation weight of each evaluation item in turn according to the health state estimation parameter set, and determining a health state estimated value according to the evaluation weight.
Preferably, the line compiling process includes:
acquiring an evaluation source code;
compiling the evaluation source codes to generate compiled code files;
determining an objective function library where the marked function is located from the compiled code file according to the identification of the objective function;
adding the statistical codes of the evaluation interval into an objective function library by adopting a buried point mode corresponding to the objective function to generate an objective compiling code file;
the links generate executable files based on the target compiled code file.
Preferably, the result uploading module includes:
an automatic recording unit: the method is used for acquiring a health state estimation result and automatically recording health state data of each authorized staff when the staff is subjected to card punching;
a storage unit: the method comprises the steps of uploading health state data of authorized staff to a cloud server for storage, and setting a data calling trigger mechanism of each authorized staff;
a statistics unit: the health status data are used for authorizing staff and carrying out health status statistics; wherein,
health status statistics include anomaly statistics and health statistics;
and a pushing unit: and the system is used for acquiring the health state statistical data and pushing the health state statistical data to corresponding authorized staff.
The invention has the beneficial effects that:
in the implementation process, facial features are analyzed according to videos acquired by a video camera through a huge basic feature database, the mental states (moods) of parameter analysis personnel such as aggressiveness, stress, tension and the like are calculated, digitalized visualization is carried out by using color bars, the suspicious degree is obtained, suspicious personnel are screened in advance, and an alarm is given. When carrying out emotion analysis, the method can carry out early warning analysis and mental assistance judgment on suspicious personnel, the suspicious personnel is mainly applied to the security field, and the mental assistance is mainly applied to mental detection of high pressure and specific crowds.
In the aspect of mental assistance detection, the emotion detection of the staff can be performed based on an AI dialogue mode, and in the specific implementation process, emotion analysis of the staff is performed by integrating a method for comprehensively testing emotion cognition at home and abroad, so that a report is automatically generated.
During the AI session, a change in the physiological index of Yuan Yong is detected, for example: and detecting the physiological health level of the staff by the rate, heart rate variability, blood oxygen and blood pressure changes, and judging whether the spirit of the staff is abnormal or not.
The psychological emotion detection and tracking are carried out by analyzing the expression change of the staff in the AI dialogue process, the psychological emotion of the staff is presented in the form of a psychological change curve, if the sensitivity problem exists in the AI dialogue process, the great change of the emotion of the staff is caused, the statistics of the sensitivity problem is carried out, the sorting is automatically realized according to the influence of the sensitivity problem on the emotion of the staff, the emotion of the staff is further actively evaluated, and whether the psychological unhealthy conditions such as harm to the staff and depression exist or not is judged.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention may be realized and attained by the structure particularly pointed out in the written description and drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a system diagram of an AI intelligent decision system for pre-post health detection in accordance with one embodiment of the invention;
FIG. 2 is a flowchart of construction of an engineering model in an embodiment of the invention;
FIG. 3 is a flowchart of a compiling process according to an embodiment of the invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
The application provides an AI decision system for carrying out safety monitoring on the physical health state of staff before going on duty, which specifically comprises the following steps:
identity judging module: acquiring biological characteristic information of a card punching person through an attendance checking and card punching device, and judging whether the person is an authorized worker or not;
identity dividing module: the method is used for carrying out identity division when the card punching personnel is an authorized staff, and generating an identity mark
Front post acquisition module: the method comprises the steps of extracting identity information data of corresponding identity mark personnel according to the identity mark;
health judgment module: the health state estimation module is used for estimating the health state according to the physical state data;
and a result uploading module: and the health state estimation result is used for obtaining the health state estimation result and uploading the health state estimation result to the user side.
The principle of the technical scheme is as follows:
as shown in fig. 1, in the process of security detection before post, the present application does not obtain specific physical examination report information of the card punching personnel, but obtains biological feature information (both real-time video and video data can be analyzed, and biological feature information can be extracted), where the biological feature information includes mental states (wakefulness, drowsiness, fatigue, anxiety, etc.), stress indexes, body health (functional age, functional activity, recovery indexes, etc.), disease risks (diabetes risk, cardiovascular disease risk, arteriosclerosis risk, atrial fibrillation detection, etc.), drunk driving detection, moods (happiness, anger, surprise, fear, etc.), physiological indexes (heart rate, heart rate variability, respiration, blood pressure, blood oxygen, etc.), and the like. The method also comprises the step of judging whether the person is an authorized worker or not according to the face information of the card punching person.
Then classifying the personnel with different kinds and different health conditions by means of identity division; for example: many posts require not only normal physical personnel, but also possibly disabled persons, and the requirements for the physical health status are different for these two different classes of people. Therefore, different identities are required for people of different kinds and different physical states.
After receiving the identification mark of face recognition, the pre-post acquisition module formulates specific health state evaluation standards for different authorized staff according to the identification mark, realizes evaluation of the health state (suspicious staff with abnormal emotion is detected in advance, and the images are snap shot to give an alarm, and can be automatically recognized in the process of recognition by dynamic emotion recognition and staff walking, and is applied to various recognition scenes such as office buildings, construction site, early detection of patients in hospitals and the like), and also accords with customized and dynamic health evaluation modes.
In the specific identification process, a contrast photo is not needed, and only identification processing of an image is needed.
The final health judgment module can be uploaded to the user terminal to read specific health state information.
The beneficial effects of the technical scheme are that:
the intelligent control system can scientifically, conveniently, efficiently and intelligently control, monitor and manage the physical health condition of on-duty workers. The present invention is applicable to all groups and organizations (hereinafter, collectively referred to simply as "users") of enterprises, public institutions, government institutions, organizations, individual organizations, individuals, etc., is applicable to all industries and fields (e.g., workers in all fields and industries such as aviation, aerospace, railway, construction, industrial and mining, various vehicle driving, and mechanical equipment operation), and supports all vehicles and mechanical equipment, etc. (hereinafter, referred to simply as "vehicles"). The software system supports each computer end, a computer webpage end, an APP end, an applet end, a mobile phone webpage end and the like.
In the implementation process, facial features are analyzed according to videos acquired by a video camera through a huge basic feature database, the mental states (moods) of parameter analysis personnel such as aggressiveness, stress, tension and the like are calculated, digitalized visualization is carried out by using color bars, the suspicious degree is obtained, suspicious personnel are screened in advance, and an alarm is given. When carrying out emotion analysis, the method can carry out early warning analysis and mental assistance judgment on suspicious personnel, the suspicious personnel is mainly applied to the security field, and the mental assistance is mainly applied to mental detection of high pressure and specific crowds.
In the aspect of mental assistance detection, the emotion detection of the staff can be performed based on an AI dialogue mode, and in the specific implementation process, emotion analysis of the staff is performed by integrating a method for comprehensively testing emotion cognition at home and abroad, so that a report is automatically generated.
During the AI session, a change in the physiological index of Yuan Yong is detected, for example: and detecting the physiological health level of the staff by the rate, heart rate variability, blood oxygen and blood pressure changes, and judging whether the spirit of the staff is abnormal or not.
The psychological emotion detection and tracking are carried out by analyzing the expression change of the staff in the AI dialogue process, the psychological emotion of the staff is presented in the form of a psychological change curve, if the sensitivity problem exists in the AI dialogue process, the great change of the emotion of the staff is caused, the statistics of the sensitivity problem is carried out, the sorting is automatically realized according to the influence of the sensitivity problem on the emotion of the staff, the emotion of the staff is further actively evaluated, and whether the psychological unhealthy conditions such as harm to the staff and depression exist or not is judged.
Specifically, the identity determination module includes:
sensing unit: the method comprises the steps of setting an induction area of an attendance card punching device, and starting a biological characteristic extraction mechanism when face information appears in the induction area;
face extraction unit: the face extraction method is used for extracting face data according to a biological feature extraction mechanism to obtain face features;
a matching identification unit: the method is used for carrying out feature matching in a preset identity database according to the face features and judging whether corresponding identification data exist or not;
a determination unit: and when the corresponding identification data exists, identifying the card punching personnel as authorized staff and extracting the identity data of the card punching personnel.
The principle of the technical scheme is as follows:
the personnel can be continuously detected, and the face information can be extracted as long as the detected personnel are in the capturing range of the camera, so that whether the personnel are authorized personnel or not is judged. All the software systems for punching cards and detecting results automatically record, save and count, and a user can pass through the user side of the software system. Related data are acquired by binding related hardware equipment (including modules and functions such as a camera, an infrared temperature sensor, a data transceiver, a microphone, a prompt lamp, a loudspeaker and the like) matched with the software system or through a third party manufacturer interface, and the hardware can be additionally installed or directly bound with the original equipment to acquire the related data (such as a driver's seat camera and the like of front-loading or rear-loading of a vehicle).
The beneficial effects of the technical scheme are that:
the identity judgment module is the same as the conventional identity judgment mode, can extract the biological characteristics of the staff, so that corresponding identity recognition is performed, the biological characteristics comprise the facial biological characteristics or the iris biological characteristics of the staff, and the like, and when judging, the identity judgment module can perform the identity recognition of the staff only by performing characteristic matching on the identity characteristics and the staff identity in the identity database, determine the specific identity information of the staff who punches a card, and can also judge whether abnormal conditions of the staff of non-current enterprises exist.
Specifically, the identity dividing module includes:
a work model unit: the method is used for constructing an work model for checking work attendance and punching cards and implanting identity information of workers of different work types;
and a response unit: the method comprises the steps of receiving a card punching response, and calling an identity recognition mechanism of a corresponding work class when receiving card punching information of authorized staff; wherein,
the identity recognition mechanism comprises a name extraction mechanism, a face comparison mechanism and a work content judgment mechanism;
a work pattern unit: the method comprises the steps of constructing a first work type requirement identification model according to the body health state requirements of different work types, and constructing a second work type requirement identification model according to the historical body state information of staff of different work types;
a mapping construction unit: the body detection atlas is used for constructing body detection atlas of different work types according to the identity recognition mechanism, the first work type requirement recognition model and the second work type requirement recognition model;
identity dividing unit: the method is used for carrying out identity division on different authorized staff according to the post detection map, and generating identity division information.
The principle of the technical scheme is as follows:
aiming at different work types, the method is provided with different evaluation mechanisms of the health condition of the staff, and the evaluation mechanisms are divided by means of identity information;
in the specific implementation, the method is not limited to setting up attendance card punching rules, attendance card punching time, attendance card punching places, selecting health and physical state detection items, report pushing frequency and receiving personnel and departments, inputting the identity information (name, sex, age and the like), face recognition data, voiceprint data and other information of checked-in and health safety detection personnel, setting up the health and physical condition requirements, abnormal condition rules, abnormal condition receivers and receiving departments of the work on duty of each staff, and accordingly carrying out specific division.
The response unit receives the card punching response of the staff, invokes an identity recognition mechanism of the corresponding work type, and determines whether the identity information and the post information of the staff are matched; for the work pattern unit, the physical state identification of different work requirements is carried out based on the physical state requirements of different work types, so that different post detection patterns are set for staff of different work types, and staff identity information division and authorization are realized.
The beneficial effects of the technical scheme are that:
the utility model discloses a can carry out identification according to different work stations, can also set up different health detection atlas based on the work stations, to the different health condition requirement of setting for of different work stations.
Specifically, the construction of the engineering model comprises the following steps:
pre-building a punching template based on different industrial types, and setting implantation punching response on the punching template; wherein,
the card punching response comprises the following steps: a card punching time response, a card punching place response, a physical state analysis response, a report pushing response and an identity information identification response;
and when the card punching responses are triggered, outputting a calling instruction of the identity recognition mechanism.
The principle of the technical scheme is as follows:
according to the method, different punching templates are set for staff at different work stations, corresponding punching response information is set, after the punching response is triggered, comprehensive calling of an identity information recognition mechanism is carried out, and recognition and identification of staff identity are carried out.
The beneficial effects of the technical scheme are that:
the method and the device can call specific card punching response mechanisms for staff at different work stations, reduce the identification procedures among the work stations, and reduce card punching identification time, thereby reducing system pressure and carrying out synchronous identity identification of a large number of staff more rapidly.
Specifically, the physical state map includes the following steps:
determining physical state standards of different work types through the work types, and generating a physical state judgment matrix;
analyzing the body state judgment matrix through a preset big data platform, and determining body state parameter intervals corresponding to different kinds of work;
according to the body state fixed matrix and the body state parameter interval, an initial body state model is generated, and state judgment modes and state judgment standards of different positions of the body are determined;
the method is used for dividing the state judgment modes and the state judgment standards of different work types and performing sparse coding on each divided body judgment position;
and generating a judging map of the physical state according to the sparse coding.
The principle of the technical scheme is as follows:
in the process of generating the staff physical state maps of different posts, different work posts are provided with different physical state evaluation standards, so that an evaluation matrix for judging the physical state is generated, then analysis of the physical state is carried out based on big data, distinguishing parameters required by the physical state among different work posts are determined, so that a staff physical state evaluation model is built, different state judgment standards are set for different staff, different positions of the staff are provided with different evaluation standards, state coefficient codes of different physical parts of the staff are carried out, a judgment map for the physical state of the staff is built, and state judgment is carried out on the physical state of the staff.
The beneficial effects of the technical scheme are that:
according to the method and the device, the physical state of the staff can be judged, for staff without work types, sparse coding is carried out according to different physical parts, so that evaluation of physical state standards corresponding to staff with different work posts is judged, and the physical state of the staff is judged.
Specifically, the pre-post acquisition module comprises:
detection element judgment unit: the detection element is used for determining the corresponding work type according to the identity;
a table generation unit: the method is used for constructing a detection table according to the detection elements;
a data extraction unit: and the system is used for extracting the physical state data according to the detection table.
The principle of the technical scheme is as follows:
when the physical state of the staff is detected, a physical detection form of the staff is generated according to the detection elements, and physical state data of the staff are extracted one by one through the detection form.
The card punching personnel verify through hardware equipment (including functions of a camera, an infrared temperature sensor, data receiving and transmitting, a microphone and the like), face recognition, sound and the like (the modes can be independently verified by one or more combinations), after verification, face data of corresponding personnel automatically acquired by a system analyze mental states (wakefulness, drowsiness, fatigue, anxiety organisms and the like) of the personnel through an AI algorithm, pressure indexes, organism health (functional age, functional activity, recovery indexes and the like), disease risks (diabetes risks, cardiovascular disease risks, vascular sclerosis risks, atrial fibrillation detection and the like), drunk driving detection, emotion (happiness, anger, surprise, fear and the like), physiological indexes (heart rate, heart rate variability, respiration, blood pressure, blood oxygen and the like) and the like of the corresponding values set by a user in the software system (the user sets a normal temperature range value, a heart rate normal range value, a blood oxygen normal range value, a blood pressure normal range value, an alcohol content normal range value, emotion and mental state value and the like through the software system), and the like, and when the card punching is not set in the range, the card punching is not set up to the normal state value, the abnormal state is recorded through the corresponding hardware interface, the abnormal user can also carry out the abnormal command and the abnormal command is recorded through the related hardware interface; and when no abnormality is detected, successful card punching is performed.
The system can continuously detect personnel, and can continuously detect mental states (wakefulness, drowsiness, fatigue, anxiety organisms and the like), stress indexes, organism health (functional age, functional activity, recovery indexes and the like), disease risks (diabetes risks, cardiovascular disease risks, vascular sclerosis risks, atrial fibrillation detection and the like), drunk driving detection, moods (happiness, anger, surprise, fear and the like), physiological indexes (heart rate, heart rate variability, respiration, blood pressure, blood oxygen and the like) and the like of all personnel in the range as long as the detected personnel are in the capture range of the camera, and when detected data are abnormal, the system executes audible and visual alarm prompt of hardware equipment according to rules set by a user, and simultaneously automatically pushes abnormal information to related management departments and superior leaders set by the user, and can also push abnormal information to related management departments of the state through a technical interface.
Specifically, the physical state data includes: mental state data, disease risk data and physiological detection data; wherein,
the mental state data includes: wakefulness data, stress index, anxiety index, match index, physical health data, and mood data; the method comprises the steps of carrying out a first treatment on the surface of the
Disease risk data includes: diabetes risk data, cardiovascular risk data, vascular sclerosis risk data, atrial fibrillation detection data;
the physiological test data includes: heart rate data, respiration data, blood pressure data, and blood oxygen data.
The principle of the technical scheme is as follows:
when the physical state data of the staff is acquired, mental state, disease risk and physiological detection data of the staff are acquired, and the detection data are all obtained by detecting a plurality of physical element data of the staff through the configured pre-post physical detection equipment after the identity of the staff is identified, so that the corresponding physical state is determined.
Specifically, the health determination module includes:
setting corresponding identity mark personnel, evaluation items and evaluation intervals corresponding to the evaluation items according to the identity information data;
processing the physical state data and determining key information in the physical state data;
according to the key information and the evaluation items, invoking evaluation source codes corresponding to each item of key information in an evaluation database; wherein,
program source codes for judging different health states are configured in the evaluation database;
compiling the evaluation source codes according to the evaluation source codes and the evaluation interval to generate an evaluation process file;
carrying out evaluation processing on the physical state data through an evaluation process file to obtain corresponding evaluation health state estimated parameters;
traversing all health state estimation items of the corresponding identity label personnel to generate a health state estimation parameter set;
and setting the evaluation weight of each evaluation item in turn according to the health state estimation parameter set, and determining a health state estimated value according to the evaluation weight.
The principle of the technical scheme is as follows:
when the health state evaluation is carried out, the health state evaluation items of corresponding staff and the evaluation intervals required by each evaluation item are set according to the identity information data of the staff, so that the health state data of the staff are processed and analyzed, key information is determined, the key information and the evaluation items are corresponding, the state parameters of the current staff relative to each evaluation item are determined, in order to ensure that the health data of each staff has certain privacy, the privacy of the staff is protected, the health state data are converted into evaluation source codes, the evaluation source codes and the evaluation intervals are compiled, evaluation scripts of the health state of the staff are generated, the evaluation scripts are fused to generate a positive health state evaluation parameter set of the staff, and the traversing function is to prevent the existence of the evaluation items from being evaluated.
The beneficial effects of the technical scheme are that:
the method and the device can automatically compile evaluation scripts which accord with staff of different workers, even individuals of different staff, according to the physical health state of the staff in a program script mode and evaluate the physical health state of the staff. The physical health state of staff meets the health requirement of working posts.
Specifically, the compiling processing includes:
acquiring an evaluation source code;
compiling the evaluation source codes to generate compiled code files;
determining an objective function library where the marked function is located from the compiled code file according to the identification of the objective function;
adding the statistical codes of the evaluation interval into an objective function library by adopting a buried point mode corresponding to the objective function to generate an objective compiling code file;
the links generate executable files based on the target compiled code file.
The principle of the technical scheme is as follows:
as shown in fig. 3, in the compiling process, the present application obtains the evaluation source codes of different evaluation items of each employee's body evaluation, compiles through the evaluation source codes to generate script code files, then calls the corresponding objective function through the preset identification of the objective function, that is, the identification of the evaluation item of the corresponding work class, adopts the embedded point mode of the objective function, adds codes to generate the target compiled code files of different evaluation items, that is, the evaluation scripts, then loads the target compiled code files into the development platform to generate script programs, and connects the corresponding script programs to the background system.
The beneficial effects of the technical scheme are that:
the method and the device can automatically generate the executable file and automatically call the evaluation function in the compiling process, so that the script compiling of the evaluation item can be dynamically carried out in real time, and the automatic body health state evaluation can be carried out.
Specifically, the result uploading module includes:
an automatic recording unit: the method is used for acquiring a health state estimation result and automatically recording health state data of each authorized staff when the staff is subjected to card punching;
a storage unit: the method comprises the steps of uploading health state data of authorized staff to a cloud server for storage, and setting a data calling trigger mechanism of each authorized staff;
the data calling triggering mechanism can automatically trigger the authorization information of the callable data according to the level of the authorized staff, and the data can be called after being identified in other modes.
A statistics unit: the health status data are used for authorizing staff and carrying out health status statistics; wherein,
health status statistics include anomaly statistics and health statistics;
and a pushing unit: and the system is used for acquiring the health state statistical data and pushing the health state statistical data to corresponding authorized staff.
The principle of the technical scheme is as follows:
all the software systems for punching cards and detecting results automatically record, save and count, a user can check at any time through each end (a computer end, an APP end, an applet end, a mobile phone webpage end, a computer webpage end and the like) of the software system, a report (the content comprises personnel names, sexes, ages, attendance conditions, punching cards, health detection conditions, abnormal conditions and the like) is automatically generated, and the report is automatically pushed according to rules of pushing frequencies, pushing time, receivers, receiving departments, receiving country related management departments and the like which are set by user definition.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. An AI intelligent decision system for pre-post health detection, comprising:
identity judging module: acquiring biological characteristic information of a card punching person through an attendance checking and card punching device, and judging whether the person is an authorized worker or not;
identity dividing module: the method is used for carrying out identity division when the card punching personnel is an authorized staff, and generating an identity mark
Front post acquisition module: the method comprises the steps of extracting identity information data of corresponding identity mark personnel according to the identity mark;
health judgment module: the health state estimation module is used for estimating the health state according to the physical state data;
and a result uploading module: and the health state estimation result is used for obtaining the health state estimation result and uploading the health state estimation result to the user side.
2. The AI intelligent decision system for pre-post health detection of claim 1, wherein said identity decision module comprises:
sensing unit: the method comprises the steps of setting an induction area of an attendance card punching device, and starting a biological characteristic extraction mechanism when face information appears in the induction area;
face extraction unit: the face extraction method is used for extracting face data according to a biological feature extraction mechanism to obtain face features;
a matching identification unit: the method is used for carrying out feature matching in a preset identity database according to the face features and judging whether corresponding identification data exist or not;
a determination unit: and when the corresponding identification data exists, identifying the card punching personnel as authorized staff and extracting the identity data of the card punching personnel.
3. The AI intelligent decision system for pre-post health detection of claim 1, wherein the identity partitioning module comprises:
a work model unit: the method is used for constructing an work model for checking work attendance and punching cards and implanting identity information of workers of different work types;
and a response unit: the method comprises the steps of receiving a card punching response, and calling an identity recognition mechanism of a corresponding work class when receiving card punching information of authorized staff; wherein,
the identity recognition mechanism comprises a name extraction mechanism, a face comparison mechanism and a work content judgment mechanism;
a work pattern unit: the method comprises the steps of constructing a first work type requirement identification model according to the body health state requirements of different work types, and constructing a second work type requirement identification model according to the historical body state information of staff of different work types;
a mapping construction unit: the body detection atlas is used for constructing body detection atlas of different work types according to the identity recognition mechanism, the first work type requirement recognition model and the second work type requirement recognition model;
identity dividing unit: the method is used for carrying out identity division on different authorized staff according to the post detection map, and generating identity division information.
4. An AI intelligent decision system for pre-job health detection as set forth in claim 3, wherein said constructing a job model comprises:
pre-building a punching template based on different industrial types, and setting implantation punching response on the punching template; wherein,
the card punching response comprises the following steps: a card punching time response, a card punching place response, a physical state analysis response, a report pushing response and an identity information identification response;
and when the card punching responses are triggered, outputting a calling instruction of the identity recognition mechanism.
5. The AI intelligent decision system for pre-post health detection of claim 4, wherein said body state map comprises the steps of:
determining physical state standards of different work types through the work types, and generating a physical state judgment matrix;
analyzing the body state judgment matrix through a preset big data platform, and determining body state parameter intervals corresponding to different kinds of work;
according to the body state fixed matrix and the body state parameter interval, an initial body state model is generated, and state judgment modes and state judgment standards of different positions of the body are determined;
the method is used for dividing the state judgment modes and the state judgment standards of different work types and performing sparse coding on each divided body judgment position;
and generating a judging map of the physical state according to the sparse coding.
6. The AI intelligent decision system for pre-post health detection of claim 1, wherein the pre-post acquisition module comprises:
detection element judgment unit: the detection element is used for determining the corresponding work type according to the identity;
a table generation unit: the method is used for constructing a detection table according to the detection elements;
a data extraction unit: and the system is used for extracting the physical state data according to the detection table.
7. The AI intelligent decision system for pre-post health detection of claim 1, wherein the physical state data comprises: mental state data, disease risk data and physiological detection data; wherein,
the mental state data includes: wakefulness data, stress index, anxiety index, match index, physical health data, and mood data; the method comprises the steps of carrying out a first treatment on the surface of the
Disease risk data includes: diabetes risk data, cardiovascular risk data, vascular sclerosis risk data, atrial fibrillation detection data;
the physiological test data includes: heart rate data, respiration data, blood pressure data, and blood oxygen data.
8. The AI intelligent decision system for pre-post health detection of claim 1, wherein the health decision module comprises:
an evaluation setting unit: setting an evaluation item corresponding to the identity mark personnel and an evaluation interval corresponding to the evaluation item according to the identity information data;
key information confirmation unit: processing the physical state data and determining key information in the physical state data;
calling unit: according to the key information and the evaluation items, invoking evaluation source codes corresponding to each item of key information in an evaluation database; wherein,
program source codes for judging different health states are configured in the evaluation database;
a compiling unit: compiling the evaluation source codes according to the evaluation source codes and the evaluation interval to generate an evaluation process file;
an evaluation unit: carrying out evaluation processing on the physical state data through an evaluation process file to obtain corresponding evaluation health state estimated parameters;
traversing unit: traversing all health state estimation items of the corresponding identity label personnel to generate a health state estimation parameter set;
weight evaluation unit: and setting the evaluation weight of each evaluation item in turn according to the health state estimation parameter set, and determining a health state estimated value according to the evaluation weight.
9. The AI intelligent decision system for pre-post health detection of claim 8, wherein said performing a compilation process comprises:
acquiring an evaluation source code;
compiling the evaluation source codes to generate compiled code files;
determining an objective function library where the marked function is located from the compiled code file according to the identification of the objective function;
adding the statistical codes of the evaluation interval into an objective function library by adopting a buried point mode corresponding to the objective function to generate an objective compiling code file;
the links generate executable files based on the target compiled code file.
10. The AI intelligent decision system for pre-post health detection of claim 1, wherein the result upload module comprises:
an automatic recording unit: the method is used for acquiring a health state estimation result and automatically recording health state data of each authorized staff when the staff is subjected to card punching;
a storage unit: the method comprises the steps of uploading health state data of authorized staff to a cloud server for storage, and setting a data calling trigger mechanism of each authorized staff;
a statistics unit: the health status data are used for authorizing staff and carrying out health status statistics; wherein,
health status statistics include anomaly statistics and health statistics;
and a pushing unit: and the system is used for acquiring the health state statistical data and pushing the health state statistical data to corresponding authorized staff.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311691035.XA CN117476234A (en) | 2023-12-11 | 2023-12-11 | AI intelligent judging system for pre-post health detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311691035.XA CN117476234A (en) | 2023-12-11 | 2023-12-11 | AI intelligent judging system for pre-post health detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117476234A true CN117476234A (en) | 2024-01-30 |
Family
ID=89629494
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311691035.XA Pending CN117476234A (en) | 2023-12-11 | 2023-12-11 | AI intelligent judging system for pre-post health detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117476234A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118588298A (en) * | 2024-08-07 | 2024-09-03 | 天津科电石化科技发展有限公司 | Enterprise employee health management method, system, electronic equipment and medium |
-
2023
- 2023-12-11 CN CN202311691035.XA patent/CN117476234A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118588298A (en) * | 2024-08-07 | 2024-09-03 | 天津科电石化科技发展有限公司 | Enterprise employee health management method, system, electronic equipment and medium |
| CN118588298B (en) * | 2024-08-07 | 2024-10-22 | 天津科电石化科技发展有限公司 | Enterprise employee health management method, system, electronic equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20030133597A1 (en) | Physiomagnetometric inspection and surveillance system and method | |
| US6743022B1 (en) | System and method for automated self measurement of alertness equilibrium and coordination and for ventification of the identify of the person performing tasks | |
| US8065529B2 (en) | Methods for using a biometric parameter in the identification of persons | |
| CN117476234A (en) | AI intelligent judging system for pre-post health detection | |
| CN106780250B (en) | Intelligent community security event processing method and system based on Internet of things technology | |
| CN111881822B (en) | Access control method, device, equipment and storage medium based on face recognition | |
| CN111241883B (en) | Method and device for preventing cheating of remote tested personnel | |
| WO2020202694A1 (en) | Surveillance system, surveillance device, surveillance method, and non-temporary computer readable medium | |
| CN117219296A (en) | Personnel intelligent health monitoring management method and system | |
| CN111259682B (en) | Method and device for monitoring safety of construction site | |
| CN113763613B (en) | Method and system for managing information of personnel entering and exiting from community | |
| US9390627B1 (en) | Stimulus recognition training and detection methods | |
| CN117197998A (en) | Sensor integrated nursing system of thing networking | |
| CN111870253A (en) | Method and system for monitoring condition of tic disorder disease based on vision and voice fusion technology | |
| EP3109837A1 (en) | System and method of smart incident analysis in control system using floor maps | |
| CN115880113A (en) | Digital management system and management method based on comprehensive treatment of smart villages | |
| CN112968775B (en) | Personnel biological characteristic recognition system | |
| CN113724853A (en) | Intelligent medical system based on deep learning | |
| Scataglini et al. | Application of wearable monitoring system in tourette syndrome assessment | |
| CN116631172B (en) | Early warning method and device based on linkage of door lock and electronic doorbell | |
| CN114360006B (en) | Face recognition system and detection method thereof | |
| CN117292427A (en) | Method and system for screening health risks of staff on site before on-duty | |
| CN116959700A (en) | Health detection management method and system | |
| CN116884583A (en) | Hospital field management and control method and system based on Internet of things | |
| CN113555103A (en) | Internet remote physical examination and photographing system for driver |
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 |