2643 results about "Sleep state" patented technology

The invention relates to the field of sleep monitoring, in particular to a sleep monitoring visual analysis method and system based on a smart bracelet. The method comprises the following steps: extracting a sleep physiological signal of a wrist part of a user based on a smart bracelet; sliding time window analysis and multi-mode physiological state sensing are carried out, and a dynamic sleep state sensing map is constructed; performing transient mutation rhythm recognition on the dynamic sleep state sensing map, performing sleep stage evolution trend analysis, and constructing a sleep stage evolution model; the method comprises the following steps: collecting multi-dimensional parameters of a sleep environment, carrying out environment parameter change detection and environment disturbance-sleep stage change association identification, and obtaining an environment disturbance-sleep rhythm mutation association rule; environment disturbance intensity evaluation is carried out according to the association rule, and a real-time sleep state visual view is constructed. According to the method, accurate and high-readability sleep monitoring data visualization is realized, the overall sleep quality is improved, and the long-term health risk is reduced.

The invention relates to the technical field of sleep aiding, in particular to a method and a system for extracting feature information of a sleep state monitoring model. The method comprises the following steps: carrying out multi-mode physiological signal acquisition on a detected object to obtain original sleep monitoring data; performing noise removal and signal enhancement processing on the original sleep monitoring data, and performing signal segmentation to obtain multi-channel sleep signal fragment data; performing feature extraction based on electroencephalogram, eye movement diagram, electromyogram, electrocardiogram and accelerometer signals on the multi-channel sleep signal fragment data to obtain multi-dimensional feature data; and performing ultrasonic feature and acoustic feature extraction on the multichannel sleep signal fragment data to generate acoustic feature data. According to the method, dynamic modeling and trend prediction are carried out on the conversion process of the sleep state, potential sleep disorder events can be accurately recognized, influence evaluation is carried out on the potential sleep disorder events through deep learning, and support is provided for personalized sleep diagnosis.

The invention relates to the technical field of health monitoring, in particular to a deep sleep analysis and early warning system integrated with heart rate monitoring, which comprises a physiological parameter acquisition module, an environmental parameter acquisition module, a deep sleep analysis module, an anomaly detection and early warning module, a dynamic feedback and optimization module, a personalized suggestion module and a data storage and analysis module. The physiological parameter acquisition module acquires physiological parameters of a user, the environmental parameter acquisition module acquires environmental parameters, the deep sleep analysis module identifies deep sleep features based on a multivariable data analysis algorithm and evaluates sleep quality, and the anomaly detection and early warning module detects physiological anomaly and triggers early warning. The dynamic feedback and optimization module optimizes model parameters according to user feedback, the personalized suggestion module generates sleep improvement suggestions, and the data storage and analysis module stores data. According to the invention, the deep sleep state of the user can be comprehensively analyzed, a personalized health management and sleep optimization scheme is provided, and the sleep quality of the user is improved.

Various embodiments herein provide techniques related to transmission of a wake-up signal (WUS) from a base station to a user equipment (UE). In embodiments, the WUS may be received by a wake-up receiver (WUR) of the UE. Based on reception of the WUS, a main receiver of the UE may exit from a deep-sleep state or an off state. Other embodiments may be described and / or claimed.

The invention discloses a vital sign and sleep monitoring method and system based on a millimeter-wave radar, the method utilizes the millimeter-wave radar to realize non-contact sleep monitoring, and the millimeter-wave radar is firstly used to collect radar echo signals obtained by vibration of a chest wall in a sleep state; determining the position of a monitored object and extracting a vital sign signal of the target; then accurately detecting a first amplitude body movement and a second amplitude body movement of the target; whether an apnea event happens to the target is detected in real time, and alarm information is prompted under the condition that the event happens for a long time; three sleeping postures of supine, side-lying and prostrate are detected; and finally, sleep state monitoring is formed, a user sleep quality analysis report is formed in combination with the monitored information, and health suggestions are given. The method is simple, convenient, accurate, economical and efficient, is suitable for various application scenes such as families, hospitals and nursing homes, and provides all-weather health monitoring services for users.

A computer system for persistent cognitive neural architecture implementing sophisticated state preservation and sleep-state optimization capabilities. The system operates a layered neural network monitored by a hierarchical supervisory system that collects activation data, identifies operation patterns, and implements architectural changes. A meta-supervisory system tracks behavior patterns and extracts generalizable principles. A cognitive neural orchestrator manages operational states and coordinates decision-making across the network. The system maintains persistent neural network state through mechanisms that store and retrieve neural activation patterns and architectural configurations across operational sessions. During designated sleep states, the system executes optimization operations including memory consolidation and insight generation. This innovative architecture enables neural networks to maintain knowledge continuity across system restarts while implementing sophisticated optimization during periods of reduced demand, enhancing long-term performance through persistent cognitive capabilities.

The invention discloses a sleep state monitoring and analyzing system based on multi-sensor fusion, and relates to the technical field of health monitoring, the sleep state monitoring and analyzing system comprises a multi-modal sensor module used for collecting multi-dimensional data related to a sleep state, the multi-dimensional data comprises a bio-electricity signal, a physiological parameter, body movement data and an environment parameter, and the multi-modal sensor module is used for collecting the multi-dimensional data; the multi-modal sensor module comprises a non-contact sensor, a flexible electronic skin sensor and a bio-electricity signal sensor, and the data fusion and processing module is used for carrying out preprocessing, dynamic self-adaptive fusion and federal learning modeling on collected original data. According to an existing contact type sleep state monitoring scheme, more flexible and accurate sleep state data are realized through a non-contact type monitoring sensor in cooperation with dynamic adjustment of sleep monitoring content and adjustment of weights of various sensors for monitoring the sleep state; and a more accurate and intuitive reference report is provided for the sleep state and the health state of the subsequent user.

The invention relates to a multi-device cooperative control method and device based on a user state and an air conditioner. The method comprises: monitoring a sleep state of a user; and determining a sleep stage of the user based on the sleep state, and performing cooperative control on each device according to a control strategy matched with the sleep stage. The method and the device can adapt to the difference of dynamic sleep stages, and control the devices to operate cooperatively according to the control strategies matched with the different sleep stages, so that the self-adaptive adjustment and parameter adjustment precision of the devices is improved, and the problems of poor sleep mode adjustment effect and low adaptability in the prior art are solved.

The invention relates to the technical field of infant sleep nursing, solves the problem that in the prior art, the infant respiration frequency cannot be monitored in a non-contact mode, and provides a non-contact infant respiration monitoring method, device and equipment and a storage medium. The method comprises the following steps: acquiring multiple frames of real-time images in an infant sleep scene; monitoring the sleep state of the real-time image, and identifying a first target image when the infant enters the sleep state; performing image enhancement processing on the first target image, and outputting a second target image after respiratory movement enhancement; feature extraction is carried out on the second target image, and a target area related to infant respiration is recognized; according to the maximum likelihood criterion, the target area is processed, and infant respiration information is determined. The infant respiration is monitored in a non-contact mode, the accuracy of respiration frequency monitoring is improved through image collection, image enhancement processing and other modes, and intrusive monitoring on the infant is not needed.

The invention discloses a self-adaptive music synthesis sleep aiding method and system based on physiological feedback. The method comprises the following steps: acquiring physiological data of a user; preprocessing the physiological data; evaluating the sleep state of the user based on the preprocessed physiological data; defining a music parameter space according to the sleep state; optimizing music parameters based on the sleep state and the music parameter space; generating and playing music according to the optimized music parameters; while music is played, physiological reactions of the user are continuously monitored, music parameters are adjusted in real time based on the physiological reactions, and feedback circulation is formed; analyzing a long-term sleep pattern of the user based on the data obtained in the feedback loop; according to the long-term sleep mode, updating a music parameter space and an optimization strategy; security monitoring is executed, and intervention is carried out when an abnormal condition is detected; according to the invention, a plurality of key indexes such as sleep time, deep sleep proportion, sleep quality and the like are obviously improved.

The invention belongs to the technical field of intelligent hardware control methods, and discloses a low-power-consumption intelligent hardware control method which comprises the following steps: acquiring working state parameters and user interaction information of intelligent hardware, and generating an equipment state feature vector; judging whether a dormancy condition is met or not according to the equipment state feature vector; when the sleep condition is satisfied, sending a network communication agent instruction; the coprocessor configures an internal timer and awakens signal output after receiving the instruction; the master control stores a system operation state, configures a wake-up source and then enters a deep sleep state; the coprocessor cuts off the power supply of the inactive module; when a timer of the coprocessor reaches a preset network heartbeat cycle, a wake-up signal is sent to the master controller; and the master control recovers the system state, updates the feature vector and re-decides whether to sleep or not. And through multi-dimensional state perception and a master-slave cooperation architecture, and through refined power management and a dynamic reevaluation mechanism, the equipment power consumption is obviously reduced on the premise of ensuring the user experience.

The invention discloses a sleep quality analysis system based on human body HRV measurement, and relates to the technical field of sleep quality, a preliminary analysis module can quickly judge the sleep quality fluctuation condition of a user through calculation of a heart rate variability factor HRV, when the HRV value exceeds a preset threshold value, the system automatically sends a sleep quality fluctuation command to a cloud platform, and the sleep quality fluctuation command is sent to the cloud platform. Therefore, the change of the sleep state is timely responded. Besides, the neural activity module analyzes the balance state of parasympathetic nerves and sympathetic nerves and constructs a neural activity proportion Jhb, the activity deviation of the nervous system of the user in the sleep state can be determined, and a reliable basis is provided for deep analysis of the sleep state. The sleep state comprehensive analysis module is further combined with the heart rate recovery ratio Xhb and the neural activity ratio Jhb, a sleep quality evaluation index Sgzs is calculated through the trained sleep quality prediction model, and quantitative evaluation of the sleep quality of the user is further achieved.

The invention discloses a sleep state real-time monitoring method and system, and belongs to the technical field of sleep monitoring, and the method specifically comprises the steps: collecting a heart rate variability signal, an electroencephalogram signal and body movement data of a user in real time through a non-invasive sleep pad integrating a piezoelectric sensor, a flexible dry electrode and a pressure sensor; based on the physiological data, whether the user reaches an autonomous sleep state or not is judged through a first algorithm model; if not, starting an active intervention program for playing the adjustable music, and dynamically adjusting the music volume, the playing speed or the track in combination with the physiological data feedback until the user enters an autonomous sleep state; after the user falls asleep, physiological data are continuously collected, and a sober period, a light sleep period, a deep sleep period and a rapid eye movement period are divided through a second algorithm model; if the staging result is a waking period, the autonomous sleep state judgment is executed again; according to the invention, non-intrusive monitoring and personalized intervention are combined, and the monitoring comfort and accuracy are improved.

Disclosed embodiments provide techniques for automated passive acoustic monitoring with machine learning. An acoustic sensor is accessed. The acoustic sensor includes an embedded acoustic controller which hosts a machine learning model. The acoustic sensor is coupled to one or more hydrophones. The acoustic sensor is deployed in a body of water and is submerged. The acoustic sensor can enter a sleep mode. The hydrophones receive an underwater audio signal. The audio signal can be associated with an acoustic pressure. The acoustic sensor can be woken from sleep when the acoustic pressure is above a pressure threshold. The machine learning model classifies a predicted source of the underwater audio signal. The classifying can be based on filtering the underwater audio signal for a first frequency band associated with a source of interest. The predicted source is reported to a user using a communications device.

The invention particularly relates to a quartered sleep state monitoring method and a quartered sleep state monitoring system based on a non-contact vibration sensor. The quartered sleep state monitoring method and the quartered sleep state monitoring system are particularly suitable for realizing non-sensitive sleep quality evaluation through an intelligent bed in a family environment. Comprising the following steps that 1, vibration signals of a human body in the sleep process are continuously collected through a non-contact vibration sensor; step 2, preprocessing the vibration signal, including denoising and segmentation processing, to obtain time domain vibration data; step 3, performing frequency domain transformation on the time domain vibration data, and extracting frequency domain features including respiratory rate, heart rate and heart variability parameters; 4, time alignment is carried out on the frequency domain features and sleep staging labels synchronously obtained through a polysomnography, and a training data set is constructed; an XGBoost classification model based on time-frequency domain feature fusion is provided, fundamental frequency and harmonic energy proportions of respiratory signals are extracted through short-time Fourier transform, and quartering classification is achieved in combination with the LF / HF ratio of heart rate variability.

The invention relates to the technical field of smart home, and discloses an electric blanket system capable of adjusting calorific value by self-adaption to environment temperature, comprising a sleep sensing module used for collecting physiological signal data of a user; the state recognition module is used for recognizing the current sleep state of the user; the temperature target generation module is used for determining a corresponding target temperature value according to the current sleep state; the control calculation module is used for calculating a control instruction of each heating area; the multi-area heating execution module is used for performing heating control on the plurality of independent heating areas; and the temperature acquisition and feedback module is used for acquiring the real-time temperature of each heating area and feeding back the temperature to the control calculation module. Through linkage of the AI housekeeper and the external electronic bracelet, adaptive adjustment of the intelligent temperature control system is realized, a temperature control strategy is dynamically optimized according to real-time temperature data, user behaviors and environmental changes, limitation of a traditional static scheme is avoided, personalized temperature adjustment is provided, and flexibility and comfort are improved.

The invention discloses a real-time clock calibration method, device and equipment and a medium, and relates to the technical field of electric vehicle charging time calibration, and the method comprises the steps: obtaining a clock calibration parameter based on a preset time interval; executing a compensation error calculation process based on the clock calibration parameter to obtain a compensation error; and when a sleep instruction is received and it is determined that the vehicle is not in the sleep state, the compensation error is utilized to calibrate the wake-up timestamp, and a target wake-up timestamp is obtained. The method is used for solving the problem that in the prior art, when the vehicle is in the dormant state, the vehicle cannot be normally used due to the fact that the vehicle stops for a long time or exhausts the electric quantity of the storage battery in the dormant state, the target awakening timestamp is determined when the dormant instruction is received, the dormant vehicle control unit is awakened at the target awakening timestamp, and the dormant vehicle control unit is awakened at the target awakening timestamp. Therefore, the vehicle controller controls the high-voltage system to charge the storage battery, and the problem that the vehicle cannot be normally used due to the fact that the voltage of the storage battery is lower than the critical voltage is solved.

The invention discloses a sleep state monitoring method based on a GM-GP algorithm, and relates to the technical field of intelligent health monitoring, and the method comprises the steps: collecting a multi-modal signal in real time through a physiological signal collection device, and carrying out the preprocessing; electroencephalogram signals are separated from the preprocessed multi-mode signals, nonlinear feature extraction is carried out, and correlation dimensions of the electroencephalogram signals are calculated; the correlation dimensions of the electroencephalogram signals are input into a GM model for modeling, and dynamic change characteristics of different sleep stages are captured; introducing a hybrid memory enhancement network, and performing trend prediction on the time sequence of the electroencephalogram signal and the multi-modal signal; based on the prediction result of the hybrid memory enhancement network and the optimized sleep staging result, detecting the time proportion and quantity of the user in different sleep stages in real time; according to the invention, trend prediction is carried out on the multi-modal physiological signals by adopting the hybrid memory enhancement network, so that the real-time performance and continuity of sleep state monitoring are ensured, and the stability and reliability of overall monitoring are improved.

The invention belongs to the field of intelligent environment comprehensive regulation and control, and particularly discloses and provides an intelligent environment comprehensive regulation and control method based on sleep aiding, which comprises the following steps: firstly, according to the heart rate and skin resistance of a user, evaluating the stability of a sleep state, automatically adjusting the brightness and color temperature of light, and creating a suitable sleep atmosphere; secondly, determining the temperature and humidity of the preference environment by analyzing the longest sleep time, the sleep time and the number of times of waking up at night in the historical sleep data of the user, and intelligently regulating and controlling the environment to match the temperature and humidity of the preference environment of the user. And finally, the system recommends a suitable music type according to the environmental noise type, and accurately recommends sleep music based on preference feedback of the user for each piece of music. Meanwhile, environmental noise decibel is monitored in real time, music volume is dynamically adjusted, harmonious coexistence of music and environmental noise is ensured, a more comfortable and quiet sleep environment is created for the user, and the sleep quality of the user is improved in multiple dimensions.

The invention relates to the technical field of sleep monitoring, in particular to a sleep monitoring method and system, computer equipment and a storage medium, and the sleep monitoring method comprises the following steps: monitoring the pressure change of the head and neck of a user through a miniature differential pressure sensor, collecting pressure data in real time, recording a respiratory cycle according to pressure fluctuation, and determining the sleep state of the user; and identifying high and low pressure peak values, and generating head pressure monitoring data. According to the invention, by monitoring the pressure change of the head and the neck in real time, the capturing capability of tiny breathing changes is improved, refined breathing cycle recording and high-precision pressure peak value recognition are realized, potential breathing abnormity can be found at the initial stage, timely response is ensured, and the breathing frequency and amplitude are comprehensively analyzed; the breathing modes are accurately classified, so that the recognition of the abnormal breathing state is quicker, more accurate and more detailed dynamic monitoring and data analysis are realized, the evaluation of the sleep depth and stage is enhanced, and the comprehensive evaluation of the sleep quality is more scientific.

The invention provides a sleep scheduling method and a related device, the method is applied to a terminal device, and the method comprises the following steps: after first service data is transmitted through a wireless communication system (such as a wireless fidelity Wi-Fi system) and a network device, the wireless communication system is dormant and awakened according to a first sleep scheduling strategy, the first sleep scheduling strategy comprises a first duration (comprising at least one first time slice and at least one second time slice), the first time slice and the second time slice in the first duration are alternately performed, and the wireless communication system is in a sleep state in the first time slice and is in a working state (comprising a monitoring state) in the second time slice. For example, the length of the first time slice and / or the second time slice is determined according to the time delay of the service requirement corresponding to the first service data. Therefore, periodical dormancy and monitoring can be carried out based on the time delay requirement of the current service instead of being in a monitoring state all the time, the real-time experience of the service is ensured, and the power consumption is reduced.

The invention provides a communication method and a communication device. The communication method comprises: a network device sending first information to a terminal device, the first information being used by the terminal device to determine a first access opportunity for initiating random access to the network device, the terminal device being one of a group of terminal devices selected by the network device; accordingly, after receiving the first information, the terminal device enters a dormant state in a first dormant time period and initiates random access to the network device at a first access time period, and the first dormant time period is before the first access time period. In the communication method provided by the application, since the terminal device is dormant in the process of waiting for random access, the power consumption of the terminal device in the process of randomly accessing to the network device is reduced.

Certain aspects of the present disclosure are directed to a radio frequency digital-to-analog converter (RFDAC). The RFDAC generally includes a plurality of digital-to-analog (DAC) unit cells. At least one DAC unit cell is capable of being configured in an active state or in a sleep state. For the at least one DAC unit cell, an output impedance of the DAC unit cell in the active state is equal to an output impedance of the DAC unit cell in the sleep state.

The present invention relates to method of energy saving in a cellular network. The method comprises configuring, by the Base Station (BS), different periodicity for at least one Synchronization Signal Block (SSB) beam of a plurality of SSB beams in an SSB burst, based on the load on the network. The method includes transmitting, by the BS, a relaxed signal in less number of time and frequency resources than the resources used for an SSB. The method further includes indicating sleep states of the BS to a User Equipment (UE) to reduce unwanted monitoring of resources. The method also includes determining, by the BS, active number of ports and indicating, to the UE, active ports using a parameter. The method further includes dynamically determining, by the BS, transmit power of downlink (DL) signal and DL channel, and signalling a parameter about the transmit power to the UE.

The invention discloses a multi-modal data fusion and intelligent analysis high-precision sleep monitoring system and method. The system comprises a data acquisition layer, a transmission layer, an analysis layer and an application layer, the data acquisition layer transmits data acquired by a sensor to the transmission layer step by step through BLE or Wi-Fi, the transmission layer divides the data acquired by the sensor into two paths through a Wi-Fi module and transmits the data to a main control device and a cloud server in the analysis layer, and the main control device and the cloud server process the data. The data collection layer comprises a data collection module, the data collection module comprises a physiological data collection unit, an environment data collection unit and a subjective data collection unit, the data collection layer is used for collecting data of multiple sources such as physiological data, environment data and subjective data, and the data collection layer is used for collecting data of multiple sources such as the physiological data, the environment data and the subjective data. The deep learning and big data analysis technology is applied, high-precision recognition of the sleep state and precise evaluation of health risks are achieved, and a personalized sleep improvement scheme is provided.

The invention discloses a self-adaptive equipment dormancy method based on a Wi-Fi signal state, and the method comprises the following steps: 1, based on the continuous monitoring of a physical layer index of associated equipment, sending a suggested wake-up instruction to the corresponding associated equipment when it is predicted that the signal quality is rapidly reduced but does not fall off a switching threshold; step 2, according to a received suggested wake-up instruction or a signal degradation trend detected by the corresponding associated device, specifically, switching from a deep sleep state to a standby wake-up state, shortening a sleep period and pre-loading authentication information; 3, the wireless access point dynamically adjusts the sending opportunity of the suggested wake-up instruction according to the service delay requirement of the associated equipment; 4, the associated device dynamically elects a main link and a slave link based on a multi-attribute decision algorithm, and the main link is responsible for receiving a wireless access point instruction and uniformly scheduling dormancy and awakening of the slave link; and 5, generating a prediction result of future data traffic, and controlling the on-demand wake-up time of the slave link by the main link.

The invention relates to the technical field of SoC main control chips, and discloses a deep sleep wake-up control method and system for a multimode SoC main control chip. The method comprises the following steps: acquiring voltage and current data and temperature distribution data of each functional module of a multi-mode SoC main control chip under different environments and operation conditions EOC to obtain a chip monitoring data set; constructing a functional module topological graph and mapping the functional module topological graph into potential features to obtain deep sleep state criteria of each functional module; establishing a hierarchical Bayesian model, and identifying the state transition probability and EOC influence factors of each functional module to obtain a combination scheme of the deep sleep functional modules; determining a collaborative sleep control sequence; a hierarchical Bayesian model is input, a wake-up voltage and a clock sequence are generated, power consumption response of each function module is monitored in real time through a dynamic graph neural network, a safe wake-up control result is output, mutual interference among the function modules is reduced, and the overall power consumption management efficiency of a chip is improved.

The invention relates to the technical field of communication, and discloses an awakening method, equipment and a storage medium. The wake-up method comprises the following steps: when a hardware device enters a sleep state, setting a data acquisition pin in a serial communication protocol interface in a power-off state in the hardware device as a trigger function. When a data acquisition pin receives a low level signal on a data line of a corresponding communication bus, a hardware device can be directly triggered to wake up from a sleep state; or when the data acquisition pin receives a low level signal on the data line of the corresponding communication bus, the serial communication protocol interface can be triggered to enter a working state, and after the serial communication protocol interface receives address data and an awakening instruction matched with the hardware device, the hardware device is awakened from the sleep state. Therefore, based on the method, when the hardware device enters the sleep state, the wake-up source (namely the serial communication protocol interface) can enter the power-off state, so that the power consumption of the electronic equipment is saved.

The invention discloses a multi-view fusion emotion recognition method under a sleep deprivation condition, and the method comprises the steps: constructing and training a recognition model which comprises a Transform network based on multi-view fusion in an offline stage, carrying out the multi-view fusion of an input signal through employing the trained recognition model in an online stage, and achieving the real-time detection. According to the method, the accuracy of emotion recognition under a single mode (EEG signal) is improved by introducing the multi-view fusion Transform model, the dependence on multi-mode data is reduced, and the influence of the sleep state on the emotion is evaluated more accurately by improving the experimental design and eliminating the interference of material fixation on the result.

A sound masking apparatus and method are provided. The sound masking apparatus includes a sensing device that measures image information and biometric information of a passenger in a vehicle. The apparatus also includes a controller connected with the sensing device. The controller determines a sleep state of the passenger based on the biometric information and determines whether the passenger is disturbed in sleep based on the image information in the sleep state of the passenger. The controller measures noise in the vehicle in response to determining that the passenger is disturbed in sleep and determines whether there is a need for sound masking based on the measured noise. The controller performs the sound masking based on the sleep state in response to determining that there is the need for the sound masking.