Anesthesia resuscitation intelligent nursing device and system based on artificial intelligence
Through the artificial intelligence-based anesthesia resuscitation intelligent care system, multiple sets of sensors are used to monitor vital signs and combine deep learning and machine learning algorithms, the problems of inaccurate monitoring and late warning during anesthesia resuscitation are solved, and accurate monitoring and timely early warning of the depth of anesthesia are achieved, ensuring the safety and resuscitation efficiency of patients.
Patent Information
- Application Number
- CN202510801024.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-16
- Publication Date
- 2025-08-12
AI Technical Summary
In the prior art, it is difficult to achieve accurate monitoring and timely early warning of patients during anesthesia resuscitation. Traditional methods rely on doctor experience and lack unified standards, resulting in inaccurate monitoring of anesthesia and inability to promptly warning of complications, increasing surgical risks and patient burden.
Anesthesia resuscitation intelligent care system is adopted based on artificial intelligence, including vital sign monitoring unit, shaking wake-up unit and artificial intelligence unit. Vital sign data is monitored in real time through multiple sets of sensors, deep learning models calculate anesthesia depth index, machine learning algorithms warn of hypotension and respiratory depression events, and shake-up awakening is performed through left and right activities of brackets.
Accurate monitoring and timely warning of the depth of anesthesia are achieved, the risks of surgery are reduced, the safety and efficiency of anesthesia are improved, and the safety and smoothness of the patient's resuscitation process is ensured.
Smart Images
Figure CN120458855A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of anesthesia resuscitation intelligent nursing technology, and in particular to anesthesia resuscitation intelligent nursing device and system based on artificial intelligence. Background Art
[0002] In the medical field, the anesthesia recovery phase is crucial for patient safety. Patients undergoing general anesthesia are prone to respiratory amnesia during resuscitation, often manifesting as a decrease in respiratory rate and a prolonged respiratory cycle. Respiratory amnesia can be difficult to detect, and prolonged amnesia can reduce the patient's ventilation, leading to hypoxemia and, in severe cases, death from respiratory failure. Mild cases of respiratory amnesia require prompt resuscitation through maneuvers such as shouting and shaking the patient's head. In more severe cases, measures such as pressurized mask-assisted ventilation and naloxone awakening are required. Currently, care for resuscitated patients is typically provided by medical staff or family members. However, medical staff have limited resources and, when simultaneously caring for multiple patients, struggle to maintain close attention to each resuscitated patient. Family members often lack professional medical judgment and are prone to oversight during manual care, resulting in a delay in resuscitating patients experiencing respiratory amnesia.
[0003] Furthermore, during anesthesia, traditional anesthetic decision-making relies heavily on physician experience and lacks unified standards, resulting in inconsistent treatment outcomes and difficulties ensuring patient safety. For example, while the traditional bispectral index (BIS) can reflect a patient's level of consciousness by analyzing brain electrical activity, anesthetic depth is also dependent on more complex physiological signals, such as drug concentration and heart rate variability. Therefore, relying solely on the BIS is insufficient to comprehensively and accurately monitor anesthetic depth. Regarding complication prediction, traditional methods exhibit significant lags, failing to provide timely warnings of anesthesia-related complications, increasing surgical risk and patient burden. With the rapid development of artificial intelligence (AI) technology, its application in the medical field is gaining increasing attention. Leveraging machine learning, deep learning, and intelligent algorithms, AI can accurately screen high-risk patients preoperatively, dynamically adjust anesthetic depth intraoperatively, and assist with postoperative recovery management, thereby improving anesthesia safety and efficiency. Against this backdrop, the development of an AI-based intelligent anesthesia and resuscitation care system and device is of great practical significance. Summary of the Invention
[0004] To address the shortcomings of the aforementioned background technology, a technical solution for an artificial intelligence-based anesthesia resuscitation intelligent nursing system is provided. The system comprises a vital signs monitoring unit, a shaking awakening unit, and an artificial intelligence unit. The vital signs monitoring unit comprises multiple sets of sensors that monitor vital signs during anesthesia. The shaking awakening unit comprises a bracket that supports the patient's head and neck, and a drive element that drives the bracket left and right.
[0005] The artificial intelligence unit consists of a computer and a deep learning model or machine learning algorithm built into the computer. The deep learning model integrates EEG spectrum characteristics, blood pressure fluctuations and drug metabolism dynamics data to calculate the depth of anesthesia index; the machine learning algorithm analyzes historical data to provide early warning of hypotension and respiratory depression events.
[0006] The technical solution of an artificial intelligence-based anesthesia resuscitation intelligent nursing device is also provided: it includes the following structural components: a human body function monitoring mechanism attached to the human body, and a linear shaking resuscitation mechanism fixed to the anesthesia bed;
[0007] The human body function monitoring mechanism includes a controller and a sensor assembly; wherein the sensor assembly includes 6-20 sensor wire harnesses fixedly connected to the data transmission end of the controller, and a plurality of electroencephalogram sensors, electrocardiogram sensors, blood pressure sensors, blood oxygen saturation sensors, respiratory rate sensors and myoelectric sensors fixed to the end of the sensor wire harness;
[0008] The linear shaking recovery mechanism includes a linear movable mechanism and a linear driving member fixed to the upper surface of the linear movable mechanism, and a head bracket fixed to the top surface of the linear driving member;
[0009] The linear movable mechanism includes a straight rod, fixed plates fixed to the left and right ends of the top surface of the straight rod, and a V-belt fixed between the fixed plates and passing through the linear drive member;
[0010] The head bracket includes a protective cover, an arc-shaped support plate fixedly connected to the top surface of the protective cover, and an arc-shaped silicone pad fixed to the upper surface of the arc-shaped support plate by an adhesive;
[0011] The linear drive component includes a backplate, four hollow tubes arranged on the front side of the backplate, and 8-10 rollers rotatably connected to each other in the hollow tubes, and the inner surface of the rollers is in rolling contact with the outer surface of the straight rod. The top surface of the backplate is fixedly connected to a servo motor, and a synchronous wheel is connected to the output shaft of the servo motor.
[0012] In the above technical solution, preferably: the electroencephalogram sensor, electrocardiogram sensor, blood pressure sensor, blood oxygen saturation sensor, respiratory rate sensor and electromyography sensor are respectively adhered to the surface of the human body to receive functional data of the human body during anesthesia.
[0013] In the above technical solution, preferably: the sensor harness is used to receive sensor data into the controller, and the data output end of the controller is connected to a computer.
[0014] In the above technical solution, preferably: the bottom surface of the straight rod is fixed on the anesthesia bed, and the V-belt is bent and wound around the outer ring surface of the synchronous wheel and the outer ring surface of the top roller.
[0015] In the above technical solution, preferably: the bottom surface of the protective cover is fixedly connected to the top surface of the back plate, and the protective cover covers the linear drive component.
[0016] In the above technical solution, preferably: a medical non-woven fabric is laid on the top surface of the arc-shaped silicone pad, and contacts the back of the head and the inner surface of the neck of the human body.
[0017] In the above technical solution, preferably: the hollow tubes are arranged in a rectangular array, and the hollow tubes are located at the four corners of the outer surface of the straight rod.
[0018] In the above technical solution, preferably: a bracket for supporting the servo motor is fixedly connected to the top surface of the back plate.
[0019] In the above technical solution, preferably: a control mainboard for controlling the rotation speed of the servo motor rotor is installed on the rear surface of the back plate.
[0020] As can be seen from the above technical solutions, the present invention provides an artificial intelligence-based anesthesia resuscitation intelligent nursing device and system. Compared with the prior art, the present invention has the following beneficial effects:
[0021] The multiple sets of sensors in the vital signs monitoring unit can comprehensively and in real time collect all kinds of vital signs data during anesthesia, providing a reliable basis for subsequent analysis. In the artificial intelligence unit, the deep learning model integrates multi-dimensional data to calculate the depth of anesthesia index, helping anesthesiologists to accurately adjust drug dosages; the machine learning algorithm analyzes historical data to provide early warning of events such as hypotension and respiratory depression, thereby reducing risks. The shaking awakening unit achieves shaking awakening through the left and right movement of the bracket, promoting patient resuscitation. In terms of the device, the sensors of the human body function monitoring mechanism have clear division of labor and accurately obtain functional data; the linear shaking resuscitation mechanism has a reasonable structure and can stably achieve shaking movements. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces and describes the drawings required for use in the embodiments of the present invention or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention, and those skilled in the art can derive other drawings based on these drawings without inventive effort.
[0023] Figure 1 This is a schematic diagram of the overall structure of the anesthesia recovery intelligent nursing device;
[0024] Figure 2 A schematic diagram of a human body function monitoring mechanism;
[0025] Figure 3 is a schematic diagram of the sensor assembly;
[0026] Figure 4 is a schematic diagram of the controller;
[0027] Figure 5 is a schematic diagram of the linear shaking resuscitation mechanism;
[0028] Figure 6 is a schematic diagram of the head bracket;
[0029] Figure 7 is a schematic diagram of a linear movable mechanism;
[0030] Figure 8 Schematic diagram of the linear drive component.
[0031] Attachment Figure 1 -Attached Figure 8 The corresponding relationship between the components is as follows:
[0032] 1. Human body function monitoring mechanism; 11. Controller; 12. Sensor assembly; 121. Sensor harness; 122. EEG sensor; 123. ECG sensor; 124. Blood pressure sensor; 125. Blood oxygen saturation sensor; 126. Respiratory rate sensor; 127. Myoelectric sensor; 2. Linear shaking resuscitation mechanism; 21. Linear movable mechanism; 211. Straight rod; 212. Fixed plate; 213. V-belt; 22. Head support; 221. Protective cover; 222. Arc support plate; 223. Arc silicone pad; 3. Linear drive component; 31. Back plate; 32. Servo motor; 33. Synchronous wheel; 34. Roller; 35. Hollow tube. DETAILED DESCRIPTION
[0033] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. In order to make a clearer explanation and description of the technical solutions and implementation methods of the present invention, the following introduces a preferred specific embodiment for implementing the technical solutions of the present invention.
[0034] Example 1: The vital signs monitoring unit utilizes multiple sets of high-precision sensors. The EEG sensor uses a 16-lead sensor from a US brand, which accurately captures the patient's EEG spectrum during anesthesia. A non-invasive continuous blood pressure monitor from a German company provides real-time blood pressure fluctuation data. Pharmacokinetic data is obtained through the hospital's information system, which records information such as the type, dosage, and administration time of anesthetic drugs used before and during surgery. Within the artificial intelligence unit, a deep learning model, built using the Python programming language and the TensorFlow framework, integrates these EEG spectrum features, blood pressure fluctuations, and pharmacokinetic data. After training with a large amount of anesthesia case data, it accurately calculates the depth of anesthesia index, which ranges from 0 to 100, with higher values indicating shallower anesthesia. The machine learning algorithm, using a support vector machine (SVM), analyzes historical data from anesthetized patients over the past five years, providing early warning of hypotension and respiratory depression events with an accuracy rate exceeding 90%. The bracket of the shaking awakening unit is made of ergonomic plastic material to support the patient's head and neck. The driving part is an electric push rod, which controls the extension and retraction of the electric push rod to achieve left and right movement of the bracket. The range of movement is ±15 cm and the frequency of movement is 10-15 times per minute.
[0035] In the intelligent anesthesia resuscitation care device based on this system, the controller 11 of the human body function monitoring mechanism 1 utilizes an industrial-grade single-chip microcomputer. The sensor assembly 12 comprises 12 sensor harnesses 121, each of which is secured to the end with an electroencephalogram (EEG) sensor 122, an electrocardiogram (ECG) sensor 123, a blood pressure sensor 124, a blood oxygen saturation (O2) sensor 125, a respiratory rate sensor 126, and an electromyography (EMG) sensor 127. The sensor harnesses 121 utilize shielded flexible cables to ensure stable data transmission. The linear movable mechanism 21 of the linear rocking resuscitation mechanism 2 comprises a 1.2-meter-long stainless steel rod 211 fixed to the anesthesia bed frame. The fixing plates 212 are made of aluminum alloy and bolted to the left and right ends of the top surface of the rod 211. The V-belt 213 is made of high-strength rubber and is wound around the outer surfaces of the synchronous pulley 33 and the top roller 34. The protective cover 221 of the head support 22 is made of plastic, the curved support plate 222 is made of wood, and the curved silicone pad 223 is 5 mm thick. The top surface is covered with medical non-woven fabric, and the back of the patient's head and neck contact the inner surface of the curved silicone pad 223. The back plate 31 of the linear actuator 3 is made of steel and welded to the side of the anesthesia bed. Hollow tubes 35 are arranged in a rectangular array at the four corners of the outer surface of the straight rod 211. The rollers 34 are made of rubber, and their inner surfaces roll in contact with the outer surface of the straight rod 211. The servo motor 32 is fixed to the top surface of the back plate 31 via a bracket. The synchronous pulley 33 connected to the output shaft drives the V-belt 213, achieving linear oscillation of the head support 22.
[0036] Example 2: In the vital signs monitoring unit, the EEG sensor is an 8-lead sensor that can quickly acquire EEG signals; the blood pressure sensor is a wrist-mounted blood pressure monitor, convenient for patients to wear; and pharmacokinetic data is obtained through integration with the hospital pharmacy system. The artificial intelligence unit's deep learning model is built on the PyTorch framework. After integrating data, it calculates the depth of anesthesia index, which is displayed in real time on the monitoring screen during surgery for easy observation by the anesthesiologist. The machine learning algorithm uses a random forest algorithm, trained on data from anesthetized patients in the hospital over the past three years. When hypotension or respiratory depression occurs, it alerts medical staff through both audio and on-screen prompts. The rocking wake-up unit's bracket is made of soft memory foam to enhance patient comfort. The drive element is a small stepper motor, which controls the rotation of the stepper motor to achieve left and right movement, with an amplitude of ±10 cm and a frequency of 8-12 times per minute.
[0037] In the intelligent anesthesia resuscitation care device based on this system, the controller 11 of the human body function monitoring mechanism 1 utilizes an embedded controller, and the sensor assembly 12 includes ten sensor harnesses 121, each of which is secured to the end with an electroencephalogram (EEG) sensor 122, an electrocardiogram (ECG) sensor 123, a blood pressure sensor 124, a blood oxygen saturation (OS) sensor 125, a respiratory rate sensor 126, and an electromyography (EMG) sensor 127. The sensor harnesses 121 utilize flat cables for easy organization and securement. In the linear movable mechanism 21 of the linear rocking resuscitation mechanism 2, the straight rod 211 is constructed of aluminum alloy, is one meter long, and is secured to the foot of the anesthesia bed. The fixing plates 212 are made of plastic and secured to the left and right ends of the top surface of the straight rod 211 via snaps. The triangular belt 213 is made of nylon and exhibits excellent wear resistance. The protective cover 221 of the head support 22 is made of acrylic, the curved support plate 222 is made of plastic, and the curved silicone pad 223 is 3 mm thick. The top surface is covered with medical non-woven fabric, and the back of the patient's head and neck come into contact with the inner surface of the curved silicone pad 223. The back plate 31 of the linear actuator 3 is made of aluminum alloy and bolted to the side of the anesthesia bed. Hollow tubes 35 are arranged in a rectangular array at the four corners of the outer surface of the straight rod 211. The rollers 34 are made of plastic, with their inner surfaces in rolling contact with the outer surface of the straight rod 211. The servo motor 32 is fixed to the top surface of the back plate 31 via a bracket. The synchronous pulley 33 connected to the output shaft drives the V-belt 213, achieving linear oscillation of the head support 22. A control board for controlling the rotational speed of the servo motor 32's rotor is mounted on the rear surface of the back plate 31, and parameters can be set via the touch screen.
[0038] Example 3: The sensors for the vital signs monitoring unit are economical products. The EEG sensor is a 4-lead sensor that meets basic monitoring needs. The blood pressure sensor is a finger-clip blood pressure monitor that is easy to operate. Pharmacokinetic data is acquired through manual recording and input into the system. The deep learning model of the artificial intelligence unit is built based on the Keras framework. After integrating the data, it calculates the depth of anesthesia index, which is displayed as a bar chart on the monitoring screen. The machine learning algorithm uses a decision tree algorithm, which learns from the hospital's anesthetized patients' data from the past year. When warning of hypotension or respiratory depression, it notifies medical staff by flashing an indicator light. The bracket of the shaking awakening unit is made of hard plastic wrapped in cotton material. The driving element is a manual joystick. Medical staff manually shake the joystick to move the bracket left and right, with an amplitude of ±5 cm and a frequency of 5-8 times per minute.
[0039] In the intelligent anesthesia resuscitation care device based on this system, the controller 11 of the human body function monitoring mechanism 1 utilizes a simple single-chip microcomputer, and the sensor assembly 12 comprises eight sensor harnesses 121, each of which is secured to the end with an electroencephalogram (EEG) sensor 122, an electrocardiogram (ECG) sensor 123, a blood pressure sensor 124, a blood oxygen saturation (O2) sensor 125, a respiratory rate sensor 126, and an electromyography (EMG) sensor 127. The sensor harnesses 121 utilize conventional cables, resulting in lower costs. In the linear movable mechanism 21 of the linear rocking resuscitation mechanism 2, the straight rod 211 is made of wood, 0.8 meters in length, and is fixed to the headboard of the anesthesia bed. The fixing plates 212 are also made of wood and are glued to the left and right ends of the top surface of the straight rod 211. The triangular belt 213 is made of cotton and exhibits a certain degree of elasticity. The protective cover 221 of the head support 22 is made of paper, the curved support plate 222 is made of wood, the curved silicone pad 223 is 2 mm thick, and the top surface is covered with medical non-woven fabric. The back of the patient's head and neck are in contact with the inner surface of the curved silicone pad 223. The back plate 31 of the linear drive 3 is made of wood and fixed to the side of the anesthesia bed with nails; the hollow tubes 35 are arranged in a rectangular array and are located at the four corners of the outer surface of the straight rod 211; the roller 34 is made of wood, and its inner surface is in rolling contact with the outer surface of the straight rod 211; the manual rocker is connected to the roller 34 via a shaft to achieve linear shaking of the head support 22.
[0040] According to the content of the preferred technical solution described above, the workflow of the technical solution is explained: during the surgical anesthesia stage, the human body function monitoring mechanism 1 starts working, and the electroencephalogram sensor 122, electrocardiogram sensor 123, blood pressure sensor 124, blood oxygen saturation sensor 125, respiratory rate sensor 126 and electromyography sensor 127 in the sensor assembly 12 are respectively adhered to the surface of the human body. These sensors collect functional data of the patient during anesthesia in real time, such as electroencephalogram signals, electrocardiogram waveforms, blood pressure values, blood oxygen saturation, respiratory rate and electromyography activity, etc. The sensor harness 121 transmits these data to the controller 11, and the controller 11 then outputs the data to the computer connected to the artificial intelligence unit.
[0041] After receiving this data, the deep learning model in the artificial intelligence unit integrates EEG spectrum characteristics, blood pressure fluctuations, and pharmacokinetic data (pharmacokinetic data is obtained and entered into the system through the hospital information system, pharmacy system connection, or manual recording) to calculate an anesthesia depth index. This index reflects the patient's current anesthesia depth state, and the anesthesiologist can adjust the dosage of anesthetic drugs based on this index. At the same time, the machine learning algorithm analyzes and learns from historical data. By mining a large amount of data on anesthesia patients, it can determine in advance whether the patient is likely to experience hypotension, respiratory depression, and other events. Once a potential risk is discovered, it will promptly issue an early warning signal to remind medical staff to take appropriate measures.
[0042] When the operation is over and enters the anesthesia recovery stage, the linear shaking recovery mechanism 2 begins to work. For the electric drive embodiment, the servo motor 32 is started under the control of the control motherboard, and its output shaft drives the synchronous wheel 33 to rotate. The V-belt 213 is bent and wrapped around the outer ring surface of the synchronous wheel 33 and the outer ring surface of the top roller 34. The movement of the V-belt 213 drives the linear drive component 3 as a whole to perform linear motion on the straight rod 211. Since the bottom surface of the protective cover 221 of the head bracket 22 is fixedly connected to the top surface of the back plate 31, the head bracket 22 will move with the linear drive component 3 to achieve a left and right shaking awakening action of the patient's head and neck. The activity amplitude and frequency are based on preset parameters to help the patient gradually regain consciousness; for the manual drive embodiment, the medical staff manually shakes the joystick, and the joystick drives the roller 34 to rotate through the shaft, thereby moving the V-belt 213 to achieve linear shaking of the head bracket 22. Throughout the entire process, the vital signs monitoring unit continuously monitors the patient's vital signs data, the artificial intelligence unit analyzes the data in real time and provides feedback on the anesthesia depth index and potential risk warnings, and the linear shaking resuscitation mechanism 2 performs shaking-type awakening operations in a timely manner according to the patient's resuscitation status. The three work together to ensure the safety and smoothness of the patient's anesthesia resuscitation process.
[0043] The present invention is not limited to the above-mentioned optimal implementation mode. Anyone should be aware that any structural changes made under the guidance of the present invention, and any technical solutions that are the same or similar to those of the present invention, fall within the scope of protection of the present invention. Finally, it should be noted that the structures, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification for people familiar with this technology to understand and read, and are not used to limit the conditions under which this application can be implemented. Therefore, they have no technical significance. Any structural modification, change in proportional relationship or adjustment of size, without affecting the efficacy and purpose that can be achieved by this application, should still fall within the scope of the technical content disclosed in this application.
Claims
1. An artificial intelligence-based anesthesia resuscitation intelligent nursing system, characterized by: It includes a vital signs monitoring unit, a shaking awakening unit, and an artificial intelligence unit; The vital signs monitoring unit is composed of multiple groups of sensors that monitor the vital signs data of the human body during anesthesia; The shaking awakening unit is composed of a bracket that supports the patient's head and neck, and a driving member that drives the bracket to move left and right; The artificial intelligence unit is composed of a computer and a deep learning model or machine learning algorithm built into the computer, wherein the deep learning model integrates EEG spectrum characteristics, blood pressure fluctuations and drug metabolism dynamics data to calculate the anesthesia depth index; The machine learning algorithm analyzes historical data to provide early warning of hypotension and respiratory depression events.
2. An artificial intelligence-based anesthesia resuscitation intelligent nursing device, characterized by: The anesthesia resuscitation intelligent nursing system based on artificial intelligence is applicable to any one of claim 1, and the anesthesia resuscitation intelligent nursing device comprises the following structural components: a human body function monitoring mechanism (1) attached to the human body, and a linear shaking resuscitation mechanism (2) fixed on the anesthesia bed; The human body function monitoring mechanism (1) includes a controller (11) and a sensor assembly (12); wherein the sensor assembly (12) includes 6-20 sensor harnesses (121) fixedly connected to a data transmission end of the controller (11), and a plurality of electroencephalogram (EEG) sensors (122), electrocardiogram (ECG) sensors (123), blood pressure sensors (124), blood oxygen saturation sensors (125), respiratory rate sensors (126), and myoelectric sensors (127) fixed to the end of the sensor harness (121); The linear shaking recovery mechanism (2) includes a linear movable mechanism (21), a linear driving member (3) fixed on the upper surface of the linear movable mechanism (21), and a head bracket (22) fixed on the top surface of the linear driving member (3); The linear movable mechanism (21) includes a straight rod (211), fixed plates (212) fixed to the left and right ends of the top surface of the straight rod (211), and a V-belt (213) fixed between the fixed plates (212) and passing through the linear drive member (3); The head bracket (22) includes a protective cover (221), an arc-shaped support plate (222) fixedly connected to the top surface of the protective cover (221), and an arc-shaped silicone pad (223) fixed to the upper surface of the arc-shaped support plate (222) by an adhesive; The linear drive member (3) includes a back plate (31), four hollow tubes (35) arranged on the front side of the back plate (31), and 8-10 rollers (34) rotatably connected to each other between the hollow tubes (35), and the inner surface of the roller (34) is in rolling contact with the outer surface of the straight rod (211). The top surface of the back plate (31) is fixedly connected to a servo motor (32), and the output shaft of the servo motor (32) is connected to a synchronous wheel (33).
3. The artificial intelligence-based anesthesia resuscitation intelligent nursing device according to claim 2, characterized in that: The electroencephalogram sensor (122), electrocardiogram sensor (123), blood pressure sensor (124), blood oxygen saturation sensor (125), respiratory rate sensor (126) and myoelectric sensor (127) are respectively adhered to the surface of the human body and are used to receive functional data of the human body during anesthesia.
4. The artificial intelligence-based anesthesia resuscitation intelligent nursing device according to claim 2, characterized in that: The sensor harness (121) is used to receive sensor data into the controller (11), and the data output end of the controller (11) is connected to a computer.
5. The artificial intelligence-based anesthesia resuscitation intelligent nursing device according to claim 2, characterized in that: The bottom surface of the straight rod (211) is fixed on the anesthesia bed, and the triangular belt (213) is bent and wound around the outer ring surface of the synchronous wheel (33) and the outer ring surface of the top roller (34).
6. The artificial intelligence-based anesthesia resuscitation intelligent nursing device according to claim 2, characterized in that: The bottom surface of the protective cover (221) is fixedly connected to the top surface of the back plate (31), and the protective cover (221) covers the linear drive member (3).
7. The artificial intelligence-based anesthesia resuscitation intelligent nursing device according to claim 2, characterized in that: The top surface of the arc-shaped silicone pad (223) is covered with medical non-woven fabric, and the back of the head and the neck of the human body are in contact with the inner surface of (233).
8. The artificial intelligence-based anesthesia resuscitation intelligent nursing device according to claim 2, characterized in that: The hollow tubes (35) are arranged in a rectangular array, and the hollow tubes (35) are located at the four corners of the outer surface of the straight rod (211).
9. The artificial intelligence-based anesthesia resuscitation intelligent nursing device according to claim 2, characterized in that: A bracket for supporting a servo motor (32) is fixedly connected to the top surface of the back plate (31).
10. The artificial intelligence-based anesthesia resuscitation intelligent nursing device according to claim 2, characterized in that: A control mainboard for controlling the rotation speed of the rotor of the servo motor (32) is installed on the rear surface of the back plate (31).