Child sleep monitoring and improving system based on big data

Abstract

The invention discloses a children sleep monitoring and improving system based on big data, which comprises a monitoring module, an analysis module, an intervention module and a feedback module based on a system architecture, the monitoring module adopts a distributed architecture and comprises a data acquisition module and a data transmission module, the monitoring module collects data of different sources and different types, and the data transmission module transmits the data to the analysis module. The distributed architecture ensures the stability and the expandability of the system, so that the monitoring module can flexibly adapt to application scenes with different scales and complexity. Compared with the prior art, the system has the advantages that comprehensive monitoring and evaluation are realized; the scheme is improved individually; flexibility and expandability are realized; and user friendliness is realized.

Description

Technical Field

[0001] The present invention relates to the field of medical health monitoring technology, and specifically to a children's sleep monitoring and improvement system based on big data. Background Art

[0002] With the accelerated pace of modern life, children's sleep problems are receiving increasing attention. Good sleep is essential for children's growth and development, cognitive ability and emotional stability. However, most of the existing methods of monitoring children's sleep rely on traditional questionnaires, parent observations and other methods, which are highly subjective and inaccurate. In addition, although there are some children's sleep monitoring systems based on wearable devices on the market, they can often only provide simple sleep duration and light sleep / deep sleep status distinction, lacking a comprehensive assessment of sleep quality and improvement suggestions.

[0003] In the field of patents, there have been some patent applications for related technologies, such as patent number CN202010123456.X, which proposes a sensor-based children's sleep monitoring system that can monitor heart rate, breathing and other vital signs. However, the system is relatively simple in data processing and analysis, and fails to fully utilize the advantages of big data technology for deep mining and personalized intervention. In addition, patent number CN201920678901.X proposes an intelligent sleep improvement device. Although it includes certain intervention measures, it has deficiencies in data interaction, modular design and user feedback, and it is difficult to meet different application scenarios and needs. Summary of the invention

[0004] In view of the problems and shortcomings in the prior art, the present invention proposes a children's sleep monitoring and improvement system based on big data, which aims to achieve comprehensive monitoring, accurate evaluation and personalized improvement of children's sleep quality through technical means such as distributed architecture, modular design and event-driven architecture.

[0005] Specifically, the technical solution provided by the present invention is: a children's sleep monitoring and improvement system based on big data, including a monitoring module, an analysis module, an intervention module and a feedback module based on the system architecture. The monitoring module adopts a distributed architecture, including a data acquisition module and a data transmission module. The monitoring module collects data from different sources and of different types, and transmits it to the central processing unit through the network for aggregation and analysis. Its distributed architecture ensures the stability and scalability of the system, so that the monitoring module can flexibly adapt to application scenarios of different scales and complexities; the analysis module usually adopts a modular design, encapsulating different analysis functions into two independent sub-modules, specifically a data storage and processing module and a sleep quality assessment module. The sub-modules are configured as needed. The modules can be combined and configured to meet different analysis needs. The analysis module also has powerful data processing and computing capabilities, which can efficiently process large amounts of data and draw accurate conclusions. The intervention module adopts an event-driven architecture, including a personalized intervention plan generation module, an execution and control module. The intervention module responds to instructions from the analysis module or other trigger sources in real time, and has high flexibility and scalability, and can be customized and configured according to different application scenarios and needs. The feedback module adopts a user-friendly interface design, including a real-time monitoring feedback module, an effect evaluation and adjustment module, which is convenient for users to view and submit feedback information. The feedback module has powerful data processing and storage capabilities, which can efficiently process a large amount of user feedback and save it as a queryable record.

[0006] Furthermore, the interaction between the monitoring module and other modules is mainly achieved through the data interface. The monitoring module transmits the collected data to the analysis module in JSON and XML formats, and also receives instructions from the intervention module to adjust the monitoring strategy or parameters.

[0007] Furthermore, the interaction between the analysis module and the monitoring module and intervention module is mainly realized through the data interface and the command interface. The analysis module obtains data from the monitoring module and presents the analysis results to the user in the form of charts and reports. At the same time, according to the analysis results, instructions are sent to the intervention module to trigger corresponding intervention measures.

[0008] Furthermore, the interaction between the intervention module and other modules is mainly realized through the command interface, which receives instructions from the analysis module and executes corresponding intervention measures. At the same time, the intervention results are fed back to the analysis module or the user for reference.

[0009] Furthermore, the interaction between the feedback module and the user and other modules is mainly achieved through the user interface and data interface. The user can submit feedback information and view the processing results through the user interface; the feedback module can transmit user feedback in a specific format to other modules for processing and analysis.

[0010] Furthermore, the data acquisition module is used to collect various vital signs data of children during sleep, including heart rate, respiratory rate, movement amplitude and sleep cycle data. The collection methods include wireless bio-radar monitoring and piezoelectric sensor monitoring to ensure that children are not disturbed during sleep; the data transmission module transmits the collected data to the central processor in real time for analysis and processing. The transmission methods include WIFI and Bluetooth transmission technology to ensure the real-time and accuracy of data transmission.

[0011] Furthermore, the data storage and processing module is used to store various vital signs data of children during sleep, and perform denoising and filtering pre-processing on the data, and then use big data algorithms to further analyze the processed data to extract key information related to children's sleep quality; the sleep quality assessment module assesses children's sleep quality based on the stored data and key information. The assessment criteria include sleep duration, sleep depth, and sleep cycle distribution. At the same time, it is compared with the data of children's normal sleep to determine whether the child has a sleep disorder.

[0012] Furthermore, the personalized intervention plan generation module generates a personalized sleep improvement plan based on the sleep quality assessment results. The plan includes adjusting work and rest schedules, improving the sleep environment, and providing psychological counseling. The execution and control module converts the generated personalized intervention plan into executable operation instructions, executes the operation instructions through smart devices or manual methods, and makes real-time adjustments to the children's sleep environment to improve sleep quality.

[0013] Furthermore, the real-time monitoring feedback module is used to monitor the changes in children's vital signs during sleep in real time, and to promptly feedback the change information to the user. The feedback methods include voice broadcast and mobile phone APP push, to ensure that users can understand the children's sleep conditions in a timely manner; the effect evaluation and adjustment module will re-evaluate the children's sleep quality after the intervention measures have been implemented for a period of time to determine the effectiveness of the intervention. According to the evaluation results, the intervention plan will be adjusted and optimized to ensure continuous improvement of children's sleep quality.

[0014] Compared with the prior art, the advantages of the present invention are: (1) Comprehensive monitoring and evaluation: By collecting a variety of vital sign data and using big data analysis technology for in-depth mining, it is possible to comprehensively evaluate the sleep quality of children and accurately identify sleep disorders; (2) Personalized improvement plan: Generate a personalized sleep improvement plan based on the evaluation results, including adjusting work and rest time, improving the sleeping environment, and providing psychological counseling, etc., which is highly targeted and effective; (3) Flexibility and scalability: The system adopts a distributed architecture and modular design, which can flexibly adapt to application scenarios of different scales and complexities, and is easy to expand and upgrade; (4) User-friendliness: The feedback module adopts a user-friendly interface design, which is convenient for users to view and submit feedback information, thereby improving user experience and satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a schematic diagram of the architecture of a children's sleep monitoring and improvement system based on big data.

[0016] Figure 2 It is a schematic diagram of the architecture of the monitoring module.

[0017] Figure 3 Schematic diagram of the analysis module architecture.

[0018] Figure 4 It is a schematic diagram of the architecture of the intervention module.

[0019] Figure 5 Schematic diagram of the feedback module architecture. DETAILED DESCRIPTION

[0020] The present invention is further described in detail below in conjunction with the accompanying drawings.

[0021] Embodiment 1

[0022] like Figure 1 As shown, the system of the present invention includes a monitoring module, an analysis module, an intervention module and a feedback module. The monitoring module adopts a distributed architecture, which can collect data from different sources and of different types, and transmit them to the central processing unit through the network for aggregation and analysis. The analysis module adopts a modular design, including a data storage and processing module and a sleep quality assessment module, which can efficiently process large amounts of data and draw accurate conclusions. The intervention module adopts an event-driven architecture, which can respond to instructions in real time according to the analysis results and execute personalized intervention measures. The feedback module adopts a user-friendly interface design, which is convenient for users to view and submit feedback information.

[0023] The children's sleep quality assessment system is mainly based on sensor technology, data analysis and processing, and intelligent algorithms to monitor children's sleep status in real time, including sleep duration, sleep depth, breathing rate, heart rate and other indicators. By analyzing these data, the system can assess children's sleep quality and provide targeted improvement suggestions. The working principle of the system is as follows:

[0024] (1) Data collection: The system collects physiological data of children during sleep, such as movement, breathing, heart rate, etc., through built-in or external sensors (such as smart watches, bracelets, sleep stickers, etc.). At the same time, the system can also collect sleep environment factors, such as noise, light, etc., to more comprehensively evaluate sleep quality.

[0025] (2) Data transmission: The collected data is transmitted to smart devices (such as mobile phones, tablets, etc.) via wireless signals to achieve real-time monitoring. The data can also be stored in the cloud for subsequent analysis and processing.

[0026] (3) Data analysis: Smart devices or cloud servers analyze and process the collected data to assess the children’s sleep quality. The analysis process may involve machine learning algorithms such as feature extraction, classification, and clustering to identify different sleep stages and types of disorders.

[0027] (4) Result output: Based on the analysis results, the system provides children with personalized sleep improvement suggestions, such as adjusting their sleep schedules, improving their sleep environment, etc. The system can also generate a sleep health report to let parents understand their children’s sleep status and adjust their lifestyle based on the report.

[0028] The workflow of this system includes: (1) Preparation stage: Put the sensor device on the child to ensure that the device can collect data normally. Set the parameters of the smart device, such as monitoring time, data transmission method, etc. (2) Monitoring stage: After the child falls asleep, the sensor starts to collect data and transmits the data to the smart device or cloud server. The system monitors the data in real time to ensure the integrity and accuracy of the data. (3) Analysis stage: The smart device or cloud server preprocesses the collected data to eliminate noise and outliers. The system uses machine learning algorithms to classify and cluster features to identify different sleep stages and types of disorders. Based on the analysis results, the system calculates a comprehensive sleep quality score. (4) Feedback stage: The system displays the analysis results and sleep quality score to parents or children in an intuitive way. Based on the analysis results, the system provides personalized sleep improvement suggestions and health reports. Parents can adjust their children's schedules, sleeping environment, etc. according to the suggestions to improve sleep quality.

[0029] Embodiment 2

[0030] Based on the first embodiment, Figure 1 and Figure 2 As shown, during data preprocessing, the denoising filter of the data storage and processing module adopts a mean filter, and the mean filter formula is:

[0031]

[0032] Where x[n] is the original signal, y[n] is the denoised signal, and M is the filter window size.

[0033] The filtering is implemented using a moving average filter, and its formula is:

[0034]

[0035] Where N is the length of the filter.

[0036] The following is the execution code for denoising and filtering:

[0037]

[0038]

[0039] Embodiment 3

[0040] Based on the first embodiment, Figure 1 and Figure 2 As shown, in the big data algorithm analysis stage, a machine learning algorithm is used to extract key information related to children's sleep quality. For example, a classification algorithm can be used to identify children's sleep stages (such as light sleep, deep sleep, REM, etc.), or a regression algorithm can be used to predict children's sleep quality scores. This solution uses a random forest classifier to identify children's sleep stages. The algorithm steps include: (1) collecting a sample set containing multiple vital sign data (such as heart rate, respiratory rate, body movement, etc.); (2) preprocessing the sample set, including denoising, filtering, etc.; (3) extracting features, such as heart rate variability, respiratory rate stability, etc.; (4) using a random forest classifier to train the sample set to identify children's sleep stages; (5) predicting new data to evaluate its sleep stage. The execution code is given below:

[0041] from sklearn.ensemble import RandomForestClassifier

[0042] from sklearn.model_selection import train_test_split

[0043] from sklearn.metrics import accuracy_score

[0044] #Assume we have a DataFrame containing features and labels

[0045] #Features include processed heart rate, breathing rate, etc., and labels are sleep stages (light sleep, deep sleep, REM, etc.)

[0046] #Random data is used here to simulate features and labels

[0047] num_samples=1000

[0048] num_features=5

[0049] sleep_stages=['Light','Deep','REM']

[0050] #Randomly generate features and labels

[0051] X=np.random.rand(num_samples,num_features)

[0052] y=np.random.choice(sleep_stages,num_samples)

[0053] # Divide the data into training set and test set

[0054] X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2,random_state=42)

[0055] # Use random forest classifier for training

[0056] clf=RandomForestClassifier(n_estimators=100,random_state=42)

[0057] clf.fit(X_train,y_train)

[0058] # Make predictions on the test set

[0059] y_pred = clf.predict(X_test)

[0060] #Calculate accuracy

[0061] accuracy=accuracy_score(y_test,y_pred)

[0062] print(f'Accuracy:{accuracy:.2f}')

[0063] Embodiment 4

[0064] Based on the first embodiment, Figure 1 and Figure 3 As shown in the figure, the main task of the sleep quality assessment module is to evaluate the sleep quality of children based on the stored data and key information. In terms of the sleep quality assessment algorithm, key information related to children's sleep quality, such as heart rate variability (HRV), respiratory rate variability (BRV), body movement index (MI), etc., has been obtained through data preprocessing and feature extraction steps. We can use these features to construct a comprehensive sleep quality score (Sleep Quality Score, SQS). Comprehensive sleep quality score (SQS) formula:

[0065] SQS=w 1HRV_score+w 2 BRV_scpre+w 3 MI_score+...+w n feature_n_score

[0066] Among them, w 1 , w 2 ,…,w n are the weights of each feature, which can be learned through machine learning algorithms (such as random forests, gradient boosting machines, etc.) or set based on expert experience. HRV_score, BRV_score, MI_score, ..., feature_n_score are the scores corresponding to each feature, which can be normalized feature values ​​or grade scores obtained according to specific rules (such as threshold division). The execution code is given below:

[0067]

[0068]

[0069] The above shows and describes the basic principles and main features of the present invention and the advantages of the invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A children's sleep monitoring and improvement system based on big data, including a monitoring module, an analysis module, an intervention module and a feedback module based on a system architecture, characterized in that: The monitoring module adopts a distributed architecture, including a data acquisition module and a data transmission module. The monitoring module collects data from different sources and different types, and transmits the data to the central processing unit through the network for aggregation and analysis. The distributed architecture ensures the stability and scalability of the system, so that the monitoring module can flexibly adapt to application scenarios of different scales and complexities. The analysis module usually adopts a modular design, encapsulating different analysis functions into two independent sub-modules, specifically a data storage and processing module and a sleep quality assessment module. The sub-modules are combined and configured as needed to adapt to different analysis needs. The analysis module also has strong data processing and computing capabilities, and can efficiently process a large amount of data and draw accurate conclusions. The intervention module adopts an event-driven architecture, including a personalized intervention program generation module and an execution and control module. The intervention module responds to instructions from the analysis module or other trigger sources in real time, has high flexibility and scalability, and is customized and configured according to different application scenarios and needs. The feedback module adopts a user-friendly interface design, including a real-time monitoring feedback module and an effect evaluation and adjustment module, which is convenient for users to view and submit feedback information. The feedback module has strong data processing and storage capabilities, and can efficiently process a large amount of user feedback and save it as a queryable record.

2. The big data-based children's sleep monitoring and improvement system according to claim 1, characterized in that: The interaction between the monitoring module and other modules is mainly achieved through the data interface. The monitoring module transmits the collected data to the analysis module in JSON and XML formats, and also receives instructions from the intervention module to adjust the monitoring strategy or parameters.

3. The big data-based children's sleep monitoring and improvement system according to claim 1, characterized in that: The interaction between the analysis module and the monitoring module and intervention module is mainly realized through the data interface and the command interface. The analysis module obtains data from the monitoring module and presents the analysis results to the user in the form of charts and reports. At the same time, according to the analysis results, instructions are sent to the intervention module to trigger corresponding intervention measures.

4. The big data-based children's sleep monitoring and improvement system according to claim 1, characterized in that: The interaction between the intervention module and other modules is mainly realized through the command interface, receiving the command from the analysis module and executing the corresponding intervention measures, and at the same time, feeding back the intervention results to the analysis module or the user for reference.

5. The big data-based children's sleep monitoring and improvement system according to claim 1, characterized in that: The interaction between the feedback module and the user and other modules is mainly achieved through the user interface and data interface. The user can submit feedback information and view the processing results through the user interface; the feedback module can transmit user feedback in a specific format to other modules for processing and analysis.

6. The big data-based children's sleep monitoring and improvement system according to claim 1, characterized in that: The data acquisition module is used to collect various vital signs data of children during sleep, including heart rate, respiratory rate, movement amplitude and sleep cycle data. The collection methods include wireless bio-radar monitoring and piezoelectric sensor monitoring to ensure that children are not disturbed during sleep; the data transmission module transmits the collected data to the central processing unit in real time for analysis and processing. The transmission methods include WIFI and Bluetooth transmission technology to ensure the real-time and accuracy of data transmission.

7. The big data-based children's sleep monitoring and improvement system according to claim 1, characterized in that: The data storage and processing module is used to store various vital sign data of children during sleep, and to perform denoising and filtering pre-processing on the data, and then use the big data algorithm to further analyze the processed data to extract key information related to the children's sleep quality; the sleep quality assessment module assesses the children's sleep quality based on the stored data and key information, and the assessment criteria include sleep duration, sleep depth, and sleep cycle distribution, and at the same time compares with the data of the children's normal sleep to determine whether the children have sleep disorders.

8. The big data-based children's sleep monitoring and improvement system according to claim 1, characterized in that: The personalized intervention program generation module generates a personalized sleep improvement program based on the sleep quality assessment results, and the program content includes adjusting the work and rest time, improving the sleep environment, and providing psychological counseling; the execution and control module converts the generated personalized intervention program into executable operation instructions, executes the operation instructions through smart devices or manually, and adjusts the child's sleep environment in real time to improve sleep quality.

9. The big data-based children's sleep monitoring and improvement system according to claim 1, characterized in that: The real-time monitoring feedback module is used to monitor the changes in children's vital sign data during sleep in real time, and to promptly feedback the change information to the user. The feedback methods include voice broadcast and mobile phone APP push, to ensure that users can understand the children's sleep conditions in a timely manner; the effect evaluation and adjustment module re-evaluates the children's sleep quality after the intervention measures have been implemented for a period of time to determine the intervention effect. According to the evaluation results, the intervention plan is adjusted and optimized to ensure continuous improvement of children's sleep quality.

Images