WO2022142271A1 - 面向高传染性隔离病区的全方位智能护理***及方法 - Google Patents
面向高传染性隔离病区的全方位智能护理***及方法 Download PDFInfo
- Publication number
- WO2022142271A1 WO2022142271A1 PCT/CN2021/106859 CN2021106859W WO2022142271A1 WO 2022142271 A1 WO2022142271 A1 WO 2022142271A1 CN 2021106859 W CN2021106859 W CN 2021106859W WO 2022142271 A1 WO2022142271 A1 WO 2022142271A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- nursing
- robot
- remote control
- control system
- isolation ward
- Prior art date
Links
- 230000000474 nursing effect Effects 0.000 title claims abstract description 167
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000002955 isolation Methods 0.000 title claims abstract description 45
- 238000004891 communication Methods 0.000 claims abstract description 24
- 238000003066 decision tree Methods 0.000 claims abstract description 22
- 230000009471 action Effects 0.000 claims abstract description 18
- 230000007246 mechanism Effects 0.000 claims abstract description 11
- 238000000605 extraction Methods 0.000 claims abstract description 6
- 230000008569 process Effects 0.000 claims description 27
- 238000001514 detection method Methods 0.000 claims description 26
- 208000015181 infectious disease Diseases 0.000 claims description 23
- 230000006870 function Effects 0.000 claims description 17
- 230000005540 biological transmission Effects 0.000 claims description 12
- 230000002787 reinforcement Effects 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 10
- 238000011156 evaluation Methods 0.000 claims description 8
- 230000002458 infectious effect Effects 0.000 claims description 8
- 239000012535 impurity Substances 0.000 claims description 7
- 239000000463 material Substances 0.000 claims description 7
- 230000033001 locomotion Effects 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 230000036772 blood pressure Effects 0.000 claims description 5
- 239000000284 extract Substances 0.000 claims description 5
- 206010061818 Disease progression Diseases 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 3
- 230000005750 disease progression Effects 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 230000035485 pulse pressure Effects 0.000 claims description 2
- 208000035473 Communicable disease Diseases 0.000 abstract description 15
- 238000010586 diagram Methods 0.000 description 14
- 201000010099 disease Diseases 0.000 description 9
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 9
- 230000001681 protective effect Effects 0.000 description 9
- 238000012544 monitoring process Methods 0.000 description 8
- 238000003860 storage Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000003745 diagnosis Methods 0.000 description 7
- 238000007726 management method Methods 0.000 description 7
- 238000005070 sampling Methods 0.000 description 7
- 239000007924 injection Substances 0.000 description 5
- 238000002347 injection Methods 0.000 description 5
- 241000711573 Coronaviridae Species 0.000 description 4
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 4
- 244000052616 bacterial pathogen Species 0.000 description 4
- 239000003153 chemical reaction reagent Substances 0.000 description 4
- 238000004140 cleaning Methods 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 4
- 229910052760 oxygen Inorganic materials 0.000 description 4
- 239000001301 oxygen Substances 0.000 description 4
- 229920000742 Cotton Polymers 0.000 description 3
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 3
- 230000006399 behavior Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 229910052744 lithium Inorganic materials 0.000 description 3
- 239000012567 medical material Substances 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000011084 recovery Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 206010011409 Cross infection Diseases 0.000 description 2
- 206010029803 Nosocomial infection Diseases 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000003542 behavioural effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000036760 body temperature Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 239000000645 desinfectant Substances 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 229940079593 drug Drugs 0.000 description 2
- 238000012377 drug delivery Methods 0.000 description 2
- 238000009513 drug distribution Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000003331 infrared imaging Methods 0.000 description 2
- 210000000214 mouth Anatomy 0.000 description 2
- 239000000243 solution Substances 0.000 description 2
- 239000007921 spray Substances 0.000 description 2
- 238000004659 sterilization and disinfection Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000002792 vascular Effects 0.000 description 2
- 229920000049 Carbon (fiber) Polymers 0.000 description 1
- 206010008631 Cholera Diseases 0.000 description 1
- 206010011224 Cough Diseases 0.000 description 1
- 208000028399 Critical Illness Diseases 0.000 description 1
- 206010035148 Plague Diseases 0.000 description 1
- 206010047700 Vomiting Diseases 0.000 description 1
- 241000607479 Yersinia pestis Species 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 206010064097 avian influenza Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 210000004204 blood vessel Anatomy 0.000 description 1
- 210000001124 body fluid Anatomy 0.000 description 1
- 239000010839 body fluid Substances 0.000 description 1
- 239000004917 carbon fiber Substances 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 230000009352 congenital transmission Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000249 desinfective effect Effects 0.000 description 1
- 230000006806 disease prevention Effects 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 210000000245 forearm Anatomy 0.000 description 1
- 231100001261 hazardous Toxicity 0.000 description 1
- 210000003128 head Anatomy 0.000 description 1
- 238000010253 intravenous injection Methods 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 230000009916 joint effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 229920000642 polymer Polymers 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 230000005180 public health Effects 0.000 description 1
- 230000002685 pulmonary effect Effects 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 230000000241 respiratory effect Effects 0.000 description 1
- 210000002345 respiratory system Anatomy 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 238000010863 targeted diagnosis Methods 0.000 description 1
- 238000001931 thermography Methods 0.000 description 1
- 210000003462 vein Anatomy 0.000 description 1
- 230000005570 vertical transmission Effects 0.000 description 1
- 230000008673 vomiting Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J11/00—Manipulators not otherwise provided for
- B25J11/008—Manipulators for service tasks
- B25J11/009—Nursing, e.g. carrying sick persons, pushing wheelchairs, distributing drugs
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J15/00—Gripping heads and other end effectors
- B25J15/0009—Gripping heads and other end effectors comprising multi-articulated fingers, e.g. resembling a human hand
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
- B25J19/02—Sensing devices
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J5/00—Manipulators mounted on wheels or on carriages
- B25J5/005—Manipulators mounted on wheels or on carriages mounted on endless tracks or belts
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1602—Programme controls characterised by the control system, structure, architecture
- B25J9/161—Hardware, e.g. neural networks, fuzzy logic, interfaces, processor
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1628—Programme controls characterised by the control loop
- B25J9/163—Programme controls characterised by the control loop learning, adaptive, model based, rule based expert control
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1679—Programme controls characterised by the tasks executed
- B25J9/1689—Teleoperation
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
Definitions
- the present disclosure belongs to the field of artificial intelligence pattern recognition, and relates to an all-round intelligent nursing system and method for highly infectious isolation wards.
- Infectious diseases can be transmitted by direct contact with infected individuals, body fluids or excrement of infected people, and objects contaminated by infected people, and can also be transmitted through air, water, food, contact, soil, and vertical transmission ( mother-to-child transmission), etc.
- pulmonary infectious diseases which are transmitted through the air and through the respiratory tract, have the typical characteristics of strong infectivity and fast transmission, and usually cause cluster outbreaks in hospitals, schools, public transportation systems and other places, resulting in The number of patients has surged, causing a serious public health emergency.
- the present disclosure proposes an all-round intelligent nursing system and method for highly contagious isolation wards.
- the present disclosure can realize the ability to autonomously or accept remote A comprehensive nursing robot architecture that completes tasks such as drug distribution, diagnostic reagent retrieval and delivery, injection, etc., and monitors patients' conditions in real time, adjusts the nursing level, and makes intelligent decisions.
- the present disclosure adopts the following technical solutions:
- An all-round intelligent nursing system for highly infectious isolation wards including a remote control system, a communication network, several collectors and nursing robots, wherein:
- the nursing robot includes a robot body and a controller, and the controller controls the walking mechanism and the mechanical arm of the robot body according to the received remote control instructions;
- the collector is arranged in the isolation ward and is used to detect the physiological indicators of the user and transmit them to the remote control system;
- the communication network is a star topology, including a plurality of communication modules, configured to realize the communication between each nursing robot, the collector and the remote control system;
- the remote control system receives the information of the collector, performs feature extraction on the collected multiple physiological signals, combines the basic information of the user, uses the decision tree model to learn, dynamically adjusts the corresponding nursing level, and sends instructions to the corresponding nursing staff. Nursing robot.
- the robot body is provided with a camera
- the controller is configured to receive data collected by the camera, complete real-time object video detection according to a target detection algorithm, and generate corresponding instructions to the walking mechanism, for autonomous driving.
- a robotic palm is provided on the robotic arm, and a pressure sensor and an infrared sensor are provided on the robotic palm.
- the robot body is provided with a storage space for storing nursing supplies.
- the communication network is centered on a remote control system, and communication modules are set at different positions in the isolation ward and on each nursing robot, and backup links are established between different nursing robots. If the information transmission between the robot and the remote control system is not smooth, open the backup link and interact with the remote control system through another nursing robot.
- the working method based on the above system includes the following steps:
- the nursing robot moves to the corresponding position in the isolation ward according to the received instructions, and provides the user with corresponding nursing materials and nursing actions.
- the controller uses a reinforcement learning algorithm to optimize the action of the manipulator, and reinforcement learning is implemented through strategy iteration.
- an action execution strategy is given, and the iterative Bellman equation is used to obtain the value function of the strategy , and then update the policy through the value function, adjust the value function according to the evaluation, recalculate the value function, and cycle until the policy converges, until it converges to an optimal value function and policy.
- the present disclosure provides medical-free infectious disease isolation wards.
- the comprehensive nursing robot on-site nursing and the remote guidance of professional physicians are adopted.
- the infected individuals and healthy personnel can be completely shielded and the transmission route is effectively guaranteed. the safety of medical staff.
- the nursing robot completes self-cleaning through ultraviolet irradiation or disinfectant spray to avoid the attachment of germs.
- the robot is a non-biological individual and will not become an intermediate host of germs, which effectively avoids cross-infection caused by contact with different patients in the nursing process.
- the present disclosure adopts the deep learning target detection YOLO algorithm based on the regression method, and only one convolutional neural network (CNN) can be used to determine the categories and positions of different targets.
- the object detection is modeled as a regression problem for processing.
- the detection process only contains a neural network, which optimizes the detection performance in an end-to-end manner, while obtaining faster objects. detection rate.
- more abstract features can be learned, which improves the ability to identify specific targets in complex scenarios of isolation wards.
- FIG. 1 Application scenario diagram of comprehensive nursing intelligent robot
- FIG. 1 The flow chart of the task automation management of the comprehensive nursing intelligent robot
- Fig. 4 Mechanical structure diagram of comprehensive nursing intelligent robot
- Figure 5 The principle diagram of the comprehensive nursing robot nursing level intelligent decision-making
- Figure 6 is a structural diagram of the information exchange network in the intelligent ward
- Figure 8 is a schematic diagram of the nursing action self-improvement algorithm based on reinforcement learning
- Figure 9 is a structural frame diagram of an intelligent cruise system based on the YOLO algorithm
- Figure 10 is a schematic diagram of object-oriented control software design
- Fig. 11 is the algorithm flow chart of nursing level self-decision system based on ensemble learning
- a series of tasks such as patient interaction and symptom monitoring can effectively protect susceptible populations; at the same time, the contact between medical staff and patients to varying degrees in the traditional nursing process is completely avoided, and the transmission route is completely cut off to ensure the safety of medical staff in an all-round way, and avoid medical staff and patients. spread of the disease caused by contact.
- an all-round intelligent nursing system for highly infectious isolation wards includes a remote control system, a communication network, several collectors and nursing robots, wherein:
- the nursing robot includes a robot body and a controller, and the controller controls the movement of the walking mechanism and the mechanical arm of the robot body according to the received remote control instructions;
- the collector is arranged in the isolation ward and is used to detect the physiological indicators of the user and transmit them to the remote control system;
- the communication network is a star topology, including a plurality of communication modules, configured to realize the communication between each nursing robot, the collector and the remote control system;
- the remote control system receives the information of the collector, performs feature extraction on the collected multiple physiological signals, combines the basic information of the user, uses the decision tree model to learn, dynamically adjusts the corresponding nursing level, and sends instructions to the corresponding nursing staff. Nursing robot.
- the nursing robot uses lithium batteries to power the robot.
- the advantages of high energy density, large capacity, and no memory it can complete fast charging on a 220V household power supply, and can achieve high reliability and long-distance endurance. Satisfied with the effect.
- the circular queue method is used to complete the comprehensive management of the nursing affairs of patients in the whole ward, and the transactions stored in the memory space are implemented one by one according to the chronological order, so as to make full use of the storage space and avoid the occurrence of "false overflow".
- Medical staff use the remote control platform to add patients and targeted diagnosis and treatment measures to the intelligent system, and the instructions are transmitted wirelessly based on different IoT communication standards such as WiFi, 5G, Bluetooth, Zigbee, etc.
- the intelligent nursing robot in the isolation ward begins Perform nursing operations, and at the same time, the robot can also send the monitored video-based patient dynamic information to the remote monitoring platform through wireless transmission, so as to complete the doctor's visit and the doctor-patient interaction.
- the intelligent nursing robot accepts the task through the command center, it completes the handover of medical materials with specialized medical staff in the sterile warehouse, and automatically plans the route based on the coordinates of the target patient's bed in the task queue.
- the camera installed on the wheeled base is used in combination with the relevant target detection algorithm to complete the real-time object video detection to realize automatic driving.
- the wheeled base is driven by lithium batteries, and the multi-drive crawler structure has the characteristics of good stability and strong power. Compared with the leg-shaped mechanical structure, it can effectively overcome the damage of medical items caused by bumps during walking, and can adapt to the stairs in the ward, Special road conditions such as thresholds.
- Use the infrared sensor installed on the side of the wheeled base to sense surrounding objects, and change the route in time to avoid collision when encountering obstacles.
- a robotic arm with six degrees of freedom is installed on the wheeled base, and a robotic palm is installed at the end of the arm.
- the arm and the palm are driven by lithium batteries, and rely on motors and solenoids as transmission devices.
- the robotic palm is equipped with a built-in pressure sensor, which can transmit the force to the central processing chip in real time when grasping or moving objects, which can effectively prevent the cotton swab from falling or the bag of medical reagents being squeezed. Taking the care of patients infected with the new coronavirus as an example, after the wheeled base travels to the task area, the robotic arm will be activated.
- the robot can choose the existing nursing robot.
- joint motion is the basic unit for intelligent manipulators to complete complex nursing tasks during mechanical joint activity control. Determining the target distance and accurately judging whether the joint rotation scale meets the task completion requirements is the standard process for realizing joint intelligence. As shown in Figure 7, it is an intelligent control process of joint rotation with independent action.
- the infrared sensor on the side of the palm emits an infrared beam to the target, and the distance is judged according to the reflected light.
- a light-emitting diode, a rotating bearing and a light sensor are installed in the joint. After the bearing starts to rotate, the light-emitting diode emits light through the groove on the bearing and irradiates the light sensor.
- the light sensor can read the periodic light flashing pattern with the rotation of the bearing.
- the robotic arm can carry out the nursing process of grabbing throat swabs, sampling and recycling them in the oral cavity and throat.
- the venous blood vessel imaging of the human arm is obtained through the thermal infrared imaging device installed on the outside of the robotic arm, and the thermal imaging picture is sent to the central processor of the nursing robot, and the appropriate one is selected according to the picture.
- the venipuncture operation is performed according to the determined puncture point.
- completing operations such as throat swab sampling and venipuncture requires not only professional training but also a certain period of clinical practice.
- the oral swab of the throat swab can be wiped during the repeated operation of the robotic arm.
- venous needle puncture angle, puncture depth and other technical indicators are constantly revised to strengthen the rationality and standardization of nursing actions.
- the reinforcement learning algorithm can be used to continuously interact with the external environment in the process of task execution. Mapping relationship to optimize the action. As shown in Figure 8, taking venipuncture as an example, the robot can continuously improve the puncture angle, depth and other action plans to adapt to the task object during the nursing process of action, evaluation, improvement, and re-action. Reinforcement learning is implemented through strategy iteration. First, an action execution strategy is given, the value function of the strategy is obtained by using the iterative Bellman equation, and then the strategy is updated through the value function.
- the ⁇ -greedy strategy in Figure 8 which represents the depth of venipuncture, refers to selecting the behavior that can obtain the greatest satisfaction with the probability of ⁇ , and randomly selecting the action mode with the probability of 1- ⁇ .
- the value function is recalculated, and the loop is repeated until the policy converges.
- the iterative process will eventually converge to an optimal value function V * (s) and policy ⁇ * , indicating that the action strategy has been able to meet the requirements of clinical practice.
- the YOLO algorithm is used to control the nursing robot to automatically find the target of the task patient, and make real-time decisions through the top camera device in the process of driving to the execution area to ensure that there is no obstacle such as other pedestrians or objects. Contact causes collision.
- the target detection is modeled as a regression problem for processing, and an end-to-end network structure is used to complete the process from the input of the camera image to the position of the object and the output of the category.
- the YOLO network is based on the GoogLeNet network structure. As shown in Figure 9, the Inception module is replaced by a 1 ⁇ 1+3 ⁇ 3 convolutional layer to complete cross-channel information integration.
- the convolutional layer is used to extract features, and the fully connected layer is used to predict the probability and position of objects in the scene, and guide the driving route. Different from the target recognition methods of sliding window and area detection, the strategy of using the whole image as scene information further reduces the detection error rate.
- the object-oriented software design method can use the model organization form close to the real world to complete the program structure.
- this embodiment adopts the strategy of simplifying complexity, summarizes specific nursing objects (patients), extracts the common properties of such objects and describes them, and constructs a patient class. It includes two steps: data abstraction and behavioral abstraction. Patients share basic information such as age, gender, pulse, blood pressure, blood oxygen saturation, etc., which are defined as class attributes to complete data abstraction. Intelligent robots need to perform operations on patients at different times. Specific nursing operations, such as drug delivery, throat swab sampling, venipuncture, etc., are defined as methods to complete behavioral abstraction.
- the patient class is instantiated as a specific patient object.
- the intelligent robot evaluates the patient's condition based on the patient's attributes, and performs nursing work on the patient based on the abstracted behavior of the patient object.
- the management of nursing tasks is carried out in a circular queue structure, using a continuous physical storage structure to form a ring-shaped logical space.
- the head of the team will leave the team when the nursing task is completed, and new nursing tasks will be added to the team from the end of the team, effectively saving storage resources and preventing false overflow. happened.
- the nursing robot reads the task units arranged in time sequence in the circular queue in sequence, and executes nursing modules such as drug delivery and injection, and can complete one-to-many nursing work in an orderly manner within a duty cycle.
- infectious diseases In terms of nursing-level decision-making based on ensemble learning, infectious diseases generally have the characteristics of rapid disease changes and rapid progress. Under the condition of manual nursing, the physician should not only be able to make a correct judgment on the condition of the patient according to the overall situation of the patient, but also have a strong ability to deal with the disease on the spot, and must have considerable clinical experience. During the epidemic period, due to the surge in the number of patients, there is a shortage of nursing physicians with rich clinical experience. Inappropriate diagnosis and evaluation will lead to excessive treatment or delay of treatment timing. The existing automated medical monitoring equipment only provides some physiological data of the patient to the nursing physician, and the condition is evaluated manually, which still relies on the clinical experience of the physician, or the data is mechanically input into the mathematical formula established in a model-driven manner. A rough assessment completely ignores the existence of individual differences in patients.
- Each node in the decision tree has an impurity, and the impurity of the child node is lower than that of the parent node, that is, the significance of the attributes of the parent node in the discrimination degree of nursing level is higher than that of the child node.
- t represents a given node
- i represents the level of care
- t) represents the sample size that reaches the level of care i under the condition of attribute t.
- Figure 11b shows the algorithm flow of constructing a single decision tree. When all the features are used, the overall impurity reaches the optimum, that is, the optimal diagnosis decision-making scheme is obtained, and the cycle ends.
- the average value, standard deviation, low frequency power, high frequency power, moving standard deviation and other characteristics of the patient's heart rate, pulse, blood pressure and other information will be collected, and the patient's age, gender, disease time, and disease progression will be extracted. Stages and other individualized information are input into the integrated learning module in the remote platform to obtain a real-time nursing level adjustment plan, which is fed back to the robot in the isolation ward to guide the completion of nursing tasks.
- a doctor in the remote monitoring room completes disease monitoring and nursing tasks
- a nurse in the sterile warehouse completes the delivery of medical materials
- several intelligent nursing robots in the ward complete specific nursing tasks, which can be achieved in one duty cycle.
- the traditional nursing method has large-scale requirements for the staffing of medical staff.
- a critically ill patient usually requires multiple nursing staff to take care of it at the same time.
- the management model of the isolation ward without a doctor realizes the nursing method from one-to-one to one-to-one.
- it is a more ideal localized emergency response method under the background of the sudden increase of patients with epidemic outbreaks, which effectively alleviates the problem of insufficient medical staff.
- the nursing robot uses task management software to make overall arrangements for nursing work for multiple patients.
- the management software is embedded in the robot's built-in chip, and the client is installed in the remote data terminal, which can adapt to Windows, Lunix , Unix, Android, Apple and other operating systems, one computer and one CD-ROM can complete the construction of the remote nursing command center, and the simple and convenient workflow fully adapts to the time constraints and the lack of personnel and materials in the emergency situation of the epidemic. .
- the object-oriented development method can effectively improve the programming efficiency. It can not only use a fixed management program mode, but also design a targeted intelligent nursing team integrated management platform for special types of isolation ward scenarios in a short period of time after the outbreak.
- the program has the characteristics of good reusability, flexibility and extensibility.
- a circular queue structure is used to coordinate the deployment of nursing affairs. On the basis of ensuring the orderly development of tasks, it can effectively avoid transaction congestion and improve storage space utilization.
- the nursing robot can complete a series of complex nursing operations without the on-site participation of medical personnel.
- the robotic palm has twelve degrees of freedom, which can complete actions such as grasping, turning, touching, pressing, etc.
- the infrared sensor installed on the outside of the palm to determine the target distance, it can grab a cotton swab and extend it into the patient at close range.
- the throat is wiped, and the cotton swab is placed in the recovery bin.
- a protective film made of polymer carbon fiber material attached to the palm surface, which not only has the characteristics of high temperature resistance and wear resistance, but also can complete the surface sterilization and disinfection through the circulating self-cleaning mechanism to avoid the attachment of infectious substances, and there is no need to replace the protective gloves.
- Multiple collections are carried out under the hood, reducing manpower and saving consumables. Infectious disease care requires wearing heavy isolation protective clothing, which increases the difficulty of artificial venipuncture.
- An infrared vascular imaging sensor is installed on the side of the robotic arm, which can obtain the venous structure of the patient's forearm, guide the movement of the robotic palm, and complete the venipuncture operation.
- the reinforcement learning algorithm is implanted into the control program, and through the cyclic iteration of trial, evaluation, feedback, improvement, and retry, the robot arm can complete self-improvement and self-evolution in the process of repeated fine nursing operations, and the movements are more standard and standardized.
- the intelligent nursing robot determines the nursing goals and specific tasks, and completes the handover of medical supplies with the nursing staff in the sterile room, it can automatically travel to the task execution area through driverless technology.
- the target determination is completed in the real scene.
- the traditional target detection algorithm adopts three basic steps of region selection, feature extraction, and classifier classification, which has defects such as high time complexity, lack of pertinence in region selection, and low robustness of manual feature extraction.
- the present invention adopts the deep learning target detection YOLO algorithm based on the regression method, and only uses one convolutional neural network (CNN) to determine the categories and positions of different targets.
- CNN convolutional neural network
- These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions
- the apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Nursing (AREA)
- Fuzzy Systems (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Electromagnetism (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Accommodation For Nursing Or Treatment Tables (AREA)
- Manipulator (AREA)
Abstract
本公开提供了一种面向高传染性隔离病区的全方位智能护理***及方法,包括远程控制***、通信网络、若干采集器和护理机器人,护理机器人,包括机器人本体和控制器,所述控制器根据接收的远程控制指令控制机器人本体的行走机构和机械臂动作;所述采集器,设置于隔离病区内,用于检测使用者的生理指标,并传输给所述远程控制***;所述通信网络,为星状拓扑结构,包括多个通信模块,被配置为实现各护理机器人、采集器与远程控制***的通信;所述远程控制***,接收采集器的信息,对采集的多元生理信号进行特征提取,结合使用者基本信息,以决策树模型进行学习,动态调整相应的护理级别,并将指示发送给在相应的护理机器人。能够实现医护人员与传染性疾病患者无接触式护理。
Description
本公开属于人工智能模式识别领域,涉及一种面向高传染性隔离病区的全方位智能护理***及方法。
本部分的陈述仅仅是提供了与本公开相关的背景技术信息,不必然构成在先技术。
传染性疾病可借由直接接触已感染个体、感染者体液或***物、感染者所污染到的物体进行传播,亦可通过空气传播、水源传播、食物传播、接触传播、土壤传播、垂直传播(母婴传播)等。尤其是肺部传染性疾病,因通过空气、飞沫途径借助呼吸道进行传播,具有传染性强、传播速度快的典型特点,通常会造成医院、学校、公共交通***等场所聚集性爆发,导致患病人数激增,引起严重突发性公共卫生事件。
大量疑似病患的确诊以及确诊病患的监护和康复过程,需要专业完备的隔离病区与一定规模的医疗护理人员,在医护人员与疑似、确诊患者的密切接触过程中如何有效防护,减小被感染隐患保护医护人员安全,避免加重非常时期医疗资源负担,是传染病护理领域有待进一步解决的实际问题。传染病护理过程中,传统的医护人员防护以佩戴口罩、医用护目镜、专用隔离防护服为主,并遵照相关传染病防治条例执行护理流程,仍存在较难以克服的现实困难。首先防护设备的清洗、消毒、替换需消耗大量社会资源,加重在抗击疫病关键时期的物资短缺,须全国性医用物资调配。其次防护流程繁杂,对于新型传播性疾病的未知以及不可控因素造成的操作不当均会不同程度引发医护人员感染事故。
发明内容
本公开为了解决上述问题,提出了一种面向高传染性隔离病区的全方位智能护理***及方法,本公开能够实现无需医护人员与传染性疾病患者密切接触情况下,能够自主或接受远端指令完成药物配送、诊断试剂取送、注射等任务并实时监控患者病情调整护理级别做出智能决策的综合护理型机器人架构。
根据一些实施例,本公开采用如下技术方案:
一种面向高传染性隔离病区的全方位智能护理***,包括远程控制***、通信网络、若干采集器和护理机器人,其中:
所述护理机器人,包括机器人本体和控制器,所述控制器根据接收的远程控制指令控制 机器人本体的行走机构和机械臂动作;
所述采集器,设置于隔离病区内,用于检测使用者的生理指标,并传输给所述远程控制***;
所述通信网络,为星状拓扑结构,包括多个通信模块,被配置为实现各护理机器人、采集器与远程控制***的通信;
所述远程控制***,接收采集器的信息,对采集的多元生理信号进行特征提取,结合使用者基本信息,以决策树模型进行学习,动态调整相应的护理级别,并将指示发送给在相应的护理机器人。
作为可选择的实施方式,所述机器人本体上设置有摄像头,所述控制器被配置为接收所述摄像头的采集数据,并根据目标检测算法完成实时对象视频检测,生成相应的指令给行走机构,以实现自动驾驶。
作为可选择的实施方式,所述机器人本体的行走机构周边设置有多个红外传感器,以感知周围物体,所述控制器接收所述红外传感器的数据,并在遇到障碍物时及时控制行走机构改变路线。
作为可选择的实施方式,所述机械臂上设置有机械手掌,所述机械手掌上设置有压力传感器和红外感知器。
作为可选择的实施方式,所述机器人本体上设置有存储空间,用于存放护理物资。
作为可选择的实施方式,所述通信网络以远程控制***为中心,在隔离病区的不同位置和各护理机器人上设置有通信模块,不同的护理机器人之间建立备份链路,当某个护理机器人与远程控制***出现信息传输不畅的情况,开启备份链路,通过另一台护理机器人与远程控制***进行交互。
基于上述***的工作方法,包括以下步骤:
利用采集器获取隔离病区内各使用者的生理指标;
对采集的多元生理信号进行特征提取,结合使用者基本信息,以决策树模型进行学习,调整相应的护理级别,并将对应护理级别的指示发送给在某护理机器人;
护理机器人根据接收的指令移动到隔离病区内相应的位置,为使用者提供相应的护理物资和护理动作。
作为可选择的实施方式,所述远程控制***利用已有的医疗数据集作为训练决策树模型的数据基础,根据不同的使用者信息寻找最佳节点和分支方法,将不纯度指标作为衡量决策树性能的依据,确定相应的护理级别。
作为可选择的实施方式,所述远程控制***根据采集患者的心率、脉搏和血压的信息进行均值、标准差、低频功率、高频功率和移动标准差特征的提取,结合使用者年龄、性别、患病时间和病情进展阶段信息,获得实时护理级别调整方案,反馈给隔离病区中的护理机器人,完成护理任务。
作为可选择的实施方式,所述控制器采用YOLO算法控制护理机器人自动寻找任务使用者目标,并在行驶至执行区域。
具体的,将目标检测建模为回归问题进行处理,采用一个端到端的网络结构,完成摄像图片输入到物***置与类别输出的过程,YOLO网络以GoogLeNet网络结构为基础,将Inception模块使用卷积层替代,完成跨通道信息整合;利用卷积层提取特征,利用全连接层预测场景中物体的概率和位置,引导行驶路线。
作为可选择的实施方式,所述控制器利用强化学习算法对机械臂的动作进行优化,强化学习通过策略迭代实现,首先给定一个动作执行策略,利用迭代贝尔曼方程求得该策略的值函数,再通过值函数更新策略,根据评价进行调整后,重新计算值函数,不断循环直至策略收敛,直到收敛到一个最优值函数和策略。
与现有技术相比,本公开的有益效果为:
本公开提供了无医式传染性疾病隔离病区。从床染病防控的三大基本途径出发,采用综合护理机器人现场护理,专业医师远程指导的方式,在完成护理工作的前提下,实现感染个体与健康人员的完全屏蔽阻断传播途径,有效保障了医务人员的安全。护理机器人通过紫外线照射或消毒液喷洒等方式完成自身清洁避免病菌附着,同时机器人为非生物个体不会成为病菌中间宿主,有效避免在护理流程中通过与不同患者的接触造成交叉感染。
本公开利用护理机器人代替人员进行物资(如药品、食物等)的运送,同时还可以利用多自由度机械臂、机械手进行静脉穿刺等操作。同时,机器人的控制器利用强化学习算法,通过尝试、评价、反馈、改进、再尝试的循环迭代,使机械臂在反复精细护理操作过程中完成自提升、自进化,动作更加标准规范。
本公开可以依据隔离病区的护理量需求,可配备数量不等的护理机器人,构成智能化护理团队。团队的信息交互采用以远程控制平台为中心的星状拓扑结构,具有可靠性高、故障隔离简单的特点。同时在不同的机器人之间也可以建立备份链路,当某个机器人与中心控制平台出现信息传输不畅的情况,可开启备份链路,通过另一台护理机器人与控制中心进行交互,具有很好的容灾能力。
本公开采用基于回归方法的深度学习目标检测YOLO算法,仅使用一个卷积神经网络(CNN) 就可以确定不同目标的类别与位置。将物体检测建模为回归问题进行处理,不同于其它基于深度学习的滑动窗结合分类器目标检测算法,检测流程仅含有一个神经网络,以端到端的方式优化检测性能,同时取得更快的物体检测速率。在训练过程中能够学习到更加抽象的特征,提升了在隔离病区复杂场景下对特定目标的识别能力。
构成本公开的一部分的说明书附图用来提供对本公开的进一步理解,本公开的示意性实施例及其说明用于解释本公开,并不构成对本公开的不当限定。
图1综合护理智能机器人应用场景图;
图2综合护理智能机器人任务自动化管理流程图形;
图3无医式隔离病区应用场景图;
图4综合护理智能机器人机械结构图;
图5综合护理机器人护理等级智能决策原理图;
图6智能病区信息交互网络结构图;
图7护理动作自动化执行流程图;
图8基于强化学习的护理动作自提升算法原理图;
图9基于YOLO算法的智能巡航***结构框架图;
图10基于面向对象的控制软件设计原理图;
图11基于集成学习的护理级别自决策***算法流程图;
下面结合附图与实施例对本公开作进一步说明。
应该指出,以下详细说明都是例示性的,旨在对本公开提供进一步的说明。除非另有指明,本文使用的所有技术和科学术语具有与本公开所属技术领域的普通技术人员通常理解的相同含义。
需要注意的是,这里所使用的术语仅是为了描述具体实施方式,而非意图限制根据本公开的示例性实施方式。如在这里所使用的,除非上下文另外明确指出,否则单数形式也意图包括复数形式,此外,还应当理解的是,当在本说明书中使用术语“包含”和/或“包括”时,其指明存在特征、步骤、操作、器件、组件和/或它们的组合。
如图1所示,传统护理方式,在传染性疾病患者由疑似确诊到治疗康复全过程中,注射、诊断试剂取送、药物配送等不同环节均需要医护人员参与,密切接触不可避免,即便采取穿戴医用口罩、护目镜、隔离防护服等措施,均无法完全避免医务人员被感染风险,存在相当 程度不可预防危险因素。本实施例基于智能机器人实现诊疗远距离全程监控,患者处于无医隔离病房中,首先做到对传染源进行屏蔽;医生仅需要在控制室通过无线信道下达指令,机器人即可完成静脉注射、医患交互、症状监测等一系列任务,有效保护易感人群;同时完全避免医护人员与患者在传统护理过程中的不同程度接触环节,彻底切断传播途径,全方位保障医护人员安全,避免因医患接触而造成的疫情扩散。
如图2所示,一种面向高传染性隔离病区的全方位智能护理***,包括远程控制***、通信网络、若干采集器和护理机器人,其中:
所述护理机器人,包括机器人本体和控制器,所述控制器根据接收的远程控制指令控制机器人本体的行走机构和机械臂动作;
所述采集器,设置于隔离病区内,用于检测使用者的生理指标,并传输给所述远程控制***;
所述通信网络,为星状拓扑结构,包括多个通信模块,被配置为实现各护理机器人、采集器与远程控制***的通信;
所述远程控制***,接收采集器的信息,对采集的多元生理信号进行特征提取,结合使用者基本信息,以决策树模型进行学习,动态调整相应的护理级别,并将指示发送给在相应的护理机器人。
首先,护理机器人采用锂电池为机器人供电,利用具有能量密度高、容量大、无记忆性等优点,可在220V家用电源上完成快速充电,在高可靠性、远距离续航能力等方面均可达到满意效果。
在全病区智能管控策略上,采用基于面向对象策略采用将数据与行为捆绑为一体的方式完成对智能控制程序的软件架构,如图2所示,将患者视为一组具有共同属性的对象成员,他们同时具有年龄、性别、护理级别、病情等定义对象状态的属性,同时需要在特定时间点被执行试剂诊断、注射、服药等护理环节,这些被执行的具体操作即方法,将所有患者定义为一个类,通过实例化在类定义基础上构造对象,即具备不同属性和需要被执行不同护理措施的独立患者。
采用循环队列方式完成对全病区患者护理事务的综合管理,按照时间顺序先进先出将存储在内存空间中的事务逐一落实,充分利用存储空间,避免“假溢出”现象发生。医务人员利用远程控制平台,对智能***进行添加患者和针对性诊疗措施的操作,指令基于WiFi、5G、蓝牙、Zigbee等不同的物联网通信标准进行无线传递,位于隔离病房中的智能护理机器人开 始执行护理操作,同时机器人也可通过无线传输方式将所监测到基于视频的患者动态信息发送给远端监控平台,完成医师巡诊与医患交互。
如图3所示,智能护理机器人通过指挥中心接受任务后,在无菌仓与专门医护人员完成医用物资交接,基于任务队列中的目标患者床位坐标自动规划路线。如图4所示,利用安装在轮式底座上的摄像头并结合相关目标检测算法完成实时对象视频检测实现自动驾驶。轮式底座依靠锂电池驱动,多驱履带式结构具有稳定性好动力强的特点,相较于腿状机械结构可有效克服行走过程中因颠簸造成的医用物品损坏,并能够适应病房中阶梯、门槛等特殊路面状况。利用安装在轮式底座侧面的红外传感器感知周围物体,遇到障碍物时及时改变路线避免碰撞。
在本实施例中,在轮式底座上安装有六个自由度标准配置的机械手臂,手臂末端安装机械手掌,手臂和手掌通过锂电池驱动,依靠马达和螺线管作为传动装置。机械手掌安装有内置的压力传感器能够在抓握或移动物品时将力度实时传送给中央处理芯片,可有效避免棉签掉落或者袋装医用试剂被挤破等。以新型冠状病毒感染者护理为例,轮式底座行驶至任务区域后,将启动机械手臂,结合末端手掌可完成咽拭子取样的复杂操作,并利用安装于手臂与手掌上的红外感知器,对人体手臂进行热红外血管成像,确定静脉结构完成穿刺任务。同时利用内置于机器人芯片中的强化学习模块,在反复的咽拭子取样、静脉穿刺等任务执行过程中根据反馈不断优化动作,使护理能力获得持续提升。
机器人可以选用现有的护理机器人。
如图5所示,利用佩戴在患者多部位的传感装置获取全时间域血压、脉搏、体温、氧饱和度等生理信号,通过无线传输发送至远程终端,终端中基于集成学习的智能算法模块将根据多模态生理信息结合患者性别、年龄等特征判断所需要采取的护理等级,并将命令反馈至综合护理机器人,机器人会根据决策自动调整不同的护理级别模式。
在具体实施时,在机械关节活动控制时,关节运动是智能机械手完成复杂护理任务的基本单元,确定目标距离并准确判断关节转动尺度是否符合任务完成要求是实现关节智能化的标准流程。如图7所示,为一个独立动作的关节转动智能控制流程,手掌侧面的红外传感器向目标物发射红外光束,根据反射光线判断距离。关节内安装有发光二极管、转动轴承、光传感器,轴承开始转动后,发光二极管发射光线穿过轴承上的凹槽照射在光传感器上,伴随轴承转动光传感器可以读取周期性的光闪烁模式,以此为依据判断轴承已经转动尺度,将光传感器获得的距离数值与红外传感器判断的距离相对照,一致则停止转动完成一个独立动作,不一致则继续转动直至达到目标尺度。依靠不同部位机械关节的转动可组合成一系列复杂的 动作,以新型冠状病毒患者护理为例,机械手能够进行抓取咽拭子在口腔咽喉部取样并回收的护理流程。
静脉结构热红外成像方面,如图4所示,通过安装在机械手臂外侧的热红外成像装置获得人体手臂的静脉血管成像,并将热成像图片发送至护理机器人中央处理器,依据图片选择合适的入针点,机械手完成抓握注射针头动作后根据确定的穿刺点进行静脉穿刺操作。在人工条件下,完成咽拭子取样、静脉穿刺等操作不仅需要专业的培训而且要经过一定周期的临床实践,借助强化学习算法,能够在机械手臂反复的操作过程中对咽拭子口腔擦拭部位、静脉针头穿刺角度、穿刺深度等技术指标不断进行修正,强化护理动作的合理规范性。
基于强化学习的护理动作自提升方面,可以利用强化学习算法机械手臂可以在任务执行过程中不断与外部环境交互,获得任务对象(被护理者)的反馈信号,习得从对象状态到动作行为的映射关系,对动作进行优化。如图8所示,以静脉穿刺为例,机器人可以在行动、评价、改进、再行动的护理过程中不断改进穿刺的角度、深度等动作方案以适应任务对象。强化学习通过策略迭代实现,首先给定一个动作执行策略,利用迭代贝尔曼方程求得该策略的值函数,再通过值函数更新策略。如图8中的ε-greedy策略,代表静脉穿刺的深度,指以ε的概率选择能够获得最大满意度的行为,以1-ε的概率随机选择动作方式。根据评价进行调整后,重新计算值函数,不断循环直至策略收敛。迭代过程最终会收敛到一个最优值函数V
*(s)和策略π
*,表示动作策略已能够符合临床操作规范要求。
基于目标检测的护理对象自动寻找方面,采用YOLO算法控制护理机器人自动寻找任务患者目标,并在行驶至执行区域的过程中通过顶部摄像装置做出实时决策,确保不与其它行人或物体等障碍发生接触引起碰撞。首先将目标检测建模为回归问题进行处理,采用一个端到端的网络结构,完成摄像图片输入到物***置与类别输出的过程。YOLO网络以GoogLeNet网络结构为基础,如图9所示,将Inception模块使用1×1+3×3的卷积层替代,完成跨通道信息整合。利用卷积层提取特征,利用全连接层预测场景中物体的概率和位置,引导行驶路线。不同于滑动窗口与区域检测的目标识别方式,将全图作为场景信息的策略进一步降低了检测误差率。
基于面向对象方法的护理任务控制流程设计方面,面向对象的软件设计方法可以利用贴近真实世界的模型组织形式完成程序的架构。如图10所示,本实施例采用化繁为简的策略,对具体的护理对象(患者)进行概括,抽出此类对象的公共性质并加以描述,构造患者类。具体包括两个步骤即数据抽象和行为抽象,患者共同具有年龄、性别、脉搏、血压、血氧饱 和度等基本信息,定义为类的属性,完成数据抽象,智能机器人需要在不同时刻对患者做出特定的护理操作,如送药、咽拭子取样、静脉穿刺等,定义为方法,完成行为抽象。将患者类实例化即为特定的患者对象,智能机器人基于患者属性对患者病情做出评价,基于患者对象抽象出的行为对患者进行护理工作。护理任务的管理采用循环队列结构进行,利用连续物理存储结构构成环状的逻辑空间,队首护理任务完成即出队,添加新护理任务即从队尾入队,有效节约存储资源,防止假溢出的发生。护理机器人顺次读取循环队列中以时间顺序排列的任务单元,进行送药、注射等护理模块的执行,可在一个值班周期内有序完成一对多的护理工作。
基于集成学习的护理级别决策方面,由于传染病普遍具有病情变化快、进展迅速的特点。在人工护理条件下,医师不但要能够根据患者全方位情况对病情做出正确判断,同时要具备较强的临机处置能力,须相当的临床经验。疫病流行期,由于病患人数激增,导致具备丰富临床经验的护理医师缺乏,不恰当的诊断评估会引起过度治疗或延误治疗时机等情况的发生。现有的自动化医疗监护设备仅是将患者若干生理数据提供给护理医师,由人工方式进行病情评估,仍依赖于医师的临床经验,或将数据机械地输入以模型驱动方式建立的数学公式,进行粗略评估,完全忽视患者个体差异的存在。
决策树为一种树形结构,如图11a所示,每个内部节点表示一个属性上的测试,如动脉血氧饱和度是否低于98%,分支代表测试输出,路径末端的叶节点表示评估结论。本实施例利用相关医疗数据集并以此为基础进行合理的扩充完善作为训练决策树模型的数据基础,根据不同的患者信息寻找最佳节点和分支方法,将不纯度指标作为衡量决策树性能的依据。决策树中每个节点都有一个不纯度,子节点的不纯度低于父节点,即父节点属性在护理级别区分度上所体现的显著性高于子节点。使用基尼系数:
决定不纯度,t表示给定节点,i代表护理级别等级,p(i|t)代表在属性t条件下达到i护理级别的样本规模。如图11b所示为构建单棵决策树的算法流程,当全部特征使用完毕时,整体不纯度达到最优,即获得最佳诊断决策方案,循环结束。如图11c所示,本实施例采用集成学习策略,通过梯度提升机(GBM)结合多个弱学习者(决策树)进行最终的预测,每个决策树中的节点采用不同的功能子集(
ID3、
C4.5、C5.0等)来选择最佳拆分方案,所构建的不同决策树能够从数据中捕获不同的信息。每一棵新构建的决策树都会以提升权值的方式关注先前决策树所犯的诊断错误,因此性能逐步优化,实现梯度提升的效果。如图5所示, 将采集患者的心率、脉搏、血压等信息进行均值、标准差、低频功率、高频功率、移动标准差等特征的提取,结合患者年龄、性别、患病时间、病情进展阶段等个体化信息,输入远程平台中的集成学习模块获得实时护理级别调整方案,反馈给隔离病区中的机器人,指导完成护理任务。
上述实施例具有以下优点:
(1)无医式传染性疾病隔离病区。从床染病防控的三大基本途径出发,采用综合护理机器人现场护理,专业医师远程指导的方式,在完成护理工作的前提下,实现感染个体与健康人员的完全屏蔽阻断传播途径,有效保障了医务人员的安全。将在传统护理过程中基于防护服隔离的策略升级为人机协同无危护理,有效避免因医务人员在护理过程中被感染而进一步加剧医疗资源短缺困境的现实问题,同时节约了大量防护消杀耗材,从人力物力两个方面保障了低成本条件下护理工作的开展。如图3所示,远程监控室一名医师完成病情监控及护理任务下达,无菌仓一名护士完成医用物资传递,病区若干部智能护理机器人完成具体护理任务,即可实现在一个值班周期内对全病区二十多张床位的护理。传统的护理方式对医护人员配备有较大规模要求,一名重症患者通常需要多名护理人员同时护理,采用无医式隔离病区的管理模式实现了护理方式从医患多对一到一对多的改变,相较于人员远程调配,是一种在疫病爆发患者突发性增长背景下更理想的本地化应急处置方式,有效缓解了医护人员不足的问题。护理机器人通过紫外线照射或消毒液喷洒等方式完成自身清洁避免病菌附着,同时机器人为非生物个体不会成为病菌中间宿主,有效避免在护理流程中通过与不同患者的接触造成交叉感染。
(2)面向对象的软件架构与循环队列的任务管理策略。如图2所示,护理型机器人通过任务管理软件进行面向多名患者的护理工作统筹安排,管理软件通过嵌入式方式植入机器人内置芯片,客户端安装于远程数据终端中,可适应Windows、Lunix、Unix、安卓、苹果等多种操作***,一台电脑一张光盘即可完成远程护理指挥中心的搭建,简单便捷的工作流程充分适应了疫情突发状况下时间紧迫,人员、物资缺乏的特点。面向对象的开发方式能有效提高编程效率,既可使用固定的管理程序模式,也可在疫情爆发后短时期内设计出应用于特殊类型隔离病区场景的针对性智能护理团队综合管理平台,同时程序具有良好的可重用性、灵活性、可扩展性等特点。管理程序中采用循环队列结构对护理事务进行统筹部署,在保证任务有序开展的基础上,有效避免事务拥塞,提升存储空间利用率。
(3)可完成复杂护理任务的智能机械手。以新型冠状病毒感染者护理为例,完成咽拭子取样是患者确诊的必要步骤,过程中被采集者通过张口、咳嗽、呕吐等动作可产生大量携带 病毒的飞沫,造成医护人员被感染风险。呼吸道传染病存在爆发性特点,疫情初期大量人员筛查检测工作导致咽拭子取样任务量激增引起防护措施不到位,同时由于早期阶段对疫病传播途径感染方式的未知,以及医务人员防护级别较低,警惕性不高等因素,进一步加重了医护人员的被感染风险。本发明将机械力学、人体工程学相关理论与精细化护理的目标任务相结合,通过智能算法控制,护理机器人即可在没有医务人员现场参与的情况下完成一系列复杂护理操作。如图4所示,机械手掌有十二个自由度,能够完成抓握、转动、触摸、按压等动作,同时结合安装于手掌外侧的红外传感器判断目标距离,可抓取棉签近距离伸进患者咽喉部进行擦拭动作,并将棉签放入回收仓。同时手掌表面附着有高分子炭纤维材料制成的防护膜,不但具有耐高温、耐磨损的特点而且可以通过循环自洁机制完成表面杀菌消毒,避免传染物附着,在无需更换防护手套的情况下进行多次采集工作,减轻人力节约耗材。传染病护理须穿戴厚重的隔离防护服,增加了人工静脉穿刺的难度,机械手臂侧面安装有红外血管成像传感器,可以获得患者前臂的静脉血管结构,指导机械手掌运动,完成静脉穿刺操作。本发明将强化学习算法植入控制程序,通过尝试、评价、反馈、改进、再尝试的循环迭代,使机械臂在反复精细护理操作过程中完成自提升、自进化,动作更加标准规范。
(4)基于星形网络结构的信息交互***。如图6所示,依据隔离病区的护理量需求,可配备数量不等的护理机器人,构成智能化护理团队。团队的信息交互采用以远程控制平台为中心的星状拓扑结构,具有可靠性高、故障隔离简单的特点。同时在不同的机器人之间也可以建立备份链路,当某个机器人与中心控制平台出现信息传输不畅的情况,可开启备份链路,通过另一台护理机器人与控制中心进行交互,具有很好的容灾能力。特定情况下隔离病区会出现人员聚集的现象,如方舱医院可集中容纳超千名患者,患者与外部的信息交互、实时疫情通报等均需通过无线网络进行,会出现网络资源紧张信息拥塞的情况。智能机器人护理团队的信息传递采用多模工作方式,安装美国Gobi基带芯片,不占用独立的频段节约频率资源,可使用现有的5G、WiFi等多种通信标准,并根据不同网络的网速、资源占用率、瞬时用户量等指标智能决策,选择空置率高的通信标准进行工作,既保证通信质量同时合理利用网络资源。在此基础上结合码分多址技术,保证在同一频率段上多名团队成员可与控制中心同时交互,进一步节约了频带资源。
(5)基于无人驾驶技术的患者目标智能定位。智能护理机器人确定护理目标与具体执行任务并在无菌室与护理人员完成医用物资交接后,通过无人驾驶技术可自动行驶到达任务执行区域。利用安装在轮式底座上方的摄像头结合实时视频对象检测算法,在真实场景中完成目标确定。传统的目标检测算法采用区域选择、特征提取、分类器分类三个基本步骤,存在 时间复杂度高、区域选择缺乏针对性、手工特征提取鲁棒性低等缺陷。本发明采用基于回归方法的深度学习目标检测YOLO算法,仅使用一个卷积神经网络(CNN)就可以确定不同目标的类别与位置。将物体检测建模为回归问题进行处理,不同于其它基于深度学习的滑动窗结合分类器目标检测算法,检测流程仅含有一个神经网络,以端到端的方式优化检测性能,同时取得更快的物体检测速率。在训练过程中能够学习到更加抽象的特征,提升了在隔离病区复杂场景下对特定目标的识别能力。
(6)基于多元信息的患者监护级别智能决策***。分级护理是根据对病人病情的轻、重、缓、急给予不同级别的护理。以数据驱动为基础的决策树模型能够有效发掘数据间的非线性关系,在临床诊断领域已经得到广泛的应用并取得良好效果。本发明将海量真实临床数据、具体化的目标任务、高准确率的自动化决策***有效结合,建立三位一体相互支撑的智能化护理级别决策框架。如图5所示,患者在不同部位佩戴由高灵敏传感器制成的贴片,能够实时采集体温、脉搏、氧饱和度、心电等生理指标,将信息通过无线路由传输至远程平台,多元生理信号经过特征提取结合患者年龄、性别、传染病类型、病情阶段等信息输入平台中以决策树模型为基础构建的更高识别准确度集成学习模块,模块将动态调整患者护理级别,并将指示发送给在隔离病区的护理机器人,机器人根据不同的护理级别制定有针对性的护理方案,使患者获得个体化实时性的综合康复治疗。
(7)广泛适用性。无医式隔离病区结合全方位智能护理机器人可面向多种高传染性疾病的集中护理工作,如霍乱、鼠疫、新型冠状病毒、非典、禽流感等,军事领域也可用于面向生化武器攻击的战地救护,具有广泛的适用性。
本领域内的技术人员应明白,本公开的实施例可提供为方法、***、或计算机程序产品。因此,本公开可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且,本公开可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本公开是参照根据本公开实施例的方法、设备(***)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器,使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中,使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品,该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上,使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理,从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
以上所述仅为本公开的优选实施例而已,并不用于限制本公开,对于本领域的技术人员来说,本公开可以有各种更改和变化。凡在本公开的精神和原则之内,所作的任何修改、等同替换、改进等,均应包含在本公开的保护范围之内。
上述虽然结合附图对本公开的具体实施方式进行了描述,但并非对本公开保护范围的限制,所属领域技术人员应该明白,在本公开的技术方案的基础上,本领域技术人员不需要付出创造性劳动即可做出的各种修改或变形仍在本公开的保护范围以内。
Claims (10)
- 一种面向高传染性隔离病区的全方位智能护理***,其特征是:包括远程控制***、通信网络、若干采集器和护理机器人,其中:所述护理机器人,包括机器人本体和控制器,所述控制器根据接收的远程控制指令控制机器人本体的行走机构和机械臂动作;所述采集器,设置于隔离病区内,用于检测使用者的生理指标,并传输给所述远程控制***;所述通信网络,为星状拓扑结构,包括多个通信模块,被配置为实现各护理机器人、采集器与远程控制***的通信;所述远程控制***,接收采集器的信息,对采集的多元生理信号进行特征提取,结合使用者基本信息,以决策树模型进行学习,动态调整相应的护理级别,并将指示发送给在相应的护理机器人。
- 如权利要求1所述的一种面向高传染性隔离病区的全方位智能护理***,其特征是:所述机器人本体上设置有摄像头,所述控制器被配置为接收所述摄像头的采集数据,并根据目标检测算法完成实时对象视频检测,生成相应的指令给行走机构,以实现自动驾驶。
- 如权利要求1所述的一种面向高传染性隔离病区的全方位智能护理***,其特征是:所述机器人本体的行走机构周边设置有多个红外传感器,以感知周围物体,所述控制器接收所述红外传感器的数据,并在遇到障碍物时及时控制行走机构改变路线。
- 如权利要求1所述的一种面向高传染性隔离病区的全方位智能护理***,其特征是:所述机械臂上设置有机械手掌,所述机械手掌上设置有压力传感器和红外感知器。
- 如权利要求1所述的一种面向高传染性隔离病区的全方位智能护理***,其特征是:所述通信网络以远程控制***为中心,在隔离病区的不同位置和各护理机器人上设置有通信模块,不同的护理机器人之间建立备份链路,当某个护理机器人与远程控制***出现信息传输不畅的情况,开启备份链路,通过另一台护理机器人与远程控制***进行交互。
- 基于权利要求1-5中任一项所述的***的工作方法,其特征是:包括以下步骤:利用采集器获取隔离病区内各使用者的生理指标;对采集的多元生理信号进行特征提取,结合使用者基本信息,以决策树模型进行学习,调整相应的护理级别,并将对应护理级别的指示发送给在某护理机器人;护理机器人根据接收的指令移动到隔离病区内相应的位置,为使用者提供相应的护理物资和护理动作。
- 如权利要求6所述的工作方法,其特征是:所述远程控制***利用已有的医疗数据集 作为训练决策树模型的数据基础,根据不同的使用者信息寻找最佳节点和分支方法,将不纯度指标作为衡量决策树性能的依据,确定相应的护理级别。
- 如权利要求6所述的工作方法,其特征是:所述远程控制***根据采集患者的心率、脉搏和血压的信息进行均值、标准差、低频功率、高频功率和移动标准差特征的提取,结合使用者年龄、性别、患病时间和病情进展阶段信息,获得实时护理级别调整方案,反馈给隔离病区中的护理机器人,完成护理任务。
- 如权利要求6所述的工作方法,其特征是:所述控制器采用YOLO算法控制护理机器人自动寻找任务使用者目标,并在行驶至执行区域:将目标检测建模为回归问题进行处理,采用一个端到端的网络结构,完成摄像图片输入到物***置与类别输出的过程,YOLO网络以GoogLeNet网络结构为基础,将Inception模块使用卷积层替代,完成跨通道信息整合;利用卷积层提取特征,利用全连接层预测场景中物体的概率和位置,引导行驶路线。
- 如权利要求6所述的工作方法,其特征是:所述控制器利用强化学习算法对机械臂的动作进行优化,强化学习通过策略迭代实现,首先给定一个动作执行策略,利用迭代贝尔曼方程求得该策略的值函数,再通过值函数更新策略,根据评价进行调整后,重新计算值函数,不断循环直至策略收敛,直到收敛到一个最优值函数和策略。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US17/910,466 US20230129990A1 (en) | 2020-12-31 | 2021-07-16 | Omni-bearing intelligent nursing system and method for high-infectious isolation ward |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011641559.4A CN112809696B (zh) | 2020-12-31 | 2020-12-31 | 面向高传染性隔离病区的全方位智能护理***及方法 |
CN202011641559.4 | 2020-12-31 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022142271A1 true WO2022142271A1 (zh) | 2022-07-07 |
Family
ID=75858115
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2021/106859 WO2022142271A1 (zh) | 2020-12-31 | 2021-07-16 | 面向高传染性隔离病区的全方位智能护理***及方法 |
Country Status (3)
Country | Link |
---|---|
US (1) | US20230129990A1 (zh) |
CN (1) | CN112809696B (zh) |
WO (1) | WO2022142271A1 (zh) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10788235B2 (en) * | 2014-11-07 | 2020-09-29 | Sony Corporation | Control system, control method, and storage medium |
CN112809696B (zh) * | 2020-12-31 | 2022-03-15 | 山东大学 | 面向高传染性隔离病区的全方位智能护理***及方法 |
CN116079720A (zh) * | 2022-12-23 | 2023-05-09 | 深圳优地科技有限公司 | 机器人控制方法、机器人和存储介质 |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106940562A (zh) * | 2017-03-09 | 2017-07-11 | 华南理工大学 | 一种移动机器人无线集群***及神经网络视觉导航方法 |
CN108052004A (zh) * | 2017-12-06 | 2018-05-18 | 湖北工业大学 | 基于深度增强学习的工业机械臂自动控制方法 |
CN109448856A (zh) * | 2018-10-16 | 2019-03-08 | 张倩 | 基于人工智能的诊疗决策*** |
US20190244366A1 (en) * | 2017-09-07 | 2019-08-08 | Comcast Cable Communications, Llc | Relevant Motion Detection in Video |
CN111358439A (zh) * | 2020-03-14 | 2020-07-03 | 厦门波耐模型设计有限责任公司 | 全科医师机器人*** |
CN112809696A (zh) * | 2020-12-31 | 2021-05-18 | 山东大学 | 面向高传染性隔离病区的全方位智能护理***及方法 |
Family Cites Families (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120072024A1 (en) * | 2002-07-25 | 2012-03-22 | Yulun Wang | Telerobotic system with dual application screen presentation |
CN1524489A (zh) * | 2003-09-15 | 2004-09-01 | 上海第二医科大学附属新华医院 | 一种临床监护仪的远程实时监测*** |
US20050154265A1 (en) * | 2004-01-12 | 2005-07-14 | Miro Xavier A. | Intelligent nurse robot |
US10875182B2 (en) * | 2008-03-20 | 2020-12-29 | Teladoc Health, Inc. | Remote presence system mounted to operating room hardware |
EP2852881A4 (en) * | 2012-05-22 | 2016-03-23 | Intouch Technologies Inc | GRAPHIC USER INTERFACES CONTAINING TOUCH PAD TOUCH INTERFACES FOR TELEMEDICINE DEVICES |
US10276260B2 (en) * | 2012-08-16 | 2019-04-30 | Ginger.io, Inc. | Method for providing therapy to an individual |
JP6360479B2 (ja) * | 2012-08-24 | 2018-07-18 | コーニンクレッカ フィリップス エヌ ヴェKoninklijke Philips N.V. | 臨床支援システム及び方法 |
CN106777960A (zh) * | 2016-12-12 | 2017-05-31 | 浙江侍维波机器人科技有限公司 | 一种Ros分布式***架构在医疗护理领域的应用 |
US20200394405A1 (en) * | 2017-12-12 | 2020-12-17 | Sony Corporation | Information processing apparatus and information processing method |
US11213359B2 (en) * | 2017-12-28 | 2022-01-04 | Cilag Gmbh International | Controllers for robot-assisted surgical platforms |
US11819369B2 (en) * | 2018-03-15 | 2023-11-21 | Zoll Medical Corporation | Augmented reality device for providing feedback to an acute care provider |
CN108769224A (zh) * | 2018-05-23 | 2018-11-06 | 厦门波耐模型设计有限责任公司 | 伺寝机器人物联网*** |
US20220152837A1 (en) * | 2019-04-16 | 2022-05-19 | University Of Louisville Research Foundation, Inc. | Adaptive robotic nursing assistant |
US20230248614A1 (en) * | 2019-04-30 | 2023-08-10 | Nucleusrx, Inc. | Connected medication dispenser |
US11545271B2 (en) * | 2019-08-20 | 2023-01-03 | GE Precision Healthcare LLC | Systems and methods for public and private communication threads |
US20230138192A1 (en) * | 2020-03-14 | 2023-05-04 | Xiamen Brana Design Co., Ltd. | Medical service robot device, and method and system thereof |
CN111449757B (zh) * | 2020-04-10 | 2022-01-11 | 京东方科技集团股份有限公司 | 远程医疗机器人、控制方法及其充电方法 |
CN111660279A (zh) * | 2020-04-20 | 2020-09-15 | 国网山东省电力公司桓台县供电公司 | 疫区病房用智能机器人及*** |
US20220059238A1 (en) * | 2020-08-24 | 2022-02-24 | GE Precision Healthcare LLC | Systems and methods for generating data quality indices for patients |
-
2020
- 2020-12-31 CN CN202011641559.4A patent/CN112809696B/zh active Active
-
2021
- 2021-07-16 US US17/910,466 patent/US20230129990A1/en active Pending
- 2021-07-16 WO PCT/CN2021/106859 patent/WO2022142271A1/zh active Application Filing
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106940562A (zh) * | 2017-03-09 | 2017-07-11 | 华南理工大学 | 一种移动机器人无线集群***及神经网络视觉导航方法 |
US20190244366A1 (en) * | 2017-09-07 | 2019-08-08 | Comcast Cable Communications, Llc | Relevant Motion Detection in Video |
CN108052004A (zh) * | 2017-12-06 | 2018-05-18 | 湖北工业大学 | 基于深度增强学习的工业机械臂自动控制方法 |
CN109448856A (zh) * | 2018-10-16 | 2019-03-08 | 张倩 | 基于人工智能的诊疗决策*** |
CN111358439A (zh) * | 2020-03-14 | 2020-07-03 | 厦门波耐模型设计有限责任公司 | 全科医师机器人*** |
CN112809696A (zh) * | 2020-12-31 | 2021-05-18 | 山东大学 | 面向高传染性隔离病区的全方位智能护理***及方法 |
Also Published As
Publication number | Publication date |
---|---|
CN112809696B (zh) | 2022-03-15 |
CN112809696A (zh) | 2021-05-18 |
US20230129990A1 (en) | 2023-04-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2022142271A1 (zh) | 面向高传染性隔离病区的全方位智能护理***及方法 | |
Wan et al. | Cognitive computing and wireless communications on the edge for healthcare service robots | |
CN111916195A (zh) | 一种医疗用机器人装置,***及方法 | |
WO2021185049A1 (zh) | 医疗服务机器人装置及其方法、*** | |
WO2021254444A1 (zh) | 五官及外科医疗数据采集分析诊断机器人,平台 | |
CN113241196B (zh) | 基于云-终端协同的远程医疗与分级监控*** | |
CN109036586A (zh) | 基于物联网技术的家庭健康远程监护*** | |
Goh et al. | A PDA-based ECG beat detector for home cardiac care | |
CN113370230A (zh) | 一种无人化智能医疗急救方法及装置 | |
US11106284B2 (en) | Determining and evaluating data representing an action to be performed by a robot | |
Umoh et al. | A proposed fuzzy framework for cholera diagnosis and monitoring | |
Adhikari et al. | Random forest for data aggregation to monitor and predict COVID-19 using edge networks | |
US20230053474A1 (en) | Medical care system for assisting multi-diseases decision-making and real-time information feedback with artificial intelligence technology | |
Shi et al. | Artificial neural networks: current applications in modern medicine | |
CN117711604A (zh) | 一种患者监护*** | |
CN108125770A (zh) | 一种基于物联网技术的智能上下肢康复训练*** | |
Irshad et al. | Convolutional neural network enable optoelectronic system for predicting cardiac response by analyzing auction-based optimization algorithms | |
Kotha et al. | ARTEMIS: AI-driven Robotic Triage Labeling and Emergency Medical Information System | |
Nagrale et al. | Internet of Robotic Things in Cardiac Surgery: An Innovative Approach | |
Gritsenko et al. | Current state and prospects for the development of digital medicine | |
Yadav et al. | IOT and Big Data Inter-Relation: A boom in biomedical healthcare | |
Baker et al. | Automatic Disease Diagnosis System Using Deep Q-Network Reinforcement Learning | |
Stephen et al. | Automatic autonomous heart monitoring device using machine learning for COVID patients | |
Alghareb et al. | 8 Smart Healthcare | |
Maity et al. | Homecare Robotic Systems: Wearable Remote Sensing with Interactive AI Features |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21913023 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 03/11/2023) |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21913023 Country of ref document: EP Kind code of ref document: A1 |