384 results about "Body movement" patented technology

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.

The invention relates to the field of human-computer interaction, and discloses a human-computer interaction robot facial expression implementation control method, which comprises the following steps: dynamically capturing the face, sound and posture of a user in a human-computer interaction scene, and generating an initial emotion perception sequence; performing hierarchical cross mapping on the initial emotion perception sequence, and performing combinatorial analysis on facial expressions, voices and intonations and body movement features to form an emotion matching vector; based on the emotion matching vector, utilizing a priority regulation model to predict the emotion trend of the user at the next moment, and identifying an expression enhancement point and an emotion attenuation area; mapping the generated facial micro-expression adjusting instruction to a robot facial driving unit, and performing real-time correction and conflict resolution on an expression action sequence; and reversely fusing a user fixation point, facial muscle micro-motion and voice emotion which are acquired in real time into an emotion matching vector, and dynamically updating a perception weight and expression regulation and control parameters. The method has the advantage of improving the emotion matching degree of the robot expressions.

A system and method for training, assessing, and providing feedback on cardiopulmonary resuscitation (CPR) performance based on at least one video of a CPR training session performed by a trainee on a non-mannequin training object. A preprocessing module is configured to process the at least one video to generate a standardized video. A marking module is configured to use pose estimation to mark points for body movements during the CPR training session based on the standardized video, and a computing module configured to compute body movement parameters for CPR based on the marked points. A classification module implements a machine learning model that classifies CPR compressions on the non-mannequin training object based on the computed body movement parameters, thereby generating compression classifications, wherein the machine learning model is trained to extract CPR-specific features. An editor module maps metrics over the standardized video based on the compression classifications and generates a feedback video based on the mapped metrics. An analysis module identifies deviations from CPR guidelines based on the feedback video and generates analysis results based on the deviations. A feedback module provides performance feedback to the trainee based on the analysis results.

The application provides application of SEBS in implanting a biological electrode base. The biological electrode based on the SEBS base can be implanted in biological tissues, and is used for continuously or discontinuously analyzing physiological parameters of the biological body. Compared with other flexible bases, the SEBS base has the characteristics of being thinner and more flexible, can reduce the interference of body movement on the electrical signal, reduce the volume range of the implanted tissue and reduce the inflammatory reaction, thereby improving the measurement accuracy and long-term stability, is expected to meet more implantation site requirements when used for implanting a sensor, and has a good application prospect.

Provided herein is a string shooting device, and more particularly, a string shooting device having that is wearable and operable by hand gestures or body movement. Embodiments include a wearable device for propelling a string including: a string shooting device; a band configured to attach to a body part of a user; and a holder, where the holder is secured by the band to the user; where, in response to the body part of the user being in a first position, the string shooting device is not actuated, and where in response to the body part of the user being in a second position, the string shooting device is actuated.

A method for training an artificial intelligence (AI) model for allowing a user to intuitively control an electronic device includes positioning a plurality of sensors at a plurality of particular positions on a human body for sensing electric signals. The method also includes recording a first set of electric signals from each of the plurality of sensors in a continuous manner. At the same time, a first set of motion intents associated with a first sequence of body movement is also recorded in a continuous manner. An AI regression model is trained using a neural network to map the first set of electric signals to the first set of motion intents. In response to receiving a second set of electric signals from the plurality of sensors in a continuous manner, the AI regression model predicts a motion intent, causing the electronic device to perform an action.

The invention discloses an air conditioner control method, device and equipment in a sleep application scenario and a medium, and the air conditioner control method in the sleep application scenario comprises the steps that point cloud data of a user sleep area is continuously obtained through a millimeter wave radar, and the covering states of covering objects of all parts of a body are accurately recognized; the defects that a traditional infrared or temperature and humidity sensor cannot penetrate through the fabric, and local exposure is difficult to judge are overcome. Based on the recognition result, the system generates wind direction, wind speed and other wind feeling adjusting instructions in real time, air supply of the air conditioner is prevented from directly blowing exposed parts, and the thermal comfort is improved. The self-adaptive optimization of the strategy is realized by continuously monitoring the body movement frequency and the turn-over times of the user before and after adjustment, evaluating the adjustment effect and carrying out positive or negative weight adjustment on the control rule. The problems that in the prior art, due to the fact that the coverage state cannot be accurately perceived, air supply is uncomfortable, cold catching is likely to happen, and adjustment lags are solved, and the air conditioner use experience in the sleep scene is remarkably improved.

The invention discloses an undisturbed sleep monitoring method and a related device, and the method comprises the steps: carrying out the feature extraction of a first piezoelectric signal, obtaining a body movement feature, and enabling the first piezoelectric signal to be obtained through the superposition of a plurality of preprocessed original piezoelectric signals; frequency domain analysis is carried out on the second piezoelectric signals, frequency components corresponding to wave crests are recognized in a sleep heart rate related frequency band, a frequency pair corresponding to each moment is extracted, a frequency set is obtained, the frequency pair comprises a plurality of preorder frequency components in the first frequency sequence and the frequency of each frequency component, and the frequency set is obtained; the first frequency sequence is obtained by arranging frequency components in a descending order according to amplitude intensity; determining heart rate characteristics at each moment according to the frequency set; performing feature extraction on the acquired piezoresistive signals to obtain piezoresistive features; and determining the sleep state according to the body movement characteristics, the heart rate characteristics at each moment and the piezoresistance characteristics. The reliability and accuracy of sleep state recognition can be improved.

The invention discloses an integrated system and method with body movement control in a home environment, and the system comprises a home task construction module which is used for constructing a simulation environment, designing home tasks, labeling task data, defining task attributes, and obtaining an original home task data set; the data enhancement module is used for performing enhancement processing on the data set by adopting a supervised fine tuning SFT method and a direct preference optimization DPO method; the evaluation index module is used for setting indexes for evaluating system performance; the HLP module is responsible for decision making and planning adaptation of a tool, and generates an output O comprising a subtask and a selected bottom layer model m based on the input instruction I; the LLE module is used for converting the subtasks output by the HLP, the selected underlying model m and the inventory inv into model calling instructions, the selected underlying model m starts to execute work, error detection is carried out in real time in the execution process, the execution result is fed back to the HLP, and the execution process is recorded. The system has excellent performance.

The application belongs to the technical field of smart home, wearable device, biological signal processing and artificial intelligence control, and specifically discloses a self-adaptive audio adjustment sleep-aiding method based on sleep state recognition, which comprises the following steps: a non-invasive touch interaction mode is introduced to simplify the starting process of the sleep-aiding process; key physiological indexes such as the heart rate and body movement of a user are continuously monitored, and subtle changes in the data are analyzed to determine the physiological state of the user and the reaction of the user to environmental changes, so that the change in the acoustic environment is ensured to be always within the comfortable range that can be accepted by the user; the amplitude of the volume adjustment is controlled to be below the perception threshold of the user, and a special disturbance observation window is set to evaluate the physiological influence of each fine adjustment operation, so that inappropriate adjustment can be found and cancelled in time before substantial interference is caused. The application significantly improves the reliability of the user experience and sleep-aiding effect.

The invention discloses an interactive digital human generation method based on picture and audio synthesis, and belongs to the crossing field of artificial intelligence and computer graphics. According to the method, a full-link process of'feature extraction-model construction-emotion driving-real-time interaction-video output 'can be automatically completed only by uploading a character picture and a section of audio by a user: key point and semantic feature extraction is performed on the picture to obtain face / posture information; performing voice recognition, semantic analysis and emotion recognition on the audio to obtain a semantic tag and an emotion parameter; generating a personalized three-dimensional digital human based on the information, and driving the personalized three-dimensional digital human to generate facial expressions and limb actions which are synchronous with emotions; the user intention is analyzed in real time through natural language understanding and computer vision, and multi-modal interaction is achieved. According to the method, digital human creation can be completed without professional modeling and motion capture equipment, the generation cost is reduced, and the method can be widely applied to virtual anchors, online education, intelligent customer service and movie and television entertainment scenes.

The invention discloses a personnel state analysis method and system based on limb movement recognition, relates to the technical field of limb movement recognition, and determines the movement state of a corresponding limb part based on recognition of each movement-expression combination. And the driving response state of the personnel is determined based on the action state of each limb part, the corresponding part priority and the driving state of the truck, so that the accuracy of the driving response state of the personnel is improved. Therefore, the change event of the facial expressions is determined according to the plurality of facial expressions at different time, and the driving fatigue state of the personnel is determined according to the change event of the facial expressions and the lane changing frequency of the truck; according to the method, the voice interaction event of the person in the driving process is collected, the multiple state key contents are determined according to recognition of the voice interaction event, the state analysis system of the person is determined according to the multiple state key contents, the driving response state of the person and the driving fatigue state, and the accuracy of the state analysis system of the person is improved.

An information management device manages information provided to a first device mounted on a mobile object and a second device used by a user at a different place from the mobile object. The information management device includes a display control part, a body movement information acquisition part, a detection part, and a detailed information acquisition part. The display control part causes the second device to display an image based on the image captured by an imaging part. The body movement information acquisition part acquires body movement information of the user. The detection part detects a feature in the image that the user focuses on based on the body movement information. The detailed information acquisition part acquires detailed information of the feature detected by the detection part. The display control part displays the feature and the detailed information in association with each other.

The application discloses a night tooth grinding detection and grading method based on multi-modal signal fusion, which acquires multi-modal physiological signals including at least electromyographic signals, body movement signals and sound signals, and respectively carries out pretreatment to extract electromyographic intensity features, body movement intensity features and acoustic features; an adaptive threshold is constructed based on the electromyographic intensity features, and the adaptive threshold is dynamically adjusted in combination with the body movement intensity features to detect suspicious tooth grinding segments; the acoustic features are further fused to confirm the suspicious tooth grinding segments, determine a tooth grinding event; and the tooth grinding event is graded and output according to intensity features, duration features and multi-modal consistency features of the tooth grinding event; the application effectively reduces the false alarm rate, improves the accuracy and stability of the night tooth grinding detection through the multi-modal signal fusion and the adaptive threshold judgment mechanism, and has good practical value.

The invention discloses a humanoid robot control method and device, a robot and a storage medium, and the method comprises the steps: firstly generating an upper body operation instruction and a lower body motion instruction which meet task requirements and are high-level semantics through a pre-trained VLA model, thereby guaranteeing the continuity and consistency of the upper body and lower body motions of the humanoid robot; then control signals of all joints of the lower limbs of the humanoid robot are generated through a pre-trained reinforcement learning model, accurate lower limb joint control over the lower body of the humanoid robot is achieved, and it is ensured that the posture of the humanoid robot is balanced and the action is stable in the instruction execution process; the technical problems that in the prior art, motion and operation of a humanoid robot are separated, the motion is discontinuous, and control is unstable are solved.

Detecting spatial positioning between a user's hands and an object, using a wearable device, to provide feedback to a user. Motion data of a person's body motion while performing an action can be received at a computer. The motion data can include sensor data from sensors at a location where the sensors detect the person's body motion. The sensors can include a wearable device on the person's body. The computer can be used to model the person's body motion using the motion data. A set of parameters for acceptable motions is determined based on an action risk assessment of the action. Feedback can be initiated to the person, using the wearable device, based on the person's body motion exceeding a body motion threshold based on the set of parameters for the acceptable motions and the model.

This invention belongs to the technical field of sleep quality analysis, specifically relating to a sleep quality analysis system and method based on sensors in a medical bed, to address the technical problem of existing methods relying too heavily on duration statistics while neglecting the continuity and circadian rhythm of sleep. The analysis method includes: S1, acquiring vital sign signal data collected by sensors in the medical bed within a sleep cycle and dividing it into multiple continuous time segments; S2, extracting physiological indicators such as respiratory rate, heart rate, and body movement amplitude within each time segment, and calculating the variability depth of the corresponding time segment; S3, generating a variability depth baseline; calculating non-steady-state disturbance factors based on the frequency and duration of micro-awakening disturbance segments; and S4, generating a comprehensive sleep quality score. The analysis method of this invention improves the comprehensiveness and objectivity of the assessment results, more realistically reflecting sleep health status.

The invention relates to the field of deep learning, and discloses a heart failure patient home care intelligent monitoring method combined with deep learning, which comprises the following steps: continuously acquiring the heart rate, blood pressure, breathing and body movement states of a patient in a home environment; performing conjoint analysis of time and activity states on the data streams after priority sorting, and forming a dynamic health feature set in combination with historical health records of patients and environment variable information; comprehensively evaluating the dynamic health feature set by using a deep learning model, and identifying a potential abnormal mode of short-time change through the deep learning model; marking and grouping the physiological parameters and related behavior scenes corresponding to the candidate abnormal events, locally evaluating the current health state of the patient based on grouping information, and identifying a potential high-risk condition; and according to the local evaluation result and the overall health trend of the patient, generating real-time early warning and personalized nursing suggestions. The method has the advantage of improving the identification capability of short-time abnormity.

The invention discloses a skiing limb movement correction system, and the system comprises a user data input module which is used for inputting the stature data of a user; the leg posture sensing module is configured on the legs of the user; the leg posture sensing module is used for collecting leg movement data in the skiing movement process; the leg movement data comprises three-axis acceleration and three-axis angular velocity data; the data storage module is used for storing predefined standard action data; the data processing module is in communication connection with the user data input module, the leg posture sensing module and the data storage module and is used for receiving and processing the stature data and the leg movement data, comparing the processed movement data with standard movement data pre-stored in the data storage module and outputting skiing movement correction information; therefore, high-precision estimation and correction guidance can be performed on the gravity center track of the whole body only based on the leg sensing data, and the portability and the user experience of the system are greatly improved.

The invention provides a CT device, a working method of the CT device and a working program product of the CT device. The CT apparatus of the present invention outputs projection data including the entire subject even when the amount of output data of projection data output to a console is reduced. A CT device (11) sets a subject region in an imaging range of a radiographic image using information relating to a subject, and calculates a region around the subject region prior to actual imaging of the subject. The present invention estimates the size of a peripheral region in a range other than a subject region beyond the subject region due to body movement of a subject as the margin size with respect to the subject region, and estimates the size of the peripheral region in the range other than the subject region as the margin size with respect to the subject region. Projection data of a channel corresponding to a range of an enlarged subject region obtained by adding a peripheral region to the subject region is output to a console (17).

The utility model discloses transcranial micro-current stimulation equipment with a sleep monitoring function, which belongs to the medical field and comprises a monitoring host and a stimulation device worn on an earlobe, the monitoring host is connected with the stimulation device through a shunt data line, and a suspension earcap is arranged on one side of a shell of the stimulation device. Compared with the prior art, the device has the advantages that the stability of the stimulation device is enhanced through the suspension earmuffs, the automatic rebound clip is prevented from falling off due to swinging of a human body, then the monitoring host is fixed on the U-shaped neck protection sleeve, and when a patient wears the U-shaped neck protection sleeve and the suspension earmuffs, the patient moves in a large-radian manner, and the patient can be prevented from being injured. The transcranial micro-current stimulation equipment with the sleep monitoring function can be fixed on the head of a patient, so that the relative position of the whole transcranial micro-current stimulation equipment can synchronously move along with a human body.

A radar system for vital signs monitoring such as at least heart rate or breathing and a method for mitigating random body movement and external interference effects in vital signs monitoring such as at least heart rate or breathing by employing a radar system that is configured for providing in-phase and quadrature signals from reflected and received radar waves are provided. The problem of random body movement effects and external interference affecting vital signs monitoring is at least mitigated by decomposing and filtering a reconstructed displacement signal using a time and frequency analysis technique such as Short-Time Fourier Transform (STFT), followed by a Non-negative Matrix Factorization (NMF) operation. This decomposition allows the identification of time and frequency basis components containing the random body movement interference. Hence, the filtered signal can be reconstructed after removing the random body movement components, thus enabling reliable and robust vital-signs parameter estimation.

The invention discloses a shape memory alloy driving-based Krasserian origami bionic adhesion crawling robot which is mainly applied to space on-orbit target surface detection and maintenance. The robot comprises a body part and an advancing part, the body part comprises a head visual perception module, a body movement module, a main control module and an energy supply module, and the advancing part comprises a leg movement module and a dry adhesion module. The robot adopts a Krassin origami structure and a shape memory alloy wire driving system, and a shape memory alloy wire is driven by current to generate phase change, so that bionic motion is realized. The energy supply module provides power needed by the robot through the solar cell panel and the battery module, and long-term stable operation of the robot is supported. The robot is designed to be light and small, so that the robot has high flexibility and adaptability when being deployed on the surface of a target to perform tasks, and is particularly suitable for maintenance of space on-orbit targets.

The present disclosure addresses the problem of improving human detection accuracy. A human detection system (100) is provided with a scattering point calculation unit (221), a processing unit (222), a position output unit (223), a body movement detection unit (224), a biological signal detection unit (225), and a presence / absence determination unit (226). A scattering point calculation unit (221) calculates a plurality of scattering points at which radio waves have been reflected. The processing unit (222) outputs point group data obtained by clustering the plurality of scattering points and the center-of-gravity position of the point group data. The position output unit (223) outputs the center-of-gravity position as the presence position of the person when the center-of-gravity position is included in the predetermined region. The body movement detection unit (224) detects the magnitude of the body movement of the person when the position output unit (223) outputs the presence position of the person. A biological signal detection unit (225) detects a biological signal of the person when the position output unit (223) outputs the presence position of the person. The presence / absence determination unit (226) determines that a person is present in the predetermined region when the magnitude of the body movement of the person is greater than a threshold value set for the magnitude of the body movement of the person and / or the biological signal is greater than a threshold value set for the biological signal.

The present application relates to the field of artificial intelligence and intelligent sleep technology, and discloses a health state evaluation model generation method and system based on multi-point body surface temperature and vital sign data during sleep. The method continuously collects body surface temperature data of multiple body contact areas during the user's sleep process, and synchronously collects data such as heart rate, respiratory rate, body movement, environmental temperature and bed surface temperature, to construct a multi-dimensional sleep physiological data set. On this basis, the multi-dimensional sleep physiological data is preprocessed, feature extraction and model analysis are performed, and the health state evaluation result and personalized health insight information of the user during sleep are generated. The staged evaluation can also be carried out in combination with the change of sleep stage, and the model is continuously optimized based on the long-term temperature adjustment behavior of the user. By using the present application, the accuracy, continuity and individual adaptability of sleep health state evaluation can be improved, and more accurate sleep health analysis basis is provided for the user.

The invention discloses a sleep-aiding equipment linkage remote control method and device based on the Internet of Things, and belongs to the technical field of equipment remote control, and the method specifically comprises the steps: collecting sleep-related data of a user, and analyzing the sleep state of the user based on the sleep-related data, the sleep-related data including heart rate, breath, body movement and environmental noise, and the sleep-related data including heart rate, breath, body movement and environmental noise; based on the sleep state, a cooperative control instruction used for multiple sleep aiding devices is generated, the cooperative control instruction comprises coordination parameters used for adjusting the action sequence and action intensity of the devices, the cooperative control instruction is sent to the sleep aiding devices through a remote communication channel, and self-adaptive adjustment is conducted according to device feedback and external disturbance; according to the invention, it is ensured that multiple devices can implement matched action modes in different sleep stages of a user, and stable instruction generation capability and flexible remote control capability are provided for a complex sleep scene.

The invention discloses an intelligent pressure sore protection data processing method and system based on the Internet of Things, and the method comprises the steps: obtaining the pressure distribution, body movement and respiratory rate data of a target object through an Internet of Things interface, and calculating a pressure sore risk index based on a pressure value and the continuous compression time. When the risk index exceeds a preset threshold value, the system can judge the sleep state of the target object: if the body movement amplitude and frequency are relatively low and breathing is stable, the sleep state is judged to be a deep sleep state, and bed body side turning at a small angle is executed; and if the body movement and breathing parameters are active, judging that the state is a non-deep sleep state, and executing large-angle bed body side turning. The application is used for reducing and interrupting the continuous sleep process of the nursed person and reducing the risk of pressure sores and rest quality of the nursed person.

The invention is applied to the field of sleep management, and discloses a sleep state recognition regulation and control method and system.The method comprises the steps that piezoelectric signal data captured by piezoelectric sensing equipment and optical pulse signal data captured by wearable sensing equipment in the sleep process of a target user are obtained; body movement artifact removal processing is conducted on the piezoelectric signal data and the optical pulse signal data, and first piezoelectric signal data and first optical pulse signal data are obtained; performing fusion processing on the first piezoelectric signal data and the first optical pulse signal data to obtain a target fusion feature; determining a sleep type of the target user based on the target fusion feature, performing sleep state recognition on the target fusion feature based on the sleep type, and generating a sleep core index corresponding to a recognition result; and according to the sleep type and the sleep core index, generating and executing a sleep regulation strategy of the target user. According to the method, the sleep quality of the user is improved.

The invention relates to the technical field of biomedical radar signal processing and artificial intelligence crossing, in particular to a physical sign recognition method based on an FMCW millimeter wave radar segmented scanning algorithm, and the method comprises the steps: dividing a monitoring space range of an FMCW millimeter wave radar into a plurality of continuous and non-overlapped sub-regions; body movement, respiration and heart rate feature vectors are extracted from each sub-region, feature weights are calculated through an entropy weight method, the optimal detection sub-region of each type of physiological signals is screened out in combination with a weighted fuzzy comprehensive evaluation method, and finally parameter calculation is completed in the respective optimal region. According to the method, the problems of loss of weak signals in a non-peak region, mutual interference of body movement and respiration / heart rate signals, difficulty in adapting to spatial distribution differences of people with different heights / body types, insufficient signal aliasing recognition precision and the like caused by traditional global single-region detection are effectively solved, and high-precision, partitioned and robust detection of the body movement, respiration and heart rate signals is realized.

Provided is a weighted reconstruction technique of a channel for suppressing a blood flow artifact and a body movement artifact in imaging using a multi-channel reception coil. In a case of reconstructing an image of a subject by using a nuclear magnetic resonance signal collected by each of a plurality of channels of a reception coil, by using a positioning image, an organ or a region causing a blood flow artifact and a body movement artifact in the subject is specified, a weight of each channel is decided by using information on the specified organ or region, and weighted reconstruction is performed by using the weight.