Anti-falling early warning method and device and bed body

Abstract

The invention discloses an anti-falling early warning method and device and a bed body. The method comprises the following steps: acquiring stress data of a bed body when a target leaves the bed, and vital sign data of the target; and determining to perform falling early warning on the target based on the vital sign data and the stress data. The technical problem of non-ideal tumble prediction accuracy in the target off-bed process is solved.

Description

Technical Field

[0001] The present application relates to the field of anti-fall equipment, and more specifically, to an anti-fall warning method, device and bed. Background Art

[0002] At present, the medical field attaches great importance to patients' fall prevention warnings. When a patient falls, not only will the existing injuries be aggravated, but other additional injuries may even be caused, causing further harm to the patient. Patients generally fall when they leave the bed and walk. Most fall prevention products are in the form of bracelets, which detect the running trajectory of the bracelet during walking to determine whether the patient has fallen. However, the data provided by the movement trajectory of the patient in the process of leaving the bed is insufficient, and it is difficult to predict the fall problem in the leaving bed stage. Generally, it can only be detected after the patient falls out of bed. Therefore, there is a problem in the related technology that the accuracy of fall prediction in the target leaving the bed is not ideal.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present application provide a fall prevention warning method, device and bed body to at least solve the technical problem of unsatisfactory fall prediction accuracy during the target leaving the bed.

[0005] According to one aspect of an embodiment of the present application, a fall prevention warning method is provided, comprising: obtaining force data of a bed when a target is leaving the bed, and vital sign data of the target; and determining a fall warning for the target based on the vital sign data and the force data.

[0006] Optionally, there are multiple action stages in the process of the target leaving the bed in accordance with the sequence of actions, and the bed body has corresponding force data in different action stages. Based on the vital signs data of the target and the force data, it is determined to give a fall warning to the target, including: based on the vital signs data and the force data of the first stage in multiple action stages, it is determined to give a fall warning to the target in the first stage; according to the force data in other stages, it is determined to give a fall warning to the target in other stages, wherein the other stages are stages other than the first stage in the multiple action stages.

[0007] Optionally, the bed is provided with guardrails on both sides of the bed, and based on the vital signs data and the force data of the first stage in multiple action stages, it is determined to give a fall warning to the target in the first stage, including: when it is detected that any guardrail set on the bed is opened, based on the force data of the first stage, determining a first coefficient indicating the movement stability of the target in the first stage; based on the vital signs data, determining a second coefficient indicating the state of the target; based on the first coefficient and the second coefficient, determining to give a fall warning to the target in the first stage.

[0008] Optionally, according to the force data of other stages, determining to provide a fall warning for the target at other stages includes: determining the force characteristics of other stages based on the force data of other stages; and when the force characteristics do not match the predetermined characteristics, determining to provide a fall warning for the target at other stages.

[0009] Optionally, the method further includes: when the force characteristic indicates the presence of a rebound force, determining that the force characteristic does not match a predetermined characteristic, wherein a force direction of the rebound force is opposite to a force direction of the target supported on the bed during the process of getting out of bed.

[0010] Optionally, based on the force data of other stages, force characteristics of other stages are determined, including: correcting the force data of other stages according to the target weight of the target to obtain corrected force data; and determining the force characteristics of other stages based on the corrected force data.

[0011] Optionally, the vital sign data is collected by using a non-wearable vital sign detection device, and the vital sign data includes at least one of the following: heartbeat data and breathing data of the target.

[0012] Optionally, at least one of the following methods is used for fall warning, including: using light to warn the user; using sound to warn the user; or using notification of a remote detection terminal to warn the user.

[0013] According to another aspect of an embodiment of the present application, a bed is provided, comprising a controller to which any one of the anti-fall warning methods is applied.

[0014] Optionally, a pressure sensor, a weighing sensor, and a non-wearable vital sign detection device are provided on the bed, wherein the target has multiple action stages in the process of leaving the bed according to the sequence of actions, and the bed has force data corresponding to different action stages. The weighing sensor is used to obtain the force data of the first stage among the multiple action stages, and the force data of the first stage is used to determine the change of the center of gravity of the target in the first stage. The pressure sensor is used to obtain the force data of other stages, and the other stages are the stages other than the first stage among the multiple action stages. The pressure sensor is set at at least one of the following positions on the bed: the head of the bed, the foot of the bed, the guardrail on the side of the bed, and the edge of the bed board; the vital sign detection device is used to obtain the vital sign data of the target.

[0015] According to another aspect of an embodiment of the present application, a fall prevention warning device is provided, including: a data acquisition module, used to obtain the force data of the bed when the target leaves the bed, and the vital signs data of the target; a fall warning module, used to determine a fall warning for the target based on the vital signs data and the force data.

[0016] In the embodiment of the present application, by obtaining the force data of the bed body and the vital sign data of the target during the process of leaving the bed, and based on the vital sign data and the force data, it is determined to give a fall warning to the target. The purpose of using multimodal data to give a fall warning to the target is achieved, and the technical effect of improving the accuracy of fall prediction during the process of leaving the bed of the target is achieved, thereby solving the technical problem of unsatisfactory accuracy of fall prediction during the process of leaving the bed of the target. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 is a flow chart of an optional fall prevention warning method provided according to an embodiment of the present application;

[0019] Figure 2 It is a schematic diagram of the force condition of a weighing sensor according to an optional anti-fall warning method provided in an embodiment of the present application;

[0020] Figure 3 is a schematic diagram of the force applied to the first pressure sensor of an optional fall prevention warning method provided in an embodiment of the present application;

[0021] Figure 4 is a schematic diagram of the force applied to the second pressure sensor of an optional anti-fall warning method provided in an embodiment of the present application;

[0022] Figure 5 It is a structural block diagram of an optional fall prevention warning method provided according to an embodiment of the present application;

[0023] Figure 6 It is a schematic diagram of an optional anti-fall warning device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] For the convenience of description, some nouns or terms involved in the embodiments of the present application are explained below:

[0027] Data fusion refers to the automatic analysis and integration of data and information from multiple sources, types or granularities under certain criteria, so as to eliminate redundancy, reduce uncertainty, improve data integrity and accuracy, and provide decision makers with more reliable information to complete the required decisions and evaluations.

[0028] The vital sign detection pad is a smart health device that detects and records the target's physiological data, such as heart rate, breathing rate, body movement, sleep cycle, etc., through embedded sensors, and then transmits the data to a connected device or application for analysis. The device has the advantages of non-wearable, non-sensing detection, long-term detection, accurate data, and simple operation.

[0029] A neural network model refers to a deep learning model with a large number of parameters and complex structure. This model can capture complex patterns and features in the data and can often be used to process and learn high-dimensional, large-scale data sets, such as image recognition, natural language processing, and speech recognition.

[0030] According to an embodiment of the present application, a method embodiment of a fall prevention warning is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0031] Figure 1 is a flow chart of an optional fall prevention warning method provided according to an embodiment of the present application, such as Figure 1 As shown, the method comprises the following steps:

[0032] Step S102, obtaining the force data of the bed body and the vital sign data of the target during the process of leaving the bed;

[0033] It can be understood that by installing a vital sign detection device, such as a vital sign detection pad, on the bed to detect and obtain the target's vital sign data, a pressure sensor and a weighing sensor can also be installed on the bed to detect and obtain the target's force data. By obtaining the target's vital sign data and force data in real time, a rich and comprehensive data set is provided for the subsequent fall prevention prediction of the target leaving the bed, thereby improving the accuracy of the prediction results.

[0034] Optionally, the vital sign detection pad is mainly used in the field of health monitoring, and is used to continuously detect the target's vital sign data, such as heart rate, breathing rate, body movement, etc., in a non-invasive and non-wearable manner. According to the different sensors used, the vital sign detection pad can be divided into pressure sensing pads, capacitive sensing pads, optical fiber sensing pads, electromagnetic induction pads and pyroelectric infrared sensing pads. Pressure sensing pads use a pressure sensor array to detect the target's weight distribution, and obtain the target's heart rate and breathing rate based on the target's weight changes. Capacitive sensing pads use capacitive sensors to detect the capacitance changes between the target and the pad, thereby detecting the target's heartbeat and breathing and other vital signs. Optical fiber sensing pads use optical fiber sensor technology to detect target vital signs. When the optical fiber is compressed and deformed, its light transmission characteristics will change, and the target's breathing rate, heart rate, etc. are obtained based on the changes. Electromagnetic induction pads use the electromagnetic induction principle to detect the changes in the electromagnetic field caused by the target through the coil in the pad to obtain information such as heart rate and breathing. The pyroelectric infrared sensor pad uses a pyroelectric infrared sensor to detect the target's heartbeat, breathing, etc. by detecting the infrared rays released by the human body. The design of the vital sign detection pad takes into account comfort, durability and accuracy. It can continuously and accurately detect the target's vital sign data, providing important data support for fall warning, etc.

[0035] In an optional embodiment, there are multiple action stages in the process of the target getting out of bed according to the sequence of actions, and the bed body has corresponding force data in different action stages. Based on the vital sign data of the target and the force data, it is determined to give a fall warning to the target, including: based on the vital sign data and the force data of the first stage in the multiple action stages, it is determined to give a fall warning to the target in the first stage; according to the force data in other stages, it is determined to give a fall warning to the target in other stages, wherein the other stages are stages other than the first stage in the multiple action stages.

[0036] It can be understood that according to the order of the target's actions in the process of leaving the bed, the target's leaving the bed is divided into multiple action stages, and the bed body has corresponding force data in each action stage. In the first stage, early warning is combined with the target's vital signs data. The first stage is the start of the action from the target leaving the lying state. The vital signs data detected by the target during the lying period can be used to understand the target's health status, which is conducive to early warning before the actual fall from bed. The other stages are different from the first stage. Since the target leaves the lying state, the non-wearable vital signs detection equipment used no longer continues to obtain vital signs data, and the target is warned of falls in other stages according to the force data. Through the above processing, the vital signs data and force data are combined as multimodal data, and appropriate early warning measures are taken according to the characteristics of different stages to improve the overall efficiency and safety of the early warning system.

[0037] In an optional embodiment, the bed is provided with guardrails on both sides of the bed, and based on vital sign data and force data of the first stage in multiple action stages, it is determined to perform a fall warning for the target in the first stage, including: when it is detected that any guardrail set on the bed is opened, based on the force data of the first stage, determining a first coefficient representing the movement stability of the target in the first stage; based on the vital sign data, determining a second coefficient representing the state of the target; based on the first coefficient and the second coefficient, determining to perform a fall warning for the target in the first stage.

[0038] It can be understood that in order to prevent the target from falling, switchable guardrails are installed on both sides of the bed. When the target stands up, the vital sign detection pad can be analyzed based on the target's vital sign data, for example, using a neural network model to obtain a second coefficient representing the target's state, namely the weakness coefficient. When the target moves to the bedside, the weighing sensors installed at the four corners of the bed will judge the movement of the target's center of gravity and obtain the target's movement time based on the force data. Based on the movement time and the stability coefficient of the weighing sensor data, the data fusion technology is used to obtain the first coefficient representing the stability of the target's movement in the first stage, namely the mobility coefficient. When the target moves to the bedside and the guardrail status sensor detects that the guardrail is open, the first stage warning value is obtained based on the above first coefficient and second coefficient, and the first stage warning activity is started. The above first stage fall warning is turned on after the guardrail is opened, which effectively reduces the probability of misjudgment and improves the warning efficiency. In addition, the first warning value can be dynamically adjusted according to the weakness coefficient and the mobility coefficient, which improves the flexibility and effectiveness of the warning activity.

[0039] Optionally, the above neural network model is trained based on a large number of vital sign data such as heartbeat amplitude, diastolic retraction speed and heart rate of weak patients. The data set consisting of a large number of vital sign data of weak patients collected is divided into a training set and a validation set, and the neural network model is trained using the training set data. During the training process, the error between the predicted results and the actual results is reduced by minimizing the loss function, and the network parameters are optimized so that the predicted results are gradually close to the actual results, thereby improving the prediction ability of the network. The performance of the neural network model is verified using the validation set data, the prediction performance of the network is evaluated, and the network is optimized and adjusted in combination with the actual data and the validation results, so that the model is continuously updated and calibrated. By dividing the data set into a training set and a validation set, the neural network model can continuously learn and optimize, becoming a reliable and high-precision tool, thereby improving the accuracy of the prediction results of the target frailty coefficient.

[0040] Optionally, the above-mentioned data fusion technology can comprehensively process data from multiple sources and multiple types to improve the accuracy and completeness of the data, thereby improving the accuracy and comprehensiveness of the prediction results. Data fusion technology includes data reception, data processing and decision output, wherein data reception is used to receive real-time data from sensors, data processing is used to preprocess, extract features and fuse real-time data from sensors, and decision output is used to output decisions based on the results of data processing. Using data fusion technology, the target's action force coefficient is obtained based on the stability coefficient of sensor data and target movement time data obtained by weighing sensors installed at different positions on the bed. The action force coefficient can be used to accurately reflect the target's actual movement state, improve the accuracy of target fall warning, and enhance the reliability of the warning system.

[0041] Optionally, the first coefficient is determined based on the time / speed of the target center of gravity moving. Figure 2 is a schematic diagram of the force applied to a weighing sensor according to an optional anti-fall warning method provided in an embodiment of the present application, Figure 2 As can be seen in the figure, there are multiple sensors installed on the bed. There is a vital sign detection pad on the bed to detect the target's vital sign data; four weighing sensors 1, 2, 3, and 4 are installed at the four corners of the bed to detect the movement of the target's center of gravity; a guardrail status sensor is installed on the guardrail to detect the guardrail switch status; pressure sensors are installed at the foot of the bed, guardrails, and the edge of the bed to detect the target's force data. Figure 2As shown, when the target is located at X0, the target center of gravity is located in the middle of the bed, and the force data of the four sensors are similar. When the target moves from X0 to X1, the target's center of gravity will gradually approach sensors 3 and 4, and away from sensors 1 and 2. At this time, the force on sensors 3 and 4 increases, and the force on sensors 1 and 2 decreases. Since X1 is closest to the position of sensor 3, the force on sensor 3 is the largest, and it can be judged that the target may get out of bed from the position of sensor 3. Based on the time consumed by the target to move from X0 to X1 and the stability coefficient of the sensor data, the target's action coefficient B is obtained. Optionally, when the target is lying on the bed, the vital sign detection pad will always detect the target's vital sign data such as breathing and heart rate. When no vital signs are detected for a predetermined period of time, such as no vital signs within 3 seconds, it is considered that the target has been detected to get up. Then, the vital sign data for a period of time before the target gets up is analyzed, and then the second coefficient (i.e., weakness coefficient) is obtained.

[0042] In an optional embodiment, according to the force data of other stages, determining to provide a fall warning for the target at other stages includes: determining the force characteristics of other stages based on the force data of other stages; and determining to provide a fall warning for the target at other stages when the force characteristics do not match the predetermined characteristics.

[0043] It can be understood that the pressure sensor installed on the bed can sense the target's pressure, and based on the pressure on the sensor and the target's weight, the target's getting-up strength is obtained, and based on the target getting-up strength and the first-stage warning value, the second-stage warning value is obtained. The second-stage warning is activated based on the matching of the pressure felt by the pressure sensor and the predetermined characteristics (i.e., the pressure felt by the target's normal bed-leaving pressure sensor). When the pressure felt by the pressure sensor does not match the predetermined characteristics, the second-stage warning activity is activated based on the above-mentioned second-stage warning value; when the pressure felt by the pressure sensor matches the predetermined characteristics, the second-stage warning activity is not activated. By comparing and analyzing the target's bed-leaving pressure change characteristics with the pressure felt by the normal bed-leaving pressure sensor, it is possible to determine whether the target's bed-leaving state is normal, and by quantifying the abnormal state, the accuracy of the warning results is improved, thereby enhancing the prevention and management capabilities of the target's fall risk.

[0044] Optionally, the pressure felt by the pressure sensor when the target leaves the bed normally can reflect the force data of the pressure sensor during the target's normal getting out of bed. First, the target will support the body through the bed until the feet slowly touch the ground, and then use force to stand up until fully standing, and finally leave the bed. For the target leaving the bed normally, the pressure felt by the pressure sensor will slowly increase in the process of the target supporting the body through the bed. When the target supports the body through the bed until the feet touch the ground, the pressure felt by the pressure sensor will fluctuate around the maximum pressure value received during the process of the bed supporting the body. When the target gets up with force, the pressure felt by the pressure sensor will suddenly increase. In the process of the target getting up to fully standing, the pressure felt by the pressure sensor will maintain fluctuations near the maximum pressure received when getting up with force. When the target leaves the bed, it will slowly leave the bed, and the pressure felt by the pressure sensor will gradually decrease until it disappears. By analyzing the force data of the entire process of the normal target leaving the bed, it is possible to judge whether the target's leaving the bed process is normal, thereby improving the efficiency of anti-fall warning.

[0045] In an optional embodiment, the method further includes: when the force characteristic indicates the presence of a rebound force, determining that the force characteristic does not match a predetermined characteristic, wherein a force direction of the rebound force is opposite to a force direction of the target supported on the bed during the process of leaving the bed.

[0046] It can be understood that when the pressure sensor produces a rebound force in the opposite direction to the pressure generated by the supporting bed, it can be determined that the force characteristic does not match the predetermined characteristic, that is, the pressure felt by the pressure sensor when the target normally leaves the bed. At this time, the target's fall coefficient is obtained based on the rebound force and the target's weight, that is, the third-stage warning value, and the third-stage warning activity is initiated.

[0047] Optionally, when the target falls after standing up, the target will support itself by increasing the pressure on the bed, so the pressure on the pressure sensor will suddenly increase. When the target cannot support the bed and falls off the bed, the pressure on the pressure sensor will suddenly disappear. At the same time, in order to restore the deformation, the bed will generate a rebound force in the opposite direction of the pressure, so that the bed will slowly return to its original state.

[0048] Optionally, the target's leaving bed process is divided into three stages according to the sequence of the target's actions in the process of leaving the bed, and the bed has corresponding force data for each action stage. In the first stage, the target's first-stage warning value is obtained based on the target's vital signs data and the force data of the bed in the first stage, and the first-stage warning activity is started based on the first-stage warning value. In the second stage, the target's second-stage warning value is obtained based on the force data of the bed in the second stage, and the second-stage warning activity is started based on the second-stage warning value. In the third stage, the target's third-stage warning value is obtained based on the force data of the bed in the third stage, and the third-stage warning activity is started based on the third-stage warning value. By refining the target's leaving bed process into three stages, not only can the risk of falling be effectively detected and evaluated, but also appropriate warning measures can be taken according to the characteristics of different stages to improve the overall efficiency and safety of the warning system.

[0049] Optionally, the above-mentioned target leaving bed and falling warning is divided into three stages, and the three warning stages are divided according to the order of the target leaving bed. In the first stage, the target stands up and moves to the guardrail beside the bed. When the target opens one of the guardrails, the target has the condition of falling, and at this time, the first stage warning is turned on. In the second stage, the target starts to get out of bed. In the process of getting out of bed, the risk of falling of the target increases, and the pressure sensor installed on the bed body will be under pressure. At this time, based on the force data of the pressure sensor, the second stage warning is turned on. In the third stage, if the target feels that he is about to fall in the process of getting out of bed, the target will increase the pressure on the bed body to prevent himself from falling. When the target cannot grab the bed body due to falling, the bed body will generate a reverse force due to the sudden disappearance of pressure, eliminating the deformation of the bed body caused by pressure. When the pressure sensor feels the reverse force, the third stage warning is turned on. Subdividing the target leaving bed process, different warning values ​​can be set according to the characteristics of different stages, making the warning system more flexible and effective, reducing the probability of misjudgment, and improving the accuracy of the prediction result.

[0050] In an optional embodiment, based on the force data of other stages, force characteristics of other stages are determined, including: correcting the force data of other stages according to the target weight of the target to obtain corrected force data; and determining the force characteristics of other stages based on the corrected force data.

[0051] It can be understood that in order to reduce the influence of the target's own weight on the force characteristics, the force data of other stages are corrected according to the target weight of the target to obtain the corrected force data, and then the force characteristics without the target-specific characteristics are obtained, which helps to provide more accurate fall warning.

[0052] Optionally, in order to reduce the impact of the target's own weight on the force characteristics of the bed, the target weight can be used to correct the force data collected by the pressure sensor when the target gets out of bed, and the target's getting up force is obtained, recorded as C, where C = guardrail force / target weight, and the range of C is 0 to 1. When the calculated C is greater than 1, C is 1.

[0053] Optionally, in order to avoid the influence of different target body weights on the determination of the rebound force, the maximum negative pressure indicated in the rebound force is corrected by using the target weight to obtain the fall coefficient D, that is, the third-stage warning value, where D = |maximum negative pressure| / target weight.

[0054] In an optional embodiment, the vital sign data is collected by using a non-wearable vital sign detection device, and the vital sign data includes at least one of the following: heartbeat data and breathing data of the target.

[0055] It can be understood that by installing a non-wearable vital sign detection device on the bed, the target's vital sign data can be obtained, and the target's vital sign data can be obtained using a vital sign detection pad. The above vital sign data may include the target's heart rate, respiratory rate and other data. By installing a non-wearable vital sign detection device and obtaining the target's vital sign data, not only can the target's health status be evaluated, but also data support can be provided for the target's fall prevention warning during the process of leaving the bed, providing more comprehensive health monitoring for the target.

[0056] Optionally, the vital sign detection device can be divided into wearable vital sign detection device and non-wearable vital sign detection device according to its usage. Wearable vital sign detection devices require the target to wear them directly on a certain part of the body, which may cause discomfort and restraint to the target and have application limitations. Non-wearable vital sign detection devices do not need to be worn directly by the target, and usually detect the target's vital sign data through sensors or devices in the environment. For example, vital sign detection pads, smart bedside tables, cameras and infrared technology, and acoustic detection equipment. It can be used to detect the target's heart rate, respiratory rate, body temperature, body movement and other vital sign data. Non-wearable vital sign detection devices do not require the target to wear any equipment, which avoids the problem of detection interruption caused by discomfort in wearing the equipment or the equipment falling off, and can reduce discomfort. It is used for long-term detection and night monitoring.

[0057] Step S104: Based on the vital sign data and the force data, determine whether to issue a fall warning to the target.

[0058] It can be understood that the target's vital sign data is obtained based on the vital sign detection equipment, and the force data of the target at different action stages is obtained based on the pressure sensor and the weighing sensor, and the target is given a staged fall warning based on the above vital sign data and force data. Using the target's vital sign data and force data as evaluation indicators for fall warning not only takes into account the target's physiological state, but also the target's action state, enriching the evaluation indicators of fall warning and improving the accuracy and comprehensiveness of the warning results.

[0059] In an optional embodiment, at least one of the following methods is used for fall warning, including: using light to warn the user; using sound to warn the user; or using notification of a remote detection terminal to warn the user.

[0060] It can be understood that anti-fall warning activities can be implemented by installing multiple output devices such as bedside lights, buzzers, wireless transmission devices and data receivers on the bed. The bedside light can provide light warnings. According to the detected fall risk level, the system will automatically adjust the flashing frequency or color of the light. The buzzer can provide sound warnings. A buzzer or other sound device is installed on or around the bed. According to the calculated warning value, the buzzer will emit alarm sounds of different volumes. The wireless transmission device and the data receiver can notify the remote detection end of the warning information. The wireless transmission device sends the warning information, including the real-time status of the target, the risk of falling, and the possible fall location. The data receiver installed at the remote detection end is used to receive the warning information issued by the wireless transmission device so that it can respond quickly and reduce the occurrence of fall events. The integrated use of multiple warning devices can provide a multi-level warning mechanism, improve the accuracy and timeliness of the warning, and reduce the risk of falling of the target.

[0061] Through the above step S102, the force data of the bed body and the vital sign data of the target are obtained during the process of leaving the bed; and in step S104, based on the vital sign data and the force data, it is determined to give a fall warning to the target. The purpose of using multimodal data to give a fall warning to the target can be achieved, and the technical effect of improving the accuracy of fall prediction during the process of leaving the bed of the target is achieved, thereby solving the technical problem of unsatisfactory accuracy of fall prediction during the process of leaving the bed of the target.

[0062] Based on the above embodiments and optional embodiments, the present application proposes an optional implementation method, by installing multiple sensors and multiple output devices on and around the bed, wherein the sensors include a vital sign detection pad, a weighing sensor, a side guardrail status sensor and a pressure sensor, and the multiple output devices include a bedside lamp, a buzzer, a wireless transmission device, and a nurse station receiver. The target's vital signs and force data are detected and analyzed to obtain the warning values ​​of the target at different action stages, and the target is warned of falling in stages based on the warning, and the output device is used to execute the warning and activities.

[0063] According to the sequence of the target's movements in the process of leaving the bed, the target's leaving the bed process is divided into three stages. For each stage of movement, the bed has corresponding force data. In the first stage, based on the target's vital signs data and the force data of the bed in the first stage, the target's first-stage warning value is obtained, and based on the first-stage warning value, the first-stage warning activity is started. In the second stage, based on the force data of the bed in the second stage, the target's second-stage warning value is obtained, and based on the second-stage warning value, the second-stage warning activity is started. In the third stage, based on the force data of the bed in the third stage, the target's third-stage warning value is obtained, and based on the third-stage warning value, the third-stage warning activity is started. By refining the target's movements in the process of leaving the bed into three stages, not only can the risk of falling be effectively detected and evaluated, but also appropriate warning measures can be taken according to the characteristics of different stages to improve the overall efficiency and safety of the warning system.

[0064] In the first warning stage, the target stands up and moves toward the guardrail beside the bed. When the target lies on the bed, the vital sign detection pad will continue to detect the target's breathing and heart rate. When the target stands up, the vital sign detection pad cannot detect the target's vital signs. If the vital sign detection pad cannot detect the target's vital sign data within 3 seconds, the trained neural network model will be used to calculate the target's breathing and heart rate data before the target stands up to obtain the second coefficient of the target's state, that is, the target's weakness coefficient A, where the weakness coefficient ranges from 0 to 1. The weaker the target, the higher the value of A.

[0065] When the target starts to move, the weighing sensor on the bed calculates the position of the target's center of gravity based on the force data, determines whether the target is moving toward the edge of the bed, and at the same time, obtains the target movement time. Based on the movement time and the stability coefficient of the weighing sensor data (reflecting the stability of the target's movement process), data fusion technology is used to obtain the first coefficient representing the target's movement stability in the first stage, namely the action force coefficient B, where the range of the action force coefficient B is 0 to 1, and the lower the target's action force, the higher the value.

[0066] When the target moves to the edge of the bed and the guardrail status sensor detects that the guardrail is opened, the first-stage warning value W1 is obtained based on the first coefficient A and the second coefficient B. The formula of the first-stage warning value W1 is:

[0067] W1=A+B

[0068] The first-stage warning activity is activated according to the first-stage warning value W1, including: when W1≤0.6, the light under the bed will flash at a frequency of 1HZ (Hertz) for warning; when W1>0.6, the light under the bed will flash at a frequency of 1HZ for warning; when W1>1.0, the light under the bed will flash at a frequency of 2HZ for warning; when W1>1.5, the light under the bed will flash at a frequency of 2HZ for warning, and the buzzer will be turned on for warning.

[0069] from Figure 2 As can be seen in the figure, there are multiple sensors installed on the bed. There is a vital sign detection pad on the bed to detect the target's vital sign data; four weighing sensors 1, 2, 3, and 4 are installed at the four corners of the bed to detect the movement of the target's center of gravity; a guardrail status sensor is installed on the guardrail to detect the guardrail switch status; pressure sensors are installed at the foot of the bed, guardrails, and the edge of the bed to detect the target's force data. Figure 2 As shown in the figure, when the target is at X0, the target's center of gravity is in the middle of the bed, and the force data of the four sensors are similar. When the target moves from X0 to X1, the target's center of gravity will gradually approach sensors 3 and 4, and move away from sensors 1 and 2. At this time, the force on sensors 3 and 4 increases, and the force on sensors 1 and 2 decreases. Since X1 is closest to sensor 3, the force on sensor 3 is the greatest, and it can be judged that the target may get out of bed from the position of sensor 3. Based on the time consumed by the target to move from X0 to X1 and the stability coefficient of the sensor data, the target's action coefficient B is obtained.

[0070] In the second warning stage, the target starts to get out of bed. During the process of getting out of bed, the target's risk of falling increases, and the pressure sensor installed on the bed body will be under pressure. At this time, based on the force data of the pressure sensor, the second stage warning is activated. During the process of the target getting out of bed, the pressure sensor installed on the bed body can feel the pressure of the target. Based on the pressure on the sensor and the target weight, the target's standing force C is obtained, where C = guardrail force / target weight, and the range of C is 0-1. When the calculated C is greater than 1, C is 1. Based on the target standing force C and the first stage warning value W1, the second stage warning value W2 is obtained. The second stage warning is activated according to the matching of the pressure felt by the pressure sensor and the predetermined feature (i.e., the pressure felt by the target's normal bed leaving pressure sensor). When the pressure felt by the pressure sensor does not match the predetermined feature, the second stage warning activity is activated based on the above second stage warning value; when the pressure felt by the pressure sensor matches the predetermined feature, the second stage warning activity is not activated. By comparing and analyzing the pressure change characteristics of the target leaving bed with the pressure felt by the normal leaving bed pressure sensor, it is possible to determine whether the target's leaving bed status is normal, and by quantifying the abnormal status, the accuracy of the early warning results can be improved, thereby enhancing the prevention and management capabilities of the target's fall risk.

[0071] The formula of the second stage warning value W2 is:

[0072] W2=A+B+C

[0073] The second-stage warning activity is activated according to the second-stage warning value W2, including: when W2≤0.6, the bedside light will flash at a frequency of 1HZ for warning; when W2>0.6, the bedside light will flash at a frequency of 1HZ for warning; when W2>1.0, the bedside light will flash at a frequency of 2HZ for warning; when W2>1.5, the bedside light will flash at a frequency of 2HZ for warning, and the buzzer will be turned on for warning; when W2>2.0, the bedside light will flash at a frequency of 2HZ for warning, and the buzzer will be turned on for warning, and the fall warning information will be sent to the nurse station receiver.

[0074] Figure 3 is a schematic diagram of the force applied to the first pressure sensor of an optional fall prevention warning method provided in an embodiment of the present application, Figure 3 That is, a predetermined characteristic of the pressure felt by a predetermined pressure sensor (i.e., the pressure felt by the target normal bed-out pressure sensor), Figure 3 The force characteristics of the pressure sensor installed on the guardrail during the target's normal bed exit process are described. Figure 3As shown, first, the target will help the guardrail and maintain it until the feet touch the ground. After the feet touch the ground, the target will help the guardrail to stand up and maintain it until it is fully standing. After standing up, the target will slowly leave the bed and let go of the guardrail. In the above process of leaving the bed, the pressure sensor installed on the guardrail will continue to receive the pressure applied by the target until the target releases the guardrail. First, in the process of the target helping the guardrail, the target will gradually hold the guardrail to support the body. At this time, the pressure felt by the pressure sensor will slowly increase. When the target's feet begin to touch the ground, the target's pressure on the guardrail will no longer continue to increase, and will fluctuate around the maximum pressure value received during the above process of supporting the body until the target's feet touch the ground. After the target's feet touch the ground, the target will help the guardrail to stand up. At this time, in order to support the weight of the body, the pressure felt by the pressure sensor will suddenly increase. In the process of the target standing up to fully standing, the pressure felt by the pressure sensor will maintain fluctuations near the maximum pressure received when trying to stand up. In the process of the target slowly leaving the bed and letting go of the guardrail, the pressure felt by the pressure sensor will gradually decrease until it disappears.

[0075] In the third stage, when the target feels that he is about to fall while getting out of bed, he will increase the pressure on the bed to prevent himself from falling. When the target cannot hold the bed due to falling, the bed will generate a reverse force due to the sudden disappearance of pressure, eliminating the deformation of the bed caused by the pressure. When the pressure sensor senses the reverse force, the third stage warning is activated. When the pressure sensor appears to have a rebound force in the opposite direction of the pressure generated by the supporting bed, it can be determined that the force characteristic does not match the predetermined characteristic, that is, the pressure felt by the pressure sensor when the target normally leaves the bed. At this time, the target's fall coefficient D is obtained based on the rebound force and the target's physical signs, that is, the third stage warning value, where D = |maximum negative pressure| / target weight.

[0076] Based on the third-stage warning value, the third-stage warning activity is activated, including when D>0.1, the bedside light will flash at a frequency of 2HZ to give a prompt, and the buzzer will alarm at the maximum volume, and send an SOS warning message to the nurse station receiver.

[0077] Figure 4 FIG. 1 is a schematic diagram of the force applied to the second pressure sensor of an optional anti-fall warning method provided in an embodiment of the present application. Figure 4 In the figure, the solid line represents the force characteristics of the pressure sensor installed on the guardrail when the target leaves the bed normally, and the dotted line represents the force characteristics of the pressure sensor installed on the guardrail when the target falls during leaving the bed. Figure 4It can be seen that compared with the normal process of getting out of bed, the force data of the pressure sensor installed on the guardrail in the case of a fall during the process of getting out of bed will have two obvious abnormal values. First, the force curve of the fall will be subjected to a particularly large force when the target tries to get up, and the amplitude is significantly higher than the normal bed leaving. This is because when the target is about to fall, it will suddenly increase the grip on the guardrail to avoid falling, resulting in a sudden increase in the pressure on the pressure sensor. Secondly, the force curve of the fall has a negative phenomenon. This is because when the target's arm can no longer support the body, the target will leave the guardrail, the pressure on the pressure sensor will suddenly disappear, and the guardrail will rebound due to deformation, generating a rebound force in the opposite direction of the pressure, causing the guardrail to slowly return to its original state.

[0078] Figure 5 is a structural block diagram of an optional anti-fall warning method provided according to an embodiment of the present application, from Figure 5 It can be seen that by installing multiple sensors and multiple output devices on and around the bed, the target is given an anti-fall warning. Among them, the sensors include a vital sign detection pad, a weighing sensor, a side guardrail status sensor and a pressure sensor, and the multiple output devices include a bedside lamp, a buzzer, a wireless transmission device, and a nurse station receiver. The target's vital signs and force data are detected and analyzed to obtain the warning values ​​of the target's different action stages. Based on the warning, the target is given a staged fall warning and the output device is used to perform warning activities. In the first stage, the target lies on the bed, and the vital sign detection pad will detect the target's vital sign data and obtain the weakness coefficient A. After the target starts to move, the weighing sensor will determine the target's movement trajectory based on the change of the target's center of gravity, and obtain the target's action force coefficient B. Based on the weakness coefficient A and the action force coefficient B, the first stage warning value W1 is obtained. The guardrail status sensor is used to detect the guardrail status to determine whether the guardrail is open. If the guardrail is not open, the sensor continues to detect the target. If the guardrail is open, the first stage warning activity is started based on the first stage warning value W1. If the guardrail is open, the pressure sensor is used to detect the force data of the guardrail, and the target standing force C is obtained based on the pressure on the guardrail. The second-stage warning value W2 is obtained based on the weakness coefficient A, the mobility coefficient B and the target standing force C, and the second-stage warning activity is started. If the pressure sensor detects a negative rebound force on the guardrail, the third-stage warning is started. Based on the rebound force, the target fall coefficient D, that is, the third-stage warning value, is obtained, and the third-stage warning activity is started.

[0079] The above optional implementation achieves at least the following effects: combining the target's vital sign data and mobility data to perform anti-fall warning using multimodal data, detecting the entire process of the target leaving the bed, and improving the efficiency of warning and the accuracy of warning results. Using multiple output devices to perform warning actions, the target is given an anti-fall warning through three-stage sound and light alarms, which improves the timeliness of the warning and reduces the target's risk of falling.

[0080] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0081] In an embodiment of the present application, a bed is also provided, and a controller using the anti-fall warning method provided in any of the above embodiments is applied.

[0082] In this embodiment, a fall prevention warning device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the terms "module" and "device" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0083] According to an embodiment of the present application, a device embodiment for implementing a fall prevention warning method is also provided. Figure 6 is a schematic diagram of a fall prevention warning device according to an embodiment of the present application, such as Figure 6 As shown, the above-mentioned anti-fall warning device includes a data acquisition module 602 and a fall warning module 604. The device is described below.

[0084] The data acquisition module 602 is used to acquire the force data of the bed body when the target leaves the bed, and the vital sign data of the target;

[0085] The fall warning module 604 is connected to the data acquisition module 602 and is used to determine a fall warning for the target based on the vital sign data and the force data.

[0086] In a fall prevention warning device provided in an embodiment of the present application, a data acquisition module 602 is provided to obtain the force data of the bed body of the target during the process of leaving the bed, as well as the vital sign data of the target; a fall warning module 604 is connected to the data acquisition module 602, and is used to determine the fall warning for the target based on the vital sign data and the force data. The purpose of using multimodal data to carry out target fall warning is achieved, and the technical effect of improving the accuracy of fall prediction during the process of the target leaving the bed is achieved, thereby solving the technical problem of unsatisfactory fall prediction accuracy during the process of the target leaving the bed.

[0087] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0088] It should be noted that the data acquisition module 602 and the fall warning module 604 correspond to steps S102 to S104 in the embodiment, and the examples and application scenarios implemented by the modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments. It should be noted that the modules as part of the device can be run in a computer terminal.

[0089] It should be noted that the optional or preferred implementation of this embodiment can refer to the relevant description in the embodiment, which will not be repeated here.

[0090] The above-mentioned anti-fall warning device may also include a processor and a memory. The data acquisition module 602, the fall warning module 604, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions.

[0091] The processor includes a kernel, which retrieves the corresponding program unit from the memory. There can be one or more kernels. The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one storage chip.

[0092] An embodiment of the present application provides a non-volatile storage medium on which a program is stored. When the program is executed by a processor, an anti-fall warning method is implemented.

[0093] The embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are implemented: obtaining the force data of the bed body of the target during the process of leaving the bed, and the vital sign data of the target; based on the vital sign data and the force data, determining to provide a fall warning for the target. The device in this article can be a server, a PC, etc.

[0094] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes the following method steps: obtaining the force data of the bed when the target leaves the bed, and the vital signs data of the target; based on the vital signs data and the force data, determining a fall warning for the target.

[0095] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0096] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0097] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0098] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0099] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0100] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0101] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0102] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0103] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0104] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A fall prevention warning method, characterized in that: include: Acquiring force data of the bed body when the target leaves the bed, as well as vital sign data of the target; Based on the vital sign data and the force data, it is determined to provide a fall warning for the target.

2. The method according to claim 1, characterized in that The target has multiple action stages in the process of leaving the bed according to the action sequence, and the bed body has force data corresponding to different action stages. The step of determining a fall warning for the target based on the vital sign data of the target and the force data includes: Based on the vital sign data and the force data of the first stage in the multiple action stages, determining to provide a fall warning for the target in the first stage; According to the force data of other stages, it is determined to provide a fall warning to the target in the other stages, wherein the other stages are stages other than the first stage in the multiple action stages.

3. The method according to claim 2, characterized in that The bed body is provided with guardrails on both sides of the bed, and the step of determining, based on the vital sign data and the force data of the first stage of the multiple action stages, to provide a fall warning to the target in the first stage includes: When it is detected that any guardrail provided on the bed is opened, based on the force data of the first stage, determining a first coefficient indicating the stability of the movement of the target in the first stage; Based on the vital sign data, determining a second coefficient representing a state of the target; Based on the first coefficient and the second coefficient, it is determined to perform a fall warning for the target in the first stage.

4. The method according to claim 2, characterized in that: Determining, according to the force data of other stages, to provide a fall warning for the target at the other stages includes: Determining the force characteristics of the other stages based on the force data of the other stages; When the force characteristic does not match the predetermined characteristic, it is determined to provide a fall warning to the target in the other stage.

5. The method according to claim 4, characterized in that The method further comprises: In the case where the force characteristic indicates the presence of a rebound force, it is determined that the force characteristic does not match the predetermined characteristic, wherein a force direction of the rebound force is opposite to a force direction in which the target is supported on the bed during getting out of bed.

6. The method according to claim 5, characterized in that The determining the force characteristics of the other stages based on the force data of the other stages includes: According to the target weight of the target, the force data of the other stages are corrected to obtain corrected force data; Based on the corrected force data, force characteristics of the other stages are determined.

7. The method according to any one of claims 1 to 6, characterized in that: The vital sign data is collected by using a non-wearable vital sign detection device, and the vital sign data includes at least one of the following: heartbeat data and breathing data of the target.

8. The method according to any one of claims 1 to 6, characterized in that Use at least one of the following methods to provide fall warning, including: Use lighting to warn of falls; Use sound to warn of falls; Fall warning is carried out by notifying the remote detection terminal.

9. A bed, characterized in that: A controller comprising the anti-fall warning method according to any one of claims 1 to 8.

10. The bed according to claim 9, characterized in that: The bed is provided with a pressure sensor, a weighing sensor, and a non-wearable vital sign detection device, wherein the target has multiple action stages in a sequence of actions during the process of leaving the bed, and the bed has force data corresponding to different action stages. The weighing sensor is used to obtain the force data of the first stage of the multiple action stages, and the force data of the first stage is used to determine the change of the center of gravity of the target in the first stage. The pressure sensor is used to obtain the force data of other stages, and the other stages are the stages of the multiple action stages except the first stage. The pressure sensor is set at at least one of the following positions on the bed: the head of the bed, the foot of the bed, the guardrail on the side of the bed, and the edge of the bed board; the vital sign detection device is used to obtain the vital sign data of the target.

11. A fall prevention warning device, characterized in that: include: A data acquisition module, used to acquire the force data of the bed body when the target leaves the bed, and the vital sign data of the target; A fall warning module is used to determine a fall warning for the target based on the vital sign data and the force data.

Images