Intelligent dynamic pressure distribution monitoring system based on sickbed

Abstract

The invention relates to the technical field of medical instruments, and discloses an intelligent dynamic pressure distribution monitoring system based on a sickbed, and the system comprises an image collection module which is used for collecting an image of a patient in the sickbed at a fixed angle according to a fixed time interval; the image processing module is used for comparing the acquired image with the image of the sickbed to obtain a posture profile diagram of the patient in the sickbed; the clustering module is used for clustering the posture profile diagrams of the patients and determining feature postures of the patients; the blood pressure and flow monitoring module is used for optically monitoring the skin of the patient to obtain the blood pressure and flow of the subcutaneous tissue of each part of the patient on different transverse plates; the planning module is used for controlling the height of each transverse plate of the sickbed according to the blood pressure flow of the subcutaneous tissue of each part of the patient on different transverse plates and the posture profile diagram of the patient on the sickbed.

Description

Technical Field

[0001] The present invention relates to the field of medical devices, and more particularly, to an intelligent dynamic pressure distribution monitoring system based on a hospital bed. Background Art

[0002] In patients who need to stay in bed for a long time for treatment or rehabilitation, the blood circulation in a certain part of the body is obstructed due to prolonged pressure on that part, and the tissues cannot get enough oxygen and nutrients, which eventually causes damage or even necrosis of the skin and the tissues underneath.

[0003] However, the existing anti-bedsore bed is a bed body composed of multiple horizontal boards, and the height of the horizontal boards is controlled by fixed logic to achieve partial decompression of the patient's soft tissue.

[0004] Due to varying patient bed rest positions, the forces acting on the subcutaneous tissue vary across the patient, leading to varying risks of bedsores. Fixed-logic horizontal control leads to repeated, ineffective decompression of the patient's low-risk subcutaneous tissue. Simultaneously, while decompressing low-risk subcutaneous tissue, the pressure on the patient's high-risk subcutaneous tissue increases, increasing the risk of rupture and bedsores. Summary of the Invention

[0005] The present invention provides an intelligent dynamic pressure distribution monitoring system based on a hospital bed, which solves the technical problems raised in the background technology.

[0006] In the first aspect, an intelligent dynamic pressure distribution monitoring system based on a hospital bed includes an image acquisition module, an image processing module, a clustering module, a blood pressure and flow monitoring module, and a planning module:

[0007] An image acquisition module, used to acquire images of the patient in bed at a fixed angle and at fixed time intervals;

[0008] An image processing module is used to compare the collected image with an image of an unoccupied bed to obtain a contour image of the patient's posture in the bed;

[0009] A clustering module, used to cluster the patient's posture profile map to determine the patient's characteristic posture;

[0010] The blood pressure flow monitoring module is used to optically monitor the patient's skin and obtain the blood pressure flow of the subcutaneous tissue of each part of the patient on different horizontal boards;

[0011] The planning module is used to control the height of each horizontal board of the bed according to the blood pressure flow of the subcutaneous tissue of each part of the patient on different horizontal boards and the patient's posture contour map on the bed.

[0012] Furthermore, the images of the patient in the bed are collected at fixed angles and fixed time intervals, including:

[0013] Adjust the camera's shooting angle so that the camera captures the image of the bed at a vertical angle;

[0014] Manually select the camera's captured image and discard images outside the manually selected image.

[0015] Furthermore, the collected image is compared with an image of an unoccupied bed to obtain a contour map of the patient's posture in the bed, including:

[0016] Collect an image of an empty bed and set it as a reference image;

[0017] Collect the image of the patient in bed at the i-th moment, and overlap the image with the reference image to obtain an overlapped image;

[0018] Based on the overlapping images, the patient's posture contour map on the bed is obtained.

[0019] Furthermore, the patient's posture profile is clustered to determine the patient's characteristic posture, including:

[0020] Setting a first preset time period, and obtaining a posture profile of the patient at each moment within the time period;

[0021] The patient's characteristic posture is obtained by clustering the patient's posture contour map at each moment in the time period; the characteristic posture represents the patient's common bed rest posture.

[0022] Furthermore, the patient's skin is optically monitored to obtain the blood pressure flow of the patient's subcutaneous tissue on different horizontal plates, including:

[0023] During a first preset time period, blood pressure and flow monitoring modules are spaced apart on the back of the patient's trunk, wherein the blood pressure and flow monitoring modules include a light emitting unit and a monitoring unit;

[0024] a light-emitting unit, configured to emit red light at a fixed time interval and a fixed intensity toward the patient's subcutaneous tissue;

[0025] a monitoring unit for monitoring the intensity of red light reflected by the light emitting unit toward the patient's subcutaneous tissue;

[0026] At fixed time intervals, the highest and lowest light intensities of each part of the patient's subcutaneous tissue are obtained through optical monitoring;

[0027] The blood pressure flow of the subcutaneous tissue of each part of the patient on different horizontal plates is calculated based on the highest light intensity and the lowest light intensity of the subcutaneous tissue of each part of the patient.

[0028] Furthermore, matching the patient's characteristic posture with the blood pressure flow in the first preset time period includes:

[0029] Matching the patient's blood pressure flow at each moment with the patient's posture profile at each moment to obtain the patient's posture profile at each moment within a first preset time period and the blood pressure flow corresponding to each posture profile;

[0030] The blood pressure flow of the patient in a first preset time period is clustered according to the patient's characteristic posture, and average blood pressure flow data of each part of the patient's subcutaneous tissue in each characteristic posture is determined.

[0031] Furthermore, the height of each horizontal board of the bed is controlled according to the blood pressure flow of the subcutaneous tissue of each part of the patient on different horizontal boards and the patient's posture contour map on the bed, including:

[0032] Acquire an image of the patient at the kth moment within a second preset time period, and obtain a posture contour map of the patient at the kth moment by comparing it with the reference image;

[0033] Fitting the patient's posture contour map at the kth moment to the patient's characteristic posture;

[0034] If the posture contour at the kth moment fails to fit the characteristic posture, the posture at the kth moment is determined to be the connecting posture between the characteristic postures, and the heights of the horizontal boards of the bed are not adjusted;

[0035] If the posture contour map at the kth moment is successfully fitted to the characteristic posture, then the blood pressure flow data of each part of the patient's subcutaneous tissue at the kth moment is approximately the average blood pressure flow data of each part of the patient's subcutaneous tissue under the characteristic posture;

[0036] Based on the blood pressure and flow data of each part of the patient's subcutaneous tissue at the kth moment, the horizontal board of the bed that needs to be adjusted is determined.

[0037] Furthermore, based on the blood pressure flow data of each part of the patient's subcutaneous tissue at the kth moment, the bed board that needs to be adjusted is determined, including:

[0038] Set low blood pressure flow data and high blood pressure flow data of each part of subcutaneous tissue;

[0039] Compare the blood pressure flow data of each part of the patient's subcutaneous tissue at the kth moment with the low blood pressure flow data and high blood pressure flow data respectively;

[0040] If the blood pressure flow data of the p-th part of the subcutaneous tissue of the patient at the k-th moment is greater than the high blood pressure flow data of the p-th part of the subcutaneous tissue, it is determined that the p-th part of the subcutaneous tissue of the patient is congested;

[0041] If the blood pressure flow data of the p-th part of the subcutaneous tissue of the patient at the k-th moment is between the low blood pressure flow data and the high blood pressure flow data of the p-th part of the subcutaneous tissue, then the p-th part of the subcutaneous tissue of the patient is normal;

[0042] If the blood pressure flow data of the p-th part of the subcutaneous tissue of the patient at the k-th moment is less than the standard blood pressure flow data of the p-th part of the subcutaneous tissue, it is determined that the p-th part of the subcutaneous tissue of the patient is anemic;

[0043] Mark the areas of the patient's subcutaneous tissue that are anemic and congested, including:

[0044] The patient's posture contour map at the kth moment is segmented by the horizontal plate in the reference image, and the segmented map and the horizontal plate are matched one by one;

[0045] If there is anemic subcutaneous tissue in the qth segmentation image, the horizontal plate matched with the qth segmentation image is first marked;

[0046] If all subcutaneous tissues in the qth segmentation image are congested, a second mark is performed on the horizontal plate that matches the qth segmentation image.

[0047] Furthermore, at the kth moment within the second preset time period, the horizontal board with the first mark is lifted, the horizontal board with the second mark is lowered, and the other horizontal boards remain stationary.

[0048] In a second aspect, a bed-based intelligent dynamic pressure distribution monitoring method is applied to the system, comprising:

[0049] Step 1: Capture images of the patient in bed at a fixed angle and at fixed time intervals;

[0050] Step 2: Compare the collected image with the image of the unoccupied bed to obtain a contour map of the patient's posture in the bed;

[0051] Step 3: clustering the patient's posture profile to determine the patient's characteristic posture;

[0052] Step 4: Optically monitor the patient's skin to obtain the blood pressure flow of the patient's subcutaneous tissue on different horizontal plates;

[0053] Step 5: Control the height of each horizontal board of the bed according to the blood pressure flow of the subcutaneous tissue of each part of the patient on different horizontal boards and the patient's posture contour map on the bed.

[0054] The beneficial effects of the present invention are: by identifying the different posture contours of the patient and clustering the patient's posture to obtain characteristic postures, the blood pressure flow of the subcutaneous tissue of each part of each characteristic posture is determined respectively, and then the patient is personalized with the decompression, avoiding ineffective decompression of the patient, which is beneficial to avoiding the risk of bedsores in the patient, and at the same time increasing the patient's comfort and safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1This is a module diagram of an intelligent dynamic pressure distribution monitoring system based on a hospital bed according to the present invention;

[0056] Figure 2 This is a flow chart of an intelligent dynamic pressure distribution monitoring method based on a hospital bed according to the present invention. DETAILED DESCRIPTION

[0057] The subject matter described herein will now be discussed with reference to exemplary embodiments. It should be understood that these embodiments are discussed solely to enable those skilled in the art to better understand and implement the subject matter described herein, and that the functions and arrangements of the elements discussed may be varied without departing from the scope of this specification. Various examples may omit, substitute, or add various processes or components as needed. Furthermore, features described for some examples may be combined in other examples.

[0058] like Figures 1 and 2 As shown, an intelligent dynamic pressure distribution monitoring system based on a hospital bed includes an image acquisition module, an image processing module, a clustering module, a blood pressure and flow monitoring module, and a planning module:

[0059] An image acquisition module, used to acquire images of the patient in bed at a fixed angle and at fixed time intervals;

[0060] An image processing module is used to compare the collected image with an image of an unoccupied bed to obtain a contour image of the patient's posture in the bed;

[0061] A clustering module, used to cluster the patient's posture profile map to determine the patient's characteristic posture;

[0062] The blood pressure flow monitoring module is used to optically monitor the patient's skin and obtain the blood pressure flow of the subcutaneous tissue of each part of the patient on different horizontal boards;

[0063] The planning module is used to control the height of each horizontal board of the bed according to the blood pressure flow of the subcutaneous tissue of each part of the patient on different horizontal boards and the patient's posture contour map on the bed.

[0064] In one embodiment of the present invention, capturing images of a patient in a hospital bed at a fixed angle and at fixed time intervals includes:

[0065] Adjust the camera's shooting angle so that the camera captures the image of the bed at a vertical angle;

[0066] Manually select the camera's captured image and discard images outside the manually selected image.

[0067] In one embodiment of the present invention, the following steps are included:

[0068] Step 201, adjusting the shooting angle of the camera so that its optical axis is perpendicular to the plane of the bed, that is, the camera shoots the bed at a vertical angle;

[0069] Step 202: At a fixed time interval Δt, collect an image sequence I of the patient on the bed. raw ;

[0070] I raw ={a,b,t i}, where t i represents the i-th moment, a and b represent the length and width of the image respectively;

[0071] Step 203: manually set a fixed-size frame selection area, retain the data within the frame selection area, and obtain a frame selection image.

[0072] It should be noted that the frame selection may include an outer frame and an inner frame. The outer frame is used to frame the bed image and discard the image outside the outer frame. The inner frame is used to be set according to the actual position of the horizontal board for subsequent segmentation processing of the patient's posture contour map.

[0073] In one embodiment of the present invention, the collected image is compared with an image of an unoccupied bed to obtain a patient's posture profile in bed. The collected image is compared with an image of an unoccupied bed to obtain a patient's posture profile in bed, including:

[0074] Collect an image of an empty bed and set it as a reference image;

[0075] Collect the image of the patient in bed at the i-th moment, and overlap the image with the reference image to obtain an overlapped image;

[0076] Based on the overlapping images, the patient's posture contour map on the bed is obtained.

[0077] In one embodiment of the present invention, the following steps are included:

[0078] Step 301: select a framed image of an unoccupied bed as a reference image;

[0079] Step 302: Calculate a difference image between the reference image and the framed image at the i-th moment;

[0080] Step 303 : Set a binarization threshold, binarize the difference image, and obtain a Boolean matrix of the posture profile map. The elements with a value of 1 in the Boolean matrix represent the posture profile of the patient.

[0081] In one embodiment of the present invention, clustering the patient's posture profile to determine the patient's characteristic posture includes:

[0082] Setting a first preset time period, and obtaining a posture profile of the patient at each moment within the time period;

[0083] The patient's characteristic posture is obtained by clustering the patient's posture contour map at each moment in the time period; the characteristic posture represents the patient's common bed rest posture.

[0084] In one embodiment of the present invention, the following steps are included:

[0085] Step 401, select a preset time period, including N moments;

[0086] Step 402, obtaining a posture profile at each moment;

[0087] In step 403, the Dice coefficient is used to define the similarity metric, and the formula is as follows:

[0088] Among them, D Dice (C(t i ),C(t j )) represents the posture contour graph C(t i ) and posture contour map C(t j ), C(t i ) represents the preset time period t i The posture contour map at the moment, C(t j ) represents the preset time period t j A profile of the posture at the moment;

[0089] Step 404: cluster the N posture profiles using K-means to obtain K clusters;

[0090] Step 405 : For each cluster, calculate the average posture profile of the cluster, and determine the average posture profile as a characteristic posture.

[0091] In one embodiment of the present invention, optical monitoring of the patient's skin is performed to obtain blood pressure flow of subcutaneous tissue of various parts of the patient on different horizontal plates, including:

[0092] During a first preset time period, blood pressure and flow monitoring modules are spaced apart on the back of the patient's trunk, wherein the blood pressure and flow monitoring modules include a light emitting unit and a monitoring unit;

[0093] a light-emitting unit, configured to emit red light at a fixed time interval and a fixed intensity toward the patient's subcutaneous tissue;

[0094] a monitoring unit for monitoring the intensity of red light reflected by the light emitting unit toward the patient's subcutaneous tissue;

[0095] At fixed time intervals, the highest and lowest light intensities of each part of the patient's subcutaneous tissue are obtained through optical monitoring;

[0096] The blood pressure flow of the subcutaneous tissue of each part of the patient on different horizontal plates is calculated based on the highest light intensity and the lowest light intensity of the subcutaneous tissue of each part of the patient.

[0097] It should be noted that the patient is required to wear the blood pressure and flow monitoring module only during the first preset time period.

[0098] In one embodiment of the present invention, the following steps are included:

[0099] Step 501, setting up a plurality of blood pressure and flow monitoring modules on the back of the patient's torso;

[0100] Step 502: A flexible red light plate and a micro-monitoring device are configured as a blood pressure flow monitoring module. The flexible red light plate emits red light of a fixed intensity at a fixed time interval toward the patient's subcutaneous tissue. The micro-monitoring device monitors the intensity of red light reflected by the adjacent flexible red light plate from the subcutaneous tissue.

[0101] Step 503: During each adjacent moment, monitor the subcutaneous tissue of each part of the patient and record the maximum and minimum reflected light intensities;

[0102] Step 504: Calculate the blood pressure flow at each location using the following formula:

[0103] Q(p)=f(R max (p),R min (p)); where Q(p) is the blood pressure flow at p; R max (p) is the maximum red light intensity at point p; R min (p) is the minimum red light intensity at p; f(·) is a function obtained based on a simulation experiment that maps the maximum red light intensity at p and the minimum red light intensity at p to blood pressure flow. For example, the maximum red light intensity and the minimum red light intensity at p as well as the blood pressure flow data are collected experimentally, and then f(·) is obtained by neural network fitting or least squares fitting. Preferably, the f(·) obtained from the experiment is approximately used for patients of the same body type. For example, the body type is divided by height and weight. For patients of the same body type, the function that maps the maximum red light intensity and the minimum red light intensity at p on their body to blood pressure flow is the same.

[0104] In one embodiment of the present invention, matching the patient's characteristic posture with the blood pressure flow within the first preset time period includes:

[0105] Matching the patient's blood pressure flow at each moment with the patient's posture profile at each moment to obtain the patient's posture profile at each moment within a first preset time period and the blood pressure flow corresponding to each posture profile;

[0106] The blood pressure flow of the patient in a first preset time period is clustered according to the patient's characteristic posture, and average blood pressure flow data of each part of the patient's subcutaneous tissue in each characteristic posture is determined.

[0107] In one embodiment of the present invention, the following steps are included:

[0108] Step 601: within a first preset time period, for each time t i , the patient's blood pressure flow data Q(p,t i ) and posture contour map C(t i ) to match;

[0109] Step 602: for each characteristic posture, determine the corresponding time set;

[0110] Step 603: Calculate the average blood pressure flow of the subcutaneous tissue of each part of the patient in each characteristic posture to obtain the average blood pressure flow of the subcutaneous tissue of each part of the patient in each characteristic posture.

[0111] In one embodiment of the present invention, the height of each horizontal board of the hospital bed is controlled according to the blood pressure flow of the subcutaneous tissue of each part of the patient on different horizontal boards and the patient's posture contour map on the bed, including:

[0112] Acquire an image of the patient at the kth moment within a second preset time period, and obtain a posture contour map of the patient at the kth moment by comparing it with the reference image;

[0113] Fitting the patient's posture contour map at the kth moment to the patient's characteristic posture;

[0114] If the posture contour at the kth moment fails to fit the characteristic posture, the posture at the kth moment is determined to be the connecting posture between the characteristic postures, and the heights of the horizontal boards of the bed are not adjusted;

[0115] If the posture contour map at the kth moment is successfully fitted to the characteristic posture, then the blood pressure flow data of each part of the patient's subcutaneous tissue at the kth moment is approximately the average blood pressure flow data of each part of the patient's subcutaneous tissue under the characteristic posture;

[0116] Based on the blood pressure and flow data of each part of the patient's subcutaneous tissue at the kth moment, the horizontal board of the bed that needs to be adjusted is determined.

[0117] In one embodiment of the present invention, the following steps are included:

[0118] Step 701: At the kth moment in the second preset time period, an image I={a, b, t k}, and obtain the patient's posture contour image C(t k );

[0119] Step 702: C(t k ) and characteristic poses {P1,P1,…,P k ,} perform similarity calculation and select the feature posture with the highest similarity;

[0120] Step 703, performing fitting judgment;

[0121] If the similarity of the characteristic posture with the highest similarity is greater than a preset threshold, the patient's posture is determined to be the characteristic posture;

[0122] If the similarity of the characteristic posture with the highest similarity is less than a preset threshold, the patient posture is determined to be a connecting posture between the characteristic postures;

[0123] Step 704: If the fitting is successful, the time t k The blood pressure flow data is approximately the average blood pressure flow under the characteristic posture of the fitting.

[0124] In one embodiment of the present invention, determining the bed board that needs to be adjusted based on the blood pressure flow data of each part of the patient's subcutaneous tissue at the kth moment includes:

[0125] Set low blood pressure flow data and high blood pressure flow data of each part of subcutaneous tissue;

[0126] Compare the blood pressure flow data of each part of the patient's subcutaneous tissue at the kth moment with the low blood pressure flow data and high blood pressure flow data respectively;

[0127] If the blood pressure flow data of the p-th part of the subcutaneous tissue of the patient at the k-th moment is greater than the high blood pressure flow data of the p-th part of the subcutaneous tissue, it is determined that the p-th part of the subcutaneous tissue of the patient is congested;

[0128] If the blood pressure flow data of the p-th part of the subcutaneous tissue of the patient at the k-th moment is between the low blood pressure flow data and the high blood pressure flow data of the p-th part of the subcutaneous tissue, then the p-th part of the subcutaneous tissue of the patient is normal;

[0129] If the blood pressure flow data of the p-th part of the subcutaneous tissue of the patient at the k-th moment is less than the standard blood pressure flow data of the p-th part of the subcutaneous tissue, it is determined that the p-th part of the subcutaneous tissue of the patient is anemic;

[0130] Mark the areas of the patient's subcutaneous tissue that are anemic and congested, including:

[0131] The patient's posture contour map at the kth moment is segmented by the horizontal plate in the reference image, and the segmented map and the horizontal plate are matched one by one;

[0132] If there is anemic subcutaneous tissue in the qth segmentation image, the horizontal plate matched with the qth segmentation image is first marked;

[0133] If all subcutaneous tissues in the qth segmentation image are congested, a second mark is performed on the horizontal plate that matches the qth segmentation image.

[0134] In one embodiment of the present invention, the following steps are included:

[0135] Step 801, for each part of the patient's subcutaneous tissue, set a low blood pressure flow threshold and a high blood pressure flow threshold;

[0136] Step 802 , comparing the average blood pressure flow of each part of the patient's subcutaneous tissue with a low blood pressure flow threshold and a high blood pressure flow threshold to determine its state as congestion, normal, or anemia;

[0137] Step 803, marking all anemic subcutaneous tissues;

[0138] Step 804 , segmenting the patient's posture contour image according to the portion overlapping with the horizontal board to obtain a segmentation image;

[0139] Step 805, for each horizontal plate;

[0140] If an anemia mark is present, the horizontal board is first marked;

[0141] If all are congestion marks, a second mark is made on the horizontal board.

[0142] In one embodiment of the present invention, at the kth moment within the second preset time period, the horizontal board with the first mark is lifted, the horizontal board with the second mark is lowered, and the remaining horizontal boards remain stationary.

[0143] In one embodiment of the present invention, the following steps are included:

[0144] Step 901, determine the adjustment range of the horizontal plate and set several gears;

[0145] Step 902, analyzing the markers in the segmentation graph of the qth horizontal plate match;

[0146] If the segmentation map matching the qth horizontal plate includes m first markers, then the height of the qth horizontal plate is reduced to f(m) accordingly;

[0147] If the marks of the segmentation map matched by the qth horizontal plate are all the second marks and there are n of them, then the height of the corresponding raised qth horizontal plate is f(n);

[0148] If the segmentation map matched by the qth horizontal board is not marked, the height of the qth horizontal board remains unchanged.

[0149] A bed-based intelligent dynamic pressure distribution monitoring method, applied to the bed-based intelligent dynamic pressure distribution monitoring system, comprises:

[0150] Step 1: Capture images of the patient in bed at a fixed angle and at fixed time intervals;

[0151] Step 2: Compare the collected image with the image of the unoccupied bed to obtain a contour map of the patient's posture in the bed;

[0152] Step 3: clustering the patient's posture profile to determine the patient's characteristic posture;

[0153] Step 4: Optically monitor the patient's skin to obtain the blood pressure flow of the patient's subcutaneous tissue on different horizontal plates;

[0154] Step 5: Control the height of each horizontal board of the bed according to the blood pressure flow of the subcutaneous tissue of each part of the patient on different horizontal boards and the patient's posture contour map on the bed.

[0155] The above describes the embodiments of this embodiment, but this embodiment is not limited to the above specific implementation methods. The above specific implementation methods are merely illustrative and not restrictive. Ordinary technicians in this field can also make many forms based on the inspiration of this embodiment, all of which are protected by this embodiment.

Claims

1. An intelligent dynamic pressure distribution monitoring system based on a hospital bed, characterized in that: Including image acquisition module, image processing module, clustering module, blood pressure and flow monitoring module and planning module: An image acquisition module is used to acquire images of the patient in the bed at a fixed angle and at fixed time intervals; An image processing module is used to compare the collected image with an image of an unoccupied bed to obtain a contour image of the patient's posture in the bed; A clustering module, used to cluster the patient's posture profile map to determine the patient's characteristic posture; The blood pressure flow monitoring module is used to optically monitor the patient's skin and obtain the blood pressure flow of the subcutaneous tissue of each part of the patient on different horizontal boards; The planning module is used to control the height of each horizontal board of the bed according to the blood pressure flow of the subcutaneous tissue of each part of the patient on different horizontal boards and the patient's posture contour map on the bed.

2. The intelligent dynamic pressure distribution monitoring system based on a hospital bed according to claim 1, characterized in that: The images of the patient in the bed are collected at fixed angles and time intervals, including: Adjust the camera's shooting angle so that the camera captures the image of the bed at a vertical angle; Manually select the camera's captured image and discard images outside the manually selected image.

3. The intelligent dynamic pressure distribution monitoring system based on a hospital bed according to claim 1, characterized in that: Compare the captured image with the image of the unoccupied bed to obtain a contour map of the patient's posture in bed, including: Collect an image of an empty bed and set it as a reference image; Collect the image of the patient in bed at the i-th moment, and overlap the image with the reference image to obtain an overlapped image; Based on the overlapping images, the patient's posture contour map on the bed is obtained.

4. The intelligent dynamic pressure distribution monitoring system based on a hospital bed according to claim 1, characterized in that: Cluster the patient's posture profile to determine the patient's characteristic posture, including: Setting a first preset time period, and obtaining a posture profile of the patient at each moment within the time period; The patient's characteristic posture is obtained by clustering the patient's posture contour map at each moment in the time period; the characteristic posture represents the patient's common bed rest posture.

5. The intelligent dynamic pressure distribution monitoring system based on a hospital bed according to claim 4, characterized in that: Optical monitoring of the patient's skin is performed to obtain the blood pressure flow of the patient's subcutaneous tissue on different horizontal panels, including: During a first preset time period, blood pressure and flow monitoring modules are spaced apart on the back of the patient's trunk, wherein the blood pressure and flow monitoring modules include a light emitting unit and a monitoring unit; a light-emitting unit, configured to emit red light at a fixed time interval and a fixed intensity toward the patient's subcutaneous tissue; a monitoring unit for monitoring the intensity of red light reflected by the light emitting unit toward the patient's subcutaneous tissue; At fixed time intervals, the highest and lowest light intensities of each part of the patient's subcutaneous tissue are obtained through optical monitoring; The blood pressure flow of the subcutaneous tissue of each part of the patient on different horizontal plates is calculated based on the highest light intensity and the lowest light intensity of the subcutaneous tissue of each part of the patient.

6. The intelligent dynamic pressure distribution monitoring system based on a hospital bed according to claim 5, characterized in that: Matching the patient's characteristic posture with the blood pressure flow during the first preset time period includes: Matching the patient's blood pressure flow at each moment with the patient's posture profile at each moment to obtain the patient's posture profile at each moment within a first preset time period and the blood pressure flow corresponding to each posture profile; The blood pressure flow of the patient in a first preset time period is clustered according to the patient's characteristic posture, and average blood pressure flow data of each part of the patient's subcutaneous tissue in each characteristic posture is determined.

7. The intelligent dynamic pressure distribution monitoring system based on a hospital bed according to claim 3, characterized in that: The height of each horizontal board of the bed is controlled according to the blood pressure flow of the subcutaneous tissue of each part of the patient on different horizontal boards and the patient's posture contour diagram on the bed, including: Acquire an image of the patient at the kth moment within a second preset time period, and obtain a posture contour map of the patient at the kth moment by comparing it with the reference image; Fitting the patient's posture contour map at the kth moment to the patient's characteristic posture; If the posture contour at the kth moment fails to fit the characteristic posture, the posture at the kth moment is determined to be the connecting posture between the characteristic postures, and the heights of the horizontal boards of the bed are not adjusted; If the posture contour map at the kth moment is successfully fitted to the characteristic posture, then the blood pressure flow data of each part of the patient's subcutaneous tissue at the kth moment is approximately the average blood pressure flow data of each part of the patient's subcutaneous tissue under the characteristic posture; Based on the blood pressure and flow data of each part of the patient's subcutaneous tissue at the kth moment, the horizontal board of the bed that needs to be adjusted is determined.

8. The intelligent dynamic pressure distribution monitoring system based on a hospital bed according to claim 7, characterized in that: Based on the blood pressure and flow data of each part of the patient's subcutaneous tissue at the kth moment, determine the bed crossbar that needs to be adjusted, including: Set low blood pressure flow data and high blood pressure flow data of each part of subcutaneous tissue; Compare the blood pressure flow data of each part of the patient's subcutaneous tissue at the kth moment with the low blood pressure flow data and high blood pressure flow data respectively; If the blood pressure flow data of the p-th part of the subcutaneous tissue of the patient at the k-th moment is greater than the high blood pressure flow data of the p-th part of the subcutaneous tissue, it is determined that the p-th part of the subcutaneous tissue of the patient is congested; If the blood pressure flow data of the p-th part of the subcutaneous tissue of the patient at the k-th moment is between the low blood pressure flow data and the high blood pressure flow data of the p-th part of the subcutaneous tissue, then the p-th part of the subcutaneous tissue of the patient is normal; If the blood pressure flow data of the p-th part of the subcutaneous tissue of the patient at the k-th moment is less than the standard blood pressure flow data of the p-th part of the subcutaneous tissue, it is determined that the p-th part of the subcutaneous tissue of the patient is anemic; Mark the areas of the patient's subcutaneous tissue that are anemic and congested, including: The patient's posture contour map at the kth moment is segmented by the horizontal plate in the reference image, and the segmented map and the horizontal plate are matched one by one; If there is anemic subcutaneous tissue in the qth segmentation image, the horizontal plate matched with the qth segmentation image is first marked; If all subcutaneous tissues in the qth segmentation image are congested, a second mark is performed on the horizontal plate that matches the qth segmentation image.

9. The intelligent dynamic pressure distribution monitoring system based on a hospital bed according to claim 8, characterized in that: At the kth moment in the second preset time period, the horizontal board with the first mark is lifted, the horizontal board with the second mark is lowered, and the other horizontal boards remain stationary.

10. An intelligent dynamic pressure distribution monitoring method based on a hospital bed, applied to the system according to any one of claims 1 to 9, characterized in that: include: Step 1: Capture images of the patient in bed at a fixed angle and at fixed time intervals; Step 2: Compare the collected image with the image of the unoccupied bed to obtain a contour map of the patient's posture in the bed; Step 3: clustering the patient's posture profile to determine the patient's characteristic posture; Step 4: Optically monitor the patient's skin to obtain the blood pressure flow of the patient's subcutaneous tissue on different horizontal plates; Step 5: Control the height of each horizontal board of the bed according to the blood pressure flow of the subcutaneous tissue of each part of the patient on different horizontal boards and the patient's posture contour map on the bed.

Images