Patient behavior monitoring and alert system

Abstract

Embodiments of the present disclosure disclose a patient behavior monitoring and early warning system. A specific embodiment of the system comprises: a door lock control device: opening or closing a toilet door of a patient toilet according to received access card information, and sending an opening time point and a closing time point of the opening or closing of the toilet door to a monitoring terminal; a weight sensing device: collecting weight data of the patient in an open state, and sending the weight data to the monitoring terminal; and the monitoring terminal: storing the opening time point and the closing time point in a patient toilet entry record table corresponding to a patient number, recording received weight data in a pre-established patient weight data table, and monitoring a toilet entry duration and weight data of the patient to obtain a monitoring result, and performing a corresponding early warning operation according to the monitoring result. The embodiment can accurately record patient toilet entry time and real-time monitor patient toilet entry status.

Description

TECHNICAL FIELD

[0001] Embodiments of the present disclosure relate to the medical field and the computer field, and in particular to a patient behavior monitoring and early warning system. BACKGROUND

[0002] The existing ward toilet door lock is a common door lock, which has problems such as being unable to accurately record the patient's toilet time, being unable to monitor the patient's toilet state in real time, and lacking an emergency unlocking and alarm mechanism.

[0003] The above information disclosed in the background section is only for the purpose of enhancing the understanding of the background of the present inventive concept, and therefore, it can include information that does not form the prior art known to those of ordinary skill in the art. SUMMARY

[0004] The summary section is provided to introduce the concepts briefly in a simplified form, which will be described in detail in the specific embodiments section. The summary section is not intended to identify key or essential features of the claimed technology nor is it intended to be used to limit the scope of the claimed technology.

[0005] Some embodiments of the present disclosure propose a patient behavior monitoring and early warning system to solve the technical problems mentioned in the background section.

[0006] In a first aspect, some embodiments of the present disclosure provide a patient behavior monitoring and early warning system, which comprises: a door lock control device configured to: open or close a toilet room door of a ward toilet according to received access card information, and send an opening time point and a closing time point of opening or closing the toilet room door to a monitoring terminal, wherein the access card information is generated by the door lock control device by a personal monitoring wristband worn by a patient, the personal monitoring wristband is provided with a unique identification signal, and the identification signal of the personal monitoring wristband is bound to a patient number of the patient during a hospitalization period of the patient; a body weight sensing device configured to: collect body weight data of the patient in an open state, and send the body weight data to the monitoring terminal, wherein the body weight sensing device comprises a first sensing device and a second sensing device, and the first sensing device and the second sensing device are used to measure the gravity exerted by both feet of the patient when entering the toilet as the body weight data; and the monitoring terminal is configured to: store the opening time point and the closing time point in a patient toilet record table corresponding to the patient number, record the received gravity data in a pre-established patient body weight data table, and monitor the toilet time and the body weight data of the patient to obtain a monitoring result, and perform a corresponding early warning operation according to the monitoring result, wherein the patient toilet record table and the patient body weight data table are bound to the patient number of the patient.

[0007] In a second aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by one or more processors, the one or more processors implement the system described in any implementation method of the above-mentioned first aspect.

[0008] In a third aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the system described in any implementation of the first aspect is implemented.

[0009] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the patient behavior monitoring and early warning system of some embodiments of the present disclosure, it is possible to accurately record the patient's toilet time, monitor the patient's toilet status in real time, and be equipped with emergency unlocking and alarm mechanisms to ensure patient safety. Specifically, the reasons for the inability to accurately record the patient's toilet time, the inability to monitor the patient's toilet status in real time, and the lack of emergency unlocking and alarm mechanisms are that the existing ward toilet door locks are ordinary door locks, but even if they are set as smart door locks, they require more complex recognition logic, and it is difficult to ensure the accuracy of recognition. Based on this, the patient behavior monitoring and early warning system of some embodiments of the present disclosure, first of all, in order to accurately record the patient's toilet time, introduces a door lock control device and a personal monitoring wristband. Specifically, according to the received access control card swiping information, the toilet door of the ward toilet is opened or closed, and the opening time and closing time of opening or closing the toilet door are sent to the above-mentioned monitoring terminal. The access control card swipe information is generated by the patient's personal monitoring wristband, which senses the door lock control device. The wristband is equipped with a unique identification signal. During the patient's hospitalization period, the identification signal of the wristband is bound to the patient's patient ID. The wristband, when worn by the patient, not only records the patient's vital signs but also records the time the patient swipes their card to use the restroom, which serves as the patient's restroom visit time. This allows for accurate recording of the patient's restroom visit time. Considering the difficulty of monitoring patients' restroom use, the inappropriate installation of cameras in restrooms, and the limitations of radar, infrared, and other measuring instruments, such as computing power, accuracy, and interference, a weight sensor device that can directly measure the patient's weight has been introduced. When enabled, the weight sensor device can collect the patient's weight data and transmit it to the monitoring terminal. The weight sensor device comprises a first sensing device and a second sensing device, each of which measures the force exerted by the patient's feet when using the restroom, generating weight data. This allows for real-time collection of patient weight data. Therefore, the number of times that patients are manually guided to weigh themselves can be greatly reduced, freeing up medical resources. Finally, by introducing a monitoring terminal, the opening and closing time points can be stored in the patient toilet record table corresponding to the above-mentioned patient number, the received gravity data can be recorded in a pre-established patient weight data table, and the patient's toilet time and weight data can be monitored to obtain the monitoring results. According to the monitoring results, the corresponding early warning operation is performed. Among them, the above-mentioned patient toilet record table and the above-mentioned patient weight data table are bound to the patient number of the above-mentioned patient. Therefore, the patient's weight data measured by the weight sensing device can be used to analyze the patient's behavior to determine whether the patient has any abnormal conditions in the toilet. For example, there are sudden situations such as falls, convulsions, and fainting.Thus, the patient's physical condition when going to the toilet is monitored in real time, and an alarm can be issued in time to improve the patient's personal safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0011] Figure 1 is a schematic diagram of an application scenario of the patient behavior monitoring and early warning system according to the present disclosure;

[0012] Figure 2 is a flow chart of some embodiments of the patient behavior monitoring and early warning system according to the present disclosure;

[0013] Figure 3 This is a schematic diagram of the scenario of the weight sensing device;

[0014] Figure 4 It is a structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0015] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0016] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other.

[0017] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0018] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0019] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0020] With regard to the collection, storage, and use of user personal information (such as user heart rate information, user weight information, etc.) involved in this disclosure, before performing the corresponding operations, the relevant organizations or individuals shall fulfill their obligations, including conducting personal information security impact assessments, fulfilling the obligation to inform the personal information subject, and obtaining the authorization and consent of the personal information subject in advance.

[0021] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0022] Figure 1 It is a schematic diagram of an application scenario of the patient behavior monitoring and early warning system of some embodiments of the present disclosure.

[0023] exist Figure 1 In the application scenario, the patient behavior monitoring and early warning system may include: a door lock control device 102, a weight sensing device 103, a personal monitoring wristband 104, and a monitoring terminal 105. First, the door lock control device 102 is configured to open or close the toilet door of the ward toilet according to the received access card swiping information, and send the opening and closing time points of the toilet door to the monitoring terminal. The access card swiping information is generated by the patient's personal monitoring wristband 104 sensing the door lock control device 102. The personal monitoring wristband 104 is provided with a unique identification signal. During the patient's hospitalization period, the identification signal of the personal monitoring wristband 104 is bound to the patient number of the patient. Then, the weight sensing device 103 is configured to: in the turned-on state, collect the weight data of the patient, and send the weight data to the monitoring terminal 105, wherein the weight sensing device 103 includes a first sensing device 1031 and a second sensing device 1032, and the first sensing device and the second sensing device are used to measure the gravity applied by the patient's feet when entering the toilet as weight data. Finally, the monitoring terminal 105 is configured to: store the opening time point and the closing time point in the patient toilet record table corresponding to the patient number, record the received gravity data in a pre-established patient weight data table, and conduct behavioral monitoring of the patient's toilet entry time and weight data to obtain monitoring results, and perform corresponding early warning operations based on the monitoring results, wherein the patient toilet record table and the patient weight data table are bound to the patient number of the patient.

[0024] It should be noted that the patient behavior monitoring and early warning system described above can be hardware or software. When the computing device is hardware, it can be implemented as a distributed cluster composed of multiple servers or terminal devices, or as a single server or single terminal device. When the patient behavior monitoring and early warning system is software, it can be installed in the hardware devices listed above. It can be implemented as multiple software or software modules, for example, to provide distributed services, or as a single software or software module. Herein, no specific limitation is made. It should be understood that Figure 1 The number of gravity sensing devices or door lock control devices in the patient behavior monitoring and early warning system in the above embodiments can have any number according to the needs of implementation.

[0025] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0026] Figure 2 Flow 200 of some embodiments of the patient behavior monitoring and early warning system according to the present disclosure is shown. The patient behavior monitoring and early warning system includes the following steps:

[0027] In step 201, the door lock control device is configured to open or close the toilet room door of the ward toilet according to the received access card information, and send the opening time point and the closing time point of opening or closing the toilet room door to the monitoring terminal.

[0028] In some embodiments, the door lock control device in the execution subject (e.g., a computing device) of the patient behavior monitoring and early warning system is configured to open or close the toilet room door of the ward toilet according to the received access card information, and send the opening time point and the closing time point of opening or closing the toilet room door to the monitoring terminal. Wherein the access card information is generated by the patient through the personal care wristband worn by the patient, and the personal care wristband is provided with a unique identification signal. The identification signal of the personal care wristband is bound to the patient number of the patient during the patient's hospitalization period. Here, the personal care wristband can establish a communication connection with the door lock control device within a certain distance through wireless transmission, so that the door lock control device can identify the identification signal of the personal care wristband.

[0029] In some optional implementations of some embodiments, the door lock control device can include a door lock device, an outside door sensing device, and an inside door sensing device; and

[0030] The execution subject opens or closes the toilet room door of the ward toilet according to the received access card information, and sends the opening time point and the closing time point of opening or closing the toilet room door to the monitoring terminal, including:

[0031] The first step is to determine whether the toilet is occupied in response to receiving the access card information for the door outside induction device. When the toilet is occupied, the other personal monitoring wristbands cannot open the door through the induction of the door outside induction device. The door lock control device extracts the corresponding patient number when the personal monitoring wristband is scanned. Here, the door lock control device can determine whether the toilet is occupied according to whether it is locked. If it is not locked, it is determined that it is not occupied. In addition, the inside of the door lock control device is also provided with a manual unlocking knob.

[0032] The second step is to issue a toilet occupation prompt in response to being occupied. The door lock control device can be provided with a voice prompt function. When the toilet is occupied, a prompt sound such as "toilet occupied" is issued. Alternatively, an occupation display board is provided on the toilet door, displaying the words "toilet occupied".

[0033] The third step is to issue a prompt indicating entry in response to being unoccupied, and to determine the opening time point as the opening time point. The voice prompt function can be used to issue a prompt sound such as "the door is open, please enter".

[0034] The fourth step is to control the door lock device to be unlocked in response to receiving the access card information for the door inside induction device, and to determine the closing time point as the closing time point. After the toilet room door is unlocked, the occupation state of the toilet in the ward is adjusted. The closing time point of the toilet room door is determined as the starting time point before receiving the access card information for the door inside induction device and before receiving the access card information for the door outside induction device. Here, the access card information for the door inside induction device can be information for unlocking. In addition, if the access card information is not sensed, the time point of manual unlocking can also be determined as the closing time point. Secondly, before receiving the access card information for the door inside induction device and before receiving the access card information for the door outside induction device, it can be indicated that the patient did not sense the personal monitoring wristband or the sensing failed when entering the toilet. Therefore, data compensation can be performed in this way.

[0035] In practice, the door outside induction device and the door inside induction device of the door lock control device can be provided near the door handle, so that the patient can automatically scan the personal monitoring wristband worn on the patient's hand when opening the door. Thus, even if the patient forgets to scan, the patient's toilet entry time can also be recorded.

[0036] Step 202, the body weight induction device is configured to collect patient weight data in an open state, and send the weight data to the monitoring terminal.

[0037] In some embodiments, the weight sensing device in the execution subject is configured to, when enabled, collect the patient's weight data and transmit the weight data to the monitoring terminal. The weight sensing device may include a first sensing device and a second sensing device, each of which is configured to measure the weight applied by the patient's feet when using the toilet as weight data.

[0038] In some optional implementations of some embodiments, the weight sensing device is further configured to:

[0039] The first step is to activate the weight sensing device in response to detecting a card swipe for the door sensor when the ward restroom is unoccupied. In practice, to avoid wasting power by leaving the weight sensing device on for extended periods when the restroom is unused, the weight sensing device can be turned off when the restroom is unoccupied. Therefore, upon detecting a card swipe for the door sensor, the weight sensing device can be reactivated.

[0040] The second step is to activate the weight sensing device in response to the failure to detect the access card swipe information for the door sensor and the receipt of the toilet door automatic lock information. Since the door sensor may not detect the personal monitoring wristband or fail to detect it when the patient enters the toilet, the weight sensing device also needs to be activated when the ward toilet automatically locks, indicating that the patient has entered the toilet.

[0041] In practice, when a patient closes the door after exiting the ward, the ward toilet automatically locks and the gravity-sensing device turns off. Therefore, even if the next patient enters without their access card being detected, the door can be manually unlocked and the gravity-sensing device turned on. Furthermore, if the patient leaves the toilet without closing the door, the weight-sensing device can automatically turn off after a certain period of time (e.g., 20 seconds) without pressure. Therefore, when the next patient enters the toilet, the weight-sensing device can still be activated when the access card is detected for the external door sensor or when the toilet door is automatically locked.

[0042] The third step is to turn off the weight sensing device in response to detecting the access card swiping information for the door sensor.

[0043] In some optional implementations of some embodiments, when the weight sensing device is turned on, collecting the patient's weight data and sending the weight data to the monitoring terminal include:

[0044] The first step is to initialize the weight sensing device. Initialization can be to reset the weight sensing device to zero, thereby preventing debris placed on the weight sensing device from affecting the patient's weight measurement results.

[0045] In the second step, the weight sensing device, including the first sensing device and the second sensing device, is used to measure the gravity applied by the patient when entering the toilet, thereby obtaining first weight sensing data and second weight sensing data. The results measured by the first sensing device and the second sensing device may not distinguish between left and right feet. The first sensing device and the second sensing device may be located in the front area of ​​the toilet. Therefore, whether the patient is standing or sitting, they can naturally step on the first sensing device and the second sensing device to obtain the first weight sensing data and the second weight sensing data.

[0046] For example, see Figure 3 . Figure 3 The weight sensing device is arranged in front of the toilet 301. Therefore, no matter standing (e.g., urinating) or sitting (e.g., urinating and / or defecating), the user needs to step on the gravity sensing device. Figure 3 The dotted circles in the figure represent the support legs for the first and second sensing devices. The first and second sensing devices can be waterproof scales. A drain outlet can also be provided on the underside of the device to prevent water accumulation in the mounting groove. The first and second sensing devices are embedded in the ground, with their upper surfaces parallel to the ground, to prevent bumps. The weight sensing device can be connected to the monitoring terminal via a wired connection (weight sensing devices in multiple ward restrooms can be centralized via a switch and connected to one or more monitoring terminals via a wired connection). This enhances anti-interference capabilities and avoids interference that can occur with wireless connections. This improves the real-time and accuracy of measurement results. Furthermore, if the weight sensing device still displays a reading when no one is in the restroom, the monitoring terminal can send a device fault alert to the medical terminal. For example, if a foreign object is lodged between the first or second sensing device and the ground. This allows for timely troubleshooting and ensures proper operation of the device.

[0047] The third step is to combine the first weight sensing data, the second weight sensing data and the corresponding timestamp into weight data, and send the weight data to the monitoring terminal.

[0048] In step 203, the monitoring terminal is configured to: store the opening time point and the closing time point in the patient toilet record table corresponding to the patient number, record the received gravity data in a pre-established patient weight data table, and perform behavioral monitoring on the patient's toilet duration and weight data to obtain monitoring results, and execute corresponding early warning operations based on the monitoring results.

[0049] In some embodiments, the monitoring terminal in the execution entity is configured to: store the opening and closing time points in a patient toilet record table corresponding to the patient number, record the received gravity data in a pre-established patient weight data table, and monitor the patient's toilet duration and weight data to obtain monitoring results, and execute corresponding early warning operations based on the monitoring results. The patient toilet record table and the patient weight data table are both bound to the patient number of the patient.

[0050] In some optional implementations of some embodiments, the execution entity monitors the patient's toilet usage time and weight data to obtain monitoring results, including:

[0051] The first step is to extract the predicted patient weight corresponding to the patient number in the access card swiping information from the preset database in response to the access card swiping information of the door sensor device, wherein the predicted patient weight is the patient weight pre-measured for the patient manually.

[0052] In the second step, the sum of the first weight sensing data and the second weight sensing data in the above weight data is determined as the current patient weight.

[0053] In the third step, the difference between the first weight sensing data and the second weight sensing data in the above weight data is determined as the gravity difference between the patient's feet. The continuous gravity difference between the patient's feet can be used to determine whether the patient's standing posture is stable.

[0054] The fourth step is to determine the number of people going to the toilet based on the predicted patient weight, the current patient weight and the difference in gravity between the patient's feet. In which, in response to the difference between the current patient weight and the predicted patient weight being greater than a preset weight interval, it is determined that the number of people going to the toilet is greater than 1. In practice, the judgment of the number of people going to the toilet may also include at least one of the following judgment strategies: in response to the difference between the current patient weight and the predicted patient weight being less than a preset weight interval, it is determined that the target of going to the toilet is not the person himself or that the standing position is deviated, and the person may be guided to the toilet standing position by manual reminder. If the difference is within the preset weight interval, it can be determined that the number of people going to the toilet is equal to 1. If the difference in gravity between the patient's feet is greater than a preset threshold, and the patient's legs are normal, it is determined that the number of people going to the toilet is greater than 1. Thus, the actual number of people going to the toilet can be greatly determined to avoid errors in measuring the patient's weight. In addition, if the measurement result is uncertain, the current patient weight can be marked as an abnormal value.

[0055] In step 5, in response to the number of people using the toilet being greater than 1, and the number of people using the toilet in the patient's last toilet visit record also being greater than 1, 1 is added to a preset toilet visit excess count, where the toilet visit excess count is a statistical value of the number of people using the toilet being greater than 1 in the patient's consecutive toilet visit records. Here, a continuous excess count greater than 1 may indicate that the patient is unable to use the toilet alone, and manual weight measurement can be performed regularly if necessary.

[0056] In step 6, in response to the above-mentioned excess toilet user count exceeding the pre-set value, a weight monitoring pause instruction is generated, and the above-mentioned current patient weight is marked as an abnormal value. In particular, marking the abnormal value can be used to eliminate abnormal data when the patient weight data is subsequently used, thereby preventing the impact on feature extraction and improving accuracy.

[0057] In practice, the above-mentioned number of people using the restroom can be determined by using a sliding window approach, judging the data at consecutive time points (for example, 10 frames), and then aggregating the data to obtain the final result. This prevents individual sudden data from affecting the judgment result.

[0058] In some optional implementations of some embodiments, the execution subject monitors the patient's toilet usage time and weight data to obtain monitoring results, further comprising:

[0059] In response to the number of people using the toilet being equal to 1, the following processing steps are performed according to the added patient weight data table:

[0060] The first step is to extract the weight data after the door opening time from the above-mentioned patient weight data table to obtain the patient weight sequence, the patient's left foot gravity sequence, and the patient's right foot gravity sequence. The patient weight sequence, the patient's left foot gravity sequence, and the patient's right foot gravity sequence can be obtained from the data corresponding to the patient weight field in the patient weight data table and the weight data after the door opening time.

[0061] In the second step, the values ​​marked with abnormal values ​​in the above patient weight sequence, patient left foot gravity sequence and patient right foot gravity sequence are removed to obtain the removed patient weight sequence, removed patient left foot gravity sequence and removed patient right foot gravity sequence.

[0062] In practice, considering that the patient weight data is collected by the first sensing device and the second sensing device, when the patient steps move, it is easy to detect large and small weight data. The change of the data itself also represents the change characteristics of the patient's posture. Therefore, when the data is denoised, the commonly used denoising algorithm is not applicable, and the common denoising method cannot be directly used to remove outliers. Instead, the data previously marked as outliers should be removed, which is not only more accurate, but also reduces the computing power, while retaining the patient's own posture characteristics, which can then be used to monitor whether the patient has a sudden abnormality during the toilet period according to these data.

[0063] In the third step, according to the current patient weight, the removed patient left foot gravity sequence and the removed patient right foot gravity sequence are subjected to weight regression processing to obtain the processed patient left foot gravity sequence and the processed patient right foot gravity sequence. The weight regression processing is to take the current patient weight as the reference value to denoise the removed patient left foot gravity sequence and the removed patient right foot gravity sequence, and the weight regression processing is used to remove the inertia characteristics caused by the patient's movement to retain the original behavior characteristics of the patient's left and right feet.

[0064] Specifically, first, the ratio between the sum of the removed patient left foot gravity and the removed patient right foot gravity corresponding to the same timestamp and the current patient weight can be determined. If the ratio is greater than 1, it is determined that there is an inertia characteristic. Then, the ratio between the patient's double foot gravity difference and the current patient weight is determined as the correction ratio. After that, the product of the correction ratio and the patient's double foot gravity difference can be determined as the correction value. Finally, the larger one of the removed patient left foot gravity and the removed patient right foot gravity can be subtracted by the correction value to obtain the removed patient left foot gravity or the removed right foot gravity.

[0065] In practice, the other smaller removed patient right foot gravity or removed patient left foot gravity can remain unchanged. Here, considering that the inertia of the larger value of the two values often affects the subsequent judgment. Therefore, if it is determined that there is an inertia characteristic, the larger value of the two values is reduced. In addition, in order to avoid excessive reduction, the ratio between the patient's double foot gravity difference and the current patient weight is determined as the correction ratio, and the larger the correction ratio is, the larger the inertia of the larger value is, and therefore the larger the correction value is. At the same time, in order to avoid being less than the current patient weight after correction, the patient's double foot gravity difference is also taken as the basis of the correction value, so that the correction is made on this basis. Not only can the inertia characteristics be reduced, but also the original characteristics of the double foot gravity data can be retained.

[0066] In the fourth step, the defecation posture of the patient is determined according to the sequence of the removed body weight of the patient, and a defecation posture identifier is obtained. The defecation posture identifier represents a standing posture or a sitting posture. If the removed body weight of the patient in a continuous time period (for example, 5 seconds) is within a certain percentage range (for example, between 20% and 40%) of the current body weight of the patient, it is determined that the defecation posture of the patient is a sitting posture. Otherwise, it is determined that the defecation posture of the patient is a standing posture.

[0067] In the fifth step, overall body weight monitoring is performed on the sequence of the removed body weight of the patient to obtain an overall body weight monitoring result. The overall body weight monitoring is used to detect whether the removed body weight of the patient in a continuous time period (for example, 3 seconds) is outside a preset body weight monitoring range. If the removed body weight of the patient in a continuous time period is outside the preset body weight monitoring range, it is determined that the patient has an emergency situation (for example, falling, convulsions, or syncope) during defecation. The preset body weight monitoring range is adjusted according to the defecation posture identifier and the current body weight of the patient. In practice, the overall body weight monitoring result can be used to determine whether the patient has an emergency situation (for example, falling, convulsions, or syncope) from the perspective of the overall body weight of the patient. In addition, the applied gravity is different for different defecation postures. Therefore, the preset body weight monitoring range is adjusted according to the defecation posture identifier and the current body weight of the patient.

[0068] In the sixth step, feature extraction is performed on the two-dimensional data obtained by merging the processed left foot gravity sequence and the processed right foot gravity sequence according to the defecation posture identifier to obtain patient posture abnormality information. The processed left foot gravity sequence and the processed right foot gravity sequence are continuous data sequences. Even if the left foot gravity and the right foot gravity are interchanged, the data in the processed left foot gravity sequence and the processed right foot gravity sequence is still gradually changing. However, the feedback of the gravity in the case of an emergency situation (for example, falling, convulsions, or syncope) of the patient is usually sudden. Therefore, the two-dimensional data is detected by a preset dynamic sliding window, and the data in the window is extracted by a pre-trained SVM (Support Vector Machine) algorithm to obtain an abnormal posture identifier. The abnormal posture identifier is determined as the patient posture abnormality information. The step size of the dynamic sliding window can be changed according to the detected abnormal posture identifier.

[0069] In practice, when an abnormal posture identifier representing an abnormal situation such as a fall or convulsion is detected, the window step can be reduced to improve the detection accuracy, considering that it belongs to a mutation type. For example, the window step is reduced by 20%. If an abnormal posture identifier representing an abnormal situation such as syncope is detected, the window length can be increased, considering that it belongs to a long-term trend, and then the step can be increased based on the fixed window length. For example, the window step is increased by 20%. Thus, the accuracy of detection is improved.

[0070] Here, the SVM algorithm can extract the following data from the data in the window: mean, standard deviation, kurtosis, skewness, quantile, and dynamic features. Here, the dynamic features can include acceleration and impact index. A radial basis kernel function can be set in the SVM algorithm. In addition, feature extraction can be performed in combination with auxiliary judgment to obtain an abnormal posture identifier. For example, if the data in the window is detected to be small and unchanged for a long time, it can be determined that the patient is syncope, and an abnormal posture identifier representing syncope is generated. Thus, without introducing more models, the consumption of computing resources is reduced.

[0071] Optionally, the monitoring terminal is further configured to:

[0072] First, the heart rate monitoring data is obtained. The heart rate monitoring data is the data corresponding to the same time period as the removed patient weight sequence detected by the personal monitoring wristband. Here, the personal monitoring wristband can be a wristband with sensing function. It can not only be used to unlock access control, but also be used to monitor patient heart rate and other data.

[0073] Second, the heart rate monitoring data is analyzed to generate a heart rate abnormality analysis result. First, the heart rate data corresponding to the patient posture abnormal information in the heart rate monitoring data can be located. Then, the heart rate data can be analyzed by a pre-set abnormality analysis algorithm to generate a heart rate abnormality analysis result. Here, the heart rate data corresponding to the patient posture abnormal information can be the timestamp of the data in the sliding window corresponding to the patient posture abnormal identifier when the patient posture abnormal identifier is detected, as the timestamp for selecting heart rate data. Thus, the heart rate data at the same time as the patient posture abnormality can be located. Thus, the abnormal situation of the patient can be determined by the heart rate data.

[0074] In some optional implementations of some embodiments, the execution subject performs corresponding warning operations according to the monitoring result, including:

[0075] The first step is to issue a toilet timeout warning in response to determining that the toilet visit duration exceeds a preset threshold. If the toilet visit duration exceeds the preset threshold (e.g., 15 minutes), there is a high risk of undetected abnormalities. Furthermore, prolonged toilet visits can negatively impact patients, so a toilet timeout warning is necessary. For example, this can be accomplished by issuing a voice prompt through the door lock control device or notifying a medical terminal.

[0076] In the second step, in response to the abnormal posture information including an indicator indicating abnormal patient behavior, or the abnormal heart rate analysis result including an indicator indicating abnormal patient heart rate, an emergency rescue command is issued to the target terminal, and the door lock control device is controlled to perform emergency unlocking. This effectively monitors the patient while they are in the restroom, allowing for timely emergency unlocking and alarm activation based on abnormal patient conditions, thereby improving patient safety.

[0077] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the patient behavior monitoring and early warning system of some embodiments of the present disclosure, it is possible to accurately record the patient's toilet time, monitor the patient's toilet status in real time, and be equipped with emergency unlocking and alarm mechanisms to ensure patient safety. Specifically, the reasons for the inability to accurately record the patient's toilet time, the inability to monitor the patient's toilet status in real time, and the lack of emergency unlocking and alarm mechanisms are that the existing ward toilet door locks are ordinary door locks, but even if they are set as smart door locks, they require more complex recognition logic, and it is difficult to ensure the accuracy of recognition. Based on this, the patient behavior monitoring and early warning system of some embodiments of the present disclosure, first of all, in order to accurately record the patient's toilet time, introduces a door lock control device and a personal monitoring wristband. Specifically, according to the received access control card swiping information, the toilet door of the ward toilet is opened or closed, and the opening time and closing time of opening or closing the toilet door are sent to the above-mentioned monitoring terminal. The access control card swipe information is generated by the patient's personal monitoring wristband, which senses the door lock control device. The wristband is equipped with a unique identification signal. During the patient's hospitalization period, the identification signal of the wristband is bound to the patient's patient ID. The wristband, when worn by the patient, not only records the patient's vital signs but also records the time the patient swipes their card to use the restroom, which serves as the patient's restroom visit time. This allows for accurate recording of the patient's restroom visit time. Considering the difficulty of monitoring patients' restroom use, the inappropriate installation of cameras in restrooms, and the limitations of radar, infrared, and other measuring instruments, such as computing power, accuracy, and interference, a weight sensor device that can directly measure the patient's weight has been introduced. When enabled, the weight sensor device can collect the patient's weight data and transmit it to the monitoring terminal. The weight sensor device comprises a first sensing device and a second sensing device, each of which measures the force exerted by the patient's feet when using the restroom, generating weight data. This allows for real-time collection of patient weight data. Therefore, the number of times that patients are manually guided to weigh themselves can be greatly reduced, freeing up medical resources. Finally, by introducing a monitoring terminal, the opening and closing time points can be stored in the patient toilet record table corresponding to the above-mentioned patient number, the received gravity data can be recorded in a pre-established patient weight data table, and the patient's toilet time and weight data can be monitored to obtain the monitoring results. According to the monitoring results, the corresponding early warning operation is performed. Among them, the above-mentioned patient toilet record table and the above-mentioned patient weight data table are bound to the patient number of the above-mentioned patient. Therefore, the patient's weight data measured by the weight sensing device can be used to analyze the patient's behavior to determine whether the patient has any abnormal conditions in the toilet. For example, there are sudden situations such as falls, convulsions, and fainting.Thus, real-time monitoring of the patient's physical state when using the toilet is achieved. Further, timely alarm can be given to improve the patient's personal safety.

[0078] Reference will now be made to the following description Figure 4 which shows a structural schematic diagram of an electronic device (such as a computing device) suitable for use to implement some embodiments of the present disclosure. Figure 4 The electronic device shown is merely an example and should not impose any limitation on the function and use range of the embodiments of the present disclosure. As Figure 4 As shown, the computer device includes a processor, a memory and a network interface connected through a system bus, wherein the memory can include a non-volatile storage medium and an internal memory. The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions which, when executed, can cause the processor to perform any method. The processor is used to provide computing and control capabilities to support the operation of the entire computer device. The internal memory provides an environment for the computer program in the non-volatile storage medium, which, when executed by the processor, can cause the processor to perform any method. The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art can understand that Figure 4 The structure shown in the figure is only a block diagram of part of the structure related to the present disclosure scheme, and does not constitute a limitation on the computer device to which the present disclosure scheme is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0079] It should be understood that the processor can be a central processing unit (CPU), and the processor can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0080] In one embodiment, the processor is configured to run a computer program stored in the memory to implement the following steps: the door lock control device is configured to: according to the received access card information, open or close the toilet door of the ward toilet, and send the opening time point and the closing time point of the opening or closing of the toilet door to the monitoring terminal, wherein the access card information is generated by the patient by wearing a personal monitoring wristband to sense the door lock control device, the personal monitoring wristband is provided with a unique identification signal, and the identification signal of the personal monitoring wristband is bound to the patient number of the patient during the patient's hospitalization period; the weight sensing device is configured to: in the open state, collect the weight data of the patient, and send the weight data to the monitoring terminal, wherein the weight sensing device comprises a first sensing device and a second sensing device, and the first sensing device and the second sensing device are used to measure the gravity applied by the patient's feet when entering the toilet as weight data; the monitoring terminal is configured to: store the opening time point and the closing time point in the patient toilet record table corresponding to the patient number, record the received gravity data in the pre-established patient weight data table, and monitor the toilet time and weight data of the patient to obtain a monitoring result, and perform a corresponding warning operation according to the monitoring result, wherein the patient toilet record table and the patient weight data table are bound to the patient number of the patient.

[0081] The embodiments of the present disclosure further provide a computer readable storage medium, and the computer readable storage medium stores a computer program. The computer program includes program instructions. When the program instructions are executed, a method can be implemented. The method can refer to the embodiments of the patient behavior monitoring and warning system.

[0082] The computer readable storage medium can be an internal storage unit of the computer device, such as a hard disk or a memory of the computer device. The computer readable storage medium can also be an external storage device of the computer device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc.

[0083] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0084] The above descriptions are merely some preferred embodiments of the present disclosure and illustrate the underlying technical principles. Those skilled in the art should understand that the scope of the invention encompassed by the embodiments of the present disclosure is not limited to technical solutions formed by specific combinations of the aforementioned technical features. It also encompasses other technical solutions formed by any combination of the aforementioned technical features or their equivalents, without departing from the aforementioned inventive concept. For example, a technical solution formed by replacing the aforementioned features with (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A patient behavior monitoring and early warning system, characterized in that: The patient behavior monitoring and early warning system includes: a door lock control device, a weight sensing device, a personal monitoring wristband and a monitoring terminal, wherein: The door lock control device is configured to: open or close the toilet door of the ward toilet according to the received access card swipe information, and send the opening time and closing time of the toilet door to the monitoring terminal, wherein the access card swipe information is generated by the patient through the personal monitoring wristband worn by the patient to sense the door lock control device, and the personal monitoring wristband is provided with a unique identification signal. During the patient's hospitalization period, the identification signal of the personal monitoring wristband is bound to the patient number of the patient; The weight sensing device is configured to: when in an on state, collect the patient's weight data and send the weight data to the monitoring terminal, wherein the weight sensing device includes a first sensing device and a second sensing device, the first sensing device and the second sensing device being used to measure the gravity exerted by the patient's feet when entering the toilet as the weight data; The monitoring terminal is configured to: store the opening time point and the closing time point in a patient toilet record table corresponding to the patient number, record the received gravity data in a pre-established patient weight data table, and monitor the patient's toilet usage duration and weight data to obtain monitoring results, and execute corresponding early warning operations based on the monitoring results, wherein the patient toilet record table and the patient weight data table are bound to the patient number of the patient; The monitoring results of the patient's toilet usage time and weight data are obtained by behavioral monitoring, including: In response to the access card swipe information for the door sensor, extracting the predicted patient weight corresponding to the patient number in the access card swipe information from a preset database, wherein the predicted patient weight is a pre-measured patient weight; determining the sum of the first weight sensing data and the second weight sensing data in the weight data as the current patient weight; Determine the difference between the first weight sensing data and the second weight sensing data in the weight data as the weight difference between the patient's two feet, wherein the continuous weight difference between the patient's two feet is used to determine whether the patient's standing posture is stable; The number of people using the toilet is determined based on the predicted patient weight, the current patient weight, and the gravity difference between the patient's feet.

2. The patient behavior monitoring and early warning system according to claim 1, characterized in that: The door lock control device includes: a door lock device, an outside door sensing device and an inside door sensing device; and The method of opening or closing the toilet door of the ward toilet according to the received access card swiping information, and sending the opening time point and the closing time point of the toilet door to the monitoring terminal includes: In response to receiving access card swipe information for an external door sensor, determining whether the ward restroom is occupied, wherein when the restroom is occupied, other personal monitoring wristbands cannot open the door through the induction of the external door sensor, the door lock control device extracts the corresponding patient number when the personal monitoring wristband is scanned, and the door lock device is used to automatically lock the door after the patient manually closes the door; In response to the toilet being occupied, issuing a toilet occupancy prompt; In response to the door being unoccupied, issuing a prompt to enter, and determining the door opening time as the opening time; In response to receiving the access control card swiping information for the door interior sensing device, the door lock device is controlled to be unlocked, and the time point of the card swiping information is determined as the closing time point. After the toilet door is unlocked, the occupancy status of the ward toilet is adjusted, and before the access control card swiping information for the door interior sensing device is received and the access control card swiping information for the door exterior sensing device is not received, the time point when the toilet door is closed is determined as the starting time point.

3. The patient behavior monitoring and early warning system according to claim 2, characterized in that: The weight sensing device is further configured to: When the ward toilet is not occupied, in response to detecting access card swiping information for the door sensor, the weight sensing device is activated; In response to not detecting access card swiping information for the door sensor device outside the door and receiving information that the toilet door is automatically locked, activating the weight sensing device; In response to detecting access card swiping information for the door induction device, the weight sensing device is turned off.

4. The patient behavior monitoring and early warning system according to claim 1, characterized in that: In the turned-on state, collecting the patient's weight data and sending the weight data to the monitoring terminal includes: Initializing the weight sensing device; The weight sensing device comprises a first sensing device and a second sensing device, respectively measuring the gravity exerted by the patient when entering the toilet, to obtain first weight sensing data and second weight sensing data; The first weight sensing data, the second weight sensing data and the corresponding timestamp are combined into weight data, and the weight data is sent to the monitoring terminal.

5. The patient behavior monitoring and early warning system according to claim 1, characterized in that: The behavioral monitoring of the patient's toilet time and weight data is performed to obtain monitoring results, including: In response to a difference between the current patient weight and the predicted patient weight being greater than a preset weight interval, determining that the number of people using the toilet is greater than 1; In response to the number of people entering the toilet being greater than 1, and the number of people entering the toilet in the patient's last toilet visit record also being greater than 1, adding 1 to a preset toilet visit excess count, wherein the toilet visit excess count is a statistical value in which the number of people entering the toilet is greater than 1 in the patient's consecutive toilet visit records; In response to the excess count of the number of people entering the toilet being greater than a pre-set value, a weight monitoring pause instruction is generated, and the current patient weight is marked as an abnormal value.

6. The patient behavior monitoring and early warning system according to claim 5, characterized in that: The behavioral monitoring of the patient's toilet usage time and weight data to obtain monitoring results also includes: In response to the number of people using the toilet being equal to 1, the following processing steps are performed according to the added patient weight data table: Extracting the weight data after the door opening time point from the patient weight data table to obtain the patient weight sequence, the patient left foot gravity sequence, and the patient right foot gravity sequence; The values ​​marked with abnormal values ​​in the patient weight sequence, the patient left foot gravity sequence, and the patient right foot gravity sequence are obtained to obtain a post-removal patient weight sequence, a post-removal patient left foot gravity sequence, and a post-removal patient right foot gravity sequence; performing weight regression processing on the patient's left foot gravity sequence and the patient's right foot gravity sequence after removal according to the current patient weight, to obtain a processed patient left foot gravity sequence and a processed patient right foot gravity sequence, wherein the weight regression processing uses the current patient weight as a reference value, and performs noise reduction on the patient's left foot gravity sequence and the patient's right foot gravity sequence after removal. The weight regression processing is used to remove inertial features generated by patient movement to retain the original behavioral features of the patient's left and right feet; Determining the patient's toileting method based on the removed patient weight sequence to obtain a toileting method identifier, wherein the toileting method identifier represents a standing posture or a sitting posture; Performing overall weight monitoring on the post-removal patient weight sequence to generate an overall weight monitoring result, wherein the overall weight monitoring is used to detect whether the post-removal patient weight sequence continuously exceeds a preset weight monitoring range, wherein the post-removal patient weight continuously exceeding the preset weight monitoring range indicates that the patient has a sudden abnormality during toileting, and the preset weight monitoring range is adaptively adjusted according to the toileting method identifier and the current patient weight; According to the toileting method identifier, feature extraction is performed on the two-dimensional data formed by combining the processed patient left foot gravity sequence and the processed patient right foot gravity sequence to generate abnormal posture information of the patient.

7. The patient behavior monitoring and early warning system according to claim 6, characterized in that: The monitoring terminal is further configured to: Acquiring heart rate monitoring data, wherein the heart rate monitoring data is data detected by the personal monitoring wristband and corresponds to the same time period as the weight sequence of the patient after removal; An abnormality analysis is performed on the heart rate monitoring data to generate a heart rate abnormality analysis result.

8. The patient behavior monitoring and early warning system according to claim 7, characterized in that: The corresponding early warning operation is performed according to the monitoring results, including: In response to determining that the toilet time duration is greater than a preset time threshold, issuing a toilet timeout warning operation; In response to the abnormal posture information of the patient including an identifier characterizing abnormal patient behavior, or the abnormal heart rate analysis result including an identifier characterizing abnormal patient heart rate, an emergency rescue instruction is sent to the target terminal, and the door lock control device is controlled to perform emergency unlocking.

9. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the system according to any one of claims 1 to 8.

10. A computer-readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the system according to any one of claims 1 to 8 is implemented.

Images