A pre-warning information determination method, device and equipment and a computer readable storage medium

Abstract

Embodiments of the present application disclose a method for determining early warning information, which comprises: collecting, based on a first sampling frequency, to-be-processed positioning information of a to-be-monitored object determined by multiple positioning modes; performing data preprocessing on the multiple to-be-processed positioning information to obtain initial positioning information, and determining a weight of each initial positioning information based on the accuracy of each initial positioning information, the signal strength corresponding to the initial positioning information, and the signal stability; determining target positioning information of the to-be-monitored object based on the multiple initial positioning information and the multiple weights; and outputting a lost early warning information of the to-be-monitored object based on the target positioning information, a target activity area of the to-be-monitored object, a heart rate deviation degree, and a motion deviation degree. Embodiments of the present application also disclose a device for determining early warning information, equipment and a computer readable storage medium.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a method, apparatus, device, and computer-readable storage medium for determining early warning information. Background Technology

[0002] Currently, there are various anti-wandering warning solutions on the market for special groups (the elderly, children, people with dementia, etc.). These mainly include anti-wandering warning methods based on wearable device positioning information and electronic fences, and anti-wandering warning solutions based on image analysis. Among them, the anti-wandering warning method based on wearable device positioning information and electronic fences relies on real-time positioning information, which can easily lead to inaccurate positioning in areas with poor network signal or signal obstruction, resulting in low positioning accuracy. The anti-wandering warning solution based on image analysis often depends on the resolution of the camera and the accuracy of the algorithm, and may have problems such as limited camera coverage, insufficient resolution, and insufficient algorithm accuracy, resulting in low positioning accuracy. Summary of the Invention

[0003] To address the aforementioned technical problems, this application aims to provide a method, apparatus, device, and computer-readable storage medium for determining early warning information, which can solve the problem of low positioning accuracy in related technologies.

[0004] The technical solution of this application is implemented as follows:

[0005] A method for determining early warning information, the method comprising:

[0006] Based on the first sampling frequency, the location information of the monitored object determined by multiple positioning methods is collected and processed.

[0007] Data preprocessing is performed on multiple locations to be processed to obtain initial locations, and the weight of each initial location is determined based on the accuracy of each initial location, the signal strength and signal stability corresponding to the initial location.

[0008] Based on multiple initial positioning information and multiple weights, the target positioning information of the object to be monitored is determined;

[0009] Based on the target location information, the target activity area of ​​the object to be monitored, the heart rate deviation, and the movement deviation, the system outputs a warning information for the object to be monitored to prevent it from getting lost.

[0010] In the above scheme, the step of outputting a missing person warning based on the target location information, the target activity area of ​​the monitored object, heart rate deviation, and movement deviation includes:

[0011] Based on the target location information and the target activity area, the location deviation of the object to be monitored is determined;

[0012] If the positioning deviation is greater than or equal to the positioning threshold, the heart rate deviation and movement deviation of the object to be monitored are determined.

[0013] When the heart rate deviation is less than or equal to the heart rate threshold, the target attention of the monitored object is determined based on the motion deviation and the motion environment parameters of the monitored object; wherein, the target attention is the attention given to the positioning deviation.

[0014] Based on the location deviation and the target attention level, the missing person warning information is output.

[0015] In the above scheme, determining the positioning deviation of the object to be monitored based on the target positioning information and the target activity area includes:

[0016] Determine multiple reference locations within the target activity area;

[0017] Based on the target positioning information and the multiple reference positions, the position deviation parameter of the object to be monitored is determined;

[0018] The positioning deviation degree is determined based on the position deviation parameter and the position threshold.

[0019] In the above scheme, determining the heart rate deviation and exercise deviation of the monitored object includes:

[0020] Based on the second sampling frequency, the target heart rate parameters, first exercise parameters in a first time period, and second exercise parameters in a second time period of the monitored object are collected at multiple times; wherein, the first time period is longer than the second time period.

[0021] The heart rate deviation is determined based on multiple target heart rate parameters, the first heart rate parameter of the subject under monitoring in a resting state, and the second heart rate parameter of the subject under monitoring in an exercise state;

[0022] The motion deviation is determined based on the first motion parameter and the second motion parameter.

[0023] In the above scheme, determining the target attention level of the monitored object based on the motion deviation and the motion environment parameters of the monitored object includes:

[0024] Based on the motion deviation, the initial attention level of the object to be monitored is determined;

[0025] The initial attention level is adjusted based on the motion environment parameters to obtain the target attention level.

[0026] In the above scheme, the step of outputting the missing person warning information based on the positioning deviation and the target attention includes:

[0027] Based on the positioning deviation and the target attention level, a warning value is determined;

[0028] If the warning value is greater than or equal to the warning threshold, the missing person warning information is output.

[0029] In the above scheme, the method for determining the early warning information further includes:

[0030] If the heart rate deviation is greater than the heart rate threshold, the first sampling frequency is updated to obtain the first updated sampling frequency, and the second sampling frequency is updated to obtain the second updated sampling frequency.

[0031] Based on the first update sampling frequency, the initial positioning information of the object to be monitored, determined by multiple positioning methods, is collected;

[0032] Based on the second update sampling frequency, the target heart rate parameters, first exercise parameters in the first time period, and second exercise parameters in the second time period of the object to be monitored are collected at multiple times.

[0033] A warning information determination device, the device comprising:

[0034] The acquisition unit is used to acquire the location information of the object to be monitored, which is determined by multiple positioning methods, based on the first sampling frequency.

[0035] The determining unit is used to perform data preprocessing on multiple locations to be processed to obtain initial locations, and to determine the weight of each initial location based on the accuracy of each initial location, the signal strength and signal stability corresponding to the initial locations;

[0036] The determining unit is further configured to determine the target positioning information of the object to be monitored based on multiple initial positioning information and multiple weights;

[0037] The processing unit is used to output a missing person warning information for the monitored object based on the target positioning information, the target activity area of ​​the monitored object, the heart rate deviation, and the movement deviation.

[0038] A warning information determination device, the device comprising: a processor, a memory, and a communication bus;

[0039] The communication bus is used to realize the communication connection between the processor and the memory;

[0040] The processor is used to execute the warning information determination program stored in the memory to implement the steps of the above-described warning information determination method.

[0041] A computer-readable storage medium storing one or more programs that can be executed by one or more processors to implement the steps of the warning information determination method described above.

[0042] The early warning information determination method, apparatus, device, and computer-readable storage medium provided in this application embodiment first collects the location information to be processed of the monitored object determined by multiple positioning methods based on a first sampling frequency. Then, it performs data preprocessing on the multiple locations to be processed to obtain initial location information. Based on the accuracy of each initial location information, the signal strength and signal stability corresponding to the initial location information, it determines the weight of each initial location information. Then, based on the multiple initial location information and multiple weights, it determines the target location information of the monitored object. Finally, based on the target location information, the target activity area of ​​the monitored object, and the target location information, it determines the target location information of the monitored object. The system outputs missing person warning information for the monitored object by measuring heart rate deviation and movement deviation. In this way, by acquiring location information to be processed (i.e., multimodal data) collected in multiple ways, and fusing the collected location information to be processed with multimodal data to obtain target location information, instead of using only single location data as in related technologies, the missing person status of the monitored object is determined by using the target location information, the target activity area of ​​the monitored object, heart rate deviation, and movement deviation. This not only realizes comprehensive and continuous monitoring of the health status and daily behavior patterns of special populations, but also greatly improves the accuracy of missing person warnings and effectively reduces the risk of missing persons. Attached Figure Description

[0043] Figure 1 A flowchart illustrating a method for determining early warning information provided in an embodiment of this application;

[0044] Figure 2 A module interaction diagram of a method for determining early warning information provided in an embodiment of this application;

[0045] Figure 3 A flowchart illustrating another method for determining early warning information provided in an embodiment of this application;

[0046] Figure 4 A flowchart illustrating another method for determining early warning information provided in this application embodiment;

[0047] Figure 5 A schematic diagram of a monitoring system for a method of determining early warning information provided in an embodiment of this application;

[0048] Figure 6 This is a schematic diagram of the functional interface of a method for determining early warning information provided in an embodiment of this application;

[0049] Figure 7 A schematic diagram of the system architecture for a method for determining early warning information provided in an embodiment of this application;

[0050] Figure 8 This is a schematic diagram of the structure of a warning information determination device provided in an embodiment of this application;

[0051] Figure 9 This is a schematic diagram of the structure of a warning information determination device provided in an embodiment of this application. Detailed Implementation

[0052] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0053] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0054] It should be noted that while there are various smart wearable products on the market for preventing people from wandering and for health monitoring targeting specific groups (such as the elderly, children, and people with dementia), most products focus on a single function, such as providing only GPS positioning or simple health data monitoring. This lacks effective integration with fixed devices and effective fusion of multiple data sources. Furthermore, in rural areas with poor network coverage, such wearable devices may result in inaccurate identification or false alarms for lost persons. Existing technical solutions for personnel positioning and missing persons warnings generally include the following: anti-wandering warnings based on wearable devices and electronic fences, issuing warnings when the wearer leaves the designated electronic fence area; and image analysis based on cameras in key areas, issuing warnings when devices deployed at key intersections in rural areas capture images of the target person appearing within the image range and moving away from houses or residential areas. However, anti-wandering warning methods based on wearable device positioning information and electronic fences rely on real-time positioning information. Rural areas often have poor or blocked network signals, leading to lost or delayed location information uploads, resulting in low accuracy and high false alarm rates. Image-based anti-wandering warning solutions often rely on camera resolution and algorithm accuracy. However, in real-world applications, there may be issues such as limited camera coverage, insufficient resolution, and inadequate algorithm accuracy, which may prevent the effective identification of missing persons.

[0055] Based on this, embodiments of this application provide a method for determining early warning information, which can be applied to an early warning information determining device, with reference to... Figure 1 As shown, the method includes the following steps:

[0056] Step 101: Based on the first sampling frequency, collect the location information of the object to be monitored, which is determined by multiple positioning methods.

[0057] In this embodiment, the first sampling frequency may refer to the collection frequency of the location information to be processed of the monitored object collected by multiple positioning methods; multiple positioning methods (i.e., multimodal) may include GPS or Beidou positioning collected by smart wearable devices, Long Range Radio (LoRa) base station positioning, Bluetooth beacon positioning, and image recognition positioning collected by a camera; the monitored object may refer to a special group of people who need to be monitored; the location information to be processed may refer to the location information directly collected by the positioning method.

[0058] In the embodiments of this application, such as Figure 2 The data collection shown can employ a first sampling frequency to collect unprocessed location information of the monitored object obtained through GPS or BeiDou positioning methods collected by smart wearable devices, LoRa base station positioning methods, Bluetooth beacon positioning methods, and image recognition positioning methods obtained through cameras. In this way, in rural areas targeting the prevention of wandering among special populations, it not only achieves seamless integration of multi-source data—satellite positioning, long-range radio communication positioning, low-power Bluetooth communication positioning, camera visual image analysis, and data generated by built-in sensors in wearable devices—but also efficiently integrates these previously independent data sources through data fusion algorithms, forming a comprehensive, multi-layered data network. This provides comprehensive anti-wandering and health care services for special populations in rural areas. In one feasible implementation, the monitored object can refer to individuals requiring anti-wandering and health care services, such as the elderly, children, and people with dementia; the initial location information can refer to the location coordinates of the monitored object collected through multiple positioning methods; and the first sampling frequency can refer to sampling once per minute.

[0059] Step 102: Perform data preprocessing on multiple location information to be processed to obtain initial location information, and determine the weight of each initial location information based on the accuracy, signal strength and signal stability of each initial location information.

[0060] In this embodiment of the application, after collecting the location information to be processed through various positioning methods, the collected location information to be processed can also be processed as follows: Figure 2 The data preprocessing shown includes noise reduction, data synchronization, and normalization, which then yields the initial positioning information.

[0061] In this embodiment of the application, after obtaining the initial positioning information, the accuracy of the initial positioning information, the signal strength corresponding to the initial positioning information, and the signal stability can be used to perform actions such as... Figure 2 The diagram shows the weights for each initial positioning information, specifically the signal strength (S). i Signal strength index (RSSI) can reflect the real-time quality of a signal and can be calculated using real-time acquired signal strength index (RSSI) or signal-to-noise ratio (SNR). A higher value indicates a better signal, ranging from 0 to 100. Signal stability index (HSI) reflects the signal's real-time quality. i This refers to evaluating signal reliability based on historical data, specifically calculating packet loss rate, number of disconnections, etc., over a past period based on historical signal quality data; the more stable the signal, the higher the score. Accuracy (A) i This can reflect historical positioning accuracy, calculated based on historical positioning errors (such as the average error of GPS or Bluetooth). The smaller the error, the higher the accuracy. Furthermore, historical errors can be normalized to a score from 0 to 100, with smaller errors resulting in higher scores. Specifically, weights (W) can be assigned to each piece of initial positioning information based on its accuracy, corresponding signal strength, and signal stability. i The calculation is performed using the formula shown in formula (1) below:

[0062] W i =α·S i +β·H i +γ·A i Formula (1)

[0063] Here, α, β, and γ are the weighting coefficients of each factor, representing the importance of each factor. α is generally more important in dynamic or fast-moving environments, especially in scenarios with high real-time requirements, such as in transportation where equipment moves quickly and signal strength changes frequently, making real-time performance crucial; therefore, α values ​​can be relatively large. β is more suitable for long-term, slowly changing scenarios, such as homes and indoor environments. In these scenarios, signal stability determines the reliability of data transmission and positioning; therefore, β can be set higher. γ is critical for scenarios with high requirements such as precise positioning and behavior monitoring. If the application scenario requires high-precision positioning (such as medical monitoring or positioning of special personnel), γ should be large; that is, the weights of various positioning data should be determined according to the positioning application scenario. Finally, after normalizing each signal source, the sum of the weights is made equal to 1.

[0064] It should be noted that the data preprocessing specifically includes: 1) For noise reduction, median filtering can be used to denoise the original positioning data, eliminating sudden erroneous positioning points. Median filtering can effectively remove isolated noise points without affecting the overall trend of the data. The formula for median filtering is x. i ′=median(x i-n ,...,x i ,...,x i+n ), where x i These are the original data points, x i ′ represents the filtered data point, and n is the size of the filtering window. Assume that in a time series, most data points fluctuate within a relatively stable range, but occasionally some outliers deviate from the normal range. When using median filtering, a certain number of adjacent data points are selected, and their median is used as the estimated value of the current point. This effectively eliminates isolated outliers. Without denoising, outliers will affect the data fusion results, potentially increasing the location estimation error and impacting the system's positioning accuracy and stability. 2) Regarding data synchronization, synchronization is unnecessary when only one data source reports data within a certain period. However, when multiple data sources are present in the same time period, time synchronization is required for data collected at different frequencies using interpolation or sampling methods. This ensures that data from different sensors are aligned in time, guaranteeing consistency between different data sources. The specific formula for data synchronization is... Where t i and t i+1 The time of the known data point is x(t). i ) and x(t i+1) represents the known data point value, and t represents the time point to be interpolated. Through linear interpolation, the value at any time point can be estimated, aligning the data from different sensors at the same time point. Without time synchronization, the data from different sensors will be misaligned on the time axis, leading to incorrect correlations during data fusion and affecting the accurate judgment of personnel location and behavior. 3) Regarding normalization, normalization is not required when only one data source reports data within a certain period. However, when multiple data sources report data within the same time period, it is necessary to eliminate the dimensional differences between different sensor data to bring the data to the same scale, facilitating subsequent fusion and analysis. The initial positioning information is primarily processed by normalizing all data into latitude and longitude data. The specific normalization methods are as follows: For GPS or BeiDou positioning data: since this data already contains latitude and longitude data, no normalization is required; For LoRa base station information data: since LoRa communication cannot directly obtain the latitude and longitude information of the wearable device, it can be calculated using 1) the system's stored base station latitude and longitude information plus distance information. The accuracy of the normalized data obtained using this method is generally low; 2) if the wearable device has established communication with at least three LoRa base stations and obtained distance information, latitude and longitude can be calculated using trilateration. The accuracy of the normalized data obtained using this method is relatively high. The basic principle of trilateration is to determine the unknown location using three known base stations and their distances to the unknown location. In two-dimensional space, if there are three known points and the distances from the unknown point to these three points, the location of the unknown point can be determined using the intersection of circles. The specific calculation steps are: there are three base stations A, B, and C, whose positions are (λ... A ,φ A ), (λ B ,φ B ) and (λ C ,φ C ), and the distances between the wearable device and these three base stations are d respectively. A d B and d C Then, based on the distance formula, the following system of equations is constructed. Then, the system of equations is solved to obtain the coordinates (λ, φ) of the unknown point wearable device. 4) For Bluetooth beacon information data: Since Bluetooth beacons are generally deployed indoors and the signal coverage range is generally 3-40 meters, the system-pre-stored beacon latitude and longitude is used as the positioning data in this scenario without normalization. 5) For camera image analysis data: When the monitored person appears in the camera's shooting range and is accurately identified by the image analysis algorithm, the monitored person's camera positioning data can be determined based on the camera's location data. For example, considering factors such as camera coverage and image analysis algorithm requirements (clearly capturing the monitored person's face), the system-pre-stored camera latitude and longitude can be used as the monitored person's camera positioning data in this scenario. Alternatively, the monitored person's positioning data can be calculated based on the camera's latitude and longitude and the monitored person's user depth information in the captured image without normalization.

[0065] Step 103: Based on multiple initial positioning information and multiple weights, determine the target positioning information of the object to be monitored.

[0066] In this embodiment of the application, multiple initial location information within the same time period (such as the same time or within 5 seconds) are processed as follows: Figure 2 The data fusion shown calculates a precise positioning information, namely the target positioning information. Thus, based on the weights of various positioning data calculated according to the positioning application scenario, the cleaned multimodal positioning data is fused to obtain the final fused positioning result (i.e., the target positioning information). By combining multiple positioning data with the positioning application scenario for fused positioning, the accuracy of positioning can be improved. The target positioning information can be specifically calculated using the following formula (2):

[0067]

[0068] Where, x f (t) represents the fused positioning data, i.e., the target positioning information, w i It is the weight of the i-th data source, x i (t) represents the initial location information of the i-th data source at time t.

[0069] It should be noted that after obtaining the target location information, it is also possible to combine the target location information from different time periods to form a time-sequential trajectory chain, such as trajectory chain = {(t1,x1),(t2,x2),...,(t...}. n ,x n )}.

[0070] Step 104: Based on the target location information, the target activity area of ​​the object to be monitored, the heart rate deviation, and the movement deviation, output the missing person warning information of the object to be monitored.

[0071] The target activity area can be a relatively safe activity area for the monitored object, formed by recording the routes and places the monitored object frequently travels.

[0072] In this embodiment, considering that during the process of getting lost, compared with the same time period under normal circumstances, in addition to deviation from the conventional location information, there is often a significant increase in exercise and irregular fluctuations in heart rate, basic health monitoring indicators (such as heart rate and exercise volume) have positive reference significance for getting lost early warning. Therefore, smart wearable devices can provide location and health warnings for getting lost. Thus, health data of the monitored object can be collected through smart wearable devices, including heart rate, blood pressure, body temperature, and motion sensing data, such as steps. Then, based on the target location information, the target activity area of ​​the monitored object, the heart rate deviation determined by the heart rate parameter, and the motion deviation determined by the motion parameter, it can be jointly determined whether the monitored object is lost. If it is determined that the monitored object is lost, a getting lost early warning message is issued to the monitored object's guardian.

[0073] The method for determining early warning information provided in the embodiments of this application acquires location information to be processed (i.e., multimodal data) collected in multiple ways, and performs multimodal data fusion on the collected location information to be processed to obtain target location information, instead of using only a single location data as in related technologies. Then, the target location information, the target activity area of ​​the monitored object, the heart rate deviation, and the movement deviation are used to jointly determine the missing status of the monitored object. This not only realizes comprehensive and continuous monitoring of the health status and daily behavior patterns of special populations, but also greatly improves the accuracy of early warning of missing objects and effectively reduces the risk of missing objects.

[0074] Based on the foregoing embodiments, this application provides another method for determining early warning information, referring to... Figure 3 and Figure 4 As shown, the method may include the following steps:

[0075] Step 201: The early warning information determination device collects the initial positioning information of the object to be monitored, which is determined by multiple positioning methods, based on the first sampling frequency.

[0076] Step 202: The early warning information determination device performs data preprocessing on multiple location information to be processed to obtain initial location information, and determines the weight of each initial location information based on the accuracy, signal strength and signal stability of each initial location information.

[0077] Step 203: Early Warning Information Determination. The device determines the target location information of the object to be monitored based on multiple initial positioning information and multiple weights.

[0078] It should be noted that after determining the target location information, the following steps can be taken: Figure 2 The decision-making and application shown include the following steps:

[0079] Step 204: Early Warning Information Determination. Based on the target positioning information and the target activity area, the device determines the positioning deviation of the object to be monitored.

[0080] In this embodiment of the application, the position deviation parameter can be determined first by the target positioning information and the target activity area, and then the positioning deviation degree can be determined based on the position deviation parameter and the position threshold.

[0081] It should be noted that step 204 can be achieved in the following way:

[0082] Step 204A1: The early warning information determination device determines multiple reference locations in the target activity area;

[0083] In this embodiment, the reference positions can be multiple location coordinates determined from the target active region, and the multiple reference positions in the target active region can be represented as graph = {(x1,y1),(x2,y2),...,(x...}. n ,y n )}.

[0084] Step 204A2: Early Warning Information Determination. Based on the target positioning information and multiple reference positions, the device determines the position deviation parameters of the object to be monitored.

[0085] In this embodiment, the position deviation parameter is the minimum distance from the target location information X(t) to the target activity area; the target location information can be expressed as X(t) = (x, y), then the position deviation parameter D(t) can be expressed by the formula Calculated.

[0086] Step 204A3: The warning information determination device determines the positioning deviation degree based on the position deviation parameters and position threshold.

[0087] In this embodiment of the application, the position deviation parameter D(t) and the position threshold D can be... t When comparing, when D(t) > D t At time t, the positioning deviation G(t) exceeds D(t). t The ratio is such that, otherwise the positioning deviation G(t) is 0, as shown in the following formula (3):

[0088]

[0089] It should be noted that the location threshold D t The embodiments in this application are not subject to specific limitations and can be adjusted according to the actual situation.

[0090] Step 205: When the positioning deviation of the device is greater than or equal to the positioning threshold, the heart rate deviation and movement deviation of the object to be monitored are determined.

[0091] In this embodiment of the application, if the positioning deviation is greater than or equal to the positioning threshold, it indicates that the monitored object is moving away from the target activity area (i.e., it indicates that the monitored object may be at risk of getting lost). In this case, the heart rate deviation and motion deviation of the monitored object can be determined, and then the heart rate deviation and motion deviation can be combined to determine whether the monitored object has gotten lost.

[0092] It should be noted that step 205 can be achieved in the following way:

[0093] Step 205B1: The warning information determination device collects the target heart rate parameters, the first motion parameters in the first time period, and the second motion parameters in the second time period of the monitored object at multiple times based on the second sampling frequency.

[0094] The first time period is longer than the second time period.

[0095] In this embodiment, the second sampling frequency can refer to the sampling frequency for collecting the target heart rate parameters and motion parameters of the monitored object; the heart rate parameters of the monitored object can be collected through a smart wearable device, and the motion parameters of the monitored object can also be collected through a smart wearable device. The first motion parameter refers to the average calculation of the motion parameters collected within the first time period, and the second calculation parameter is the summation of the motion parameters collected within the second time period. In one feasible implementation, the motion parameter can refer to the number of steps taken, the first time period can refer to one month, and if the first time period refers to one month, the second time period can refer to the time period from 0:00 to the current time on a certain day of that month; the second sampling frequency can refer to sampling once every 10 minutes.

[0096] Step 205B2: The warning information determination device determines the heart rate deviation based on multiple target heart rate parameters, the first heart rate parameter of the monitored object in the resting state, and the second heart rate parameter of the monitored object in the exercise state.

[0097] In this embodiment, the first heart rate parameter Rr can refer to the average heart rate of the monitored object measured in multiple resting states; the second heart rate parameter Re can refer to the average heart rate of the monitored object measured in multiple exercise states; the multiple target heart rate parameters are the heart rate parameters of the monitored object collected at multiple times (such as the current time and the time before the current time), and the target heart rate parameter at time t can be expressed as R(t), and the target heart rate parameter before time t can be expressed as R(t-1), R(t-2), etc.; the current heart rate change amplitude of the monitored object can be determined first by the multiple target heart rate parameters, and then the heart rate change amplitude of the monitored object from the resting state to the exercise state can be calculated by the first heart rate parameter and the second heart rate parameter. Then, the heart rate deviation H(t) can be calculated based on the ratio of the current heart rate change amplitude to the heart rate change amplitude from the resting state to the exercise state, as shown in the following formula (4):

[0098]

[0099] Step 205B3: The warning information determination device determines the motion deviation based on the first motion parameter and the second motion parameter.

[0100] In this embodiment of the application, the first motion parameter S can be... m Second motion parameter S t Comparison, when S t >S m When the motion deviation S(t) is determined to be S t Exceeding S m The proportion when S t m When the motion deviation S(t) is determined to be 0, the specific formula is as follows (5):

[0101]

[0102] It should be noted that steps 206 to 207 can be executed after step 205, and steps 208 to 210 can also be executed after step 205.

[0103] Step 206: When the heart rate deviation is less than or equal to the heart rate threshold, the warning information determination device determines the target attention level of the monitored object based on the motion deviation and the motion environment parameters of the monitored object.

[0104] Among them, target attention refers to the attention given to the degree of positioning deviation.

[0105] In this embodiment of the application, the initial attention level of the object to be monitored can be determined first based on the motion deviation, and then the target attention level of the object to be monitored can be determined based on the initial attention level and the motion environment parameters of the object to be monitored.​

[0106] It should be noted that step 206 can be achieved in the following way:

[0107] Step 206C1: The early warning information determination device determines the initial attention level of the object to be monitored based on the motion deviation.

[0108] In this embodiment, considering the strong positive correlation between location information and activity level information, when the location deviation is greater than the location threshold (i.e., indicating that the monitored object may be at risk of getting lost), if the activity deviation is large or continues for a period of time, it indicates that the user may have been walking for a long time, and the risk of leaving the usual place (i.e., the target activity area) is relatively high. In this case, greater attention can be paid to the location deviation. Since the activity deviation and the initial attention are related by an arcsine function, the initial attention ω can be calculated by the following formula (6):

[0109] ω=sin -1 S(t) Formula (6)

[0110] It should be noted that the initial level of attention to the monitored subject can also be determined based on the heart rate deviation.

[0111] Step 206C2: The warning information determination device adjusts the initial attention based on motion environment parameters to obtain the target attention.

[0112] In this embodiment of the application, in order to improve the accuracy of the initial attention ω, ω can be corrected by combining the current motion environment parameters of the object to be monitored. The motion environment parameters may include the current weather, temperature, motion trajectory, motion altitude change, etc. For example, if the temperature of the motion environment of the object to be monitored is high or the motion altitude change is large (e.g., high altitude indicates a lot of climbing), then ω can be corrected to be smaller to obtain the target attention ω′.

[0113] It should be noted that the initial attention ω of the object to be monitored can be determined by the motion deviation S(t), and the initial attention ω can be dynamically adjusted based on the motion environment parameters of the object to be monitored to obtain the adjusted target attention ω′. In this way, by combining the actual motion of the object to be monitored, the positioning warning can be dynamically disturbed and corrected to improve the accuracy of the missing person warning.

[0114] It should be noted that, in addition to adjusting the initial attention level based on the exercise environment parameters of the monitored object, the initial attention level can also be dynamically adjusted based on the heart rate deviation; or, the initial attention level can be adjusted by weighted fusion of exercise volume deviation and heart rate deviation.

[0115] Step 207: The device determines the early warning information based on the positioning deviation and the target attention level, and outputs the missing person early warning information.

[0116] In this embodiment of the application, a warning value can be determined first based on the location deviation and the target attention. Then, it is determined whether the object to be monitored has gone missing based on the warning value. If it is determined that the object to be monitored has gone missing based on the warning value, a missing warning information is output to the monitoring object of the object to be monitored.

[0117] It should be noted that step 207 can be achieved in the following way:

[0118] Step 207D1: The warning information determination device determines the warning value based on the positioning deviation and target attention.

[0119] In this embodiment of the application, the warning value P can be calculated from the positioning deviation and the target attention using the following formula (7). d :

[0120] P d =ω′G(t) Formula (7)

[0121] Step 207D2: Warning Information Determination. When the warning value is greater than or equal to the warning threshold, the device outputs a missing person warning.

[0122] In this embodiment, the warning threshold can be set according to the actual situation; the warning value and the warning threshold can be compared, and when the warning value is greater than the warning threshold, it is determined that the object to be monitored is missing, a missing warning is triggered, and missing warning information is output; in one feasible implementation, the warning threshold can be set to 0.7.

[0123] It should be noted that this application introduces heart rate, movement trajectory and positioning information collected by wearable devices and deeply integrates it with data from fixed devices to establish a comprehensive evaluation system based on positioning deviation, heart rate fluctuation and movement volume changes. The data fusion technology is used to accurately calculate the warning signal strength, which improves the accuracy and precision of missing person warnings. Once the signal strength exceeds the preset safe warning threshold, the warning mechanism will be activated immediately and automatically to ensure a rapid and efficient response.

[0124] It should be noted that the above embodiments may also include the following steps:

[0125] Step 208: When the device determines that the heart rate deviation is greater than the heart rate threshold, it updates the first sampling frequency to obtain the first updated sampling frequency and updates the second sampling frequency to obtain the second updated sampling frequency.

[0126] Step 209: The early warning information determination device collects the initial positioning information of the object to be monitored, which is determined by multiple positioning methods, based on the first update sampling frequency;

[0127] Step 210: The warning information determination device collects the target heart rate parameters, the first motion parameters in the first time period, and the second motion parameters in the second time period of the monitored object at multiple times based on the second update sampling frequency.

[0128] In this embodiment, considering that the permanent residence area (i.e., the target activity area) of rural users is relatively small, if the heart rate deviation is large, it indicates that the user to be monitored may have been exercising for a long time (e.g., walking for a long time) or is currently in poor health. Therefore, when the heart rate deviation is large, risk warning should be given special attention. At this time, the data sampling frequency can be dynamically adjusted based on the heart rate deviation. That is, when the heart rate deviation is greater than the heart rate threshold, the sampling frequency of parameters such as location information, heart rate, and exercise volume is increased. That is, the first sampling frequency is updated to obtain the first updated sampling frequency, and the second sampling frequency is updated to obtain the second updated sampling frequency. Specifically, the step size of the sampling frequency increase can be determined according to the difference between the heart rate deviation and the heart rate threshold. Then, the various data after the sampling frequency is increased are used to perform the location and missing risk warning processing of the monitored object in the above manner (i.e., steps 201 to 207). In this way, by increasing the sampling frequency of various data used for location and missing risk warning, the missing risk warning can be judged in a timely manner through dense data, thereby improving the sensitivity and accuracy of missing risk warning.

[0129] It should be noted that, given the criticality of wearable device battery life and its direct impact on the accuracy of missing person warnings, this application introduces heart rate fluctuation data (i.e., heart rate deviation) as a dynamic adjustment factor to intelligently adjust the data acquisition frequency of wearable devices. This strategy not only effectively extends the battery life of wearable devices, but also significantly improves the sensitivity and accuracy of missing person warnings at critical moments, thus safeguarding the safety of special populations.

[0130] It should be noted that the missing persons early warning method proposed in this application not only greatly improves the accuracy of missing persons early warning for special populations in rural areas and effectively reduces the risk of them getting lost, but also achieves comprehensive and continuous monitoring of the health status and daily behavior patterns of special populations through in-depth analysis of cross-modal data. This not only enhances the reliability of the system, but also greatly enriches its application scenarios, making it an indispensable intelligent tool for protecting the safety and health of special populations. Specifically, this is reflected in the following: 1) Heart rate affects data collection frequency: In health monitoring and missing persons early warning scenarios, a mechanism for dynamically adjusting the data sampling frequency based on heart rate deviation is introduced. This innovation not only improves the accuracy of early warning, but also takes into account the device's battery life. 2) Improved early warning accuracy: When the system detects a significant increase in the heart rate deviation of the monitored person, it may mean that they are in a state of tension, anxiety, or excessive physical exertion. These states are often associated with precursors to missing persons events. At this time, the system immediately increases the sampling frequency of key data such as location, heart rate, and activity level to ensure that it can track the location changes and physiological state of the monitored person in real time and accurately, thereby timely capturing and assessing the risk of getting lost. 3) Increased battery life: When the risk of getting lost is low or the person being monitored is in a stable state, the system automatically reduces the data sampling frequency based on parameters such as heart rate deviation, reducing unnecessary energy consumption. This intelligent energy-saving mode helps extend the device's battery life, ensuring sufficient power support in critical moments.

[0131] It should be noted that the advantages of this application compared to existing technologies are as follows: 1) Comprehensive functionality: It integrates multiple functions such as positioning, trajectory tracking, behavior monitoring, health monitoring, early warning, and emergency communication, meeting the diverse needs of special groups in rural areas. 2) Strong environmental adaptability: Through multimodal positioning technology and linkage with fixed equipment, the characteristics of different data sources and the complexity of the rural environment are considered, improving the system's adaptability and robustness, effectively overcoming the problem of complex network environments in rural areas, and improving positioning accuracy and real-time performance. 3) Higher accuracy in missing person warnings: The innovative multimodal data fusion method and trend warning algorithm effectively improve the accuracy of missing person warning judgments.

[0132] In other embodiments of this application, reference is made to Figure 5 As shown, smart wearable devices and fixed devices work together to collect data. The data fusion and analysis platform integrates and analyzes the collected data to form a health record and determine whether a person has gone missing. If a person is found to be missing, a missing person warning is generated. If a warning is generated, the guardian and / or grassroots staff of the person to be monitored are notified by phone, SMS, etc. The relevant personnel then take appropriate action based on the missing person warning information.

[0133] In other embodiments of this application, reference is made to Figure 6As shown, this application adopts a multimodal data fusion approach to realize functions such as positioning and trajectory tracking, behavior monitoring and health monitoring, electronic fence and proactive early warning, SOS one-click call and proactive communication, health data management and file establishment. Grassroots managers can realize comprehensive management and analysis within the area through the monitoring screen, and guardians can conduct point-to-point management of the monitored persons through mobile terminals.

[0134] In other embodiments of this application, reference is made to Figure 7 As shown, the overall architecture of this application integrates smart wearable devices (such as smartwatches or smart bracelets), fixed devices (such as cameras installed on the sides of roads and at intersections), and a data fusion analysis platform. The smart wearable devices include a positioning module, health monitoring functions, and a communication module. The data fusion analysis platform, after fusing and analyzing multimodal data, can provide early warnings of missing persons and visualize relevant trajectory tracking and user health record information on a large monitoring screen. The smart wearable devices are responsible for collecting location and health data of the monitored individuals, prioritizing mobile communication networks for transmission. In outdoor areas with poor signal (such as valleys and forests), they can interact with fixed small base stations via LoRa communication technology. In indoor areas with poor signal, they can use Bluetooth beacons for positioning and data transmission, ensuring smooth communication. Fixed devices are used to assist in positioning and data transmission; cameras collect and analyze image data. The data fusion analysis platform fuses and analyzes multimodal data, and the special needs care system provides information display and operational support. The smart wearable device integrates a GPS or BeiDou satellite signal receiving module, a LoRa communication module, health monitoring sensors (heart rate sensor, blood pressure sensor, etc.), behavior monitoring sensors (accelerometer, gyroscope), an emergency call (SOS) one-button, and an active communication module. The smart wearable device adopts a low-power design to meet the needs of extended use. Furthermore, the smart wearable device uses encryption technology to encrypt transmitted data, ensuring data security and privacy.

[0135] It should be noted that the descriptions of the same steps and contents as in other embodiments in this embodiment can be found in the descriptions in other embodiments, and will not be repeated here.

[0136] The early warning information determination method provided in this application acquires location information to be processed (i.e., multimodal data) collected in multiple ways, and performs multimodal data fusion on the acquired location information to obtain target location information, instead of using only a single location data as in related technologies. Then, the target location information, the target activity area of ​​the monitored object, heart rate deviation, and movement deviation are used to jointly determine the missing status of the monitored object. This not only realizes comprehensive and continuous monitoring of the health status and daily behavior patterns of special populations, but also greatly improves the accuracy of early warning of missing objects and effectively reduces the risk of missing objects.

[0137] Based on the foregoing embodiments, this application provides a warning information determination device, which can be applied to... Figure 1 and Figure 3 In the corresponding embodiment, the method for determining early warning information refers to... Figure 8 As shown, the early warning information determining device 3 may include: an acquisition unit 31, a determining unit 32, and a processing unit 33, wherein:

[0138] The acquisition unit 31 is used to acquire the location information to be processed of the object to be monitored, which is determined by multiple positioning methods, based on the first sampling frequency.

[0139] The determining unit 32 is used to perform data preprocessing on multiple positioning information to obtain initial positioning information, and to determine the weight of each initial positioning information based on the accuracy of each initial positioning information, the signal strength and signal stability corresponding to the initial positioning information.

[0140] The determining unit 32 is also used to determine the target positioning information of the object to be monitored based on multiple initial positioning information and multiple weights;

[0141] The processing unit 33 is used to output a warning message of the object being monitored as it wanders off, based on the target location information, the target activity area of ​​the object to be monitored, the heart rate deviation, and the movement deviation.

[0142] In other embodiments of this application, the processing unit 33 is further configured to perform the following steps:

[0143] Based on the target location information and the target activity area, determine the location deviation of the object to be monitored;

[0144] If the positioning deviation is greater than or equal to the positioning threshold, determine the heart rate deviation and movement deviation of the monitored object;

[0145] When the heart rate deviation is less than or equal to the heart rate threshold, the target attention of the monitored object is determined based on the exercise deviation and the exercise environment parameters of the monitored object; whereby the target attention is the attention given to the positioning deviation.

[0146] Based on the location deviation and target attention level, a missing person warning message is output.

[0147] In other embodiments of this application, the processing unit 33 is further configured to perform the following steps:

[0148] Determine multiple reference locations within the target activity area;

[0149] Based on the target location information and multiple reference locations, determine the position deviation parameters of the object to be monitored;

[0150] The positioning deviation is determined based on the position deviation parameter and the position threshold.

[0151] In other embodiments of this application, the processing unit 33 is further configured to perform the following steps:

[0152] Based on the second sampling frequency, target heart rate parameters, first motion parameters in the first time period, and second motion parameters in the second time period of the monitored object are collected at multiple times; wherein the first time period is longer than the second time period.

[0153] Based on multiple target heart rate parameters, the first heart rate parameter of the subject under resting state and the second heart rate parameter of the subject under exercise state, the heart rate deviation is determined;

[0154] The motion deviation is determined based on the first motion parameter and the second motion parameter.

[0155] In other embodiments of this application, the processing unit 33 is further configured to perform the following steps:

[0156] The initial level of attention to the object to be monitored is determined based on the degree of motion deviation.

[0157] The initial attention level is adjusted based on motion environment parameters to obtain the target attention level.

[0158] In other embodiments of this application, the processing unit 33 is further configured to perform the following steps:

[0159] The warning value is determined based on the location deviation and the target attention level;

[0160] If the warning value is greater than or equal to the warning threshold, output a missing person warning message.

[0161] In other embodiments of this application, the processing unit 33 is further configured to perform the following steps:

[0162] If the heart rate deviation is greater than the heart rate threshold, the first sampling frequency is updated to obtain the first updated sampling frequency, and the second sampling frequency is updated to obtain the second updated sampling frequency.

[0163] Based on the first update sampling frequency, the initial location information of the monitored object determined by multiple positioning methods is collected;

[0164] Based on the second update sampling frequency, the target heart rate parameters, the first exercise parameters in the first time period, and the second exercise parameters in the second time period of the monitored object are collected at multiple times.

[0165] It should be noted that the specific implementation process of the steps performed by each module in the embodiments of this application can be referred to Figure 1 and Figure 3 The implementation process of the warning information determination method provided in the corresponding embodiment will not be described in detail here.

[0166] The early warning information determination device provided in the embodiments of this application acquires location information to be processed (i.e., multimodal data) collected in multiple ways, and performs multimodal data fusion on the acquired location information to be processed to obtain target location information, instead of using only a single location data as in related technologies. Then, it uses the target location information, the target activity area of ​​the monitored object, heart rate deviation, and movement deviation to jointly determine the missing status of the monitored object. This not only realizes comprehensive and continuous monitoring of the health status and daily behavior patterns of special populations, but also greatly improves the accuracy of the early warning of the missing object and effectively reduces the risk of getting lost.

[0167] Based on the foregoing embodiments, embodiments of this application provide a warning information determining device, which can be applied to... Figure 1 and Figure 3 In the corresponding embodiment, the method for determining early warning information refers to... Figure 9 As shown, the warning information determining device 4 may include: a processor 41, a memory 42, and a communication bus 43, wherein:

[0168] Communication bus 43 is used to realize the communication connection between processor 41 and memory 42;

[0169] The processor 41 is used to execute the warning information determination program in the memory 42 to perform the following steps:

[0170] Based on the first sampling frequency, the location information of the monitored object determined by multiple positioning methods is collected and processed.

[0171] Multiple location information to be processed are preprocessed to obtain initial location information, and the weight of each initial location information is determined based on the accuracy, signal strength and signal stability of each initial location information.

[0172] Based on multiple initial positioning information and multiple weights, the target positioning information of the object to be monitored is determined;

[0173] Based on the target location information, the target activity area of ​​the monitored object, heart rate deviation, and movement deviation, the system outputs a warning message about the monitored object going missing.

[0174] In other embodiments of this application, the processor 41 is used to execute the warning information determination program in the memory 42, based on target location information, the target activity area of ​​the monitored object, heart rate deviation, and movement deviation, to output the missing warning information of the monitored object, in order to achieve the following steps:

[0175] Based on the target location information and the target activity area, determine the location deviation of the object to be monitored;

[0176] If the positioning deviation is greater than or equal to the positioning threshold, determine the heart rate deviation and movement deviation of the monitored object;

[0177] When the heart rate deviation is less than or equal to the heart rate threshold, the target attention of the monitored object is determined based on the exercise deviation and the exercise environment parameters of the monitored object; whereby the target attention is the attention given to the positioning deviation.

[0178] Based on the location deviation and target attention level, a missing person warning message is output.

[0179] In other embodiments of this application, the processor 41 is used to execute the warning information determination program in the memory 42 to determine the positioning deviation of the object to be monitored based on the target positioning information and the target activity area, so as to achieve the following steps:

[0180] Determine multiple reference locations within the target activity area;

[0181] Based on the target location information and multiple reference locations, determine the position deviation parameters of the object to be monitored;

[0182] The positioning deviation is determined based on the position deviation parameter and the position threshold.

[0183] In other embodiments of this application, the processor 41 is used to execute the warning information determination program in the memory 42 to determine the heart rate deviation and movement deviation of the monitored object, in order to achieve the following steps:

[0184] Based on the second sampling frequency, target heart rate parameters, first motion parameters in the first time period, and second motion parameters in the second time period of the monitored object are collected at multiple times; wherein the first time period is longer than the second time period.

[0185] Based on multiple target heart rate parameters, the first heart rate parameter of the subject under resting state and the second heart rate parameter of the subject under exercise state, the heart rate deviation is determined;

[0186] The motion deviation is determined based on the first motion parameter and the second motion parameter.

[0187] In other embodiments of this application, the processor 41 is used to execute the warning information determination program in the memory 42 to determine the target attention level of the monitored object based on the motion deviation degree and the motion environment parameters of the monitored object, so as to achieve the following steps:

[0188] The initial level of attention to the object to be monitored is determined based on the degree of motion deviation.

[0189] The initial attention level is adjusted based on motion environment parameters to obtain the target attention level.

[0190] In other embodiments of this application, the processor 41 is used to execute the warning information determination program in the memory 42 based on the positioning deviation and target attention, and output missing person warning information to achieve the following steps:

[0191] The warning value is determined based on the location deviation and the target attention level;

[0192] If the warning value is greater than or equal to the warning threshold, output a missing person warning message.

[0193] In other embodiments of this application, the processor 41 is used to execute the warning information determination method of the warning information determination program in the memory 42 to implement the following steps:

[0194] If the heart rate deviation is greater than the heart rate threshold, the first sampling frequency is updated to obtain the first updated sampling frequency, and the second sampling frequency is updated to obtain the second updated sampling frequency.

[0195] Based on the first update sampling frequency, the initial location information of the monitored object determined by multiple positioning methods is collected;

[0196] Based on the second update sampling frequency, the target heart rate parameters, the first exercise parameters in the first time period, and the second exercise parameters in the second time period of the monitored object are collected at multiple times.

[0197] It should be noted that a detailed description of the steps performed by the processor can be found in [reference needed]. Figure 1 and Figure 3 The implementation process of the warning information determination method provided in the corresponding embodiment will not be described in detail here.

[0198] The early warning information determination device provided in this application acquires location information to be processed (i.e., multimodal data) collected in multiple ways, and performs multimodal data fusion on the acquired location information to obtain target location information, instead of using only a single location data as in related technologies. Then, it uses the target location information, the target activity area of ​​the monitored object, heart rate deviation, and movement deviation to jointly determine the missing status of the monitored object. This not only realizes comprehensive and continuous monitoring of the health status and daily behavior patterns of special populations, but also greatly improves the accuracy of the early warning of missing objects and effectively reduces the risk of missing objects.

[0199] Based on the foregoing embodiments, this application provides a computer-readable storage medium storing one or more programs that can be executed by one or more processors to achieve... Figure 1 and Figure 3 The steps in the warning information determination method provided in the corresponding embodiment.

[0200] It should be noted that the aforementioned computer-readable storage media can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM), etc.; or it can be various electronic devices that include one or any combination of the above-mentioned memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc.

[0201] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0202] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0203] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0204] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0205] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0206] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0207] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for determining early warning information, characterized in that, The method includes: Based on the first sampling frequency, the location information of the monitored object determined by multiple positioning methods is collected and processed. Data preprocessing is performed on multiple locations to be processed to obtain initial locations, and the weight of each initial location is determined based on the accuracy of each initial location, the signal strength and signal stability corresponding to the initial location. Based on multiple initial positioning information and multiple weights, the target positioning information of the object to be monitored is determined; Based on the target location information, the target activity area of ​​the object to be monitored, the heart rate deviation, and the movement deviation, the system outputs a warning information for the object to be monitored to prevent it from getting lost.

2. The method according to claim 1, characterized in that, Based on the target location information, the target activity area of ​​the monitored object, heart rate deviation, and movement deviation, the system outputs a missing person warning information for the monitored object, including: Based on the target location information and the target activity area, the location deviation of the object to be monitored is determined; If the positioning deviation is greater than or equal to the positioning threshold, the heart rate deviation and movement deviation of the object to be monitored are determined. When the heart rate deviation is less than or equal to the heart rate threshold, the target attention of the monitored object is determined based on the motion deviation and the motion environment parameters of the monitored object; wherein, the target attention is the attention given to the positioning deviation. Based on the location deviation and the target attention level, the missing person warning information is output.

3. The method according to claim 2, characterized in that, The step of determining the positioning deviation of the object to be monitored based on the target positioning information and the target activity area includes: Determine multiple reference locations within the target activity area; Based on the target positioning information and the multiple reference positions, the position deviation parameter of the object to be monitored is determined; The positioning deviation degree is determined based on the position deviation parameter and the position threshold.

4. The method according to claim 2, characterized in that, Determining the heart rate deviation and exercise deviation of the monitored object includes: Based on the second sampling frequency, the target heart rate parameters, first exercise parameters in a first time period, and second exercise parameters in a second time period of the monitored object are collected at multiple times; wherein, the first time period is longer than the second time period. The heart rate deviation is determined based on multiple target heart rate parameters, the first heart rate parameter of the subject under monitoring in a resting state, and the second heart rate parameter of the subject under monitoring in an exercise state; The motion deviation is determined based on the first motion parameter and the second motion parameter.

5. The method according to claim 2, characterized in that, The determination of the target attention level of the monitored object based on the motion deviation and the motion environment parameters of the monitored object includes: Based on the motion deviation, the initial attention level of the object to be monitored is determined; The initial attention level is adjusted based on the motion environment parameters to obtain the target attention level.

6. The method according to claim 2, characterized in that, The step of outputting the missing person warning information based on the positioning deviation and the target attention level includes: Based on the positioning deviation and the target attention level, a warning value is determined; If the warning value is greater than or equal to the warning threshold, the missing person warning information is output.

7. The method according to claim 2, characterized in that, The method further includes: If the heart rate deviation is greater than the heart rate threshold, the first sampling frequency is updated to obtain the first updated sampling frequency, and the second sampling frequency is updated to obtain the second updated sampling frequency. Based on the first update sampling frequency, the initial positioning information of the object to be monitored, determined by multiple positioning methods, is collected; Based on the second update sampling frequency, the target heart rate parameters, first exercise parameters in the first time period, and second exercise parameters in the second time period of the object to be monitored are collected at multiple times.

8. A device for determining early warning information, characterized in that, The device includes: The acquisition unit is used to acquire the location information of the object to be monitored, which is determined by multiple positioning methods, based on the first sampling frequency. The determining unit is used to perform data preprocessing on multiple locations to be processed to obtain initial locations, and to determine the weight of each initial location based on the accuracy of each initial location, the signal strength and signal stability corresponding to the initial locations; The determining unit is further configured to determine the target positioning information of the object to be monitored based on multiple initial positioning information and multiple weights; The processing unit is used to output a missing person warning information for the monitored object based on the target positioning information, the target activity area of ​​the monitored object, the heart rate deviation, and the movement deviation.

9. A device for determining early warning information, characterized in that, The device includes: a processor, a memory, and a communication bus; The communication bus is used to realize the communication connection between the processor and the memory; The processor is used to execute a warning information determination program in the memory to implement the steps of the warning information determination method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores one or more programs, which can be executed by one or more processors to implement the steps of the warning information determination method as described in any one of claims 1 to 7.

Images