Newborn care unit environment early warning monitoring system and method

Abstract

The invention relates to the technical field of data analysis, in particular to a neonatal care unit environment early warning monitoring system and method, and the method comprises the steps that a data collection module collects environment information in a neonatal care unit; the data processing module preprocesses the environment information; the data judgment module judges whether the preprocessed environment information belongs to a preset safety range or not, and if not, early warning information is generated; the data analysis module is used for analyzing the environment information by adopting a neural network model, identifying the cleaning state information of the hands of each medical worker in the neonatal care unit, judging whether the hands of the medical workers are in a hand hygiene completion state or not, and generating hand cleaning prompt information if the hands of the medical workers are not in the hand hygiene completion state; and the central control early warning module receives the early warning information, carries out early warning according to the early warning information, receives hand cleaning prompt information, and carries out display and pre-reminding. According to the scheme, the collected environment information in the neonatal care unit can be analyzed in multiple directions, the data utilization rate is increased, and the monitoring accuracy and comprehensiveness are guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a neonatal intensive care unit environment early warning monitoring system and method. Background Art

[0002] The Neonatal Intensive Care Unit (NICU) is a department in the hospital that is dedicated to the treatment and care of premature babies and other newborns who need special medical care. In the NICU, newborns are cared for by medical staff throughout the entire process. In this environment, maintaining stable temperature, humidity, sound, light intensity, air quality and other conditions is crucial to the health of newborns. Therefore, it is necessary to establish an early warning monitoring system for the NICU environment.

[0003] Common early warning monitoring systems are mainly used to achieve real-time monitoring of environmental parameters in neonatal intensive care units, to provide timely warnings when environmental parameters exceed the safe range, and to support remote monitoring and management, so that medical staff can understand environmental conditions at any time. For a large amount of collected data, only the safe range is analyzed, the analysis method is single, and the data utilization rate is low, which affects the accuracy and comprehensiveness of monitoring.

[0004] In particular, the early warning monitoring system only monitors the environmental parameters in the neonatal intensive care unit in real time. It does not monitor whether the medical staff who are the only ones in contact with the newborns comply with the contact requirements of the neonatal intensive care unit and accurately clean and disinfect their hands. Newborns in the neonatal intensive care unit are cared for by medical staff throughout the entire process. As the only outsiders who can come into contact with the newborns, medical staff need to comply with strict disinfection procedures and clean their hands properly when entering the neonatal intensive care unit to prevent the introduction of germs.

[0005] Therefore, there is an urgent need for a neonatal intensive care unit environment early warning monitoring system and method, which can conduct multi-directional analysis of the collected environmental information in the neonatal intensive care unit, improve data utilization, ensure the accuracy and comprehensiveness of monitoring, and monitor and analyze whether medical staff comply with contact requirements based on the collected environmental information, perform accurate hand cleaning, and further ensure the safety of the neonatal intensive care unit. Summary of the invention

[0006] One of the purposes of the present invention is to provide a neonatal intensive care unit environment early warning monitoring system, which can conduct multi-directional analysis on the collected environmental information in the neonatal intensive care unit, improve data utilization, and ensure the accuracy and comprehensiveness of monitoring.

[0007] The present invention provides a basic solution 1: a neonatal intensive care unit environment early warning monitoring system, comprising:

[0008] A data acquisition module, used to collect environmental information in the neonatal intensive care unit;

[0009] A data processing module, used for preprocessing environmental information;

[0010] The data judgment module is used to judge whether the pre-processed environmental information belongs to the preset safety range. If not, it generates warning information and sends it to the central control warning module;

[0011] The data analysis module is used to analyze the pre-processed environmental information using a neural network model to identify the cleanliness status information of the hands of medical staff in the neonatal intensive care unit, and determine whether the hands of the medical staff are in a hand hygiene completion state based on the cleanliness status information. If not, a hand cleaning prompt message is generated and sent to the central control warning module;

[0012] The central control warning module is used to receive warning information and issue warnings based on the warning information; it is also used to receive hand cleaning reminder information and display and pre-remind based on the hand cleaning reminder information.

[0013] Furthermore, the environmental information includes one or more of temperature and humidity information, air quality information, sound information, lighting information, and surveillance video image information.

[0014] Furthermore, the pre-processed environmental information is analyzed using a neural network model to identify the cleanliness status information of the hands of each medical staff in the neonatal intensive care unit, including:

[0015] The CNN neural network model is used to take the monitoring video image information as input and output the cleanliness status information of each medical staff member's hands;

[0016] The CNN neural network model includes: input layer, output layer, several convolutional layers, pooling layers, and fully connected layers;

[0017] The input layer inputs the monitoring video image information, and then passes through the convolution layer to extract image features, the pooling layer to compress image features, and the fully connected layer to analyze the cleanliness status information of each medical staff member's hands based on the image features.

[0018] Furthermore, the specific structure of the CNN neural network model is: an input layer and an output layer, two convolutional layers, a pooling layer and a fully connected layer;

[0019] The preprocessed surveillance video image information is input through the input layer and transmitted to the first convolutional layer for image feature C1 extraction;

[0020] The image feature C1 is input into the first pooling layer for image feature compression to obtain the image feature S2. The strategy adopted by the pooling layer is maximum pooling.

[0021] Input the image feature S2 into the second convolutional layer to extract the image feature C3;

[0022] Input the image feature C3 to the second pooling layer for image feature compression to obtain image feature S4;

[0023] The image feature S4 is input into the first fully connected layer to analyze the cleanliness status information of each medical staff member's hands, obtain the output result F5, and activate the output result F5 using the Leaky ReLU function;

[0024] The activated output result F5 is input to the second fully connected layer to analyze the clean status information of each medical staff member's hands, obtain the output result F6, and activate the output result F6 using the Leaky ReLU function; wherein the number of nodes in the first fully connected layer and the second fully connected layer are both greater than or equal to the number of image features S4;

[0025] The activated output result F6 is input into the output layer for conversion, and the final prediction result f(out) is output as the cleanliness status information of the medical staff's hands.

[0026] Furthermore, historical surveillance video image information and medical staff hand cleaning status information are used to construct training sets and validation sets to train and validate the CNN neural network model, including:

[0027] The constructed CNN neural network model is trained using the training set;

[0028] The trained CNN neural network model is verified using the validation set. If it meets the preset requirements, the training is completed and the trained CNN neural network model is output;

[0029] If it does not meet the preset requirements, continue to train the CNN neural network model;

[0030] During the training process, the weights of the nodes in the fully connected layer are updated using an optimization algorithm, including:

[0031] Randomly generate several weight schemes as individual schemes to form an initial population;

[0032] Construct a weight evaluation function based on the training evaluation value of the CNN neural network model;

[0033] According to the weight evaluation function, select the weight scheme in the initial population, perform iterative optimization, and obtain the optimal weight scheme. Further, construct a weight evaluation function to evaluate the difference between the final prediction result f(out) and the actual result y, which is:

[0034] P=aE -1 ;

[0035] Where P is the weight evaluation value, E is the mean square error loss function, and a is the adjustment constant;

[0036]

[0037] Among them, f(out i ) is the final prediction result output by the CNN neural network model of the input data in the i-th group of training data in the training set, y i is the actual result in the i-th group of training data in the training set.

[0038] Further, the weighting scheme in the initial population is selected according to the weight evaluation function, and iterative optimization is performed to obtain the optimal weighting scheme, including:

[0039] Initialize the number of iterations k = 1;

[0040] According to the individual schemes in the population, the weights in the CNN neural network model are set, and the CNN neural network models with different weights are trained using the same training set to obtain the corresponding final prediction results f(out i );

[0041] According to the mean square error loss function, calculate the weight evaluation value P of each individual solution j , where is the weight evaluation value of the jth individual solution;

[0042] According to the weight evaluation value P of each individual solution j , using the roulette wheel method to select individual solutions from the initial population; the selection probability is proportional to the weight evaluation value;

[0043] The selected individual solutions are mutated and crossed, and the individual solutions that cannot be realized are eliminated to form a new population; among them, the unrealizable ones;

[0044] Determine whether the current number of iterations is equal to the preset number. If so, obtain the individual solution with the largest weight evaluation value as the optimal weight solution. If not, update the number of iterations k=k+1, and then execute according to the individual solutions in the population, set the weights in the CNN neural network model, and use the same training set to train the CNN neural network models with different weights to obtain the corresponding final prediction results f(out i ).

[0045] Further, according to the mean square error loss function, the weight evaluation value P of each individual solution is calculated. j , where is the weight evaluation value of the jth individual solution, and also includes:

[0046] Compare whether the weight evaluation value of each individual solution in the kth iteration is greater than the weight evaluation value of the corresponding parent in the k-1th iteration. If not, replace the individual solution in the kth iteration with the individual solution of its parent. If so, execute the weight evaluation value P of each individual solution. j , using the roulette method to select individual solutions from the initial population.

[0047] Furthermore, in the CNN neural network model, the image feature dimension is expanded according to the environmental information, the fully connected layer analyzes the cleanliness status information of each medical staff member's hands according to the image features of the feature dimension, and the output layer outputs the cleanliness status information of each medical staff member's hands.

[0048] Beneficial effects of this solution: This solution collects environmental information in the neonatal intensive care unit through the data acquisition module. In addition to the traditional method of judging whether the pre-processed environmental information belongs to the preset safety range, if not, generating warning information and sending it to the central control warning module for warning, this solution also sets up a data analysis module to analyze the pre-processed environmental information using a neural network model, identify the cleanliness status information of the hands of medical staff in the neonatal intensive care unit, and judge whether the hands of the medical staff are in a hand hygiene completion state based on the cleaning status information. If not, generate hand cleaning prompt information, increase the analysis method, and improve data utilization;

[0049] In particular, this solution constructs a neural network model to analyze the surveillance video image information, and uses historical data to train the neural network model to ensure the accuracy of the neural network model prediction. At the same time, during the training of the neural network model, the weights of the nodes in the fully connected layer are updated using an optimization algorithm. The weight scheme is evaluated according to the constructed weight evaluation function, and cross-mutation and iterative optimization are performed to find the optimal weight scheme, thereby further improving the accuracy of the neural network model prediction.

[0050] Multi-faceted early warning monitoring and analysis can effectively ensure the accuracy and comprehensiveness of neonatal intensive care unit monitoring.

[0051] In summary, this solution can conduct multi-directional analysis of the environmental information collected in the neonatal intensive care unit, improve data utilization, ensure the accuracy and comprehensiveness of monitoring, and monitor and analyze whether medical staff comply with contact requirements and perform accurate hand cleaning based on the collected environmental information, thereby further ensuring the safety of the neonatal intensive care unit.

[0052] The second purpose of the present invention is to provide a neonatal intensive care unit environment early warning monitoring method, which can conduct multi-directional analysis of the collected environmental information in the neonatal intensive care unit, improve data utilization, ensure the accuracy and comprehensiveness of monitoring, and can monitor and analyze whether medical staff comply with contact requirements based on the collected environmental information, perform accurate disinfection, and further ensure the safety of the neonatal intensive care unit.

[0053] The present invention provides a second basic solution: a method for early warning monitoring of the environment of a neonatal intensive care unit, using the above-mentioned early warning monitoring system for the environment of a neonatal intensive care unit, comprising:

[0054] Collect environmental information in the neonatal intensive care unit;

[0055] Preprocessing of environmental information;

[0056] Determine whether the pre-processed environmental information belongs to the preset safety range. If not, generate warning information and issue a warning based on the warning information;

[0057] The pre-processed environmental information is analyzed using a neural network model to identify the cleanliness status information of the hands of medical staff in the neonatal intensive care unit, and based on the cleanliness status information, it is determined whether the hands of the medical staff are in a hand hygiene completion state. If not, hand cleaning prompt information is generated, and displayed and pre-reminded based on the hand cleaning prompt information. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 The present invention is a logic block diagram of an embodiment of a neonatal intensive care unit environment early warning monitoring system. DETAILED DESCRIPTION

[0059] The following is further described in detail through specific implementation methods:

[0060] Embodiment 1

[0061] The embodiment is basically as shown in the attached Figure 1 Shown: A neonatal intensive care unit environment early warning monitoring system, comprising:

[0062] A data acquisition module is used to collect environmental information in the neonatal intensive care unit; the environmental information includes one or more of temperature and humidity information, air quality information, sound information, lighting information, and monitoring video image information;

[0063] The data processing module is used to pre-process the environmental information; the pre-processing includes: data standardization and data cleaning; in particular, the monitoring video image information is pre-processed, including: de-meaning, normalization, PCA dimensionality reduction and whitening;

[0064] The data judgment module is used to judge whether the pre-processed environmental information belongs to the preset safety range. If not, it generates warning information and sends it to the central control warning module;

[0065] Specifically, according to the temperature and humidity information, it is determined whether the temperature and humidity belong to the preset temperature and humidity range. If not, a warning message containing abnormal temperature and humidity is generated and sent to the central control warning module; wherein the temperature and humidity include temperature and humidity, and a preset temperature range and a preset humidity range are set correspondingly. If the temperature or humidity does not belong to the corresponding preset temperature range or preset humidity range, a warning message containing abnormal temperature and humidity is generated and sent to the central control warning module;

[0066] According to the air quality information, determine whether the air quality falls within the preset air quality range. If not, generate warning information containing abnormal air quality and send it to the central control warning module; the air quality information mainly includes: sulfur dioxide (SO2) concentration, nitrogen dioxide (NO2) concentration, inhalable particulate matter (PM10) concentration, carbon monoxide (CO) concentration, fine particulate matter (PM2.5) concentration;

[0067] According to the sound information, determine whether the sound belongs to the preset sound range. If not, generate an early warning message containing abnormal sound and send it to the central control early warning module;

[0068] According to the lighting information, it is determined whether the lighting information meets the preset lighting intensity range of the current time node. If not, an early warning message containing lighting anomalies is generated and sent to the central control early warning module.

[0069] The data analysis module is used to analyze the pre-processed environmental information using a neural network model to identify the cleanliness status information of the hands of medical staff in the neonatal intensive care unit, and determine whether the hands of the medical staff are in a hand hygiene completion state based on the cleanliness status information. If not, a hand cleaning prompt message is generated and sent to the central control warning module;

[0070] Specifically, the monitoring video image information includes: monitoring video images of medical staff washing hands collected by a monitoring device set up in the hand washing area of ​​the neonatal intensive care unit; the neural network model evaluates the cleanliness status of the medical staff's hands based on the monitoring video image information of the medical staff washing hands, and outputs an evaluation value, i.e., the cleanliness status information;

[0071] The CNN neural network model is used to take the pre-processed monitoring video image information as input, output the cleaning status information of each medical staff's hands, and judge whether the cleaning status information belongs to the preset status value range. If so, it is judged that the medical staff's hands are in the hand hygiene completion state. If not, it is judged that the medical staff's hands are not in the hand hygiene completion state, and the hand cleaning prompt information is generated and sent to the central control warning module; the CNN neural network model judges whether the medical staff's hand washing process complies with the preset hand washing actions, such as the seven-step hand washing method, based on the pre-processed monitoring video image information, so as to generate and output the cleaning status information;

[0072] The CNN neural network model includes: input layer, output layer, several convolutional layers, pooling layers, and fully connected layers;

[0073] The input layer inputs the monitoring video image information, and then extracts the image features through the convolution layer, compresses the image features through the pooling layer, and analyzes the cleanliness status information of each medical staff's hands according to the image features in the fully connected layer. The output layer outputs the cleanliness status information of the medical staff's hands;

[0074] Specifically, the specific structure of the CNN neural network model in this embodiment is: an input layer and an output layer, two convolutional layers, a pooling layer and a fully connected layer;

[0075] The preprocessed surveillance video image information is input through the input layer and transmitted to the first convolutional layer for image feature C1 extraction;

[0076] The image feature C1 is input into the first pooling layer for image feature compression to obtain the image feature S2. The strategy adopted by the pooling layer is Max Pooling.

[0077] Input the image feature S2 into the second convolutional layer to extract the image feature C3;

[0078] Input the image feature C3 to the second pooling layer for image feature compression to obtain image feature S4;

[0079] The image feature S4 is input into the first fully connected layer to analyze the cleanliness status information of each medical staff member's hands, obtain the output result F5, and activate the output result F5 using the Leaky ReLU function (non-linear mapping);

[0080] The activated output result F5 is input to the second fully connected layer to analyze the clean status information of each medical staff member's hands, obtain the output result F6, and activate the output result F6 using the Leaky ReLU function; wherein the number of nodes in the first fully connected layer and the second fully connected layer are both greater than or equal to the number of image features S4;

[0081] The activated output result F6 is input into the output layer (softmax layer) for conversion, and the final prediction result f(out), i.e., the cleanliness status information of the medical staff's hands, is output.

[0082] In the process of building the CNN neural network model, historical surveillance video image information and medical staff's hand cleaning status information were used to build training sets and validation sets;

[0083] The constructed CNN neural network model is trained using the training set;

[0084] The trained CNN neural network model is verified using the validation set. If it meets the preset requirements, the training is completed and the trained CNN neural network model is output;

[0085] If it does not meet the preset requirements, continue to train the CNN neural network model;

[0086] In the above training process, the weights of the nodes in the fully connected layer are updated using an optimization algorithm;

[0087] Specifically,

[0088] Randomly generate several weight schemes as individual schemes to form the initial population; specifically, the weight scheme is [w1,w2,…,w m ], where w m is the mth weight value;

[0089] Construct a weight evaluation function based on the training evaluation value of the CNN neural network model;

[0090] Specifically, a weight evaluation function is constructed to evaluate the difference between the final prediction result f(out) and the actual result y, which is:

[0091] P = aE -1 ;

[0092] Where P is the weight evaluation value, E is the mean square error loss function, and a is the adjustment constant;

[0093]

[0094] Among them, f(out i ) is the final prediction result output by the CNN neural network model of the input data in the i-th group of training data in the training set, y i is the actual result in the i-th group of training data in the training set;

[0095] According to the weight evaluation function, select the weight scheme in the initial population, perform iterative optimization, and obtain the optimal weight scheme;

[0096] Specifically, the number of initialization iterations k=1;

[0097] According to the individual schemes in the population, the weights in the CNN neural network model are set, and the CNN neural network models with different weights are trained using the same training set to obtain the corresponding final prediction results f(out i );

[0098] According to the mean square error loss function, calculate the weight evaluation value P of each individual solution j , where is the weight evaluation value of the jth individual solution;

[0099] According to the weight evaluation value P of each individual solution j , using the roulette wheel method to select individual solutions from the initial population; the selection probability is proportional to the weight evaluation value;

[0100] The selected individual schemes are mutated and crossovered to form a new population;

[0101] Determine whether the current number of iterations is equal to the preset number. If so, obtain the individual solution with the largest weight evaluation value as the optimal weight solution. If not, update the number of iterations k=k+1, and then execute according to the individual solutions in the population, set the weights in the CNN neural network model, and use the same training set to train the CNN neural network models with different weights to obtain the corresponding final prediction results f(out i ).

[0102] In other embodiments, the weight evaluation value P of each individual solution is j , using the roulette wheel method, before selecting individual solutions in the initial population, it also includes:

[0103] Determine whether there is an individual solution with a weight evaluation value greater than the preset weight evaluation value. If so, the individual solution with the largest weight evaluation value in the current population is used as the optimal weighted solution. If not, execute the solution based on the weight evaluation value P of each individual solution. j , a roulette wheel method is used to select individual solutions in the initial population, so that when a weight solution that meets the preset weight requirements is reached, the iteration is ended early, which reduces computing requirements and memory consumption and speeds up the training process.

[0104] The central control warning module is used to receive warning information and issue warnings based on the warning information; it is also used to receive hand cleaning prompt information and display and pre-remind based on the hand cleaning prompt information;

[0105] Specifically, the central control warning module receives warning information containing different abnormalities and issues corresponding warnings. The specific warning methods include but are not limited to sound and light warnings, pop-up window warnings, information push warnings and other warning methods to ensure the effectiveness of the warnings. At the same time, the central control warning module is also used to receive hand cleaning reminder information and display it according to the hand cleaning reminder information, so as to facilitate monitoring of the situation in the neonatal intensive care unit and ensure the safety of newborns. At the same time, a soft light reminder device is set in the hand washing area of ​​the neonatal intensive care unit. According to the hand cleaning reminder information, the soft light is controlled to light up, so as not to affect the internal lighting, but also directly remind medical staff that their hands are not cleaned properly.

[0106] In other embodiments, the data analysis module is also used to analyze using a neural network model to identify the cleaning status information of the hands of medical staff in the neonatal intensive care unit, and at the same time identify the cleaning time of the hands of the medical staff as the cleaning status information, and judge whether the hands of the medical staff are in a hand hygiene completion state based on the cleaning status information. If not, generate hand cleaning prompt information and send it to the central control warning module; specifically, based on the collected surveillance video images of the medical staff washing their hands, a neural network model is used to identify the cleaning time from the start to the end of the user's hand washing, and judge whether the evaluation value is greater than the preset evaluation value, and the cleaning time is greater than the preset cleaning time. If so, it is determined that the hands of the medical staff are in a hand hygiene completion state; if not, it is determined that the hands of the medical staff are not in a hand hygiene completion state.

[0107] This embodiment also provides a method for monitoring the environment of a neonatal intensive care unit, using the above-mentioned neonatal intensive care unit environment early warning monitoring system, including:

[0108] Collect environmental information in the neonatal intensive care unit;

[0109] Preprocessing of environmental information;

[0110] Determine whether the pre-processed environmental information belongs to the preset safety range. If not, generate warning information and issue a warning based on the warning information;

[0111] The pre-processed environmental information is analyzed using a neural network model to identify the cleanliness status information of the hands of medical staff in the neonatal intensive care unit, and based on the cleanliness status information, it is determined whether the hands of the medical staff are in a hand hygiene completion state. If not, hand cleaning prompt information is generated, and displayed and pre-reminded based on the hand cleaning prompt information.

[0112] Embodiment 2

[0113] This embodiment is basically the same as the above embodiment, except that: according to the mean square error loss function, the weight evaluation value P of each individual solution is calculated. j , where is the weight evaluation value of the jth individual solution, and also includes:

[0114] Compare whether the weight evaluation value of each individual solution in the kth iteration is greater than the weight evaluation value of the corresponding parent in the k-1th iteration. If not, replace the individual solution in the kth iteration with the individual solution of its parent. If so, execute the weight evaluation value P of each individual solution. j , a roulette wheel method is used to select individual solutions in the initial population, so as to retain better individual solutions, ensure that the priority is always in the optimal direction, improve the optimization effect, and ensure that the weight of the individual solution found can enable the CNN neural network model to have a better prediction effect.

[0115] Embodiment 3

[0116] This embodiment is basically the same as the above embodiment, except that: in the CNN neural network model, the image feature dimension is expanded according to the environmental information, the fully connected layer analyzes the cleanliness status of each medical staff member's hands according to the image features of the feature dimension, and the output layer outputs the cleanliness status information of each medical staff member's hands;

[0117] Specifically, after the image feature S4 is obtained, the temperature and humidity information, air quality information and illumination information obtained at the same time as the input monitoring video image information are added to the feature vector as new row data to form a new multi-dimensional feature vector S4';

[0118] The feature vector S4' is input into the first fully connected layer to analyze the cleaning status information of each medical staff member's hands, obtain the output result F5, and activate the output result F5 using the Leaky ReLU function (non-linear mapping);

[0119] The activated output result F5 is input to the second fully connected layer to analyze the clean status information of each medical staff member's hands, obtain the output result F6, and activate the output result F6 using the Leaky ReLU function; wherein the number of nodes in the first fully connected layer and the second fully connected layer are both greater than or equal to the number of image features S4;

[0120] The activated output result F6 is input into the output layer for conversion, and the final prediction result f(out) is output, which is the cleanliness status information of the medical staff's hands.

[0121] In the CNN neural network model, when the image features output by the convolutional layer and the pooling layer are used as the input of the fully connected layer, the dimension of the feature vector is increased and combined with other environmental information, thereby improving the reference dimension of the prediction. This can comprehensively consider multiple factors, improve prediction accuracy, and further improve the hand disinfection effect of medical staff.

[0122] Embodiment 4

[0123] This embodiment is basically the same as the above embodiment, except that:

[0124] When touching different newborns, you should also clean and disinfect your hands, because all newborns in the neonatal intensive care unit are sick, and you should prevent continuous contact with different newborns to prevent cross infection.

[0125] Therefore, the data analysis module in this solution is also used to identify the action information of medical staff according to the pre-processed environmental information, and to determine whether there is an irregular action or irregular action tendency according to the action information. If so, an irregular prompt message is generated and sent to the central control warning module and the terminal of the medical staff of the corresponding action for reminder;

[0126] Specifically, the monitoring video image information also includes: full-area monitoring video images in the neonatal intensive care unit;

[0127] Annotate surveillance video image information and divide it into video clips containing different action information;

[0128] Extract features from video clips, such as optical flow, 3D convolutional features (C3D), spatiotemporal feature maps, etc.

[0129] Construct a deep learning model and train the model, using the extracted features and their corresponding action information for training, so that it can learn the action pattern from the input features; in this embodiment, an RNN model is used;

[0130] Use the trained deep learning model to classify surveillance video image information and identify the action information that is taking place;

[0131] Construct a time series model, and use the historical action sequence to construct input-output pairs, train the time series model so that it can predict the next action based on the action information that is happening, and output the predicted next action information; in this embodiment, the LSTM model is used;

[0132] When medical staff enter the neonatal intensive care unit, it is analyzed whether they have any action information for hand cleaning within the preset time period. If not, it is determined that there is an illegal action, and a non-compliant prompt message is generated and sent to the central control warning module and the terminal of the medical staff who took the corresponding action for reminder; thereby supervising and reminding medical staff to clean their hands first after entering the neonatal intensive care unit;

[0133] When the medical staff enters the neonatal intensive care unit, if the next action information of the medical staff is predicted for the first time to be contact with the newborn, it is queried whether the action information of the medical staff within the preset time period before the current time point contains action information for hand cleaning. If not, it is determined that there is a tendency of non-compliant actions, and non-compliant prompt information is generated and sent to the central control early warning module and the terminal of the medical staff who performed the corresponding action for reminder; the information includes action information for hand cleaning, including hand washing in the hand washing area and hand cleaning with disinfectant, so as to supervise and remind the medical staff to disinfect their hands after contacting the previous newborn and before contacting the next newborn to prevent cross infection.

[0134] The above is only an embodiment of the present invention. The common sense such as the known specific structure and characteristics in the scheme is not described in detail here. The ordinary technicians in the relevant field know all the common technical knowledge in the technical field of the invention before the application date or priority date, can obtain all the existing technologies in the field, and have the ability to apply the conventional experimental means before that date. The ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for ordinary technicians in the relevant field to implement this application. It should be pointed out that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the protection scope of the present invention, which will not affect the effect of the implementation of the present invention and the practicality of the patent. The protection scope required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. A neonatal intensive care unit environment early warning monitoring system, characterized in that: include: A data acquisition module, used to collect environmental information in the neonatal intensive care unit; A data processing module, used for preprocessing environmental information; The data judgment module is used to judge whether the pre-processed environmental information belongs to the preset safety range. If not, it generates warning information and sends it to the central control warning module; The data analysis module is used to analyze the pre-processed environmental information using a neural network model to identify the cleanliness status information of the hands of medical staff in the neonatal intensive care unit, and determine whether the hands of the medical staff are in a hand hygiene completion state based on the cleanliness status information. If not, a hand cleaning prompt message is generated and sent to the central control warning module; The central control warning module is used to receive warning information and issue warnings based on the warning information; It is also used to receive hand cleaning reminder information, and display and pre-remind according to the hand cleaning reminder information.

2. The neonatal intensive care unit environment early warning monitoring system according to claim 1, characterized in that: One or more of temperature and humidity information, air quality information, sound information, lighting information, and surveillance video image information.

3. The neonatal intensive care unit environment early warning monitoring system according to claim 2, characterized in that: The pre-processed environmental information is analyzed using a neural network model to identify the cleanliness status information of the hands of each medical staff in the neonatal intensive care unit, including: The CNN neural network model is used to take the monitoring video image information as input and output the cleanliness status information of each medical staff member's hands; The CNN neural network model includes: input layer, output layer, several convolutional layers, pooling layers, and fully connected layers; The input layer inputs the monitoring video image information, and then passes through the convolution layer to extract image features, the pooling layer to compress image features, and the fully connected layer to analyze the cleanliness status information of each medical staff member's hands based on the image features.

4. The neonatal intensive care unit environment early warning monitoring system according to claim 3, characterized in that: The specific structure of the CNN neural network model is: an input layer and an output layer, two convolutional layers, a pooling layer and a fully connected layer; The preprocessed surveillance video image information is input through the input layer and transmitted to the first convolutional layer for image feature C1 extraction; The image feature C1 is input into the first pooling layer for image feature compression to obtain the image feature S2. The strategy adopted by the pooling layer is maximum pooling. Input the image feature S2 into the second convolutional layer to extract the image feature C3; Input the image feature C3 to the second pooling layer for image feature compression to obtain image feature S4; The image feature S4 is input into the first fully connected layer to analyze the cleanliness status information of each medical staff member's hands, obtain the output result F5, and activate the output result F5 using the Leaky ReLU function; The activated output result F5 is input to the second fully connected layer to analyze the clean status information of each medical staff member's hands, obtain the output result F6, and activate the output result F6 using the Leaky ReLU function; wherein the number of nodes in the first fully connected layer and the second fully connected layer are both greater than or equal to the number of image features S4; The activated output result F6 is input into the output layer for conversion, and the final prediction result f(out) is output as the cleanliness status information of the medical staff's hands.

5. The neonatal intensive care unit environment early warning monitoring system according to claim 4, characterized in that: The historical surveillance video image information and the cleaning status information of the medical staff's hands are used to construct the training set and the validation set to train and validate the CNN neural network model, including: The constructed CNN neural network model is trained using the training set; The trained CNN neural network model is verified using the validation set. If it meets the preset requirements, the training is completed and the trained CNN neural network model is output; If it does not meet the preset requirements, continue to train the CNN neural network model; During the training process, the weights of the nodes in the fully connected layer are updated using an optimization algorithm, including: Randomly generate several weight schemes as individual schemes to form an initial population; Construct a weight evaluation function based on the training evaluation value of the CNN neural network model; According to the weight evaluation function, the weight scheme in the initial population is selected, and iterative optimization is performed to obtain the optimal weight scheme.

6. The neonatal intensive care unit environment early warning monitoring system according to claim 5, characterized in that: Construct a weight evaluation function to evaluate the difference between the final prediction result f(out) and the actual result y, which is: P=aE -1 ; Where P is the weight evaluation value, E is the mean square error loss function, and a is the adjustment constant; Among them, f(out i ) is the final prediction result output by the CNN neural network model of the input data in the i-th group of training data in the training set, y i is the actual result in the i-th group of training data in the training set.

7. The neonatal intensive care unit environment early warning monitoring system according to claim 6, characterized in that: The method of selecting a weight scheme in the initial population according to the weight evaluation function and performing iterative optimization to obtain the optimal weight scheme includes: Initialize the number of iterations k = 1; According to the individual schemes in the population, the weights in the CNN neural network model are set, and the CNN neural network models with different weights are trained using the same training set to obtain the corresponding final prediction results f(out i ); According to the mean square error loss function, calculate the weight evaluation value P of each individual solution j , where is the weight evaluation value of the jth individual solution; According to the weight evaluation value P of each individual solution j , using the roulette wheel method to select individual solutions from the initial population; the selection probability is proportional to the weight evaluation value; The selected individual solutions are mutated and crossed, and the individual solutions that cannot be realized are eliminated to form a new population; among them, the unrealizable ones; Determine whether the current number of iterations is equal to the preset number. If so, obtain the individual solution with the largest weight evaluation value as the optimal weight solution. If not, update the number of iterations k=k+1, and then execute according to the individual solutions in the population, set the weights in the CNN neural network model, and use the same training set to train the CNN neural network models with different weights to obtain the corresponding final prediction results f(out i ).

8. The neonatal intensive care unit environment early warning monitoring system according to claim 7, characterized in that: According to the mean square error loss function, the weight evaluation value P of each individual solution is calculated j , where is the weight evaluation value of the jth individual solution, and also includes: Compare whether the weight evaluation value of each individual solution in the kth iteration is greater than the weight evaluation value of the corresponding parent in the k-1th iteration. If not, replace the individual solution in the kth iteration with the individual solution of its parent. If so, execute the weight evaluation value P of each individual solution. j , using the roulette method to select individual solutions from the initial population.

9. The neonatal intensive care unit environment early warning monitoring system according to claim 3, characterized in that: In the CNN neural network model, the image feature dimension is expanded according to the environmental information, the fully connected layer analyzes the cleanliness status information of each medical staff member's hands according to the image features of the feature dimension, and the output layer outputs the cleanliness status information of each medical staff member's hands.

10. A method for early warning monitoring of a neonatal intensive care unit environment, characterized in that: A neonatal intensive care unit environment early warning monitoring system as claimed in any one of claims 1 to 9, comprising: Collect environmental information in the neonatal intensive care unit; Preprocessing environmental information; Determine whether the pre-processed environmental information belongs to the preset safety range. If not, generate warning information and issue a warning based on the warning information; The pre-processed environmental information is analyzed using a neural network model to identify the cleanliness status information of the hands of each medical staff in the neonatal intensive care unit, and based on the status information, it is determined whether the newborn is in a healthy state. If not, status prompt information is generated and displayed and pre-reminds are given based on the status prompt information.

Images