Data monitoring and processing method and system based on intelligent hospital bed

Abstract

A data monitoring and processing method and system based on an intelligent hospital bed. The data monitoring and processing method based on an intelligent hospital bed comprises the following steps: hospital bed partitioning (S1), fall risk monitoring (S2) and cloud service (S3). The method comprises: collecting pressure feature information of a hospital bed sub-area of a preset patient by means of a pressure sensor, and performing data processing to acquire hospital bed pressure data; then, monitoring, in real time, the hospital bed pressure data of the preset patient so as to acquire a fall risk index, and comparing the fall risk index with a fall risk threshold; if the fall risk index is less than the fall risk threshold, continuing to perform monitoring, otherwise, feeding the fall risk index to a medical worker by means of an alarm notification; and finally, transmitting, in real time, the fall risk index to a deployed patient cloud server for data integration and storage. Thus, the present invention achieves the effect of improving the fall risk analysis efficiency, and solves the problem in the prior art of fall risk analysis being slow.

Description

Data monitoring and processing method and system based on intelligent hospital bed Technical Field

[0001] The present invention relates to the technical field of electronic digital data processing, and in particular to a data monitoring and processing method and system based on an intelligent hospital bed. Background Art

[0002] With the rapid development of information technology, the medical industry is undergoing a profound change in digital transformation. As an important part of the medical equipment system, the development and application of intelligent beds are gradually receiving attention. Intelligent beds can improve the hospital's bed turnover rate, improve medical quality, and reduce medical costs. Therefore, the market demand is growing. In order to improve their competitiveness, medical institutions have introduced intelligent bed systems. Data monitoring and processing plays a vital role in modern society, especially in the fields of environmental protection, medical health, industrial production, etc. With the advancement of science and technology and the rapid development of sensor technology, the ability of data monitoring and processing has been significantly improved. In the medical field, data monitoring and processing are widely used in patients. In terms of monitoring of patients' vital signs and early warning of diseases, smart beds are one of the typical applications. By using information technology, we can strengthen medical quality management, reduce the incidence of medical errors, and ensure patient safety. Through data analysis and processing of patient monitoring systems, hospitals can optimize medical processes, improve the efficiency and quality of medical services, and establish a digital communication platform to facilitate timely and effective communication between doctors and patients and enhance mutual trust between doctors and patients. At the same time, the application of smart beds and patient monitoring systems will also help achieve the construction goals of digital hospitals, promote the digital transformation and upgrading of the medical industry, and realize the sharing and optimal allocation of medical resources through the construction of digital hospitals, thereby improving resource utilization efficiency.

[0003] In existing technologies, intelligent beds integrate sensors, Internet of Things technology, artificial intelligence algorithms and remote control systems to achieve real-time monitoring of patients' vital signs, automatic adjustment of bed posture to optimize comfort, intelligent reminders to medical staff of patients' needs and changes in health status, and seamless connection with hospital information systems, thereby greatly improving the efficiency and quality of medical care, providing patients with a more personalized, safe and comfortable rehabilitation environment, and achieving improved medical care efficiency.

[0004] For example, the invention patent announcement with announcement number: CN116776258B discloses a method and system for processing monitoring data of electric power equipment, comprising: obtaining monitoring time series data of a first data attribute of a first electric power equipment, grouping the monitoring time series data according to equipment control parameters to obtain monitoring time series data grouping results, and then constructing a similarity matrix based on the i-th group of monitoring time series data of the monitoring time series data grouping results, performing cluster analysis on the i-th group of monitoring time series data based on the similarity matrix to obtain N clustering results, and performing outlier division on the N clustering results to obtain abnormal data division results, replacing the missing values ​​of the i-th group of monitoring time series data and the abnormal data division results with the cluster centroid mean of the N clustering results to obtain the i-th group of monitoring time series data optimization results, and finally transmitting the i-th group of monitoring time series data optimization results to the user terminal.

[0005] For example, the invention patent publication number CN115292301B discloses an AI-based task data anomaly monitoring and processing method and system, including the following steps: obtaining first office task data recorded by a monitoring system for a specified monitoring range; determining the locations of X characters within a target monitoring range in the first office task data to obtain X locations; determining the locations of specified characters corresponding to each of the X characters in the second office task data to obtain X specified locations; determining difference vectors between each location and each specified location to obtain X difference vectors; and optimizing the characters within the target monitoring range within the first office task data using the X difference vectors to obtain target office task data.

[0006] However, in the process of implementing the technical solutions of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:

[0007] In the existing technology, a highly sensitive electrocardiograph (ECG) machine or a dedicated acquisition module integrated into medical equipment is used to accurately collect cardiac electrical signals from the body surface of a preset patient on a preset intelligent bed. The collected ECG data is then carefully preprocessed. Complex algorithms and technical means are then used to accurately extract key information such as heart rate, heart rhythm, QRS complex, ST segment, and T wave from the preprocessed ECG data. Based on the patient's specific condition and the doctor's diagnostic needs, a series of ECG parameter ranges, including heart rate range, identification of specific arrhythmia types, and ST segment deviation, are preset. During real-time monitoring and comparison, the system will continuously compare the collected ECG data with historical fall ECG parameters to perform a preliminary diagnosis of the patient's heart condition or a fall risk assessment. However, the ECG data needs to undergo complex preprocessing and feature extraction processes, which are time-consuming and result in slow fall risk analysis in intelligent bed applications.

[0008] Summary of the Invention

[0009] The embodiments of the present application solve the problem of slow fall risk analysis in intelligent bed applications in the prior art by providing a data monitoring and processing method and system based on an intelligent bed, thereby improving the efficiency of fall risk analysis.

[0010] An embodiment of the present application provides a data monitoring and processing method based on an intelligent bed, comprising the following steps: S1, using a pressure sensor to collect pressure characteristic information of a preset patient bed sub-area and performing data processing to obtain bed pressure data; S2, real-time monitoring of the bed pressure data of the preset patient to obtain a fall risk index, and comparing it with a fall risk threshold; if the fall risk index is less than the fall risk threshold, monitoring continues; otherwise, feedback is given to medical staff through an alarm notification, wherein the fall risk index is used to measure the fall risk level of the preset patient in the preset intelligent bed; S3, transmitting the fall risk index in real time to a deployed patient cloud server for data integration and storage.

[0011] Furthermore, the real-time monitoring of the bed pressure data of the preset patient to obtain the fall risk index also includes obtaining the fall risk threshold. The specific method is as follows: obtaining the historical fall frequency based on the historical number of falls of the preset patient in the preset time period, and the historical fall frequency is used to measure the frequency of falls of the preset patient; obtaining the historical fall severity coefficient based on the historical fall injury data of the preset patient, and the historical fall severity coefficient is used to measure the impact of the fall on the preset patient; obtaining the fall reference value from the preset database, and normalizing the historical fall frequency and the historical fall severity coefficient to obtain the fall risk threshold, and the fall risk threshold is used to judge the fall risk level of the preset patient in bed.

[0012] Furthermore, the fall risk threshold is calculated using the following formula:

[0013] Where DF0 represents the fall risk threshold, e represents the natural constant, a represents the historical fall frequency, b represents the historical fall severity coefficient, a0 represents the historical fall frequency reference value, and b0 represents the historical fall severity reference value.

[0014] Furthermore, the specific method for obtaining the fall risk index is as follows: measuring the sub-area pressure value of the bed sub-area through a pressure sensor, and the sub-area pressure value is used to measure the pressure level of the bed sub-area; by counting the sub-area pressure values ​​and calculating the average pressure value, the average pressure value is used to measure the overall pressure level; detecting the pressure value of the bed sub-area in a preset time period through a pressure sensor to obtain the sub-area pressure fluctuation value, and the sub-area pressure fluctuation value is used to measure the pressure fluctuation level of the bed sub-area in the preset time period; measuring the pressure value distribution of the bed sub-area through a pressure sensor to obtain the pressure distribution risk coefficient, and the pressure distribution risk coefficient is used to measure the abnormality of the pressure distribution of the preset intelligent bed; obtaining the pressure deviation weight factor and the pressure fluctuation weight factor from the preset database, and combining the sub-area pressure value, the average pressure value, the sub-area pressure fluctuation value and the pressure distribution risk coefficient to obtain the fall risk index.

[0015] Furthermore, the fall risk index is calculated using the following formula:

[0016] Where DF represents the fall risk index, h represents the bed sub-area number, h = 1, 2, ..., H, H represents the total number of bed sub-areas of the preset intelligent beds, x h represents the sub-area pressure value of the h-th bed sub-area, Indicates the average pressure value, y h represents the sub-area pressure fluctuation value of the h-th bed sub-area, z represents the pressure distribution hazard coefficient, α1 represents the pressure deviation weight factor, and α2 represents the pressure fluctuation weight factor.

[0017] An embodiment of the present application provides a data monitoring and processing system based on an intelligent bed, including a bed zoning module, a fall risk monitoring module and a cloud service module; wherein the bed zoning module is used to use a pressure sensor to collect pressure characteristic information of a preset patient bed sub-area and perform data processing to obtain bed pressure data; the fall risk monitoring module is used to monitor the bed pressure data of a preset patient in real time to obtain a fall risk index, and compare it with a fall risk threshold. If the fall risk index is less than the fall risk threshold, monitoring continues; otherwise, feedback is given to medical staff through an alarm notification. The fall risk index is used to measure the fall risk level of a preset patient in a preset intelligent bed; the cloud service module is used to transmit the fall risk index in real time to a deployed patient cloud server for data integration and storage.

[0018] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0019] 1. The pressure characteristic information of the preset patient bed sub-area is collected through the pressure sensor and the data is processed to obtain the bed pressure data. Then, the bed pressure data of the preset patient is monitored in real time to obtain the fall risk index, and compared with the fall risk threshold. Finally, the fall risk index is transmitted in real time to the deployed patient cloud server for data integration and storage, thereby achieving a more accurate analysis of the fall risk and thus improving the efficiency of the fall risk analysis, effectively solving the problem of slow fall risk analysis in the application of intelligent beds in the existing technology.

[0020] 2. The pressure sensor is used to measure the sub-area pressure value of the bed sub-area to obtain the average pressure value, and then the pressure sensor is used to detect the pressure value of the bed sub-area in the preset time period to obtain the sub-area pressure fluctuation value. Finally, the pressure sensor is used to measure the pressure value distribution of the bed sub-area to obtain the pressure distribution hazard coefficient, and the pressure deviation weight factor and the pressure fluctuation weight factor are combined to obtain the fall risk index, thereby realizing the numerical assessment of the fall risk and thus achieving a more accurate assessment of the fall risk.

[0021] 3. By comparing the sub-area pressure values, the maximum sub-area pressure value is obtained, and the coordinate point of the maximum sub-area pressure value is determined according to the two-dimensional coordinate system to obtain the pressure concentration point data. Then, the center coordinate point data is obtained according to the preset bed surface geometric center of the intelligent bed. Finally, the pressure distribution risk coefficient is obtained by combining the pressure concentration point data, thereby realizing the numerical evaluation of the pressure distribution risk and thus achieving a more accurate evaluation of the pressure distribution risk. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] FIG1 is a flow chart of a data monitoring and processing method based on an intelligent hospital bed provided in an embodiment of the present application;

[0023] FIG2 is a statistical diagram of changes in the pressure distribution risk coefficient provided in an embodiment of the present application;

[0024] FIG3 is a schematic structural diagram of a data monitoring and processing system based on an intelligent hospital bed provided in an embodiment of the present application.

[0025] FIG4 is a schematic diagram of a usage scenario of the data monitoring and processing system provided in an embodiment of the present application DETAILED DESCRIPTION

[0026] The embodiments of the present application solve the problem of slow fall risk analysis in intelligent bed applications in the prior art by providing a data monitoring and processing method and system based on an intelligent bed. The method uses a pressure sensor to collect pressure characteristic information of a preset patient bed sub-area and performs data processing to obtain bed pressure data. The bed pressure data of the preset patient is then monitored in real time to obtain a fall risk index, which is compared with a fall risk threshold. If the fall risk index is less than the fall risk threshold, monitoring continues; otherwise, an alarm notification is provided to the medical staff. Finally, the fall risk index is transmitted in real time to the deployed patient cloud server for data integration and storage, thereby improving the efficiency of fall risk analysis in intelligent bed applications.

[0027] The technical solution in the embodiment of the present application is to solve the problem of slow fall risk analysis in the above-mentioned intelligent bed application. The overall idea is as follows:

[0028] The fall risk index is obtained by real-time monitoring of the bed pressure data of preset patients and compared with the fall risk threshold. If the fall risk index is less than the fall risk threshold, monitoring will continue. Otherwise, an alarm notification will be given to medical staff. At the same time, the fall risk index will be transmitted in real time to the deployed patient cloud server, thereby improving the efficiency of fall risk analysis.

[0029] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0030] As shown in Figure 1, a flow chart of a data monitoring and processing method based on an intelligent bed provided in an embodiment of the present application is provided. The method includes the following steps: S1, using a pressure sensor to collect pressure characteristic information of a preset patient bed sub-area and perform data processing to obtain bed pressure data, the pressure characteristic information is used to record the pressure information of the preset patient bed sub-area, the bed pressure data includes a pressure value and a pressure change value, and the bed sub-area is obtained by partitioning the preset intelligent bed; S2, real-time monitoring of the bed pressure data of the preset patient to obtain a fall risk index, and comparing it with the fall risk threshold. If the fall risk index is less than the fall risk threshold, monitoring continues, otherwise it is fed back to medical staff through an alarm notification. The fall risk index is used to measure the fall risk level of the preset patient in the preset intelligent bed; S3, transmitting the fall risk index in real time to the deployed patient cloud server for data integration and storage. The patient cloud server is used to feed back the real-time changes in the fall risk index to the medical team for real-time monitoring and remote access.

[0031] In this embodiment, the patient cloud server is one of the technical solutions that already exists and is widely used in reality. With the development of information technology in the medical field, many medical institutions and health management organizations have adopted cloud servers to manage and store patients' health data. These systems usually include specially designed software platforms and cloud computing infrastructure for securely storing and managing patients' electronic health records, imaging data, laboratory results, etc. The patient cloud server not only provides the ability to remotely access and share data, but also protects patients' privacy and data integrity through advanced security measures. Medical institutions using patient cloud servers can more effectively manage patient care, realize data-driven medical decisions, and support collaboration and information sharing among multidisciplinary teams. The application of this technology not only improves the quality of medical services, but also improves patients' treatment effects and satisfaction; and achieves improved data management reliability.

[0032] Furthermore, the specific method for obtaining bed pressure data is as follows: partition the preset intelligent bed according to the measured length and width of the preset intelligent bed to obtain bed sub-areas, and deploy pressure sensors in each bed sub-area; use the pressure sensor to collect pressure characteristic information of the preset patient bed sub-area, and perform information preprocessing on the pressure characteristic information of the preset patient bed sub-area, and the information preprocessing includes deduplication and processing of missing information; use the analog-to-digital converter to convert the pressure characteristic information after information preprocessing into a numerical form to obtain bed pressure data, and convert the obtained bed pressure data into a preset format.

[0033] In this embodiment, the length and width of the bed are evenly divided into several small squares or small rectangular areas. For example, if the length of the bed is 2.2 meters and the width is 1.2 meters (Figure 4 shows a schematic diagram of the use scenario of the data monitoring and processing system of this application), it can be divided into a grid of 22 rows and 12 columns, and each grid is a sub-area; deduplication is used to delete repeated pressure feature information, and information processing is used to fill in the missing pressure feature information through the average value; the pressure feature information after information preprocessing is converted into a numerical form, which usually involves an analog-to-digital converter. The analog-to-digital converter is an electronic device used to convert continuous analog signals into digital signals for further processing and analysis by computers or digital circuits. The analog-to-digital converter quantizes the analog signal into discrete digital values, usually represented in binary form; the reliability of obtaining bed pressure data is improved, and the safety of the preset intelligent bed is further improved.

[0034] Furthermore, the bed pressure data of the preset patients is monitored in real time to obtain the fall risk index, which also includes obtaining the fall risk threshold. The specific method is as follows: the historical fall frequency is obtained based on the historical number of falls of the preset patients in the preset time period, and the historical fall frequency is used to measure the frequency of falls of the preset patients; the historical fall severity coefficient is obtained based on the historical fall injury data of the preset patients, and the historical fall severity coefficient is used to measure the impact of falls on the preset patients; the fall reference value is obtained from the preset database, and the historical fall frequency and the historical fall severity coefficient are normalized to obtain the fall risk threshold. The fall reference value includes the historical fall frequency reference value and the historical fall severity reference value. The fall reference value is used to measure the risk level of falls of the preset patients, and the fall risk threshold is used to judge the fall risk level of the preset patients in bed.

[0035] In this embodiment, the historical fall frequency is represented by the ratio of the historical number of falls to a preset time period, and the historical fall severity coefficient is represented by the historical fall injury data of a preset patient. The historical fall injury data comes from medical records, nursing logs or other health records, and is rated according to the type of injury caused by the fall to obtain the historical fall severity coefficient. For example, minor injuries include skin abrasions and minor bruises, and the historical fall severity coefficient is 1. Moderate injuries include sprains and minor fractures, and the historical fall severity coefficient is 2. Severe injuries include hip fractures, intracranial hemorrhage and multiple fractures, and the historical fall severity coefficient is 3. Life-threatening injuries include severe craniocerebral injuries and multi-system injuries, and the historical fall severity coefficient is 4. This achieves a more accurate analysis of the bedridden status of the preset patient, and further achieves a more accurate analysis of the fall risk.

[0036] Furthermore, the fall risk threshold is calculated using the following formula:

[0037] Where DF0 represents the fall risk threshold, e represents the natural constant, a represents the historical fall frequency, b represents the historical fall severity coefficient, a0 represents the historical fall frequency reference value, and b0 represents the historical fall severity reference value.

[0038] In this embodiment, a historical fall frequency reference value and a historical fall severity reference value are obtained from a preset database. The data in the preset database is obtained through medical records, nursing logs or other health records. The preset database includes detailed records of past fall events of a preset patient, such as the time, place, cause of the fall, whether injury was caused, etc. The algorithm of this embodiment combines the historical fall frequency and the historical fall severity coefficient, and comprehensively analyzes to obtain a fall risk threshold. In this formula, the historical fall frequency and the historical fall severity coefficient influence each other. Frequent fall events will increase the probability of the patient being injured in the future. Multiple falls usually mean that the patient faces a higher risk, which may increase the severity of injury when falling, indicating the risk level of falls of the preset patient. Therefore, by establishing a mathematical form, accurate analysis can be performed.

[0039] To facilitate analysis, define α1 is the fall frequency coefficient, defined as α2 is the fall severity coefficient, and the calculation formula for the fall risk threshold is DF0=log2[α1*α2+1]. The statistical table of changes in the fall risk threshold is shown in Table 1:

[0040] Table 1 Statistics of changes in fall risk threshold

[0041] Among them, the fall frequency coefficient is positively correlated with the fall risk threshold, and the fall severity coefficient is positively correlated with the fall risk threshold; patients who fall frequently obviously face a higher risk of falling. Even if they are not bedridden at present, due to frequent falls, they are more likely to fall again in the future, especially when performing general activities in daily life. Even if the frequency of falls is not high, if they have experienced serious falls in the past, their fall risk is still high, because these patients may have specific physiological or behavioral characteristics, which makes them more likely to fall again in similar situations, and the injuries caused by the fall may be more serious; thereby achieving a comprehensive assessment of fall risk, further achieving a more accurate assessment of fall risk, and effectively solving the problem of slow fall risk analysis in the application of intelligent beds.

[0042] Furthermore, the specific method for obtaining the fall risk index is as follows: measuring the sub-area pressure value of the bed sub-area through a pressure sensor, and the sub-area pressure value is used to measure the pressure level of the bed sub-area; by counting the sub-area pressure values ​​and calculating the average pressure value, the average pressure value is used to measure the overall pressure level; detecting the pressure value of the bed sub-area in a preset time period through a pressure sensor to obtain the sub-area pressure fluctuation value, and the sub-area pressure fluctuation value is used to measure the pressure fluctuation level of the bed sub-area in the preset time period; measuring the pressure value distribution of the bed sub-area through a pressure sensor to obtain the pressure distribution risk coefficient, and the pressure distribution risk coefficient is used to measure the degree of abnormality of the pressure distribution of the preset intelligent bed; obtaining the pressure deviation weight factor and the pressure fluctuation weight factor from the preset database, and combining the sub-area pressure value, the average pressure value, the sub-area pressure fluctuation value and the pressure distribution risk coefficient to obtain the fall risk index, the pressure deviation weight factor is used to measure the degree of influence of the deviation between the pressure value and the average pressure value on the fall risk index, and the pressure fluctuation weight factor is used to measure the degree of influence of pressure fluctuation on the fall risk index.

[0043] In this embodiment, the sub-area pressure fluctuation value is expressed by calculating the standard deviation of the pressure value of the bed sub-area in a preset time period; the pressure deviation weight factor and the pressure fluctuation weight factor are obtained from a preset database; in a specific embodiment, the pressure deviation value is the difference between the sub-area pressure value and the average pressure value, and a mapping set of pressure deviation values ​​and their corresponding weight factors is constructed based on the relationship between historical pressure deviation values ​​and the fall risk index, and the real-time pressure deviation value is input into the mapping set to obtain the corresponding pressure deviation weight factor; a mapping set of pressure fluctuation values ​​and their corresponding weight factors is constructed based on the relationship between historical pressure fluctuation values ​​and the fall risk index, and the real-time pressure fluctuation value is input into the mapping set to obtain the corresponding pressure fluctuation weight factor; the reliability of fall risk analysis is improved, and a more accurate analysis of fall risk is further achieved.

[0044] Furthermore, the fall risk index is calculated using the following formula:

[0045] Where DF represents the fall risk index, h represents the bed sub-area number, h = 1, 2, ..., H, H represents the total number of bed sub-areas of the preset intelligent beds, x h represents the sub-area pressure value of the h-th bed sub-area, Indicates the average pressure value, y h represents the sub-area pressure fluctuation value of the h-th bed sub-area, z represents the pressure distribution hazard coefficient, α1 represents the pressure deviation weight factor, and α2 represents the pressure fluctuation weight factor.

[0046] In this embodiment, the algorithm of this embodiment combines the sub-region pressure value, the average pressure value, the sub-region pressure fluctuation value, and the pressure distribution risk coefficient to comprehensively analyze and obtain the fall risk index. In this formula, the sub-region pressure fluctuation value and the pressure distribution risk coefficient affect each other. The pressure distribution risk coefficient can affect the sub-region pressure fluctuation value. For example, if the pressure distribution risk coefficient of a certain region is high, it may mean that the pressure on the region is uneven or excessive, resulting in large pressure fluctuations in this area when the patient changes his posture or moves. The sub-region pressure fluctuation value can directly affect the pressure distribution risk coefficient. If the pressure fluctuation value of a certain region is large, it may indicate that the pressure distribution in this region is unstable or inappropriate, which may increase the possibility of the patient falling in this area. Therefore, the pressure distribution risk coefficient will be increased, indicating the fall risk level of the preset patient on the preset intelligent bed. Therefore, by establishing a mathematical form, accurate analysis can be performed. The sub-region pressure value reflects the pressure intensity of a specific area on the mattress or bed surface. If the pressure value of a certain area is too high or too low, it may affect the patient's comfort and stability in this area. For example, too high a pressure value may cause the patient to feel uncomfortable when staying in this area for a long time, increase the frequency of movement or adjustment of body position, and thus increase the risk of falling. The average pressure value is the average pressure level across all areas of a mattress or bed. An appropriate average pressure value can promote patient comfort and stability and reduce the frequency of movement due to discomfort. If the average pressure value is too high or too low, it may affect overall sleep quality and postural stability, thereby increasing the risk of falls. The sub-area pressure fluctuation value represents the range of pressure fluctuations within a specific area of ​​a mattress or bed. Large pressure fluctuation values ​​may indicate unstable pressure distribution in that area, which may be due to structural problems with the mattress or bed or posture changes caused by the patient's own high activity frequency. Unstable pressure distribution may increase the risk of falls in this area, especially when the patient attempts to adjust their position or move. The pressure distribution risk factor reflects whether the pressure distribution on the mattress or bed is balanced and appropriate. A high risk factor may mean that the pressure in certain areas is excessive or uneven, increasing the risk of pressure ulcers. This poor pressure distribution can cause discomfort to the patient in this area, increasing instability when adjusting their posture or moving, and thus increasing the risk of falls. This achieves a comprehensive assessment of fall risk and further improves the efficiency of fall risk analysis, effectively solving the problem of low accuracy in fall risk level analysis for pre-set patients on pre-set intelligent beds.

[0047] Furthermore, the specific method for obtaining the pressure distribution risk coefficient is as follows: taking the lower left corner of the preset intelligent bed as the origin and the bed surface of the preset intelligent bed as the plane to establish a coordinate axis to obtain a two-dimensional coordinate system, the two-dimensional coordinate system is used to quantify the position information of the coordinate point; obtaining the maximum sub-area pressure value by comparing the sub-area pressure values, and determining the coordinate point of the maximum sub-area pressure value according to the two-dimensional coordinate system to obtain the pressure concentration point data, the maximum sub-area pressure value is used to measure the pressure concentration of the preset intelligent bed, the pressure concentration point data includes the horizontal axis coordinate value of the pressure concentration point and the vertical axis coordinate value of the pressure concentration point, the pressure concentration point data is used to quantify the sub-area pressure value concentration of the preset patient; obtaining the center coordinate point data according to the geometric center of the bed surface of the preset intelligent bed, and obtaining the pressure distribution risk coefficient in combination with the pressure concentration point data, the center coordinate point data includes the horizontal axis coordinate value of the center coordinate point and the vertical axis coordinate value of the center coordinate point, the center coordinate point data is used to quantify the center position of the preset intelligent bed.

[0048] In this embodiment, the pressure distribution risk coefficient is calculated using the following formula:

[0049] Where, e represents the natural constant, z represents the pressure distribution risk coefficient, p x Indicates the horizontal axis coordinate value of the center coordinate point, p y Indicates the vertical coordinate value of the center coordinate point, g x Indicates the horizontal axis coordinate value of the pressure concentration point, g y represents the vertical axis coordinate value of the pressure concentration point; the sub-area pressure fluctuation value is obtained by calculating the standard deviation of the pressure values ​​of the bed sub-area in a preset time period; specifically, the algorithm of this embodiment combines the horizontal axis coordinate value of the central coordinate point, the vertical axis coordinate value of the central coordinate point, the horizontal axis coordinate value of the pressure concentration point and the vertical axis coordinate value of the pressure concentration point, and comprehensively analyzes to obtain the pressure distribution risk coefficient. In this formula, the horizontal axis coordinate value of the central coordinate point and the horizontal axis coordinate value of the pressure concentration point affect each other. When the horizontal axis coordinate value of the pressure concentration point deviates from the horizontal axis coordinate value of the central coordinate point, it means that the patient's body may be in an unbalanced or unstable state. This situation increases the risk of accidents or falls of patients in bed, especially for vulnerable groups or patients who cannot move independently, such as the elderly or paralyzed patients. The deviation of the horizontal axis coordinate value of the pressure concentration point from the horizontal axis coordinate value of the central coordinate point may indicate that their body posture is inappropriate or there are problems with the bed setting. These factors will increase the potential risk of falling and indicate the degree of abnormality of the pressure distribution of the preset intelligent bed. Therefore, by establishing a mathematical form, accurate analysis can be performed.

[0050] For the convenience of analysis, define β1=(p x -g x ) 2 , β1 is the pressure horizontal axis coefficient, β2=(p y -gy ) 2 , β2 is the pressure vertical axis coefficient, then the calculation formula of the pressure distribution hazard coefficient is: As shown in Figure 2, a statistical graph of the changes in the pressure distribution risk coefficient provided in the example of this application is shown. It can be seen from the figure that the pressure horizontal axis coefficient is positively correlated with the pressure distribution risk coefficient, and the pressure vertical axis coefficient is positively correlated with the pressure distribution risk coefficient. The center coordinate point is obtained according to the geometric center of the bed surface of the preset intelligent bed, and the preset patient pressure concentration point is a pressure point that may be generated when the patient's weight distribution and posture adjustment are taken into account. If the offset between these two points is large, the bed surface may be unbalanced in supporting and dispersing pressure, causing the patient to feel unstable when moving or adjusting his position, increasing the risk of falling. A comprehensive assessment of the pressure distribution is achieved, and a more accurate detection of the pressure distribution of the preset intelligent bed is further achieved, effectively solving the problem of low accuracy in the analysis of the abnormal degree of pressure distribution of the preset intelligent bed.

[0051] Furthermore, the specific steps of data integration and storage are as follows: the fall risk index is transmitted to the deployed patient cloud server via Ethernet, and the received fall risk index is statistically analyzed using a drawn line chart, which is used to measure the changing trend of the fall risk index; the line chart of the fall risk index is monitored in real time and visualized, and the visual display is used to feed back the real-time changes of the fall risk index to the medical team.

[0052] In this embodiment, Ethernet is a commonly used local area network technology that is suitable for transmitting large amounts of data in medical facilities or home environments. Through Ethernet connection, stable, high-speed and reliable data transmission can be achieved; through the visual display of the line chart of the fall risk index, not only can the patient's fall risk be monitored, but also real-time feedback can be provided to the medical team. Medical staff can view changes in fall risk in real time through the monitoring interface, and take intervention measures or adjust treatment plans as needed. When implementing this process, data security and privacy protection must be ensured, data is transmitted using encryption, and only authorized personnel can access and view the data; the security of data transmission is improved, and real-time monitoring of the fall risk index is further realized.

[0053] Furthermore, the specific method of drawing a line graph is as follows: use Matplotlib to create a preset statistical graph, which is used to count the fall risk index of a preset patient in a preset time period; input the received fall risk index into the preset statistical graph to obtain the fall risk index data points, and connect the fall risk index data points in sequence; add statistical chart annotations to obtain a line graph of the fall risk index, which is used to explain what each broken line represents, and the statistical chart annotations include the patient's name and the statistical time period of the fall risk index.

[0054] In this embodiment, Matplotlib is a Python drawing library that is widely used to generate various types of charts, including line charts, bar charts, scatter plots, etc. The Mathematical Plotting Library (Matplotlib) is used to create a preset statistical graph. The preset statistical graph contains fall risk index data points distributed in chronological order. A line graph of the fall risk index is obtained by connecting the fall risk index data points. The line graph will show the trend of the fall risk index over time, and the changes in the fall risk index are reflected by the rise or fall of the line; thereby achieving more accurate analysis of the fall risk index and further improving the reliability of the fall risk analysis.

[0055] FIG3 is a schematic diagram of the structure of a data monitoring and processing system based on an intelligent bed according to an embodiment of the present application. The data monitoring and processing system based on an intelligent bed according to an embodiment of the present application includes: a bed partitioning module, a fall risk monitoring module, and a cloud service module. The bed partitioning module is configured to use a pressure sensor to collect pressure characteristic information of a preset patient bed sub-area and perform data processing to obtain bed pressure data. The pressure characteristic information is used to record the pressure information of the preset patient bed sub-area. The bed pressure data includes a pressure value and a pressure change value. The bed sub-area is obtained by partitioning the preset intelligent bed. The fall risk monitoring module is configured to monitor the bed pressure data of the preset patient in real time to obtain a fall risk index and compare it with a fall risk threshold. If the fall risk index is less than the fall risk threshold, monitoring continues; otherwise, an alarm is notified to medical staff. The fall risk index is used to measure the fall risk level of the preset patient in the preset intelligent bed. The cloud service module is configured to transmit the fall risk index in real time to a deployed patient cloud server for data integration and storage. The patient cloud server is configured to feedback the real-time changes in the fall risk index to the medical team for real-time monitoring and remote access.

[0056] In this embodiment, if the fall risk index is monitored to exceed the fall risk threshold, the system will trigger an alarm notification, which will be immediately fed back to the relevant medical staff or nursing site. The alarm notification content usually includes the patient's identification information, the current fall risk status, recommended countermeasures and emergency contact information. The recommended countermeasures include increasing the monitoring frequency, checking the bed setting or adjusting the patient's posture. The emergency contact information is used for medical staff to take necessary actions immediately, such as going to the patient's bedside to check or provide support. If the fall risk index is less than the fall risk threshold, monitoring and data recording will continue, but the alarm notification will not be triggered; the real-time performance of the alarm notification is improved, and the safety of the preset patient in bed is further improved.

[0057] To summarize, the embodiment of the present application utilizes a pressure sensor to collect pressure characteristic information of a preset patient bed sub-area and performs data processing to obtain bed pressure data, then monitors the preset patient bed pressure data in real time to obtain a fall risk index, and compares it with the fall risk threshold. Finally, the fall risk index is transmitted in real time to the deployed patient cloud server for data integration and storage, thereby achieving a more accurate analysis of the fall risk, and further improving the efficiency of the fall risk analysis, effectively solving the problem of slow fall risk analysis in the application of intelligent beds in the prior art.

[0058] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0059] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0060] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0061] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0062] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0063] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A data monitoring and processing method based on an intelligent bed, characterized in that: The following steps are involved: S1, using a pressure sensor to collect pressure characteristic information preset in a patient bed sub-area, and performing data processing to obtain bed pressure data; S2, real-time monitoring of the bed pressure data of the preset patient to obtain the fall risk index, and compare it with the fall risk threshold. If the fall risk index is less than the fall risk threshold, continue monitoring, otherwise, give feedback to the medical staff through an alarm notification. The fall risk index is used to measure the fall risk level of the preset patient in the preset intelligent bed; S3, transmits the fall risk index in real time to the deployed patient cloud server for data integration and storage; The specific method for obtaining the bed pressure data is as follows: Partition the preset intelligent bed according to the measured length and width of the preset intelligent bed to obtain bed sub-areas, and deploy a pressure sensor in each bed sub-area; Using a pressure sensor to collect pressure characteristic information of a preset patient bed sub-area, and performing information preprocessing on the pressure characteristic information of the preset patient bed sub-area; The pressure characteristic information after information preprocessing is converted into a numerical form by using an analog-to-digital converter to obtain the bed pressure data, and the acquired bed pressure data is converted into a preset format.

2. The data monitoring and processing method based on the intelligent bed according to claim 1, characterized in that: The real-time monitoring of the bed pressure data of the preset patient to obtain the fall risk index also includes obtaining the fall risk threshold, and the specific method is as follows: Obtaining a historical fall frequency according to the number of historical falls of a preset patient in a preset time period, wherein the historical fall frequency is used to measure the frequency of falls of the preset patient; Obtaining a historical fall severity coefficient based on historical fall injury data of a preset patient, wherein the historical fall severity coefficient is used to measure the impact of the fall on the preset patient; Obtain a fall reference value from a preset database, and normalize the historical fall frequency and historical fall severity coefficient to obtain a fall risk threshold, which is used to determine the preset The patient's fall risk level based on their bedridden status.

3. The data monitoring and processing method based on the intelligent bed according to claim 1, characterized in that: The specific method for obtaining the fall risk index is as follows: Measuring a sub-region pressure value of a bed sub-region by a pressure sensor, wherein the sub-region pressure value is used to measure a pressure level of the bed sub-region; By counting the pressure values ​​of the sub-areas and calculating the average pressure value, the average pressure value is used to measure the overall pressure level; The pressure sensor detects the pressure value of the bed sub-area in a preset time period to obtain a sub-area pressure fluctuation value, wherein the sub-area pressure fluctuation value is used to measure the pressure fluctuation level of the bed sub-area in the preset time period; The pressure distribution of the sub-areas of the bed is measured by a pressure sensor to obtain a pressure distribution risk coefficient, where the pressure distribution risk coefficient is used to measure the degree of abnormality of the pressure distribution of the preset intelligent bed; The pressure deviation weight factor and the pressure fluctuation weight factor are obtained from the preset database, and the fall risk index is obtained by combining the sub-area pressure value, the average pressure value, the sub-area pressure fluctuation value and the pressure distribution hazard coefficient.

4. The data monitoring and processing method based on the intelligent bed as claimed in claim 3, characterized in that: The specific method for obtaining the pressure distribution hazard coefficient is as follows: Taking the lower left corner of the preset intelligent bed as the origin and the bed surface of the preset intelligent bed as the plane, a coordinate axis is established to obtain a two-dimensional coordinate system; The maximum sub-region pressure value is obtained by comparing the sub-region pressure values, and the coordinate point of the maximum sub-region pressure value is determined according to the two-dimensional coordinate system to obtain the pressure concentration point data, wherein the maximum sub-region pressure value is used to measure the pressure concentration of the preset intelligent bed; The center coordinate point data is obtained according to the geometric center of the bed surface of the preset intelligent bed, and the pressure distribution hazard coefficient is obtained in combination with the pressure concentration point data.

5. The data monitoring and processing method based on the intelligent bed according to claim 1, characterized in that: The specific steps of data integration and storage are as follows: The fall risk index is transmitted to the deployed patient cloud server via Ethernet, and the received fall risk index is statistically calculated using a drawn line chart; Monitor the line chart of the fall risk index in real time and display it visually.

6. The data monitoring and processing method based on the intelligent bed according to claim 5, characterized in that: The specific method of drawing the line graph is as follows: Using Matplotlib to create a preset statistical graph, wherein the preset statistical graph is used to count the fall risk index of a preset patient in a preset time period; Input the received fall risk index into a preset statistical graph to obtain fall risk index data points, and connect the fall risk index data points in sequence; Add a statistical chart annotation to obtain a line chart of the fall risk index, where the statistical chart annotation is used to explain what each line represents.

7. The data monitoring and processing system based on intelligent hospital beds is characterized by: The system is used to execute the data monitoring and processing method based on the intelligent bed according to any one of claims 1 to 6, and the system includes a bed partition module, a fall risk monitoring module and a cloud service module; Wherein, the bed partition module is used to collect pressure characteristic information of a preset patient bed sub-area using a pressure sensor and perform data processing to obtain bed pressure data; The fall risk monitoring module is used to monitor the bed pressure data of the preset patient in real time to obtain the fall risk index, and compare it with the fall risk threshold. If the fall risk index is less than the fall risk threshold, the monitoring continues, otherwise the alarm notification is fed back to the medical staff. The fall risk index is used to measure the fall risk level of the preset patient in the preset intelligent bed; The cloud service module is used to transmit the fall risk index in real time to the deployed patient cloud server for data integration and storage.

Images