Ward patient off-bed behavior monitoring and falling early warning method based on millimeter wave radar

Abstract

The invention relates to the technical field of medical care, and provides a ward patient off-bed behavior monitoring and falling early warning method based on millimeter wave radar, comprising the following steps: step 1, driving the millimeter wave radar to release a radar signal, and receiving a springback signal; step 2, based on a positioning chest plate worn by a patient lying on the sickbed and a springback reinforcing signal received by the millimeter wave radar, dividing areas to confirm the area position of each sickbed based on the direction of the reinforcing signal; and 3, performing posture anchoring on the state of the patient at regular time, continuously monitoring the position and action posture of the patient through a rebound signal, setting a prohibited area and removing an abnormal value. The position and action posture of the patient can be continuously monitored, dynamic real-time monitoring of the patient is achieved, monitoring blind areas existing in traditional manual inspection and patient autonomous calling modes are avoided, monitoring timeliness and accuracy are improved, the risk that the patient falls down after leaving the bed is effectively reduced, and the safety of the patient is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of medical care, and specifically to a method for monitoring the behavior of patients getting out of bed and fall warning in a ward based on millimeter-wave radar. Background Art

[0002] In the field of medical care, especially in the ward, patients may fall after getting out of bed due to sudden illness, physical weakness, inconvenient movement, etc., which may cause serious physical harm to the patients and even endanger their lives. Traditional monitoring methods mainly rely on the manual patrol of medical staff and the independent call of patients. This method has obvious limitations. For example, it is impossible to monitor the dynamics of patients in real time, there are easy monitoring blind spots, and for patients with inconvenient movement or unclear consciousness, their independent call ability is limited and they cannot send out help signals in time.

[0003] In addition, although existing medical monitoring technologies can achieve a certain degree of monitoring, there are privacy issues, which are likely to cause resistance among patients, and are easily affected by environmental light, occlusion and other factors, resulting in a decrease in the accuracy and reliability of monitoring. Therefore, a method for monitoring the behavior of patients getting out of bed and fall warning in a ward based on millimeter-wave radar is needed. Summary of the Invention

[0004] In view of the deficiencies of the prior art, the present invention provides a method for monitoring the behavior of patients getting out of bed and fall warning in a ward based on millimeter-wave radar, which solves the problems that existing medical monitoring technologies have privacy issues, are likely to cause resistance among patients, and are easily affected by environmental light, occlusion and other factors.

[0005] To achieve the above objectives, the present invention is realized through the following technical solutions: A method for monitoring the behavior of patients getting out of bed and fall warning in a ward based on millimeter-wave radar, comprising the following steps: Step 1: Drive the millimeter-wave radar to release radar signals and receive the rebound signals; Step 2: Based on the positioning chest tag worn by the patient lying in the hospital bed, the millimeter-wave radar receives the strengthened rebound signals. Based on the azimuth of the strengthened signals, regions are divided to confirm the regional positions of each hospital bed; Step 3: Regularly perform attitude anchoring on the patient's state, continuously monitor the patient's position and movement attitude through the rebound signals, and set prohibited areas and remove outliers; Step 4: Based on the attitude anchoring data in Step 3, perform attitude detection and prohibited area monitoring to determine whether the patient is safely located in the hospital bed; Step 5: When the patient is in the prohibited area for 5-10 seconds, switch to monitoring the movement attitude of the patient individual, and continuously track the movement trajectory and body attitude of the patient; Step 6: When the patient's movement trajectory and body posture data are no longer updated, and the data in the prohibited area stops updating, perform a fall judgment. Step 7: If the judgment is successful, an alarm is issued.

[0006] Preferably, the signal frequency range of the millimeter-wave radar is 59 - 64 GHz, and the material of the positioning chest tag is a micro-nano structure material to enhance the signal reflection intensity of the millimeter-wave radar, so as to determine whether it is a patient according to the signal intensity.

[0007] Preferably, in Step 3, if the outlier is not refreshed in the prohibited area position interval less than 3 s and does not carry data with enhanced signals, it is determined as non-patient personnel including medical staff, patient families, etc.

[0008] Preferably, the specific steps of outlier rejection in Step 3 include: S1: Based on the intensity and time interval of the rebound signal, filter out abnormal signals with signal intensity lower than the threshold and duration shorter than the set value; S2: According to the source direction and movement trajectory of the abnormal signal, compare with the known hospital bed position and the patient's activity range to determine whether the signal is generated by non-patient personnel; S3: Reject the abnormal signals determined to be generated by non-patient personnel and retain the valid signals related to the patient.

[0009] Preferably, the specific steps of posture anchoring in Step 3 include: S1: Convert the rebound radar signal received by the millimeter-wave radar into a digital signal; S2: Convert the digital signal in S1 into a curve model; S3: Based on the curve model, determine the patient's posture on the bed and match it with the previously collected patient body posture reflection curve; S4: If the matching rate is higher than the threshold, determine that the patient is in the matching posture, otherwise repeat S1 - S4; S5: Perform numerical anchoring based on the matching posture and set it as a reference value, that is, the posture anchoring data.

[0010] Preferably, the specific steps of posture detection in Step 4 are: S1: Capture the change value based on the posture anchoring data and monitor the amplitude and frequency of the patient's posture change in real time; S2: Analyze whether the patient is in the pre-action state of getting out of bed according to the characteristics of the posture change.

[0011] Preferably, the frequency of action posture monitoring in Step 5 is 10 times per second.

[0012] Preferably, the interval between each attitude anchoring in step three is 10 s.

[0013] Preferably, the alarm methods in step seven include sound alarm, light alarm and information push alarm, and the alarm level increases step by step according to the risk degree of the patient.

[0014] Preferably, the objects of the information push alarm include nearby nurses, doctors and patient families.

[0015] The present invention provides a method for monitoring the behavior of a patient getting out of bed and fall warning in a ward based on a millimeter-wave radar. It has the following beneficial effects: 1. The present invention can continuously monitor the position and movement posture of the patient, realizes the real-time monitoring of the patient's dynamics, avoids the monitoring blind spots existing in the traditional manual patrol and the patient's independent calling methods, improves the timeliness and accuracy of the monitoring, effectively reduces the risk of the patient falling after getting out of bed, and ensures the safety of the patient.

[0016] 2. The present invention uses a positioning chest tag to enhance the signal reflection intensity of the millimeter-wave radar, which is convenient for accurately identifying the patient. At the same time, by processing the rebound signal, it can effectively eliminate the abnormal signals generated by non-patient personnel, improve the accuracy of the monitoring, reduce the false alarm situation, improve the work efficiency of medical staff, and reduce the anxiety of the patient. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flowchart of the method of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0018] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0019] Embodiment: Please refer to the attached Figure 1 , the embodiment of the present invention provides a method for monitoring the behavior of a patient getting out of bed and fall warning in a ward based on a millimeter-wave radar, including the following steps: Step 1: Drive the millimeter-wave radar to release radar signals and receive the rebound signals. The signal frequency range of the millimeter-wave radar is 59-64 GHz, and the material of the positioning chest tag is a micro-nano structure material to enhance the signal reflection intensity of the millimeter-wave radar, so as to determine whether it is a patient according to the signal intensity; Step 2: Based on the positioning nameplate worn by the patient lying in the hospital bed, the millimeter-wave radar receives a strengthened signal that rebounds. Based on the azimuth of the strengthened signal, divide the area to confirm the area positions of each hospital bed; Step 3: Regularly perform pose anchoring on the patient's state. The interval between each pose anchoring is 10 s. Continuously monitor the patient's position and movement pose through the rebound signal, and set prohibited areas and remove outliers. If the outlier does not refresh within an interval less than 3 s at the prohibited area position and does not carry data with a strengthened signal, it is determined as a non-patient person including medical staff, patient family members, etc.; The specific steps of pose anchoring include: S1: Convert the rebound radar signal received by the millimeter-wave radar into a digital signal; S2: Convert the digital signal in S1 into a curve model; S3: Based on the curve model, determine the pose of the patient lying in the bed and match it with the pre-collected patient body reflection curve; S4: If the matching rate is higher than the threshold, determine that the patient is in the matching pose; otherwise, repeat S1 - S4; S5: Perform numerical anchoring based on the matching pose and set it as a reference value, that is, pose anchoring data; The specific steps of outlier removal include: S1: Based on the strength and time interval of the rebound signal, filter out abnormal signals with a signal strength lower than the threshold and a duration shorter than the set value; S2: According to the source direction and movement trajectory of the abnormal signal, compare it with the known hospital bed position and the patient's activity range to determine whether it is a signal generated by a non-patient person; S3: Remove the abnormal signals determined to be generated by non-patient persons and retain the valid signals related to the patient; Step 4: Based on the pose anchoring data in Step 3, perform pose detection and prohibited area monitoring to determine whether the patient is safely lying in the hospital bed. The specific steps of pose detection are as follows: S1: Capture the change value based on the pose anchoring data and continuously monitor the amplitude and frequency of the patient's pose change; S2: Analyze whether the patient is in the pre-action state of getting out of bed according to the characteristics of the pose change; Step 5: When the patient has been in the prohibited area for 5 - 10 s, switch to action pose monitoring for this patient individual, continuously track the patient's action trajectory and body pose, and the frequency of action pose monitoring is 10 times per second; Step 6: When the patient's action trajectory and body pose data no longer update and the data in the prohibited area stops updating, perform a fall judgment; Step 7: If successful, an alarm is issued. The alarm methods include sound alarm, light alarm, and information push alarm. Moreover, the alarm level increases step by step according to the risk level of the patient. The objects of the information push alarm include nearby nurses, doctors, and the patient's family members.

[0020] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for monitoring the behavior of ward patients getting out of bed and fall warning based on millimeter-wave radar, characterized in that, It includes the following steps: Step 1: Drive the millimeter-wave radar to release radar signals and receive the rebound signals; Step 2: Based on the positioning chest tag worn by the patient lying in the hospital bed, the millimeter-wave radar receives the strengthened rebound signals. Based on the azimuth of the strengthened signals, divide the area to confirm the area positions of each hospital bed; Step 3: Regularly perform attitude anchoring on the patient's state, continuously monitor the patient's position and movement posture through the rebound signals, and set prohibited areas and remove outliers; Step 4: Based on the attitude anchoring data in Step 3, perform attitude detection and prohibited area monitoring to determine whether the patient is safely located in the hospital bed; Step 5: When the patient is in the prohibited area for 5 - 10 seconds, switch to monitoring the patient's action posture, and continuously track the patient's action trajectory and body posture; Step 6: When the patient's action trajectory and body posture data no longer update, and after the data in the prohibited area stops updating, perform a fall judgment; Step 7: If the judgment is successful, issue an alarm.

2. The method for monitoring the behavior of a ward patient getting out of bed and fall warning based on a millimeter-wave radar according to claim 1, wherein The signal frequency range of the millimeter-wave radar is 59 - 64 GHz, and the material of the positioning chest tag is a micro-nano structure material to enhance the signal reflection intensity of the millimeter-wave radar, so as to determine whether it is a patient according to the signal intensity.

3. A method for monitoring the behavior of a ward patient getting out of bed and fall warning based on a millimeter-wave radar according to claim 1, characterized in that, In Step 3, if the outlier does not refresh within an interval less than 3 seconds at the prohibited area position and does not carry data with strengthened signals, it is determined to be a non-patient person including medical staff, patient family members, etc.

4. A method for monitoring the behavior of a ward patient getting out of bed and fall warning based on a millimeter-wave radar according to claim 1, characterized in that, The specific steps for removing outliers in Step 3 include: S1: Based on the intensity and time interval of the rebound signals, screen out abnormal signals with signal intensity lower than the threshold and duration shorter than the set value; S2: According to the source direction and movement trajectory of the abnormal signals, compare them with the known hospital bed positions and the patient's activity range to determine whether they are signals generated by non-patient persons; S3: Remove the abnormal signals determined to be generated by non-patient persons and retain the valid signals related to the patient.

5. A method for monitoring the behavior of a ward patient getting out of bed and fall warning based on a millimeter-wave radar according to claim 1, characterized in that, The specific steps for attitude anchoring in Step 3 include: S1: Convert the received rebound radar signals of the millimeter-wave radar into digital signals; S2: Convert the digital signals in S1 into a curve model; S3: Based on the curve model, determine the patient's posture on the bed and match it with the previously collected patient body posture reflection curve; S4: If the matching rate is higher than the threshold, determine that the patient is in the matching posture, otherwise repeat S1 - S4; S5: Perform numerical anchoring based on the matching posture and set it as the reference value, that is, the attitude anchoring data.

6. The method for monitoring the behavior of a ward patient getting out of bed and fall warning based on a millimeter-wave radar according to claim 5, characterized in that, The specific steps for attitude detection in Step 4 are: S1: Capture the change values based on the attitude anchoring data and real-time monitor the amplitude and frequency of the patient's attitude changes; S2: Analyze whether the patient is in the pre-action state of getting out of bed according to the characteristics of the attitude changes.

7. A method for monitoring the behavior of patients getting out of bed and fall warning in a ward based on millimeter-wave radar according to claim 1, characterized in that, The monitoring frequency of the action posture in Step 5 is 10 times per second.

8. A method for monitoring the behavior of patients getting out of bed and fall warning in a ward based on millimeter-wave radar according to claim 1, characterized in that The interval for each attitude anchoring in Step 3 is 10 seconds.

9. A method for monitoring the behavior of a ward patient getting out of bed and fall warning based on a millimeter-wave radar according to claim 1, characterized in that, The ways of the alarm in Step 7 include sound alarm, light alarm and information push alarm, and the alarm level increases step by step according to the patient's risk level.

10. A method for monitoring the behavior of a ward patient getting out of bed and fall warning based on a millimeter-wave radar according to claim 9, characterized in that, The objects of the information push alarm include nearby nurses, doctors and patient family members.

Images