Patient information monitoring method and device based on in-hospital smart wristband

Through the monitoring system combining intelligent wristbands with hospital three-dimensional models, patient information is collected and displayed in real time, solving the problem that existing technology cannot monitor patients in real time, and fully automatic intelligent supervision is achieved, reducing safety risks and management difficulties.

CN118629569BActive Publication Date: 2024-11-15CHINA JAPAN FRIENDSHIP HOSPITAL
View PDF 11 Cites 0 Cited by

Patent Information

Application Number
CN202411094687.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-10
Publication Date
2024-11-15
Estimated Expiration
2044-08-10

AI Technical Summary

Technical Problem

The existing hospital wristbands cannot monitor patients in real time, resulting in failure to respond to emergencies in a timely manner, high-risk patients are lost or discharged from the hospital area, and severe patients need to inspect frequently to prevent emergencies.

Method used

Using a patient information monitoring method based on the in-hospital smart wristband, the patient information is collected through the smart wristband and combined with the hospital's three-dimensional model page to display the patient icon information in real time, including blood pressure, bed status and monitoring level, and using bed detection equipment and alarm equipment to achieve it Off-bed monitoring and positioning, and promptly alarm and positioning.

Benefits of technology

It has realized a fully automatic and full-region intelligent supervision model, accurate off-bed monitoring, positioning and alarm, reducing safety risks, improving the level of intelligent management, and reducing medical disputes.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118629569B_ABST
    Figure CN118629569B_ABST
Patent Text Reader

Abstract

The present application relates to the field of patient information monitoring, and specifically to a method and device for monitoring patient information based on an in-hospital smart wristband. A specific implementation of the method includes: displaying the icon information of each patient who has worn a smart wristband in a three-dimensional model page of the hospital; in response to detecting the patient leaving bed information sent by the target bed detection device, modifying the patient bed status included in the patient icon information corresponding to the target bed detection device to the leaving bed status; locating the coordinate position information of the smart wristband corresponding to the patient icon information; in response to determining that the coordinate position information is not within the first preset range, controlling the associated patient alarm device to issue an alarm prompt; controlling each smart wristband that has been worn to collect the patient's blood pressure information in real time. This implementation method combines the three-dimensional model of the hospital to display the patient's real-time location, movement trajectory, out-of-bounds alarm and information push in a three-dimensional visual form, thereby improving the level of intelligent management and reducing safety risks.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of patient information monitoring, and specifically to a method and device for monitoring patient information based on an in-hospital smart wristband. Background Art

[0002] Currently, patients in hospitals are required to wear wristbands to identify users and verify information. At present, wristbands in hospitals cannot monitor patients in real time. Therefore, there are usually the following technical problems: patients who go for examinations sometimes have emergencies during the examination, and ordinary wristbands do not have reminders and alarms, and cannot respond in time; elderly patients or patients with dementia are prone to getting lost in the hospital, causing accidents and great risks; ordinary patients change their own clothes and leave the hospital area at will, causing unknown invisible risks and malignant effects; critically ill patients require first-level care, and the patient's condition must be inspected every hour, and the possibility of sudden conditions in patients during the time gap is inevitable. Summary of the invention

[0003] The content of this application is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this application is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0004] Some embodiments of the present application propose a patient information monitoring method, a computer device, and a computer-readable storage medium based on an in-hospital smart wristband to solve the technical problems mentioned in the above background technology section.

[0005] In the first aspect, some embodiments of the present application provide a patient information monitoring method based on an in-hospital smart wristband, the method comprising: in response to detecting a viewing operation on the patient information of the smart wristband, displaying the icon information of each patient who has worn the smart wristband in the associated hospital three-dimensional model page, wherein the patient icon information includes: user name, user number, user hospitalization information, blood pressure information, patient bed status and patient monitoring level, and the smart wristband has an identification QR code, which is used to identify the patient information; in response to detecting the patient leaving bed information sent by the target bed detection device, modifying the patient bed status included in the patient icon information corresponding to the above-mentioned target bed detection device to the leaving bed status, and determining whether the patient monitoring level included in the above-mentioned patient icon information is Satisfy the first monitoring condition; in response to determining that the patient monitoring level included in the above-mentioned patient icon information satisfies the first monitoring condition, control the associated patient alarm device to issue an alarm prompt; in response to determining that the patient monitoring level included in the above-mentioned patient icon information does not satisfy the first monitoring condition, determine whether the above-mentioned patient monitoring level satisfies the second monitoring condition; in response to determining that the above-mentioned patient monitoring level satisfies the second monitoring condition, locate the coordinate position information of the smart wristband corresponding to the above-mentioned patient icon information; in response to determining that the above-mentioned coordinate position information is not within the first preset range, control the associated patient alarm device to issue an alarm prompt; control each worn smart wristband to collect the patient's blood pressure information in real time, and display the collected blood pressure information in real time on the above-mentioned hospital three-dimensional model page.

[0006] In a second aspect, the present application also provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the method described in any implementation of the first aspect is implemented.

[0007] In a third aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, wherein when the computer program is executed by a processor, the method described in any implementation of the first aspect is implemented.

[0008] The above-mentioned embodiments of the present application have the following beneficial effects: a fully automatic, full-area, and full-target active intelligent supervision mode is present, which can complete accurate bed leaving monitoring, bed status diagnosis, high-precision positioning, tracking and monitoring in the hospital building for hospitalized patients, whether they are sitting, lying down, or walking, whether they are in the ward or ward. When the status of hospitalized patients is abnormal, an alarm will be automatically triggered, and combined with the three-dimensional model of the hospital, the patient's real-time location, movement trajectory, out-of-bounds alarm and information push are displayed in a three-dimensional visualization form, thereby improving the level of intelligent management, reducing safety risks, and reducing medical disputes. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar figure labels represent the same or similar elements. It should be understood that the drawings are schematic and that the components and elements are not necessarily drawn to scale.

[0010] Figure 1 is a flow chart of some embodiments of a patient information monitoring method based on an in-hospital smart wristband according to the present application;

[0011] Figure 2 It is a schematic diagram of the structure of a computer device suitable for implementing some embodiments of the present application. DETAILED DESCRIPTION

[0012] Embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not intended to limit the scope of protection of the present application.

[0013] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other.

[0014] It should be noted that the concepts such as "first" and "second" mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0015] It should be noted that the modifications of "one" and "plurality" mentioned in the present application are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0016] The names of the messages or information exchanged between multiple devices in the embodiments of the present application are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0017] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments.

[0018] Figure 11 is a flowchart of some embodiments of the patient information monitoring method based on the in-hospital smart wristband according to the present application. 100 of some embodiments of the patient information monitoring method based on the in-hospital smart wristband according to the present application is shown. The patient information monitoring method based on the in-hospital smart wristband includes the following steps:

[0019] Step 101, in response to detecting a viewing operation on the smart wristband patient information, displaying icon information of each patient who has worn the smart wristband in an associated hospital three-dimensional model page.

[0020] In some embodiments, the execution subject (e.g., computer device) of the patient information monitoring method based on the in-hospital smart wristband can display the icon information of each patient wearing the smart wristband in the associated hospital three-dimensional model page in response to detecting the viewing operation for the patient information of the smart wristband. Among them, the patient icon information includes: user name, user number, user hospitalization information, blood pressure information, patient bed status and patient monitoring level. The user name may refer to the name of the patient in the hospital. The user number may refer to the admission number of the patient when the patient is admitted to the hospital. The user hospitalization information may refer to the hospitalization information of the department where the patient is hospitalized, which may include: department information, hospitalization building number, room number, bed number, hospitalization duration, doctor information, nurse information. Blood pressure information may refer to the patient's blood pressure, heart rate, blood oxygen and other information. The patient bed status may include: in-bed status and out-of-bed status; the in-bed status may indicate the patient's status in the bed; the out-of-bed status may indicate the patient's status out of the bed. The patient monitoring level may indicate the patient's severity level (nursing level). The higher the patient monitoring level, the less the patient can move around at will. The hospital three-dimensional model page may be a pre-built three-dimensional model page corresponding to the target hospital. The hospital three-dimensional model may refer to the three-dimensional architectural model of the target hospital. The smart wristbands worn in the hospital three-dimensional model page may refer to the smart wristbands in the target hospital. The patient icon information may refer to the patient information displayed in the hospital three-dimensional model page wearing the smart wristband. It should be noted that only the patient information corresponding to the smart wristband in the wearing state will be displayed in the hospital three-dimensional model page. Smart wristband patient information may refer to the information of each patient wearing the smart wristband in the target hospital. The viewing operation may refer to the click operation of the corresponding smart wristband patient information. The smart wristband also has the following functions: a smart watch with steps, distance, calories, deep sleep, light sleep, positioning, electronic fence, call (depending on the technology, there may be no call function), SOS, sedentary reminder, medicine reminder, blood pressure, heart rate, blood oxygen, external ECG long-term monitoring and reading, ECG spectrum analysis, pulse wave blood pressure static and long-term monitoring and analysis, and combined with the system core algorithm, patient emotion analysis, pulse diagnosis analysis, nutritional recipes, network popular science push, group voice, and the hospital opened an interventional department doctor station, nurse station, medical alliance co-construction department and remote consultation system. It can continuously measure blood pressure, suitable for middle-aged and elderly people, passive detection, and carry with you. For example, the smart wristband can be a medical smart bracelet. The patient icon information is displayed in the form of a display box on the hospital 3D model page. The smart wristband has an identification QR code, which is used to identify patient information. Among them, a transparent pocket is set on the smart wristband for storing paper QR codes.

[0021] Furthermore, the hospital 3D model page can be constructed by following the steps below:

[0022] The first step is to obtain the three-dimensional image data and hospital building component information set of the target hospital, where the hospital building component information includes hospital building components. Hospital building components may refer to component diagrams of single hospital buildings. The target hospital may refer to the hospital corresponding to the hospital three-dimensional model page. The three-dimensional image data may refer to the image and data information of the target hospital area, and may include the three-dimensional height data of each building component of the target hospital. The surface elevation data may be the heights of each building component of the target hospital relative to a vertical reference plane. For example, the vertical reference plane may be the ground.

[0023] In the second step, the building component outline feature is extracted from the three-dimensional image data to obtain a building component outline information set. The building component outline information may include position information and elevation data. The position information may be the geographic coordinates of the building component. The elevation data may be the height of the building component relative to the vertical reference plane.

[0024] The building component outline feature extraction is performed on the above three-dimensional image data to obtain a building component outline information set, including:

[0025] First, perform image enhancement processing on the three-dimensional image data to obtain enhanced three-dimensional image data. A filter enhancement method can be used to perform image enhancement processing on the three-dimensional image data to obtain enhanced three-dimensional image data. The filter enhancement method can be: median filtering, mean filtering.

[0026] Second, the building component recognition processing is performed on the enhanced three-dimensional image data to obtain building component recognition information.

[0027] The building component recognition processing of the enhanced three-dimensional image data includes:

[0028] 1. Performing building component region feature extraction on the enhanced three-dimensional image data to obtain image feature data of each building component region. For example, a pre-trained building component region feature extraction model may be used to perform feature extraction on the enhanced three-dimensional image data to obtain image feature data of each building component region. The building component region feature extraction model may be a pre-trained neural network model that takes the enhanced three-dimensional image data as input and takes the corresponding image feature data of each building component region as output. For example, the building component region feature extraction model may be a convolutional neural network model or a HOG feature extraction model.

[0029] 2. For each building component area image feature data, perform the following processing steps:

[0030] First, the building component regional image feature data is input into the convolution layer included in the pre-trained regional image feature classification model to generate a convolution information set. The regional image feature classification model also includes: a capsule network and an output layer. The convolution layer can be a temporal convolution layer, including multiple convolution layers. Each convolution layer includes: multiple convolution networks connected in series. The convolution networks between the layers are connected in parallel. The convolution information can be image feature extraction information in the building component regional image feature data.

[0031] Next, the convolution information set is input into the capsule network to generate a matrix information set. One convolution information corresponds to one matrix information. The capsule network may be a capsule network (CapsulesNet). The matrix information may refer to a matrix corresponding to a capsule entity.

[0032] Afterwards, each matrix information in the above matrix information set is spliced ​​to obtain matrix splicing information. Each matrix information can be spliced ​​horizontally.

[0033] Then, the matrix splicing information is input into the output layer to obtain the feature classification information corresponding to the image feature data of the building component area. For example, the output layer may be a Softmax function.

[0034] 3. Determine the building component region image feature data corresponding to the feature classification information that meets the preset classification condition in each feature classification information as the building component image region data, and obtain the building component image region data group. The preset classification condition may be that the feature classification information is greater than a preset classification result threshold. For example, the preset classification result threshold may be 90%. The building component image region data group may be each building component region image feature data whose feature classification information is greater than the preset classification result threshold.

[0035] 4. Adjust the position of each building component image area data in the building component image area data group to obtain an adjusted building component image area data group. For example, first, input the building component area image feature data corresponding to the building component image area data into a pre-trained building component position adjustment model to obtain the building component position offset information corresponding to the building component image area data. Secondly, use the building component position offset information to adjust the position of the building component image area data to obtain the adjusted building component image area data. For example, adjusting the position of the building component image area data may include: first, determining the horizontal axis coordinate of the corner point coordinate included in the building component image area data as the horizontal coordinate to be updated. Second, determining the vertical axis coordinate of the corner point coordinate included in the building component image area data as the vertical coordinate to be updated. Third, determining the component height included in the building component image area data as the height to be updated. Fourth, determining the component width included in the building component image area data as the width to be updated. Fifth, the product of the horizontal coordinate offset value included in the position offset information of the building component and the width to be updated and the sum of the horizontal coordinate to be updated are determined as the horizontal coordinate of the updated corner point. Sixth, the product of the vertical coordinate offset value included in the position offset information of the building component and the height to be updated and the sum of the vertical coordinate to be updated are determined as the vertical coordinate of the updated corner point. Seventh, the horizontal coordinate of the updated corner point and the vertical coordinate of the updated corner point are determined as the updated corner point coordinate. Eighth, the product of the height scaling value of the real number e to the power and the height to be updated is determined as the height of the updated area. The height scaling value can be the height scaling ratio included in the position offset information. Ninth, the product of the width scaling value of the real number e to the power and the width to be updated is determined as the width of the updated area. The width scaling value can be the width scaling ratio included in the position offset information. Tenth, the updated corner point coordinates, the height of the updated area and the width of the updated area are merged into the data of adjusting the image area of ​​the building component.

[0036] 5. Perform regional redundancy elimination on each adjusted building component image region data in the adjusted building component image region data group to obtain a redundant adjusted building component image region data group. A non-maximum suppression algorithm may be used to perform regional redundancy elimination on each adjusted building component image region data in the adjusted building component image region data group to obtain a redundant adjusted building component image region data group.

[0037] 6. Determine the above-mentioned redundantly adjusted building component image area data group as building component identification information.

[0038] Third, the building component position information set is determined through the building component identification information, and one hospital building component information corresponds to one building component position information. The building component position information can be the three-dimensional coordinate position of the building component in the world coordinate system.

[0039] Fourth, according to the three-dimensional elevation data of the target hospital included in the three-dimensional image data and the building component position information set, a building component elevation data set is determined. One building component position information corresponds to one building component elevation data. For example, for each building component position information, the elevation data corresponding to the building component position information can be found from the three-dimensional elevation data as the building component elevation data.

[0040] Fifth, for each piece of building component position information in the building component position information set, the building component position information and the corresponding building component elevation data are combined into building component outline information.

[0041] The third step is to generate an initial hospital 3D building model according to the above building component outline information set. The above initial hospital 3D building model may be a 3D model including each building component in the above target hospital. For example, the initial hospital 3D building model may be constructed according to the above building component outline information set by a 3D modeling tool. For example, the 3D modeling tool may be: Maya or 3Dmax tool.

[0042] In the fourth step, each hospital building component included in the hospital building component information set is filled into the corresponding position in the initial hospital 3D building model to obtain a filled hospital 3D building model. For example, the Substance Painter tool can be used to fill each hospital building component included in the hospital building component information set into the corresponding position in the initial hospital 3D building model to obtain a filled hospital 3D building model.

[0043] The fifth step is to extract point cloud data from the above-mentioned filled hospital three-dimensional building model to obtain hospital building point cloud data. The above-mentioned hospital building point cloud data can be each point cloud extracted from the above-mentioned filled hospital three-dimensional building model. The point cloud in the above-mentioned hospital building point cloud data can be a point cloud three-dimensional coordinate included in the world coordinate system. For example, the above-mentioned execution subject can use the Meshlab point cloud extraction tool to extract point cloud from the above-mentioned filled hospital three-dimensional building model to obtain hospital building point cloud data.

[0044] The sixth step is to perform hospital building component segmentation processing on the above hospital building point cloud data to obtain a hospital building component monomer image information set. First, each point cloud whose vertical axis coordinate of the point cloud in the above hospital building point cloud data is less than or equal to a preset height threshold can be deleted from the above hospital building point cloud data to obtain updated hospital building point cloud data. Then, the updated hospital building point cloud data is segmented into building components to obtain a hospital building component monomer image information set. For example, a segmentation algorithm based on component region growth can be used to segment the updated hospital building point cloud data into building components to obtain a hospital building component monomer image information set.

[0045] Step 7: Reconstruct the three-dimensional model of the above-mentioned hospital building component monomer image information set to obtain the three-dimensional model of the hospital of the above-mentioned target hospital. A three-dimensional reconstruction tool can be used to reconstruct the three-dimensional model of the above-mentioned hospital building component monomer image information set to obtain the three-dimensional model of the hospital of the above-mentioned target hospital. For example, the above-mentioned three-dimensional reconstruction tool can be: Meshroom or OpenMVG.

[0046] In the eighth step, the hospital 3D model is rendered into a target page to obtain a hospital 3D model page. The target page may be a pre-built page for storing hospital 3D model images.

[0047] Therefore, the modeling accuracy is improved due to the wide coverage and high resolution of the 3D image data of the target hospital. The segmentation of hospital building components can accurately capture the surface morphology and details of the building components, making the established 3D model of the hospital more accurate.

[0048] The building component position adjustment model can be trained by the following steps:

[0049] First, obtain a sample set of building components. The building component samples include: sample feature vectors of sample building components, component boundary information corresponding to the sample building components, and initial component boundary information. The initial component boundary information is component boundary information obtained by performing component region extraction on the sample building components. The component boundary information may be an actual rectangular boundary of the building components included in the sample building components. The initial component boundary information may be a rectangular boundary of the building components obtained by performing component extraction on the sample building components.

[0050] Second, a building component sample is selected from the building component sample set as the target building component sample. For example, a building component sample can be randomly selected from the building component sample set as the target building component sample.

[0051] Third, the sample feature vector included in the target building component sample is input into the initial building component position adjustment model to obtain the corresponding predicted position offset information. The initial building component position adjustment model may be a regression model. The predicted position offset information may be the position offset information predicted by the regression model. The predicted position offset information may include offset corner point coordinates and scaling parameters. The offset corner point coordinates may include a horizontal coordinate offset value and a vertical coordinate offset value. The scaling parameters may include a height scaling ratio and a width scaling ratio.

[0052] Fourth, based on the predicted position offset information and the initial component boundary information included in the target building component sample, the corresponding predicted component boundary information is determined. The predicted component boundary information may be component boundary information after the initial component boundary information is offset-adjusted according to the predicted position offset information. For example, the initial component boundary information may be updated according to the predicted position offset information to obtain the updated initial component boundary information as the predicted component boundary information.

[0053] Fifth, a model loss value is determined according to the predicted component boundary information and the component boundary information included in the target building component sample. The execution entity may determine the distance between the corner point coordinates included in the predicted component boundary information and the corner point coordinates included in the component boundary information as the coordinate distance, and determine the difference between the area corresponding to the predicted component boundary information and the area corresponding to the component boundary information as the area difference. Then, the coordinate distance and the area difference are combined to determine the model loss value.

[0054] Sixth, determine whether the above model loss value is less than or equal to a preset model loss value. The preset model loss value may include a coordinate distance loss value and an area difference loss value.

[0055] Seventh, in response to determining that the above-mentioned model loss value is less than or equal to the preset model loss value, the initial building component position adjustment model is determined as the trained building component position adjustment model.

[0056] Therefore, the building component position adjustment model can handle various complex backgrounds, shapes and occlusion situations, learn the complex characteristics of the building components, and thus predict the component position offset. The building component image area data can be adjusted according to the predicted position offset, thereby improving the accuracy of the position adjustment of the building component image area data.

[0057] Step 102, in response to detecting the patient leaving bed information sent by the target bed detection device, modifying the patient bed status included in the patient icon information corresponding to the above target bed detection device to the bed leaving status, and determining whether the patient monitoring level included in the above patient icon information meets the first monitoring condition.

[0058] In some embodiments, the above-mentioned execution subject may, in response to detecting the patient leaving bed information sent by the target bed detection device, modify the patient bed status included in the patient icon information corresponding to the above-mentioned target bed detection device to the leaving bed status, and determine whether the patient monitoring level included in the above-mentioned patient icon information meets the first monitoring condition. The target bed detection device may refer to a pressure sensing device arranged on the bed, which is used to detect whether the patient is in bed. The patient leaving bed information may indicate that the patient has left the bed and is not lying on the bed. For example, the target bed detection device may refer to a pressure sensor with a processor, which will send the patient leaving bed information to the above-mentioned execution subject after detecting that the patient has left the bed. The target bed detection device may refer to the bed detection device of the bed where the patient wearing the smart wristband is located. The first monitoring condition may be: the patient monitoring level is in the first monitoring level interval. The first monitoring level interval indicates that the patient corresponding to the interval cannot leave the bed.

[0059] Step 103: In response to determining that the patient monitoring level included in the patient icon information satisfies a first monitoring condition, controlling an associated patient alarm device to issue an alarm prompt.

[0060] In some embodiments, the execution subject may control the associated patient alarm device to issue an alarm prompt in response to determining that the patient monitoring level included in the patient icon information satisfies the first monitoring condition. The patient alarm device may be an alarm device associated with a nurse station and a bed, and may issue an alarm prompt sound to prompt the patient to leave the bed. For example, the patient alarm device may be a speaker.

[0061] Step 104: in response to determining that the patient monitoring level included in the patient icon information does not satisfy the first monitoring condition, determine whether the patient monitoring level satisfies the second monitoring condition.

[0062] In some embodiments, the execution subject may determine whether the patient monitoring level meets the second monitoring condition in response to determining that the patient monitoring level included in the patient icon information does not meet the first monitoring condition. The second monitoring condition may refer to the patient monitoring level being in the second monitoring level interval. The second monitoring level interval indicates that the patient corresponding to the interval can leave the bed, but cannot leave the room where the bed is located.

[0063] Step 105: in response to determining that the patient monitoring level satisfies the second monitoring condition, locating the coordinate position information of the smart wristband corresponding to the patient icon information.

[0064] In some embodiments, the above-mentioned execution subject can locate the coordinate position information of the smart wristband corresponding to the above-mentioned patient icon information in response to determining that the above-mentioned patient monitoring level meets the second monitoring condition. The coordinate position information may refer to the coordinate position of the smart wristband. That is, the coordinate position information of the smart wristband can be located in real time through the positioning chip in the smart wristband. Therefore, the high-precision positioning technology on the Bluetooth network side is adopted, which is mainly composed of positioning base stations, positioning tags, positioning engines, application services, etc. In order to improve the level of informatization of hospital ward management work, promote the management work to develop towards intelligence, standardization, and real-time, and lay a solid foundation for the health and safety of hospitalized patients.

[0065] Step 106: In response to determining that the coordinate position information is not within the first preset range, controlling the associated patient alarm device to issue an alarm prompt.

[0066] In some embodiments, the execution subject may control the associated patient alarm device to issue an alarm prompt in response to determining that the coordinate position information is not within a first preset range. The first preset range may refer to the room where the bed is located.

[0067] Step 107, controlling each smart wristband that has been worn to collect the patient's blood pressure information in real time, and displaying the collected blood pressure information in real time on the above-mentioned hospital three-dimensional model page.

[0068] In some embodiments, the execution subject can control each smart wristband worn to collect the patient's blood pressure information in real time, and display the collected blood pressure information in real time on the hospital 3D model page. For example, the blood pressure information can be displayed in the patient icon information of the corresponding patient in the hospital 3D model page.

[0069] At present, the main methods for non-invasive and continuous measurement of blood pressure using sensors in smart wristbands include arterial tension method, pulse wave characteristic parameter determination method, and pulse wave test method. The basic principle of arterial tension method is that when a blood vessel is partially flattened by an external force, the circumferential stress in its blood vessel wall changes. When the external pressure is equal to the internal pressure, the blood pressure in the blood vessel can be obtained by measuring the external pressure. At the same time, based on the correlation between peripheral arterial pressure and central arterial pressure, the central arterial pressure is calculated using the corresponding conversion function. However, the sensor is highly sensitive to position and pressure, so it is relatively difficult to maintain a fixed position for long-term measurement. At the same time, long-term pressurization through the airbag pressurization device will also make the person being side-passed feel uncomfortable. The pulse wave parameter determination method mainly performs statistical analysis on the characteristic parameters extracted from the pulse wave. These characteristic parameters mainly include the relative height of the main wave peak, the rise time of the main wave, the height of the dicrotic wave, etc. In addition, physiological factors such as age and blood sugar should also be considered. The blood pressure value is obtained by regression analysis of the parameters with greater correlation. Due to differences in individual factors, the blood pressure value can only be valid within a certain range. The pulse wave velocity measurement method is proposed based on the linear relationship between the propagation velocity of the pulse wave and the arterial blood pressure. The measured pulse wave velocity (PWV) value is used to indirectly calculate the arterial blood pressure value. The pulse wave velocity is calculated by the pulse wave propagation time between two points in the artery. If the distance between the two points remains unchanged, the pulse wave velocity is inversely proportional to the pulse wave propagation time. Therefore, the arterial blood pressure value can be indirectly calculated by the pulse wave propagation time (PWlW). A large number of theories and experiments have shown that there is a quasi-linear relationship between blood pressure and pulse wave velocity. The measurement methods of pulse wave propagation time basically use the time delay of synchronous detection of electrocardiogram (ECC) and fingertip photoplethysmography (PPT) signals.

[0070] Further, in response to determining that the patient monitoring level does not meet the second monitoring condition, but meets the third monitoring condition, the coordinate position information of the smart wristband corresponding to the patient icon information is located in real time. The third monitoring condition may mean that the patient monitoring level is in the third monitoring level interval. The second monitoring level interval indicates that the patient corresponding to the interval can leave the room where the bed is located, but cannot leave the pre-divided activity area in the target hospital.

[0071] Furthermore, in response to detecting that the coordinate position information is not within the second preset range, the associated patient alarm device is controlled to issue an alarm prompt. The second preset range may refer to a pre-divided activity area within the target hospital.

[0072] The present application also provides a computer device 200. Figure 2As shown, the computer device 200 includes: a bus 201, a processor 202, a memory 203 and a communication interface 204. The processor 202, the memory 203 and the communication interface 204 communicate with each other through the bus 202. The computer device 200 can be a server or a terminal device. It should be understood that the present application does not limit the number of processors and memories in the computer device 200.

[0073] The bus 202 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 The bus 202 is represented by only one line, but it does not mean that there is only one bus or one type of bus. The bus 202 may include a path for transmitting information between various components of the computer device 200 (for example, the memory 202, the processor 203, and the communication interface 204).

[0074] The processor 203 may include any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0075] The memory 202 may include a volatile memory, such as a random access memory (RAM). The memory 202 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0076] The memory 202 stores executable program codes, and the processor 202 executes the executable program codes to respectively implement the functions of the acquisition module, the sampling module, the determination module, and the mixing module, thereby implementing the above-mentioned method for monitoring patient information based on the in-hospital smart wristband. That is, the memory 202 stores instructions for executing the above-mentioned method for monitoring patient information based on the in-hospital smart wristband.

[0077] The communication interface 204 uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the computer device 200 and other devices or a communication network.

[0078] An embodiment of the present application also provides a chip, which includes a processor and a data interface. The processor reads instructions stored in a memory through the data interface to execute the above-mentioned method for monitoring patient information based on an in-hospital smart wristband.

[0079] The embodiment of the present application also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium that can be stored by a computing device or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk). The computer-readable storage medium includes instructions that instruct the computing device to execute the above-mentioned method for monitoring patient information based on an in-hospital smart wristband.

[0080] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0081] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the protection scope of the technical solutions of the embodiments of the present application.

Claims

1. A patient information monitoring method based on an in-hospital smart wristband, the method include: Acquire three-dimensional image data of a target hospital and a hospital building component information set, where the hospital building component information includes hospital building components; Extracting building component outline features from the three-dimensional image data to obtain a building component outline information set; generating an initial three-dimensional hospital building model according to the building component outline information set; Filling each hospital building component included in the hospital building component information set into a corresponding position in the initial hospital three-dimensional building model to obtain a filled hospital three-dimensional building model; Extracting point cloud data from the filled three-dimensional building model of the hospital to obtain point cloud data of the hospital building; Performing hospital building component segmentation processing on the hospital building point cloud data to obtain a hospital building component monomer image information set; Reconstructing a three-dimensional model of the hospital building component monomer image information set to obtain a three-dimensional model of the target hospital; Rendering the hospital 3D model to a target page to obtain a hospital 3D model page; In response to detecting a viewing operation for the patient information of the smart wristband, the icon information of each patient wearing the smart wristband is displayed in the associated hospital three-dimensional model page, wherein the patient icon information includes: user name, user number, user hospitalization information, blood pressure information, patient bed status and patient monitoring level, and the smart wristband has an identification QR code, which is used to identify the patient information; In response to detecting the patient leaving bed information sent by the target bed detection device, modifying the patient bed status included in the patient icon information corresponding to the target bed detection device to the leaving bed status, and determining whether the patient monitoring level included in the patient icon information meets the first monitoring condition; In response to determining that the patient monitoring level included in the patient icon information meets the first monitoring condition, controlling the associated patient alarm device to issue an alarm prompt; In response to determining that the patient monitoring level included in the patient icon information does not satisfy a first monitoring condition, determining whether the patient monitoring level satisfies a second monitoring condition; In response to determining that the patient monitoring level meets the second monitoring condition, locating the coordinate position information of the smart wristband corresponding to the patient icon information; In response to determining that the coordinate position information is not within the first preset range, controlling the associated patient alarm device to issue an alarm prompt; Controlling each smart wristband worn to collect the patient's blood pressure information in real time, and displaying the collected blood pressure information in real time on the hospital three-dimensional model page; The step of extracting the building component outline features from the three-dimensional image data to obtain a building component outline information set includes: Performing image enhancement processing on the three-dimensional image data to obtain enhanced three-dimensional image data; Performing building component recognition processing on the enhanced three-dimensional image data to obtain building component recognition information; Determine a building component location information set through the building component identification information, where one hospital building component information corresponds to one building component location information; Determine a building component elevation data set according to the three-dimensional elevation data of the target hospital included in the three-dimensional image data and the building component position information set, wherein one building component position information corresponds to one building component elevation data; For each piece of building component position information in the building component position information set, combining the building component position information and corresponding building component elevation data into building component outline information; The step of performing building component recognition processing on the enhanced three-dimensional image data to obtain building component recognition information includes: Extracting building component area features from the enhanced three-dimensional image data to obtain image feature data of each building component area; For each building component area image feature data, perform the following processing steps: Inputting the building component regional image feature data into a convolutional layer included in a pre-trained regional image feature classification model to generate a convolution information set, wherein the regional image feature classification model further includes: a capsule network and an output layer; Inputting the convolution information set into the capsule network to generate a matrix information set; splicing each matrix information in the matrix information set to obtain matrix splicing information; Inputting the matrix splicing information into the output layer to obtain feature classification information corresponding to the image feature data of the building component area; Determine the building component area image feature data corresponding to the feature classification information that meets the preset classification conditions in each feature classification information as the building component image area data, and obtain the building component image area data group; Adjusting the position of each building component image area data in the building component image area data group to obtain an adjusted building component image area data group; Performing region redundancy elimination on each adjusted building component image region data in the adjusted building component image region data group to obtain a redundantly eliminated adjusted building component image region data group; Determining the redundantly adjusted building component image region data group as building component identification information; The step of adjusting the position of each building component image area data in the building component image area data group includes: Acquire a sample set of building components, wherein the building component samples include: a sample feature vector of the sample building component, component boundary information corresponding to the sample building component, and initial component boundary information, wherein the initial component boundary information is component boundary information obtained by performing component region extraction on the sample building component; Selecting a building component sample from the building component sample set as a target building component sample; Inputting the sample feature vector included in the target building component sample into the initial building component position adjustment model to obtain corresponding predicted position offset information; Determining corresponding predicted component boundary information based on the predicted position offset information and initial component boundary information included in the target building component sample; Determining a model loss value according to the predicted component boundary information and the component boundary information included in the target building component sample; Determine whether the model loss value is less than or equal to a preset model loss value; In response to determining that the model loss value is less than or equal to a preset model loss value, determining the initial building component position adjustment model as the trained building component position adjustment model; Inputting the building component region image feature data corresponding to the building component image region data into a pre-trained building component position adjustment model to obtain the building component position offset information corresponding to the building component image region data; The position of the building component image area data is adjusted by using the building component position offset information to obtain adjusted building component image area data.

2. The patient information monitoring method based on the in-hospital smart wristband according to claim 1, It is characterized in that The method further comprises: In response to determining that the patient monitoring level does not meet the second monitoring condition but meets the third monitoring condition, locating the coordinate position information of the smart wristband corresponding to the patient icon information in real time; In response to detecting that the coordinate position information is not within the second preset range, the associated patient alarm device is controlled to issue an alarm prompt.

3. A computer device, in, The computer device comprises a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 2 are implemented.

4. A computer-readable storage medium, in, The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 2 are implemented.

Citation Information

Patent Citations

  • Telemetering monitoring method and system of multiparameter automatic early warning and rapid positioning response

    CN105105762A

  • Intelligent monitoring system utilizing waistband and monitoring method

    CN107066832A

  • Real-time monitoring system for patient

    CN110179442A

  • Building volume data estimation method and device, equipment and storage medium

    CN113989310A

  • Intelligent clinical pulse detection system for cardiovascular medicine department

    CN114795150A