53 results about "Night sleep" patented technology

The invention discloses a deep learning model optimization method in sleep health monitoring, and belongs to the technical field of model optimization. Monitoring and counting the exercise data and beverage data of the user on the current day, performing targeted data processing and analysis by using different influence modules in the sleep health monitoring model, and performing reliability verification on basic sleep quality data corresponding to sleep at night by using the exercise data and beverage data of the user on the current day; performing reliability analysis of influence effects on a sleep positive influence module, a sleep negative influence module and a sleep fusion influence module in the sleep health monitoring model by using sleep influence verification data corresponding to a plurality of times of sleep health monitoring of the user; dynamically managing influence processing schemes implemented by different influence modules in the sleep health monitoring model in a self-adaptive manner according to an evaluation result; the method and the device are used for solving the technical problem of poor personalized monitoring analysis and management effects of a deep learning model for different individual users in the existing scheme.

The utility model relates to the field of spine correction, and discloses a scoliosis corrector for teenagers, which is used for adjusting and correcting sleeping postures at night and comprises a correction plate, the front side and the rear side of the left side of the bottom of the correction plate are fixedly connected with first supporting plates, and the front side and the rear side of the right side of the bottom of the correction plate are fixedly connected with second supporting plates. The front faces of the first supporting plate and the second supporting plate are both in threaded connection with connecting rods, and the front sides of the tops of the connecting rods are movably connected with movable plates. According to the waist correcting device for the teenager, through mutual cooperation of the structures of the screw rod, the adjusting block and the fixing rod, after the adjusting block is driven by the screw rod, the limiting plate drives the extrusion cylinder to conduct sleeping posture correcting work on the lateral bending positions of the lumbar vertebra and the thoracic vertebra of the teenager, and the purpose that the waist of the teenager is corrected when the teenager lies on the correcting plate to sleep is achieved; the lateral bending parts of the lumbar vertebrae and the thoracic vertebrae on the two sides of the teenager are also corrected, scoliosis caused by improper sleeping postures is prevented, and the teenager can be prevented from falling from the correction plate due to the change of the sleeping postures during sleeping.

The application relates to the technical field of air conditioner control, and discloses an air conditioner indoor unit control method, device, equipment and storage medium, the method realizes the cooperative control of the air conditioner indoor unit and the lighting mechanism in the night scene, and a complete logic chain of scene recognition, information collection, state determination and accurate control is constructed; through the combination of a millimeter wave radar sensor and a human state detection model, the accurate perception of the human state is realized, non-target interference can be effectively filtered, and three states, i.e., frequent rotation, sitting up and getting out of bed, can be distinguished, so that the false touch rate is greatly reduced; the air conditioner parameter adjustment or the lighting control is respectively performed according to different states, the problems of high false touch rate and unsuitable brightness of a traditional night light can be solved, the defects of the fixed parameter operation of a traditional air conditioner can be made up, and the user's night sleep comfort and night convenience are significantly improved; meanwhile, a high-frequency scanning mode is adopted, the real-time performance and the accuracy of state determination are ensured, and a reliable data basis is provided for subsequent parameter adjustment and lighting control.

The purpose of the present invention is to discover an eye drop capable of effectively lowering intraocular pressure even at night, especially during night sleep, in patients with glaucoma or ocular hypertension.　The present invention is an eye drop for lowering intraocular pressure during night sleep in patients suffering from glaucoma or ocular hypertension, the eye drop containing sepetaprost at a concentration of 0.002% (w / v) as an active ingredient.

The invention relates to the technical field of disease detection, in particular to an early cardiovascular and cerebrovascular disease detection method based on sleep data. The method comprises the following steps: acquiring sensor data in a night sleep process of a user, and preprocessing the data to obtain intermediate features; constructing a data set based on historical data and establishing a probability distribution hypothesis, and performing parameter learning on a probability density function by using methods such as maximum likelihood estimation and the like to form a training model; extracting intermediate features from newly collected sleep data, inputting the intermediate features into the model, calculating the probability of occurrence of the intermediate features in the distribution, and judging whether the user has the risk of cardiovascular and cerebrovascular diseases according to the probability; meanwhile, the new features are stored in an individual database, and an individualized probability distribution function is constructed; and integrating the existing model and the individualized model, calculating the risk probability of the user, and outputting early warning information when the risk probability meets a preset condition. According to the invention, early risk prompting of cardiovascular and cerebrovascular diseases can be realized by using night sleep data.

The utility model discloses a shoulder pillow device for limiting an affected limb after a rotator cuff repair operation. The shoulder pillow device comprises a bottom pad and a clamping bag. The bottom pad is arranged from the shoulder of the affected side to the arm of the affected side, so that the shoulder of the affected side is lifted up to the arm of the affected side. The clamping bag is triangular and is clamped between the affected arm and the trunk, one corner of the clamping bag is attached to the interior of the armpit of the affected side, and the space of the armpit of the affected side is filled. When a patient sleeps at night, the patient after the rotator cuff repair lies on the sickbed, the shoulder of the affected side is supported to the height of the arm of the patient through the bottom pad, the abduction angle of the shoulder joint of the affected side is supported through the clamping bag, the clamping bag is attached to the abduction position of the affected limb to be placed, the abduction position braking effect of the affected limb is achieved, postoperative wound growth is promoted, and secondary injury caused by traction due to adduction of the arm of the patient is avoided; and the patient feels comfortable.

The utility model discloses a self-adaptive absorption tampon, which relates to the technical field of hygienic products and comprises an inner layer and an outer layer, the outer layer is fixedly arranged outside the inner layer, the inner layer comprises a super absorbent resin layer and a cellulose fiber layer, and the outer layer is formed by interweaving elastic fibers and hydrophilic non-woven fabrics. By means of the layered composite structure and the spiral drainage channel design, the sanitary tampon can automatically adjust the absorption speed and mode according to menstrual blood flow, greatly improves absorption efficiency, effectively reduces side leakage risks, can provide reliable protection no matter when a user sleeps in the daytime or at night when the menstrual blood flow is large, and is safe and reliable. Due to the flexible protrusions on the outer layer, the tampon can be better attached to vagina structures of different females, foreign body sensation is reduced, comfort can be kept even during sports or long-time activities, and the experience feeling of a user is improved.

The invention discloses a sleep disorder curative effect dynamic evaluation system based on multi-modal data fusion and artificial intelligence, and relates to the technical field of intelligent medical treatment, the sleep disorder curative effect dynamic evaluation system comprises a cloud analysis platform, the cloud analysis platform is in communication connection with the following modules: a curative effect time sequence analysis module, a sliding time window is fused with a long-short-term memory network and a trend decomposition algorithm, and continuous multi-night sleep data authorized by a user is dynamically analyzed. Through the curative effect time sequence analysis module, a 7-day sliding window is combined with a long-short-term memory network and a seasonal trend decomposition algorithm, time sequence dependence characteristics are extracted, long-term trend and periodic fluctuation are separated, the limitation of traditional single or subjective evaluation is broken through, a quantitative curative effect curve and a stability index which are updated every day can be generated, and the evaluation accuracy is improved. The long-term evolution situation and the short-term fluctuation of the sleep quality are visually reflected in a data visualization form, and a continuous and objective dynamic data basis is provided for curative effect evaluation.

The invention discloses a monitoring method and system for nursing old stroke patients at home, and belongs to the technical field of dynamic monitoring. Acquiring turning frequency, breathing frequency and heart rate data of the home old stroke patient sleeping at night; performing time window division on the night sleep duration; calculating a night sleep quality index in a single time window; calculating a breathing fluctuation variable quantity and a turning-over fluctuation variable quantity, and calculating a night sleep quality abnormal degree of the household senile cerebral apoplexy patient in the next time window; presetting a night sleep quality abnormality threshold value, and analyzing and reminding medical staff to perform nursing early warning. According to the invention, by calculating the abnormal degree of the sleep quality and combining the breathing and turning-over fluctuation change of the patient, the abnormal situation of sleep is accurately identified, and the medical staff is timely notified to carry out intervention, so that the accuracy of data and the continuity of monitoring are improved, and the safety and response efficiency of home care are improved.

The invention relates to a divisional application with the application number of 202411328371.2, discloses a method and system for evaluating the growth and development state of 0-6-year-old children based on intestinal flora and application, and belongs to the field of development evaluation of 0-6-year-old children, and the development state to be evaluated comprises one or more of neuropsychological development, skin, excrement, crying and screaming and night sleep; the method comprises the following steps: acquiring intestinal flora information of a to-be-predicted target population; the intestinal flora information comprises relative abundance information of flora significantly related to the corresponding development state; the intestinal flora information is input into a pre-constructed prediction evaluation model, evaluation results output by the prediction evaluation model are obtained, and the quantification results correspond to different development states. According to the method, near and long-term neuropsychological development, skin, excrement, crying and screaming conditions and night sleep indexes of the children are predicted through intestinal flora of the children, target spots capable of reference improvement are provided, bad development results possibly existing in the future can be found in time, and prevention and improvement are carried out in time.

1. Name of the Design Product: Packaging Kit (Gemini Good Night Sleep Eye Mask). 2. Use of the Design Product: For packaging eye masks. 3. Design Key Points of the Design Product: Lies in the pattern. 4. Picture or Photo Best Showing the Design Key Points: Perspective view of Kit 1. 5. Other Situations Requiring Explanation: Other Explanation: Kit 1 is the outer packaging, and Kit 2 is the inner packaging; Kit 2 is a thin product, so the left view, right view, top view, and bottom view of Kit 2 are omitted.

The present application relates to the field of old-age service management, and particularly relates to a smart old-age service management system based on the Internet of Things, which is provided with an observation and collection module, which comprises an image collection unit for collecting infrared images of a monitoring target and an audio collection unit for collecting respiratory sound volumes of the monitoring target; a behavior analysis module, which is used to identify respiratory behavior characteristics based on the infrared images of the monitoring target every monitoring period, analyze respiratory state abnormality characteristic values for the monitoring target based on the respiratory behavior characteristics, and divide respiratory state abnormality tendency categories of the monitoring target; and a behavior analysis module, which is used to adaptively analyze the monitoring target according to the respiratory state abnormality tendency categories. The present application analyzes the characteristic state presented by the monitoring target during night sleep, discovers the sleep abnormality of the monitoring target in time, issues a warning prompt information so as to enable a caretaker to check in time, ensures the sleep health of the monitoring target, and reduces the risk of occurrence of other health problems.

The application discloses a kind of method, system and application based on intestinal flora to assess the growth and development state of children of 0-6 years old, belong to the development assessment field of children of 0-6 years old, and the development state to be assessed includes one or several of neuropsychological development, skin, stool, crying, night sleep;The method comprises the following steps: obtaining the intestinal flora information of the target population to be predicted;The intestinal flora information includes the relative abundance information of the flora significantly related to the corresponding development state;Intestinal flora information is input into the prediction evaluation model constructed in advance, and the evaluation result output by the prediction evaluation model is obtained, and the quantitative result corresponds to different development states.The present application predicts the neuropsychological development, skin, stool, crying condition, night sleep index of children in the short and long term through the intestinal flora of children, provides target points that can be referred to for improvement, can timely find the adverse development results that may exist in the future, and timely prevent and improve.

1. The name of the product of this design: Eye mask (Gemini Goodnight Sleeping Eye Mask). 2. The purpose of this design product: used for shading, relieving eye fatigue and promoting sleep. 3. The design key point of this appearance design product lies in the pattern. 4. The picture or photo that best illustrates the design points: three-dimensional picture. 5. This appearance design product is a thin product, and the left view, right view, top view and bottom view are omitted.

The utility model discloses a night construction sound insulation cover, relates to the technical field of night road construction, and aims to solve the technical problems that in the current night construction environment, nearby residents are in a sleep state, mechanical equipment can generate noise during construction, and the life of the surrounding residents and night sleep are greatly influenced. Comprising a bottom frame mechanism, a sound insulation cover body and a lower sound insulation mechanism, the sound insulation cover body and the lower sound insulation mechanism are installed on the bottom frame mechanism, the bottom frame mechanism comprises a keel frame, the sound insulation cover body comprises a side screen body, a front screen body, a top screen body, an L-shaped stand column and a pressing plate, and mesh galvanized cover plates are arranged on the inner wall of the side screen body and the inner wall of the front screen body in an array mode; sound absorption cotton is arranged in the mesh galvanized cover plate, and the lower sound insulation mechanism comprises a plurality of lower sound insulation plates rotationally installed at the lower end of the keel frame. The utility model has the advantages that the noise generated by construction can be effectively reduced, a quiet environment is provided for residents, and the influence of night construction on surrounding residential areas is avoided.

The utility model discloses a sacrococcygeal region pressure sore prevention type nursing device, relates to the technical field of medical nursing instruments, and aims to solve the technical problem that the sacrococcygeal region is extruded due to the fact that a patient is easy to turn over inautonomously when sleeping at night at present, and the sacrococcygeal region pressure sore treatment of the patient cannot be guaranteed. Comprising an adjusting mechanism, a nursing mechanism installed on the adjusting mechanism and a limiting mechanism installed on the nursing mechanism, the adjusting mechanism comprises a supporting seat, the nursing mechanism comprises two nursing seats, the two nursing seats are symmetrically distributed, and rotating pieces are arranged at the side ends of the nursing seats; the limiting mechanism comprises a limiting plate rotationally mounted at the side end of the nursing seat, and the rotating part comprises a mounting plate and a mounting rod arranged at the front end of the mounting plate. The pillow has the advantages that the sacrococcygeal region of a patient is in a suspended state, the patient is prevented from turning over unconsciously when sleeping at night, pressure sore prevention nursing can be effectively carried out on the sacrococcygeal region, and the treatment effect of pressure sores of the sacrococcygeal region is guaranteed.

The invention discloses a method and a system for comprehensively monitoring daytime and nighttime symptoms of Parkinson's disease, which are used for solving the problems of fragmentization, strong subjectivity, low calculation efficiency and the like of the existing monitoring. The system synchronously collects real-time clock, body position, EOG, EMG and IMU (inertial measurement unit) multi-mode signals, hierarchically identifies daytime activity, night sleep, pre-sleep and initial awakening stages, and then adaptively activates corresponding modules to analyze symptoms: monitoring movement symptoms and tumble in daytime and attributing, identifying sleep disorder at night, and identifying sleep disorder at night. A morning stiffness severity index is generated by fusing time, myoelectricity and motion signals in the initial awakening period; the characteristics are mapped into UPDRS / PDDS scores based on machine learning, a structured report containing visualization and historical comparison is generated, a diagnosis and treatment closed loop of'monitoring-analysis-reporting-doctor evaluation-treatment adjustment 'is constructed, objective continuous monitoring is achieved, Parkinson's disease diagnosis and treatment are assisted, and medical efficiency is improved.

The invention discloses a sleep staging model training method based on non-wearable device data and application. Comprising the following steps: 1) acquiring all-night sleep data synchronously acquired based on a non-wearable device and polysleep monitoring, and constructing an original all-night sleep data set of the non-wearable device and a data set of polysleep monitoring contrast; 2) constructing a reconstructed sleep data set required by sleep staging in combination with expert opinions and non-wearable device data; 3) extracting local features by using a convolutional neural network (CNN, including multi-scale convolution), and establishing a time sequence model in combination with a bidirectional gating cycle unit (BiGRU); the method comprises the following steps of (1) performing training by using a reconstructed data set, data enhancement and optimization parameters, label smoothing and a KL divergence loss function, and (5) evaluating a trained model by using LOO-CV. The method not only can achieve accuracy comparable with that of a traditional polysleep monitor, but also can greatly improve monitoring convenience and comfort.

The present application relates to the technical field of intelligent health monitoring, and discloses an age-adaptive unsupervised automatic sleep staging method, comprising: taking a single-lead electroencephalogram (EEG) signal as the core, sequentially performing data preprocessing and epoch slicing, EEG multi-dimensional feature extraction and unsupervised decision space construction, EEG-guided initial sleep staging, age-adaptive deep sleep N3 threshold calibration, electrooculogram (EOG)-assisted N1 / REM boundary conservative revision, and timing consistency constraint decoding, and finally outputting an all-night sleep staging result; the present application solves the problem that the prior art is difficult to simultaneously meet the requirements of unsupervised label-free, low-channel adaptation, cross-age accurate discrimination, boundary recognition stability, and strong timing consistency.

The invention discloses an evaluation method and system for improving postoperative sleep of an elderly patient through nerve block analgesia, relates to the field of anesthesiology and pain management, and solves the problems that it is difficult to construct a staging model by using a CNN deep learning framework, and it is difficult to obtain multiple comprehensive indexes by recording data related to sleep quality in the whole night sleep period through PSG detection. The method comprises the following steps of: randomly dividing the elderly patients into a control group and an experimental group; carrying out a PSG test in a hospital sleep laboratory; constructing a staging model by using a CNN deep learning framework, and obtaining a sleep time comprehensive evaluation index, an awakening time continuous interval comprehensive index and a sleep respiration and limb disorder comprehensive index; the multiple indexes and the sleep efficiency are combined to obtain a comprehensive sleep quality evaluation index; and analyzing the sleep quality improvement condition according to the control group-experimental group comprehensive sleep quality proportion value.

The invention provides a snore classification method and system based on a multi-dimensional sleep sign signal feature graph, and relates to the technical field of data processing, the method comprises the following steps: preprocessing an all-night sleep acoustic signal, an oxyhemoglobin saturation signal and a pulse rate signal which are synchronously collected; based on the preprocessed acoustic signal, a plurality of independent snore event segments are positioned and cut by detecting the envelope peak value of the acoustic signal and combining a double-threshold endpoint detection method; based on each snore event segment, Mel frequency cepstral coefficient features, time domain features and frequency domain features are extracted from the corresponding acoustic signals to form an acoustic feature set, and fluctuation features and extreme value features are synchronously extracted from the corresponding oxyhemoglobin saturation signals and pulse rate signals to form a physiological feature set. According to the method, high-precision automatic classification of pathological snore and normal snore is realized.

The invention discloses a preparation method and application of a medicine for preventing and treating premature ovarian failure, the medicine comprises the following components in parts by weight: 3-10 parts of eucommia ulmoides, 2-8 parts of salvia miltiorrhiza and 1-6 parts of ligusticum wallichii. The premature ovarian failure (POF) is also called ovarian insufficiency, refers to ovarian function decline, follicle-stimulating hormone level increase and estrogen level decrease of women before 40 years old, and shows secondary amenorrhea and infertility, and is often accompanied with menopausal symptoms such as sweating, insomnia, hypomnesis and the like in a night sleep process; at present, hormone replacement treatment is a main treatment method for premature ovarian failure, but the side effect is large after hormone is taken for a long time, and the probability of suffering from breast cancer and endometrial cancer can be increased; the medicine composition disclosed by the invention can be further developed into a molecular traditional Chinese medicine for preventing POF and delaying the POF process, so that the comprehensive utilization of the composition is promoted, and a new choice is provided for patients with POF.

The invention aims to provide a student work auxiliary management device based on multi-modal perception, and the device comprises a multi-modal perception system which carries out the data interaction with a data middle platform, and is used for collecting the basic data of students; the basic data of the student comprises one or more of daily face appearance, wearing, facial micro expression and night abnormal behavior of the student at school. The data processing system performs data interaction with the multi-mode sensing system and is used for acquiring state data of the students in class or night sleeping condition data of the students according to the basic data; according to the state data of the students in class and the night sleeping condition data of the students, abnormal behaviors of the students are judged, and judgment data are obtained; and the application layer performs data interaction with the data processing system and is used for sending reminding information to guardians of the students according to the judgment data so as to perform targeted management on the students.

The invention relates to the technical field of risk prediction and large model prediction, in particular to a spontaneous abortion risk prediction system and method based on ensemble learning and prevention and control behaviors. A prediction device of the system comprises two parts, in the first part, a plurality of models are used to predict spontaneous abortion risk indexes based on influence parameters input by an input device; in the second part, the spontaneous abortion risk indexes output by all the models in the first part are combined to obtain the final prediction value of the spontaneous abortion risk. The influence parameters comprise male / female age, male / female sedentariness time, male / female social time difference and male / female night sleep time; social time difference refers to time difference between sleep in workdays and sleep in rest days. According to the method, the defect that a high-precision spontaneous abortion risk prediction technology is lacked in the prior art is overcome, and the spontaneous abortion risk can be predicted with high precision in combination with known behavior information.

The application is suitable for the technical field of breathing machines, and particularly relates to a breathing machine control method and system based on sleep behavior data. The method comprises the following steps: obtaining behavior data and first operation data; wherein the behavior data comprises first behavior data for reflecting the movement of the abdominal cavity diaphragm of a user during sleep and second behavior data for reflecting the breathing movement of the user during sleep; determining an adjustment gain parameter based on the first behavior data; identifying sleep feature data for reflecting the actual required breathing machine tidal volume adjustment requirement of the user during the sleep process from the first operation data based on the second behavior data and the adjustment gain parameter; and generating second operation data based on the sleep feature data and the adjusted first operation data after the adjustment of the first operation data based on the adjustment gain parameter. The method makes the tidal volume of the breathing machine in line with the sleep habits of the user during night sleep, thereby improving the use experience of the breathing machine.

The present application relates to the technical field of health monitoring, and discloses a home health risk assessment method and system based on night sleep activity. The present application collects night sleep physiological data and night activity trajectory data of a user through a sign monitoring module under a mattress and a night behavior trajectory module in a residence, and uploads the data after time stamp alignment by a gateway. Abnormal physiological values are cleaned out, sleep-behavior correlation features are constructed, and composite features such as difficulty falling asleep, heart rate sudden change and apnea are extracted. The risk of heart, respiration and cognitive decline is assessed in different dimensions, and long-term risk aggravation warning can be generated through 30-day personal dynamic baseline and linear regression significance analysis. The present application solves the problems of data isolation, rough index and cognitive assessment blind area in the prior art, realizes non-invasive and accurate early warning of home health, and is suitable for home care monitoring of the elderly.

The application discloses a kind of infantile smart prompting device of kicking quilt, belong to the technical field of infantile night sleep monitoring equipment, to solve the technical problem that infantile kicking quilt cannot be discovered in time, parents frequent night check influence sleep.The device adopts split wireless design, from temperature measurement ring of wearing on the ankle of infant and parent wearing host ring are composed, from machine carries high-precision temperature sensor and real-time collection ambient temperature, by bluetooth etc.wireless transmission point to point transmission to host;Host preset temperature threshold, real-time comparison temperature data, below threshold when automatically triggering vibration or buzzer double mode early warning, night uses mute vibration mode to avoid disturb infant.The device uses long press anti-misoperation control, independent Type-C charging module, with low power consumption, high sensitivity, low false alarm characteristics, whether infant can be reflected in real time whether kicking quilt, timely remind parents, guarantee infant sleep health, alleviate parents monitoring pressure, adapt to family night infant sleep monitoring scene.

The utility model discloses a lengthened night sanitary towel belongs to sanitary towel technical field, including sanitary towel body, the both sides of sanitary towel body are equipped with the sticky surface, the lower fixed connection of sanitary towel body has the fixed device for the application of different size, the lower fixed connection of fixed device has the aromatherapy device for emitting fragrance when extruding, the fixed device includes movable belt and fixed band, movable belt and fixed band all are fixedly connected in the lower sanitary towel body. In the utility model, when need fixing sanitary towel body, first, stick the paste face to the outside of underpants, then, pull the elastic band and drive the fixed band to move, and through pulling the fixed band, the elastic band is clamped into the preset long groove, then, pull the elastic band to make the second magic paste and the first magic paste firmly adhere, thereby realize the firm fixing of sanitary towel body, and the structure effectively avoids the sanitary towel body displacement problem caused by turning over or body compression in the traditional fixing mode in the night sleep.

The invention belongs to the field of cardiovascular diagnosis, and particularly relates to a cardiovascular diagnosis and risk early warning system and method based on millimeter wave radar monitoring. Synchronous non-inductive monitoring of multi-dimensional parameters such as the body fluid retention index, the heart rate variability, the arrhythmia and the respiratory event of the user during night sleep is achieved. According to the system, through an original multi-mode risk feature incidence matrix and an artificial intelligence time sequence model, the core pathophysiological and physiological index of dynamic balance of body fluid is deeply fused with other physiological signals, and a specific high-risk coupling mode is identified; therefore, early-stage and high-specificity risk early warning of acute myocardial infarction, ischemic cerebral apoplexy and acute heart failure decompensation is realized; according to the invention, the problems of lack of pathophysiological depth and insufficient specificity in the existing early warning technology are solved, and a revolutionary active health management tool is provided for cardiovascular and cerebrovascular high-risk groups.

The invention provides a universal postoperative shoulder back cushion. The universal postoperative shoulder back cushion comprises a base; the first supporting block is detachably connected to the base, one side of the first supporting block is arranged to be an arc surface, and the first supporting block and the second supporting block are arranged in a spaced mode; the third supporting block and the second supporting block are fixedly connected to the base in a spaced mode, the second supporting block is located between the first supporting block and the third supporting block, the first supporting block, the second supporting block and the third supporting block are arranged on the same straight line, and arc-shaped pieces inclining upwards gradually are arranged on one side of the second supporting block and one side of the third supporting block correspondingly. The pillow can effectively support the shoulders and the big arms of a patient, avoid falling of the arms, keep the shoulders stable, and remarkably relieve pain of the patient during sleep at night; the shoulder requirements of patients with different postures can be met, and the universality and applicability of the product are improved; the shoulder curve of different patients can be automatically fitted, the comfortable supporting experience is provided, and meanwhile the customization requirement is reduced.