Fall detection and alerting method, apparatus, device, storage medium and product

Abstract

The application discloses a fall detection and alarm method, device, equipment, storage medium and product, relates to the technical field of wireless sensing and health monitoring, and the method comprises the steps of acquiring a signal state parameter generated by user activity in a preset detection range; processing the signal state parameter to obtain an amplitude feature and a phase feature; determining whether a human body fall event occurs in the preset detection range according to a rate of change of the amplitude value of the amplitude feature and a phase change acceleration of the phase feature; when it is determined that the human body fall event occurs, matching the signal state parameter with preset radio frequency fingerprint data to determine an environmental risk category to which a position where the human body fall event occurs belongs; determining a corresponding observation time length according to the environmental risk category, and continuously acquiring the signal state parameter in the observation time length to determine whether the user recovers a motion state; determining a corresponding alarm mode based on whether the user recovers the motion state, and executing the alarm according to the alarm mode.

Description

Technical Field

[0001] This application relates to the field of wireless sensing and health monitoring technology, and in particular to a fall detection and alarm method, device, equipment, storage medium and product. Background Technology

[0002] With the increasing aging of the population, falls have become a major safety hazard for elderly people living at home. Body fat scales, as common household health devices, often have built-in WiFi modules that remain powered on in standby mode but are only used for data transmission, their potential underutilized. Existing fall detection technologies mainly fall into three categories: first, computer vision-based solutions, which, while highly accurate, pose privacy risks and are difficult to deploy in private areas such as bathrooms and toilets; second, wearable device-based solutions, which require users to actively wear them and are easily forgotten, resulting in a poor user experience; and third, solutions based on independent WiFi sensing nodes, which achieve contactless detection but require additional dedicated equipment, increasing hardware costs and installation complexity. Furthermore, all of these solutions employ a uniform alarm strategy for all fall events, failing to consider the environmental risks associated with different fall locations, leading to insufficient alarm effectiveness.

[0003] Therefore, how to reuse the body fat scale's own WiFi module to achieve privacy-friendly adaptive fall detection and graded alarms is an urgent problem to be solved. Summary of the Invention

[0004] The main objective of this application is to provide a fall detection and alarm method, device, equipment, storage medium, and product, aiming to solve the technical problem of how to reuse the body fat scale's own WiFi module to achieve privacy-friendly environmental adaptive fall detection and graded alarm.

[0005] To achieve the above objectives, this application proposes a fall detection and alarm method, which is applied to a body fat scale, and the method includes: In standby mode, acquire signal status parameters generated by the user's activities within a preset detection range; The signal state parameters are processed to obtain amplitude characteristics reflecting the amplitude of human movement and phase characteristics reflecting the speed of human movement. Based on the amplitude change rate of the amplitude feature and the phase change acceleration of the phase feature, it is determined whether a human fall event has occurred within the preset detection range; When a human fall event is determined to have occurred, the signal state parameters are matched with preset radio frequency fingerprint data to determine the environmental risk category to which the location of the human fall event belongs. The corresponding observation period is determined based on the environmental risk category, and the signal status parameters are continuously acquired within the observation period to determine whether the user has resumed movement. The corresponding alarm method is determined based on whether the user resumes movement, and the alarm is executed according to the alarm method.

[0006] In one embodiment, the step of processing the signal state parameters to obtain amplitude characteristics reflecting the amplitude of human movement and phase characteristics reflecting the speed of human movement includes: Extract multiple amplitude sequences and multiple phase sequences from the signal state parameters; The multi-channel amplitude sequences are statistically fused to obtain a representative amplitude trajectory, and the multi-channel phase sequences are statistically fused to obtain a representative phase trajectory. The phase change acceleration is obtained by performing a second-order difference calculation on the representative phase trajectory, and the phase change acceleration is used as the phase feature. The amplitude change rate is obtained by performing differential calculation on the representative amplitude trajectory, and the amplitude change rate is used as the amplitude feature.

[0007] In one embodiment, the step of determining whether a human fall event has occurred within the preset detection range based on the amplitude change rate of the amplitude feature and the phase change acceleration of the phase feature includes: The amplitude change rate and the phase change acceleration are detected in a single frame. When the phase change acceleration exceeds a preset acceleration threshold and the amplitude change rate exceeds a preset change rate threshold in any detection period, an effective detection period is obtained. The number of valid detection cycles is accumulated, and when the number of cycles reaches a preset number, the human fall event is confirmed to have occurred.

[0008] In one embodiment, the step of matching the signal state parameters with preset radio frequency fingerprint data to determine the environmental risk category to which the location of the human fall event belongs includes: Obtain the current signal characteristics from the signal state parameters; Calculate the similarity between the current signal feature and the signal features corresponding to each location identifier in the preset radio frequency fingerprint database, wherein the preset radio frequency fingerprint database contains the correspondence between the location identifier and the environmental risk category; The environmental risk category corresponding to the location with the highest similarity is determined as the environmental risk category to which the human fall event belongs.

[0009] In one embodiment, the step of determining the corresponding observation duration based on the environmental risk category and continuously acquiring the signal state parameters within the observation duration to determine whether the user has resumed movement includes: The corresponding observation duration is determined based on the environmental risk category; The signal state parameters are continuously acquired during the observation period, and the motion intensity index is obtained from the signal state parameters. When the exercise intensity index reaches the standing determination threshold within the observation period, it is determined that the user has resumed exercise.

[0010] In one embodiment, the step of determining the corresponding alarm method based on whether the user resumes movement and executing the alarm according to the alarm method includes: When it is determined that the user has resumed movement, an alarm is triggered according to the first alarm method, which includes: pushing an event notification to the bound mobile terminal and sending a prompt message to the preset family member terminal; When it is determined that the user has not resumed movement, an alarm is triggered according to the second alarm method. The second alarm method includes: activating an audio-visual prompt, pushing an event notification to the bound mobile terminal, sending a prompt message to the preset family member terminal, and sending an emergency help message to the preset emergency contact terminal. The urgency level of the second alarm method is higher than that of the first alarm method.

[0011] Furthermore, to achieve the above objectives, this application also proposes a fall detection and alarm device, the device comprising: The signal acquisition module is used to acquire signal status parameters generated by the user's activities within a preset detection range in standby mode; The signal processing module is used to process the signal state parameters to obtain amplitude characteristics reflecting the amplitude of human movement and phase characteristics reflecting the speed of human movement. A fall detection module is used to determine whether a human fall event has occurred within the preset detection range based on the amplitude change rate of the amplitude feature and the phase change acceleration of the phase feature. An environmental identification module is used to match the signal state parameters with preset radio frequency fingerprint data when the occurrence of the human fall event is determined, so as to determine the environmental risk category of the location where the human fall event occurs. The status judgment module is used to determine the corresponding observation duration based on the environmental risk category, and continuously acquire the signal status parameters within the observation duration to determine whether the user has resumed the movement state. The alarm execution module is used to determine the corresponding alarm method based on whether the user has resumed movement, and to execute the alarm according to the alarm method.

[0012] In addition, to achieve the above objectives, this application also proposes a fall detection and alarm device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the fall detection and alarm method as described above.

[0013] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the fall detection and alarm method described above.

[0014] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the fall detection and alarm method described above.

[0015] One or more technical solutions proposed in this application have at least the following technical effects: This application can first acquire signal status parameters generated by the user's activities within a preset detection range while in standby mode; then process the signal status parameters to obtain amplitude characteristics reflecting the amplitude of human movement and phase characteristics reflecting the speed of human movement; then determine whether a human fall event has occurred within the preset detection range based on the amplitude change rate of the amplitude characteristics and the phase change acceleration of the phase characteristics; when a human fall event is determined to have occurred, the signal status parameters are matched with preset radio frequency fingerprint data to determine the environmental risk category to which the human fall event occurred; then determine the corresponding observation time based on the environmental risk category, and continuously acquire signal status parameters within the observation time to determine whether the user has resumed movement; finally, determine the corresponding alarm method based on whether the user has resumed movement, and execute the alarm according to the alarm method. This application utilizes the body fat scale's own WiFi signal transmission and reception function to sense human activity, extracts amplitude and phase features to detect fall events, and identifies the environmental risk category of the fall location through signal matching after a fall is detected. Then, it executes differentiated alarms based on the environmental risk category and whether the user has resumed movement. This achieves a fall detection solution that can classify alarms based on the risk level of the fall location without adding any new hardware. Attached Figure Description

[0016] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating the first embodiment of the fall detection and alarm method of this application; Figure 2 This is a flowchart illustrating the second embodiment of the fall detection and alarm method of this application; Figure 3 This is a flowchart illustrating the third embodiment of the fall detection and alarm method of this application; Figure 4 This is a schematic diagram of the module structure of the fall detection and alarm device according to an embodiment of this application; Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the fall detection and alarm method in the embodiments of this application.

[0019] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0020] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0021] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0022] With the increasing aging of the population, falls have become a major safety hazard for elderly people living at home. Body fat scales, as common household health devices, often have built-in WiFi modules that remain powered on in standby mode but are only used for data transmission, their potential underutilized. Existing fall detection technologies mainly fall into three categories: first, computer vision-based solutions, which, while highly accurate, pose privacy risks and are difficult to deploy in private areas such as bathrooms and toilets; second, wearable device-based solutions, which require users to actively wear them and are easily forgotten, resulting in a poor user experience; and third, solutions based on independent WiFi sensing nodes, which achieve contactless detection but require additional dedicated equipment, increasing hardware costs and installation complexity. Furthermore, all of the above solutions use a uniform alarm strategy for all fall events, failing to consider the environmental risks varying at the fall location, leading to insufficient alarm effectiveness.

[0023] Therefore, how to reuse the body fat scale's own WiFi module to achieve privacy-friendly adaptive fall detection and graded alarms is an urgent problem to be solved.

[0024] The main solution of this application embodiment is as follows: First, in standby mode, acquire signal status parameters generated by the user's activity within a preset detection range; then, process the signal status parameters to obtain amplitude features reflecting the amplitude of human movement and phase features reflecting the speed of human movement; then, based on the amplitude change rate of the amplitude features and the phase change acceleration of the phase features, determine whether a human fall event has occurred within the preset detection range; when a human fall event is determined to have occurred, match the signal status parameters with preset radio frequency fingerprint data to determine the environmental risk category to which the human fall event occurred; then, determine the corresponding observation period based on the environmental risk category, and continuously acquire signal status parameters within the observation period to determine whether the user has resumed movement; finally, determine the corresponding alarm method based on whether the user has resumed movement, and execute the alarm according to the alarm method. This application utilizes the body fat scale's own WiFi signal transmission and reception function to sense human activity, extracts amplitude and phase features to detect fall events, and identifies the environmental risk category of the fall location through signal matching after a fall is detected. Then, it executes differentiated alarms based on the environmental risk category and whether the user has resumed movement. This achieves a fall detection solution that can classify alarms based on the risk level of the fall location without adding any new hardware.

[0025] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a body fat scale, tablet computer, personal computer, or mobile phone, or a fall detection and alarm device capable of performing the above functions. The following description uses a body fat scale as an example to illustrate this embodiment and the subsequent embodiments.

[0026] Based on this, embodiments of this application provide a fall detection and alarm method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the fall detection and alarm method of this application.

[0027] In this embodiment, the method is applied to a body fat scale, and the method includes steps S10 to S60: Step S10: In standby mode, acquire the signal status parameters generated by the user's activity within the preset detection range.

[0028] Step S20: Process the signal state parameters to obtain amplitude characteristics reflecting the amplitude of human body movements and phase characteristics reflecting the speed of human body movements.

[0029] It should be noted that standby mode can refer to the working mode of the body fat scale when it is not performing weight or body composition measurement tasks, but the internal circuit is still powered on and running.

[0030] Signal state parameters can be physical quantities that cause changes in channel response due to human activity during the propagation of WiFi signals in indoor spaces, resulting from reflection, scattering, and absorption of the signals.

[0031] Amplitude characteristics can be used to measure the degree of energy attenuation of a WiFi signal along its propagation path.

[0032] Phase characteristics can be a measure used to characterize the degree of phase shift experienced by a WiFi signal along its propagation path.

[0033] The preset detection range can refer to the spatial area centered on the body fat scale, where the WiFi signal can effectively cover and sense human activity, such as a range with a coverage radius of about 15 to 20 meters in an unobstructed indoor environment.

[0034] In its implementation, the body fat scale continuously receives WiFi signals via a WiFi chip while in standby mode, collecting channel state information data for each subcarrier. This channel state information data includes amplitude and phase information for each subcarrier. Amplitude and phase sequences are extracted from this data. The amplitude sequence records the amplitude values ​​of each subcarrier at different times, and the phase sequence records the phase values ​​of each subcarrier at different times. The body fat scale then processes the amplitude sequence to obtain amplitude features and the phase sequence to obtain phase features. It should be noted that the WiFi chip can be an ESP32-S3 or an equivalent chip that supports channel state information acquisition, operating at 2.4GHz or 5GHz, with 56 to 114 subcarriers, a sampling rate of 10Hz to 50Hz, and a transmit power of 20dBm. The body fat scale collects channel state information data packets at fixed intervals, for example, one data packet every 50ms. Each data packet contains amplitude and phase information for multiple subcarriers.

[0035] After obtaining the multiple amplitude and phase sequences, the body fat scale performs differential calculations on the amplitude sequences to obtain the amplitude change rate, which is then used as the amplitude feature. Simultaneously, differential calculations are performed on the phase sequences to obtain the phase change acceleration, which is then used as the phase feature. Preprocessing methods that can be used during the process include, but are not limited to, filtering, denoising, and calibration. For example, Hampel filtering can be used to remove outliers in the phase sequence, or linear phase shifts can be removed to calibrate the phase data.

[0036] For example, a body fat scale is placed in the living room and continuously collects WiFi signals in standby mode. When a user slowly sits down from a standing position, the body's movements are small and slow, resulting in gradual changes in the amplitude and phase features extracted by the body fat scale. However, when the user suddenly falls, both the amplitude and speed of the body's movements change drastically, leading to significant abrupt changes in the amplitude and phase features. The features extracted in these two scenarios differ significantly and can be used for subsequent fall detection.

[0037] Step S30: Based on the amplitude change rate of the amplitude feature and the phase change acceleration of the phase feature, determine whether a human fall event has occurred within the preset detection range.

[0038] Step S40: When it is determined that the human fall event has occurred, the signal state parameters are matched with preset radio frequency fingerprint data to determine the environmental risk category to which the location of the human fall event belongs.

[0039] It should be noted that the preset radio frequency fingerprint database is a database established by collecting signal state parameter samples at different locations around the body fat scale and extracting the signal features of each location. The database contains the correspondence between location identifiers and environmental risk categories.

[0040] Environmental risk categories are based on the degree to which a fall poses a threat to personal safety. For example, high-risk areas include bathrooms, toilets, and stairwells; medium-risk areas include kitchens; and low-risk areas include living rooms and bedrooms.

[0041] Radio frequency fingerprints refer to signal patterns formed by the unique reflection, scattering, and absorption characteristics of WiFi signals at different spatial locations, similar to the uniqueness of a human fingerprint.

[0042] In its implementation, the body fat scale calculates the phase change acceleration and amplitude change rate in real time for each detection cycle, comparing the phase change acceleration with a preset acceleration threshold and the amplitude change rate with a preset rate of change threshold. When both the phase change acceleration and the amplitude change rate exceed the preset acceleration threshold and the rate of change threshold, the body fat scale marks the current detection cycle as a valid detection cycle.

[0043] During the extremely short time it takes for a person to go from standing to falling, the WiFi signal undergoes a dramatic change. The body fat scale utilizes this brief window following the change to quickly determine the occurrence of multiple consecutive detection cycles. For each valid detection cycle, the scale increments its count. When the number of consecutive valid detection cycles reaches a preset number (e.g., 3 consecutive times, corresponding to approximately 150 milliseconds), the scale confirms a fall. If any detection cycle fails to meet this threshold during the counting process, the count is reset and restarted. Through this multi-cycle confirmation mechanism, the body fat scale can quickly confirm the event at the moment of a fall, while avoiding false triggers caused by momentary signal fluctuations.

[0044] After confirming a fall, the body fat scale extracts current signal features from the current signal state parameters and then calculates the similarity between these features and the signal features corresponding to various location markers in a pre-set radio frequency fingerprint database. This database is established by collecting signal state parameter samples from different locations around the body fat scale and extracting signal features from each location. The database contains the correspondence between location markers and environmental risk categories. The body fat scale determines the environmental risk category corresponding to the location marker with the highest similarity as the environmental risk category to which the fall occurred.

[0045] For example, when a body fat scale determines that a user has fallen in the bathroom, the bathroom floor is slippery and the space is narrow, making it a high-risk area, and the body fat scale will match the environmental risk category as high risk. If the fall occurs in the living room, the living room space is open and the floor is dry, making it a low-risk area, and the body fat scale will match the environmental risk category as low risk.

[0046] Step S50: Determine the corresponding observation duration based on the environmental risk category, and continuously acquire the signal status parameters within the observation duration to determine whether the user has resumed movement.

[0047] Step S60: Determine the corresponding alarm method based on whether the user has resumed motion, and execute the alarm according to the alarm method.

[0048] It should be noted that the observation period refers to the length of time from the confirmation of the fall, during which the body fat scale waits and monitors whether the user gets up on their own. Different environmental risk categories correspond to different observation periods; high-risk environmental categories have shorter observation periods, while low-risk environmental categories have longer observation periods. For example, the bathroom is a high-risk environment category, and the corresponding observation period could be 1 minute; the living room is a low-risk environment category, and the corresponding observation period could be 3 minutes.

[0049] The exercise intensity index is a parameter used to quantify the intensity of a user's activity over a period of time. It is extracted based on continuously acquired signal state parameters, such as the exercise intensity index based on CSI variance.

[0050] In its implementation, the body fat scale determines the observation duration based on the matched environmental risk category, searching for and matching it with a pre-defined database. Higher-risk environmental categories correspond to shorter observation durations, while lower-risk categories require longer ones. During the observation period, the scale continuously collects WiFi signals and extracts an exercise intensity index from the acquired signal status parameters. This exercise intensity index, calculated based on the CSI variance, quantifies the intensity of the user's activity within the observation period.

[0051] During the observation period, the body fat scale continuously compared the exercise intensity index with the standing-up threshold. When the exercise intensity index reached the standing-up threshold, the body fat scale determined that the user had resumed exercise (i.e., the user stood up voluntarily). When the exercise intensity index never reached the standing-up threshold throughout the entire observation period, the body fat scale determined that the user had not resumed exercise.

[0052] Subsequently, the body fat scale determines the corresponding alarm method based on the above judgment results. When it is determined that the user has resumed exercise, the body fat scale determines to execute the alarm according to the first alarm method. The first alarm method includes: pushing an event notification to the bound mobile terminal and sending a prompt message to the preset family member terminals. This method is a regular notification used to inform the user that a fall event has occurred but the user has recovered on their own.

[0053] When the scale determines that the user has not resumed exercise, it will issue an alarm according to the second alarm method. This second alarm method includes: activating an audio-visual alert, pushing an event notification to the linked mobile terminal, sending a notification message to a preset family member's terminal, and sending an emergency help message to a preset emergency contact's terminal. The second alarm method is more urgent than the first alarm method and is designed to help users seek emergency assistance when they are unable to get up on their own.

[0054] The channels in the above alarm methods can be executed simultaneously. For example, when the body fat scale determines that the user has not resumed exercise, it can simultaneously activate an audio-visual alert to remind people around, and send notifications to mobile terminal applications, family member terminals, and emergency contact terminals via the network.

[0055] For example, if an elderly person falls in the bathroom, the environmental risk category is determined to be high-risk, and the body fat scale determines the observation time to be 1 minute based on the high-risk category. During the next minute, the body fat scale continuously collects WiFi signals and extracts exercise intensity indicators. If the elderly person stands up on their own after 40 seconds, the exercise intensity indicator reaches the threshold for standing up, and the body fat scale determines that the user has resumed exercise. It then executes an alarm according to the first alarm method: pushing a notification to the linked mobile app that a fall occurred in the bathroom and the person has recovered, and simultaneously sending a reminder SMS to a pre-set children's mobile phone. If the elderly person fails to stand up within 1 minute, the exercise intensity indicator does not reach the threshold for standing up, and the body fat scale determines that the user has not resumed exercise. It then executes an alarm according to the second alarm method: activating a buzzer and flashlight to issue an audible and visual alert, pushing an emergency notification to the linked mobile app that a fall occurred in the bathroom and the user has not recovered, sending an emergency reminder SMS to a pre-set children's mobile phone, and sending an emergency help message to a pre-set emergency contact terminal (such as 120 or a neighbor).

[0056] In this embodiment, the system first acquires signal status parameters generated by the user's activity within a preset detection range while in standby mode. Then, it processes these parameters to obtain amplitude characteristics reflecting the magnitude of human movement and phase characteristics reflecting the speed of human movement. Next, based on the amplitude change rate of the amplitude characteristics and the phase change acceleration of the phase characteristics, it determines whether a human fall event has occurred within the preset detection range. If a fall event is detected, the signal status parameters are matched with preset radio frequency fingerprint data to determine the environmental risk category of the fall event's location. Then, based on the environmental risk category, a corresponding observation period is determined, and signal status parameters are continuously acquired within this period to determine whether the user has resumed movement. Finally, based on whether the user has resumed movement, a corresponding alarm method is determined, and the alarm is executed according to the alarm method. This embodiment uses the body fat scale's own WiFi signal transmission and reception function to sense human activity, extract amplitude and phase features to detect fall events, and identifies the environmental risk category of the fall location through signal matching after a fall is detected. Then, it executes differentiated alarms based on the environmental risk category and whether the user has resumed movement. This achieves a fall detection solution that can classify alarms according to the risk level of the fall location without adding any new hardware.

[0057] Based on the first embodiment of this application, a second embodiment of this application is proposed. In the second embodiment, content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 , Figure 2 This is a flowchart illustrating the second embodiment of the fall detection and alarm method of this application.

[0058] In this embodiment, the step of processing the signal state parameters to obtain amplitude characteristics reflecting the amplitude of human movement and phase characteristics reflecting the speed of human movement includes: Step S201: Extract multiple amplitude sequences and multiple phase sequences from the signal state parameters.

[0059] Step S202: Perform statistical fusion on the multi-channel amplitude sequences to obtain a representative amplitude trajectory, and perform statistical fusion on the multi-channel phase sequences to obtain a representative phase trajectory.

[0060] Step S203: Perform second-order difference calculation on the representative phase trajectory to obtain the phase change acceleration, and use the phase change acceleration as the phase feature.

[0061] Step S204: Perform differential calculation on the representative amplitude trajectory to obtain the amplitude change rate, and use the amplitude change rate as the amplitude feature.

[0062] It should be noted that a multi-amplitude sequence refers to a data sequence in which the amplitude values ​​of multiple subcarriers in a WiFi signal change over time, with each subcarrier corresponding to one amplitude sequence.

[0063] A multi-phase sequence refers to a data sequence in which the phase values ​​of multiple subcarriers in a WiFi signal change over time, with each subcarrier corresponding to one phase sequence.

[0064] Statistical fusion refers to the process of integrating multiple data sequences into a single representative data sequence using mathematical methods, such as median fusion or principal component analysis fusion.

[0065] The representative amplitude trajectory is a single-channel amplitude data sequence obtained after fusion, used to characterize the overall amplitude variation trend of the signal.

[0066] The phase trajectory is a single-channel phase data sequence obtained after fusion, used to characterize the overall phase change trend of the signal.

[0067] Channel state information data refers to channel response data recorded on subcarriers in a specific frequency domain, which includes information in two dimensions: amplitude and phase.

[0068] In its implementation, the body fat scale receives WiFi signals via a built-in WiFi chip and extracts channel state information data from these signals. This channel state information data includes amplitude and phase information for each subcarrier. The body fat scale then extracts multiple amplitude sequences and multiple phase sequences from this channel state information data.

[0069] Taking a subcarrier count of 56 as an example, the body fat scale extracts 56 amplitude sequences and 56 phase sequences from the channel state information data. Each amplitude sequence records the amplitude value of the corresponding subcarrier at different times, and each phase sequence records the phase value of the corresponding subcarrier at different times.

[0070] Body fat scales statistically fuse multiple amplitude sequences. For example, they can take the median amplitude values ​​of all subcarriers at the same time, arrange the medians in chronological order, and form a representative amplitude trajectory. Alternatively, body fat scales can use principal component analysis to extract the first principal component of the multiple amplitude sequences as the representative amplitude trajectory. Similarly, body fat scales statistically fuse multiple phase sequences. For example, they can take the median phase values ​​of all subcarriers at the same time, arrange the medians in chronological order, and form a representative phase trajectory. Principal component analysis can also be used to obtain the representative phase trajectory.

[0071] After obtaining the representative amplitude trajectory and the representative phase trajectory, the body fat scale performs a first-order difference calculation on the representative amplitude trajectory. The representative amplitude trajectory is denoted as A(t), where t represents different times. The body fat scale calculates the amplitude difference between adjacent times, i.e.: Rate of change of amplitude = |A(t) - A(t-1)|; Where A(t) represents the amplitude value at the current moment, and A(t-1) represents the amplitude value at the adjacent previous moment. The body fat scale uses the above amplitude change rate as the amplitude feature.

[0072] The body fat scale performs a second-order difference calculation on the representative phase trajectory. The representative phase trajectory is denoted as p(t), where t represents different times. The body fat scale first calculates the first-order difference to obtain the phase velocity, i.e.: v(t) = p(t) - p(t-1); Where v(t) represents the phase velocity at the current moment, p(t) represents the phase value at the current moment, and p(t-1) represents the phase value of the adjacent previous moment. Subsequently, the body fat scale calculates the phase change acceleration using second-order difference, i.e.: a(t) = v(t) - v(t-1); Where a(t) represents the phase change acceleration at the current moment, v(t) represents the phase velocity at the current moment, and v(t-1) represents the phase velocity at the adjacent previous moment. The body fat scale uses the above phase change acceleration as a phase feature.

[0073] The above differential calculation is repeated at each data acquisition moment to obtain the amplitude feature sequence and phase feature sequence on the continuous time axis.

[0074] For example, the WiFi chip in a body fat scale operates in the 2.4GHz band and supports the acquisition of channel state information for 56 subcarriers. At a given data acquisition moment, the body fat scale acquires 56 amplitude sequences and 56 phase sequences. Each sequence contains the measured value at that moment, and the amplitude values ​​of each subcarrier at the same moment are 0.25, 0.31, 0.28, ... (a total of 56 values). The body fat scale takes the median value of 0.29 as the representative amplitude trajectory value for that moment. Similarly, the median of the 56 phase values ​​is taken as the representative phase trajectory value for that moment. Subsequently, the body fat scale calculates the difference between the current representative amplitude trajectory value of 0.29 and the previous representative amplitude trajectory value of 0.21 to obtain an amplitude change rate of 0.08. The difference between the current representative phase trajectory value of 0.35 radians and the previous representative phase trajectory value of 0.30 radians is taken as the phase velocity of 0.05 radians / second. The difference between the current phase velocity of 0.05 radians and the previous phase velocity of 0.02 radians is taken as the phase change acceleration of 0.03 radians / second², which are used as the phase characteristics at that moment.

[0075] Further, in this embodiment, the step of determining whether a human fall event has occurred within the preset detection range based on the amplitude change rate of the amplitude feature and the phase change acceleration of the phase feature includes: Step S301: Perform single-frame detection on the amplitude change rate and the phase change acceleration respectively. When the phase change acceleration exceeds a preset acceleration threshold and the amplitude change rate exceeds a preset change rate threshold in any detection period, an effective detection period is obtained.

[0076] Step S302: Accumulate the number of valid detection cycles. When the number of cycles reaches a preset number, confirm that the human fall event has occurred.

[0077] It should be noted that single-frame detection means that the body fat scale independently performs a fall determination once in each detection cycle, based on the amplitude change rate and phase change acceleration obtained in that cycle.

[0078] The detection cycle is the time interval between two consecutive data collection and processing of signal status parameters by the body fat scale. For example, if data is collected and processed every 50ms, then one detection cycle is 50ms.

[0079] An effective detection period refers to a period in which both the phase change acceleration and the amplitude change rate simultaneously meet their respective threshold conditions, meaning that a suspected fall signal is detected within that period.

[0080] The preset acceleration threshold is a pre-set critical value for phase change acceleration, used to determine whether the phase change acceleration has reached the severity corresponding to the fall event. For example, it can be obtained from a large amount of fall experiment data.

[0081] The preset rate of change threshold is a pre-set critical value for the rate of change of amplitude, used to determine whether the rate of change of amplitude has reached the severity corresponding to the fall event.

[0082] The preset number of times is the minimum number of consecutive occurrences within a pre-defined effective detection cycle, used to confirm a fall event rather than a random fluctuation in the signal. For example, it can be set to 3 times.

[0083] In its implementation, the body fat scale operates on a detection cycle basis, performing single-frame detection of both amplitude change rate and phase change acceleration within each cycle. The scale compares the phase change acceleration acquired in the current detection cycle with a preset acceleration threshold and the amplitude change rate with a preset rate of change threshold. When both the phase change acceleration and amplitude change rate exceed the preset rate of change thresholds, the scale marks the current detection cycle as a valid detection cycle.

[0084] The body fat scale then accumulates a count of consecutive valid detection cycles. Each time a detection cycle is marked as valid, the scale increments the cycle count by 1. When the total number of cycles reaches a preset threshold, the scale confirms that a fall has occurred.

[0085] If, during the accumulation process, the phase change acceleration of a certain detection cycle does not exceed the preset acceleration threshold or the amplitude change rate does not exceed the preset change rate threshold, the body fat scale will reset the current cycle count to zero and restart the accumulation process.

[0086] It is understood that the aforementioned preset acceleration threshold and preset rate of change threshold can be fixed values ​​or can be adaptively adjusted according to the environmental noise level.

[0087] The preset number of times can be set to 3, meaning a fall is confirmed when a valid signal is detected for 3 consecutive detection cycles. Taking a detection cycle of 50ms as an example, the time required from the first detection of an abnormality to the confirmation of a fall event is 150ms. This time window is within the process of a person going from standing to falling, and the body fat scale can quickly complete the event confirmation within this time window.

[0088] For example, the body fat scale has a detection cycle of 50ms, a preset acceleration threshold of 2.0 radians / second², a preset rate of change threshold of 0.15, and a preset number of detections of 3. In the first detection cycle, the body fat scale acquires a phase change acceleration of 2.3 radians / second² (exceeding 2.0) and an amplitude change rate of 0.18 (exceeding 0.15), satisfying both conditions. The body fat scale marks the first cycle as a valid detection cycle and records the cycle count as 1. In the second detection cycle, the phase change acceleration is 2.5 radians / second² and the amplitude change rate is 0.20, again satisfying the condition, and the cycle count is recorded as 2. In the third detection cycle, the phase change acceleration is 2.1 radians / second² and the amplitude change rate is 0.17, again satisfying the condition. The cycle count reaches the preset number of 3, and the body fat scale confirms a fall event has occurred. If the amplitude change rate in the third detection cycle is only 0.08, which does not exceed the preset change rate threshold of 0.15, the body fat scale will reset the cycle count to zero and will not confirm a fall.

[0089] Furthermore, in this embodiment, the step of matching the signal state parameters with preset radio frequency fingerprint data to determine the environmental risk category to which the location of the human fall event belongs includes: Step S401: Obtain the current signal characteristics in the signal state parameters.

[0090] Step S402: Calculate the similarity between the current signal feature and the signal features corresponding to each location identifier in the preset radio frequency fingerprint database, wherein the preset radio frequency fingerprint database contains the correspondence between the location identifier and the environmental risk category.

[0091] Step S403: Determine the environmental risk category corresponding to the location marker with the highest similarity as the environmental risk category to which the human fall event belongs.

[0092] It should be noted that the current signal features refer to the feature parameters extracted from the signal state parameters obtained at the moment of fall event confirmation for location differentiation, such as the distribution pattern of multipath features.

[0093] The preset radio frequency fingerprint database is a database established by collecting signal state parameter samples at different locations around the body fat scale and extracting signal features at each location. The database contains the correspondence between location identifiers and signal features, as well as the correspondence between location identifiers and environmental risk categories.

[0094] Location identifiers are used to uniquely distinguish different spatial locations around the body fat scale, such as bathrooms, kitchens, and living rooms. Similarity measures how close the current signal characteristics are to the signal characteristics corresponding to a location identifier in the database; higher similarity indicates that the current location is closer to the environment of that location in the database.

[0095] In its implementation, after confirming a fall, the body fat scale reads the signal state parameters at the current moment and extracts signal features from these parameters to distinguish spatial locations. These signal features may include the distribution pattern of multipath characteristics. These multipath characteristics describe the signal pattern formed when a WiFi signal travels through different paths in an indoor environment before reaching the receiver; different spatial locations have different multipath characteristic distributions.

[0096] A pre-defined radio frequency fingerprint database is stored in the body fat scale's local memory. This database is established by pre-collecting signal state parameter samples at different locations around the body fat scale. The body fat scale collects multiple sets of signal state parameters at various locations within a pre-defined detection range, extracts signal features from these parameters for each location, assigns a unique location identifier to each location, and associates and stores the location identifier with the corresponding signal feature. Simultaneously, the database also stores the correspondence between location identifiers and environmental risk categories; for example, the bathroom corresponds to a high-risk category, and the living room corresponds to a low-risk category.

[0097] The body fat scale calculates the similarity between the current signal feature and the signal features corresponding to each location identifier in the database. This similarity can be quantified by calculating indicators such as Euclidean distance, cosine similarity, or correlation coefficient between two signal features. The higher the similarity, the closer the current fall location is to the spatial location corresponding to that location identifier in the database.

[0098] The body fat scale sorts the calculated similarities from highest to lowest and selects the location marker with the highest similarity as the matching result. Then, the body fat scale reads the environmental risk category corresponding to the location marker from the database and determines this environmental risk category as the location of the human fall incident.

[0099] For example, a pre-stored RFID fingerprint database contains four location identifiers: bathroom, kitchen, living room, and bedroom. Each location identifier is associated with a corresponding signal feature and environmental risk category. The bathroom corresponds to the high-risk category, the kitchen to the medium-risk category, and the living room and bedroom to the low-risk category. After the body fat scale confirms a fall, it extracts the current signal feature from the current signal state parameters and calculates the similarity between the current signal feature and the signal features corresponding to the four location identifiers in the database. The results are: 0.85 similarity with the bathroom, 0.42 similarity with the kitchen, 0.38 similarity with the living room, and 0.25 similarity with the bedroom. The body fat scale determines that the similarity with the bathroom is the highest, and therefore identifies the high-risk category corresponding to the bathroom as the environmental risk category for this fall event.

[0100] Based on the first and second embodiments of this application, a third embodiment of this application is proposed. In this third embodiment, content that is the same as or similar to the first and second embodiments described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 3 , Figure 3 This is a flowchart illustrating the third embodiment of the fall detection and alarm method of this application.

[0101] In this embodiment, the step of determining the corresponding observation duration based on the environmental risk category and continuously acquiring the signal state parameters within the observation duration to determine whether the user has resumed movement includes: Step S501: Determine the corresponding observation duration based on the environmental risk category.

[0102] Step S502: Continuously acquire the signal state parameters within the observation period, and obtain the motion intensity index from the signal state parameters.

[0103] Step S503: When the exercise intensity index reaches the standing determination threshold within the observation period, it is determined that the user has resumed exercise.

[0104] It should be noted that the observation period is the length of time the body fat scale waits and monitors whether the user gets up on their own after confirming a fall.

[0105] The observation duration mentioned above corresponds to the environmental risk category determined by the body fat scale during the matching process; different environmental risk categories correspond to different observation durations. The exercise intensity index is a parameter extracted from the signal state parameters and used to quantify the intensity of the user's physical activity within the observation duration. For example, the body fat scale can calculate the exercise intensity index based on the variance of the signal state parameters; a larger variance indicates more intense physical activity. The standing-up judgment threshold is a pre-set critical value for the exercise intensity index. When the exercise intensity index reaches or exceeds this threshold, the body fat scale determines that the user has completed the standing-up action.

[0106] The aforementioned threshold for determining when to stand up can be obtained by statistically analyzing sample data from multiple normal standing-up movements. For example, the average or minimum value of the exercise intensity index during multiple normal standing-ups can be used as the threshold.

[0107] In its implementation, the body fat scale obtains the environmental risk category during the database matching process and then determines the corresponding observation time based on that category. High-risk environmental categories correspond to shorter observation times, while low-risk environmental categories correspond to longer observation times. For example, bathrooms and toilets are considered high-risk environments, and the observation time can be 1 minute; living rooms and bedrooms are considered low-risk environments, and the observation time can be 3 minutes.

[0108] Before the observation period begins, the body fat scale can enter a cool-down period. The duration of the cool-down period is fixed and does not change with the environmental risk category, for example, 5 seconds. The cool-down period is used to allow the residual signal fluctuations after the fall event to stabilize, avoiding misjudgments of exercise intensity indicators due to signal aftershocks. After the cool-down period, the body fat scale officially begins timing the observation period.

[0109] During the observation period, the body fat scale continuously acquires signal state parameters and calculates an exercise intensity index based on these parameters. This exercise intensity index is calculated based on the variance of the signal state parameters; a larger variance indicates more intense physical activity at the current location. The body fat scale continuously compares the calculated exercise intensity index with a standing-up threshold.

[0110] When the body fat scale detects that the exercise intensity index has reached the threshold for determining when to stand up within the observation period, the body fat scale determines that the user has resumed exercise, that is, the user has stood up on their own.

[0111] To more accurately detect whether a user has resumed exercise, the body fat scale can use a continuous target setting method for determination. For example, it can require the exercise intensity index to continuously reach the standing threshold for a preset period of time before finally confirming that the user has resumed exercise. The preset period can be set to 1 second to avoid misjudgments caused by instantaneous signal fluctuations.

[0112] If the exercise intensity index does not reach the threshold for getting up throughout the entire observation period, the body fat scale will not determine whether the user has resumed exercise.

[0113] For example, the body fat scale determines the observation period to be 3 minutes based on the environmental risk category (low-risk category, such as the living room). After confirming a fall, the body fat scale waits for a 5-second cool-down period before starting the 3-minute timer. During these 3 minutes, the body fat scale continuously acquires WiFi signals and calculates the exercise intensity index. Assuming the threshold for determining when to stand up is set to 0.25 (based on the variance normalization of signal state parameters), if the user stands up on their own approximately 40 seconds after the fall, the exercise intensity index calculated by the body fat scale jumps to 0.32, exceeding the standing-up threshold of 0.25, and the body fat scale determines that the user has resumed exercise. Alternatively, if the user remains lying on the ground for the entire 3 minutes without getting up, the exercise intensity index calculated by the body fat scale fluctuates between 0.05 and 0.08, never reaching 0.25, then the body fat scale determines that the user has not resumed exercise after the entire 3 minutes have elapsed.

[0114] Furthermore, in this embodiment, the step of determining the corresponding alarm method based on whether the user resumes movement, and executing the alarm according to the alarm method, includes: Step S601: When it is determined that the user has resumed the motion state, an alarm is triggered according to the first alarm method, which includes: pushing an event notification to the bound mobile terminal and sending a prompt message to the preset family member terminal.

[0115] Step S602: When it is determined that the user has not resumed the movement state, an alarm is executed according to the second alarm method. The second alarm method includes: activating the sound and light prompt, pushing the event notification to the bound mobile terminal, sending the prompt information to the preset family member terminal, and sending the emergency help information to the preset emergency contact terminal. The urgency level of the second alarm method is higher than that of the first alarm method.

[0116] It should be noted that the first alarm method is the conventional notification method executed when the user resumes motion state, including pushing event notifications to the bound mobile terminal and sending prompt messages to preset family member terminals.

[0117] The second alarm method is an emergency alarm method that is executed when the user has not resumed the movement state. In addition to the notification content in the first alarm method, it also includes activating the sound and light prompts and sending emergency help information to the preset emergency contact terminal. The above level of urgency is higher than that of the first alarm method.

[0118] A bound mobile terminal refers to a user's mobile device, such as a mobile phone, that has been pre-associated with the body fat scale. It is usually paired with the body fat scale via Bluetooth or WiFi network.

[0119] Preset family member terminals refer to mobile communication devices owned by family members that the user has pre-set, such as children's mobile phones.

[0120] Preset emergency contact terminals refer to mobile communication devices or public service numbers that users pre-set for emergency contact, such as a neighbor's mobile phone or emergency number.

[0121] In its implementation, after the observation period ends, the body fat scale determines the corresponding alarm method based on whether the user has resumed exercise. When it is determined that the user has resumed exercise, the body fat scale issues an alarm according to the first alarm method. When it is determined that the user has not resumed exercise, the body fat scale issues an alarm according to the second alarm method.

[0122] Specifically, the first alarm method includes pushing event notifications to the bound mobile terminal and sending prompt messages to preset family member terminals. The event notification may include the time and location of the fall, as well as information that the user has resumed movement. The prompt message is used to inform family members that the user has fallen but has recovered on their own and no emergency intervention is needed.

[0123] The second alarm method includes activating audible and visual alerts, pushing event notifications to the linked mobile terminal, sending alert messages to preset family member terminals, and sending emergency assistance messages to preset emergency contact terminals. The audible and visual alerts can be implemented using the body fat scale's built-in buzzer and indicator lights to remind those around the user to pay attention to their condition. The emergency assistance messages can include the time and location of the fall, as well as an explanation of the emergency situation if the user has not resumed movement, so that emergency contacts can take timely rescue measures.

[0124] The second type of alarm is more urgent than the first type, which is reflected in the number of alarm channels, the more urgent alarm content, and the inclusion of emergency contacts in the alarm recipient list.

[0125] The alarm channels in the above alarm methods can be executed simultaneously. For example, when the body fat scale determines that the user has not resumed exercise, it can simultaneously activate an audio-visual alert and send corresponding notifications to the bound mobile terminal, the preset family member terminal, and the preset emergency contact terminal via the network.

[0126] After the cooling-off period ends and before the observation period ends, the body fat scale can first activate the audio-visual prompt channel to send an inquiry signal to the user. If the user resumes exercise within the observation period, the body fat scale will stop the above audio-visual prompts and switch to the first alarm mode.

[0127] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the fall detection and alarm method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0128] This application also provides a fall detection and alarm device; please refer to [reference needed]. Figure 4 The device includes: The signal acquisition module 10 is used to acquire signal status parameters generated by the user's activities within a preset detection range in standby mode; The signal processing module 20 is used to process the signal state parameters to obtain amplitude characteristics reflecting the amplitude of human movement and phase characteristics reflecting the speed of human movement. The fall detection module 30 is used to determine whether a human fall event has occurred within the preset detection range based on the amplitude change rate of the amplitude feature and the phase change acceleration of the phase feature. The environmental identification module 40 is used to match the signal state parameters with preset radio frequency fingerprint data when the occurrence of the human fall event is determined; The status judgment module 50 is used to determine the corresponding observation duration based on the environmental risk category, and continuously acquire the signal status parameters within the observation duration to determine whether the user has resumed the movement state. The alarm execution module 60 is used to determine the corresponding alarm method based on whether the user has resumed motion, and to execute the alarm according to the alarm method.

[0129] The fall detection and alarm device provided in this application, employing the fall detection and alarm method described in the above embodiments, can solve the technical problem of how to reuse the body fat scale's own WiFi module to achieve privacy-friendly environment-adaptive fall detection and graded alarms. Compared with the prior art, the beneficial effects of the fall detection and alarm device provided in this application are the same as those of the fall detection and alarm method provided in the above embodiments, and other technical features in the fall detection and alarm device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0130] This application provides a fall detection and alarm device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the fall detection and alarm method in the first embodiment described above.

[0131] The following is for reference. Figure 5 The diagram illustrates a structural schematic suitable for implementing the fall detection and alarm device in the embodiments of this application. The fall detection and alarm device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The fall detection and alarm device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of this application.

[0132] like Figure 5As shown, the fall detection and alarm device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the fall detection and alarm device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the fall detection and alarm device to exchange data wirelessly or via wired communication with other devices. Although fall detection and alarm devices with various systems are shown in the figures, it should be understood that it is not required to implement or possess all of the systems shown. More or fewer systems may be implemented alternatively.

[0133] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0134] The fall detection and alarm device provided in this application, employing the fall detection and alarm method described in the above embodiments, solves the technical problem of how to reuse the body fat scale's own WiFi module to achieve privacy-friendly environment-adaptive fall detection and graded alarms. Compared with the prior art, the beneficial effects of the fall detection and alarm device provided in this application are the same as those of the fall detection and alarm method provided in the above embodiments, and other technical features of this fall detection and alarm device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0135] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0136] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0137] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the fall detection and alarm method in the above embodiments.

[0138] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0139] The aforementioned computer-readable storage medium may be included in the fall detection and alarm device; or it may exist independently and not assembled into the fall detection and alarm device.

[0140] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by the fall detection and alarm device, the fall detection and alarm device: in standby mode, acquires signal state parameters generated by the user's activity within a preset detection range; processes the signal state parameters to obtain amplitude features reflecting the amplitude of human movement and phase features reflecting the speed of human movement; determines whether a human fall event has occurred within the preset detection range based on the amplitude change rate of the amplitude features and the phase change acceleration of the phase features; when a human fall event is determined to have occurred, matches the signal state parameters with preset radio frequency fingerprint data to determine the environmental risk category to which the location of the human fall event belongs; determines the corresponding observation period based on the environmental risk category, and continuously acquires the signal state parameters within the observation period to determine whether the user has resumed movement; determines the corresponding alarm method based on whether the user has resumed movement, and executes the alarm according to the alarm method.

[0141] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0142] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0143] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0144] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described fall detection and alarm method. This solves the technical problem of how to reuse the built-in WiFi module of a body fat scale to achieve privacy-friendly, environmentally adaptive fall detection and tiered alarms. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the fall detection and alarm method provided in the above embodiments, and will not be repeated here.

[0145] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the fall detection and alarm method described above.

[0146] The computer program product provided in this application solves the technical problem of how to reuse the built-in WiFi module of a body fat scale to achieve privacy-friendly adaptive fall detection and graded alarms. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the fall detection and alarm methods provided in the above embodiments, and will not be repeated here.

[0147] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A fall detection and alarm method, characterized in that, The method is applied to a body fat scale, and the method includes: In standby mode, acquire signal status parameters generated by the user's activities within a preset detection range; The signal state parameters are processed to obtain amplitude characteristics reflecting the amplitude of human movement and phase characteristics reflecting the speed of human movement. Based on the amplitude change rate of the amplitude feature and the phase change acceleration of the phase feature, it is determined whether a human fall event has occurred within the preset detection range; When a human fall event is determined to have occurred, the signal state parameters are matched with preset radio frequency fingerprint data to determine the environmental risk category to which the location of the human fall event belongs. The corresponding observation period is determined based on the environmental risk category, and the signal status parameters are continuously acquired within the observation period to determine whether the user has resumed movement. The corresponding alarm method is determined based on whether the user resumes movement, and the alarm is executed according to the alarm method.

2. The method as described in claim 1, characterized in that, The step of processing the signal state parameters to obtain amplitude characteristics reflecting the amplitude of human movement and phase characteristics reflecting the speed of human movement includes: Extract multiple amplitude sequences and multiple phase sequences from the signal state parameters; The multi-channel amplitude sequences are statistically fused to obtain a representative amplitude trajectory, and the multi-channel phase sequences are statistically fused to obtain a representative phase trajectory. The phase change acceleration is obtained by performing a second-order difference calculation on the representative phase trajectory, and the phase change acceleration is used as the phase feature. The amplitude change rate is obtained by performing differential calculation on the representative amplitude trajectory, and the amplitude change rate is used as the amplitude feature.

3. The method as described in claim 1, characterized in that, The step of determining whether a human fall event has occurred within the preset detection range based on the amplitude change rate of the amplitude feature and the phase change acceleration of the phase feature includes: The amplitude change rate and the phase change acceleration are detected in a single frame. When the phase change acceleration exceeds a preset acceleration threshold and the amplitude change rate exceeds a preset change rate threshold in any detection period, an effective detection period is obtained. The number of valid detection cycles is accumulated, and when the number of cycles reaches a preset number, the human fall event is confirmed to have occurred.

4. The method as described in claim 1, characterized in that, The step of matching the signal state parameters with preset radio frequency fingerprint data to determine the environmental risk category to which the location of the human fall event belongs includes: Obtain the current signal characteristics from the signal state parameters; Calculate the similarity between the current signal feature and the signal features corresponding to each location identifier in the preset radio frequency fingerprint database, wherein the preset radio frequency fingerprint database contains the correspondence between the location identifier and the environmental risk category; The environmental risk category corresponding to the location with the highest similarity is determined as the environmental risk category to which the human fall event belongs.

5. The method as described in claim 1, characterized in that, The step of determining the corresponding observation duration based on the environmental risk category, and continuously acquiring the signal state parameters within the observation duration to determine whether the user has resumed movement includes: The corresponding observation duration is determined based on the environmental risk category; The signal state parameters are continuously acquired during the observation period, and the motion intensity index is obtained from the signal state parameters. When the exercise intensity index reaches the standing determination threshold within the observation period, it is determined that the user has resumed exercise.

6. The method as described in claim 1, characterized in that, The step of determining the corresponding alarm method based on whether the user resumes movement, and executing the alarm according to the alarm method, includes: When it is determined that the user has resumed movement, an alarm is triggered according to the first alarm method, which includes: pushing an event notification to the bound mobile terminal and sending a prompt message to the preset family member terminal; When it is determined that the user has not resumed movement, an alarm is triggered according to the second alarm method. The second alarm method includes: activating an audio-visual prompt, pushing an event notification to the bound mobile terminal, sending a prompt message to the preset family member terminal, and sending an emergency help message to the preset emergency contact terminal. The urgency level of the second alarm method is higher than that of the first alarm method.

7. A fall detection and alarm device, characterized in that, The device includes: The signal acquisition module is used to acquire signal status parameters generated by the user's activities within a preset detection range in standby mode; The signal processing module is used to process the signal state parameters to obtain amplitude characteristics reflecting the amplitude of human movement and phase characteristics reflecting the speed of human movement. A fall detection module is used to determine whether a human fall event has occurred within a preset detection range based on the amplitude change rate of the amplitude feature and the phase change acceleration of the phase feature. An environmental identification module is used to match the signal state parameters with preset radio frequency fingerprint data when the occurrence of the human fall event is determined, so as to determine the environmental risk category of the location where the human fall event occurs. The status judgment module is used to determine the corresponding observation duration based on the environmental risk category, and continuously acquire the signal status parameters within the observation duration to determine whether the user has resumed the movement state. The alarm execution module is used to determine the corresponding alarm method based on whether the user has resumed movement, and to execute the alarm according to the alarm method.

8. A fall detection and alarm device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the fall detection and alarm method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the fall detection and alarm method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the fall detection and alarm method as described in any one of claims 1 to 6.

Images