Pressure distribution monitoring-based pressure ulcer risk warning system, method, and device

Abstract

Disclosed are a pressure distribution monitoring-based pressure ulcer risk warning system, a method, and a device, which relate to the technical field of medical instruments. First, a pressure monitoring area is split up, which can improve the accuracy and precision of pressure monitoring, and facilitates subsequent data analysis and processing; analysis is performed on sensor operating data of each pressure monitoring sub-area of a user, which can identify possible problems with the sensors in a timely manner; simultaneously, analysis is performed on network connection data of each pressure monitoring sub-area of the user, which can reduce the possibility of monitoring data distortion or underreporting, and allows for a more correct understanding of the state of health of pressure distribution monitoring; consequently, analysis obtains a pressure determination result for the user, and last, a warning notification is carried out on a user interface according to the pressure determination result for the user. The present invention can implement the prediction of potential pressure ulcer risks, and improves the accuracy of pressure determination.

Description

Pressure ulcer risk early warning system, method and device based on pressure distribution monitoring Technical Field

[0001] The present invention relates to the technical field of medical devices, and in particular to a pressure ulcer risk early warning system method and device based on pressure distribution monitoring. Background Art

[0002] In the field of pressure ulcer risk warning technology, data analysis technology can be used to monitor and process the pressure data collected by pressure sensors, so as to provide timely warning prompts. Since pressure data is easily affected by factors such as temperature, it may cause fluctuations or distortion of pressure data, which may in turn affect the pressure value collected by the pressure sensor and be inaccurate. This error may lead to misjudgment of pressure ulcer risk and issuance of warnings too early or too late.

[0003] Existing technologies, such as the invention patent announcement with announcement number: CN112336307B, discloses a real-time dynamic prevention and detection system for pressure injuries based on optical sensors, including: a local pressure stimulation detection module, which uses an optical sensor array laid on a mattress to detect local pressure stimulation information caused by at least one pressure point where a bedridden patient contacts the mattress; a patient activity feedback detection module, which uses an optical sensor array to collect activity information actively emitted by the bedridden patient and / or emitted in response to the local pressure stimulation information; a pressure sore risk analysis module, which includes a discomfort perception analysis unit, a limb coordination analysis unit, and a body function analysis unit. The pressure sore risk analysis module can analyze the probability of pressure sores in the bedridden patient based on the local pressure stimulation information and activity information and in combination with the stored medical database.

[0004] Existing technologies such as the invention patent announcement with announcement number: CN114532995B discloses a reminder method and reminder device for preventing pressure sores, which establishes a pressure sore generation reminder model based on historical pressure sore formation data, stores the pressure sore generation reminder model in a newly created storage space in the storage, and provides an external call interface; divides the historical pressure sore formation data into a training set and a test set; and trains the pressure sore generation reminder model based on the training set to obtain a pressure sore generation coefficient; tests the pressure sore generation reminder model based on the test set and the pressure sore generation coefficient; obtains real-time monitoring data, inputs the real-time monitoring data into the pressure sore generation reminder model, and obtains the time A required for the currently monitored patient to generate a pressure sore; determines the reminder time based on the time A required for the currently monitored patient to generate a pressure sore and the current time; and automatically reminds medical staff to help the patient turn over to avoid the formation of pressure sores.

[0005] Combined with the above scheme, it is found that in the current field of pressure ulcer risk warning technology, usually only the patient's activity data and historical pressure ulcer formation data are analyzed, and the accuracy of the pressure monitoring data cannot be evaluated, which may lead to inaccurate pressure monitoring data, affect the final risk assessment results, and may not be able to provide timely warning prompts. Summary of the Invention

[0006] In response to the deficiencies in the prior art, the present invention provides a pressure ulcer risk warning system, method, and device based on pressure distribution monitoring, which can effectively solve the problems involved in the above-mentioned background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a pressure ulcer risk warning system based on pressure distribution monitoring includes an area division module for dividing the pressure monitoring area to obtain the user's pressure monitoring sub-areas.

[0008] The data acquisition and processing module is used to collect the sensor operation data of each pressure monitoring sub-area of ​​the user, the network connection data of each pressure monitoring sub-area of ​​the user, the pressure measurement data of the user, and the historical pressure ulcer information of the user within each preset supervision cycle.

[0009] The data anomaly analysis module is used to analyze the sensor operation data of each pressure monitoring sub-area of ​​the user in each supervision cycle, obtain the sensor anomaly index value of each pressure monitoring sub-area of ​​the user, and at the same time combine the network connection data of each pressure monitoring sub-area of ​​the user in each supervision cycle for analysis to obtain the comprehensive risk assessment value of data anomaly of each pressure monitoring sub-area of ​​the user, and provide adjustment prompts.

[0010] The risk warning prompt module is used to comprehensively analyze the user's historical pressure ulcer information, the user's pressure measurement data in each supervision cycle, and the comprehensive risk assessment value of data abnormalities in each pressure monitoring sub-area of ​​the user, obtain the user's pressure judgment result, and issue a warning prompt to the user interface based on the user's pressure judgment result.

[0011] Furthermore, the sensor abnormality index value of each pressure monitoring sub-area of ​​the user is obtained. The specific process is: extracting the sensor operation data of each pressure monitoring sub-area of ​​the user in each supervision cycle, including the average output voltage, average sensitivity, average signal strength, average sampling frequency and average bias value of each sensor, and adding the product of the average output voltage of each sensor in each pressure monitoring sub-area of ​​the user and the average sensitivity of each sensor to the average bias value of each sensor as the static pressure of each sensor in each pressure monitoring sub-area of ​​the user in each supervision cycle.

[0012] A comprehensive analysis is performed on the static pressure, average signal strength and average sampling frequency of each sensor in each pressure monitoring sub-area of ​​the user in each supervision period to obtain the sensor abnormality index value of each pressure monitoring sub-area of ​​the user.

[0013] Furthermore, the network connection data of each pressure monitoring sub-area of ​​the user in each supervision cycle is analyzed. The specific analysis process is: the network connection data of each pressure monitoring sub-area of ​​the user in each supervision cycle is extracted, including the number of sensor network connections, the total number of sensors, the total number of data packets sent by each sensor, and the average sampling frequency of each sensor.

[0014] The difference between the total number of sensors in each pressure monitoring sub-area of ​​the user in each supervision cycle and the number of sensor network connections is used as the number of sensor network offlines in each pressure monitoring sub-area of ​​the user in each supervision cycle.

[0015] The ratio of the total number of data packets sent by each sensor in each pressure monitoring sub-area of ​​the user in each supervision cycle to the duration of each supervision cycle is used as the data transmission frequency of each sensor in each pressure monitoring sub-area of ​​the user in each supervision cycle.

[0016] Based on the number of sensor network offlines and the data transmission frequency of each sensor in each pressure monitoring sub-area of ​​the user in each supervision cycle, combined with the average sampling frequency of each sensor in each pressure monitoring sub-area of ​​the user in each supervision cycle, a comprehensive analysis is performed to obtain the network connection anomaly index value of each pressure monitoring sub-area of ​​the user.

[0017] Furthermore, the comprehensive risk assessment value of data anomaly in each pressure monitoring sub-area of ​​the user is obtained. The specific process is as follows:

[0018] A comprehensive analysis is performed on the sensor abnormality index values ​​of each pressure monitoring sub-area of ​​the user and the network connection abnormality index values ​​of each pressure monitoring sub-area of ​​the user to obtain the data abnormality comprehensive risk assessment value of each pressure monitoring sub-area of ​​the user, and then the data analysis results of each pressure monitoring sub-area of ​​the user are obtained by analysis.

[0019] The data analysis results of each pressure monitoring sub-area of ​​the user include normal data analysis and abnormal data analysis.

[0020] The data anomaly comprehensive risk assessment value of each pressure monitoring sub-area of ​​the user is compared with the set data anomaly comprehensive assessment threshold. If the data anomaly comprehensive risk assessment value of a certain pressure monitoring sub-area of ​​the user is lower than the set data anomaly comprehensive assessment threshold, the data analysis result of the pressure monitoring sub-area of ​​the user is marked as normal data analysis.

[0021] If the data anomaly comprehensive risk assessment value of a certain pressure monitoring sub-area of ​​the user is higher than or equal to the set data anomaly comprehensive assessment threshold, the data analysis result of the pressure monitoring sub-area of ​​the user will be marked as data analysis anomaly.

[0022] According to the data analysis results of each pressure monitoring sub-area of ​​the user, adjustment prompts are given to the sensors of each pressure monitoring sub-area of ​​the user.

[0023] Furthermore, based on the data analysis results of each pressure monitoring sub-area of ​​the user, adjustment prompts are given to the sensors of each pressure monitoring sub-area of ​​the user. The specific process is: if the data analysis result of a certain pressure monitoring sub-area of ​​the user is a data analysis abnormality, the staff is prompted that the data analysis is abnormal, and the data acquisition and processing system is updated. At the same time, the sensor is reconnected and the data transmission frequency and sampling frequency of the sensor are adjusted.

[0024] Furthermore, the pressure ulcer risk warning system based on pressure distribution monitoring also includes: extracting the user's historical pressure ulcer information, including the number of times the user's pressure ulcers occurred and the average time it takes for the user's pressure ulcers to heal.

[0025] The user's pressure measurement data is extracted in each monitoring cycle, including the average pressure of each pressure monitoring sub-area of ​​the user and the pressure distribution diagram of each pressure monitoring sub-area of ​​the user.

[0026] Based on the average pressure of each pressure monitoring sub-area of ​​the user in each supervision cycle, the data analysis results of each pressure monitoring sub-area of ​​the user, combined with the number of times the user's pressure ulcers occur and the average time for the user's pressure ulcers to heal, a comprehensive analysis is performed to obtain the user's pressure judgment result.

[0027] Furthermore, the user's pressure judgment result is obtained. The specific process is: if the data analysis result of a certain pressure monitoring sub-area of ​​the user is abnormal, the sensor of the pressure monitoring sub-area of ​​the user is adjusted and prompted; if the data analysis result of a certain pressure monitoring sub-area of ​​the user is normal, the average pressure threshold of each pressure monitoring sub-area of ​​the user is obtained according to the number of pressure ulcers of the user and the average time for pressure ulcer healing.

[0028] The average pressure of each pressure monitoring sub-area of ​​the user during the supervision period is compared with the average pressure threshold of each pressure monitoring sub-area of ​​the corresponding user. If the average pressure of a certain pressure monitoring sub-area of ​​the user during the supervision period is higher than or equal to the average pressure threshold of each pressure monitoring sub-area of ​​the corresponding user, the pressure judgment result of the user is marked as abnormal, and all abnormal pressure monitoring sub-areas of the user are marked at the same time. If the average pressure of each pressure monitoring sub-area of ​​the user during the supervision period is lower than the average pressure threshold of each pressure monitoring sub-area of ​​the corresponding user, the pressure judgment result of the user is marked as normal, thereby obtaining the pressure judgment result of the user, and issuing an early warning prompt to the user interface based on the pressure judgment result of the user.

[0029] Furthermore, the user interface is given an early warning prompt based on the user's pressure judgment result. The specific process is: if the user's pressure judgment result is normal, the staff is prompted through the user interface, indicating that the user has no pressure ulcer risk. If the user's pressure judgment result is abnormal, all abnormal pressure monitoring sub-areas of the user are marked through the user interface, and the pressure ulcer risk early warning information and the corresponding pressure distribution map of the user's pressure monitoring sub-area are sent to the staff.

[0030] A second aspect of the present invention provides a pressure ulcer risk early warning method based on pressure distribution monitoring, comprising: dividing the pressure monitoring area to obtain pressure monitoring sub-areas of the user.

[0031] During a preset supervision period, sensor operation data of each pressure monitoring sub-area of ​​the user, network connection data of each pressure monitoring sub-area of ​​the user, pressure measurement data of the user, and historical pressure ulcer information of the user are collected.

[0032] The sensor operation data of each pressure monitoring sub-area of ​​the user in each supervision cycle is analyzed to obtain the sensor abnormality index value of each pressure monitoring sub-area of ​​the user. Combined with the network connection data of each pressure monitoring sub-area of ​​the user in each supervision cycle, the comprehensive risk assessment value of data abnormality of each pressure monitoring sub-area of ​​the user is obtained, and adjustment prompts are provided.

[0033] A comprehensive analysis is performed on the user's historical pressure ulcer information, the user's pressure measurement data, and the comprehensive risk assessment value of data abnormalities in each pressure monitoring sub-area of ​​the user during each supervision cycle to obtain the user's pressure judgment result, and an early warning prompt is given to the user interface based on the user's pressure judgment result.

[0034] The third aspect of the present invention provides a pressure sore risk warning device based on pressure distribution monitoring, which also includes: a processor, and a memory and a network interface connected to the processor: the network interface is connected to the non-volatile memory in the server: the processor calls the computer program from the non-volatile memory through the network interface during operation, and runs the computer program through the memory to execute the above-mentioned pressure sore risk warning method based on pressure distribution monitoring.

[0035] The present invention has the following beneficial effects:

[0036] (1) The present invention provides a pressure ulcer risk warning system based on pressure distribution monitoring. First, the pressure monitoring area is divided to better reflect the pressure changes in the pressure monitoring sub-area. Then, the sensor operation data of each pressure monitoring sub-area of ​​the user in each supervision cycle is analyzed. At the same time, the network connection data of each pressure monitoring sub-area of ​​the user in each supervision cycle is analyzed to improve the reliability of the data. Finally, the pressure judgment result of the user is obtained by analysis, which can clearly understand the abnormal pressure status of the user, take preventive measures in time, and improve the accuracy of pressure judgment.

[0037] (2) The present invention obtains the sensor abnormality index value of each pressure monitoring sub-area of ​​the user by analyzing and performing abnormal analysis on the sensor operation data, which can timely discover abnormalities in data measurement and improve the accuracy of pressure data measurement, thereby helping to improve the accuracy of pressure monitoring, identify abnormal problems existing in the sensor, provide data support for subsequent sensor adjustments, and improve the reliability of overall monitoring.

[0038] (3) The present invention obtains the comprehensive risk assessment value of data anomalies of each pressure monitoring sub-area of ​​the user through analysis, which can timely discover sensor failures or data anomalies, reduce the impact of possible erroneous measurement data of the sensor on the monitoring results, improve the reliability of sensor data measurement, and provide data support for subsequent maintenance and optimization, thereby improving the long-term stability of the sensor and further improving the accuracy of pressure anomaly assessment.

[0039] (4) The present invention obtains the user's stress judgment results through analysis and can generate a personalized stress anomaly assessment for each user, which helps to better reflect the user's actual situation and make the stress anomaly risk warning prompt more targeted, thereby issuing warning information to the staff in a timely manner and improving the accuracy and effectiveness of stress judgment.

[0040] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] FIG1 is a schematic diagram showing the connection of system modules of the present invention.

[0042] FIG2 is a schematic flow chart of the method of the present invention.

[0043] FIG3 is an example diagram of pressure distribution in the pressure monitoring sub-area.

[0044] FIG4 is an example diagram of the comprehensive risk assessment value of data anomaly. DETAILED DESCRIPTION

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0046] Please refer to Figure 1. The first aspect of an embodiment of the present invention provides a technical solution: a pressure sore risk warning system based on pressure distribution monitoring, including an area division module for dividing the pressure monitoring area to obtain various pressure monitoring sub-areas of the user.

[0047] It should be added that the division of the pressure monitoring area refers to the division of the pressure monitoring area according to different measurement parts of the human body, such as the ischium, heel, shoulder blade, etc.

[0048] The data acquisition and processing module is used to collect the sensor operation data of each pressure monitoring sub-area of ​​the user, the network connection data of each pressure monitoring sub-area of ​​the user, the pressure measurement data of the user, and the historical pressure ulcer information of the user within each preset supervision cycle.

[0049] The data anomaly analysis module is used to analyze the sensor operation data of each pressure monitoring sub-area of ​​the user in each supervision cycle, obtain the sensor anomaly index value of each pressure monitoring sub-area of ​​the user, and at the same time combine the network connection data of each pressure monitoring sub-area of ​​the user in each supervision cycle for analysis to obtain the comprehensive risk assessment value of data anomaly of each pressure monitoring sub-area of ​​the user, and provide adjustment prompts.

[0050] The risk warning prompt module is used to comprehensively analyze the user's historical pressure ulcer information, the user's pressure measurement data in each supervision cycle, and the comprehensive risk assessment value of data abnormalities in each pressure monitoring sub-area of ​​the user, obtain the user's pressure judgment result, and issue a warning prompt to the user interface based on the user's pressure judgment result.

[0051] It should be added that the pressure ulcer risk warning system based on pressure distribution monitoring also includes a user interface, a wearable human surface pressure sensor, and a remote monitoring module.

[0052] Specifically, the sensor abnormality index value of each pressure monitoring sub-area of ​​the user is obtained. The specific process is: extracting the sensor operation data of each pressure monitoring sub-area of ​​the user in each supervision cycle, including the average output voltage, average sensitivity, average signal strength, average sampling frequency and average bias value of each sensor, and adding the product of the average output voltage of each sensor in each pressure monitoring sub-area of ​​the user and the average sensitivity of each sensor to the average bias value of each sensor as the static pressure of each sensor in each pressure monitoring sub-area of ​​the user in each supervision cycle.

[0053] It should be added that the average output voltage of each sensor refers to the average value of the sensor output voltage during the supervision period. An oscilloscope or digital multimeter can be connected to the output of the sensor, the voltage value during the supervision period can be recorded, and the average value can be calculated. The average sensitivity of each sensor refers to the proportional relationship between the sensor output signal and the input physical quantity. It is usually expressed as the output change caused by the input change per minute. The ratio of the change in the sensor's output voltage to the change in the input pressure is used as the sensor sensitivity. The average signal strength of each sensor refers to the amplitude or strength of the sensor output signal. It can be obtained by measuring the voltage amplitude of the output signal using an oscilloscope or multimeter. The average sampling frequency of each sensor refers to the average number of times the signal is sampled during the supervision period. The number of samples is collected using a data acquisition device, and the total collection time and the number of samples are recorded. The ratio of the number of samples to the total time is used as the sampling frequency of the sensor. The average sampling frequency is obtained by taking the average value. The average offset value of each sensor refers to the DC component of the sensor output signal, that is, the output value of the sensor when there is no input signal. Usually, when there is no input signal, the sensor output voltage is measured to obtain the sensor offset, and the average value is obtained by taking the average value.

[0054] A comprehensive analysis is performed on the static pressure, average signal strength and average sampling frequency of each sensor in each pressure monitoring sub-area of ​​the user in each supervision period to obtain the sensor abnormality index value of each pressure monitoring sub-area of ​​the user.

[0055] It should be noted that the sensor abnormality index value of each pressure monitoring sub-area of ​​the user represents the numerical quantification result of the sensor abnormality index value obtained by analyzing the sensor operation data. It is used to comprehensively quantify the impact of the static pressure of each sensor on the evaluation accuracy of the sensor abnormality index value. It can be obtained through the following analysis method. The specific analysis conditions are as follows:

[0056] Where γi represents the sensor abnormality index value of the user's i-th pressure monitoring sub-area, represents the static pressure of the kth sensor in the i-th pressure monitoring sub-area of ​​the user in the j-th supervision cycle, θ1 represents the correction factor corresponding to the set static pressure, represents the average signal strength of the kth sensor in the i-th pressure monitoring sub-area of ​​the user in the j-th supervision cycle, θ2 represents the correction factor corresponding to the set signal strength, represents the average sampling frequency of the kth sensor in the i-th pressure monitoring sub-area of ​​the user in the j-th supervision cycle, represents the set reference sampling frequency, θ3 represents the correction factor corresponding to the set sampling frequency, j represents the number of each supervision cycle, j = 1, 2, 3, ... m, m represents the total number of supervision cycles, i represents the number of each pressure monitoring sub-area of ​​the user, i = 1, 2, 3, ... n, n represents the total number of pressure monitoring sub-areas, k represents the number of each sensor, k = 1, 2, 3, ... h, h represents the total number of sensors.

[0057] It should be added that since higher static pressure may cause the deviation of the sensor output signal to increase, resulting in an increase in the abnormal index value, the greater the static pressure of each sensor, the greater the sensor abnormal index value. When the average signal strength of the sensor is low, the sensor may be subject to more noise interference. This interference will weaken the effective signal output by the sensor and increase the possibility of false alarms and abnormalities. Therefore, when the signal strength is low, the abnormal index value may be relatively high.

[0058] It should be added that, in this embodiment, the correction factor corresponding to the preset static pressure, the correction factor corresponding to the signal strength, and the correction factor corresponding to the sampling frequency are obtained from the pressure distribution monitoring database.

[0059] It should be noted that the correction factor corresponding to the static pressure represents the numerical value of the influence of the static pressure of the sensor on the abnormal index value of the sensor, the correction factor corresponding to the signal strength represents the numerical value of the influence of the average signal strength of the sensor on the abnormal index value of the sensor, and the correction factor corresponding to the sampling frequency represents the numerical value of the influence of the average sampling frequency of the sensor on the abnormal index value of the sensor. These corresponding relationships are pre-set mapping relationships. For example, the static pressure of each sensor and the correction factor corresponding to the preset static pressure obtained from the pressure distribution monitoring database form a mapping set. The real-time static pressure of each sensor in each pressure monitoring sub-area of ​​the user is input into the mapping set to obtain the static pressure of each sensor in each pressure monitoring sub-area of ​​the user. A correction factor corresponding to the static pressure of the sensor, a correction factor corresponding to the average signal strength of each sensor and the preset signal strength obtained from the pressure distribution monitoring database form a mapping set, the real-time average signal strength of each sensor in each pressure monitoring sub-area of ​​the user is input into the mapping set, and the correction factor corresponding to the average signal strength of each sensor in each pressure monitoring sub-area of ​​the user is obtained, the average sampling frequency of each sensor and the correction factor corresponding to the preset sampling frequency obtained from the pressure distribution monitoring database form a mapping set, the real-time average sampling frequency of each sensor in each pressure monitoring sub-area of ​​the user is input into the mapping set, and the weight factor corresponding to the sampling frequency of each sensor in each pressure monitoring sub-area of ​​the user is obtained.

[0060] It should be added that the static pressure, average signal strength, and average sampling frequency of each sensor in each pressure monitoring sub-area of ​​the user within each regulatory cycle are correlated and do not exist independently. For example, changes in static pressure will directly affect the average signal strength of the sensor. The higher the static pressure, the higher the signal strength will be due to the characteristics of the sensor. When the static pressure changes significantly, the sensor needs to increase the sampling frequency to obtain more detailed pressure change information.

[0061] It should be noted that by analyzing the static pressure of each sensor in each pressure monitoring sub-area of ​​the user in each supervision cycle, potential sensor problems or failures can be discovered, reducing the impact of the failure on subsequent pressure measurements. Analyzing the average signal strength and average sampling frequency of each sensor in each pressure monitoring sub-area of ​​the user in each supervision cycle can reflect the working status of the sensor in each supervision cycle, and then adjust to improve the accuracy of sensor data measurement.

[0062] In this implementation, a comprehensive analysis of the static pressure, average signal strength, and average sampling frequency of each sensor in each pressure monitoring sub-area of ​​the user within each supervision cycle can help identify abnormal states of the sensor and facilitate real-time monitoring of the sensor state and fault warning.

[0063] Specifically, the network connection data of each pressure monitoring sub-area of ​​the user in each supervision cycle are analyzed. The specific analysis process is: the network connection data of each pressure monitoring sub-area of ​​the user in each supervision cycle are extracted, including the number of sensor network connections, the total number of sensors, the total number of data packets sent by each sensor and the average sampling frequency of each sensor.

[0064] It should be added that the number of sensor network connections refers to the number of sensors that respond normally within the supervision cycle, which can be counted through the status information collected by the monitoring system. The total number of sensors refers to the number of all pressure sensors installed in the pressure monitoring sub-area, which can be queried from the system log. The total number of data packets sent by each sensor refers to the number of data packets sent from each sensor to the data receiver within the supervision cycle. The log file of the data receiver is used to count the data packets sent by each sensor.

[0065] The difference between the total number of sensors in each pressure monitoring sub-area of ​​the user in each supervision cycle and the number of sensor network connections is used as the number of sensor network offlines in each pressure monitoring sub-area of ​​the user in each supervision cycle.

[0066] The ratio of the total number of data packets sent by each sensor in each pressure monitoring sub-area of ​​the user in each supervision cycle to the duration of each supervision cycle is used as the data transmission frequency of each sensor in each pressure monitoring sub-area of ​​the user in each supervision cycle.

[0067] Based on the number of sensor network offlines and the data transmission frequency of each sensor in each pressure monitoring sub-area of ​​the user in each supervision cycle, combined with the average sampling frequency of each sensor in each pressure monitoring sub-area of ​​the user in each supervision cycle, a comprehensive analysis is performed to obtain the network connection anomaly index value of each pressure monitoring sub-area of ​​the user.

[0068] It should be noted that the network connection anomaly index value of each pressure monitoring sub-area of ​​the user represents the numerical quantification result of the network connection anomaly index value obtained by analyzing the network connection data. It is used to comprehensively quantify the impact of the data transmission frequency of each sensor on the evaluation accuracy of the network connection anomaly index value. It can be obtained through the following analysis method. The specific analysis conditions are as follows:

[0069] Where δi represents the network connection abnormality index value of the user's i-th pressure monitoring sub-area, represents the number of offline sensor networks in the user's i-th pressure monitoring sub-area during the j-th supervision cycle, μ1 represents the weight factor corresponding to the set number of offline sensor networks, represents the data transmission frequency of the kth sensor in the i-th pressure monitoring sub-area of ​​the user in the j-th supervision cycle, represents the set reference data transmission frequency, μ2 represents the weight factor corresponding to the set data transmission frequency, represents the average sampling frequency of the kth sensor in the i-th pressure monitoring sub-area of ​​the user in the j-th supervision cycle, represents the set reference sampling frequency, μ3 represents the weight factor corresponding to the set sampling frequency, j represents the number of each supervision cycle, j = 1, 2, 3, ... m, m represents the total number of supervision cycles, i represents the number of each pressure monitoring sub-area of ​​the user, i = 1, 2, 3, ... n, n represents the total number of pressure monitoring sub-areas, k represents the number of each sensor, k = 1, 2, 3, ... h, h represents the total number of sensors.

[0070] It should be added that, in this embodiment, the weight factors corresponding to the preset number of offline sensor networks, the weight factors corresponding to the data transmission frequency, and the weight factors corresponding to the sampling frequency are obtained from the pressure distribution monitoring database.

[0071] It should be noted that the weight factor corresponding to the number of sensor network offlines represents the numerical value of the degree of influence of the number of sensor network offlines on the network connection anomaly index value, the weight factor corresponding to the data transmission frequency represents the numerical value of the influence of the sensor data transmission frequency on the network connection anomaly index value, and the weight factor corresponding to the sampling frequency represents the numerical value of the influence of the sensor average sampling frequency on the network connection anomaly index value. These corresponding relationships are pre-set mapping relationships. For example, the number of sensor network offlines in each pressure monitoring sub-area of ​​the user and the weight factors corresponding to the preset number of sensor network offlines obtained from the pressure distribution monitoring database form a mapping set. The real-time number of sensor network offlines in a certain pressure monitoring sub-area of ​​the user is input into the mapping set to obtain the weight factor corresponding to the number of sensor network offlines in the pressure monitoring sub-area of ​​the user. The data transmission frequency of each sensor and the weight factors corresponding to the preset data transmission frequency obtained from the pressure distribution monitoring database form a mapping set. The real-time data transmission frequency of each sensor is input into the mapping set to obtain the weight factor corresponding to the data transmission frequency of each sensor. The average sampling frequency of each sensor and the weight factors corresponding to the preset sampling frequency obtained from the pressure distribution monitoring database form a mapping set. The real-time average sampling frequency of each sensor is input into the mapping set to obtain the weight factor corresponding to the sampling frequency of each sensor.

[0072] It should be added that there is a correlation between the number of sensor network offlines in each pressure monitoring sub-area of ​​the user within each regulatory cycle, the data transmission frequency of each sensor, and the average sampling frequency, and they do not exist independently. For example, the number of sensor network offlines usually directly affects the data transmission frequency. When the sensor is offline, the sensor cannot send data at the predetermined frequency, which will cause the data traffic of the entire monitoring system to decrease. When the data transmission frequency is high, the sensor needs to send data to the central server more frequently. Too high a frequency may cause network congestion.

[0073] It should be noted that by analyzing the number of sensor network offlines in each pressure monitoring sub-area of ​​a user during each regulatory cycle, it is helpful to timely identify and locate network connection problems, ensure that timely measures are taken to restore communication, and analyze the data transmission frequency of each sensor in each pressure monitoring sub-area of ​​a user during each regulatory cycle. The responsiveness and real-time performance of the sensor can be revealed, and potential network failures can be warned more effectively. By analyzing the average sampling frequency of each sensor in each pressure monitoring sub-area of ​​a user during each regulatory cycle, bottlenecks and weak links in network connections can be discovered, thereby improving the timeliness and reliability of monitoring data.

[0074] In this implementation plan, a comprehensive analysis of the number of sensor network offlines, the data transmission frequency of each sensor, and the average sampling frequency in each pressure monitoring sub-area of ​​the user within each supervision cycle can evaluate the health status of the entire monitoring network, help identify potential network problems, and thus provide data support for subsequent maintenance.

[0075] Specifically, a comprehensive risk assessment value of data anomalies for each pressure monitoring sub-area of ​​the user is obtained. The specific process is: a comprehensive analysis is performed on the sensor anomaly index values ​​of each pressure monitoring sub-area of ​​the user and the network connection anomaly index values ​​of each pressure monitoring sub-area of ​​the user to obtain a comprehensive risk assessment value of data anomalies for each pressure monitoring sub-area of ​​the user, and then the data analysis results of each pressure monitoring sub-area of ​​the user are obtained by analysis.

[0076] It should be noted that the data anomaly comprehensive risk assessment value for each pressure monitoring sub-area of ​​the user represents the numerical quantification result of the data anomaly comprehensive risk assessment value obtained by analyzing the network connection data and sensor operation data. It is used to comprehensively quantify the impact of the network connection anomaly index value on the assessment accuracy of the data anomaly comprehensive risk assessment value. It can be obtained through the following analysis method. The specific analysis conditions are as follows:

[0077] Where βi represents the data anomaly comprehensive risk assessment value of the user's i-th pressure monitoring sub-area, γi represents the sensor anomaly index value of the user's i-th pressure monitoring sub-area, represents the weight factor corresponding to the set sensor abnormality index value, δi represents the network connection abnormality index value of the user's i-th pressure monitoring sub-area, Indicates the weight factor corresponding to the set network connection abnormality index value, i represents the number of each pressure monitoring sub-area of ​​the user, i=1,2,3,…n, and n represents the total number of pressure monitoring sub-areas.

[0078] In a specific embodiment, Table 1 shows the sensor abnormality index values ​​and network connection abnormality index values ​​of different pressure monitoring sub-areas and the corresponding data abnormality comprehensive risk assessment values. In this embodiment, the weight factor corresponding to the sensor abnormality index value is 0.3, and the weight factor corresponding to the network connection abnormality index value is 0.7.

[0079] Table 1 Sensor anomaly index values ​​and network connection anomaly index values ​​for different pressure monitoring sub-areas and their corresponding data anomaly comprehensive risk assessment values

[0080] It should be explained that in Table 1, as the sensor anomaly index value and the network connection anomaly index value increase, the data anomaly comprehensive risk assessment value increases accordingly. Table 1 lists the sensor anomaly index values ​​and network connection anomaly index values ​​of three different pressure monitoring sub-areas and the corresponding data anomaly comprehensive risk assessment values, and provides the degree of influence of different sensor anomaly index values ​​and network connection anomaly index values ​​on the data anomaly comprehensive risk assessment value. The data anomaly comprehensive risk assessment value comprehensively considers the sensor anomaly index value and the network connection anomaly index value, providing data support for the data anomaly comprehensive risk assessment.

[0081] It should be explained that Figure 4 is an example diagram of the comprehensive risk assessment value of data anomaly. As shown in Figure 4, the x-axis represents the sensor anomaly index value, and the y-axis represents the comprehensive risk assessment value of data anomaly. In this embodiment, three different sets of example parameters are defined in the figure, corresponding to different situations of the three curves, respectively represented by solid lines, dashed lines and dotted lines, and the corresponding curve labels are a, b, and c.

[0082] It should be explained that when the network connection abnormality index value is 1.3, the functional relationship image between the sensor abnormality index value and the data abnormality comprehensive risk assessment value is shown as curve a; when the network connection abnormality index value is 1.7, the functional relationship image between the sensor abnormality index value and the data abnormality comprehensive risk assessment value is shown as curve b; when the network connection abnormality index value is 2.2, the functional relationship image between the sensor abnormality index value and the data abnormality comprehensive risk assessment value is shown as curve c. The data abnormality comprehensive risk assessment value increases with the increase of the sensor abnormality index value. When the network connection abnormality index value increases, the data abnormality comprehensive risk assessment value increases accordingly. The curve can be used to quickly and accurately obtain the data abnormality comprehensive risk assessment value, which solves the problem in the existing technology that the data abnormality comprehensive risk assessment value cannot be accurately analyzed due to the lack of detailed analysis process, thereby realizing accurate analysis of pressure abnormalities.

[0083] It should be added that, in this embodiment, the preset weight factors corresponding to the sensor abnormality index value and the preset weight factors corresponding to the network connection abnormality index value are obtained from the pressure distribution monitoring database.

[0084] It should be noted that the weight factor corresponding to the sensor abnormality index value represents the numerical value of the influence of the sensor abnormality index value on the comprehensive risk assessment value of data abnormality, and the weight factor corresponding to the network connection abnormality index value represents the numerical value of the influence of the network connection abnormality index value on the comprehensive risk assessment value of data abnormality. These corresponding relationships are pre-set mapping relationships. For example, the sensor abnormality index value of each pressure monitoring sub-area of ​​the user and the weight factors corresponding to the preset sensor abnormality index values ​​obtained in the pressure distribution monitoring database form a mapping set, and the real-time sensor abnormality index value of a certain pressure monitoring sub-area of ​​the user is input into the mapping set to obtain the weight factor corresponding to the sensor abnormality index value of the pressure monitoring sub-area of ​​the user, and the network connection abnormality index value of each pressure monitoring sub-area of ​​the user and the weight factor corresponding to the preset network connection abnormality index value obtained in the pressure distribution monitoring database form a mapping set, and the real-time network connection abnormality index value of a certain pressure monitoring sub-area of ​​the user is input into the mapping set to obtain the weight factor corresponding to the network connection abnormality index value of the pressure monitoring sub-area of ​​the user.

[0085] In this implementation, a comprehensive analysis is performed on the sensor abnormality index values ​​and network connection abnormality index values ​​of each pressure monitoring sub-area of ​​the user, which can evaluate the sensor data measurement process and then adjust the sensor to improve the accuracy of subsequent sensor pressure data measurements.

[0086] The data analysis results of each pressure monitoring sub-area of ​​the user include normal data analysis and abnormal data analysis.

[0087] The data anomaly comprehensive risk assessment value of each pressure monitoring sub-area of ​​the user is compared with the set data anomaly comprehensive assessment threshold. If the data anomaly comprehensive risk assessment value of a certain pressure monitoring sub-area of ​​the user is lower than the set data anomaly comprehensive assessment threshold, the data analysis result of the pressure monitoring sub-area of ​​the user is marked as normal data analysis.

[0088] If the data anomaly comprehensive risk assessment value of a certain pressure monitoring sub-area of ​​the user is higher than or equal to the set data anomaly comprehensive assessment threshold, the data analysis result of the pressure monitoring sub-area of ​​the user will be marked as data analysis anomaly.

[0089] According to the data analysis results of each pressure monitoring sub-area of ​​the user, adjustment prompts are given to the sensors of each pressure monitoring sub-area of ​​the user.

[0090] Specifically, based on the data analysis results of each pressure monitoring sub-area of ​​the user, the sensors of each pressure monitoring sub-area of ​​the user are adjusted. The specific process is: if the data analysis result of a certain pressure monitoring sub-area of ​​the user is an abnormal data analysis, the staff is prompted that the data analysis is abnormal, and the data acquisition and processing system is updated. At the same time, the sensor is reconnected and the data transmission frequency and sampling frequency of the sensor are adjusted.

[0091] It should be noted that the sensor is reconnected and the data transmission frequency and sampling frequency of the sensor are adjusted to match the target data transmission frequency and target sampling frequency.

[0092] It should be added that the target data transmission frequency and target sampling frequency are obtained according to the matching of the data anomaly comprehensive risk assessment value, and a mapping set is constructed between the data anomaly comprehensive risk assessment value interval and its corresponding target data transmission frequency and target sampling frequency. The real-time data anomaly comprehensive risk assessment value is input, and the interval in which the data anomaly comprehensive risk assessment value is located is matched. The target data transmission frequency and target sampling frequency corresponding to the data anomaly comprehensive risk assessment value are obtained through the mapping set.

[0093] Specifically, the pressure ulcer risk warning system based on pressure distribution monitoring also includes: extracting the user's historical pressure ulcer information, including the number of times the user's pressure ulcers occurred and the average time it takes for the user's pressure ulcers to heal.

[0094] It should be added that the user's historical pressure ulcer information refers to the number of times each user has developed pressure ulcers, which can be obtained through medical records. The average time it takes for a user's pressure ulcer to heal refers to the average time required from the formation of a pressure ulcer to complete healing, which can be obtained through medical records.

[0095] The user's pressure measurement data is extracted in each monitoring cycle, including the average pressure of each pressure monitoring sub-area of ​​the user and the pressure distribution diagram of each pressure monitoring sub-area of ​​the user.

[0096] It should be added that the average pressure of each pressure monitoring sub-area of ​​the user refers to the ratio of the change in pressure in the pressure monitoring sub-area during the supervision period to the time interval. The pressure is monitored in real time using a pressure sensor, and the pressure at multiple time points is recorded to calculate the pressure change rate.

[0097] It should be added that Figure 3 is an example diagram of the pressure distribution of the pressure monitoring sub-area. The pressure distribution diagram of each pressure monitoring sub-area of ​​the user displays the pressure values ​​at different positions within the pressure monitoring sub-area. Pressure data can be collected through a pressure sensor, and data analysis and visualization tools can be used to convert the collected pressure data into a visual pressure distribution diagram. In Figure 3, the x-axis represents the horizontal position of the pressure monitoring sub-area, and the y-axis represents the vertical position of the pressure monitoring sub-area.

[0098] Based on the average pressure of each pressure monitoring sub-area of ​​the user in each supervision cycle, the data analysis results of each pressure monitoring sub-area of ​​the user, combined with the number of times the user's pressure ulcers occur and the average time for the user's pressure ulcers to heal, a comprehensive analysis is performed to obtain the user's pressure judgment result.

[0099] Specifically, the pressure judgment result of the user is obtained, and the specific process is: if the data analysis result of a certain pressure monitoring sub-area of ​​the user is abnormal, the sensor of the pressure monitoring sub-area of ​​the user is adjusted and prompted; if the data analysis result of a certain pressure monitoring sub-area of ​​the user is normal, the average pressure threshold of each pressure monitoring sub-area of ​​the user is obtained according to the number of pressure ulcers of the user and the average time for pressure ulcer healing.

[0100] It should be added that the average pressure threshold of each pressure monitoring sub-area of ​​the user is obtained by matching the number of pressure sore occurrences of the user and the average time for pressure sore healing, and a mapping set is constructed between the interval of the number of pressure sore occurrences of the user and the first pressure threshold of each pressure monitoring sub-area of ​​the user corresponding to the number of pressure sore occurrences of the user. The real-time number of pressure sore occurrences of the user is input, and the interval in which the number of pressure sore occurrences of the user is matched is obtained. The first pressure threshold of each pressure monitoring sub-area of ​​the user corresponding to the number of pressure sore occurrences of the user is obtained through the mapping set. A mapping set is constructed between the interval of the average time for pressure sore healing of the user and the second pressure threshold of each pressure monitoring sub-area of ​​the user corresponding to the average time for pressure sore healing of the user is input, and the interval in which the average time for pressure sore healing of the user is matched is obtained. The second pressure threshold of each pressure monitoring sub-area of ​​the user corresponding to the average time for pressure sore healing of the user is obtained through the mapping set. The first pressure threshold and the second pressure threshold of each pressure monitoring sub-area of ​​the user are averaged to obtain the average pressure threshold of each pressure monitoring sub-area of ​​the user.

[0101] The average pressure of each pressure monitoring sub-area of ​​the user during the supervision period is compared with the average pressure threshold of each pressure monitoring sub-area of ​​the corresponding user. If the average pressure of a certain pressure monitoring sub-area of ​​the user during the supervision period is higher than or equal to the average pressure threshold of each pressure monitoring sub-area of ​​the corresponding user, the pressure judgment result of the user is marked as abnormal, and all abnormal pressure monitoring sub-areas of the user are marked at the same time. If the average pressure of each pressure monitoring sub-area of ​​the user during the supervision period is lower than the average pressure threshold of each pressure monitoring sub-area of ​​the corresponding user, the pressure judgment result of the user is marked as normal, thereby obtaining the pressure judgment result of the user, and issuing an early warning prompt to the user interface based on the pressure judgment result of the user.

[0102] It should be added that the user's pressure judgment result also includes a comprehensive analysis based on the average pressure of each pressure monitoring sub-area of ​​the user in each supervision cycle, the comprehensive risk assessment value of data abnormality of each pressure monitoring sub-area of ​​the user, the number of times the user's pressure ulcers occur, and the average healing time of the user's pressure ulcers to obtain the user's pressure abnormality assessment value.

[0103] It should be added that in the process of analyzing and obtaining the user's pressure abnormality assessment value, the average pressure of each pressure monitoring sub-area of ​​the user, the comprehensive risk assessment value of data abnormality of each pressure monitoring sub-area of ​​the user, the number of pressure ulcers of the user and the average time for the user's pressure ulcer healing were all de-unitized.

[0104] It should be noted that the user's pressure abnormality assessment value represents the numerical quantification result of the pressure abnormality assessment value obtained by analyzing the user's historical pressure ulcer information and pressure measurement data. It is used to comprehensively quantify the impact of the user's average pressure ulcer healing time on the assessment accuracy of the pressure abnormality assessment value. It can be obtained through the following analysis method. The specific analysis conditions are as follows:

[0105] In the formula, α represents the user's stress abnormality assessment value, represents the average pressure of the user's i-th pressure monitoring sub-area in the j-th supervision cycle, ω1 represents the weight factor corresponding to the set pressure, β i represents the data anomaly comprehensive risk assessment value of the user's i-th pressure monitoring sub-area, ω2 represents the weight factor corresponding to the set data anomaly comprehensive risk assessment value, represents the number of pressure sores that occur in the user during the jth supervision period, ω3 represents the weight factor corresponding to the set number of pressure sores, represents the average duration of pressure sore healing for the user in the jth supervision cycle, ω4 represents the weight factor corresponding to the set pressure sore healing duration, j represents the number of each supervision cycle, j = 1, 2, 3, ... m, m represents the total number of supervision cycles, i represents the number of each pressure monitoring sub-area of ​​the user, i = 1, 2, 3, ... n, n represents the total number of pressure monitoring sub-areas.

[0106] It should be added that, in this embodiment, the weight factor corresponding to the preset pressure, the weight factor corresponding to the comprehensive risk assessment value of data anomaly, the weight factor corresponding to the number of pressure ulcer occurrences, and the weight factor corresponding to the pressure ulcer healing time are obtained from the pressure distribution monitoring database.

[0107] It should be noted that the weight factor corresponding to the pressure represents the numerical value of the influence of the average pressure of each pressure monitoring sub-area of ​​the user on the pressure anomaly assessment value, the weight factor corresponding to the data anomaly comprehensive risk assessment value represents the numerical value of the influence of the data anomaly comprehensive risk assessment value on the pressure anomaly assessment value, the weight factor corresponding to the number of pressure sore occurrences represents the numerical value of the influence of the number of pressure sore occurrences of the user on the pressure anomaly assessment value, and the weight factor corresponding to the pressure sore healing time represents the numerical value of the influence of the average pressure sore healing time of the user on the pressure anomaly assessment value. These corresponding relationships are pre-set mapping relationships. For example, the average pressure of each pressure monitoring sub-area of ​​the user and the weight factors corresponding to the preset pressures obtained from the pressure distribution monitoring database form a mapping set. The real-time average pressure of each pressure monitoring sub-area of ​​the user is input into the mapping set to obtain the weight factors corresponding to the average pressure of each pressure monitoring sub-area of ​​the user. The data anomaly comprehensive risk assessment values ​​of each pressure monitoring sub-area of ​​the user and the weight factors corresponding to the preset data anomaly comprehensive risk assessment values ​​obtained from the pressure distribution monitoring database form a mapping set, and the real-time data anomaly comprehensive risk assessment values ​​of each pressure monitoring sub-area of ​​the user are input into the mapping set to obtain the weight factors corresponding to the data anomaly comprehensive risk assessment values ​​of each pressure monitoring sub-area of ​​the user. The number of pressure sore occurrences of the user and the weight factors corresponding to the preset number of pressure sore occurrences obtained from the pressure distribution monitoring database form a mapping set, and the real-time number of pressure sore occurrences of the user are input into the mapping set to obtain the weight factors corresponding to the number of pressure sore occurrences of the user. The average time for the healing of pressure sores of the user and the weight factors corresponding to the preset pressure sore healing time obtained from the pressure distribution monitoring database form a mapping set, and the real-time average time for the healing of pressure sores of the user is input into the mapping set to obtain the weight factors corresponding to the average time for the healing of pressure sores of the user.

[0108] It should be added that there is a correlation between the average pressure of each pressure monitoring sub-area of ​​the user in each supervision cycle, the comprehensive risk assessment value of data anomalies in each pressure monitoring sub-area of ​​the user, the number of pressure ulcers of the user and the average time for the pressure ulcer to heal. They do not exist independently. For example, when the average pressure of the pressure monitoring sub-area is high, it means that the monitoring sub-area may have experienced an unstable pressure state and the probability of pressure ulcers may be high.

[0109] In this implementation plan, a comprehensive analysis is conducted on the average pressure of each pressure monitoring sub-area of ​​the user in each supervision cycle, the comprehensive risk assessment value of data abnormality in each pressure monitoring sub-area of ​​the user, the number of pressure ulcers of the user and the average healing time of the pressure ulcers of the user, so as to assess the pressure ulcer risk of each user and take timely measures to prevent the occurrence of pressure ulcers.

[0110] It should be added that obtaining the user's pressure judgment result also includes comparing the user's pressure abnormality assessment value with the set pressure abnormality assessment threshold. If the user's pressure abnormality assessment value is lower than the set pressure abnormality assessment threshold, the user's pressure judgment result is marked as normal. If the user's pressure abnormality assessment value is higher than or equal to the set pressure abnormality assessment threshold, the user's pressure judgment result is marked as abnormal, thereby obtaining the user's pressure judgment result.

[0111] Specifically, the user interface is given a warning prompt based on the user's pressure judgment result. The specific process is: if the user's pressure judgment result is normal, the staff will be prompted through the user interface, indicating that the user has no pressure ulcer risk. If the user's pressure judgment result is abnormal, all abnormal pressure monitoring sub-areas of the user will be marked through the user interface, and the pressure ulcer risk warning information and the corresponding pressure distribution map of the user's pressure monitoring sub-area will be sent to the staff.

[0112] It should be noted that the pressure ulcer risk warning system based on pressure distribution monitoring also includes a pressure distribution monitoring database, which is used to store the correction factor corresponding to the static pressure obtained by analyzing historical data, the correction factor corresponding to the signal strength, the reference data transmission frequency, the reference sampling frequency, the correction factor corresponding to the sampling frequency, the weight factor corresponding to the number of sensor network offline, the weight factor corresponding to the data transmission frequency, the weight factor corresponding to the sampling frequency, the weight factor corresponding to the sensor abnormality index value, the weight factor corresponding to the network connection abnormality index value, the data abnormality comprehensive evaluation threshold, the sensor abnormality index threshold, the network connection abnormality index threshold, the weight factor corresponding to the pressure, the weight factor corresponding to the data abnormality comprehensive risk assessment value, the weight factor corresponding to the number of pressure ulcer occurrences, the weight factor corresponding to the pressure ulcer healing time and the pressure abnormality evaluation threshold.

[0113] As shown in FIG2 , the second aspect of the present invention provides a pressure ulcer risk warning method based on pressure distribution monitoring, including: dividing the pressure monitoring area to obtain pressure monitoring sub-areas of the user.

[0114] During a preset supervision period, sensor operation data of each pressure monitoring sub-area of ​​the user, network connection data of each pressure monitoring sub-area of ​​the user, pressure measurement data of the user, and historical pressure ulcer information of the user are collected.

[0115] The sensor operation data of each pressure monitoring sub-area of ​​the user in each supervision cycle is analyzed to obtain the sensor abnormality index value of each pressure monitoring sub-area of ​​the user. Combined with the network connection data of each pressure monitoring sub-area of ​​the user in each supervision cycle, the comprehensive risk assessment value of data abnormality of each pressure monitoring sub-area of ​​the user is obtained, and adjustment prompts are provided.

[0116] A comprehensive analysis is performed on the user's historical pressure ulcer information, the user's pressure measurement data, and the comprehensive risk assessment value of data abnormalities in each pressure monitoring sub-area of ​​the user during each supervision cycle to obtain the user's pressure judgment result, and an early warning prompt is given to the user interface based on the user's pressure judgment result.

[0117] The third aspect of the present invention provides a pressure sore risk warning device based on pressure distribution monitoring, which also includes: a processor, and a memory and a network interface connected to the processor: the network interface is connected to the non-volatile memory in the server: the processor calls the computer program from the non-volatile memory through the network interface during operation, and runs the computer program through the memory to execute the above-mentioned pressure sore risk warning method based on pressure distribution monitoring.

[0118] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0119] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to the specific embodiments described. Obviously, numerous modifications and variations are possible based on the contents of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention.

Claims

1. A pressure sore risk early warning system based on pressure distribution monitoring, characterized in that: include: The area division module is used to divide the pressure monitoring area to obtain the pressure monitoring sub-areas of the user; A data collection and processing module, used to collect sensor operation data of each pressure monitoring sub-area of ​​the user, network connection data of each pressure monitoring sub-area of ​​the user, pressure measurement data of the user, and historical pressure ulcer information of the user within each preset supervision cycle; The data anomaly analysis module is used to analyze the sensor operation data of each pressure monitoring sub-area of ​​the user in each supervision period, obtain the sensor anomaly index value of each pressure monitoring sub-area of ​​the user, and analyze the network connection data of each pressure monitoring sub-area of ​​the user in each supervision period to obtain the data anomaly comprehensive risk assessment value of each pressure monitoring sub-area of ​​the user, and provide adjustment prompts; The risk warning prompt module is used to comprehensively analyze the user's historical pressure ulcer information, the user's pressure measurement data in each supervision cycle, and the comprehensive risk assessment value of data abnormalities in each pressure monitoring sub-area of ​​the user, obtain the user's pressure judgment result, and issue a warning prompt to the user interface based on the user's pressure judgment result.

2. The pressure sore risk early warning system based on pressure distribution monitoring according to claim 1 is characterized in that: The specific process of obtaining the sensor abnormality index value of each pressure monitoring sub-area of ​​the user is as follows: Extract sensor operation data of each pressure monitoring sub-area of ​​the user in each supervision cycle, including average output voltage, average sensitivity, average signal strength, average sampling frequency and average bias value of each sensor, and add the product of average output voltage of each sensor in each pressure monitoring sub-area of ​​the user and average sensitivity of each sensor to the average bias value of each sensor as the static pressure of each sensor in each pressure monitoring sub-area of ​​the user in each supervision cycle; A comprehensive analysis is performed on the static pressure, average signal strength and average sampling frequency of each sensor in each pressure monitoring sub-area of ​​the user in each supervision period to obtain the sensor abnormality index value of each pressure monitoring sub-area of ​​the user.

3. The pressure sore risk early warning system based on pressure distribution monitoring according to claim 1 is characterized in that: The network connection data of each pressure monitoring sub-area of ​​the user in each supervision cycle is analyzed, and the specific analysis process is as follows: Extract the network connection data of each pressure monitoring sub-area of ​​the user in each supervision cycle, including the number of sensor network connections, the total number of sensors, the total number of data packets sent by each sensor, and the average sampling frequency of each sensor; The difference between the total number of sensors in each pressure monitoring sub-area of ​​the user in each supervision period and the number of sensor network connections is used as the number of sensor network offlines in each pressure monitoring sub-area of ​​the user in each supervision period; The ratio of the total number of data packets sent by each sensor in each pressure monitoring sub-area of ​​the user in each supervision cycle to the duration of each supervision cycle is used as the data transmission frequency of each sensor in each pressure monitoring sub-area of ​​the user in each supervision cycle; According to the number of sensor network offlines and the data transmission frequency of each sensor in each pressure monitoring sub-area of ​​the user in each supervision cycle, combined with the average sampling frequency of each sensor in each pressure monitoring sub-area of ​​the user in each supervision cycle, a comprehensive analysis is performed to obtain the network connection abnormality index value of each pressure monitoring sub-area of ​​the user.

4. The pressure sore risk early warning system based on pressure distribution monitoring according to claim 3 is characterized in that: The specific process of obtaining the data anomaly comprehensive risk assessment value of each pressure monitoring sub-area of ​​the user is as follows: Comprehensively analyze the sensor abnormality index values ​​of each pressure monitoring sub-area of ​​the user and the network connection abnormality index values ​​of each pressure monitoring sub-area of ​​the user to obtain the data abnormality comprehensive risk assessment value of each pressure monitoring sub-area of ​​the user, and then analyze and obtain the data analysis results of each pressure monitoring sub-area of ​​the user; The data analysis results of each pressure monitoring sub-area of ​​the user include normal data analysis and abnormal data analysis; Compare the data anomaly comprehensive risk assessment value of each pressure monitoring sub-area of ​​the user with the set data anomaly comprehensive assessment threshold. If the data anomaly comprehensive risk assessment value of a certain pressure monitoring sub-area of ​​the user is lower than the set data anomaly comprehensive assessment threshold, mark the data analysis result of the pressure monitoring sub-area of ​​the user as normal data analysis; If the data anomaly comprehensive risk assessment value of a certain pressure monitoring sub-area of ​​the user is higher than or equal to the set data anomaly comprehensive assessment threshold, the data analysis result of the pressure monitoring sub-area of ​​the user is marked as data analysis anomaly; According to the data analysis results of each pressure monitoring sub-area of ​​the user, adjustment prompts are given to the sensors of each pressure monitoring sub-area of ​​the user.

5. The pressure sore risk early warning system based on pressure distribution monitoring according to claim 4 is characterized in that: According to the data analysis results of each pressure monitoring sub-area of ​​the user, the sensor of each pressure monitoring sub-area of ​​the user is adjusted and prompted, and the specific process is as follows: If the data analysis result of a certain pressure monitoring sub-area of ​​the user is abnormal, the staff will be prompted that the data analysis is abnormal, and the data acquisition and processing system will be updated. At the same time, the sensor will be reconnected and the data transmission frequency and sampling frequency of the sensor will be adjusted.

6. The pressure sore risk early warning system based on pressure distribution monitoring according to claim 1, further comprising: Extract the user's historical pressure sore information, including the number of pressure sores the user has had and the average time it takes for the user's pressure sores to heal; Extracting the user's pressure measurement data in each monitoring cycle, including the average pressure of each pressure monitoring sub-area of ​​the user and the pressure distribution diagram of each pressure monitoring sub-area of ​​the user; Based on the average pressure of each pressure monitoring sub-area of ​​the user in each supervision cycle, the data analysis results of each pressure monitoring sub-area of ​​the user, combined with the number of times the user's pressure ulcers occur and the average time for the user's pressure ulcers to heal, a comprehensive analysis is performed to obtain the user's pressure judgment result.

7. The pressure sore risk early warning system based on pressure distribution monitoring according to claim 6 is characterized in that: The specific process of obtaining the user's pressure judgment result is as follows: If the data analysis result of a certain pressure monitoring sub-area of ​​the user is abnormal, the sensor of the pressure monitoring sub-area of ​​the user is adjusted. If the data analysis result of a certain pressure monitoring sub-area of ​​the user is normal, the average pressure threshold of each pressure monitoring sub-area of ​​the user is obtained according to the number of pressure sores of the user and the average time of pressure sore healing; The average pressure of each pressure monitoring sub-area of ​​the user within the supervision period is compared with the average pressure threshold of each pressure monitoring sub-area of ​​the corresponding user. If the average pressure of a pressure monitoring sub-area of ​​the user within the supervision period is higher than or equal to the average pressure threshold of each pressure monitoring sub-area of ​​the corresponding user, the pressure judgment result of the user is marked as abnormal, and all abnormal pressure monitoring sub-areas of the user are marked at the same time. If the average pressure of each pressure monitoring sub-area of ​​the user within the supervision period is lower than the average pressure threshold of each pressure monitoring sub-area of ​​the corresponding user, the pressure judgment result of the user is marked as normal, thereby obtaining the pressure judgment result of the user, and issuing an early warning prompt to the user interface according to the pressure judgment result of the user.

8. The pressure sore risk early warning system based on pressure distribution monitoring according to claim 7 is characterized in that: The specific process of providing an early warning prompt to the user interface based on the user's pressure judgment result is as follows: If the user's pressure judgment result is normal, the staff will be prompted through the user interface, indicating that the user has no risk of pressure sores. If the user's pressure judgment result is abnormal, all abnormal pressure monitoring sub-areas of the user will be marked through the user interface, and the pressure sore risk warning information and the corresponding pressure distribution map of the user's pressure monitoring sub-area will be sent to the staff.

9. A pressure sore risk early warning method based on pressure distribution monitoring, characterized in that: include: Divide the pressure monitoring area to obtain each pressure monitoring sub-area of ​​the user; Collecting sensor operation data of each pressure monitoring sub-area of ​​the user, network connection data of each pressure monitoring sub-area of ​​the user, pressure measurement data of the user, and historical pressure ulcer information of the user within a preset supervision period; Analyze the sensor operation data of each pressure monitoring sub-area of ​​the user in each supervision cycle to obtain the sensor abnormality index value of each pressure monitoring sub-area of ​​the user, and analyze it in combination with the network connection data of each pressure monitoring sub-area of ​​the user in each supervision cycle to obtain the data abnormality comprehensive risk assessment value of each pressure monitoring sub-area of ​​the user, and make adjustment prompts; A comprehensive analysis is performed on the user's historical pressure ulcer information, the user's pressure measurement data, and the comprehensive risk assessment value of data abnormalities in each pressure monitoring sub-area of ​​the user during each supervision cycle to obtain the user's pressure judgment result, and an early warning prompt is given to the user interface based on the user's pressure judgment result.

10. Use of any one of claims 1 to 9 for a pressure sore risk warning device based on pressure distribution monitoring, characterized in that: It includes: a processor, and a memory and a network interface connected to the processor; the network interface is connected to a non-volatile memory in a server; when the processor is running, it calls a computer program from the non-volatile memory through the network interface, and runs the computer program through the memory to execute the method described in any one of claims 1 to 9.