Sleep environment parameter recommendation system based on sleep big data

Abstract

The invention discloses a sleep environment parameter recommendation system based on sleep big data, which relates to the technical field of sleep big data and comprises a sleep monitoring system, a monitoring data analysis system, an environment equipment automatic regulation and control system and a sleep monitoring data feedback system. And the sleep monitoring system is used for monitoring the sleep process of the user and realizing data collection in the monitoring process, and the data collection is divided into body sleep data collection and environment data collection. The sleep environment parameter recommendation system based on the sleep big data can effectively collect the sleep physical state and the sleep environment of the user in a room, meanwhile, the system is further in interactive connection with all intelligent devices in the room, the sleep quality of the user is judged according to the collected sensing data, and the user experience is improved. The data is compared with an original sleep data model, and the sleep environment is automatically optimized, so that model parameters most suitable for sleep are obtained.

Description

Technical Field

[0001] The present invention relates to the technical field of sleep big data, and in particular to a sleep environment parameter recommendation system based on sleep big data. Background Art

[0002] Good sleep quality is the basis for maintaining daytime physical strength and energy, and is also the guarantee for efficient work and study; long-term lack of sleep can lead to physical discomfort, such as inducing mental problems such as trance and hallucinations, and even death.

[0003] Sleep is closely related to many physiological functions of the human body. Lack of sleep will endanger the health of the cardiovascular system, immune system, metabolic system and reproductive system, and will also affect mental psychology, cognition, learning and memory. For example, in terms of sleep and learning and memory, the brain processes and processes information during sleep, and the precise coupling between slow wave oscillations and spindle waves during non-rapid eye movement sleep is very important for memory consolidation. In terms of sleep and neurocognition, the sleep process is an important stage for the brain to clear metabolic waste. Lack of sleep will damage the blood-brain barrier and cause dysfunction of the brain waste clearance system. In terms of sleep and immunity, lack of sleep can lead to decreased immunity and increase the risk of infectious diseases and autoimmune diseases. In terms of sleep, metabolism and cardiovascular, long-term lack of sleep and circadian rhythm disorders will increase the risk of metabolic diseases such as obesity, diabetes, and hyperlipidemia, and cardiovascular diseases such as hypertension and atrial fibrillation. In terms of sleep and mental psychology, sleep problems are very common among patients with mental disorders. Sleep disorders may limit the success of psychotherapy, and poor sleep quality is related to poor psychotherapy results.

[0004] The sleeping environment has a significant impact on sleep quality; an ideal sleeping environment should be quiet, comfortable, and of appropriate temperature, which helps improve sleep quality and enables people to enter deep sleep faster; on the contrary, a noisy, overly bright, or too high or too low temperature environment may cause difficulty falling asleep and affect sleep quality.

[0005] Currently, comprehensive monitoring of sleep quality requires going to a medical institution with more complete equipment, which has specific requirements for the monitoring environment and is therefore not applicable. Moreover, the monitoring cannot be used as a benchmark for normal sleep data, and it is impossible to give corresponding recommended adjustments based on the monitoring results. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention provides a sleep environment parameter recommendation system based on sleep big data, which solves the problems raised in the above background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a sleep environment parameter recommendation system based on sleep big data, including a sleep monitoring system, a monitoring data analysis system, an environmental equipment automatic control system, and a sleep monitoring data feedback system;

[0008] The sleep monitoring system is used to monitor the user's sleep process and collect data during the monitoring process, where the data collection is divided into body sleep data collection and environmental data collection;

[0009] Body sleep data collection includes sleeping body temperature, body surface temperature, breathing rate, heart rate monitoring, and sleeping posture monitoring;

[0010] Environmental data collection includes environmental oxygen content, ambient temperature, ambient humidity, noise environment, air flow rate, lighting environment, insect identification, and air quality;

[0011] A monitoring data analysis system is used for analyzing, classifying, comparing, correcting differences, and storing body sleep data and environmental data in the sleep monitoring system, wherein the monitoring data analysis system is composed of a data preprocessing module, a data analysis module, and a data cache module;

[0012] The data preprocessing module is specifically divided into a data cleaning unit and a data conversion unit. It is used for processing operations before sleep monitoring data analysis. The data content needs to be preprocessed and cleaned to remove noise, missing values ​​and outliers, and the data is classified after processing.

[0013] The data analysis module uses the monitoring data analysis platform to perform data analysis and mining operations. By using statistical algorithms, it arranges the potential patterns and trends of sleep data, thereby providing a basis for users to formulate and recommend parameters. At the same time, the analysis module also supports customized data analysis tasks, adopts end-to-end deep learning methods, uses multivariate time series to classify temporal sleep stages, and performs analysis based on the Python toolkit MNE. When dealing with the imbalance problem of classification tasks, it adopts the loss function method of the reweighted model to improve the performance of the prediction model by providing features from adjacent time periods to the final classifier.

[0014] The data analysis module consists of a data comparison unit and a data difference correction unit;

[0015] A data comparison unit is used to compare the sleep data collected by the sensor with the basic data in the original database to determine the sleep quality of the user;

[0016] The data difference correction unit calculates the amplitude of the difference adjustment correction according to the size of the data difference after comparison, generates a control signal according to the difference amplitude, and sends a control instruction to the smart home monitoring module;

[0017] A data cache module is used to temporarily store the data collected in the sleep monitoring system for quick access during later comparison operations, thereby reducing frequent access to the main memory and external data sources;

[0018] The automatic control system of environmental equipment uses an intelligent system to adjust and control the equipment in the sleeping environment to maintain the stability of various parameters in the sleeping environment. The automatic control system of environmental equipment is divided into an environmental equipment control module and a monitoring equipment control module;

[0019] The sleep monitoring data feedback system is used to visualize sleep big data. It helps users understand the current status of the sleep environment through visualized data, and promptly discover problems in the sleep environment, so as to make corresponding adjustments to the sleep environment settings, provide support for sleep environment research and decision-making, and repeatedly optimize the sleep environment.

[0020] Optionally, the sleep monitoring system is composed of a sensor control module, a smart furniture monitoring module, an infrared camera module, and a data collection module;

[0021] The sensor control module includes a temperature sensor, a humidity sensor, an air detector, an air purifier, and a light sensor, which are used to monitor and collect various environmental data during the user's sleep;

[0022] The smart home monitoring module includes a volume controller, a wireless monitoring bracelet, and a smart mattress, which are used to monitor and collect the user's physiological signals, including body temperature, respiratory rate, blood oxygen saturation, sleeping position, and real-time heart rate. The wireless monitoring bracelet is used to monitor personal sleep status, including sleep time, sleep duration, and awakening frequency, and to establish a personal sleep database in conjunction with the physiological signal monitoring data collected by the smart mattress;

[0023] The infrared camera module is composed of an infrared camera device, a video acquisition unit and a wireless transmission unit. The infrared camera device is used to record the individual's sleep process; the video acquisition unit and the wireless transmission unit are used to record and transmit the video data during the sleep process;

[0024] The data collection module is used to collect and save real-time data during the use of the sensor control module, smart furniture supervision module, and infrared camera module, providing source data for subsequent data processing, analysis, and decision-making; and transmitting it to the central system / cloud platform through communication.

[0025] Optionally, the data collection module includes a data acquisition unit, a signal processing unit and a wireless communication transmission unit;

[0026] A data acquisition unit for automatically collecting information from sensors and other modules;

[0027] The signal processing unit is responsible for processing relevant data and working in coordination with other parts;

[0028] The wireless communication transmission unit realizes data transmission and ensures information interaction between various parts of the system.

[0029] Optionally, the data preprocessing module is specifically divided into a data cleaning unit and a data conversion unit.

[0030] Optionally, the data cleaning unit is used to identify and correct errors, inconsistencies and incompleteness in the sensor data set, and remove duplicates and outliers in the data set to ensure the quality and availability of the data;

[0031] The data conversion unit is used to convert the data of each sensor during the sleep monitoring process into a unified standard data set to maintain data consistency for subsequent data analysis operations.

[0032] Optionally, the monitoring data analysis system is further provided with an original database, in which a storage device, an input device, an automatic overwriting unit, and a data import and export unit are provided;

[0033] A storage device is used to store the historical physiological characteristic data of the user in the sleep state, and can train the deep learning model based on the specified deep learning model by using the historical physiological characteristic data as a training set to obtain a trained sleep staging model, and is also used to save the secondary input parameters in the later use process;

[0034] The input device is used to input new sleep control parameters during use, and is also used to perform selective adjustment operations on the original parameter model.

[0035] Optionally, the environmental equipment control module is divided into an intelligent air-conditioning control unit, an air purification control unit, a ventilation equipment control unit, a speaker control unit, and an electric curtain control unit.

[0036] Optionally, the intelligent air-conditioning control unit is used to turn on / off the air-conditioning equipment in the room, monitor the indoor and outdoor temperature changes in real time through the built-in sensor and intelligent control system, and automatically adjust the indoor temperature to achieve a more comfortable sleeping environment. At the same time, according to the collected environmental data and the comparison between the user's body surface temperature and the sleep mode parameters in the database, the switch, temperature setting and wind speed setting of the air conditioner are correspondingly and independently controlled. The intelligent air-conditioning control unit is linked with other unit items in the environmental equipment control module to automatically adjust the indoor temperature and humidity according to the preset sleep mode;

[0037] Air purification control unit, used for switching control of air purifier, equipped with air purification function, effectively filters indoor dust, bacteria, and viruses, and improves the quality of sleeping environment;

[0038] The ventilation equipment control unit controls the ventilation fan, air conditioning ventilation mode and electric windows according to the monitoring data of the indoor air oxygen content, so as to adjust the indoor air oxygen content, air humidity and ambient temperature;

[0039] The speaker control unit automatically adjusts the playback volume according to the ambient noise level;

[0040] The electric curtain control unit controls the curtains based on the real-time monitoring results of indoor light and the comparison results of ventilation conditions with preset parameters to generate different sleeping light environments and obtain feedback parameters of the user's sleeping environment.

[0041] Optionally, the sleep monitoring data feedback system includes a data visualization unit, a sleep environment optimization unit, and a cognitive model establishment unit;

[0042] A data visualization unit, used to send the sleep data to the user in the form of charts and graphs, and store it in the database in the form of data packets;

[0043] The sleep quality assessment unit is used to assess the quality of the sleep environment by preprocessing the sleep environment big data and using regression analysis methods to assess the quality of the sleep environment;

[0044] The sleep environment optimization unit is used to optimize the sleep environment. It pre-processes the sleep environment big data, uses cluster analysis to identify hot spots in the sleep environment, and optimizes the bedroom environment factors based on the user's sleep data and sleep environment data. It also analyzes the user's sleep status through the user's sleep data and sleep environment data, identifies the risk of sleep disorders, and provides personalized sleep intervention measures.

[0045] The cognitive model building unit combines the individual's physiological parameters, sleep environment parameters, and psychological state data to conduct comprehensive analysis and evaluation, thereby obtaining accurate sleep quality assessment results, establishing a sleep quality assessment model, evaluating the individual's sleep quality, and providing personalized sleep improvement suggestions. Combined with the sleep environment big data, it obtains the most suitable sleep environment optimization plan for the individual and applies it to smart homes.

[0046] The present invention provides a sleep environment parameter recommendation system based on sleep big data, which has the following features:

[0047] Beneficial effects:

[0048] The sleep environment parameter recommendation system based on sleep big data can effectively and perfectly collect the user's sleeping body state and sleeping environment in the room. At the same time, the system is also interactively connected with various smart devices in the room, and judges the user's sleep quality based on the collected sensor data. By comparing the data with the original sleep data model, the sleep environment is automatically optimized to obtain the most suitable model parameters for sleep.

[0049] The system adopts a multi-faceted and diversified approach to collect sleep data. It not only focuses on spatial environmental factors, but also on the user's sleeping posture, body temperature, eye frequency, sleep intervals, etc. during sleep, effectively combining personal data with environmental data to obtain more accurate sleep parameters. The control of smart environmental equipment is also linked, so that physical control can be achieved in the best way, which not only ensures the improvement of the sleeping environment, but also achieves energy-saving effects. DETAILED DESCRIPTION

[0050] The technical solutions in the embodiments of the present invention will be described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0051] The present invention provides a technical solution: a sleep environment parameter recommendation system based on sleep big data, including a sleep monitoring system, a monitoring data analysis system, an environmental equipment automatic control system, and a sleep monitoring data feedback system;

[0052] The sleep monitoring system is used to monitor the user's sleep process and collect data during the monitoring process, where the data collection is divided into body sleep data collection and environmental data collection;

[0053] Body sleep data collection includes sleeping body temperature, body surface temperature, breathing rate, heart rate monitoring, and sleeping posture monitoring;

[0054] Environmental data collection includes environmental oxygen content, ambient temperature, ambient humidity, noise environment, air flow rate, lighting environment, insect identification, and air quality;

[0055] The sleep monitoring system consists of a sensor control module, an intelligent furniture monitoring module, an infrared camera module, and a data collection module;

[0056] The sensor control module includes a temperature sensor, a humidity sensor, an air detector, an air purifier, and a light sensor, which are used to monitor and collect various environmental data during the user's sleep;

[0057] The smart home monitoring module includes a volume controller, a wireless monitoring bracelet, and a smart mattress, which are used to monitor and collect the user's physiological signals, including body temperature, respiratory rate, blood oxygen saturation, sleeping position, and real-time heart rate. The wireless monitoring bracelet is used to monitor personal sleep status, including sleep time, sleep duration, and awakening frequency, and to establish a personal sleep database in conjunction with the physiological signal monitoring data collected by the smart mattress;

[0058] The infrared camera module is composed of an infrared camera device, a video acquisition unit and a wireless transmission unit. The infrared camera device is used to record the individual's sleep process; the video acquisition unit and the wireless transmission unit are used to record and transmit the video data during the sleep process;

[0059] The data collection module is used to collect and save real-time data during the use of the sensor control module, smart furniture monitoring module, and infrared camera module, providing source data for subsequent data processing, analysis, and decision-making; and transmitting it to the central system / cloud platform through communication;

[0060] The data collection module includes a data acquisition unit, a signal processing unit and a wireless communication transmission unit;

[0061] A data acquisition unit for automatically collecting information from sensors and other modules;

[0062] The signal processing unit is responsible for processing relevant data and working in coordination with other parts;

[0063] Wireless communication transmission unit, which realizes data transmission and ensures information interaction between various parts of the system;

[0064] A monitoring data analysis system is used for analyzing, classifying, comparing, correcting differences, and storing body sleep data and environmental data in the sleep monitoring system, wherein the monitoring data analysis system is composed of a data preprocessing module, a data analysis module, and a data cache module;

[0065] The data preprocessing module is specifically divided into a data cleaning unit and a data conversion unit. It is used for processing operations before sleep monitoring data analysis. The data content needs to be preprocessed and cleaned to remove noise, missing values ​​and outliers, and the data is classified after processing.

[0066] The data preprocessing module is specifically divided into a data cleaning unit and a data conversion unit;

[0067] Data cleaning unit, used to identify and correct errors, inconsistencies and incompleteness in sensor data sets, and remove duplicates and outliers in the data sets to ensure data quality and availability;

[0068] The data conversion unit is used to convert the data from various sensors during sleep monitoring into a unified standard data set to maintain data consistency for subsequent data analysis operations.

[0069] The data analysis module uses the monitoring data analysis platform to perform data analysis and mining operations. By using statistical algorithms, it arranges the potential patterns and trends of sleep data, thereby providing a basis for users to formulate and recommend parameters. At the same time, the analysis module also supports customized data analysis tasks, adopts end-to-end deep learning methods, uses multivariate time series to classify temporal sleep stages, and performs analysis based on the Python toolkit MNE. When dealing with the imbalance problem of classification tasks, it adopts the loss function method of the reweighted model to improve the performance of the prediction model by providing features from adjacent time periods to the final classifier.

[0070] The data analysis module consists of a data comparison unit and a data difference correction unit;

[0071] A data comparison unit is used to compare the sleep data collected by the sensor with the basic data in the original database to determine the sleep quality of the user;

[0072] The data difference correction unit calculates the amplitude of the difference adjustment correction according to the size of the data difference after comparison, generates a control signal according to the difference amplitude, and sends a control instruction to the smart home monitoring module;

[0073] A data cache module is used to temporarily store the data collected in the sleep monitoring system for quick access during later comparison operations, thereby reducing frequent access to the main memory and external data sources;

[0074] The monitoring data analysis system also has an original database, which has storage devices, input devices, automatic coverage units, and data import and export units;

[0075] A storage device is used to store the historical physiological characteristic data of the user in the sleep state, and can train the deep learning model based on the specified deep learning model by using the historical physiological characteristic data as a training set to obtain a trained sleep staging model, and is also used to save the secondary input parameters in the later use process;

[0076] An input device is used to input new sleep control parameters during use, and is also used to selectively adjust the original parameter model;

[0077] The automatic control system of environmental equipment uses an intelligent system to adjust and control the equipment in the sleeping environment to maintain the stability of various parameters in the sleeping environment. The automatic control system of environmental equipment is divided into an environmental equipment control module and a monitoring equipment control module;

[0078] The environmental equipment control module is divided into intelligent air conditioning control unit, air purification control unit, ventilation equipment control unit, speaker control unit, and electric curtain control unit;

[0079] The intelligent air-conditioning control unit is used to turn on / off the air-conditioning equipment in the room. Through the built-in sensors and intelligent control system, it monitors the indoor and outdoor temperature changes in real time and automatically adjusts the indoor temperature to achieve a more comfortable sleeping environment. At the same time, it also controls the switch, temperature setting, and wind speed setting of the air conditioner accordingly and independently based on the collected environmental data and the comparison between the user's body surface temperature and the sleep mode parameters in the database. The intelligent air-conditioning control unit is linked with other unit items in the environmental equipment control module to automatically adjust the indoor temperature and humidity according to the preset sleep mode;

[0080] Air purification control unit, used for switching control of air purifier, equipped with air purification function, effectively filters indoor dust, bacteria, and viruses, and improves the quality of sleeping environment;

[0081] The ventilation equipment control unit controls the ventilation fan, air conditioning ventilation mode and electric windows according to the monitoring data of the indoor air oxygen content, so as to adjust the indoor air oxygen content, air humidity and ambient temperature;

[0082] The speaker control unit automatically adjusts the playback volume according to the ambient noise level;

[0083] The electric curtain control unit controls the curtains based on the real-time monitoring results of indoor light and the comparison results of ventilation conditions with preset parameters to generate different sleeping light environments and obtain feedback parameters of the user's sleeping environment;

[0084] The monitoring device control module is used to independently control various sensors for environmental monitoring and user monitoring, and to perform repeated monitoring operations according to the optimization process of the sleep environment;

[0085] The sleep monitoring data feedback system is used to visualize sleep big data. Through the visualization data, users can understand the current status of the sleep environment and find problems in the sleep environment in time, so as to make corresponding adjustments to the sleep environment settings, provide support for the research and decision-making of the sleep environment, and repeatedly optimize the sleep environment;

[0086] The sleep monitoring data feedback system includes a data visualization unit, a sleep environment optimization unit, and a cognitive model building unit;

[0087] A data visualization unit, used to send the sleep data to the user in the form of charts and graphs, and store it in the database in the form of data packets;

[0088] The sleep quality assessment unit is used to assess the quality of the sleep environment by preprocessing the sleep environment big data and using regression analysis methods to assess the quality of the sleep environment;

[0089] The sleep environment optimization unit is used to optimize the sleep environment. It pre-processes the sleep environment big data, uses cluster analysis to identify hot spots in the sleep environment, and optimizes the bedroom environment factors based on the user's sleep data and sleep environment data. It also analyzes the user's sleep status through the user's sleep data and sleep environment data, identifies the risk of sleep disorders, and provides personalized sleep intervention measures.

[0090] The cognitive model building unit combines the individual's physiological parameters, sleep environment parameters, and psychological state data to conduct comprehensive analysis and evaluation, thereby obtaining accurate sleep quality assessment results, establishing a sleep quality assessment model, evaluating the individual's sleep quality, and providing personalized sleep improvement suggestions. Combined with the sleep environment big data, it obtains the most suitable sleep environment optimization plan for the individual and applies it to smart homes.

[0091] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A sleep environment parameter recommendation system based on sleep big data, characterized in that: Including sleep monitoring system, monitoring data analysis system, environmental equipment automatic control system, sleep monitoring data feedback system; The sleep monitoring system is used to monitor the user's sleep process and collect data during the monitoring process, where the data collection is divided into body sleep data collection and environmental data collection; Body sleep data collection includes sleeping body temperature, body surface temperature, breathing rate, heart rate monitoring, and sleeping posture monitoring; Environmental data collection includes environmental oxygen content, ambient temperature, ambient humidity, noise environment, air flow rate, lighting environment, insect identification, and air quality; A monitoring data analysis system is used for analyzing, classifying, comparing, correcting differences, and storing body sleep data and environmental data in the sleep monitoring system, wherein the monitoring data analysis system is composed of a data preprocessing module, a data analysis module, and a data cache module; The data preprocessing module is specifically divided into a data cleaning unit and a data conversion unit. It is used for processing operations before sleep monitoring data analysis. The data content needs to be preprocessed and cleaned to remove noise, missing values ​​and outliers, and the data is classified after processing. The data analysis module uses the monitoring data analysis platform to perform data analysis and mining operations. By using statistical algorithms, it arranges the potential patterns and trends of sleep data, thereby providing a basis for users to formulate and recommend parameters. At the same time, the analysis module also supports customized data analysis tasks, adopts end-to-end deep learning methods, uses multivariate time series to classify temporal sleep stages, and performs analysis based on the Python toolkit MNE. When dealing with the imbalance problem of classification tasks, it adopts the loss function method of the reweighted model to improve the performance of the prediction model by providing features from adjacent time periods to the final classifier. The data analysis module consists of a data comparison unit and a data difference correction unit; A data comparison unit is used to compare the sleep data collected by the sensor with the basic data in the original database to determine the sleep quality of the user; The data difference correction unit calculates the amplitude of the difference adjustment correction according to the size of the data difference after comparison, generates a control signal according to the difference amplitude, and sends a control instruction to the smart home monitoring module; A data cache module is used to temporarily store the data collected in the sleep monitoring system for quick access during later comparison operations, thereby reducing frequent access to the main memory and external data sources; The automatic control system of environmental equipment uses an intelligent system to adjust and control the equipment in the sleeping environment to maintain the stability of various parameters in the sleeping environment. The automatic control system of environmental equipment is divided into an environmental equipment control module and a monitoring equipment control module; The sleep monitoring data feedback system is used to visualize sleep big data. It helps users understand the current status of the sleep environment through visualized data, and promptly discover problems in the sleep environment, so as to make corresponding adjustments to the sleep environment settings, provide support for sleep environment research and decision-making, and repeatedly optimize the sleep environment.

2. The sleep environment parameter recommendation system based on sleep big data according to claim 1, characterized in that: The sleep monitoring system is composed of a sensor control module, an intelligent furniture supervision module, an infrared camera module, and a data collection module; The sensor control module includes a temperature sensor, a humidity sensor, an air detector, an air purifier, and a light sensor, which are used to monitor and collect various environmental data during the user's sleep; The smart home monitoring module includes a volume controller, a wireless monitoring bracelet, and a smart mattress, which are used to monitor and collect the user's physiological signals, including body temperature, respiratory rate, blood oxygen saturation, sleeping position, and real-time heart rate. The wireless monitoring bracelet is used to monitor personal sleep status, including sleep time, sleep duration, and awakening frequency, and to establish a personal sleep database in conjunction with the physiological signal monitoring data collected by the smart mattress; The infrared camera module is composed of an infrared camera device, a video acquisition unit and a wireless transmission unit. The infrared camera device is used to record the individual's sleep process; the video acquisition unit and the wireless transmission unit are used to record and transmit the video data during the sleep process; The data collection module is used to collect and save real-time data during the use of the sensor control module, smart furniture supervision module, and infrared camera module, providing source data for subsequent data processing, analysis, and decision-making; And transmit it to the central system / cloud platform through communication.

3. The sleep environment parameter recommendation system based on sleep big data according to claim 2, characterized in that: The data collection module includes a data acquisition unit, a signal processing unit and a wireless communication transmission unit; A data acquisition unit for automatically collecting information from sensors and other modules; The signal processing unit is responsible for processing relevant data and working in coordination with other parts; The wireless communication transmission unit realizes data transmission and ensures information interaction between various parts of the system.

4. The sleep environment parameter recommendation system based on sleep big data according to claim 1, characterized in that: The data preprocessing module is specifically divided into a data cleaning unit and a data conversion unit.

5. The sleep environment parameter recommendation system based on sleep big data according to claim 4, characterized in that: The data cleaning unit is used to identify and correct errors, inconsistencies and incompleteness in the sensor data set, and remove duplicates and outliers in the data set to ensure the quality and availability of the data; The data conversion unit is used to convert the data of each sensor during the sleep monitoring process into a unified standard data set to maintain data consistency for subsequent data analysis operations.

6. The sleep environment parameter recommendation system based on sleep big data according to claim 1, characterized in that: The monitoring data analysis system is also provided with an original database, which is provided with a storage device, an input device, an automatic overwriting unit, and a data import and export unit; A storage device is used to store the historical physiological characteristic data of the user in the sleep state, and can train the deep learning model based on the specified deep learning model by using the historical physiological characteristic data as a training set to obtain a trained sleep staging model, and is also used to save the secondary input parameters in the later use process; The input device is used to input new sleep control parameters during use, and is also used to selectively adjust the original parameter model.

7. The sleep environment parameter recommendation system based on sleep big data according to claim 1, characterized in that: The environmental equipment control module is divided into an intelligent air-conditioning control unit, an air purification control unit, a ventilation equipment control unit, a speaker control unit, and an electric curtain control unit.

8. The sleep environment parameter recommendation system based on sleep big data according to claim 7, characterized in that: The intelligent air conditioning control unit is used to turn on / off the air conditioning equipment in the room. Through the built-in sensor and intelligent control system, it monitors the indoor and outdoor temperature changes in real time, automatically adjusts the indoor temperature, and achieves a more comfortable sleeping environment. At the same time, according to the collected environmental data and the comparison between the user's body surface temperature and the sleep mode parameters in the database, the switch, temperature setting, and wind speed setting of the air conditioner are controlled accordingly and independently. The intelligent air conditioning control unit is linked with other unit items in the environmental equipment control module to automatically adjust the indoor temperature and humidity according to the preset sleep mode; Air purification control unit, used for switching control of air purifier, equipped with air purification function, effectively filters indoor dust, bacteria, and viruses, and improves the quality of sleeping environment; The ventilation equipment control unit controls the ventilation fan, air conditioning ventilation mode and electric windows according to the monitoring data of the indoor air oxygen content, so as to adjust the indoor air oxygen content, air humidity and ambient temperature; The speaker control unit automatically adjusts the playback volume according to the ambient noise level; The electric curtain control unit controls the curtains based on the real-time monitoring results of indoor light and the comparison results of ventilation conditions with preset parameters to generate different sleeping light environments and obtain feedback parameters of the user's sleeping environment.

9. The sleep environment parameter recommendation system based on sleep big data according to claim 1, characterized in that: The sleep monitoring data feedback system includes a data visualization unit, a sleep environment optimization unit, and a cognitive model establishment unit; A data visualization unit, used to send the sleep data to the user in the form of charts and graphs, and store it in the database in the form of data packets; The sleep quality assessment unit is used to assess the quality of the sleep environment by preprocessing the sleep environment big data and using regression analysis methods to assess the quality of the sleep environment; The sleep environment optimization unit is used to optimize the sleep environment. It pre-processes the sleep environment big data, uses cluster analysis to identify hot spots in the sleep environment, and optimizes the bedroom environment factors based on the user's sleep data and sleep environment data. It also analyzes the user's sleep status through the user's sleep data and sleep environment data, identifies the risk of sleep disorders, and provides personalized sleep intervention measures. The cognitive model building unit combines the individual's physiological parameters, sleep environment parameters, and psychological state data to conduct comprehensive analysis and evaluation, thereby obtaining accurate sleep quality assessment results, establishing a sleep quality assessment model, evaluating the individual's sleep quality, and providing personalized sleep improvement suggestions. Combined with the sleep environment big data, it obtains the most suitable sleep environment optimization plan for the individual and applies it to smart homes.