CN115690653A - Monitoring and early warning for realizing abnormal nursing behaviors of nursing staff based on AI behavior recognition - Google Patents
Monitoring and early warning for realizing abnormal nursing behaviors of nursing staff based on AI behavior recognition Download PDFInfo
- Publication number
- CN115690653A CN115690653A CN202211332010.6A CN202211332010A CN115690653A CN 115690653 A CN115690653 A CN 115690653A CN 202211332010 A CN202211332010 A CN 202211332010A CN 115690653 A CN115690653 A CN 115690653A
- Authority
- CN
- China
- Prior art keywords
- module
- data
- behavior
- nursing
- monitoring
- 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
- 230000006399 behavior Effects 0.000 title claims abstract description 64
- 238000012544 monitoring process Methods 0.000 title claims abstract description 49
- 230000000474 nursing effect Effects 0.000 title claims abstract description 37
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 22
- 230000015946 suckling behavior Effects 0.000 title claims abstract description 22
- 238000004458 analytical method Methods 0.000 claims abstract description 22
- 238000000034 method Methods 0.000 claims abstract description 16
- 230000006855 networking Effects 0.000 claims abstract description 4
- 230000008569 process Effects 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 8
- 238000007405 data analysis Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 230000009471 action Effects 0.000 description 15
- 206010000117 Abnormal behaviour Diseases 0.000 description 8
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 208000009144 Pure autonomic failure Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000013140 knowledge distillation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013312 porous aromatic framework Substances 0.000 description 1
Images
Landscapes
- Alarm Systems (AREA)
Abstract
The invention discloses a monitoring and early warning method for realizing abnormal nursing behaviors of a caregiver based on AI behavior recognition, which comprises a behavior monitoring and early warning system, wherein the behavior monitoring and early warning system comprises a camera module, an IOT (Internet of things) module, a data console, a big data module, an algorithm module and an information pushing module, and the camera module is used for: the system is used for collecting user limb behavior data; IOT thing networking module: the system is used for storing the collected data and relieving the pressure of the local server; the data center station: the device is used for carrying out preliminary analysis on the equipment data; a big data module: the method is used for carrying out algorithm analysis statistics on the equipment data. The invention is combined with the existing nursing monitoring means such as Bluetooth beacon and recording pen, more comprehensively supervises the service behavior and service quality of the nursing staff, can realize timely discovering of the inappropriate behavior of the nursing staff or the service object, can realize early problem discovery and early treatment, provides basis for subsequent treatment, realizes the realization of standardization aiming at home service of the nursing staff, and is beneficial to standardizing the nursing behavior of the industry.
Description
Technical Field
The invention belongs to the technical field of home care and nursing, and particularly relates to monitoring and early warning of abnormal nursing behaviors of a caregiver based on AI behavior recognition.
Background
At present, relevant monitoring equipment for the attendance service of a caregiver mainly comprises a recording pen and a Bluetooth beacon, wherein the Bluetooth beacon mainly aims at whether the caregiver really visits the service or not, but the Bluetooth beacon is violently moved by the caregiver to cause abnormal positioning monitoring;
the ability to service personnel action monitoring can also be realized to present wearing formula sensor detection equipment, but wearing formula action is surveyed, need dispose a large amount of sensors at customer's house, through the different signals that the sensor received, analyzes user's action, according to assorted algorithm content, whether analysis judgement service personnel exist improper action.
The evaluation aiming at the nursing staff is basically provided by the family of the nursing object and the nursing object, the nursing behavior of the nursing staff can be effectively monitored through active monitoring and passive spot check aiming at the possible unreal or deviation of the evaluation of the solitary old man, the nursing behavior of the nursing staff is ensured to be rarely or not to be wrongly presented in the nursing process, and the service quality is improved, so that the monitoring and early warning of the abnormal nursing behavior of the nursing staff based on AI behavior recognition are necessary.
The invention actively monitors whether the body movement of the nursing staff is abnormal when the nursing staff is in home service, actively monitors and discovers the improper behavior of the nursing staff according to the related algorithm, and gives an alarm of the improper behavior in time, the nursing behavior of the nursing staff can be evaluated in all directions and at multiple angles by active behavior monitoring and dialogue recording monitoring, and a certain monitoring effect can be achieved in the aspect of improving the service quality and the service attitude of the nursing staff.
Disclosure of Invention
In order to solve the technical problems, the invention is realized by the following technical scheme:
the invention discloses a monitoring and early warning system for realizing abnormal nursing behaviors of a caregiver based on AI behavior recognition, which comprises a behavior monitoring and early warning system, wherein the behavior monitoring and early warning system comprises a camera module, an IOT (Internet of things) module, a data console, a big data module, an algorithm module and an information pushing module;
a camera module: the system is used for collecting user limb behavior data;
IOT thing networking module: the system is used for storing the acquired data and relieving the pressure of a local server;
the data center station: the device is used for carrying out preliminary analysis on the equipment data;
a big data module: the device is used for carrying out algorithm analysis statistics on the device data;
an algorithm module: the behavior model is used for generating abnormal service finally through algorithm analysis and AI model training, comparing the abnormal service with the data acquired by the video, and judging whether the improper body behaviors occur in the user service process;
the information pushing module: the system is used for notifying relevant managers and guardians of possible improper behaviors in the service process of the nursing staff when the improper behaviors of the nursing staff are found.
Further, the camera module is connected with the IOT module for collecting the user limb behavior data and transmitting the collected user limb behavior data to the IOT module.
Further, the data center station stores the key data in a local server for data analysis and data forwarding.
Furthermore, the big data module extracts a data characteristic model and is combined with an algorithm analysis module to train a relevant model;
furthermore, the algorithm module is used for combining with the big data module and carrying out model characteristic analysis and characteristic extraction aiming at the monitoring data collected by the camera.
Further, the algorithm module is connected with the information pushing module and is used for receiving the information and informing relevant managers and guardians of the information when the improper body behaviors occur in the user service process, and the managers timely stop or stop the nursing service of the nurses through video monitoring.
Compared with the prior art, the invention has the following beneficial effects:
the invention is combined with the existing nursing monitoring means such as Bluetooth beacon and recording pen, more comprehensively supervises the service behavior and service quality of the nursing staff, can realize timely discovering of the improper behavior of the nursing staff or the service object, can realize early problem discovery and early treatment, provides basis for subsequent treatment, realizes the realization of standardization aiming at home service of the nursing staff, and is beneficial to standardizing the nursing behavior of the industry.
Of course, it is not necessary for any product in which the invention is practiced to achieve all of the above-described advantages at the same time.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic structural diagram of a behavior monitoring and early warning system according to the present invention;
fig. 2 is a schematic diagram of a monitoring flow pattern one according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a monitoring flow mode two according to the embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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.
The monitoring and early warning system for realizing abnormal nursing behaviors of nursing staff based on AI behavior recognition comprises a behavior monitoring and early warning system, wherein the behavior monitoring and early warning system comprises a camera module, an IOT (Internet of things) module, a data console, a big data module, an algorithm module and an information pushing module;
a camera module: the system is used for collecting user limb behavior data;
IOT thing networking module: the system is used for storing the collected data and relieving the pressure of the local server;
the data center station: the device is used for carrying out preliminary analysis on the equipment data;
a big data module: the device is used for carrying out algorithm analysis statistics on the device data;
an algorithm module: the behavior model is used for generating abnormal service finally through algorithm analysis and AI model training, comparing the abnormal service with the data acquired by the video, and judging whether the improper body behaviors occur in the user service process;
the information pushing module: when finding that the caregivers have improper behaviors, informing relevant management personnel and guardians of the improper behaviors which may occur in the service process of the caregivers;
video detection abnormal behavior algorithm:
since the abnormal behavior detection in the field of care, we extract 14 key points of the human body for the service scene: k i ＝(k 1 ,k 2 ,...,k 14 ) In which K is i Representing the ith person, extracting key points by using an autonomously trained and reconstructed lightweight OpenPose model, adopting a MobileNet V3 network for backbone, extracting 3-stage Confidencemaps and predicting 2-stage PAFs, and combining the prediction result of the previous frame to carry out smoothing treatment;
R t ＝F(I,R t-1 ；θ)
wherein R is t The method is characterized in that 14 key points of the old people in a tth frame of picture are contained in a tth output vector, I is original picture characteristics, F is a model function, theta is a model parameter, in order to be more suitable for two-person scenes in the field of care, an original coco data set is subjected to data enhancement, pictures with the number of people exceeding 4 are filtered, and after the model is initially trained, the model is subjected to fine adjustment by using pictures extracted from a real care video in a mode that an original edition OpenPose model is used for knowledge distillation.
After extracting the posture key points of the caregiver and the old, the behavior of the caregiver is predicted by the continuous caregiver key points and the old key point data of 10 frames through a feedforward neural network:
wherein B is t As a probability distribution of the caregiver's various behaviors at time t, W i For the weights of the layer i feedforward neural network,
the abscissa of the caregiver's 14 limb key points at approximately 10 moments,
ordinate of 14 limb key points for the caregiver at approximately 10 moments, b i Is the bias of the ith layer feedforward neural network.
Meanwhile, the distance between partial point locations of the caregiver and partial point locations of the old people and the limb movement amplitude and movement speed trend are calculated to judge whether the caregiver has behaviors such as hitting or kicking on the old people:
wherein D t Probability of hitting or kicking actions for the old at time t, wherein D t ∈[0,1]。k 0j Abscissa, k, representing the jth limb keypoint 1h The ordinate of the h limb keypoint is represented.
Then, judging whether abnormal behaviors exist in the nursing staff or not by combining the neural network prediction result and the point location distance:
A t ＝Sigmoid(w 0 B t +w 1 D t )
wherein A is t Indicating the probability of the elderly having abnormal behavior, wherein A t ∈[0,1]。w 0 ∈[0,1]And w 1 ∈[0,1]For the correlation coefficient, it is responsible for coordinating B t And D t The weight of (c).
Will eventually be according to A t And set thresholds to alert the caregiver to their behavior:
specific dangerous behavior of caregiver according to B t To obtain:
Behavior＝Text(argmax B t )
wherein argmax is an index corresponding to the maximum value, namely, the probability of which Behavior is the highest is obtained, text is a character Behavior for translating the index into the corresponding character Behavior, and Behavior is a character description of the Behavior of the old people at the time t.
Preferably, the camera module is connected with the IOT module for transmitting the collected user limb behavior data to the IOT module.
Further, the data center station stores the key data in a local server for data analysis and data forwarding.
Furthermore, the big data module extracts a data characteristic model and is combined with an algorithm analysis module to train a relevant model;
furthermore, the algorithm module is used for combining with the big data module and carrying out model characteristic analysis and characteristic extraction aiming at the monitoring data collected by the camera.
Further, the algorithm module is connected with the information pushing module and is used for receiving the information and informing relevant managers and guardians of the information when the improper body behaviors occur in the user service process, and the managers timely stop or stop nursing services of the nurses through video monitoring;
the abnormal behavior monitoring model is generated by analyzing the user limb action data collected by the camera and combining a related algorithm and AI training, and whether the caregivers and the old people have improper behaviors or not can be analyzed according to the comparison between the action analysis result and the monitoring model.
Mode one, as shown in fig. 2:
1) The system is installed on video monitoring equipment of the old, and collects user data in real time.
2) And pushing the video monitoring data to an IOT platform.
3) And the algorithm analysis system performs data analysis from the subscribed data of the Internet of things platform. And analyzing whether abnormal behaviors exist in the limb data in the video stream according to a set algorithm model.
4) And when the abnormal behavior is detected in the video monitoring stream, informing relevant management personnel to perform subsequent processing.
Mode two, as shown in fig. 3:
1) Firstly, video stream data acquisition is carried out on a training side, and data is pushed to an IOT data center.
2) And the data analysis platform pulls data from the data middle platform to perform data analysis, and performs model training according to a related algorithm.
3) And after the model training is finished, outputting the abnormal behavior monitoring model.
4) The model is deployed in a user side camera which is sent to the old, once a behavior model deployed in the local camera is detected in a video stream acquired by the camera, relevant information is pushed to an IOT (Internet of things) server, a background service subscribes the IOT information, and subsequent processing is carried out.
The monitoring and early warning of abnormal nursing behaviors of a caregiver based on AI behavior recognition can be realized by monitoring the action behaviors of the caregiver through the camera, analyzing the limb action data collected by the camera, analyzing the service behaviors of the caregiver by combining related algorithms, comprehensively analyzing whether the caregiver has improper nursing behaviors in the service process by combining the data analyzed by the algorithms with related judgment conditions, analyzing the nursing behaviors of the caregiver deeply by monitoring the limb action data of the match person collected by equipment through the camera, analyzing the limb actions by the algorithm of the limb actions and analyzing the nursing behaviors of the caregiver deeply according to the algorithm analysis result, so that the nursing quality of the caregiver can be further judged by integrally analyzing the nursing behaviors of the caregiver.
Camera video monitoring action analysis, except can monitoring caregiver's nursing action, can also monitor and analyze caregiver in nursing process, whether the old man has improper action, current caregiver team mainly uses the women as the owner, women's caregiver probably meets individual old man's harassment in the nursing service in-process of going up, when the camera monitors the old man and appears improper action, can in time inform relevant managers, in time communicate with the caregiver, avoid the unexpected condition to appear, serve the sign to this type of old man, follow-up if provide continuation service, then arrange like nature caregiver service of going up to the door as far as possible.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise embodiments disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (6)
1. Monitoring and early warning of abnormal nursing behaviors of nursing staff are realized based on AI behavior recognition, and the system comprises a behavior monitoring and early warning system and is characterized in that the behavior monitoring and early warning system comprises a camera module, an IOT (Internet of things) module, a data console, a big data module, an algorithm module and an information pushing module;
a camera module: the system is used for collecting user limb behavior data;
IOT thing networking module: the system is used for storing the collected data and relieving the pressure of the local server;
the data center station: the device is used for carrying out preliminary analysis on the equipment data;
a big data module: the device is used for carrying out algorithm analysis statistics on the device data;
an algorithm module: the behavior model is used for generating abnormal service finally through algorithm analysis and AI model training, comparing the abnormal service with the data acquired by the video, and judging whether the improper body behaviors occur in the user service process;
the information pushing module: the system is used for notifying relevant managers and guardians of possible improper behaviors in the service process of the nursing staff when the improper behaviors of the nursing staff are found.
2. The AI-behavior-recognition-based monitoring and early warning of abnormal nursing behaviors of a caregiver as recited in claim 1, wherein the camera module is connected to the IOT module for transmitting collected body behavior data of the user to the IOT module.
3. The AI-behavior-recognition-based caregiver abnormal care behavior monitoring and early warning of claim 1, wherein the data center stores critical data in a local server for data analysis and data forwarding.
4. The AI-behavior-recognition-based monitoring and early warning of abnormal nursing behaviors of caregivers according to claim 1, wherein the big data module extracts a data feature model and performs training of a relevant model in combination with an algorithmic analysis module.
5. The AI-behavior-recognition-based monitoring and early warning of abnormal nursing behaviors of a caregiver, as recited in claim 1, wherein the algorithm module is configured to perform model property analysis and property extraction on the monitored data collected by the camera in conjunction with the big data module.
6. The AI-behavior-recognition-based monitoring and early warning of abnormal nursing behaviors of caregivers according to claim 1, wherein the algorithm module is connected with the information pushing module, and is used for receiving and notifying information to relevant managers and guardians when it is judged that an improper limb behavior occurs in a user service process, and the managers timely stop or stop the caregivers from performing nursing services through video monitoring.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211332010.6A CN115690653A (en) | 2022-10-28 | 2022-10-28 | Monitoring and early warning for realizing abnormal nursing behaviors of nursing staff based on AI behavior recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211332010.6A CN115690653A (en) | 2022-10-28 | 2022-10-28 | Monitoring and early warning for realizing abnormal nursing behaviors of nursing staff based on AI behavior recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115690653A true CN115690653A (en) | 2023-02-03 |
Family
ID=85046435
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211332010.6A Pending CN115690653A (en) | 2022-10-28 | 2022-10-28 | Monitoring and early warning for realizing abnormal nursing behaviors of nursing staff based on AI behavior recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115690653A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116665402A (en) * | 2023-04-27 | 2023-08-29 | 无锡稚慧启蒙教育科技有限公司 | Anti-lost system and method based on Internet of things |
| CN116863638A (en) * | 2023-06-01 | 2023-10-10 | 国药集团重庆医药设计院有限公司 | Personnel abnormal behavior detection method and security system based on active early warning |
| CN117542498A (en) * | 2024-01-08 | 2024-02-09 | 安徽医科大学第一附属医院 | Gynecological nursing management system and method based on big data analysis |
-
2022
- 2022-10-28 CN CN202211332010.6A patent/CN115690653A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116665402A (en) * | 2023-04-27 | 2023-08-29 | 无锡稚慧启蒙教育科技有限公司 | Anti-lost system and method based on Internet of things |
| CN116863638A (en) * | 2023-06-01 | 2023-10-10 | 国药集团重庆医药设计院有限公司 | Personnel abnormal behavior detection method and security system based on active early warning |
| CN116863638B (en) * | 2023-06-01 | 2024-02-23 | 国药集团重庆医药设计院有限公司 | Personnel abnormal behavior detection method and security system based on active early warning |
| CN117542498A (en) * | 2024-01-08 | 2024-02-09 | 安徽医科大学第一附属医院 | Gynecological nursing management system and method based on big data analysis |
| CN117542498B (en) * | 2024-01-08 | 2024-04-16 | 安徽医科大学第一附属医院 | Gynecological nursing management system and method based on big data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115690653A (en) | Monitoring and early warning for realizing abnormal nursing behaviors of nursing staff based on AI behavior recognition | |
| CN106412501B (en) | A kind of the construction safety behavior intelligent monitor system and its monitoring method of video | |
| Mubashir et al. | A survey on fall detection: Principles and approaches | |
| CN108647582A (en) | Goal behavior identification and prediction technique under a kind of complex dynamic environment | |
| US20030058111A1 (en) | Computer vision based elderly care monitoring system | |
| US20180314897A1 (en) | Surveillance System with Human Behavior Prediction by Human Action Recognition | |
| Teyeb et al. | A novel approach for drowsy driver detection using head posture estimation and eyes recognition system based on wavelet network | |
| Gowsikhaa et al. | Suspicious Human Activity Detection from Surveillance Videos. | |
| CN111127830A (en) | Alarm method, alarm system and readable storage medium based on monitoring equipment | |
| CN114469076B (en) | Identity-feature-fused fall identification method and system for solitary old people | |
| CN111275910B (en) | Method and system for detecting border crossing behavior of escalator based on Gaussian mixture model | |
| CN112949417A (en) | Tumble behavior identification method, equipment and system | |
| CN115984767A (en) | Abnormity early warning method and system based on real-time analysis of monitoring picture | |
| CN113850229A (en) | Method and system for early warning abnormal behaviors of people based on video data machine learning and computer equipment | |
| CN110415152A (en) | A kind of safety monitoring system | |
| CN116563797B (en) | Monitoring management system for intelligent campus | |
| CN116189305A (en) | Personnel dangerous action recognition method based on neural network model embedding | |
| Kanthaseelan et al. | CCTV intelligent surveillance on intruder detection | |
| Nandyal et al. | Recognition of suspicious human activities using klt and kalman filter for atm surveillance system | |
| CN116778657A (en) | Method and system for intelligently identifying intrusion behavior | |
| CN115148336A (en) | AI discernment is supplementary psychological disorders of lower System for evaluating treatment effect of patient | |
| Hagui et al. | A new framework for elderly fall detection using coupled hidden markov models. | |
| Soman et al. | A Novel Fall Detection System using Mediapipe | |
| Chong et al. | Visual based fall detection with reduced complexity horprasert segmentation using superpixel | |
| Anderson et al. | Extension of a soft-computing framework for activity analysis from linguistic summarizations of video |
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 | ||
| CB02 | Change of applicant information |
Address after: Room 901, 1388 Shuidian Road, Hongkou District, Shanghai 200434 Applicant after: Fushoukang Smart Medical Elderly Care Services (Shanghai) Co.,Ltd. Address before: Room 901, 1388 Shuidian Road, Hongkou District, Shanghai 200434 Applicant before: Fu Shou Kang Smart (Shanghai) Medical Elderly Care Service Co.,Ltd. |
|
| CB02 | Change of applicant information |