CN110795587A - Medical alarm early warning method, service platform and computer readable storage medium - Google Patents
Medical alarm early warning method, service platform and computer readable storage medium Download PDFInfo
- Publication number
- CN110795587A CN110795587A CN201810865119.3A CN201810865119A CN110795587A CN 110795587 A CN110795587 A CN 110795587A CN 201810865119 A CN201810865119 A CN 201810865119A CN 110795587 A CN110795587 A CN 110795587A
- Authority
- CN
- China
- Prior art keywords
- information
- personnel
- dispute
- medical
- alarm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000004422 calculation algorithm Methods 0.000 claims description 44
- 238000011156 evaluation Methods 0.000 claims description 19
- 230000001815 facial effect Effects 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 13
- 238000001356 surgical procedure Methods 0.000 claims description 8
- 201000010099 disease Diseases 0.000 claims description 6
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 6
- 230000006866 deterioration Effects 0.000 claims description 4
- 230000006399 behavior Effects 0.000 abstract description 8
- 238000012549 training Methods 0.000 description 16
- 238000004364 calculation method Methods 0.000 description 12
- 238000003062 neural network model Methods 0.000 description 10
- 238000012544 monitoring process Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 4
- 210000002569 neuron Anatomy 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000012502 risk assessment Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000007721 medicinal effect Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
- G08B25/005—Alarm destination chosen according to a hierarchy of available destinations, e.g. if hospital does not answer send to police station
Abstract
The invention provides a medical alarm early warning method based on intelligent identification, which comprises the steps of obtaining image data collected by an image collection module arranged in a hospital; extracting face feature information in the image data, and judging whether the face feature information is matched with data in a suspected dispute personnel library and a dispute personnel library which are constructed according to preset danger judgment conditions; when the personnel identity information is matched with the data in the suspected dispute personnel database, sending first alarm information; and sending second alarm information when the personnel identity information is matched with the data in the dispute personnel database. The invention can carry out graded early warning on medical alarm behaviors in hospitals based on face recognition, thereby effectively preventing and early warning the medical alarm behaviors. The invention also provides a service platform and a computer readable storage medium for the medical alarm early warning system.
Description
Technical Field
The invention belongs to the field of hospital management systems, and particularly relates to a medical alarm early warning method based on intelligent identification, a medical alarm early warning system and a computer-readable storage medium.
Background
Medical negligence or medical passing results in dissatisfaction of patients or harm to patients, thereby causing medical disputes. In addition to medical disputes caused by medical mistakes and mistakes, sometimes, a hospital side does not have any negligence or errors in medical activities, and the medical disputes are caused only by unilateral dissatisfaction of patients or unscrupulous liability of patients. If the medical accident is further worsened and progressed, medical alarm will be formed. Generally, the normal operation and order of a hospital are affected by medical alarm, so that the hospitalization of a patient is affected, and public benefits are damaged; but also easily cause adverse accidents such as limb conflict.
Although monitoring cameras are installed in public places such as the existing hospitals, the monitoring cameras are generally only used for manual monitoring of a central control room and later investigation and evidence collection. However, the potential medical alarm personnel are different from the monitoring of criminal evasion and dangerous suspicious personnel in the prior art; uncertainties often associated with potentially medically-challenged personnel, for example, family members of patients who have had medical accidents (medical malpractice or malpractice) do not necessarily have real-time medical behaviors; for another example, even if a professional medical professional is present in the hospital's monitoring area, it may be possible to actually visit the hospital to seek medical attention.
Therefore, the suspicious person detection method based on face recognition in the prior art is not suitable for preventing medical risks in hospitals. Meanwhile, in the prior art, no good technical scheme is available for effectively preventing and early warning medical alarm risks in hospitals.
Disclosure of Invention
The invention aims to provide a medical alarm early warning method, a medical alarm early warning system and a computer readable storage medium based on intelligent recognition, which can perform graded evaluation on medical alarm risks possibly existing in a hospital through face recognition, so that medical alarm behaviors are effectively prevented and early warned.
In order to achieve the purpose, the invention provides a medical alarm early warning method based on intelligent identification, which comprises the following steps:
acquiring image data acquired by an image acquisition module arranged in a hospital;
extracting face feature information in the image data, and judging whether the face feature information is matched with data in a suspected dispute personnel library and a dispute personnel library which are constructed according to preset danger judgment conditions;
when the face feature information is matched with the data in the suspected dispute personnel database, sending first alarm information to a preset receiving end of a first hospital where a first image acquisition module corresponding to the image data containing the face feature information is acquired;
and when the face feature information is matched with the data in the dispute personnel database, sending second alarm information to a preset receiving end of a second hospital where a second image acquisition module corresponding to the image data including the face feature information is acquired.
Further, after the step of sending the second alarm information to the preset receiving end of the second hospital where the second image acquisition module corresponding to the image data including the face feature information is located, the method further includes the steps of:
controlling the second image acquisition module to track a target object corresponding to the face feature information;
continuously acquiring tracking image information acquired by the second image acquisition module tracking the target object, and extracting limb action characteristic information of the target object from the tracking image information according to the face recognition algorithm and the limb action recognition algorithm;
determining whether the action of the target object meets a preset condition or not according to the limb action characteristic information of the target object;
and when the action of the target object meets a preset condition, sending third alarm information to a preset receiving end of the second hospital.
Further, after the step of sending the second alarm information to the preset receiving end of the second hospital where the second image acquisition module corresponding to the image data including the face feature information is located, the method further includes the steps of:
continuously acquiring sound information by a sound acquisition module which is matched with the position of the second image acquisition module in the second hospital, and judging whether the decibel value of the acquired sound information is larger than a preset decibel value or not;
and when the decibel value of the acquired sound information is greater than the preset decibel value, sending third alarm information to a preset receiving end of the second hospital.
Further, the method also comprises the following steps:
when the face feature information is matched with the data in the suspected dispute personnel database, acquiring personnel identity information corresponding to the face feature information, and sending the personnel identity information to a preset receiving end of the first hospital;
and when the face feature information is matched with the data in the dispute personnel database, acquiring personnel identity information corresponding to the face feature information, and sending the personnel identity information to a preset receiving end of the second hospital.
Further, the method also comprises the following steps:
acquiring identity information of suspected dispute personnel and identity information of dispute personnel according to the preset danger judgment condition;
acquiring facial feature information of the suspected dispute personnel according to the identity information of the suspected dispute personnel, and constructing a suspected dispute personnel library according to the identity information of the suspected dispute personnel and the acquired facial feature information of the suspected dispute personnel;
and acquiring the facial feature information of the dispute personnel according to the identity information of the dispute personnel, and constructing a dispute personnel library according to the identity information of the dispute personnel and the acquired facial feature information of the dispute personnel.
Further, the preset danger determination condition includes one or more of the following steps:
acquiring a medical record of a patient hospitalized in a hospital, judging whether a preset medical fault exists in the hospitalizing process of the patient, acquiring identity information of a family of the patient corresponding to the patient according to family information recorded in the hospitalizing record of the patient when the preset medical fault exists in the hospitalizing process of the patient, and recording the identity information of the family of the patient as identity information of suspected dispute personnel, wherein the preset medical fault comprises one or more of disease deterioration, a disease vanishing, a rescue failure, a surgery failure and a surgery rescue failure;
acquiring identity information of professional medical alarming personnel or identity information of medical alarming personnel at the bottom of a desk, which is stored by a service platform, a public security system server or a preset information server, and recording the identity information of the professional medical alarming personnel or the identity information of the medical alarming personnel at the bottom of the desk as the identity information of dispute personnel;
acquiring a medical record of a patient hospitalized in a hospital, acquiring medical alarm index parameter information corresponding to the patient according to the medical record of the patient, judging whether a medical alarm risk evaluation result of the patient is greater than a preset rating through a preset medical alarm risk evaluation algorithm, acquiring identity information of a family of the patient corresponding to the patient according to family information recorded in the medical record of the patient when the medical alarm risk evaluation result is greater than the preset rating, and recording the identity information of the family of the patient as identity information of dispute personnel; the medical alarm index parameters comprise one or more of medical alarm record of the patient and relatives and friends thereof, credit record of the patient, illegal record of the patient and relatives and friends thereof, personal income information of the patient, family income information of the patient, and character evaluation information of the patient and relatives and friends thereof.
Further, the step of sending the third alarm information to a preset receiving end of the second hospital includes:
and sending third alarm information to a preset receiving end of the second hospital, and sending an alarm signal to a preset alarm system or a public security bureau.
Further, the method also comprises the following steps:
acquiring update information for updating the dispute personnel database by a server of the hospital;
and updating the updated information to dispute personnel databases stored on the service terminals of other hospitals through the service platform.
The invention also provides a service platform for the medical alarm early warning system, which comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor realizes the steps of the medical alarm early warning method based on intelligent identification when executing the computer program.
The invention further provides a computer-readable storage medium, which stores a computer program, and the computer program, when executed by a processor, implements the steps of the intelligent identification-based medical alarm early warning method as described in any one of the above.
According to the invention, the face characteristic information of the identified object can be extracted and matched with the data in the suspected dispute personnel library and the dispute personnel library which are constructed according to the preset danger judgment condition, so that the purpose of evaluating the medical alarm risk of the identified object is achieved, the alarm information of different levels is sent to the preset receiving end of the hospital, and the corresponding personnel is informed to process in time, so that the medical alarm behavior is effectively prevented and early warned.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a block diagram of an embodiment of a medical alarm warning system based on intelligent recognition;
FIG. 2 is a block flow diagram of a medical alarm warning method based on intelligent recognition in an embodiment;
FIG. 3 is a block diagram of a method for medical alarm warning based on intelligent recognition in another embodiment;
fig. 4 is a flowchart of a medical alarm warning method based on intelligent recognition in another embodiment.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a medical alarm early warning system 100 based on intelligent recognition according to an embodiment of the present invention may be installed in each hospital, and the medical alarm early warning system 100 further includes a plurality of image acquisition modules 1, a plurality of sound acquisition modules 2, and a hospital server 3.
The medical alarm early warning system 100 further comprises a service platform 101, and the service platform 101 can be a cloud service platform or a remote server.
The hospital server 3 may comprise a communication module 31, a memory 32, a processor 33 and a computer program stored in said memory 32 and executable on said processor 33.
In this embodiment, the image capturing module 1 may be installed at the entrance, corridor, and entrance of the consulting room of the hospital, so as to comprehensively and conveniently capture the face information of the persons in the hospital. Specifically, the image acquisition module 1 may be a camera with an adjustable shooting angle, an intelligently controlled face tracking camera, or the like.
Similarly, the sound collection module 2 is installed at the entrance, the corridor, the entrance of the consulting room and the like of the hospital corresponding to the position of the image collection module 1, so as to comprehensively and conveniently collect the sound information of the personnel in the hospital.
The hospital server 3 communicates with the image acquisition module 1 and the sound acquisition module 2, and the hospital server 3 can acquire image data acquired by the image acquisition module 1 and sound data acquired by the sound acquisition module 2. The hospital server 3 further includes a communication module 31, and the hospital server 3 communicates with the outside through the communication module 31, including but not limited to the service platform 101, a mobile communication device (not shown), a public security system server 102, other information servers 103, and the like. Specifically, the hospital server 3 sends the acquired image data acquired by the image acquisition module 1 and the acquired sound data acquired by the sound acquisition module 2 to the service platform 101 through the communication module 31.
The hospital server 3 may be a desktop computer device, a central control server system, a central control gateway, and the like, and is not limited in particular.
A suspected dispute personnel warehouse and a dispute personnel warehouse which are constructed according to preset danger judgment conditions may be established on the service platform 101. For example, firstly, acquiring identity information of suspected dispute personnel and identity information of dispute personnel according to the preset danger judgment condition; secondly, acquiring facial feature information of the suspected dispute personnel according to the identity information of the suspected dispute personnel, and constructing a suspected dispute personnel library according to the identity information of the suspected dispute personnel and the facial feature information of the suspected dispute personnel; and acquiring the facial feature information of the dispute personnel according to the identity information of the dispute personnel, and constructing a dispute personnel library according to the identity information of the dispute personnel and the acquired facial feature information of the dispute personnel.
Specifically, the preset risk judgment condition may include one or more of the following embodiments:
In this embodiment 3, the determining, by a preset medical alarm risk assessment algorithm, whether the medical alarm risk rating result of the patient is greater than a preset rating may include:
taking the medical alarm index parameter information corresponding to the patient as sample input data, and predicting the medical alarm risk corresponding to the patient through a pre-trained algorithm model to obtain a medical alarm risk rating result corresponding to the patient; the pre-trained algorithm model is an algorithm model which predicts medical alarm risk ratings of people corresponding to medical alarm index parameter information and is obtained by training based on a convolutional neural network model by using pre-acquired medical alarm index parameter information of non-medical alarm patients and patient family members, patients with medical alarm cases and patient family members, occupational medical alarm personnel and other people as sample training data; and then judging whether the medical alarm risk rating result corresponding to the patient is greater than a preset rating.
In this embodiment, a large amount of medical alarm indicator parameter information of non-medical alarm patients and patients 'family members, patients with medical alarm at the end of the medical alarm, patients' family members, professional medical alarm personnel and other personnel can be obtained as sample training data in advance by means of big data acquisition, and then the sample training data is substituted into the established convolutional neural network model for training, so that an algorithm model for predicting medical alarm risk rating corresponding to the medical alarm indicator parameter information of a specific object can be obtained; and then, directly acquiring the medical alarm index parameter information of any object to be predicted, and predicting the medical alarm risk rating of the object to be predicted.
The service platform 101 may acquire image data acquired by the image acquisition module 1, and then extract face feature information from the image data through a preset face recognition algorithm, so as to recognize the person identity information corresponding to the face feature information, for example, the service platform 101 is already connected to a network of a public security system, and the identity information of the recognized object may be recognized in a face recognition manner.
The service platform 101 may further determine whether the face feature information matches with data in a suspected dispute personnel database and a dispute personnel database constructed according to preset danger determination conditions, so as to perform medical alarm risk evaluation on the identified object.
Specifically, when the face feature information is matched with data in the suspected dispute personnel database, first warning information is sent to a preset receiving end of a first hospital where a first image acquisition module corresponding to image data including the face feature information is located; the preset receiving end can be a central control terminal of a first hospital, an alarm system of the first hospital, handheld electronic equipment of security personnel of the first hospital and the like.
And when the face feature information is matched with the data in the dispute personnel database, sending second alarm information to a preset receiving end of a second hospital where a second image acquisition module corresponding to the image data including the face feature information is acquired. Similarly, the preset receiving end may be a central control terminal of the second hospital, an alarm system of the second hospital, a handheld electronic device of security personnel of the second hospital, and the like.
It can be understood that, in this embodiment, when it is confirmed that a certain identification object matches with the data in the dispute personnel database, it may be assumed that the medical alarm risk of the identification object is high, the camera may be controlled to perform tracking shooting, and a second alarm information is issued, where the level of the second alarm information is greater than that of the first alarm information.
Optionally, when the face feature information is matched with the data in the suspected dispute personnel database, personnel identity information corresponding to the face feature information may also be obtained, and the personnel identity information is sent to a preset receiving end of the first hospital; when the face feature information is matched with the data in the dispute personnel database, personnel identity information corresponding to the face feature information can be obtained, and the personnel identity information is sent to a preset receiving end of the second hospital; so that the corresponding preset receiving end can receive the personnel identity information of the personnel with medical risk.
Further, the service platform 101 may also control the second image acquisition module to track a target object corresponding to the facial feature information; continuously acquiring tracking image information acquired by the second image acquisition module tracking the target object, and extracting limb action characteristic information of the target object from the tracking image information according to the face recognition algorithm and the limb action recognition algorithm; determining whether the action of the target object meets a preset condition or not according to the limb action characteristic information of the target object; and when the limb action characteristic information of the target object determines that the action of the target object meets a preset condition, sending third alarm information to a preset receiving end of the second hospital.
In the embodiment, by continuously tracking and shooting dispute personnel in a staff bank with higher medical alarm risk, the body action characteristic information of the target object in the tracking image information is extracted through a face recognition algorithm and a body action recognition algorithm; and judging whether the action of the target object meets preset conditions, such as whether dangerous articles are held, whether large-amplitude action and running exist, whether limb conflict behaviors exist, and the like, so that third alarm information is sent to a preset receiving end of a hospital, and corresponding personnel are informed to process in time. The third warning information is higher in grade than the first warning information and the second warning information.
Further, when the face feature information is matched with the data in the dispute personnel database, after the step of sending second warning information to a preset receiving terminal of a second hospital, continuously collecting sound information through a sound collection module matched with the position of the second image collection module in the second hospital, and judging whether the decibel value of the collected sound information is greater than a preset decibel value; and when the decibel value of the acquired sound information is greater than the preset decibel value, sending third alarm information to a preset receiving end of the second hospital.
In this embodiment, when there is a person matching the dispute person database, it is detected whether there is a sound emission with a higher decibel level, such as a sound collision-based feature like ravel, quarrel, clutter, scream, etc., in the vicinity of the person, and the risk of medical alarm generation is further determined; the third warning information is sent to the preset receiving end of the hospital more accurately, and corresponding personnel are informed to process in time.
Furthermore, while the service platform 101 sends the third alarm information to the preset receiving end of the second hospital, the service platform may also send an alarm signal to a preset alarm system or a public security bureau.
It can be understood that, in a preferred embodiment, the manner of determining whether the motion of the target object meets the preset condition according to the limb motion characteristic information of the target object may be to use the limb motion characteristic information of the target object as sample input data, and predict the limb motion of the target object through a pre-trained algorithm model to determine whether the motion of the target object meets the preset condition; the pre-trained algorithm model is an algorithm model which is obtained by training a neural network model constructed based on an error back propagation algorithm by taking pre-acquired limb action characteristic information as sample training data and judging whether actions corresponding to the limb action characteristic information meet preset conditions.
In the step of training the neural network model constructed based on the error back propagation algorithm, the calculation process of the error back propagation algorithm comprises a forward calculation process and a reverse calculation process;
the forward computing process comprises: processing the sample input data layer by layer through a hidden unit layer, and turning to an output result, and turning to reverse calculation when the output obtained by the output result does not accord with a preset expected value;
the reverse calculation process comprises: and returning the error signal with the output not in accordance with the preset expected value along the original path, modifying the weight of each neuron in the neural network model so as to adjust the error signal to be within a preset range, and returning to the forward calculation process.
In the embodiment, the limb action characteristic information is predicted through a neural network model constructed based on an error back propagation algorithm, so that the accuracy of limb action identification can be further improved; and then, the weight of each neuron in the neural network model can be dynamically adjusted by using an error back propagation algorithm so as to adjust the error signal to a preset range, thereby obtaining a more accurate operation model and result.
In a preferred embodiment, the hospital server 3 or the service platform 101 of the medical alarm system 100 can synchronize and share the update information of other hospitals for updating the dispute personnel database.
Referring to fig. 2, the present invention further provides a medical alarm early warning method based on intelligent recognition, which includes the steps of:
and step S10, acquiring image data acquired by an image acquisition module arranged in a hospital.
Step S20, extracting the face feature information in the image data, and determining whether the face feature information matches with the data in the suspected dispute personnel database and the dispute personnel database that are constructed according to the preset danger determination condition.
Specifically, identity information of suspected dispute personnel and facial feature information of the suspected dispute personnel are recorded in the suspected dispute personnel database; the dispute personnel database records identity information of dispute personnel and facial feature information of the dispute personnel.
The service platform 101 may communicate with hospital service terminals 3 of each hospital, acquire image data acquired by the image acquisition modules 1 set in each hospital, extract corresponding face feature information from the image data through a preset face recognition algorithm, and determine whether the face feature information matches with data in the suspected dispute personnel library and the dispute personnel library, so as to realize risk rating of the detected object.
Referring to fig. 4, in an embodiment, the medical alarm warning method may further include the step of constructing the suspected dispute personnel database and the dispute personnel database according to the preset danger determination condition, which specifically includes:
step S00, acquiring identity information of suspected dispute personnel and identity information of dispute personnel according to the preset danger judgment condition;
step S01, acquiring the facial feature information of the suspected dispute person according to the identity information of the suspected dispute person, and constructing a suspected dispute person library according to the identity information of the suspected dispute person and the acquired facial feature information of the suspected dispute person;
and step S02, acquiring the facial feature information of the dispute personnel according to the identity information of the dispute personnel, and constructing a dispute personnel database according to the identity information of the dispute personnel and the acquired facial feature information of the dispute personnel.
Specifically, the preset risk determination condition in step S00 may include one or more of the following embodiments:
In this embodiment 3, the determining, by a preset medical alarm risk assessment algorithm, whether the medical alarm risk rating result of the patient is greater than a preset rating may include:
taking the medical alarm index parameter information corresponding to the patient as sample input data, and predicting the medical alarm risk corresponding to the patient through a pre-trained algorithm model to obtain a medical alarm risk rating result corresponding to the patient; the pre-trained algorithm model is an algorithm model which predicts medical alarm risk ratings of people corresponding to medical alarm index parameter information and is obtained by training based on a convolutional neural network model by using pre-acquired medical alarm index parameter information of non-medical alarm patients and patient family members, patients with medical alarm cases and patient family members, occupational medical alarm personnel and other people as sample training data; and then judging whether the medical alarm risk rating result corresponding to the patient is greater than a preset rating.
In this embodiment, a large amount of medical alarm indicator parameter information of non-medical alarm patients and patients 'family members, patients with medical alarm at the end of the medical alarm, patients' family members, professional medical alarm personnel and other personnel can be obtained as sample training data in advance by means of big data acquisition, and then the sample training data is substituted into the established convolutional neural network model for training, so that an algorithm model for predicting medical alarm risk rating corresponding to the medical alarm indicator parameter information of a specific object can be obtained; and then, directly acquiring the medical alarm index parameter information of any object to be predicted, and predicting the medical alarm risk rating of the object to be predicted.
Step S30, when the face feature information matches the data in the suspected dispute person database, sending first warning information to a preset receiving end of a first hospital where a first image acquisition module corresponding to the image data including the face feature information is located.
And when the face feature information is matched with the data in the suspected dispute personnel database, sending first alarm information to a preset receiving end of a first hospital where a first image acquisition module corresponding to the acquired image data containing the face feature information is located. The preset receiving end can be a central control terminal of a hospital, an alarm system of the hospital, handheld electronic equipment of security personnel of the hospital and the like. The level of the first alarm information may be a lower alarm level, and only the security personnel or the monitoring personnel need to pay appropriate attention to the first alarm information.
And step S40, when the face feature information is matched with the data in the dispute personnel database, sending second alarm information to a preset receiving end of a second hospital where a second image acquisition module corresponding to the image data including the face feature information is located.
Similarly, the preset receiving end can be a central control terminal of a hospital, an alarm system of the hospital, a handheld electronic device of a security worker of the hospital, and the like. It is understood that when it is confirmed that a certain identification object matches with the data in the dispute personnel database, it may be assumed that the medical alarm risk of the identification object is higher, and a second alarm information may be issued, and the level of the second alarm information is greater than that of the first alarm information.
In this embodiment, the face feature information of the identified object may be determined through face recognition, and is matched with the data in the suspected dispute personnel library and the dispute personnel library, which are constructed according to the preset danger determination condition, so as to perform the purpose of medical alarm risk evaluation on the identified object, send alarm information of different levels to the preset receiving end of the hospital, and notify corresponding personnel to process in time, thereby performing effective prevention and early warning on medical alarm behaviors.
Further, in an embodiment, specifically, the service platform 101 may be connected to a network of a public security system, and may recognize the identity information of the recognized object in a face recognition manner; the medical alarm early warning method further comprises the following steps:
when the face feature information is matched with the data in the suspected dispute personnel database, acquiring personnel identity information corresponding to the face feature information, and sending the personnel identity information to a preset receiving end of the first hospital;
and when the face feature information is matched with the data in the dispute personnel database, acquiring personnel identity information corresponding to the face feature information, and sending the personnel identity information to a preset receiving end of the second hospital.
In this embodiment, the corresponding preset receiving end can receive the personnel identity information of the personnel with medical alarm risk.
Referring to fig. 3, in another example, after the step S40, the method may further include;
and step S51, controlling the second image acquisition module to track the target object corresponding to the face feature information.
When the face feature information is matched with the data in the dispute personnel database, a face tracking technology can be further utilized to control the second image acquisition module corresponding to the image data containing the face feature information to track the target object corresponding to the face feature information.
Step S60, continuously acquiring tracking image information acquired by the second image acquisition module tracking the target object, and extracting limb motion feature information of the target object from the tracking image information according to the face recognition algorithm and the limb motion recognition algorithm;
step S70, according to whether the action of the target object meets the preset condition; if yes, go to step S80;
and step S80, sending third alarm information to a preset receiving end of the second hospital.
It can be understood that, in this embodiment, by performing continuous tracking shooting on dispute personnel database personnel with a high medical alarm risk, the limb action feature information of the target object in the tracking image information is extracted through a face recognition algorithm and a limb action recognition algorithm; and judging whether the action of the target object meets preset conditions, such as whether dangerous articles are held, whether large-amplitude action and running exist, whether limb conflict behaviors exist, and the like, so that third alarm information is sent to a preset receiving end of a hospital, and corresponding personnel are informed to process in time. The grade of the second alarm information is greater than that of the first alarm information and the second alarm information.
Optionally, in a preferred embodiment, in the step S70, the determining whether the motion of the target object meets the preset condition according to the limb motion characteristic information of the target object may be performed by taking the limb motion characteristic information of the target object as sample input data, and predicting the limb motion of the target object through a pre-trained algorithm model to determine whether the motion of the target object meets the preset condition; the pre-trained algorithm model is an algorithm model which is obtained by training a neural network model constructed based on an error back propagation algorithm by taking pre-acquired limb action characteristic information as sample training data and judging whether actions corresponding to the limb action characteristic information meet preset conditions.
In the step of training the neural network model constructed based on the error back propagation algorithm, the calculation process of the error back propagation algorithm comprises a forward calculation process and a reverse calculation process;
the forward computing process comprises: processing the sample input data layer by layer through a hidden unit layer, and turning to an output result, and turning to reverse calculation when the output obtained by the output result does not accord with a preset expected value;
the reverse calculation process comprises: and returning the error signal with the output not in accordance with the preset expected value along the original path, modifying the weight of each neuron in the neural network model so as to adjust the error signal to be within a preset range, and returning to the forward calculation process.
In the embodiment, the limb action characteristic information is predicted through a neural network model constructed based on an error back propagation algorithm, so that the accuracy of limb action identification can be further improved; and then, the weight of each neuron in the neural network model can be dynamically adjusted by using an error back propagation algorithm so as to adjust the error signal to a preset range, thereby obtaining a more accurate operation model and result.
Further, after the step S40, the method may further include;
step S52, continuously acquiring sound information by a sound acquisition module which is matched with the position of the second image acquisition module in the second hospital, and judging whether the decibel value of the acquired sound information is larger than a preset decibel value;
and when the sound information emitted by the tracked target object is greater than a preset decibel value, the step S80 is entered, and third warning information is sent to a preset receiving end of the second hospital.
In this embodiment, when there is a person matching the dispute person database, it is detected whether there is a sound emission with a higher decibel level, such as sound-based conflict features of anger roar, quarrel, clutter, scream, etc., in the vicinity of the person, so as to further determine the risk of generating a medical alarm; the third warning information is sent to the preset receiving end of the hospital more accurately, and corresponding personnel are informed to process in time.
It is understood that, in an embodiment, the medical alarm warning method may further include the steps of:
acquiring update information for updating the dispute personnel database by a server of the hospital;
and updating the updated information to dispute personnel databases stored on the service terminals of other hospitals through the service platform.
In the embodiment, dispute personnel libraries of different hospitals can be updated, so that the information of dispute personnel can be synchronized in different hospitals in time, and the medical alarm processing capacity of other hospitals can be improved.
In an optional embodiment, the step S80 may specifically include: and when the body motion characteristic information of the target object determines that the motion of the target object meets a preset condition, sending third alarm information to a preset receiving end of a hospital where a camera collecting image data corresponding to the face characteristic information is located, and sending an alarm signal to a preset alarm system or a public security bureau.
Referring to fig. 1 to 4, the present invention further provides a service platform 101, which includes a memory 11, a processor 12 and a computer program stored in the memory 11 and executable on the processor 12, wherein the processor 12 implements the steps of the alarm warning method based on intelligent recognition according to any of the above embodiments when executing the computer program.
The invention further provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the steps of the medical alarm early warning method based on intelligent identification according to any of the above embodiments are implemented, which is not described herein again in detail.
It should be noted that, since the computer program of the computer readable storage medium is executed by the processor to implement the steps of the method, all the embodiments of the method are applicable to the computer readable storage medium, and can achieve the same or similar advantages.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A medical alarm early warning method based on intelligent identification is characterized by comprising the following steps:
acquiring image data acquired by an image acquisition module arranged in a hospital;
extracting face feature information in the image data, and judging whether the face feature information is matched with data in a suspected dispute personnel library and a dispute personnel library which are constructed according to preset danger judgment conditions;
when the face feature information is matched with the data in the suspected dispute personnel database, sending first alarm information to a preset receiving end of a first hospital where a first image acquisition module corresponding to the image data containing the face feature information is acquired;
and when the face feature information is matched with the data in the dispute personnel database, sending second alarm information to a preset receiving end of a second hospital where a second image acquisition module corresponding to the image data including the face feature information is acquired.
2. The medical alarm early warning method based on intelligent recognition according to claim 1, wherein after the step of sending the second alarm information to the preset receiving end of the second hospital where the second image acquisition module corresponding to the image data including the face feature information is located, the method further comprises the steps of:
controlling the second image acquisition module to track a target object corresponding to the face feature information;
continuously acquiring tracking image information acquired by the second image acquisition module tracking the target object, and extracting limb action characteristic information of the target object from the tracking image information according to the face recognition algorithm and the limb action recognition algorithm;
determining whether the action of the target object meets a preset condition or not according to the limb action characteristic information of the target object;
and when the action of the target object meets a preset condition, sending third alarm information to a preset receiving end of the second hospital.
3. The medical alarm early warning method based on intelligent recognition according to claim 1, wherein after the step of sending the second alarm information to the preset receiving end of the second hospital where the second image acquisition module corresponding to the image data including the face feature information is located, the method further comprises the steps of:
continuously acquiring sound information by a sound acquisition module which is matched with the position of the second image acquisition module in the second hospital, and judging whether the decibel value of the acquired sound information is larger than a preset decibel value or not;
and when the decibel value of the acquired sound information is greater than the preset decibel value, sending third alarm information to a preset receiving end of the second hospital.
4. The medical alarm early warning method based on intelligent recognition of claim 1, further comprising the steps of:
when the face feature information is matched with the data in the suspected dispute personnel database, acquiring personnel identity information corresponding to the face feature information, and sending the personnel identity information to a preset receiving end of the first hospital;
and when the face feature information is matched with the data in the dispute personnel database, acquiring personnel identity information corresponding to the face feature information, and sending the personnel identity information to a preset receiving end of the second hospital.
5. The medical alarm early warning method based on intelligent recognition of claim 1, further comprising the steps of:
acquiring identity information of suspected dispute personnel and identity information of dispute personnel according to the preset danger judgment condition;
acquiring facial feature information of the suspected dispute personnel according to the identity information of the suspected dispute personnel, and constructing a suspected dispute personnel library according to the identity information of the suspected dispute personnel and the acquired facial feature information of the suspected dispute personnel;
and acquiring the facial feature information of the dispute personnel according to the identity information of the dispute personnel, and constructing a dispute personnel library according to the identity information of the dispute personnel and the acquired facial feature information of the dispute personnel.
6. The medical alarm early warning method based on intelligent recognition of claim 5, wherein the preset danger judgment condition comprises one or more of the following steps:
acquiring a medical record of a patient hospitalized in a hospital, judging whether a preset medical fault exists in the hospitalizing process of the patient, acquiring identity information of a family of the patient corresponding to the patient according to family information recorded in the hospitalizing record of the patient when the preset medical fault exists in the hospitalizing process of the patient, and recording the identity information of the family of the patient as identity information of suspected dispute personnel, wherein the preset medical fault comprises one or more of disease deterioration, a disease vanishing, a rescue failure, a surgery failure and a surgery rescue failure;
acquiring identity information of professional medical alarming personnel or identity information of medical alarming personnel at the bottom of a desk, which is stored by a service platform, a public security system server or a preset information server, and recording the identity information of the professional medical alarming personnel or the identity information of the medical alarming personnel at the bottom of the desk as the identity information of dispute personnel;
acquiring a medical record of a patient hospitalized in a hospital, acquiring medical alarm index parameter information corresponding to the patient according to the medical record of the patient, judging whether a medical alarm risk evaluation result of the patient is greater than a preset rating through a preset medical alarm risk evaluation algorithm, acquiring identity information of a family of the patient corresponding to the patient according to family information recorded in the medical record of the patient when the medical alarm risk evaluation result is greater than the preset rating, and recording the identity information of the family of the patient as identity information of dispute personnel; the medical alarm index parameters comprise one or more of medical alarm record of the patient and relatives and friends thereof, credit record of the patient, illegal record of the patient and relatives and friends thereof, personal income information of the patient, family income information of the patient, and character evaluation information of the patient and relatives and friends thereof.
7. The medical alarm early warning method based on intelligent recognition according to claim 2 or 3, wherein the step of sending a third alarm message to a preset receiving end of the second hospital comprises:
and sending third alarm information to a preset receiving end of the second hospital, and sending an alarm signal to a preset alarm system or a public security bureau.
8. The medical alarm early warning method based on intelligent recognition of any one of claims 1-6, further comprising the steps of:
acquiring update information for updating the dispute personnel database by a server of the hospital;
and updating the updated information to dispute personnel databases stored on the service terminals of other hospitals through the service platform.
9. A service platform comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor when executing the computer program implements the steps of the intelligent identification based medical alarm warning method according to any one of claims 1 to 8.
10. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for medical alarm warning based on intelligent recognition according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810865119.3A CN110795587A (en) | 2018-08-01 | 2018-08-01 | Medical alarm early warning method, service platform and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810865119.3A CN110795587A (en) | 2018-08-01 | 2018-08-01 | Medical alarm early warning method, service platform and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110795587A true CN110795587A (en) | 2020-02-14 |
Family
ID=69425025
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810865119.3A Pending CN110795587A (en) | 2018-08-01 | 2018-08-01 | Medical alarm early warning method, service platform and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110795587A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111985304A (en) * | 2020-07-03 | 2020-11-24 | 深圳英飞拓智能技术有限公司 | Patrol alarm method, system, terminal equipment and storage medium |
| CN112036749A (en) * | 2020-08-31 | 2020-12-04 | 平安医疗健康管理股份有限公司 | Method and device for identifying risk user based on medical data and computer equipment |
| CN112071044A (en) * | 2020-09-02 | 2020-12-11 | 潘传迪 | Hospital alarm management system |
| CN112487972A (en) * | 2020-11-30 | 2021-03-12 | 福州外语外贸学院 | Anti-riot early warning method and device for office places in financial industry and storage medium |
| CN113221725A (en) * | 2021-05-08 | 2021-08-06 | 上海智蕙林医疗科技有限公司 | Risk processing method and system |
| CN113592315A (en) * | 2021-08-04 | 2021-11-02 | 北京沃东天骏信息技术有限公司 | Method and device for processing dispute order |
| CN113764094A (en) * | 2021-10-09 | 2021-12-07 | 哈尔滨思哲睿智能医疗设备有限公司 | Control method for medical device, computing device, medical device, and storage medium |
| CN113923239A (en) * | 2021-09-18 | 2022-01-11 | 苏州城之瞳安防智能科技有限公司 | System, method and medium applied to hospital security |
| CN113947874A (en) * | 2021-09-01 | 2022-01-18 | 北京声智科技有限公司 | Data processing method and device, electronic equipment and readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104658188A (en) * | 2015-03-13 | 2015-05-27 | 云南智图学泰科技有限公司 | Channel security early-warning system and channel early-warning method |
| CN104978571A (en) * | 2015-07-02 | 2015-10-14 | 湖北贝力思智能科技有限公司 | Intelligent dynamic high-definition video detection system |
| CN105913559A (en) * | 2016-04-06 | 2016-08-31 | 南京华捷艾米软件科技有限公司 | Motion sensing technique based bank ATM intelligent monitoring method |
| CN105959654A (en) * | 2016-07-13 | 2016-09-21 | 合肥指南针电子科技有限责任公司 | Intelligent management system for service hall |
| CN206039795U (en) * | 2016-09-14 | 2017-03-22 | 浙江维融电子科技股份有限公司 | Self service bank's safe alarm system |
| CN107886667A (en) * | 2017-10-11 | 2018-04-06 | 深圳云天励飞技术有限公司 | Alarm method and device |
-
2018
- 2018-08-01 CN CN201810865119.3A patent/CN110795587A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104658188A (en) * | 2015-03-13 | 2015-05-27 | 云南智图学泰科技有限公司 | Channel security early-warning system and channel early-warning method |
| CN104978571A (en) * | 2015-07-02 | 2015-10-14 | 湖北贝力思智能科技有限公司 | Intelligent dynamic high-definition video detection system |
| CN105913559A (en) * | 2016-04-06 | 2016-08-31 | 南京华捷艾米软件科技有限公司 | Motion sensing technique based bank ATM intelligent monitoring method |
| CN105959654A (en) * | 2016-07-13 | 2016-09-21 | 合肥指南针电子科技有限责任公司 | Intelligent management system for service hall |
| CN206039795U (en) * | 2016-09-14 | 2017-03-22 | 浙江维融电子科技股份有限公司 | Self service bank's safe alarm system |
| CN107886667A (en) * | 2017-10-11 | 2018-04-06 | 深圳云天励飞技术有限公司 | Alarm method and device |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111985304A (en) * | 2020-07-03 | 2020-11-24 | 深圳英飞拓智能技术有限公司 | Patrol alarm method, system, terminal equipment and storage medium |
| CN112036749A (en) * | 2020-08-31 | 2020-12-04 | 平安医疗健康管理股份有限公司 | Method and device for identifying risk user based on medical data and computer equipment |
| CN112071044A (en) * | 2020-09-02 | 2020-12-11 | 潘传迪 | Hospital alarm management system |
| CN112487972A (en) * | 2020-11-30 | 2021-03-12 | 福州外语外贸学院 | Anti-riot early warning method and device for office places in financial industry and storage medium |
| CN112487972B (en) * | 2020-11-30 | 2024-03-01 | 福州外语外贸学院 | Anti-riot early warning method, device and storage medium for office places in financial industry |
| CN113221725A (en) * | 2021-05-08 | 2021-08-06 | 上海智蕙林医疗科技有限公司 | Risk processing method and system |
| CN113592315A (en) * | 2021-08-04 | 2021-11-02 | 北京沃东天骏信息技术有限公司 | Method and device for processing dispute order |
| CN113947874A (en) * | 2021-09-01 | 2022-01-18 | 北京声智科技有限公司 | Data processing method and device, electronic equipment and readable storage medium |
| CN113923239A (en) * | 2021-09-18 | 2022-01-11 | 苏州城之瞳安防智能科技有限公司 | System, method and medium applied to hospital security |
| CN113764094A (en) * | 2021-10-09 | 2021-12-07 | 哈尔滨思哲睿智能医疗设备有限公司 | Control method for medical device, computing device, medical device, and storage medium |
| CN113764094B (en) * | 2021-10-09 | 2023-07-07 | 哈尔滨思哲睿智能医疗设备股份有限公司 | Medical device control method, computing device, medical device, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110795587A (en) | Medical alarm early warning method, service platform and computer readable storage medium | |
| Huebner et al. | The effect and implications of sex offender residence restrictions: Evidence from a two‐state evaluation | |
| CN109583278B (en) | Face recognition alarm method, device and system and computer equipment | |
| CN110020770A (en) | Risk and information management based on artificial intelligence | |
| US11631306B2 (en) | Methods and system for monitoring an environment | |
| CN112907636B (en) | Multi-target tracking method and device, electronic equipment and readable storage medium | |
| CN112382407A (en) | Risk management and control method and device, electronic equipment and storage medium | |
| CN113837030B (en) | Personnel intelligent management and control method and system for epidemic situation prevention and control and computer equipment | |
| CN111227789A (en) | Human health monitoring method and device | |
| CN111045894A (en) | Database anomaly detection method and device, computer equipment and storage medium | |
| CN111291596A (en) | Early warning method and device based on face recognition | |
| CN110688931A (en) | Abnormal behavior monitoring method and device, storage medium and electronic equipment | |
| CN116032602A (en) | Method, device, equipment and storage medium for automatically identifying threat data | |
| KR20210053718A (en) | Animal tracking monitoring server and operation method thereof | |
| KR102188981B1 (en) | Smart lonely deate protecting system and method thereof | |
| KR102157201B1 (en) | System and method for determining disastrous based on image and accident record analysis | |
| CN108446819A (en) | One kind being used for garden personal management trust evaluation system | |
| CN112115882A (en) | User online detection method and device, electronic equipment and storage medium | |
| CN115329347B (en) | Prediction method, device and storage medium based on car networking vulnerability data | |
| CN116862740A (en) | Intelligent prison management and control system based on Internet | |
| CN113762092A (en) | Hospital user medical alarm detection method, system, robot and storage medium | |
| CN112949442B (en) | Abnormal event pre-recognition method and device, electronic equipment and monitoring system | |
| CN110852517B (en) | Abnormal behavior early warning method and device, data processing equipment and storage medium | |
| CN113221725A (en) | Risk processing method and system | |
| KR102190759B1 (en) | System and mehtod for monitering emergency situation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200214 |