An intelligent urological postoperative nursing device and system

Abstract

The embodiment of the application discloses a kind of intelligent urological postoperative nursing equipment and system, wherein nursing equipment includes: nursing equipment ontology, for providing postoperative rest environment for patient;Fixing component is arranged on nursing equipment ontology, for fixing patient urine bag;Image acquisition equipment is arranged in the vicinity of fixing component, for collecting urine bag image;Vital sign acquisition equipment is arranged on equipment ontology, for collecting the vital sign parameter of patient;Analysis equipment is used to obtain urine sediment, urine color and urine volume data according to urine bag image, and determine the posture parameter of nursing equipment ontology according to urine sediment, urine color, urine volume data and vital sign parameter;Adjusting component is used to adjust the posture of nursing equipment ontology according to the posture parameter of nursing equipment ontology.

Description

TECHNICAL FIELD

[0001] The present application relates to the medical technology field, and in particular to an intelligent urology postoperative nursing device and system. BACKGROUND

[0002] Urology postoperative nursing is a key link in the patient's recovery process, which is of great significance for promoting the patient's physical function recovery, preventing complications and reducing readmission rate. The postoperative nursing device is a medical device specially designed to help patients recover after surgery. It provides comfortable support and adjustable posture to help patients maintain the correct posture, promote blood circulation, reduce pain and improve postoperative recovery efficiency.

[0003] Although the existing postoperative nursing devices have made certain progress in design and function, there are still some problems and deficiencies: most of the existing nursing devices have single function, lack of intelligent adjustment and monitoring function; many nursing devices need to manually adjust the angle of the backrest and leg support, which may be very difficult for patients with limited mobility; and lack of customized design for urology surgery types, which cannot meet the special needs of different patient groups.

[0004] Therefore, it is an urgent problem for those skilled in the art to design an intelligent urology postoperative nursing device. SUMMARY

[0005] Therefore, the embodiments of the present application provide an intelligent urology postoperative nursing device and system, which intelligently adjusts the posture of the nursing device by monitoring the urine data and vital sign data of the patient, and promotes the postoperative recovery of the patient.

[0006] To achieve the purpose of the present application, the following technical solutions are adopted:

[0007] In a first aspect, an intelligent urology postoperative nursing device is provided, characterized in that it comprises:

[0008] A nursing device body is used to provide a postoperative rest environment for the patient;

[0009] A fixing component is arranged on the nursing device body and used to fix the patient's urine bag;

[0010] An image acquisition device is arranged near the fixing component and used to acquire the image of the urine bag;

[0011] A vital sign acquisition device is arranged on the device body and used to acquire the vital sign parameters of the patient;

[0012] The analysis device comprises an image analysis module and a posture analysis module, the image analysis module is used to obtain urine deposit, urine color and urine volume data according to the urine bag image, and the posture analysis module is used to determine the posture parameter of the nursing device body according to the urine deposit, the urine color, the urine volume data, the vital sign parameter and the posture parameter of the current nursing device body.

[0013] The adjusting component is used to adjust the posture of the nursing device body according to the posture parameter of the nursing device body.

[0014] Optionally, the nursing device body is a recovery chair.

[0015] Optionally, the image acquisition module comprises a camera corresponding to the urine bag, which is used to acquire the urine bag image, and the camera sends the acquired urine bag image to the analysis device.

[0016] Optionally, the sign acquisition module comprises a temperature sensor, a sphygmomanometer and a heart rate monitor, which are respectively used to acquire the temperature, blood pressure and heart rate data of the patient.

[0017] Optionally, the image analysis module is a YOLO-based model, the image analysis module comprises a backbone network, a neck network and a head network, the head network comprises a urine bag scale detection branch, a liquid level detection branch, a color detection branch and a deposit detection branch, the urine bag scale detection branch, the liquid level detection branch, the color detection branch and the deposit detection branch share the features of the neck network, and the head network outputs the urine bag scale, the urine deposit, the urine color and the liquid level position.

[0018] Optionally, the neck network comprises a feature extraction module and a feature fusion module, the feature extraction module comprises a plurality of context anchor point modules, the plurality of context anchor point modules are used to perform feature extraction on the feature maps of different layers of the backbone network, the feature fusion module comprises a feature refinement module and a feature enhancement module, the feature refinement module fuses the high-layer features and the low-layer features processed by the feature extraction module, the feature enhancement module fuses the high-layer features processed by the feature extraction module and the features fused by the feature refinement module, and the features fused by the feature refinement module and the feature enhancement module are input into each branch of the head network.

[0019] Optionally, the urine volume data is determined according to the urine bag scale and the liquid level position, if the liquid level position is at a scale line, the scale line is directly taken as the urine volume data, and if the liquid level position is between two adjacent scale lines, the urine volume data is determined by proportional calculation according to the distance between the liquid level position and the two scale lines.

[0020] Optionally, the posture parameters of the nursing device body include a chair back angle, a leg support height, and a headrest position.

[0021] Optionally, the posture analysis module includes an input layer, an LSTM layer, a feature fusion layer, a full connection layer, and an output layer, input features of the input layer include the urine deposit, the urine color, the urine volume data, the vital sign parameters, and the posture parameters of the current nursing device body, the LSTM layer processes the vital sign parameters to obtain extracted features, the feature fusion layer fuses the extracted features and the urine deposit, the urine color, the urine volume data, and the posture parameters of the current nursing device body to obtain fused features, the full connection layer extracts features from the fused features to obtain output features, and the output layer obtains the posture parameters of the nursing device body according to the output features.

[0022] Optionally, the adjustment component includes a controller and a power component, the controller receives the posture parameters of the nursing device body to generate a control signal, and the power component drives a motor or a hydraulic rod to adjust the posture of the nursing device body according to the control signal.

[0023] In a second aspect, an intelligent urological surgery postoperative nursing system includes:

[0024] The device according to the first aspect;

[0025] An information transmission module is configured to transmit the urine deposit, the urine color, the urine volume data, and the vital sign parameters to a host computer.

[0026] The host computer is configured to store and monitor the urine deposit, the urine color, the urine volume data, and the vital sign parameters, generate an alert signal when the data parameters meet preset conditions, and send the alert signal to an alert module.

[0027] The alert module is configured to generate light or sound information according to the alert signal to alert the patient and medical staff to take action.

[0028] Compared with the prior art, the present application has the following advantages:

[0029] The intelligent urological postoperative nursing device and system provided by the application can intelligently adjust the posture of the nursing device according to the urine bag image and vital sign data of the patient, and promote the postoperative recovery of the patient; the image analysis module is designed to detect the urine bag of the patient to obtain the urine information of the patient, reduce the complexity of urine detection, and adjust the nursing device in combination with the urine information of the patient, so as to better meet the special needs of the patient group of urological surgery; the posture analysis module is designed to accurately predict the posture more conducive to the recovery of the patient in combination with the urine information and vital sign data of the patient, so as to adjust the recovery device and help the patient maintain the correct posture.

[0030] The technical solutions of the application will be further described in detail below with reference to the drawings and examples. BRIEF DESCRIPTION OF DRAWINGS

[0031] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings in which:

[0032] Figure 1 Fig. 1 is a structural schematic diagram of an intelligent urological postoperative nursing device provided by an exemplary embodiment of the present application.

[0033] Figure 2 Fig. 2 is a structural schematic diagram of an intelligent urological postoperative nursing system provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0034] Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, and not all embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein.

[0035] It should be noted that: the relative arrangement, numerical expression and numerical value of the components and steps set forth in these embodiments do not limit the scope of the present application, unless otherwise specified.

[0036] Those skilled in the art can understand that the terms "first", "second" and the like in the embodiments of the present application are only used to distinguish different steps, devices or modules, and do not represent any specific technical meaning, nor do they represent the inevitable logical sequence between them.

[0037] It should also be understood that in the embodiments of the present application, "a plurality of" can mean two or more, and "at least one" can mean one, two or more.

[0038] It should also be understood that any one of the components, data, or structures mentioned in the embodiments of the present application can be one or more, unless specifically limited or unless otherwise indicated by context.

[0039] Embodiment 1

[0040] As Figure 1 shown, the present embodiment provides an intelligent urological surgery postoperative nursing device 10, in order to achieve the above purpose, the present application is realized through the following technical schemes:

[0041] The nursing device body 100 is used for providing a postoperative rest environment for a patient.

[0042] The fixing component 110 is arranged on the nursing device body and is used for fixing a patient urine bag.

[0043] The image acquisition device 120 is arranged near the fixing component and is used for acquiring an image of the urine bag.

[0044] The vital sign acquisition device 130 is arranged on the device body and is used for acquiring a vital sign parameter of the patient.

[0045] The analysis device 140 includes an image analysis module 141 and a posture analysis module 142, the image analysis module is used for obtaining urine deposit, urine color and urine volume data according to the urine bag image, and the posture analysis module is used for determining a posture parameter of the nursing device body according to the urine deposit, the urine color, the urine volume data, the vital sign parameter and a current posture parameter of the nursing device body.

[0046] The adjusting component 150 is used for adjusting the posture of the nursing device body according to the posture parameter of the nursing device body.

[0047] In the present embodiment, the nursing device body 100 is a recovery chair, which is a rehabilitation auxiliary device specially designed for postoperative patients, mainly used for helping patients to rest, recover and perform early activities during the postoperative recovery period, and can adjust the angle to help patients perform limb activities or joint training, promote blood circulation and muscle recovery.

[0048] The fixing component 110 can be a hook arranged on the nursing device body 100, and the urine bag is fixed on the fixing component 110 when the patient rests on the nursing device body 100. Among them, after the urological surgery, the patient may not be able to urinate independently due to anesthesia, surgical trauma or physical weakness, etc. The urine bag can effectively drain urine, avoid overfilling of the bladder, and reduce the risk of infection by draining urine through the urine bag. Moreover, after some urological surgeries, such as bladder surgery or ureter surgery, the urine bag can reduce the irritation of urine to the wound and promote wound healing. Therefore, the patient needs to wear a urine bag after surgery, and the fixing component 110 arranged on the nursing device body 100 can meet the needs of urological surgery patients.

[0049] The image acquisition device 120 includes a camera corresponding to the urine bag, which ensures that the urine bag is entirely within the acquisition range of the image acquisition device 120. The camera sends the collected urine bag image data to the analysis device 140.

[0050] The vital sign acquisition module 130 includes a body temperature sensor, a sphygmomanometer and a heart rate monitor, respectively used to acquire the body temperature, blood pressure and heart rate data of the patient. Among them, after urological surgery, the speed of the heart rate reflects the pain, anxiety, blood loss, arrhythmia or abnormal heart function of the patient after surgery, the blood pressure reflects the postoperative state of blood loss, blood volume deficiency, posture discomfort, etc. and the body temperature reflects the body's response to surgical trauma and inflammatory response. Therefore, the vital sign parameters of the patient are closely related to the physical condition and recovery condition of the postoperative patient.

[0051] The image analysis module 141 in the analysis device 140 is a model based on YOLO. YOLO (You Only Look Once) is a real-time target detection model based on deep learning. The core idea of YOLO is to regard the target detection task as a single regression problem, and to complete the positioning and classification of the target through a forward propagation, thereby achieving extremely high detection speed. YOLO plays an important role in many practical applications such as automatic driving, security monitoring and medical imaging. Using the YOLO model as the basis of the image analysis module 141 improves the convenience of detection from the aspect of image.

[0052] In order to match the analysis scene of the patient's urine and more accurately detect the urine information, the standard YOLO model is improved in the embodiment, specifically, the image analysis module 141 includes a backbone network, a neck network and a head network, the head network includes a urine bag scale detection branch, a liquid level detection branch, a color detection branch and a sediment detection branch, the urine bag scale detection branch, the liquid level detection branch, the color detection branch and the sediment detection branch share the features of the neck network, and the head network outputs the urine bag scale, the urine sediment, the urine color and the liquid level position.

[0053] Among them, the backbone network is the basic part in the YOLO model, which is used to extract multi-scale feature maps, in the embodiment, the backbone network extracts low-scale feature maps, medium-scale feature maps and high-scale feature maps through P3 layer, P4 layer and P5 layer respectively, so as to provide rich feature information for the detection task of the neck network.

[0054] The neck network includes a feature extraction module and a feature fusion module, the feature extraction module includes a plurality of context anchor point modules, and the plurality of context anchor point modules are used for feature extraction on the feature maps of different layers of the backbone network. After the feature maps output by the P3 layer, the P4 layer and the P5 layer of the backbone network are extracted by the context anchor point modules, long-distance context information can be captured, and the center feature can be enhanced, so as to improve the detection accuracy.

[0055] Among them, the context anchor point module is a kind of attention mechanism module, the core idea is to capture long-distance context information through strip convolution, which is suitable for detecting small targets, because the features of these targets are usually distributed in the local area of the feature map, and stronger context information is needed to improve the detection accuracy, therefore, in the embodiment, since the sediment in the urine is usually a small particle or flocculation, the scale of the detected object is small, therefore, the use of the context anchor point module can better detect the sediment in the urine.

[0056] The feature fusion module includes a feature refinement module and a feature enhancement module, the feature refinement module includes a dynamic sampling module and a selective feature fusion module, the feature refinement module uses the dynamic sampling module and the selective feature fusion module to fuse the high-level features and the low-level features processed by the feature extraction module, the feature enhancement module includes a two-dimensional convolution module and a selective feature fusion module, the feature enhancement module uses the two-dimensional convolution module and the selective feature fusion module to fuse the low-level features and the high-level features processed by the feature extraction module, and the features fused by the feature refinement module and the feature enhancement module are input to each branch of the head network.

[0057] The feature fusion module includes two feature refinement modules and two feature enhancement modules. One feature refinement module fuses the P5 layer feature map and the P4 layer feature map processed by the feature extraction module, and the other feature refinement module fuses the P5 layer feature map and the P3 layer feature map processed by the feature extraction module. One feature enhancement module fuses the P5 layer feature map processed by the feature extraction module and one feature fused by the feature refinement module, and the other feature enhancement module fuses the P5 layer feature map processed by the feature extraction module and another feature fused by the feature refinement module. Finally, the features fused by the two feature refinement modules and the two feature enhancement modules are respectively input into four branches of the head network.

[0058] After the head network outputs the urine bag scale and the liquid level position, the urine volume data is determined according to the urine bag scale and the liquid level position. If the liquid level position is at a scale line, the scale line is directly taken as the urine volume data. If the liquid level position is between two adjacent scale lines, the urine volume data is determined by proportional calculation according to the distance between the liquid level position and the two scale lines. For example, assuming that the liquid level is between the scales "100ml" and "200ml", and the distance from the "100ml" scale is 1 / 3, then the urine volume is: 100ml+31×(200ml-100ml)=133.3ml.

[0059] In this embodiment, the urine information and the vital sign information of the patient on the nursing device body can reflect whether the posture of the patient is appropriate. For example, if there are more urine sediments or abnormal color, the nursing device is adjusted to a semi-recumbent position or a sitting position, so that the body of the patient is slightly inclined, which is helpful for the discharge of urine; if the body temperature of the patient is increased, the nursing device is adjusted to a more comfortable supine position with the head slightly raised, which is beneficial to heat dissipation; for the patient with abnormal blood pressure and heart rate, the nursing device is adjusted to a semi-recumbent position or a sitting position, which reduces the burden on the heart; and the like. Therefore, the posture analysis module analyzes the appropriate posture according to the urine information, the vital sign information and the current posture of the patient, so as to promote the recovery of the patient.

[0060] The posture analysis module includes an input layer, an LSTM layer, a feature fusion layer, a full connection layer and an output layer. The input features of the input layer include urine sediments, the urine color, the urine volume data, the vital sign parameters and the posture parameters of the current nursing device body. Before the urine sediments, the urine color, the urine volume data, the vital sign parameters and the posture parameters of the current nursing device body are input into the input layer, the urine sediments, the urine color and the urine volume data are converted into numerical features, the heart rate, the blood pressure and the body temperature data are standardized, and the heart rate, the blood pressure and the body temperature data are organized into sequences according to fixed time steps (such as every minute).

[0061] Wherein, LSTM is a special recurrent neural network architecture designed to address the gradient vanishing and gradient exploding problems encountered by traditional RNNs when processing long sequence data, and LSTM can process sequence data of various lengths and is suitable for various tasks such as time series prediction.

[0062] The LSTM layer processes the vital sign parameters to obtain extracted features. The LSTM layer is used to process the time series characteristics of the vital sign parameters. Since heart rate, blood pressure, and body temperature data have time series characteristics, i.e., there is a temporal dependence between data points, the trends of heart rate, blood pressure, and body temperature data can reflect the patient's physical condition, and LSTM can capture long-term dependencies in these time series data, thereby more accurately predicting and analyzing the patient's health status.

[0063] Since the vital sign parameters belong to time series data, and the urine sediment, urine color, urine volume data, and the posture parameter of the current nursing device body belong to static data, the feature fusion layer fuses the output features of the LSTM layer with the urine sediment, urine color, urine volume data, and the posture parameter of the current nursing device body to obtain fusion features, extracting higher-level feature representations; the fully connected layer extracts features from the fusion features to obtain output features, and the output layer obtains the posture parameter of the nursing device body according to the output features.

[0064] The posture parameter of the nursing device body includes the chair back angle, leg support height, and headrest position.

[0065] The adjustment component includes a controller and a power component. The controller receives the posture parameter of the nursing device body to generate a control signal, and the power component drives a motor or a hydraulic rod to adjust the posture of the nursing device body according to the control signal.

[0066] Embodiment 2

[0067] This embodiment provides an intelligent urology surgery postoperative nursing system, as shown in Figure 2 The system includes:

[0068] The device 10 described in Embodiment 1;

[0069] An information transmission module 11 is configured to transmit urine sediment, urine color, urine volume data, and vital sign parameters to a host computer;

[0070] A host computer 12 is configured to store and monitor the urine sediment, the urine color, the urine volume data, and the vital sign parameters, generate an alert signal when the data parameters meet a preset condition, and send the alert signal to an alert module;

[0071] The reminding module 13 is configured to generate light or sound information according to the reminding signal to remind the patient and the medical staff to perform the treatment.

[0072] In the embodiment, the information transmission module 11 can use a wired communication mode of RS-232, RS-485 or USB interface, or use a wireless communication technology of Wi-Fi, Bluetooth or ZigBee.

[0073] The host 12 receives data from the nursing device and stores the data in a local database or cloud storage. When a data parameter meets a preset condition, the host 12 generates a reminding signal. For example, when the urine volume is greater than a preset value, it indicates that the urine bag will be full, and at this time, the patient or the medical staff should be reminded to empty the urine bag. When the heart rate, body temperature or blood pressure is higher than a preset value, it indicates that the patient's physical condition suddenly deteriorates, and at this time, the medical staff needs to be reminded to perform corresponding emergency treatment.

[0074] The reminding module 13 displays the reminding information using an LED lamp or a display screen, or plays a reminding sound using a loudspeaker to remind the patient and the medical staff to perform corresponding treatment.

[0075] The above describes the basic principles of the disclosure in combination with specific embodiments, but it should be pointed out that the advantages, advantages, effects and the like mentioned in the disclosure are only examples and are not limited, and these advantages, advantages, effects and the like cannot be considered as the various embodiments of the disclosure must have. In addition, the above specific details of the disclosure are only for the purpose of example and for the purpose of understanding, and the above details do not limit the disclosure to be necessarily implemented with the above specific details.

[0076] Each embodiment in the specification is described in a progressive manner, and each embodiment focuses on the difference from other embodiments. The same or similar parts of each embodiment can be referred to each other. For system embodiments, since they basically correspond to method embodiments, the description is relatively simple, and the related parts can be referred to the part of the method embodiment.

[0077] The block diagram of the device, apparatus, equipment, system involved in the disclosure is only an illustrative example and is not intended to require or imply that the connection, arrangement, configuration must be as shown in the block diagram. As a person skilled in the art will recognize, these devices, apparatuses, equipment, systems can be connected, arranged, configured in any way. Words such as "include", "contain", "have" and the like are open words, which means "including but not limited to", and can be used interchangeably. The words "or" and "and" used herein mean the word "and / or", and can be used interchangeably unless the context clearly indicates otherwise. The word "such as" used herein means the phrase "such as but not limited to", and can be used interchangeably.

[0078] The methods and apparatus of the present disclosure can be implemented in a number of ways. For example, the methods and apparatus of the present disclosure can be implemented using software, hardware, firmware, or any combination of software, hardware, and firmware. The order of any steps described above is merely exemplary and the steps of the methods of the present disclosure need not be performed in the order described unless otherwise specified. Furthermore, in some embodiments, the present disclosure can also be implemented as a program for running on a computer or a processor to implement the methods according to the present disclosure. Thus, the present disclosure also covers a record medium storing the program in a non-transitory manner. The program can be realized in any of the following forms: object code, code of assembly language, code of interpreted language, code of machine language, high-level language, and the like.

[0079] It is also noted that the methods of the present disclosure can be implemented by a computer or processor running a software program to execute the steps of the methods. In addition, the present disclosure also covers a record medium storing the software program in a non-transitory manner. The software program can be realized in any of the following forms: object code, code of assembly language, code of interpreted language, code of machine language, high-level language, and the like.

[0080] The above description is given for illustrative and descriptive purposes. Furthermore, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although several example aspects and embodiments have been discussed above, those of ordinary skill in the art will recognize certain variations, modifications, changes, additions, and sub-combinations thereof.

Claims

1. An intelligent urological postoperative care device, characterized by, include: The nursing equipment itself is used to provide patients with a postoperative rest environment; A fixing component, disposed on the main body of the nursing device, is used to fix the patient's urine bag; An image acquisition device is installed near the fixed component to acquire images of the urine bag; A vital signs acquisition device, installed on the device body, is used to collect the patient's vital signs parameters; The analysis device includes an image analysis module and a posture analysis module. The image analysis module is used to obtain data on urine deposits, urine color, and urine volume based on the urine bag image. The posture analysis module is used to determine the posture parameters of the nursing device body based on the urine deposits, urine color, urine volume data, vital sign parameters, and the current posture parameters of the nursing device body. An adjustment component is used to adjust the posture of the nursing device body according to the posture parameters of the nursing device body; The image acquisition device includes a camera corresponding to the urine bag, which is used to acquire images of the urine bag, and the camera sends the acquired images of the urine bag to the analysis device; The image analysis module is based on the YOLO model and includes a backbone network, a neck network, and a head network. The head network outputs the urine bag scale, the urine sediment, the urine color, and the liquid level position.

2. The apparatus of claim 1, wherein, The nursing equipment itself is a recovery chair.

3. The apparatus of claim 1, wherein, The vital signs acquisition equipment includes a body temperature sensor, a blood pressure monitor, and a heart rate monitor, which are used to collect the patient's body temperature, blood pressure, and heart rate data, respectively.

4. The device according to claim 1, characterized in that, The head network includes a urine bag scale detection branch, a liquid level detection branch, a color detection branch, and a sediment detection branch. The urine bag scale detection branch, the liquid level detection branch, the color detection branch, and the sediment detection branch share features of the neck network.

5. The device according to claim 4, characterized in that, The neck network includes a feature extraction module and a feature fusion module. The feature extraction module includes multiple context anchor modules, which are used to extract features from feature maps of different layers of the backbone network. The feature fusion module includes a feature refinement module and a feature enhancement module. The feature refinement module fuses high-level features processed by the feature extraction module with low-level features. The feature enhancement module fuses high-level features processed by the feature extraction module with features fused by the feature refinement module. The features fused by the feature refinement module and the feature enhancement module are input to each branch of the head network.

6. The device according to claim 4, characterized in that, The urine volume data is determined based on the urine bag scale and the liquid level position. If the liquid level position is at a scale line, the scale line is directly used as the urine volume data. If the liquid level position is between two adjacent scale lines, the urine volume data is determined by proportional calculation based on the distance between the liquid level position and the two scale lines.

7. The device according to claim 1, characterized in that, The posture parameters of the nursing device include the backrest angle, leg support height, and headrest position.

8. The device according to claim 1, characterized in that, The posture analysis module includes an input layer, an LSTM layer, a feature fusion layer, a fully connected layer, and an output layer. The input features of the input layer include the urine sediment, the urine color, the urine volume data, the vital signs parameters, and the posture parameters of the current nursing device. The LSTM layer processes the vital signs parameters to obtain extracted features. The feature fusion layer fuses the extracted features with the urine sediment, urine color, urine volume data, and the posture parameters of the current nursing device to obtain fused features. The fully connected layer extracts features from the fused features to obtain output features. The output layer obtains the posture parameters of the nursing device based on the output features.

9. The device according to claim 1, characterized in that, The adjustment component includes a controller and a power component. The controller receives the posture parameters of the nursing device body to generate a control signal, and the power component drives a motor or hydraulic rod to adjust the posture of the nursing device body according to the control signal.

10. An intelligent postoperative care system for urological surgery, characterized in that, include: The device according to any one of claims 1-9; The information transmission module is used to transmit data on urine sediment, urine color, urine volume, and vital signs to the host computer. The host is used to store and monitor the urine sediment, urine color, urine volume data and vital sign parameters. When the data parameters meet preset conditions, an alert signal is generated and sent to the alert module. The reminder module is used to generate light or sound information based on the reminder signal to remind patients and medical staff to take action.

Images