CN109925136B - Intelligent bed system based on action intention recognition and use method thereof - Google Patents
Intelligent bed system based on action intention recognition and use method thereof Download PDFInfo
- Publication number
- CN109925136B CN109925136B CN201910212283.9A CN201910212283A CN109925136B CN 109925136 B CN109925136 B CN 109925136B CN 201910212283 A CN201910212283 A CN 201910212283A CN 109925136 B CN109925136 B CN 109925136B
- Authority
- CN
- China
- Prior art keywords
- pressure
- bed plate
- lying
- intention
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000009471 action Effects 0.000 title claims abstract description 54
- 238000000034 method Methods 0.000 title claims abstract description 23
- 230000000474 nursing effect Effects 0.000 claims abstract description 32
- 230000008859 change Effects 0.000 claims abstract description 19
- 230000000630 rising effect Effects 0.000 claims description 42
- 238000012545 processing Methods 0.000 claims description 14
- 230000007306 turnover Effects 0.000 claims description 10
- 238000012544 monitoring process Methods 0.000 claims description 9
- 210000002414 leg Anatomy 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 7
- 238000010801 machine learning Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 6
- 210000003754 fetus Anatomy 0.000 claims description 6
- 210000000689 upper leg Anatomy 0.000 claims description 4
- 241001669679 Eleotris Species 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 239000003990 capacitor Substances 0.000 claims description 2
- 230000008030 elimination Effects 0.000 claims description 2
- 238000003379 elimination reaction Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 abstract description 8
- 238000005192 partition Methods 0.000 abstract description 4
- 239000000383 hazardous chemical Substances 0.000 abstract 1
- 231100000206 health hazard Toxicity 0.000 abstract 1
- 230000036544 posture Effects 0.000 description 27
- 206010011985 Decubitus ulcer Diseases 0.000 description 6
- 208000004210 Pressure Ulcer Diseases 0.000 description 6
- 238000011161 development Methods 0.000 description 5
- 230000018109 developmental process Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 210000003205 muscle Anatomy 0.000 description 4
- 238000013480 data collection Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 210000003489 abdominal muscle Anatomy 0.000 description 1
- 239000008186 active pharmaceutical agent Substances 0.000 description 1
- 239000002390 adhesive tape Substances 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000009530 blood pressure measurement Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000004438 eyesight Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000013383 initial experiment Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000035479 physiological effects, processes and functions Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 210000001519 tissue Anatomy 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Landscapes
- Invalid Beds And Related Equipment (AREA)
Abstract
本发明为一种基于动作意图识别的智能床系统及其使用方法，智能护理床系统是以现有的机械护理床为基础，增加了床板分区、压力传感器模块、控制器，对其功能进行改进，通过压力传感器模块实时获取使用者卧躺的压力变化数据，再由控制器依靠预设的意图识别算法，通过对使用者有起卧意图时床面压力数据进行分析识别，将动作意图信号传输给驱动器，控制驱动器的升压装置，使对应区域电动推杆伸缩，带动相应床板升降或倾斜，实现床板的升降和角度倾斜的功能，以自动调节卧床者的睡姿，可缓解过度压力引起压疮等健康潜在危险。
The present invention is an intelligent bed system based on action intention recognition and a method of using the same. The intelligent nursing bed system is based on the existing mechanical nursing bed, and adds a bed board partition, a pressure sensor module and a controller to improve its functions. , the pressure change data of the user is acquired in real time through the pressure sensor module, and then the controller relies on the preset intention recognition algorithm to analyze and identify the bed surface pressure data when the user has the intention of getting up and down, and transmit the action intention signal. Give the driver, control the booster device of the driver, make the electric push rod in the corresponding area expand and contract, drive the corresponding bed board to lift or tilt, realize the function of the bed board lifting and angle tilt, and automatically adjust the sleeping position of the bedridden, which can relieve the pressure caused by excessive pressure. Potential health hazards such as sores.
Description
Technical Field
The invention relates to the field of intelligent beds, in particular to an intelligent bed system based on action intention recognition and a using method thereof.
Background
Along with the gradual introduction of China into the aging society, more and more people with high risk of pressure sores are involved, and the pressure sores not only cause great harm to the physiology and the psychology of patients, but also bring heavy burden to families and the society. Handicapped people who suffer from various disasters and diseases also increase year by year, and have different degrees of disabilities such as walking, eyesight, hands and language. The traditional nursing bed is limited to the condition of manual operation no matter in a hand-operated or electric mode.
In the development process of the nursing bed, automation, safety and comfort become index parameters of the development of the nursing bed, and the development of the nursing bed is more and more emphasized by people, so that the nursing bed can drive a bed board to ascend and descend or incline at a certain angle along with action intention so as to relieve the body pressure of a user, which is an important function for the user.
An intelligent pressure sore measurement and control turn-over bed (Chenchunmi, Wanglihua, Guhaiyan and the like, the development of the intelligent pressure sore measurement and control turn-over bed, Chinese medical equipment, 2012 and 27(1)) researched by a second subsidiary hospital of Nantong university lays a special constant-temperature pressure measurement water cushion at the pressed part of a patient to obtain the pressure of the local tissue of the patient, the pressure distribution of a human body on a nursing bed is measured by the pressure sensor, and an alarm signal is sent out based on a pressure-time safe zone curve to remind medical staff to prevent pressure sores of a patient, but the special constant-temperature pressure measuring water cushion has higher cost, in addition, in the research, only the alarm signal is sent out after the safety range is exceeded, the patient can not be automatically assisted to turn over, there is a limitation because the nursing bed cannot be automatically controlled to complete the turn-over action at all without knowing the posture of the patient on the nursing bed.
Disclosure of Invention
The invention aims to provide an intelligent bed system based on action intention recognition and a using method thereof, and the system enables an intelligent nursing bed to monitor the intention of a user to get up or lean on the body and automatically drives a motor to control the inclination and the descent of a bed plate so as to adjust the sleeping posture of a human body.
In order to achieve the purpose, the invention adopts the technical scheme that:
an intelligent bed system based on action intention recognition comprises a mechanical nursing bed main body, a pressure sensor module, an upper computer, a controller and a driver; the method is characterized in that:
the nursing bed main body comprises a bed frame, a bed plate, a plurality of electric push rods and a driver, wherein the bed plate is formed by seven movably connected spliced small bed plates arranged on the bed frame, the guardrails are fixed on the bed frame and distributed around the bed plate, the electric push rods drive each small bed plate to act, the electric push rods are connected with the driver, the driver is simultaneously connected with the controller, and the controller is connected with a pressure sensing module and an upper computer;
the bed plate comprises a first small bed plate, a second small bed plate, a third small bed plate, a fourth small bed plate, a fifth small bed plate, a sixth small bed plate and a seventh small bed plate, wherein the seventh small bed plate supports the part below the shank of a human body, the first small bed plate, the second small bed plate and the third small bed plate are arranged side by side in the left-to-right sequence to support the upper half part of the human body, the fourth small bed plate, the fifth small bed plate and the sixth small bed plate are arranged side by side in the left-to-right sequence to support the waist part to the thigh part of the human body, and the first small bed plate, the second small bed plate and the third small bed plate provide supporting force when a person has the intention of getting up; when a person has an intention to turn over to the left, the first small bed plate and the fourth small bed plate provide supporting force, when the person has an intention to turn over to the right, the third small bed plate and the sixth small bed plate provide supporting force, and the second small bed plate and the fifth small bed plate provide stable areas when the person turns over; the seventh small bed board is used for helping the user to lift the legs so as to carry out leg activities;
the pressure sensor module is used for acquiring pressure change data of a user lying in real time, and is paved on a first small bed board-sixth small bed board area by adopting a flexible pressure sensor array;
the controller is internally loaded with an intention recognition algorithm and is used for processing the acquired pressure value, analyzing and recognizing the pressure data of the bed surface when a user has an intention to rise and lie, sending an action intention signal of the human body to the driver, controlling the electric push rod of the corresponding part of the bed plate and displaying the size change of the real-time pressure signal on the upper computer;
the driver comprises a control unit and a boosting device, the control unit is communicated with the controller through a serial port, the control unit is connected with the electric push rod through the boosting device, and an action signal of the controller is sent to the control unit of the driver through the serial port;
the boosting device amplifies the action intention signal received by the control unit to enable the voltage value to meet the voltage working range of the electric push rod, the voltage input of different electric push rods is connected to the output of the boosting device, when the boosting device outputs positive voltage, the part corresponding to the bed board identified by the action intention acts, and when the output voltage of the boosting device is 0, the electric push rod stops acting.
The specific process of the intention recognition algorithm is as follows:
the method comprises the following detailed steps:
step one, state judgment:
under normal operation, a minimum pressure threshold value and an effective area threshold value of the lying are set, the upper computer collects data of the flexible pressure sensor in real time through the controller, if the collected pressure data are not larger than the minimum pressure threshold value of the lying, or the area of the pressure sensor with the minimum pressure of 10% is smaller than the effective area threshold value of the lying, the data are recorded as a state 1, at the moment, the data collection mode is used for collecting data in a low-frequency low-consumption mode, and a low-consumption dormant state is realized when no person is used or a person is in the non-lying state; otherwise, the acquired pressure data is greater than the minimum pressure threshold value of lying, and meanwhile, the area of the pressure sensor at the minimum pressure of 10% is not less than the effective area threshold value of lying, so that the situation that the user lies on the bed surface can be judged, the state is recorded as 2, and the data acquisition mode is adjusted to be the normal use mode;
secondly, positioning a lying area of a user:
performing Kalman filtering processing on the pressure sensor information acquired in the state 2; the signal after interference elimination constantly detects the pressure variation amplitude of the user in the state 2, and if the pressure variation amplitude is not more than 50% within 10s, the current pressure distribution state is set to be in a normal lying state;
then under the normal lying state, acquiring different pressure values on the horizontal and vertical units on the flexible pressure sensor, generating corresponding pressure distribution maps and positioning a lying area of a user;
for lying areas, positioning a spine according to a central axis of a human body structure rule, and carrying out significant area division on three head length positions as a waist, wherein the lying areas can significantly reflect the rising action intention of a sleeper, namely the upper half areas, namely the shoulder, the back and the waist;
thirdly, monitoring the rising and lying intentions in real time:
monitoring and calculating the upper half body area by a preset identification algorithm, and indicating the intention of getting up or lying down when the pressure change proportion of the area exceeds the standard value of the algorithm; the specific flow of the recognition algorithm is as follows:
selecting a collected pressure area, setting the pressure value of +/-100 calculated by the area of each unit of the sensor and the pressure value when the sensor enters a normal lying state as an effective upper and lower limit threshold value of the point, comparing each value of the selected waist, back and shoulder areas with the effective threshold value, wherein the output of the effective upper limit threshold value which is more than or equal to the value is true, and the output of the effective lower limit threshold value which is less than or equal to the value is false; calculating the proportion of true output to false area pressure value;
setting the proportional coefficient of the rising state to be 0.5, comparing the ratio of the pressure value output as a True area to the pressure value output as a False area, when the ratio of the output True area to the output False area is larger than the proportional coefficient, the rising intention is considered, and when the ratio of the output True area to the output False area is equal to the proportional coefficient, the user is considered to be unresponsive, namely motionless; when the ratio of the output true area to the output false area is smaller than the scale factor, the user is considered to fall down; therefore, the identification of the rising intention of the user is judged;
the fourth step: memory learning
In use, the rising and lying sample data of the same user is continuously recorded, a corresponding sample classifier is set by using a machine learning algorithm, the data of effective work when the intention is correctly identified in the use process is recorded, the effective threshold value and the proportional coefficient of the rising intention are continuously judged in the third step of modifying and optimizing specific body parameters of the specific user from the original rough standard, and the monitoring accuracy of the rising and lying intention is improved.
In the intelligent bed system based on action intention recognition, the control units of the controller and the driver adopt STM32F103ZET6 chips.
The use method of the intelligent bed system based on action intention recognition comprises the following steps:
1) sleeping posture recognition and intention recognition
Transmitting the pressure data acquired by the pressure sensor module to a controller, processing the sleeping posture pressure image by the controller, processing the sleeping posture pressure image to identify the sleeping posture and identify the type of the sleeping posture; after the sleeping posture type is identified, the human action intention is identified according to the dynamic change of the pressure data acquired by the pressure sensor module and by combining an intention identification algorithm in the controller;
2) dynamic weight detection
Transmitting the dynamic weight data detected by the pressure sensor module to the controller, processing the dynamic weight data by the controller, and identifying the body movement state of the user;
3) sleeping posture adjustment
The controller comprehensively judges the state of the user according to the results of the sleeping posture identification and the dynamic weight detection, and when the sleeping posture of the user needs to be adjusted, the controller controls the small bed plate on the corresponding subarea to perform lifting, angle inclination and flat movements, so that the automatic rising and side rising of the user are realized to relieve pressure.
In the using method, the sleeping posture types are six types, namely a supine type, a prone type, a right side lying fetus type, a right side lying trunk type, a left side lying fetus type and a left side lying trunk type.
Compared with the prior art, the intelligent bed system based on action intention recognition has the beneficial effects that:
the invention has the remarkable advantages that:
the intelligent nursing bed system based on action intention recognition is based on the existing mechanical nursing bed, a bed plate partition, a pressure sensor module and a controller are added, the functions of the intelligent nursing bed system are improved, pressure change data of lying of a user are obtained in real time through the pressure sensor module, then the controller analyzes and recognizes the pressure data of the bed surface when the user has a rising and lying intention picture by means of a preset intention recognition algorithm, an action intention signal is transmitted to a driver, a boosting device of the driver is controlled, an electric push rod in a corresponding area is made to stretch and retract, the corresponding bed plate is driven to lift or tilt, the functions of lifting and tilting the bed plate are achieved, the sleeping posture of the bedridden person is automatically adjusted, and the potential health risks such as pressure sores caused by excessive pressure can be relieved.
The invention has the substantive characteristics that:
1) the bed board is divided into a first small bed board, a second small bed board, a third small bed board, a fourth small bed board, a fifth small bed board, a sixth small bed board and a seventh small bed board, seven small bed boards are spliced together to form the whole bed board, and the seven small bed boards are movably connected through hinges and controlled by an electric push rod, so that different small bed boards can independently act. The arrangement is that the sleeping postures of a human body on the bed are divided into lying on the side and lying on the flat, the actions can be divided into rising, turning over and the like, the rising is convenient for the human body to lie on the flat, and the bed board partitions designed according to different functional requirements are the basis for the free-angle inclination of the bed board.
2) The invention is provided with the controller, a conscious-graph recognition algorithm is loaded in the controller, and the automatic control can be carried out according to the action intention of the patient, so that the bed board acts, and the inconvenience caused by the fact that the existing nursing bed still needs manual control to operate is avoided.
3) The pressure sensor array is adopted to collect pressure signals, the conductive adhesive tape is used for building, the price is low, only array points are collected, the cost is low, the material and the preparation process are simple, the large-area expansion application is easy, the quantitative feedback can be carried out on the contact state, and the signal collection is accurate. The sensor module has high response speed and accurate identification. The information of contact pressure of hands, feet and the like can be clearly distinguished; capacitance sensitivity of about 1.17% V/kPa; the response speed can reach 30f/s, and the real-time graphical display of the pressure information can be realized.
4) The system can achieve action recognition and automatic adjustment, has high degree of automation and intelligence, has simple structure and stable function, can realize multidirectional inclination of the bed plate, and can flexibly adjust the sleeping posture of a human body.
In conclusion, the system is an intelligent bed which can automatically regulate and control the inclined movement of the bed plate of the nursing bed by identifying the action intention of the user so as to assist the user in getting up and lying down. The invention can change the manual control of the traditional intelligent bed into the automatic and intelligent control, and realize the functions of automatic rising and lateral angle inclination to relieve the body pressure of the user. The intelligent household nursing system can meet the requirements and development of the current intelligent household and medical market on nursing of the old people, remarkably relieves the pressure of patients and nurses, and has wide application and market prospects.
Drawings
Fig. 1 is a schematic diagram of the overall structure of an embodiment of an intelligent nursing bed system based on action intention recognition provided by the invention.
Fig. 2 is a schematic structural installation diagram of an electric push rod of the intelligent nursing bed provided by the invention.
Fig. 3 is a block diagram of an implementation of the overall control provided by the present invention.
The labels in the figures are: 1-a first small bed board, 2-a second small bed board, 3-a third small bed board, 4-a fourth small bed board, 5-a fifth small bed board, 6-a sixth small bed board, 7-a seventh small bed board, 8-a bed frame, 9-a guardrail, 10-an electric push rod, 11-a controller and 12-a driver.
Detailed Description
In order to realize the functions of the invention, the following embodiment example will specifically describe an intelligent nursing bed system based on action intention recognition provided by the invention with reference to the attached drawings.
The invention relates to an intelligent bed system based on action intention recognition, which comprises a mechanical nursing bed main body, a pressure sensor module, an upper computer, a controller and a driver, wherein the mechanical nursing bed main body is connected with the pressure sensor module;
the nursing bed main body comprises a bed frame, a bed plate, a plurality of electric push rods and a driver, wherein the bed plate is formed by seven movably connected spliced small bed plates arranged on the bed frame, the guardrails are fixed on the bed frame and distributed around the bed plate, the electric push rods drive each small bed plate to act, the electric push rods are connected with the driver, the driver is simultaneously connected with the controller, and the controller is connected with a pressure sensing module and an upper computer;
the bed plate comprises a first small bed plate, a second small bed plate, a third small bed plate, a fourth small bed plate, a fifth small bed plate, a sixth small bed plate and a seventh small bed plate, wherein the seventh small bed plate supports the part below the shank of a human body, the first small bed plate, the second small bed plate and the third small bed plate are arranged side by side in the left-to-right sequence to support the upper half part of the human body, the fourth small bed plate, the fifth small bed plate and the sixth small bed plate are arranged side by side in the left-to-right sequence to support the waist part to the thigh part of the human body, and the first small bed plate, the second small bed plate and the third small bed plate provide supporting force when a person has the intention of getting up; when a person has an intention to turn over to the left, the first small bed plate and the fourth small bed plate provide supporting force, when the person has an intention to turn over to the right, the third small bed plate and the sixth small bed plate provide supporting force, and the second small bed plate and the fifth small bed plate provide stable areas when the person turns over; the seventh small bed board is used for helping the user to lift the legs so as to carry out leg activities;
the guardrails comprise a bed head guardrail, a bed tail guardrail and two side guardrails and are used for ensuring that the use safety of a user is protected;
the pressure sensor module is used for acquiring pressure change data of a user lying in real time, and is paved on a first small bed board-sixth small bed board area by adopting a flexible pressure sensor array;
the controller is internally loaded with an intention recognition algorithm and used for processing the collected pressure values, analyzing and recognizing the pressure data of the bed surface when a user has the intention of getting up and lying down, sending an action intention signal of the human body to the driver, controlling the electric push rod of the corresponding part of the bed plate and displaying the size change of the real-time pressure signal on the upper computer.
The driver comprises a control unit and a boosting device, the control unit is communicated with the controller through a serial port, the control unit is connected with the electric push rod through the boosting device, and an action signal of the controller is sent to the control unit of the driver through the serial port;
the boosting device amplifies the action intention signal received by the control unit to enable the voltage value to meet the voltage working range of the electric push rod, the voltage input of different electric push rods is connected to the output of the boosting device, when the boosting device outputs positive voltage, the part corresponding to the bed board identified by the action intention acts, and when the output voltage of the boosting device is 0, the electric push rod stops acting.
The use method of the system comprises the following steps:
1) sleeping posture recognition and intention recognition
Transmitting the pressure data acquired by the pressure sensor module to a controller, processing the sleeping posture pressure image by the controller, processing the sleeping posture pressure image to identify the sleeping posture and identify the type of the sleeping posture; after the sleeping posture type is identified, the human action intention is identified according to the dynamic change of the pressure data acquired by the pressure sensor module and by combining an intention identification algorithm in the controller; the sleeping posture types are six types, namely a supine type, a prone type, a right side lying fetus type, a right side lying tree trunk type, a left side lying fetus type and a left side lying tree trunk type;
2) dynamic weight detection
The dynamic weight data detected by the pressure sensor module is transmitted to the controller and processed by the controller, and the body movement states of the user, such as body turning, sitting up, getting out of bed and getting into bed, are identified;
3) sleeping posture adjustment
The controller comprehensively judges the state of the user according to the results of the sleeping posture identification and the dynamic weight detection, and when the sleeping posture of the user needs to be adjusted, the controller controls the small bed plate on the corresponding subarea to lift, incline at an angle and place horizontally, so that the user can automatically rise and lean to relieve pressure.
The intention recognition algorithm analyzes and recognizes the pressure data of the user bed surface and monitors whether the user has the intention of getting up or not, thereby being beneficial to assisting the user with inconvenient activities to get up and lie down.
The specific flow of the intention recognition algorithm is as follows:
step one, state judgment:
under normal operation, a minimum pressure threshold value and an effective area threshold value of lying are set, an upper computer collects data of a flexible pressure sensor in real time through a controller main control unit, if the collected pressure data are not larger than the minimum pressure threshold value of lying, or the area of the pressure sensor with the minimum pressure of 10% is smaller than the effective area threshold value of lying, the data are recorded as a state 1, the data collection mode collects data in a low-frequency low-consumption mode at the moment, the data collection frequency is adjusted to realize a low-consumption dormant state when no person is used or someone but no lying state is present, and the normal collection frequency is recovered when someone lies; otherwise, the acquired pressure data is greater than the lowest lying pressure threshold value, and meanwhile, the area of the pressure sensor at the lowest pressure of 10% is not less than the effective lying area threshold value, so that the situation that the user lies on the bed surface can be judged, the state is recorded as 2, and the data acquisition mode is adjusted to be the normal use mode;
secondly, positioning a lying area of a user:
performing Kalman filtering processing on the pressure sensor information acquired in the state 2 to eliminate signal interference; eliminating the interfered signals, generating a visual pressure distribution diagram by using LabVIEW according to corresponding coordinates of the LabVIEW in a sensor, adjusting the scanning speed by adjusting the serial port communication baud rate of a controller to obtain a real-time pressure distribution image, detecting the pressure variation amplitude of a user at any time in a state 2, and setting the current pressure distribution state as a normal lying state if the pressure variation amplitude is not more than 50% within 10 s;
then under the normal lying state, acquiring different pressure values on the horizontal and vertical units on the flexible pressure sensor, generating corresponding pressure distribution maps and positioning a lying area of a user;
for lying areas, positioning a spine according to a central axis of a human body structure rule, and carrying out significant area division on three head length positions as a waist, wherein the lying areas can significantly reflect the rising action intention of a sleeper, namely the upper half areas, namely the shoulder, the back and the waist;
when a person has the intention of getting up, the sacrospinous muscle in the body contracts to pull the person to raise the head, and then the flexors of the muscle groups of the abdominal muscles and the hip muscles contract to drive the upper half of the body to straighten, so that the whole getting up action is completed. In the course of this action, the pressure variation trend of the lying bed surface of the human body is very obvious, which is the key for judging whether the user has the intention of getting up. The user is not strong or difficult to move, the force provided by the body muscles is not enough to complete the rising action when the user intends to rise, but the pressure change signal is provided enough to tell the user's intention to rise.
Thirdly, monitoring the rising and lying intentions in real time
Monitoring and calculating the upper half body area by a preset identification algorithm, and indicating the intention of getting up or lying down when the pressure change proportion of the area exceeds the standard value of the algorithm; the specific flow of the recognition algorithm is as follows:
selecting a collected pressure area, setting the pressure value of +/-100 calculated by the area of each unit of the sensor and the pressure value when the sensor enters a normal lying state as an effective upper and lower limit threshold value of the point, comparing each value of the selected waist, back and shoulder areas with the effective threshold value, wherein the output of the effective upper limit threshold value which is more than or equal to the value is true, and the output of the effective lower limit threshold value which is less than or equal to the value is false; calculating the proportion of true output to false area pressure value;
setting the proportional coefficient of the rising state to be 0.5, comparing the ratio of the pressure value output as a True area to the pressure value output as a False area, when the ratio of the output True area to the output False area is larger than the proportional coefficient, the rising intention is considered, and when the ratio of the output True area to the output False area is equal to the proportional coefficient, the user is considered to be unresponsive, namely motionless; when the ratio of the output true area to the output false area is smaller than the scale factor, the user is considered to fall down, and therefore the identification of the rising intention of the user is judged.
The fourth step: memory learning
In use, the rising and lying sample data of the same user is continuously recorded, a corresponding sample classifier is set by using a machine learning algorithm, effective working data such as a pressure distribution state and an effective proportional coefficient when an intention is correctly recognized in the use process are recorded, an effective threshold value and a proportional coefficient of a rising and lying intention diagram are judged in a third step from an original rough standard continuously aiming at specific body parameters of the specific user, and the monitoring accuracy of the rising and lying intention is improved so as to adapt to the change of different conditions of the same user.
And when the user changes, restoring the effective threshold value and the proportionality coefficient for judging the rising intention to the initial coarse standard value in the third step, and optimizing data through machine learning.
The sleeping posture recognition in the invention is the prior art, and the machine learning algorithm can adopt the prior art, such as: the specific process of the machine learning algorithm is as follows:
and task T: correcting and obtaining rising scale factor more fitting to user
Performance annotation P: percentage of probability of correctly identifying intention to rise
Training experience E: recumbent data each time a person successfully stands up
When the system is used for the first time, the user can get up by himself or herself for five to ten times to simulate and provide the system as an initial sample library, and the system can make the user's intention of getting up in the initial sample library all be fed back correctly by finely adjusting the scale factor K of the state of getting up with the initial value of 0.5.
Assuming that the user shows that the set of all instances of the user' S intention to rise is D, the initial sample library is continuously added with the set of instances of the use sample library formed by successful data after use is S. K is the proportional coefficient of rising state, H (i) is whether the user has the intention of rising after each rising judgment (i belongs to S, 1 is present, 0 is absent).
Sample error rate error for sample S taken from DS(H (i)) is the proportion of instances of the hypothesis misclassification in S, i.e.
(δ (K, h (i)) is 1 when h (i) ═ 0, otherwise is 0). For true error rate error in DD(h (i)), the sample error rate has a 95% confidence. Setting conditions, selecting the rising state proportionality coefficient K value with the lowest error rate, and automatically adjusting the rising state proportionality coefficient K value according to the system, thereby realizing continuous optimization of the rising state proportionality coefficient and improving the rising intention identification precision.
The minimum pressure threshold value of lying and the effective area threshold value of lying in the method can be obtained through initial experiments for many times, the effective threshold value of the intention of getting up and the setting of the proportional coefficient can also be set according to the actual situation, and the updating and the correction can be carried out through a machine learning algorithm in the later period.
Example 1
The intelligent nursing bed system based on action intention recognition comprises a mechanical nursing bed main body, a pressure sensor module, an upper computer, a controller and a driver;
the nursing bed main body comprises a bed frame, a bed plate, a plurality of electric push rods and a driver, wherein the bed plate is formed by seven movably connected spliced small bed plates arranged on the bed frame, the guardrails are fixed on the bed frame and distributed around the bed plate, the electric push rods drive each small bed plate to act, the electric push rods are connected with the driver, the driver is simultaneously connected with the controller, and the controller is connected with a pressure sensing module and an upper computer;
the bed board comprises seven small bed boards which are respectively a first small bed board 1, a second small bed board 2, a third small bed board 3, a fourth small bed board 4, a fifth small bed board 5, a sixth small bed board 6 and a seventh small bed board 7, the small bed boards are movably connected through hinges, the seventh small bed board supports the part below the shank of the human body, the first small bed board, the second small bed board and the third small bed board are arranged side by side according to the sequence from left to right to support the upper half part of the human body, the fourth small bed board, the fifth small bed board and the sixth small bed board are arranged side by side according to the sequence from left to right to support the waist part to the thigh part of the human body,
the first small bed board, the second small bed board and the third small bed board are arranged to provide supporting force when a person has the intention to rise, so that the rising force of a user is greatly reduced; when a person has the intention of turning over to the left, the first small bed plate and the fourth small bed plate provide supporting force, when the person has the intention of turning over to the right, the third small bed plate and the sixth small bed plate provide supporting force to assist the user in turning over, the second small bed plate and the fifth small bed plate provide stable areas when the person turns over, the safety of the person in use is improved, and the person is prevented from sideslipping. The seventh footplate may assist the user in raising the legs for leg activity. The bed board subareas designed according to different functional requirements are the basis for free angle inclination of the small bed board.
The pressure sensor module is laid on the first small bed board-sixth small bed board area, is built based on a cross electrode type capacitor array, structurally comprises an upper buffer layer, a lower buffer layer and a pressure-sensitive sensor array arranged between the upper buffer layer and the lower buffer layer, and is made of flexible materials. The pressure sensor module is connected with the controller, and pressure change data of the user lying down is acquired in real time through the controller.
The guardrail 9 comprises a bed head guardrail, a bed tail guardrail and two side guardrails, and is used for ensuring that the use safety of a user is protected.
All install electric putter on different little bed board subregion, little bed board is connected to electric putter 10's one end, and the other end is installed on the bedstead, and electric putter internally mounted has the encoder, and the encoder links to each other with the inside motor spindle of motor putter, through the accurate feedback motor spindle number of turns of encoder pulse to the accurate electric putter stroke that calculates changes, realizes accurate control. An electric push rod of a corresponding area is arranged under each small bed plate partition. The extension length of the electric push rod and the lifting angle of the small bed plate are acquired through the encoder, the number of rotating circles of the motor in the electric push rod is acquired controllably, the action requirements of the small bed plates at different angles are met, and the actions of lifting, inclining and leveling the small bed plate of the nursing bed are completed.
The controller 11 adopts STM32F103ZET6 chip, is loaded with intention recognition algorithm in the controller, handles the pressure value that will gather, and the host computer shows the size change of real-time pressure signal. The controller analyzes and identifies the pressure data of the bed surface when the user has the intention of rising and lying, sends the action intention signal of the human body to the driver, and controls the push rod of the corresponding part of the bed body, thereby assisting the user with inconvenient activities to rise and lie, and lifting the body to an angle to relieve the body pressure.
Distributed pressure detection can be realized by collecting capacitance values of each capacitance unit of the pressure sensor module, pressure data are converted into data values which can be processed by the controller through an A/D converter in the controller, DMA transmission in the controller is started, the controller judges whether the current value of the timer is cleared, and if the current value of the timer is not cleared, the controller continuously judges whether the timer is cleared; if the timer value is cleared and the data sending command is received, DMA (direct memory access) transmission is carried out to transmit the current data to the serial port and send the current data to the LABVIEW upper computer through the serial port, so that the pressure value of the pressure sensor can be expressed in a pressure distribution graph in real time; when the serial port transmits data, the action intention recognition is carried out through an intention recognition algorithm preset in the controller, the action intention of the human body is determined, the intention is transmitted to the driver as an electric signal, and the signal is an action intention signal.
After the action intention signal is sent to the driver control unit, the signal is amplified and output through the boosting device, when the positive voltage is output, the control unit of the driver controls the electric push rod of the part corresponding to the bed body identified by the action intention to act, and finally the action of the small bed plate is finished.
In the embodiment, the length of the whole bed board is 2m, the width of the whole bed board is 0.9m, the thicknesses of the upper buffer layer and the lower buffer layer are both 5mm, the pressure sensor array is composed of 64 multiplied by 128 pressure-sensitive sensors, and the single pressure-sensitive sensor array of the soft bed fully ensures the comfort and the integrity of pressure images of a user in different sleeping postures.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, they should be construed as being within the scope of the present invention as long as they do not exceed the scope of the present invention as set forth in the appended claims.
Nothing in this specification is said to apply to the prior art.
Claims (4)
1. An intelligent bed system based on action intention recognition comprises a mechanical nursing bed main body, a pressure sensor module, an upper computer, a controller and a driver; the method is characterized in that:
the nursing bed main body comprises a bed frame, a bed plate formed by seven movably connected spliced small bed plates arranged on the bed frame, guardrails fixed on the bed frame and distributed around the bed plate, and a plurality of electric push rods for driving each small bed plate to act, wherein the plurality of electric push rods are connected with a driver, the driver is simultaneously connected with a controller, and the controller is connected with a pressure sensing module and an upper computer;
the bed plate comprises a first small bed plate, a second small bed plate, a third small bed plate, a fourth small bed plate, a fifth small bed plate, a sixth small bed plate and a seventh small bed plate, wherein the seventh small bed plate supports the part below the shank of a human body, the first small bed plate, the second small bed plate and the third small bed plate are arranged side by side in the left-to-right sequence to support the upper half part of the human body, the fourth small bed plate, the fifth small bed plate and the sixth small bed plate are arranged side by side in the left-to-right sequence to support the waist part to the thigh part of the human body, and the first small bed plate, the second small bed plate and the third small bed plate provide supporting force when a person has the intention of getting up; when a person has an intention to turn over to the left, the first small bed plate and the fourth small bed plate provide supporting force, when the person has an intention to turn over to the right, the third small bed plate and the sixth small bed plate provide supporting force, and the second small bed plate and the fifth small bed plate provide stable areas when the person turns over; the seventh small bed board is used for helping the user to lift the legs so as to carry out leg activities;
the pressure sensor module is used for acquiring pressure change data of a user lying in real time, and is paved on a first small bed board-sixth small bed board area by adopting a flexible pressure sensor array; the pressure sensor module is built based on a cross electrode type capacitor array, and structurally comprises an upper buffer layer, a lower buffer layer and a pressure sensor array arranged between the upper buffer layer and the lower buffer layer, wherein the thicknesses of the upper buffer layer and the lower buffer layer are both 5mm, and the pressure sensor array comprises 64 multiplied by 128 pressure sensors;
the controller is internally loaded with an intention recognition algorithm and is used for processing the acquired pressure value, analyzing and recognizing the pressure data of the bed surface when a user has an intention to rise and lie, sending an action intention signal of the human body to the driver, controlling the electric push rod of the corresponding part of the bed plate and displaying the size change of the real-time pressure signal on the upper computer;
the driver comprises a control unit and a boosting device, the control unit is communicated with the controller through a serial port, the control unit is connected with the electric push rod through the boosting device, and an action signal of the controller is sent to the control unit of the driver through the serial port;
the boosting device amplifies the action intention signal received by the control unit to enable the voltage value to meet the voltage working range of the electric push rod, the voltage input of different electric push rods is connected to the output of the boosting device, when the boosting device outputs positive voltage, the part corresponding to the bed board identified by the action intention acts, and when the output voltage of the boosting device is 0, the electric push rod stops acting;
the specific process of the intention recognition algorithm is as follows:
the detailed steps of the method are as follows:
step one, state judgment:
under normal operation, setting a minimum pressure threshold value and an effective area threshold value of lying, acquiring data of the flexible pressure sensor by the upper computer through the controller in real time, and recording as a state 1 if the acquired pressure data is not greater than the minimum pressure threshold value of lying, or the area of the pressure sensor, which is 10% of the minimum pressure threshold value of lying, is smaller than the effective area threshold value of lying, wherein the data acquisition mode carries out data acquisition in a low-frequency low-consumption mode at the moment, so that the low-consumption dormant state is realized when no person uses or someone but no lying; otherwise, the acquired pressure data is greater than the minimum pressure threshold value of lying, and meanwhile, the area of the pressure sensor at 10% of the minimum pressure is not less than the effective area threshold value of lying, so that the situation that the user lies on the bed surface can be judged, the situation is recorded as a state 2, and the data acquisition mode is adjusted to be the normal use mode;
secondly, positioning a lying area of a user:
performing Kalman filtering processing on the pressure sensor information acquired in the state 2; the signal after interference elimination constantly detects the pressure variation amplitude of the user in the state 2, and if the pressure variation amplitude is not more than 50% within 10s, the current pressure distribution state is set to be in a normal lying state;
then under the normal lying state, acquiring different pressure values on the horizontal and vertical units on the flexible pressure sensor, generating a corresponding pressure distribution map, and positioning a lying area of a user;
for lying areas, positioning a spine according to a central axis of a human body structure rule, and carrying out significant area division on three head length positions as a waist, wherein the lying areas can significantly reflect the rising action intention of a sleeper, namely the upper half areas, namely the shoulder, the back and the waist;
thirdly, monitoring the rising and lying intentions in real time:
monitoring and calculating the upper half body area by a preset identification algorithm, and indicating the intention of getting up or lying down when the pressure change proportion of the area exceeds the standard value of the algorithm; the specific flow of the recognition algorithm is as follows:
selecting a collected pressure area, setting the pressure value to be +/-100 Pa of the calculated pressure value of the area of each unit of the sensor and the pressure value when the sensor enters a normal lying state as an effective upper and lower limit threshold of the pressure value, comparing each value of the selected waist, back and shoulder areas with the effective threshold, wherein the output of the pressure value which is greater than or equal to the effective upper limit threshold is true, and the output of the pressure value which is less than or equal to the effective lower limit threshold is false; calculating the proportion of true output to false area pressure value;
setting the proportional coefficient of the rising state to be 0.5, comparing the ratio of the pressure value output as a True area to the pressure value output as a False area, when the ratio of the output True area to the output False area is larger than the proportional coefficient, the rising intention is considered, and when the ratio of the output True area to the output False area is equal to the proportional coefficient, the user is considered to be unresponsive, namely motionless; when the ratio of the output true area to the output false area is smaller than the scale factor, the user is considered to fall down; therefore, the identification of the rising intention of the user is judged;
the fourth step: memory learning
In use, the rising and lying sample data of the same user is continuously recorded, a corresponding sample classifier is set by using a machine learning algorithm, the data of effective work when the intention is correctly identified in the use process is recorded, the effective threshold value and the proportional coefficient of the rising intention are continuously judged in the third step of modifying and optimizing specific body parameters of the specific user from the original rough standard, and the monitoring accuracy of the rising and lying intention is improved.
2. The intelligent bed system based on action intention recognition of claim 1, wherein the control units of the controller and the driver both adopt STM32F103ZET6 chip.
3. A method for using the intelligent bed system based on action intention recognition as claimed in claim 1, the method comprises the following steps:
1) sleeping posture recognition and intention recognition
Transmitting the pressure data acquired by the pressure sensor module to a controller, processing the sleeping posture pressure image by the controller, processing the sleeping posture pressure image to identify the sleeping posture and identify the type of the sleeping posture; after the sleeping posture type is identified, the human action intention is identified according to the dynamic change of the pressure data acquired by the pressure sensor module and by combining an intention identification algorithm in the controller;
2) dynamic weight detection
Transmitting the dynamic weight data detected by the pressure sensor module to the controller, processing the dynamic weight data by the controller, and identifying the body movement state of the user;
3) sleeping posture adjustment
The controller comprehensively judges the state of the user according to the results of the sleeping posture identification and the dynamic weight detection, and when the sleeping posture of the user needs to be adjusted, the controller controls the small bed boards on the corresponding subareas to perform lifting, angle inclination and flat movements, so that the user can automatically rise and lean to relieve pressure.
4. The use method according to claim 3, wherein the sleeping posture types are six types, i.e. supine type, prone type, right side lying fetus type, right side lying trunk type, left side lying fetus type and left side lying trunk type.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910212283.9A CN109925136B (en) | 2019-03-20 | 2019-03-20 | Intelligent bed system based on action intention recognition and use method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910212283.9A CN109925136B (en) | 2019-03-20 | 2019-03-20 | Intelligent bed system based on action intention recognition and use method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109925136A CN109925136A (en) | 2019-06-25 |
| CN109925136B true CN109925136B (en) | 2021-08-10 |
Family
ID=66987701
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910212283.9A Active CN109925136B (en) | 2019-03-20 | 2019-03-20 | Intelligent bed system based on action intention recognition and use method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109925136B (en) |
Families Citing this family (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110584911A (en) * | 2019-09-20 | 2019-12-20 | 长春理工大学 | Intelligent nursing bed based on prone position recognition |
| CN213941232U (en) * | 2019-10-09 | 2021-08-13 | 希尔-罗姆服务公司 | Human supporting device |
| CN110693471A (en) * | 2019-10-15 | 2020-01-17 | 青岛护适通医疗科技有限公司 | Intelligent mattress |
| CN111000688A (en) * | 2019-12-04 | 2020-04-14 | 江苏第二师范学院（江苏省教育科学研究院） | Intelligent medical bed monitoring system |
| CN112618212B (en) * | 2020-12-26 | 2022-11-25 | 广州市立恒信息科技有限公司 | Multifunctional nursing bed body parameter regulation and control platform |
| CN113081557A (en) * | 2021-04-19 | 2021-07-09 | 联仁健康医疗大数据科技股份有限公司 | Multifunctional control method and system for health-care facility, medical robot and storage medium |
| CN113116341A (en) * | 2021-04-19 | 2021-07-16 | 联仁健康医疗大数据科技股份有限公司 | Health facility adjusting method and system, medical robot and storage medium |
| CN113499199A (en) * | 2021-08-13 | 2021-10-15 | 高庆 | Anti-pinch auxiliary getting-up device |
| CN114287924A (en) * | 2021-12-31 | 2022-04-08 | 杭州电子科技大学 | A method for detecting lying posture of a piezoelectric sensor and a nursing device using the same |
| CN115120438B (en) * | 2022-06-27 | 2023-12-22 | 贵阳市第二人民医院 | Bedside elevation angle indicating device for medical nursing bed |
| CN115429066B (en) * | 2022-10-24 | 2023-06-30 | 河北工业大学 | A method and system for recognizing the intention to get out of bed of an array airbag mattress |
| CN115944485A (en) * | 2023-02-10 | 2023-04-11 | 康辉医疗科技(苏州)有限公司 | Intelligent obstetric table |
| CN115944472B (en) * | 2023-02-13 | 2025-02-11 | 中国人民解放军陆军军医大学第一附属医院 | Intelligent turning pillow |
| CN116098415A (en) * | 2023-02-15 | 2023-05-12 | 北京声智科技有限公司 | Mattress adjusting device and mattress |
| CN116725789B (en) * | 2023-08-10 | 2023-11-03 | 中国人民解放军总医院第一医学中心 | Control method of nursing bed based on multi-sensor monitoring |
| CN118383966B (en) * | 2024-04-23 | 2024-11-15 | 深圳市麦驰信息技术有限公司 | An intelligent hospital bed and its dynamic pressure distribution monitoring and bedsore prevention system |
| CN118845466A (en) * | 2024-08-29 | 2024-10-29 | 青海藏红艾医疗器械科技有限责任公司 | Intelligent moxibustion control method and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105877712A (en) * | 2016-06-19 | 2016-08-24 | 河北工业大学 | Multifunctional intelligent bed system |
| CN205626336U (en) * | 2016-03-18 | 2016-10-12 | 青岛锐海柏信息技术有限公司 | Multifunctional intelligent caring bed |
| CN106056116A (en) * | 2016-05-31 | 2016-10-26 | 河北工业大学 | Fuzzy rough set-based sleeping posture pressure image recognition method |
| CN107136815A (en) * | 2017-05-17 | 2017-09-08 | 王志强 | Tele-control system based on intelligent bed |
| CN108392333A (en) * | 2018-02-06 | 2018-08-14 | 复旦大学附属中山医院 | A kind of induction type moving aid bed |
| CN108577349A (en) * | 2018-04-09 | 2018-09-28 | 大连理工大学 | Ergonomics intelligent bed and its application method based on perception-motor unit |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5887120A (en) * | 1995-05-31 | 1999-03-23 | Oracle Corporation | Method and apparatus for determining theme for discourse |
| JP2013173605A (en) * | 2012-02-27 | 2013-09-05 | Mitsubishi Electric Corp | Elevator control device |
| CN105380762B (en) * | 2014-09-05 | 2018-12-04 | 深圳市三分之一睡眠科技有限公司 | A kind of bed and its adjusting method of automatic adjustment |
| CN208388594U (en) * | 2017-08-23 | 2019-01-18 | 南京老人佳智能科技有限公司 | It is embedded in the bedding of sensor |
| CN208243255U (en) * | 2018-01-08 | 2018-12-18 | 燕山大学 | A kind of Intelligent cushion with sitting prompting and correcting sitting posture |
| CN109276415B (en) * | 2018-11-28 | 2020-12-22 | 河北工业大学 | Control method of lower limb exoskeleton robot |
-
2019
- 2019-03-20 CN CN201910212283.9A patent/CN109925136B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN205626336U (en) * | 2016-03-18 | 2016-10-12 | 青岛锐海柏信息技术有限公司 | Multifunctional intelligent caring bed |
| CN106056116A (en) * | 2016-05-31 | 2016-10-26 | 河北工业大学 | Fuzzy rough set-based sleeping posture pressure image recognition method |
| CN105877712A (en) * | 2016-06-19 | 2016-08-24 | 河北工业大学 | Multifunctional intelligent bed system |
| CN107136815A (en) * | 2017-05-17 | 2017-09-08 | 王志强 | Tele-control system based on intelligent bed |
| CN108392333A (en) * | 2018-02-06 | 2018-08-14 | 复旦大学附属中山医院 | A kind of induction type moving aid bed |
| CN108577349A (en) * | 2018-04-09 | 2018-09-28 | 大连理工大学 | Ergonomics intelligent bed and its application method based on perception-motor unit |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109925136A (en) | 2019-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109925136B (en) | Intelligent bed system based on action intention recognition and use method thereof | |
| US10127788B2 (en) | Estimation and monitoring of patient torso angle | |
| US9295600B2 (en) | Person support apparatus with activity and mobility sensing | |
| EP2508128B1 (en) | Person support apparatus with activity and mobility sensing | |
| CN204636903U (en) | A kind of intelligent rehabilitation is movable bed | |
| CN109833045B (en) | Rising intention monitoring method for intelligent nursing bed | |
| CN105877712A (en) | Multifunctional intelligent bed system | |
| CN106422172B (en) | Lower limb rehabilitation training system treadmill speed adaptive control method based on myoelectricity | |
| CN112867473A (en) | Intelligent bed system | |
| CN108392333A (en) | A kind of induction type moving aid bed | |
| CN110584911A (en) | Intelligent nursing bed based on prone position recognition | |
| EP3888543A1 (en) | Patient body monitoring using radar | |
| CN111714321B (en) | Mobile auxiliary device and system of integrated gravity measurement equipment | |
| CN105943277B (en) | A kind of bed body rollover system based on sleep detection | |
| CN108392343B (en) | Pressure sensitive mattress system | |
| CN107825469A (en) | A kind of both arms, which move, multiplies robot simulation's experiment porch and its method of testing | |
| CN113317937A (en) | Internet of things-based home-based auxiliary intelligent wheelchair for old people and control method | |
| CN107536311A (en) | Intelligent multifunctional seat system | |
| CN209677917U (en) | Intelligent electric bed | |
| CN210903764U (en) | Intelligent nursing bed based on lying posture recognition | |
| CN205729326U (en) | A kind of multifunctional intellectual bed system | |
| CN214387935U (en) | Multi-control intelligent monitoring system based on bed-chair integrated robot | |
| CN109984893A (en) | Medical detection data is shared and handles intelligent management robot system | |
| CN115645235A (en) | Multi-scenario-oriented intelligent lift system | |
| CN212490682U (en) | Motion detection system of lower limb robot for disabled people |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |