Attitude induction type alarm calling method and device for bedside equipment

Abstract

The invention discloses a posture induction type alarm calling method and device for bedside equipment, and relates to the field of intelligent health monitoring. The method comprises the following steps: acquiring posture information data of a user; preprocessing the attitude information data, and constructing attitude security features according to the preprocessed attitude information data; threshold judgment is conducted according to the sleeping posture stability feature, the sitting posture stability feature and the posture sudden change detection feature, and when a preset safety threshold condition is not met, safety early warning is conducted; when a preset safety threshold condition is met, calculating to obtain a posture safety score; and performing threshold judgment according to the posture safety score and a preset posture safety score, and when the posture safety score is higher than a preset posture safety score threshold, performing safety early warning. Through multi-dimensional sensor data fusion and comprehensive evaluation of user posture features, the safety state of the user is monitored in real time to identify the falling risk, false alarms are reduced, and the accuracy of safety early warning is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent health monitoring, and in particular to a posture-sensing alarm calling method and device for bedside equipment. Background Art

[0002] As the aging population intensifies, more and more elderly people, patients, and those with special needs require long-term home care or hospitalization. Due to the gradual decline in bodily functions, the elderly and some patients are more susceptible to falls, especially at night when sleeping or getting out of bed. Falls can not only cause serious injuries such as fractures, but can also lead to other complications, and in severe cases, even be life-threatening. Therefore, effective human posture detection and early warning mechanisms have become a critical issue in the field of health monitoring.

[0003] Traditional methods of detecting human posture mostly rely on physical monitoring devices or manual nursing monitoring. Common human posture detection technologies include: Video surveillance monitoring methods: By installing cameras for video monitoring, the patient's activity status is observed in real time. However, this method is limited by privacy issues, and the monitoring effect is poor in low-light environments or when the patient is covered, and it is easy to miss detections; Sound monitoring methods: Using sound sensors to detect the sound generated during a fall event. However, this method is greatly affected by the noise environment and cannot effectively determine whether the patient is in a dangerous state or has an abnormal posture; Touch and pressure sensing monitoring methods: Installing sensors such as pressure sensing pads and mattresses to monitor whether the patient has fallen from a bed or chair. However, this type of equipment lacks flexibility, is difficult to cover all activity scenarios, and is easily affected by environmental changes.

[0004] These traditional methods cannot provide continuous, real-time and efficient monitoring in complex and changing daily environments, especially when the patient is in bed or changing postures, it is often difficult to detect potential fall risks in time. With the continuous development of sensing technology, Internet of Things technology and artificial intelligence technology, sensor-based intelligent fall monitoring solutions are gradually emerging. By collecting user posture information in real time through a variety of sensors (such as accelerometers, pressure sensors, angle sensors, etc.), and combining intelligent algorithms to analyze and process the data, more accurate and efficient fall monitoring can be achieved. Some existing smart bedside devices and wearable devices are already able to monitor user activities, but these devices generally have the following problems: Insufficient accuracy of data analysis: Failure to fully utilize multi-dimensional data leads to the possibility of false positives or omissions.

[0005] Poor adaptability to different postures: Existing monitoring systems can usually only work effectively in certain specific postures, and it is difficult to accurately judge the changes in the user's posture in different environments and different activities.

[0006] System response lag: The alarm mechanism in traditional systems often has a certain lag, and the alarm fails to be issued in time after the user accidentally falls. Summary of the Invention

[0007] In view of the above-mentioned shortcomings of the prior art, the purpose of the present invention is to provide a posture-sensing alarm call method and device for bedside equipment to solve the above-mentioned technical problems.

[0008] To achieve the above-mentioned object, the present invention provides the following technical solution: a posture-sensing alarm calling method for a bedside device, comprising: The user's posture information is obtained by detecting the user's posture information through the sensor on the bedside device; Preprocessing the posture information data, and constructing posture safety features based on the preprocessed posture information data, wherein the posture safety features include: a sleeping posture stability feature, a sitting posture stability feature, and a posture sudden change detection feature; Performing threshold judgment based on the sleeping posture stability feature, the sitting posture stability feature, and the posture mutation detection feature, and issuing a safety warning when the preset safety threshold conditions are not met; When a preset safety threshold condition is met, a posture safety score is calculated based on the sleeping posture stability feature, the sitting posture firmness feature, and the posture mutation detection feature; A threshold judgment is performed based on the posture safety score and a preset posture safety score, and a safety warning is issued when the posture safety score is higher than the preset posture safety score threshold.

[0009] The present invention is further configured such that the posture information data includes acceleration, angle, and pressure.

[0010] The present invention is further configured to construct a posture security feature based on the pre-processed posture information data, including: Calculating a sleeping posture stability characteristic according to the acceleration, the angle, and the pressure; calculating a sitting posture stability characteristic based on the acceleration, the angle, and the pressure; A posture mutation detection feature is calculated based on the acceleration and the angle.

[0011] The present invention is further configured such that the calculation logic of the posture safety score is: ,in, For safety score, Characteristics of sleeping posture stability, For the stability characteristics of sitting posture, To detect the characteristics of posture mutation, To obtain and The maximum value in is the weight coefficient.

[0012] The present invention is further configured to calculate a posture safety score according to the calculation logic of the posture safety score, perform a threshold judgment on the posture safety score and a preset posture safety score, and issue a safety warning when the posture safety score is higher than the preset posture safety score threshold.

[0013] The present invention is further configured such that the calculation logic of the posture mutation detection feature is as follows: mapping the sleeping posture stability feature, the sitting posture firmness feature and the posture mutation detection feature to corresponding discretized bin intervals respectively; Maintain the historical distribution of discretized bin intervals within a sliding window of preset length; Identify gesture combinations whose frequency in historical distribution is less than the rare pattern threshold, mark them as rare gesture combinations, and trigger an alarm call

[0014] The present invention is further configured such that the corresponding discretization binning interval mapping logic includes: For each sleep posture stability feature value collected at each moment, traverse the preset sleep bin boundary sequence in sequence, locate the smallest index i, so that the i-th item in the boundary sequence ≤ the sleep posture stability feature value < the i+1th item, and determine the corresponding i-th bin interval; Traverse the preset sitting and standing bin boundary sequence for the sitting posture stability characteristic value to determine the corresponding j-th bin interval; Traverse the preset mutation bin boundary sequence for the posture mutation detection feature value to confirm the corresponding k-th bin interval; The bin index in the form of (i, j, k) triples is used as the mapping result.

[0015] The present invention is further configured to maintain the historical distribution of the discretized bin intervals within a sliding window of a preset length, including: Set the maximum capacity of the sliding window L, initialize a circular queue to store the discretized bin index triplets, and initialize the three-dimensional combination count matrix Counts of size N×M×K, with all elements set to zero; Receive the triple index (i, j, k) obtained by the latest mapping, and append (i, j, k) to the end of the ring queue; the corresponding Counts[i][j][k] is incremented; If the length of the circular queue exceeds L, the earliest triplet (i0, j0, k0) is popped out from the head of the queue and Counts[i0][j0][k0] is decremented.

[0016] The present invention is further configured to identify a posture combination whose frequency of occurrence in the historical distribution is less than a rare pattern threshold, mark it as a rare posture combination, and trigger an alarm call, including: After updating Counts, check the latest mapping index triple (i, j, k) and get Counts[i][j][k] from the three-dimensional combination count matrix; Compare the obtained combination frequency with the rare pattern threshold. If Counts[i][j][k] is less than the rare pattern threshold, mark the triple as a rare gesture combination. For the triples marked as rare posture combinations, the timestamps and original feature values are recorded, an alarm message is generated, the alarm module is called, and an alarm call is initiated to the predefined receiving end.

[0017] The present invention also provides a posture-sensing alarm call device for bedside equipment, the device comprising: Data acquisition module: used to acquire user posture information data by detecting user posture information through sensors on the bedside device; A feature construction module is used to pre-process the posture information data and construct posture safety features based on the pre-processed posture information data, wherein the posture safety features include: sleeping posture stability features, sitting posture stability features, and posture sudden change detection features; A first warning module is configured to perform threshold judgment based on the sleeping posture stability feature, the sitting posture stability feature, and the posture sudden change detection feature, and issue a safety warning when a preset safety threshold condition is not met; A scoring calculation module is configured to calculate a posture safety score based on the sleeping posture stability feature, the sitting posture firmness feature, and the posture mutation detection feature when a preset safety threshold condition is met; The second early warning module is used to perform a threshold judgment based on the posture safety score and a preset posture safety score, and issue a safety early warning when the posture safety score is higher than the preset posture safety score threshold.

[0018] The present invention provides a posture-sensing alarm call method and device for a bedside device. The method detects user posture information through a sensor on the bedside device to obtain user posture information data; pre-processes the posture information data, and constructs a posture safety feature based on the pre-processed posture information data, wherein the posture safety feature includes: a sleeping posture stability feature, a sitting posture stability feature, and a posture mutation detection feature; a threshold judgment is performed based on the sleeping posture stability feature, the sitting posture stability feature, and the posture mutation detection feature, and a safety warning is issued when a preset safety threshold condition is not met; when the preset safety threshold condition is met, a posture safety score is calculated based on the sleeping posture stability feature, the sitting posture stability feature, and the posture mutation detection feature; a threshold judgment is performed based on the posture safety score and a preset posture safety score, and a safety warning is issued when the posture safety score is higher than the preset posture safety score threshold. The beneficial effects produced include: 1. Real-time monitoring of user posture and providing immediate safety warnings: The bedside device uses sensors to detect the user's posture information in real time, accurately capturing changes in the user's posture when sleeping, sitting, or standing. Through the collection and analysis of multi-dimensional data, it can quickly identify whether the user is in danger of falling or unstable posture, and issue safety warnings in a timely manner when abnormal situations occur, greatly improving user safety. 2. Multi-dimensional sensor data fusion improves monitoring accuracy: The fusion analysis of acceleration, angle, and pressure sensor data can provide a more comprehensive understanding of the user's actual status. Different sensor data complement each other, effectively avoiding the limitations that may exist when a sensor is used alone. For example, the acceleration sensor may be interfered with by the external environment, while the pressure sensor can supplement the accurate perception of changes in the user's body position. This fusion of multi-source data not only improves the robustness of the system, but also more accurately determines whether the user is in an unsafe posture. 3. Comprehensively assess user safety status to reduce false alarms: By analyzing multiple features, including sleeping posture stability, sitting posture stability, and posture change detection, the device avoids false alarms that can result from single-feature analysis. Not only can the device accurately detect user posture stability and changes, but it also uses thresholds and comprehensive scoring based on multiple features to more accurately assess safety scores, thereby reducing false alarms and improving alarm accuracy.

[0019] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without inventive efforts. In the drawings: Figure 1 This is a flow chart showing a posture-sensing alarm calling method for a bedside device according to an exemplary embodiment of the present invention; Figure 2 The present invention is a schematic structural diagram of a posture-sensing alarm and call device for a bedside device according to an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0021] The following describes the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art will readily appreciate the other advantages and benefits of the present invention from the disclosure herein. The present invention may also be implemented or applied through various other specific embodiments, and the various details in this specification may be modified or altered based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are intended only to illustrate the present invention and are not intended to limit the scope of protection of the present invention.

[0022] It should be noted that the illustrations provided in the following embodiments are merely schematic illustrations of the basic concept of the present invention. Therefore, the illustrations only show components related to the present invention and are not drawn according to the number, shape, and size of components in actual implementation. In actual implementation, the type, quantity, and proportion of each component may be changed arbitrarily, and the component layout may also be more complex.

[0023] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the embodiments of the present invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring the embodiments of the present invention.

[0024] Example 1 A posture sensing alarm calling method for bedside equipment, such as Figure 1 Shown, including: The user's posture information is obtained by detecting the user's posture information through the sensor on the bedside device; Preprocessing the posture information data, and constructing posture safety features based on the preprocessed posture information data, wherein the posture safety features include: a sleeping posture stability feature, a sitting posture stability feature, and a posture sudden change detection feature; Performing threshold judgment based on the sleeping posture stability feature, the sitting posture stability feature, and the posture mutation detection feature, and issuing a safety warning when the preset safety threshold conditions are not met; When a preset safety threshold condition is met, a posture safety score is calculated based on the sleeping posture stability feature, the sitting posture firmness feature, and the posture mutation detection feature; A threshold judgment is performed based on the posture safety score and a preset posture safety score, and a safety warning is issued when the posture safety score is higher than the preset posture safety score threshold.

[0025] Specifically, the sensors in the bedside device, combined with the sensors under the mattress, detect and acquire the user's posture information data in real time, including acceleration, angle, and pressure. Acceleration data is acquired through the acceleration sensors installed in the bedside device and under the mattress, and is used to monitor the user's body movement, turning over, sitting posture stability, dynamic changes, and acceleration changes when the posture suddenly changes. Angle data is acquired through the angle sensors and gyroscopes under the bedside device and mattress, and is used to detect changes in the angle between the body and the bed surface, monitoring changes in the angle when the user quickly turns or tilts, and the body tilt angle when sitting. Pressure data is acquired through the pressure sensor installed inside the mattress, and is used to monitor changes in pressure on the mattress or mattress surface, and to detect the stability of pressure distribution when sitting.

[0026] The posture information data is preprocessed to ensure the accuracy, reliability, and real-time nature of subsequent data analysis and judgment. Data preprocessing includes noise filtering and denoising, standardization and normalization, outlier detection and processing, feature extraction, and data dimensionality reduction. Noise filtering removes useless information from the collected data through filtering and smoothing, making the data smoother and more reliable. Standardization and normalization adjust all acquired data to a unified standard to facilitate subsequent analysis and comparison, and improve the effectiveness of data fusion from different sensors. Outlier detection and processing detects and corrects anomalous data generated by sensors to avoid affecting system accuracy. Feature extraction and data dimensionality reduction extract key safety features from large amounts of raw posture information data, simplifying subsequent processing and analysis.

[0027] The present invention is further configured to construct a posture security feature based on the pre-processed posture information data, including: A sleeping posture stability feature is calculated based on the acceleration, the angle, and the pressure; a sitting posture stability feature is calculated based on the acceleration, the angle, and the pressure; and a posture mutation detection feature is calculated based on the acceleration and the angle. Specifically, the calculation logic of the sleeping posture stability feature is as follows: ,in, for The stability of sleeping posture at all times, is the influence coefficient of acceleration change on stability score, is the acceleration change, is the sleep instability function, is the bed disturbance index, acceleration change The calculation logic is: ,in, is the sampling interval, the sleep instability function The calculation logic is: ,in, is the slope parameter, is the offset parameter, is the change in posture angle, bed surface disturbance index The calculation logic is: ,in, is the first adjustment parameter, is the pressure change; sleep instability function By nonlinearly responding to angle changes, it captures the user's reaction to sudden changes in posture and promptly detects changes in the user's body position, helping to more accurately determine whether there is a risk of unstable posture during sleep; bed surface disturbance index By monitoring pressure changes, it helps detect changes in the user's body position and promptly discover potential effects of unstable sleeping postures or turning over on sleeping postures; sleeping posture stability features It can quantify the user's posture stability and combine data from multiple dimensions to assess whether the user is in a safe sleeping posture. The closer it is to 1, the more unstable the user's posture is; Used to control the sensitivity of acceleration to attitude stability, the value range is [0,1]; and Used to determine the sensitivity of posture changes in the sleep instability function, The value range of is [0.1,10], The value of is adjusted according to the required change sensitivity; Used to control the sensitivity of the bed surface disturbance index, with a value range of [0,1]. By integrating data from multiple dimensions, the system can more accurately monitor changes in the user's sleeping posture and issue an alarm in time when an unstable posture is detected. The calculation logic of the sitting posture stability feature is: ,in, For the stability characteristics of sitting posture, is the smoothing parameter, Dynamic center of gravity fluctuation, is the acceleration angle linkage, Dynamic pressure fluctuation, dynamic center of gravity fluctuation The calculation logic is: ,in, is the center of gravity offset, Control the sensitivity of center of gravity displacement changes to stability, is the threshold parameter, acceleration angle linkage The calculation logic is: ,in, is the acceleration change, is the change in posture angle, is the second adjustment parameter, dynamic pressure fluctuation The calculation logic is: ,in, is the third adjustment parameter, The pressure distribution unevenness index; the sitting posture stability feature is used to evaluate the user's posture stability in the sitting state, by combining the center of gravity offset, acceleration change, posture angle change and pressure distribution for evaluation. The closer it is to 1, the more unstable the sitting posture is. For the specific calculation logic, please refer to the above calculation formula. In the above calculation formula, the dynamic center of gravity fluctuation Used to reflect the degree of displacement of the user's center of gravity when sitting or standing, and the acceleration angle linkage Used to describe the interaction between acceleration changes and posture angle changes, dynamic pressure fluctuations Used to reflect the uneven pressure distribution of the mattress; Used to control the smoothness of the score, the value range is [0.1,1]; Used to control the sensitivity of center of gravity displacement changes to stability, with a value range of [0.1,5]; Used to set the sensitivity of center of gravity offset, the value range is [0.1,5]; This feature is used to control the impact of pressure changes on sitting stability, with a value range of [0.05, 2]. By comprehensively considering dynamic center of gravity fluctuations, acceleration angle linkage, and dynamic pressure fluctuations, it more accurately assesses the user's sitting posture stability, promptly identifies potential risks, and prevents falls. The calculation logic of the posture mutation detection feature is as follows: ,in, To detect the characteristics of posture mutation, is the threshold, is the joint change characteristic of acceleration angle, is the relative mutation factor of angle and acceleration, is the adaptive threshold function, acceleration angle joint change characteristics The calculation logic is: ,in, is the acceleration change, is the change in attitude angle, is the acceleration decay time constant, is the angle decay time constant, the angle and acceleration relative mutation factor The calculation logic is: ,in, is a constant, the adaptive threshold function The calculation logic is: ,in, is the empirical coefficient; the posture mutation detection feature is used to determine whether the user has a posture change, and is detected by evaluating the changes in acceleration and angle; when the posture mutation detection feature When it is 1, it means that a sudden change in posture occurs at time t. For the specific calculation logic, please refer to the above calculation formula. In the above calculation formula, the acceleration angle joint change feature Used to express the degree of change of acceleration and posture, angle and acceleration relative mutation factor Used to measure the relative strength of acceleration and angle changes, adaptive threshold function Used to adjust the threshold for judging posture mutation; Used to determine whether the mutation condition is met, the value range is [0,1]; Used to control the attenuation rate of the effect of acceleration changes on mutation detection, with a value range of [0.1, 10]; Used to control the attenuation rate of the effect of posture angle changes on mutation detection, with a value range of [0.1,10]; It is used to determine the sensitivity of the adaptive threshold, with a value range of [0.1, 10]. By combining the changes in acceleration and posture angle, it can accurately detect sudden changes in user posture and identify unsafe postures in a timely manner. The adaptive threshold function It can dynamically adjust the threshold according to the environment and users, improving the system's adaptability in various situations.

[0028] The present invention is further configured such that the calculation logic of the posture safety score is: ,in, For safety score, Characteristics of sleeping posture stability, For the stability characteristics of sitting posture, To detect the characteristics of posture mutation, To obtain and The maximum value in is the weight coefficient; specifically, the posture safety score is used to comprehensively evaluate the user's current posture safety and is scored based on the user's different posture characteristics, including sleeping posture stability, sitting posture stability, and posture mutation detection characteristics. The posture safety score The smaller the value of The user's posture is safer at all times. For the specific calculation logic, please refer to the above calculation formula. In the above calculation formula, the sleeping posture stability feature Used to reflect the user's posture stability during sleep and the stability of sitting and standing postures Used to reflect the stability of the user's posture in a sitting or standing state and posture mutation detection features Used to detect whether the user's posture has changed suddenly. It is used to control the impact of posture mutation on posture safety score, with a value range of [0,10]. By integrating multiple features such as sleeping posture stability, sitting posture firmness, and posture mutation detection, the system can more comprehensively and accurately assess the user's posture safety. By taking the maximum value and weight coefficient, the system can adjust the score according to different user states, making the safety assessment more in line with actual needs.

[0029] The present invention is further configured to calculate a posture safety score according to the calculation logic of the posture safety score, perform a threshold judgment on the posture safety score and a preset posture safety score, and when the posture safety score is higher than the preset posture safety score threshold, issue a safety warning; specifically, compare the calculated posture safety score with the preset posture safety score threshold, and the preset posture safety score threshold is a safety standard value defined in advance according to system settings or user needs; when the posture safety score is lower than or equal to the preset posture safety score threshold, it indicates that the user's posture or state is relatively safe; when the posture safety score is higher than the preset posture safety score threshold, it indicates that there is a high safety risk, and a safety warning is issued.

[0030] The present invention further maps the sleeping posture stability feature, the sitting posture firmness feature, and the posture mutation detection feature to corresponding discretized binning intervals. Specifically, based on historical distribution, the binning boundaries of each feature are pre-set, and each boundary sequence is arranged in order of size. After collecting the three new features, the corresponding intervals are located in the corresponding boundary sequence, and an index triple is generated to represent the position of the current posture in the three-dimensional discrete space. Maintain the historical distribution of discretized bin intervals within a sliding window of preset length. Specifically, append the latest index triple to a circular queue of capacity L, and simultaneously increase the corresponding element count by 1 in the three-dimensional combination count matrix. When the queue length exceeds L, pop the oldest triple and decrease the corresponding element count by -1 in the count matrix, ensuring that the matrix always reflects the distribution of the most recent L mapping results. Identify gesture combinations whose frequency of occurrence in the historical distribution is less than the rare pattern threshold, mark them as rare gesture combinations, and trigger an alarm call. Specifically, extract the current count value of the latest triple in the count matrix and compare it with the pre-set rare pattern threshold. If the count is lower than the threshold, the triple is determined to be a rare gesture combination. Record the timestamp and original feature value of the identified rare gesture combination, generate an alarm message, and initiate an alarm call to the predefined receiving end. To prevent repeated alarms, the triggered combinations can be marked in a queue or count matrix. A real-time anomaly detection framework is constructed based on the discretization mapping and frequency statistics of three types of posture safety features. First, the sleeping posture stability feature, sitting posture firmness feature, and posture mutation detection feature are mapped to corresponding discretized binning intervals to convert continuous feature values into fixed-dimensional index triplets. Second, a sliding buffer of a preset length is used to queue the latest mapping results, and the occurrence frequency of each index triple is simultaneously maintained in a three-dimensional combination count matrix. Finally, by comparing with a rare pattern threshold, index triplets with low occurrence frequencies are identified and marked, regarded as rare posture combinations, and trigger an alarm call.

[0031] The present invention is further configured such that the corresponding discretization binning interval mapping logic includes: For each sleep posture stability feature value collected at each moment, the preset sleep bin boundary sequence is traversed in sequence to locate the smallest index i, such that the i-th item in the boundary sequence ≤ the sleep posture stability feature value < the i+1-th item, and the corresponding i-th bin interval is determined; specifically, each value in the preset sleep bin boundary sequence is read in sequence; the smallest index i is found to satisfy: the i-th item boundary ≤ the current sleep feature value < the i+1-th item boundary; and the i value is used as the bin interval identifier for the sleep feature; For the sitting posture stability feature value, the preset sitting bin boundary sequence is traversed to determine the corresponding j-th bin interval. Specifically, the sitting bin boundary sequence is traversed to locate the minimum j value such that the j-th item boundary ≤ the current sitting feature value < the j+1-th item boundary. This j value is used to identify the bin interval of the sitting feature. Traverse the preset mutation bin boundary sequence for the posture mutation detection feature value to determine the corresponding k-th bin interval; specifically, traverse the mutation bin boundary sequence to locate the minimum k value that satisfies the k-th boundary ≤ current mutation feature value < k+1-th boundary; use this k value as the bin interval identifier for the mutation feature; The bin index in the form of (i, j, k) triples is used as the mapping result.

[0032] The present invention is further configured to maintain the historical distribution of the discretized bin intervals within a sliding window of a preset length, including: Set the maximum capacity of the sliding window, L, and initialize a circular queue to store the discretized bin index triplets. Initialize the three-dimensional combination count matrix Counts of size N×M×K, with all elements set to zero. Specifically, set the maximum capacity of the window, L, to limit the length of the historical record. Create a circular queue of capacity L to store the latest L discretized bin index triplets. Construct a three-dimensional combination count matrix Counts of size N×M×K, and initialize all elements to 0 to count the number of times each index triple appears in the window. Receive the latest mapped triplet index (i, j, k), append (i, j, k) to the end of the circular queue, and increment Counts[i][j][k] accordingly. Specifically, receive the index triplet (i, j, k) mapped at the current moment, append (i, j, k) to the end of the circular queue, and increment Counts[i][j][k] by 1 to reflect the new occurrence of this combination in the window. If the length of the circular queue exceeds L, the earliest queued triple (i0, j0, k0) is popped from the front of the queue, and Counts[i0][j0][k0] is decremented. Specifically, check whether the current length of the circular queue exceeds L. If it exceeds L, the earliest queued triple (i0, j0, k0) is popped from the front of the queue. The corresponding value of Counts[i0][j0][k0] is reduced by 1 to eliminate the statistical contribution of the past moments. Ensure that the Counts matrix always accurately reflects the frequency of occurrence of all triplets in the circular queue. Counts can be read at any time to obtain the distribution overview of the most recent L posture indices for rare pattern detection or dynamic threshold adjustment.

[0033] The present invention is further configured to identify a posture combination whose frequency of occurrence in the historical distribution is less than a rare pattern threshold, mark it as a rare posture combination, and trigger an alarm call, including: After updating Counts, check the latest mapping index triple (i, j, k) and get Counts[i][j][k] from the three-dimensional combination count matrix; Compare the obtained combination frequency with the rare mode threshold. If Counts[i][j][k] is less than the rare mode threshold, mark the triplet as a rare posture combination. Specifically, after updating the sliding window and the three-dimensional combination count matrix, directly read the Counts[i][j][k] corresponding to the latest mapping index triplet (i, j, k) from the matrix. This value reflects the number of times the posture combination appears in the last L mappings. Compare the obtained combination frequency with the preset rare mode threshold. If Counts[i][j][k] is lower than the rare mode threshold, the index triplet is determined to be a rare posture combination, indicating that the current posture mode rarely appears in the user's normal state, which may indicate an abnormality. Furthermore, the rare mode threshold is a pre-set integer threshold used to distinguish between common and rare posture combinations. A value lower than this threshold is considered a rare or abnormal mode. For triplets marked as rare gesture combinations, the timestamp and original feature values are recorded, an alarm message is generated, and the alarm module is invoked to initiate an alarm call to a predefined receiving end. Specifically, for each marked rare gesture combination, the corresponding timestamp and original three-category feature values are recorded, and an alarm message containing this information is generated. This message is passed to the alarm module, which initiates an alarm call based on the predefined receiving end configuration, ensuring that abnormal gestures receive a timely response.

[0034] The above technical solution implements user fall detection. Sensors installed on the bedside device and mattress monitor the user's fall status. When the acceleration sensors of the bedside and mattress detect a sharp change, and the angle sensor detects that the tilt angle is greater than a preset threshold, and the pressure distribution on the mattress changes significantly, it is determined to be a fall. To detect abnormal chest-beating movements of the user, the camera in the bedside device collects frame images and uploads them to the cloud for abnormality detection and processing. This is the existing technology and will not be described in detail here.

[0035] The posture-sensing alarm method scheme for a bedside device also includes fall detection of the bedside device if it tilts or shakes. When the user is in an uncomfortable state, the user will try to touch or push the device, causing the device to tilt or overturn. When the bedside device tilts or changes its posture to an unstable state, these changes are monitored in real time through sensors such as acceleration sensors and angle sensors, and a set algorithm is used to determine whether the device has reached the threshold for triggering an alarm. When the device tilt reaches a preset safety risk level, an alarm is automatically triggered to remind relevant personnel to take intervention measures in time to avoid possible accidents.

[0036] Example 2 See also Figure 2 The exemplary posture-sensing alarm call device of a bedside device includes: Data acquisition module: used to acquire user posture information data by detecting user posture information through sensors on the bedside device; A feature construction module is used to pre-process the posture information data and construct posture safety features based on the pre-processed posture information data, wherein the posture safety features include: sleeping posture stability features, sitting posture stability features, and posture sudden change detection features; A first warning module is configured to perform threshold judgment based on the sleeping posture stability feature, the sitting posture stability feature, and the posture sudden change detection feature, and issue a safety warning when a preset safety threshold condition is not met; A scoring calculation module is configured to calculate a posture safety score based on the sleeping posture stability feature, the sitting posture firmness feature, and the posture mutation detection feature when a preset safety threshold condition is met; The second early warning module is used to perform a threshold judgment based on the posture safety score and a preset posture safety score, and issue a safety early warning when the posture safety score is higher than the preset posture safety score threshold.

[0037] It should be noted that the posture-sensing alarm call device for a bedside device provided in the above embodiment and the posture-sensing alarm call method for a bedside device provided in the above embodiment are of the same concept, wherein the specific manner in which each module and unit performs operations has been described in detail in the method embodiment and will not be repeated here. In actual applications, the posture-sensing alarm call device for a bedside device provided in the above embodiment can allocate the above functions to different functional modules as needed, that is, divide the internal structure of the device into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0038] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0039] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0040] In this application, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0041] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0042] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0043] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0044] In the several embodiments provided in this application, it should be understood that the disclosed system can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0045] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0046] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0047] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0048] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A posture sensing alarm calling method for bedside equipment, characterized in that: include: The user's posture information is obtained by detecting the user's posture information through the sensor on the bedside device; Preprocessing the posture information data, and constructing posture safety features based on the preprocessed posture information data, wherein the posture safety features include: a sleeping posture stability feature, a sitting posture stability feature, and a posture sudden change detection feature; Performing threshold judgment based on the sleeping posture stability feature, the sitting posture stability feature, and the posture mutation detection feature, and issuing a safety warning when the preset safety threshold conditions are not met; When a preset safety threshold condition is met, a posture safety score is calculated based on the sleeping posture stability feature, the sitting posture firmness feature, and the posture mutation detection feature; A threshold judgment is performed based on the posture safety score and a preset posture safety score, and a safety warning is issued when the posture safety score is higher than the preset posture safety score threshold.

2. The posture-sensing alarm calling method for bedside equipment according to claim 1, characterized in that: The posture information data includes acceleration, angle, and pressure.

3. The posture-sensing alarm calling method for bedside equipment according to claim 2, characterized in that: Constructing a posture security feature based on the pre-processed posture information data includes: Calculating a sleeping posture stability characteristic according to the acceleration, the angle, and the pressure; calculating a sitting posture stability characteristic based on the acceleration, the angle, and the pressure; A posture mutation detection feature is calculated based on the acceleration and the angle.

4. The posture-sensing alarm calling method for bedside equipment according to claim 1, characterized in that: The calculation logic of the posture safety score is: ,in, For safety score, Characteristics of sleeping posture stability, For the stability characteristics of sitting posture, To detect the characteristics of posture mutation, To obtain and The maximum value in is the weight coefficient.

5. The posture-sensing alarm calling method for bedside equipment according to claim 4, characterized in that: A posture safety score is calculated according to the calculation logic of the posture safety score, and a threshold judgment is performed between the posture safety score and a preset posture safety score. When the posture safety score is higher than the preset posture safety score threshold, a safety warning is issued.

6. The posture-sensing alarm calling method for bedside equipment according to claim 1, characterized in that: Map the sleeping posture stability feature, sitting posture firmness feature and posture mutation detection feature to the corresponding discretized bin intervals respectively; Maintain the historical distribution of discretized bin intervals within a sliding window of preset length; Identify the posture combinations whose frequency in the historical distribution is less than the rare pattern threshold, mark them as rare posture combinations, and trigger an alarm call.

7. The posture-sensing alarm calling method for bedside equipment according to claim 6, characterized in that: The corresponding discretization bin interval mapping logic includes: For each sleep posture stability feature value collected at each moment, traverse the preset sleep bin boundary sequence in sequence, locate the smallest index i, so that the i-th item in the boundary sequence ≤ the sleep posture stability feature value < the i+1th item, and determine the corresponding i-th bin interval; Traverse the preset sitting and standing bin boundary sequence for the sitting posture stability characteristic value to determine the corresponding j-th bin interval; Traverse the preset mutation bin boundary sequence for the posture mutation detection feature value to confirm the corresponding k-th bin interval; The bin index in the form of (i, j, k) triples is used as the mapping result.

8. The posture-sensing alarm calling method for bedside equipment according to claim 7, characterized in that: Maintain the historical distribution of discretized bin intervals within a sliding window of preset length, including: Set the maximum capacity of the sliding window L, initialize a circular queue to store the discretized bin index triplets, and initialize the three-dimensional combination count matrix Counts of size N×M×K, with all elements set to zero; Receive the triple index (i, j, k) obtained by the latest mapping, and append (i, j, k) to the end of the ring queue; the corresponding Counts[i][j][k] is incremented; If the length of the circular queue exceeds L, the earliest triplet (i0, j0, k0) is popped out from the head of the queue and Counts[i0][j0][k0] is decremented.

9. The posture-sensing alarm calling method for bedside equipment according to claim 8, characterized in that: Identify gesture combinations whose frequency in historical distribution is less than the rare pattern threshold, mark them as rare gesture combinations, and trigger an alarm call, including: After updating Counts, check the latest mapping index triple (i, j, k) and get Counts[i][j][k] from the three-dimensional combination count matrix; Compare the obtained combination frequency with the rare pattern threshold. If Counts[i][j][k] is less than the rare pattern threshold, mark the triple as a rare gesture combination. For the triples marked as rare posture combinations, the timestamps and original feature values are recorded, an alarm message is generated, the alarm module is called, and an alarm call is initiated to the predefined receiving end.

10. A posture-sensing alarm and call device for a bedside device, used to implement the posture-sensing alarm and call method for a bedside device according to any one of claims 1 to 9, characterized in that: include: Data acquisition module: used to acquire user posture information data by detecting user posture information through sensors on the bedside device; A feature construction module is used to pre-process the posture information data and construct posture safety features based on the pre-processed posture information data, wherein the posture safety features include: sleeping posture stability features, sitting posture stability features, and posture sudden change detection features; A first warning module is configured to perform threshold judgment based on the sleeping posture stability feature, the sitting posture stability feature, and the posture sudden change detection feature, and issue a safety warning when a preset safety threshold condition is not met; A scoring calculation module is configured to calculate a posture safety score based on the sleeping posture stability feature, the sitting posture firmness feature, and the posture mutation detection feature when a preset safety threshold condition is met; The second early warning module is used to perform a threshold judgment based on the posture safety score and a preset posture safety score, and issue a safety early warning when the posture safety score is higher than the preset posture safety score threshold.

Images