30 results about "Sleep analysis" patented technology

The invention discloses a sleep analysis system, method and device based on multi-mode PSG data and a medium, and relates to the technical field of artificial intelligence. The system comprises a data acquisition module used for acquiring multi-modal PSG data of a target object; the data processing module is used for preprocessing the multi-mode PSG data; the sleep recognition module is used for performing multi-dimensional prediction on the sleep condition of the target object according to the preprocessed multi-mode PSG data; wherein the sleep recognition module is provided with a sleep staging model for recognizing sleep stages, a breathing event recognition model for recognizing breathing event types and a micro-awakening recognition model for recognizing micro-awakening events; and the data statistics module is used for integrating and analyzing the preprocessed multi-modal PSG data and the multi-dimensional prediction result of the sleep recognition module to obtain a sleep analysis report of the target object. According to the scheme, the multi-mode PSG data is fully utilized to realize automatic joint identification of multiple sleep tasks in the same system.

This invention discloses a breathable, conductive hydrogel electrode, its preparation method, and its applications. The breathable, conductive hydrogel electrode comprises a porous fiber support structure and a hydrogel conductive network. The porous fiber support structure has a three-dimensional porous structure formed by interwoven porous fibers, each fiber possessing a three-dimensional interconnected channel structure formed by interconnected pores distributed on and within the porous fibers. The hydrogel conductive network is distributed on the surface and within the porous fiber support structure, forming a continuous ion conduction path within the electrode. The breathable, conductive hydrogel electrode provided by this invention has advantages such as high breathability, self-humidification, low impedance, and breathability, achieving high-fidelity, long-term acquisition of physiological signals such as electroencephalograms (EEG), electrocardiograms (ECG), and electromyograms (EMG). It can be widely used in electrophysiological signal monitoring, smart wearables, sleep analysis, and human-computer interaction.

System and methods of a mobile application to remotely monitor residents with device-free sensing of human motion over Wi-Fi is provided. A detailed behavioral analysis of various functions related to the sleep and activity of the subject has been provided. The Remote Care Application (RCA) is a mobile application on several platforms that displays the results of all the analysis and behavioral patterns obtained from the motion from the subject. The system relies on existing wireless communication signals and machine learning techniques in order to automatically detect the motion of the subject, sleep analysis of the subject, activity analysis of the subject.

The invention relates to the technical field of enuresis nursing equipment, and discloses a night intelligent urine monitoring and nursing wearable system for enuresis children, which comprises a wearable diaper unit, a physical sign monitoring module, an intelligent interaction terminal, a data fusion analysis module and an intervention strategy generation module. According to the invention, through multi-modal data fusion of the distributed capacitive humidity sensor array and physiological sign monitoring, high-precision capture and urine volume estimation of the whole enuresis event process are realized; on this basis, sleep analysis and historical data are combined to generate a dynamic and personalized hierarchical intervention strategy, so that the accuracy and effectiveness of alarm are improved, false alarm and missing alarm are reduced, and meanwhile, comprehensive and associated data support including urine parameters and physiological states is provided for clinical diagnosis; the comprehensive effects of auxiliary treatment and improvement of child sleep quality and nursing efficiency are achieved.

The present disclosure relates to systems and methods for improving analysis of sleep data by classifying users based on sleeper type. In particular, a wearable computing system can obtain a first set of motion sensor data for a user during a first time period from a motion sensor. The wearable computing system can determine a sleeper type for the user from a plurality of sleeper types based on the first set of motion sensor data received from the motion sensor. The wearable computing system can select a sleep analysis model from a plurality of sleep analysis models based on the sleeper type determined for the user. The wearable computing system can analyze a second set of motion sensor data from a second time period using the selected sleep analysis model to determine one or more sleep features for the user during the second time period.

The invention relates to the technical field of sleep monitoring, in particular to a sleep monitoring method and system based on data analysis, and the method comprises the steps: synchronously collecting a BCG original signal and electroencephalogram data, and determining a first sleep staging label according to the electroencephalogram data; determining a second sleep staging label according to the BCG original signal; determining an actual sleep staging tag in combination with the first sleep staging tag and the second sleep staging tag; determining sleep characterization states according to the actual sleep stage labels of the users, wherein the sleep characterization states comprise a sleep consistent state and a sleep inconsistent state; and determining a plurality of users for sleep analysis according to the sleep characterization state and the actual sleep staging label of each user so as to perform sleep feature analysis on each user. According to the method, the sleep characterization state is determined through statistical analysis of the actual sleep staging labels of all the users, then the users needing sleep analysis are screened out, and effective management and personalized monitoring of group sleep are achieved.

The invention discloses a control method of a massage device for assisting sleep, which comprises the following steps: S1, collecting a multi-modal physiological signal of a user in a sleep process in real time through a non-contact or micro-contact sensor, and preprocessing the multi-modal physiological signal; s2, inputting the collected multi-modal physiological signals into a pre-trained sleep analysis model, and calculating and outputting sleep stage probability distribution and sleep stability index of the current user in real time; s3, dynamically generating an optimal massage control instruction according to the sleep stage probability distribution and the sleep stability index at the current moment and a preset intervention target library; and S4, recording physiological signal change and sleep stage evolution data before and after massage intervention, and continuously optimizing the sleep analysis model and the massage decision strategy in combination with the morning subjective sleep quality score of the user.

1. The name of the design product: sleep analysis graphical user interface of electronic device. 2. The use of the design product: an electronic device. 3. The design points of the design product: the content of the graphical user interface in the display screen panel. 4. The picture or photo that best indicates the design points: front view. 5. The use of the graphical user interface: the user interface of the product is the interactive interface of the smart sleep monitor applet. 6. The human-computer interaction mode of the graphical user interface: the display interface in the front view is the home page interface; the gray "data analysis" button below the front view can be clicked for interaction, and clicking the corresponding "data analysis" button switches to the interface of interface change state diagram 1 to display the sleep state statistical analysis interface of the day; the blue "sleep analysis" button above the interface change state diagram 1 can be clicked for interaction, and clicking the corresponding "sleep analysis" button switches to the interface of interface change state diagram 2 to enter the graphical analysis interface. 7. The "gray module" covering part in the figure is a variable figure, and the variable text is replaced by "X".

The embodiment of the invention provides a multi-modal data fusion sleep monitoring system and method based on collaboration. The system comprises a mobile detection terminal, a charging dock used for charging the mobile detection terminal and a cloud data platform, the mobile detection terminal only needs to collect physiological data, and the charging dock serves as data transfer and is selectively detachably connected with multiple detection modules to supplement the modality of detection data. The cloud data platform performs data analysis and fusion to obtain a sleep analysis result, so that comprehensive information data of various types / modalities can be obtained under the condition of limited cost, and meanwhile, the cloud data platform has strong data processing capability.

The embodiment of the invention provides a single-channel electroencephalogram sleep analysis method and related equipment, and belongs to the technical field of electroencephalogram signal processing and sleep health monitoring. The method comprises the following steps: carrying out preprocessing and time sequence enhancement on a single-channel electroencephalogram signal; extracting local and global features by using a double-branch feature encoder; feature distribution alignment between a source domain and a target domain is realized through a double-contrast adversarial learning module in combination with cross-view time sequence contrast learning and conditional adversarial alignment; dynamically adjusting a target domain sample weight based on information gain through a learnable reweighting module so as to correct label distribution offset; and finally, high-precision sleep staging or OSAHS event detection is realized by utilizing a classifier. According to the method, the generalization ability and robustness of the model in a cross-subject scene are remarkably improved, accurate analysis can be achieved only through single-channel electroencephalogram signals, the hardware cost and the use threshold are reduced, and the method is suitable for scenes such as family sleep monitoring and telemedicine screening.

This invention provides a cognitive management method and system for insomnia with intelligent suggestions for bedtime. The method includes: collecting and preprocessing multi-dimensional user data to obtain standardized input data; training a sleep analysis model based on historical datasets and continuously optimizing the model using user feedback data; using the sleep analysis model to perform inference based on real-time user data for the day, dynamically generating and outputting a personalized sleep plan including suggested bedtimes; obtaining actual sleep details and calculating sleep quality indicators; conducting continuous risk monitoring based on sleep quality indicators and triggering tiered intervention suggestions; and feeding the sleep quality indicators and user feedback data as training data into the model optimization step to achieve closed-loop optimization. This invention solves the problems of rigid suggestions, lack of personalization, and insufficient continuous optimization capabilities in existing technologies, achieving precise, dynamic, and intelligent sleep management.

The invention relates to a method for monitoring a user's sleep in a motor vehicle (10), wherein a control device (22): activates a rest program of the motor vehicle (10) (S1) that assists the user while resting in the motor vehicle (10); detects that the user is resting or sleeping in the motor vehicle (10) (S2); and receives an occupant monitoring signal (S3) from a sensor device (14) of the motor vehicle (10), which describes at least one body state parameter that describes a state of one or more body parts and / or one or more body actions of the resting or sleeping user. Based on the occupant monitoring signal, the control device (22) provides a user-specific sleep analysis model (S6) that describes an overall state of the user's body and determines the sleep quality of the user's sleep (S7) based on the provided sleep analysis model.The control device (22) then generates a display signal (S8) that describes the information on the determined sleep quality and transmits this to a display device (30) of the motor vehicle (10) (S9).

The present application relates to a kind of low-frequency event fidelity decontamination system for sleep synchronization EEG-fMRI, belong to electroencephalogram signal processing technical field.Solve the problem of low-frequency event morphological characteristics of existing synchronization EEG-fMRI decontamination scheme under sleep scene.System includes EEG acquisition interface, auxiliary information input interface, processor, memory, result output interface and basic preprocessing module, low-frequency event reference construction module, low-frequency event sample generation module, decontamination model module, event fidelity training module, inference control module and quality control output module.System is by constructing low-frequency event reference, generates targeted training sample, uses event fidelity loss function to train decontamination model, implements differentiation correction control in inference stage, realizes suppression magnetic resonance related artifact while keeping low-frequency sleep event peak and valley position, amplitude characteristics and duration, improves subsequent sleep analysis and multimodal research reliability.

The invention discloses a sleep data acquisition method, a sleep data analysis method, a sleep data acquisition device and a sleep data processing system, and the method comprises the steps: dividing an acquired sleep signal according to a set length, and obtaining a plurality of sleep signal data segments; acquiring discrete cosine transform (DCT) data segments respectively corresponding to the multiple sleep signal data segments; extracting the DCT data segment in a set spectral range to obtain a key DCT data segment, the key DCT data segment comprising a plurality of frequency components; according to the energy corresponding to the multiple frequency components, key frequency components are extracted from the multiple frequency components to obtain sleep data used for sleep analysis, and the energy corresponding to the frequency components represents the intensity or contribution degree of the frequency components in the sleep signals. According to the invention, the accuracy of the sleep data for sleep analysis can be improved.

This invention discloses a sleep analysis method that integrates spatiotemporal multi-scale features, comprising the following steps: Step 1, acquiring multi-channel raw physiological signal data from a polysomnography device and preprocessing it to obtain a standardized multi-channel signal data block of fixed length; Step 2, inputting the standardized multi-channel signal data block into a pre-trained deep learning feature extraction network, which includes parallel temporal feature extraction branches and spatial feature interaction branches, and outputting a multi-scale fused feature vector; Step 3, inputting the multi-scale fused feature vector into a pre-trained sleep event recognition model based on the Transformer architecture, which then outputs a sleep analysis report. This invention has the advantages of high efficiency, accuracy, and strong generalization.

The invention relates to a monitoring and / or analysis device (24), in particular a sleep monitoring and / or sleep analysis device, with a sensor unit (10) comprising at least one contactless respiratory rhythm sensor (12) which is provided for remote detection of a respiratory rhythm of a living being (14). It is proposed that the respiratory rhythm sensor (12) is designed as a laser feedback interferometry (LFI) sensor.

The application relates to the technical field of sleep analysis, in particular to a sleep prediction method and system based on daytime brain electrical cross-frequency coupling and timing characteristics, which comprises the following steps: synchronously collecting daytime brain electrical signals and daytime skin electric response signals of a user in a daytime wake state; extracting timing characteristics of the daytime brain electrical signals to form a daytime brain electrical feature set representing daytime brain fatigue, cognitive load and emotional arousal; preprocessing the daytime skin electric response signals to extract a daytime skin electric feature set containing skin electric fluctuation amplitude and skin electric baseline level characteristics; fusing the daytime brain electrical feature set and the daytime skin electric feature set to generate a daytime neural state feature vector; and inputting the daytime neural state feature vector into a pre-trained deep learning prediction model to output a nighttime sleep prediction result of the user, thereby achieving significant improvement in prediction timeliness, objectivity and prediction accuracy.

The invention discloses a sleep-aiding music generation method and device based on multi-modal signal feedback, and the method comprises the steps: collecting the multi-modal physiological data of a target user in the sleep process, extracting and screening the target key features of the multi-modal physiological data, and carrying out the sleep analysis based on the target key features, obtaining a sleep quality scoring model of the target user; screening individual sleep-aiding audio materials of the target user through multiple rounds of structured audition in combination with physiological data feedback, and constructing a material library; extracting physiological feature parameters of the target user in a slow-wave sleep stage, and establishing a linear mapping model of the physiological feature parameters and music control parameters; and when identifying that the user is in the slow wave sleep stage, adjusting and optimizing the audio clip according to the linear mapping model, and dynamically updating a music parameter control model according to the change of a scoring result output by the sleep quality scoring model. And the accuracy and timeliness of music intervention are improved.

The invention discloses a breathable conductive hydrogel electrode and a preparation method and application thereof. The breathable conductive hydrogel electrode comprises a porous fiber supporting structure and a hydrogel conductive network, the porous fiber supporting structure is of a three-dimensional porous structure formed by interweaving porous fibers, and the porous fibers are of a three-dimensional through pore channel structure. The three-dimensional through pore channel structure is formed by mutually communicating pores distributed on the surface and inside of the porous fiber; the hydrogel conductive network is distributed on the surface and in the porous fiber supporting structure and is used for forming a continuous ion conduction path in the electrode. The breathable conductive hydrogel electrode provided by the invention has the advantages of high breathability, self-humidifying property, low impedance, breathability and the like, realizes high-fidelity and long-term acquisition of physiological signals such as electroencephalogram, electrocardio, myoelectricity and the like, and can be widely applied to the fields of electrophysiological signal monitoring, intelligent wearing, sleep analysis or human-computer interaction.

A system and method for determining a sleep disorder in a patient is disclosed. A storage device stores a digital image including the patient's face and neck. A database stores previously identified phenotypes and dimensions of facial and neck features. A sleep disorder analysis engine is coupled to the storage device and the database. The sleep disorder analysis engine is operable to identify facial and neck features on the image by determining landmarks on the image. The sleep disorder analysis engine classifies at least one phenotype on the image based on a comparison with the database. The sleep disorder analysis engine correlates the at least one phenotype and at least one feature with a sleep disorder. The sleep disorder analysis engine determines a risk score for the sleep disorder based on the correlation between the phenotype and the feature.

The invention relates to the technical field of sleep analysis, and discloses a sleep quality evaluation method which comprises the following steps: acquiring sleep evaluation; analyzing the weight of each item of sleep evaluation through an AI model, wherein the AI model dynamically adjusts the weight based on training data; and performing comprehensive calculation on the sleep evaluation, and outputting a sleep quality evaluation result. According to the method, the weight of sleep evaluation is dynamically adjusted, an existing unscientific mode of fixed weight and average weight is thoroughly replaced, it is ensured that the weight fits clinical influence and individual difference, and the accuracy of sleep evaluation is improved.

A system and method to determine a sleep disorder in a patient is disclosed. A storage device stores a digital image including a face and a neck of the patient. A database stores previously identified phenotypes and dimensions of facial and neck features. A sleep disorder analysis engine is coupled to the storage device and the database. The sleep disorder analysis engine is operable to identify features of the face and the neck from the image by determining landmarks on the image. The sleep disorder analysis engine classifies at least one phenotype from the image based on comparisons with the database. The sleep disorder analysis engine correlates the at least one phenotype and at least one feature with a sleep disorder. The sleep disorder analysis engine determines a risk score of the sleep disorder based on the correlation of the phenotype and the feature.

The invention relates to the technical field of intelligent decision, and discloses a differentiated user sleep analysis method, device, equipment and medium, the method comprises the following steps: collecting night sleep data of a target user and user attribute information, and extracting static features from the user attribute information; extracting dynamic features from the night sleep data; generating a group category label according to the static features and the dynamic features; performing sleep level analysis on the target user according to the group category label and a preset sleep quality index to obtain a sleep level; according to a preset sleep stability index, score adjustment is conducted on the sleep grade score corresponding to the sleep grade, and the sleep score of the target user is obtained. The sleep level of the target user is analyzed through the group category label and the preset sleep quality index, the matching degree of the sleep level and the real condition is remarkably improved, the sleep level score corresponding to the sleep level is adjusted, the score is made to be closer to the real sleep feeling of the user, and the accuracy of the sleep score is improved.

The application is suitable for the technical field of data recognition, and provides a sleep analysis method and device, the sleep analysis method comprises the following steps: synchronously collecting multi-modal original signals based on multi-modal sensors in an intelligent waistband; extracting a modal feature matrix composed of the multi-modal original signals; inputting the modal feature matrix into a cross-modal correlation feature extraction network for processing to obtain a cross-modal correlation feature vector corresponding to a comprehensive sleep state; inputting the cross-modal correlation feature vector into a sleep analysis model to obtain a sleep staging category and a sleep physiological event. The sleep health monitoring scheme based on the intelligent waistband not only improves the accuracy and reliability of sleep monitoring, but also enhances the use convenience of users in daily life.

The invention discloses a mattress system for intelligently monitoring and recording the sleep state of old people, and belongs to the field of intelligent health monitoring. The mattress system comprises a mattress, an intelligent monitoring board and a bed board; the intelligent monitoring board is designed to achieve automatic monitoring of the lying posture of the old people, multi-dimensional data such as the number of times of turning over, the sleeping posture, the on-bed and off-bed state and the sleeping duration are covered, meanwhile, by means of the alarm module and the voice module, voice reminding is conducted in time for the problems of poor sleeping quality, frequent getting up at night and the like, and the sleeping quality is improved. Alarm information can be quickly sent out for emergencies such as long-time static non-reaction; the problems that according to a traditional monitoring technology, data collection is not comprehensive, sleep problems are difficult to intervene in time, emergency response is delayed, and part of wearable equipment disturbs sleep are solved, sufficient data support is provided for sleep analysis and health judgment, early discovery and early intervention of the sleep problems and efficient rescue of emergency situations are achieved, and the sleep quality is improved. Meanwhile, the old can sleep naturally and comfortably and enjoy the monitoring service without perception.

A wearable physiological monitoring device is configured to determine a wearer's sleep intention. In particular, the device evaluates activity that might be objectively associated with awaking from sleep in order to distinguish between a wearer's intention to end sleep and transitory stirring or other intermittent activity occurring in the context of a longer sleep interval. By evaluating sleep intention more accurately in this manner, the device can advantageously request sleep analysis from a remote server in those instances where a user intends to end a period of sleep (so that this data can be available to the user more quickly), while avoiding unnecessary or redundant server-side processing of sleep data in those instances where a user intends to continue sleeping.

This invention discloses a sleep disorder assessment method based on a fundamental audio model. The steps include: using a self-supervised learning model as the backbone network of a sleep sound fundamental model, and adding a parameter-efficient fine-tuning module to the Transformer module of the sleep sound fundamental model; pre-training the sleep sound fundamental model using sleep sound data samples, adding a neural network module corresponding to the sleep disorder assessment task as the downstream task head to the pre-trained sleep sound fundamental model to obtain an assessment model for the sleep disorder assessment task; freezing the pre-trained part of the assessment model and using sleep sound data samples to train the assessment model for the downstream task; acquiring real-time sleep sound data and inputting it into the trained assessment model to obtain the corresponding sleep disorder assessment result. This invention improves the applicability of sound signals in sleep analysis tasks while reducing computational resource requirements.

The present invention relates to a sleep analysis period detection method and system, which is performed in a system including a layer unit, a sensor unit, a memory unit, and a data analysis unit, and includes the steps of: sensing a user's biological signal from the sensor unit provided in the layer unit; storing the user's biological signal sensed by the sensor unit in a memory unit; and analyzing the user's biological signal stored in the memory unit using the data analysis unit to detect the user's sleep analysis period.