Vital sign data acquisition method and system supporting multi-device synchronization

Abstract

The invention provides a vital sign data acquisition method and system supporting multi-device synchronization. The method comprises the following steps: acquiring vital sign data and various key event data of a patient through multiple types of acquisition equipment, and generating a personalized synchronous configuration file; based on the personalized synchronous configuration file, carrying out dynamic adjustment and optimization by applying a self-adaptive time sequence calibration algorithm to ensure that data acquisition time sequences are highly consistent, and adding microsecond-level time stamps by adopting a high-precision timestamp embedding technology to generate a vital sign data stream; based on the vital sign data stream, monitoring and evaluating signal stability by using a real-time spectral analysis algorithm, automatically adjusting acquisition frequency and a sampling strategy, and implementing immediate adjustment by adopting an environment adaptive adjustment technology to generate a multi-source vital sign data set; and generating a standardized vital sign data report based on the multi-source vital sign data set. According to the technical scheme provided by the invention, the quality and consistency of the vital sign data synchronously collected by multiple devices are greatly improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of vital sign collection, and in particular to a method and system for collecting vital sign data that supports synchronization of multiple devices. Background Art

[0002] With the rapid development of medical health monitoring technology, intelligent health management systems have been widely used in scenarios such as home health monitoring, clinical medicine, and rehabilitation care. However, in these application scenarios, higher technical requirements are put forward for the synchronous collection of vital sign data from multiple devices.

[0003] At present, there are some solutions on the market that attempt to synchronize the collection of vital sign data through multiple types of acquisition devices. These solutions usually adopt a static time base calibration method, that is, a one-time clock synchronization setting is performed when the device is initialized, and rely on a fixed sampling frequency and strategy to collect data. In addition, some advanced systems have also introduced preliminary spectrum analysis algorithms to evaluate signal quality, but lack real-time adjustment mechanisms.

[0004] Although existing solutions can achieve data synchronization of multiple devices to a certain extent, they still have significant defects. First, due to the lack of an adaptive time series calibration algorithm, existing solutions are difficult to deal with the problem of time drift between devices, resulting in low quality of vital sign data collection, especially during long-term monitoring, data consistency is difficult to ensure. Secondly, existing solutions fail to fully consider the impact of environmental changes on the stability of collected signals, and are unable to adjust key parameters in real time based on feedback information, so that the collected data may be affected by noise and other interference sources. Finally, existing solutions are relatively weak in data integration, and data collected by different devices often require additional processing to reach a unified format, which increases the complexity and uncertainty of subsequent data analysis. Summary of the invention

[0005] The embodiments of the present application provide a method and system for collecting vital sign data that supports multi-device synchronization, so as to solve the problem of low quality of vital sign data collection in the prior art.

[0006] In a first aspect, an embodiment of the present application provides a method for collecting vital sign data supporting multi-device synchronization, including:

[0007] Through multiple types of collection devices, the patient's vital signs data and various key event data are obtained to generate personalized synchronization configuration files;

[0008] Based on the personalized synchronization configuration file, the adaptive time series calibration algorithm is used to dynamically adjust and optimize the time base of each device to ensure that the data collection timing is highly consistent. The high-precision timestamp embedding technology is used to add microsecond time tags to all vital sign data points to generate a vital sign data stream;

[0009] Based on the vital signs data stream, a real-time spectrum analysis algorithm is used to monitor and evaluate the stability of the collected signals of each device, automatically adjust the collection frequency and sampling strategy, and adopt environmental adaptive adjustment technology to make real-time adjustments to key parameters based on feedback information to generate a multi-source vital signs data set;

[0010] Based on the multi-source vital sign data set, combined with corresponding timestamps, it is integrated into a unified data format to generate a standardized vital sign data report.

[0011] Optionally, based on the personalized synchronization configuration file, an adaptive time series calibration algorithm is used to dynamically adjust and optimize the time base of each device to ensure that the data acquisition timing is highly consistent, and a high-precision timestamp embedding technology is used to add microsecond time tags to all vital sign data points to generate a vital sign data stream, including:

[0012] Based on the personalized synchronization configuration file, a preliminary correction process is performed on the current time reference of each device to reduce the initial time deviation and generate a preliminary calibration time reference;

[0013] Based on the preliminary calibration time base, an adaptive time series calibration algorithm is used to continuously monitor and analyze the time offset between devices, and dynamic adjustment and optimization are implemented to ensure that the data collection timing is highly consistent and generate a consistent time base;

[0014] Based on the consistent time reference, a high-precision timestamp embedding technology is used to add a microsecond-level unique time tag when each vital sign data point is collected, thereby generating a microsecond-level vital sign data point;

[0015] Based on the microsecond-level vital sign data points, sorting and integration processing are performed to ensure that the data flow is continuous and orderly, thereby generating a vital sign data stream.

[0016] Optionally, based on the preliminary calibration time reference, an adaptive time series calibration algorithm is used to continuously monitor and analyze the time offset between devices, and dynamic adjustment and optimization are implemented to ensure that the data acquisition timing is highly consistent and generate a consistent time reference, including:

[0017] Based on the preliminary calibration time reference, continuously monitor the time offset between each device to identify a small time difference between any two devices and generate a time offset monitoring result;

[0018] Based on the time offset monitoring results, an adaptive time series calibration algorithm is used to model and predict the time series between the devices, and the model prediction value is compared with the actual monitoring value to analyze the deviation and generate accurate correction parameters;

[0019] Based on the precise correction parameters, considering the equipment response delay and the stability of the adjustment process, designing and generating specific correction instructions, and generating an optimized correction instruction set;

[0020] Based on the optimized correction instruction set, the time base of each device is adjusted in real time, the time deviation between different devices is gradually reduced, and a consistent time base is generated.

[0021] Optionally, based on the consistent time reference, a high-precision timestamp embedding technology is used to add a microsecond-level unique time tag when each vital sign data point is collected to generate a microsecond-level vital sign data point, including:

[0022] Based on the consistent time reference, the clocks of each device are synchronized and corrected to ensure that the time of all devices is consistent and generate a synchronized time frame;

[0023] Based on the synchronous time frame, a high-precision timestamp embedding technology is used to accurately time each vital sign data point at the moment of collection, obtain microsecond-level time information at the current moment, and generate a microsecond-level timestamp;

[0024] Based on the microsecond timestamp, the timestamp is firmly associated with the corresponding vital sign data point by metadata to generate a timestamp associated data point;

[0025] Based on the timestamp-associated data points, preliminary data collation and verification are performed to generate microsecond-level vital sign data points.

[0026] Optionally, based on the vital signs data stream, a real-time spectrum analysis algorithm is used to monitor and evaluate the stability of the collected signals of each device, automatically adjust the collection frequency and sampling strategy, adopt environmental adaptive adjustment technology, and make real-time adjustments to key parameters according to feedback information to generate a multi-source vital signs data set, including:

[0027] Based on the vital sign data stream, perform a preliminary quality check to identify obvious anomalies and noise, and generate a preliminary signal quality report;

[0028] Based on the preliminary signal quality report, use a real-time spectrum analysis algorithm to perform frequency domain analysis, detect noise levels and frequency characteristics, analyze and search for potential interference sources, determine periodic noise and other abnormal components, and generate a detailed signal quality report;

[0029] Based on the detailed signal quality report, an environmental adaptive adjustment technology is used to adjust key parameters in real time in combination with the current working environment noise level and the equipment operation status to generate an adaptive adjustment data set;

[0030] Based on the adaptive adjustment data set, the vital sign data of each device and the corresponding timestamp are integrated to improve data consistency and generate a multi-source vital sign data set.

[0031] Optionally, based on the preliminary signal quality report, a real-time spectrum analysis algorithm is used to perform frequency domain analysis, detect noise levels and frequency characteristics, analyze and search for potential interference sources, so as to determine periodic noise and other abnormal components, and generate a detailed signal quality report, including:

[0032] Based on the preliminary signal quality report, preprocess the signal in the vital sign data stream to remove obvious outliers and noise to generate a preprocessed signal;

[0033] Based on the preprocessed signal, a real-time spectrum analysis algorithm is used to perform frequency domain conversion, detect noise levels and frequency characteristics to identify major frequency components, analyze change trends to search for potential interference sources, comprehensively evaluate overall stability, and generate a spectrum analysis report;

[0034] Based on the spectrum analysis report and in combination with the preliminary signal quality report, comprehensively evaluate the overall signal stability and generate a comprehensive quality report;

[0035] Based on the comprehensive quality report, various key indicators and optimization measures are further refined to generate a detailed signal quality report.

[0036] Optionally, the multi-source vital sign data sets are integrated into a unified data format in combination with corresponding timestamps to generate a standardized vital sign data report, including:

[0037] Based on the multi-source vital sign data set, data from different devices are preliminarily sorted to ensure that the timestamp of each data point is accurate, and a time-calibrated data set is generated;

[0038] Based on the time calibration data set, data format conversion and standardization processing are performed to unify the data into a standard data format, thereby generating a format standardized data set;

[0039] Based on the standardized data set in the format, data cleaning and outlier detection processing are performed to remove inconsistent and erroneous data points to generate a purified data set;

[0040] Based on the purified data set and in combination with corresponding timestamps, a visualization chart is introduced to visualize the results and generate a standardized vital sign data report.

[0041] In a second aspect, an embodiment of the present application provides a vital sign data collection system supporting multi-device synchronization, including:

[0042] The collection module is used to obtain the patient's vital signs data and various key event data through multiple types of collection devices, and generate personalized synchronization configuration files;

[0043] An optimization module is used to dynamically adjust and optimize the time base of each device based on the personalized synchronization configuration file by using an adaptive time series calibration algorithm to ensure that the data acquisition timing is highly consistent, and to add microsecond time stamps to all vital sign data points by using high-precision timestamp embedding technology to generate a vital sign data stream;

[0044] A monitoring module is used to monitor and evaluate the stability of the collected signals of each device based on the vital signs data stream, use a real-time spectrum analysis algorithm, automatically adjust the collection frequency and sampling strategy, adopt environmental adaptive adjustment technology, make real-time adjustments to key parameters according to feedback information, and generate a multi-source vital signs data set;

[0045] A generation module is used to generate a standardized vital sign data report based on the multi-source vital sign data set, combined with corresponding timestamps, integrated into a unified data format.

[0046] In a third aspect, an embodiment of the present application provides a computing device, comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a vital sign data collection method that supports multi-device synchronization as described in the first aspect.

[0047] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program. When the computer program is executed by a computer, a vital sign data collection method supporting multi-device synchronization as described in the first aspect is implemented.

[0048] In an embodiment of the present application, a patient's vital signs data and various key event data are acquired through multiple types of acquisition devices to generate a personalized synchronization configuration file; based on the personalized synchronization configuration file, an adaptive time series calibration algorithm is used to dynamically adjust and optimize the time base of each device to ensure that the data acquisition timing is highly consistent, and a high-precision timestamp embedding technology is used to add microsecond time marks to all vital signs data points to generate a vital signs data stream; based on the vital signs data stream, a real-time spectrum analysis algorithm is used to monitor and evaluate the stability of the acquisition signals of each device, automatically adjust the acquisition frequency and sampling strategy, and use environmental adaptive adjustment technology to implement real-time adjustment of key parameters based on feedback information to generate a multi-source vital signs data set; based on the multi-source vital signs data set, combined with the corresponding timestamps, integrated into a unified data format to generate a standardized vital signs data report. The patient's vital signs data and various key event data are obtained through multiple types of acquisition devices, and a personalized synchronization configuration file is generated. Based on this configuration file, the time base of each device is dynamically adjusted and optimized; this method not only ensures a high degree of consistency in the data acquisition timing, but also achieves microsecond-level time marking through high-precision timestamp embedding technology; it significantly improves the accuracy and synchronization of vital signs data collection, reduces data errors caused by time deviations, and enhances the reliability of data integration between different devices.

[0049] Furthermore, the initial time deviation is reduced through preliminary correction processing, and the time offset between devices is continuously monitored and optimized using an adaptive time series calibration algorithm; this ensures a high degree of consistency in the data acquisition timing and improves the accuracy of the timestamp, so that each vital sign data point has a unique microsecond-level time stamp; the resulting vital sign data stream is continuous and orderly, greatly facilitating subsequent data analysis and processing and improving the overall performance of the system.

[0050] Furthermore, a real-time spectrum analysis algorithm is used to monitor and evaluate the stability of the collected signals of each device, and automatically adjust the collection frequency and sampling strategy; through preliminary quality inspection, obvious anomalies and noise are identified, and then the noise level and frequency characteristics are detected through frequency domain analysis to identify potential interference sources. Combined with environmental adaptive adjustment technology, key parameters are adjusted in real time based on feedback information, ensuring that the collected data is highly stable and reliable; the multi-source vital signs data set finally generated not only retains the time consistency of the original data, but also improves the overall quality and availability of the data, providing reliable data support for subsequent medical diagnosis and other applications.

[0051] These and other aspects of the present application will become more apparent from the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0053] Figure 1 A flowchart of a method for collecting vital sign data supporting multi-device synchronization provided in an embodiment of the present application;

[0054] Figure 2 A structural diagram of a vital sign data acquisition system supporting multi-device synchronization provided in an embodiment of the present application;

[0055] Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0057] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0058] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0059] Figure 1 A flowchart of a method for collecting vital sign data supporting synchronization of multiple devices is provided for an embodiment of the present application. Figure 1 As shown, the method includes:

[0060] 101. Obtain the patient's vital signs data and various key event data through various types of collection devices, and generate personalized synchronization configuration files;

[0061] In this step, multiple types of collection devices include but are not limited to heart rate monitors, blood pressure monitors, respiratory rate monitors, blood glucose meters, thermometers, etc., which are used to measure different vital signs data and various key event data. Each device provides different types of physiological data based on its specific functions and technical characteristics, providing a basis for comprehensive health monitoring.

[0062] Among them, vital signs data is the basic indicator for assessing a person's current health status, usually including body temperature, pulse (heart rate), respiratory rate and blood pressure. In addition, depending on the specific situation, other important parameters such as blood sugar level, blood oxygen saturation, etc. may also be included. These data are crucial for doctors to monitor the health status of patients.

[0063] Key event data refers to data records of specific situations or activities that occur during the medical service process and have a significant impact on the patient's diagnosis, treatment or care. For example, the time of drug administration, the time when the operation starts and ends, sudden changes in the condition, etc. This type of data helps to fully understand the patient's medical journey and provide a basis for subsequent analysis.

[0064] The personalized synchronization profile is a profile automatically generated based on vital signs data and various key event data. This profile is not only used for initial settings, but can also be dynamically adjusted according to user changes to maintain the best synchronization effect. The profile may contain information such as communication protocols between devices, time base calibration parameters, and sampling frequency settings.

[0065] In an embodiment of the present application, assuming that in a smart home health monitoring system, first, the system collects the user's heart rate, sleep pattern and other physiological characteristics through smart health bracelets and bedside monitoring devices; secondly, it combines the personal information (such as age, gender, medical history) and environmental information (such as indoor temperature and humidity) input by the user to generate a personalized synchronization configuration file; thirdly, the configuration file will automatically adapt to changes in the user's living habits (such as adjustments to work and rest schedules); finally, the configuration file supports remote updates to ensure that the device is always in the optimal synchronization state.

[0066] 102. Based on the personalized synchronization configuration file, an adaptive time series calibration algorithm is used to dynamically adjust and optimize the time base of each device to ensure that the data collection timing is highly consistent, and a high-precision timestamp embedding technology is used to add microsecond time tags to all vital sign data points to generate a vital sign data stream;

[0067] In this step, the adaptive time series calibration algorithm is an algorithm used to dynamically adjust and optimize the time base of each device. The algorithm is based on a personalized synchronization profile. By continuously monitoring and analyzing the time offset between devices, dynamic adjustment and optimization are implemented to ensure a high degree of consistency in the data acquisition timing.

[0068] Dynamic adjustment optimization is to monitor and correct the time deviation between devices in real time through an adaptive time series calibration algorithm to ensure that the data collection timing of all devices remains consistent.

[0069] High-precision timestamp embedding technology is a technology that adds microsecond-level time stamps to all vital sign data points. This timestamp ensures that each data point carries precise time information, improving the time synchronization and accuracy of the data.

[0070] Microsecond timestamps are unique timestamps added to each vital sign data point with microsecond accuracy, ensuring the time accuracy of the data point.

[0071] The vital signs data stream is a data set generated after the above processing, which contains vital signs data points with timestamps, ensuring the time synchronization and accuracy of the data, and the data stream is continuous and orderly.

[0072] In the embodiment of this application, it is assumed that the user uses a variety of vital signs monitoring devices at home for daily health monitoring. First, the system performs preliminary time correction when each device is first connected to reduce the initial time deviation; second, the system uses an adaptive time series calibration algorithm to monitor the small time differences between devices in real time and make dynamic adjustments; third, each vital sign data point collected will be immediately stamped with a microsecond time stamp; finally, all the data points with time stamps are integrated into a continuous data stream in chronological order to ensure the integrity and consistency of the data stream.

[0073] Optionally, in step 102, based on the personalized synchronization configuration file, an adaptive time series calibration algorithm is used to dynamically adjust and optimize the time base of each device to ensure that the data acquisition timing is highly consistent, and a high-precision timestamp embedding technology is used to add microsecond time tags to all vital signs data points to generate a vital signs data stream, including: based on the personalized synchronization configuration file, a preliminary correction processing is performed on the current time base of each device to reduce the initial time deviation and generate a preliminary calibration time base; based on the preliminary calibration time base, an adaptive time series calibration algorithm is used to continuously monitor and analyze the time offset between each device, and dynamic adjustment and optimization are implemented to ensure that the data acquisition timing is highly consistent and generate a consistent time base; based on the consistent time base, a high-precision timestamp embedding technology is used to add a unique time tag at the microsecond level when each vital signs data point is collected to generate a microsecond vital signs data point; based on the microsecond vital signs data points, sorting and integration processing is performed to ensure that the data stream is continuous and orderly to generate a vital signs data stream.

[0074] In this step, the preliminary correction processing is a preliminary adjustment of the current time base of each device, aiming to reduce the initial time deviation. This step generates a preliminary calibration time base, which provides a basis for subsequent more precise time synchronization.

[0075] The consistent time base is a time standard that is dynamically adjusted and optimized to ensure that the time bases of all devices are consistent. This step ensures that all devices work within the same time frame, improving the consistency and reliability of data.

[0076] Microsecond-level vital sign data points refer to vital sign data points with microsecond-level time stamps, ensuring that each data point has a high degree of time accuracy.

[0077] First, based on the personalized synchronization configuration file, the current time base of each device is preliminarily corrected to reduce the initial time deviation and generate a preliminary calibration time base. Secondly, using the preliminary calibration time base, the adaptive time series calibration algorithm is used to continuously monitor and analyze the time offset between devices, and dynamic adjustment and optimization are implemented to ensure that the data collection timing is highly consistent and generate a consistent time base. Thirdly, when each vital sign data point is collected, a high-precision timestamp embedding technology is used to add a unique time tag at the microsecond level to generate microsecond vital sign data points. Finally, all microsecond vital sign data points are sorted and integrated to ensure that the data flow is continuous and orderly, and finally a vital sign data stream is generated.

[0078] Optionally, based on the preliminary calibration time benchmark, an adaptive time series calibration algorithm is used to continuously monitor and analyze the time offset between each device, implement dynamic adjustment and optimization, ensure that the data acquisition timing is highly consistent, and generate a consistent time benchmark, including: based on the preliminary calibration time benchmark, continuously monitor the time offset between each device to identify the slight time difference between any two devices, and generate a time offset monitoring result; based on the time offset monitoring result, an adaptive time series calibration algorithm is used to model and predict the time series between each device, compare the model prediction value with the actual monitoring value to analyze the deviation, and generate precise correction parameters; based on the precise correction parameters, considering the device response delay and the stability of the adjustment process, design and generate specific correction instructions, and generate an optimized correction instruction set; based on the optimized correction instruction set, the time benchmark of each device is adjusted in real time to gradually reduce the time deviation between different devices and generate a consistent time benchmark.

[0079] The method uses high-precision timestamp embedding technology based on the consistent time base to add a unique time tag at the microsecond level when each vital sign data point is collected to generate microsecond-level vital sign data points, including: based on the consistent time base, synchronizing and correcting the clocks of each device to ensure that the time of all devices is consistent and generate a synchronous time frame; based on the synchronous time frame, using high-precision timestamp embedding technology to accurately time each vital sign data point at the moment of collection, obtain microsecond-level time information at the current moment, and generate a microsecond-level timestamp; based on the microsecond-level timestamp, firmly associate the timestamp with the corresponding vital sign data point through metadata to generate a timestamp-associated data point; based on the timestamp-associated data point, perform preliminary data sorting and verification to generate microsecond-level vital sign data points.

[0080] In this step, the preliminary calibration of the time reference includes a time standard generated by preliminary adjustment of the current time reference of each device based on the personalized synchronization profile, which is used to reduce the initial time deviation and provide a basis for subsequent more precise time synchronization.

[0081] Time drift monitoring results are data generated by continuously monitoring the minute time differences between any two devices. These data are used to identify and quantify the time deviations between devices, ensuring accurate time synchronization analysis.

[0082] The precise correction parameters are specific parameters generated based on the time offset monitoring results and the adaptive time series calibration algorithm. They are used to make real-time adjustments to the time base of each device and gradually reduce the time deviation between different devices.

[0083] The optimized calibration instruction set is a specific calibration instruction set designed and generated after considering the device response delay and the stability of the adjustment process. These instructions are used to implement precise time calibration to ensure that the time base of all devices is consistent.

[0084] The synchronous time frame is a time frame generated by synchronizing and correcting the clocks of each device, ensuring that all devices have consistent time, providing a basis for the subsequent application of high-precision timestamp embedding technology.

[0085] The microsecond timestamp is the microsecond time information of the current moment obtained after accurately timing each vital sign data point at the moment of collection. This timestamp ensures the time accuracy of each data point.

[0086] Timestamp-associated data points are data structures that firmly associate timestamps with corresponding vital sign data points through metadata. These data points contain precise time information, which facilitates subsequent data processing and analysis.

[0087] Microsecond-level vital sign data points refer to vital sign data points with microsecond-level time stamps, ensuring that each data point has a high degree of time accuracy.

[0088] In the embodiment of the present application, firstly, based on the preliminary calibration time base, the time offset between each device is continuously monitored, the slight time difference between any two devices is identified, the time series between each device is modeled and predicted by an adaptive time series calibration algorithm, the deviation between the model prediction value and the actual monitoring value is analyzed, and the precise correction parameters are generated; secondly, based on the precise correction parameters, considering the device response delay and the stability of the adjustment process, specific correction instructions are designed and generated, the time base of each device is adjusted in real time, the time deviation between different devices is gradually reduced, and a consistent time base is generated; thirdly, based on the consistent time base, the clocks of each device are synchronously corrected to ensure that the time of all devices is consistent, and a high-precision timestamp embedding technology is used to accurately time each vital sign data point at the moment of collection, obtain the microsecond time information of the current moment, and generate a microsecond timestamp; finally, the timestamp is firmly associated with the corresponding vital sign data point by metadata, preliminary data collation and verification are performed, and microsecond vital sign data points are generated.

[0089] Suppose that in a health monitoring system of a smart fitness center, firstly, based on the preliminary calibration time base, the time offset between various sports equipment (such as treadmills, spinning bikes, heart rate belts) connected to the network is continuously monitored, and the slight time difference between any two devices is identified. The time series between each device is modeled and predicted through an adaptive time series calibration algorithm, and the deviation between the model prediction value and the actual monitoring value is analyzed to generate precise correction parameters; secondly, based on the precise correction parameters, considering the device response delay and the stability of the adjustment process, specific correction instructions are designed and generated to adjust the time base of each sports equipment in real time, gradually reduce the time deviation between different devices, and generate consistency. Time base; secondly, based on the consistent time base, the clocks of all sports equipment are synchronized and corrected to ensure the consistency of time of all devices. High-precision timestamp embedding technology is used to accurately time each vital sign data point (such as heart rate, calorie consumption, exercise intensity) at the moment of collection, obtain the microsecond time information of the current moment, and generate a microsecond timestamp; finally, the timestamp is firmly associated with the corresponding vital sign data point through metadata, and the data points associated with the timestamp are preliminarily sorted and verified to generate microsecond vital sign data points, ensuring that the data flow is continuous and orderly with a high degree of time synchronization and accuracy, so as to provide users with detailed exercise reports and health recommendations.

[0090] The present application considers that in the prior art, due to the problem of inconsistent time bases between devices, the timing of vital sign data collection is not uniform, which affects the synchronization and accuracy of multi-source data. Therefore, the embodiment of the invention proposes this optional solution to solve the above technical problems, ensuring that different devices can maintain a highly consistent time base when collecting data, thereby improving the reliability and accuracy of the overall system.

[0091] Optionally, based on the time offset monitoring result, an adaptive time series calibration algorithm is used to model and predict the time series between each device, and the model prediction value is compared with the actual monitoring value to analyze the deviation and generate accurate correction parameters, including:

[0092] Based on the time offset monitoring results, preprocess the time series data between the devices to remove obvious outliers and noise, perform smoothing to reduce high-frequency noise, and determine the main characteristics of the time series through preliminary statistical analysis to generate a predicted time offset;

[0093] The predicted time offset is calculated using the following formula:

[0094]

[0095] in, is the predicted time offset of the i-th time point; t i is the actual timestamp of the i-th time point; αj ,β j ,γ j are the amplitude, frequency, and phase parameters of the jth sine function, where j is the index of the sine function, from 1 to n; δ k ,η k ,ζ k are the amplitude, width and center position parameters of the kth Gaussian function, where k is the index of the Gaussian function, from 1 to m; n is the number of sine functions; m is the number of Gaussian functions;

[0096] Based on the predicted time offset, a comparative analysis is performed with the actual timestamp to obtain the deviation value of each time point, identify the systematic deviation pattern and local fluctuation, and introduce the derivative term of each time point to capture the time series change trend and local characteristics, so as to generate an optimization objective function;

[0097] The optimization objective function is calculated using the following formula:

[0098]

[0099] Among them, E(φ) is the optimization objective function, which is used to minimize the deviation between the predicted value and the actual value and the smoothing term; φ is the parameter set in the optimization process, including λ, ω l ,μ,v p ,ρ,τ q ,ξ,χ r ,ψ r ,θ r ; σ i is the standard deviation of the time offset at the i-th time point; λ is the weight coefficient of the second-order derivative smoothing term; ω l is the weight coefficient of the lth second-order derivative smoothing term, where l ranges from 1 to L; μ is the weight coefficient of the first-order derivative smoothing term; v p is the weight coefficient of the pth first-order derivative smoothing term, where p ranges from 1 to P; ρ is the weight coefficient of the third-order derivative smoothing term; τ q is the weight coefficient of the qth third-order derivative smoothing term, where q ranges from 1 to Q; ξ is the weight coefficient of the nonlinear deviation term; χ r is the weight coefficient of the rth nonlinear bias term, where r ranges from 1 to R; ψ r is the central position parameter of the rth nonlinear deviation term; θ r is the width parameter of the rth nonlinear deviation term; is the second derivative of the predicted time offset; is the first derivative of the predicted time offset; is the third-order derivative of the predicted time offset; N is the total number of time points; L is the number of second-order derivative smoothing terms; P is the number of first-order derivative smoothing terms; Q is the number of third-order derivative smoothing terms; R is the number of nonlinear deviation terms;

[0100] Based on the optimization objective function, the gradient descent method is used to minimize the objective function to obtain the optimal parameter set, which is applied to the time series of each device to ensure that the data acquisition timing is highly consistent and generate accurate correction parameters.

[0101] This method aims to use an adaptive time series calibration algorithm to model and predict the time series between each device, analyze the deviation by comparing the model prediction value with the actual monitoring value, and generate accurate correction parameters. The formula design aims to minimize the deviation between the predicted value and the actual value, while considering the changing trend and local characteristics of the time series to ensure that the corrected data has high accuracy and smoothness.

[0102] In the prediction time offset, the periodic component fitting term It is used to capture the inherent periodic time deviation between devices, so that the model can reflect these periodic change characteristics. By introducing the sine function, it can effectively simulate and correct the periodic drift phenomenon caused by device hardware characteristics or environmental factors, and improve the prediction accuracy; non-periodic local fluctuation fitting term Used to capture sudden time drifts in a short period of time to ensure that the model can adapt to instantaneous changes. The Gaussian function can well describe local fluctuations, especially for those time deviations that suddenly appear but disappear quickly, providing a flexible modeling method and enhancing the model's ability to adapt to complex environments;

[0103] Among them, α j ,β j ,γ j Obtained by extracting the periodic component from the time series through Fourier transform; δ k ,η k ,ζ k Obtained by identifying local features in time series using kernel density estimation methods;

[0104] In the optimization objective function, the squared deviation term Measures the deviation between the predicted value and the actual value to ensure that the model is as close to the actual situation as possible. By minimizing this term, the prediction error can be effectively reduced and the accuracy of the model can be improved. Smoothing the time series curve and reducing overfitting helps prevent the model from following the noise too sensitively, thereby improving the generalization ability of the model and ensuring that its performance on unseen data remains stable; first-order derivative trend term Capture the changing trend of time series and ensure that the model can reflect the overall trend of time series. By introducing the first-order derivative, the model can better adapt to the long-term changes of time series and improve the rationality of prediction; the third-order derivative local characteristic term Capture the local characteristics of the time series to ensure that the model can adapt to the subtle changes in the time series. This item is particularly suitable for processing data with complex dynamic characteristics, making the model more sophisticated and accurate; nonlinear deviation term Handling nonlinear deviations to ensure that the model can capture complex deviation patterns. By introducing nonlinear terms, the model can better adapt to situations that do not meet linear assumptions and improve robustness to abnormal data points.

[0105] Among them, σ i It is obtained by calculating the standard deviation of the time series; λ is obtained by selecting the optimal smoothing coefficient through cross-validation; ω l and v p The main change trends and smoothing term weights are obtained by principal component analysis; μ, ρ, τ q ,ξ,χ r ,ψ r ,θ r Obtained through gradient descent optimization;

[0106] Assume that in a health monitoring system of a smart sports venue, the system collects vital sign data from multiple devices (such as heart rate belts, blood pressure monitors, and respiratory rate sensors) to ensure data synchronization; assume that the total number of time points in the time offset monitoring results is N = 100; the number of sine functions n = 2, and the number of Gaussian functions m = 3; periodic component fitting item parameters: α1 = 0.5, β1 = 0.1, γ1 = π / 4; α2 = 0.3, β2 = 0.05, γ2 = π / 2; non-periodic local fluctuation fitting item parameters: δ1 = 0.2, η1 = 0.05, ζ1 = 50; δ2 = 0.15, η2 = 0.07, ζ2 = 60; δ3 = 0.1, η3 = 0.08, ζ3 = 70; standard deviation σ i =0.01; smoothing coefficient λ = 0.01; main change trend and smoothing term weight ω l =0.1; weight of trend term v p =0.1; local feature weight τ q =0.001; nonlinear bias weight ξ = 0.0001, χ r =0.0001; nonlinear deviation term center position and width parameter ψ r =50,θ r =10;

[0107]

[0108] Assuming the threshold is 3, since the calculated result 2.5 is less than the set threshold, it shows that the corrected data has high time and synchronization accuracy, and the systematic deviation is effectively controlled. Through the above steps, it is ensured that different devices can maintain a highly consistent time base during data collection, improve the synchronization and accuracy of multi-source data, and thus enhance the reliability and accuracy of the entire health monitoring system.

[0109] 103. Based on the vital signs data stream, use a real-time spectrum analysis algorithm to monitor and evaluate the stability of the collected signals of each device, automatically adjust the collection frequency and sampling strategy, adopt environmental adaptive adjustment technology, make real-time adjustments to key parameters based on feedback information, and generate a multi-source vital signs data set;

[0110] In this step, the real-time spectrum analysis algorithm is an algorithm used to monitor and evaluate the stability of the signals collected by each device. The algorithm can detect the noise level and frequency characteristics, identify potential sources of interference (such as periodic noise and other abnormal components), and ensure signal quality.

[0111] The acquisition frequency and sampling strategy are parameters that are automatically adjusted according to the real-time spectrum analysis results, aiming to optimize the data acquisition process and improve data quality and reliability.

[0112] Environmental adaptive adjustment technology is a technology that instantly adjusts key parameters (such as sampling intervals and filter settings) based on feedback information to adapt to environmental changes and ensure data stability and accuracy.

[0113] The multi-source vital signs dataset is a data set generated after the above processing, which contains vital signs data from multiple devices, ensuring the overall stability and consistency of the data.

[0114] In an embodiment of the present application, assuming that in a multi-device monitoring system of a hospital, first, the system performs spectral analysis on the initially collected vital signs data stream to identify the main noise sources and abnormal components; secondly, the collection frequency is automatically adjusted based on the analysis results, from once per second to a more appropriate frequency; thirdly, environmental adaptive adjustment technology is introduced to dynamically adjust the filter parameters according to the current environmental noise level; finally, the adjusted parameters are applied to each device to ensure that the collected data has the highest stability and the lowest noise impact, thereby generating a multi-source vital signs data set.

[0115] Optionally, the method in step 103 is based on the vital signs data stream, uses a real-time spectrum analysis algorithm to monitor and evaluate the stability of the collected signals of each device, automatically adjusts the collection frequency and sampling strategy, uses environmental adaptive adjustment technology, and implements real-time adjustment of key parameters according to feedback information to generate a multi-source vital signs data set, including: based on the vital signs data stream, performing a preliminary quality check, identifying obvious abnormalities and noise, and generating a preliminary signal quality report; based on the preliminary signal quality report, using a real-time spectrum analysis algorithm to perform frequency domain analysis, detect noise levels and frequency characteristics, analyze and search for potential interference sources to determine periodic noise and other abnormal components, and generate a detailed signal quality report; based on the detailed signal quality report, using environmental adaptive adjustment technology, combined with the current working environment noise level and equipment operating status, implement real-time adjustment of key parameters to generate an adaptive adjustment data set; based on the adaptive adjustment data set, integrate the vital signs data of each device and the corresponding timestamp to improve data consistency and generate a multi-source vital signs data set.

[0116] Among them, based on the preliminary signal quality report, the real-time spectrum analysis algorithm is used to perform frequency domain analysis, detect noise levels and frequency characteristics, analyze and search for potential interference sources to determine periodic noise and other abnormal components, and generate a detailed signal quality report, including: based on the preliminary signal quality report, the signal in the vital signs data stream is preprocessed to remove obvious outliers and noise to generate a preprocessed signal; based on the preprocessed signal, the real-time spectrum analysis algorithm is used to perform frequency domain conversion, detect noise levels and frequency characteristics to identify major frequency components, analyze change trends to search for potential interference sources, comprehensively evaluate overall stability, and generate a spectrum analysis report; based on the spectrum analysis report, combined with the preliminary signal quality report, comprehensively evaluate the overall stability of the signal to generate a comprehensive quality report; based on the comprehensive quality report, further refine various key indicators and optimization measures to generate a detailed signal quality report.

[0117] In this step, the preliminary quality check is the first round of quality inspection of the vital signs data stream, which aims to identify obvious outliers and noise and generate a preliminary signal quality report. This step ensures that the data entering the subsequent analysis has a high initial quality.

[0118] The preprocessed signal is the vital sign data after removing obvious outliers and noise, ensuring the accuracy of subsequent spectrum analysis.

[0119] The spectrum analysis report is a detailed report generated based on the preprocessed signal using a real-time spectrum analysis algorithm. It contains information such as noise level, frequency characteristics, and main frequency components, and is used to evaluate the overall stability of the signal.

[0120] The comprehensive quality report combines the preliminary signal quality report and spectrum analysis results to comprehensively evaluate the overall stability of the signal and generate a detailed signal quality assessment.

[0121] The detailed signal quality report is the final report generated, which details the key indicators and optimization measures, provides a comprehensive signal quality analysis, and is used to guide subsequent data adjustments and optimizations.

[0122] Environmental adaptive adjustment technology is a technology that implements real-time adjustment of key parameters according to the current working environment noise level and equipment operating status to ensure signal stability and reliability.

[0123] The adaptive adjustment data set is a data set adjusted by the environmental adaptive adjustment technology to ensure that the vital signs data collected by each device are highly consistent and reliable.

[0124] In an embodiment of the present application, first, a preliminary quality check is performed based on the vital signs data stream, obvious outliers and noise are identified and marked, and the information in the preliminary signal quality report is used to preprocess the signals in the vital signs data stream, remove obvious outliers and noise, and generate a preprocessed signal; secondly, based on the preprocessed signal, a real-time spectrum analysis algorithm is used to perform frequency domain conversion, detect noise levels and frequency characteristics, identify major frequency components, analyze change trends to search for potential interference sources, combine the spectrum analysis report and the preliminary signal quality report, comprehensively evaluate the overall signal stability, refine various key indicators and optimization measures, and generate a detailed signal quality report; thirdly, an environmental adaptive adjustment technology is used, combined with the current working environment noise level and equipment operating status, to implement real-time adjustment of key parameters and generate an adaptive adjustment data set; finally, based on the adaptive adjustment data set, the vital signs data and corresponding timestamps of each device are integrated to improve data consistency, and finally a multi-source vital signs data set is generated.

[0125] Assume that in a health monitoring system of a smart nursing home, firstly, a preliminary quality check is performed based on the vital signs data stream, obvious outliers and noise are identified and marked, and the signals in the vital signs data stream are preprocessed to remove obvious outliers and noise, and generate preprocessed signals; secondly, a real-time spectrum analysis algorithm is used to perform frequency domain conversion, detect noise levels and frequency characteristics, identify major frequency components, analyze change trends to search for potential interference sources, combine spectrum analysis reports and preliminary signal quality reports, comprehensively evaluate the overall stability of the signal, refine various key indicators and optimization measures, and generate a detailed signal quality report; thirdly, based on the detailed signal quality report, the environmental adaptive adjustment technology is used, combined with the current working environment noise level (such as background noise, interference from other electronic devices) and the equipment operating status (such as battery power, connection status), to implement real-time adjustments to key parameters (such as sampling frequency, filter settings), integrate the vital signs data of each device and the corresponding timestamps, and ensure data consistency; finally, through the high-precision timestamp embedding technology, the time synchronization of the data is further improved, and a multi-source vital signs data set is generated, which provides accurate and reliable data support for the health management of the elderly and helps medical staff to detect abnormal situations in a timely manner and take corresponding measures.

[0126] This application takes into account that in a multi-device synchronized vital sign data acquisition system, due to hardware differences and environmental interference between different devices, the collected signals have varying degrees of noise and unstable frequency domain characteristics. This not only affects the quality of the data, but may also lead to erroneous health assessment results. Therefore, this optional solution is proposed to solve these problems and ensure that the data collected by each device has consistent and reliable frequency domain characteristics, thereby improving the accuracy and reliability of the overall system.

[0127] Optionally, based on the preprocessed signal, a real-time spectrum analysis algorithm is used to perform frequency domain conversion, detect noise levels and frequency characteristics to identify major frequency components, analyze change trends to search for potential interference sources, comprehensively evaluate overall stability, and generate a spectrum analysis report, including:

[0128] Based on the preprocessed signal, a window function is used to reduce spectrum leakage, zero padding is performed to increase frequency domain resolution, and a time domain signal is converted into a frequency domain signal by fast Fourier transform to generate a power spectral density;

[0129] The power spectral density is calculated using the following formula:

[0130]

[0131] Where S(f) is the power spectrum density at frequency f; x[n] is the value of the preprocessed signal at the nth sampling point, where n is the index of the sampling point, from 1 to N-1; N is the total number of sampling points of the signal; f is the frequency; α is the weighting coefficient, which is used to balance the influence of frequency domain conversion and time domain noise level; is the average value of the preprocessed signal; j is an imaginary unit, satisfying j 2 = -1;

[0132] Based on the power spectrum density, the frequency domain data is statistically analyzed to obtain the statistical characteristics of each frequency point to identify the main frequency components and noise levels, and the first-order and second-order derivatives of the power spectrum density are introduced to capture the frequency change trend and local characteristics to generate a spectrum analysis function;

[0133] The spectrum analysis function is calculated using the following formula:

[0134]

[0135] F(ψ) is the spectrum analysis function, which is used to comprehensively evaluate the overall stability of the spectrum and identify potential interference sources; S(f) is the power spectrum density at frequency f; ψ is the set of parameters in the analysis process, including λ, ω k ,μ,ν m ,ρ,τ p ,ψ p ,θ p ; is the average value of the power spectral density; σ S is the standard deviation of the power spectrum density; λ is the weight coefficient of the second-order derivative smoothing term; ω k is the weight coefficient of the kth second-order derivative smoothing term, where k is the index of the second-order derivative smoothing term, from 1 to K; μ is the weight coefficient of the first-order derivative smoothing term; ν m is the weight coefficient of the mth first-order derivative smoothing term, where m is the index of the first-order derivative smoothing term, from 1 to M; ρ is the weight coefficient of the nonlinear deviation term; τ p is the weight coefficient of the pth nonlinear bias term, where p is the index of the nonlinear bias term, from 1 to P; ψ p is the center frequency of the pth nonlinear deviation term; θ p is the width parameter of the pth nonlinear deviation term; is the predicted power spectral density; is the standard deviation of the predicted power spectral density; F is the total number of frequency points in the frequency range, from 1 to F; K is the number of second-order derivative smoothing terms; M is the number of first-order derivative smoothing terms; P is the number of nonlinear deviation terms; is the second-order derivative of the power spectral density with respect to frequency f; is the first-order derivative of the power spectral density with respect to frequency f;

[0136] Based on the spectrum analysis function, peak detection is implemented to identify significant frequency components, background noise is eliminated by setting thresholds, and sub-band division is performed through frequency band division technology to perform statistical analysis on energy distribution characteristics, evaluate energy concentration and dispersion, and generate a spectrum analysis report.

[0137] This method aims to use a real-time spectrum analysis algorithm to perform frequency domain conversion on the preprocessed signal, identify the main frequency components by detecting the noise level and frequency characteristics, and comprehensively evaluate the overall stability to generate a spectrum analysis report. The formula design aims to accurately calculate the power spectral density and evaluate the overall stability of the spectrum, identify potential interference sources, and ensure that the corrected data has high accuracy and smoothness.

[0138] In the power spectral density, the frequency domain conversion term This sub-item is used to convert the time domain signal into the frequency domain signal and capture the frequency components of the signal. Through the fast Fourier transform (FFT), the complex time domain waveform can be effectively decomposed into a superposition of a series of sine and cosine waves, thereby revealing the periodic and non-periodic components hidden in the signal; Time domain noise level balance item This sub-item is used to balance the impact of frequency domain conversion and time domain noise level. By introducing this item, the impact of time domain noise can be considered while calculating frequency domain features, so that the model can reflect the real frequency domain features and appropriately consider the impact of noise, thereby improving the robustness and generalization ability of the model;

[0139] Where x[n] is the value of the preprocessed signal at the nth sampling point, which is extracted from the original data; N is the total number of sampling points of the signal, which is determined according to the actual data length; f is the frequency, which is determined by the frequency domain conversion process; α is obtained by selecting the optimal smoothing coefficient through cross-validation; is the average value of the preprocessed signal, which is obtained by calculating the average value of all sampling points;

[0140] In the spectrum analysis function, the squared deviation term This sub-item measures the deviation between the power spectrum density and the average value, ensuring that the model is as close to the actual situation as possible. By minimizing this item, the prediction error can be effectively reduced and the accuracy of the model can be improved; the second-order derivative smoothing term This sub-item is used to smooth the frequency domain curve and reduce overfitting. By introducing the second-order derivative smoothing term, the impact of high-frequency noise on the model can be reduced while maintaining the signal characteristics, thereby improving the generalization ability of the model. This sub-item is used to capture the frequency change trend and ensure that the model can reflect the overall trend of the frequency domain. By introducing the first-order derivative, the model can better adapt to the long-term changes of the time series and improve the rationality of the prediction; nonlinear deviation term This sub-item is used to handle nonlinear deviations and ensure that the model can capture complex deviation patterns. By introducing an exponential decay factor, the model can adapt to local features more flexibly and improve the robustness to abnormal data points.

[0141] in, is the average value of the power spectrum density, obtained by calculating the average value of all frequency points; σ S is the standard deviation of the power spectrum density, obtained by calculating the standard deviation of all frequency points; λ,ω k ,μ,v m ,ρ,τ p ,ψ p ,θ p Obtained through gradient descent optimization; is the predicted power spectral density, obtained through model prediction; The standard deviation of the predicted power spectral density is obtained by calculating the standard deviation of the predicted values;

[0142] Assume that in a remote monitoring system of a smart hospital ward, it is necessary to ensure that different devices can maintain stable frequency domain characteristics during data acquisition; assume that the total number of time points N = 1024; the weighting coefficient α = 0.05; the total number of frequency points in the frequency range F = 512; the number of second-order derivative smoothing terms K = 3; the number of first-order derivative smoothing terms M = 2; the number of nonlinear deviation terms P = 2; the window function uses the Hanning window; the smoothing coefficient λ = 0.01; the main change trend and smoothing term weight ω k =0.1; weight of trend term v m =0.1; nonlinear bias weight ρ = 0.001; center frequency ψ p =[10,20]; width parameter θ p =[5,10]; noise level threshold

[0143]

[0144] Assuming the threshold is 20, since the calculated result 15.2 is less than the set threshold, it shows that the corrected spectrum has high stability and reliability, and the noise level is effectively controlled. Through the above steps, it is ensured that different devices can maintain stable frequency domain characteristics during data acquisition, improve the reliability and accuracy of multi-source data, and thus enhance the reliability and accuracy of the entire health monitoring system.

[0145] 104. Based on the multi-source vital sign data set, combined with corresponding timestamps, integrated into a unified data format, a standardized vital sign data report is generated.

[0146] In this step, the timestamp is a unique time mark in each vital sign data point, ensuring the time accuracy of the data point.

[0147] The unified data format is a predefined standard format that ensures that data from different sources can be seamlessly integrated, facilitating subsequent data processing and analysis.

[0148] The standardized vital signs data report is the final report generated after the above processing, which contains structured data (such as numerical vital signs readings), statistical summaries (such as average, maximum, minimum) and visual charts (such as trend charts, spectrum charts), providing medical personnel with a comprehensive reference basis and supporting efficient clinical decision-making and health management.

[0149] In an embodiment of the present application, it is assumed that in a remote medical diagnosis system, first, the system integrates all multi-source vital signs data with timestamps into a unified data platform; second, the data is cleaned and converted according to a predefined unified data format to remove inconsistent or erroneous data points; third, a standardized vital signs data report containing structured data, statistical summaries, and visual charts is generated; finally, the report is transmitted to medical personnel through a secure channel to support remote diagnosis and the formulation of personalized health recommendations.

[0150] Optionally, the step 104 is based on the multi-source vital signs data set, combined with corresponding timestamps, integrated into a unified data format to generate a standardized vital signs data report, including: based on the multi-source vital signs data set, preliminary sorting of data from different devices to ensure that the timestamp of each data point is accurate, and generating a time calibration data set; based on the time calibration data set, performing data format conversion and standardization processing to unify into a standard data format, and generating a format standardized data set; based on the format standardized data set, performing data cleaning and outlier detection processing to remove inconsistent and erroneous data points, and generating a purified data set; based on the purified data set, combined with corresponding timestamps, introducing visualization charts to visualize the results, and generating a standardized vital signs data report.

[0151] In this step, the time calibration data set is a data set that has been initially sorted to ensure that the timestamp of each data point is accurate. This step solves the problem of slight time differences that may exist between different devices and improves data consistency.

[0152] The format standardized data set is a data set generated through data format conversion and standardization. All data are unified into a standard data format. This step ensures that data from different sources can be seamlessly integrated, facilitating subsequent data processing and analysis.

[0153] The purified data set is a data set generated after data cleaning and outlier detection processing, removing inconsistent and erroneous data points. This step improves the quality and reliability of the data and ensures the accuracy of subsequent analysis.

[0154] Visual charts are charts generated by introducing visualization tools, such as trend charts, spectrum charts, etc., which are used to intuitively display the changing trends and characteristics of vital signs data. These charts help users understand the data more clearly and support efficient decision-making.

[0155] In this step, first, based on the multi-source vital signs dataset, the data from different devices are preliminarily sorted to ensure that the timestamp of each data point is accurate and generate a time-calibrated dataset; secondly, based on the time-calibrated dataset, data format conversion and standardization are performed to unify all data into a standard data format to generate a format-standardized dataset; thirdly, based on the format-standardized dataset, data cleaning and outlier detection are performed to remove inconsistent and erroneous data points to generate a purified dataset; finally, based on the purified dataset, combined with the corresponding timestamps, visual charts are introduced to visualize the results and generate a standardized vital signs data report.

[0156] Assume that in a large enterprise employee health management platform, first, the system collects vital signs data from devices such as smart health bracelets, desktop heart rate monitors, and automatic blood pressure monitors distributed in different office locations within the enterprise, and performs preliminary sorting to ensure that the timestamp of each data point is accurate, and generates a time-calibrated data set; secondly, the system converts the data in the time-calibrated data set into a unified standard format, such as JSON or CSV format, to generate a format-standardized data set; thirdly, the system cleans the format-standardized data set, identifies and removes outliers and duplicate data points, and generates a purified data set; finally, the system uses the purified data set to generate standardized vital signs data reports containing trend charts, spectrum charts, and other visual charts, providing comprehensive data support for the enterprise health management team, helping them monitor the health of employees, develop personalized health promotion plans, and promptly detect and respond to potential health risks.

[0157] In summary, steps 101 to 104 cover the complete process from preprocessing of multi-source vital signs data to generating standardized vital signs data reports, aiming to provide an efficient, accurate and reliable data processing framework to meet the strict requirements of multi-device synchronized vital signs data acquisition systems for data consistency, stability and accuracy.

[0158] Figure 2 A structural diagram of a vital sign data acquisition system supporting multi-device synchronization is provided for an embodiment of the present application. Figure 2 As shown, the device comprises:

[0159] The acquisition module 21 is used to acquire the patient's vital signs data and various key event data through multiple types of acquisition devices, and generate a personalized synchronization configuration file;

[0160] The optimization module 22 is used to dynamically adjust and optimize the time base of each device based on the personalized synchronization configuration file by using an adaptive time series calibration algorithm to ensure that the data acquisition timing is highly consistent, and to add microsecond time stamps to all vital sign data points by using high-precision timestamp embedding technology to generate a vital sign data stream;

[0161] The monitoring module 23 is used to monitor and evaluate the stability of the collected signals of each device based on the vital sign data stream using a real-time spectrum analysis algorithm, automatically adjust the collection frequency and sampling strategy, and use environmental adaptive adjustment technology to make real-time adjustments to key parameters based on feedback information to generate a multi-source vital sign data set;

[0162] The generating module 24 is used to generate a standardized vital sign data report based on the multi-source vital sign data set combined with corresponding timestamps and integrated into a unified data format.

[0163] Figure 2 The vital sign data acquisition system supporting multi-device synchronization can be executed Figure 1 The implementation principle and technical effect of the method for collecting vital sign data supporting multi-device synchronization described in the embodiment shown are not described in detail. The specific manner in which each module and unit performs operations in the vital sign data collection system supporting multi-device synchronization in the above embodiment has been described in detail in the embodiment of the method, and will not be described in detail here.

[0164] In one possible design, Figure 2 A vital sign data collection system supporting multi-device synchronization in the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0165] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0166] The processing component 32 is used to: obtain the patient's vital signs data and various key event data through multiple types of acquisition devices, and generate a personalized synchronization configuration file; based on the personalized synchronization configuration file, use an adaptive time series calibration algorithm to dynamically adjust and optimize the time base of each device to ensure that the data acquisition timing is highly consistent, use high-precision timestamp embedding technology to add microsecond time tags to all vital signs data points, and generate a vital signs data stream; based on the vital signs data stream, use a real-time spectrum analysis algorithm to monitor and evaluate the stability of the acquisition signal of each device, automatically adjust the acquisition frequency and sampling strategy, use environmental adaptive adjustment technology, and implement real-time adjustment of key parameters based on feedback information to generate a multi-source vital signs data set; based on the multi-source vital signs data set, combine the corresponding timestamps, integrate them into a unified data format, and generate a standardized vital signs data report.

[0167] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0168] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0169] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0170] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0171] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0172] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0173] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The illustrated embodiment provides a method for collecting vital sign data that supports synchronization of multiple devices.

[0174] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0175] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0176] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0177] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for collecting vital sign data supporting multi-device synchronization, characterized in that: include: Through multiple types of collection devices, the patient's vital signs data and various key event data are obtained to generate personalized synchronization configuration files; Based on the personalized synchronization configuration file, the adaptive time series calibration algorithm is used to dynamically adjust and optimize the time base of each device to ensure that the data collection timing is highly consistent. The high-precision timestamp embedding technology is used to add microsecond time tags to all vital sign data points to generate a vital sign data stream; Based on the vital signs data stream, a real-time spectrum analysis algorithm is used to monitor and evaluate the stability of the collected signals of each device, automatically adjust the collection frequency and sampling strategy, and adopt environmental adaptive adjustment technology to make real-time adjustments to key parameters based on feedback information to generate a multi-source vital signs data set; Based on the multi-source vital sign data set, combined with corresponding timestamps, it is integrated into a unified data format to generate a standardized vital sign data report.

2. The method according to claim 1, characterized in that Based on the personalized synchronization configuration file, the adaptive time series calibration algorithm is used to dynamically adjust and optimize the time base of each device to ensure that the data collection timing is highly consistent. The high-precision timestamp embedding technology is used to add microsecond time tags to all vital sign data points to generate a vital sign data stream, including: Based on the personalized synchronization configuration file, a preliminary correction process is performed on the current time reference of each device to reduce the initial time deviation and generate a preliminary calibration time reference; Based on the preliminary calibration time base, an adaptive time series calibration algorithm is used to continuously monitor and analyze the time offset between devices, and dynamic adjustment and optimization are implemented to ensure that the data collection timing is highly consistent and generate a consistent time base; Based on the consistent time reference, a high-precision timestamp embedding technology is used to add a microsecond-level unique time tag when each vital sign data point is collected, thereby generating a microsecond-level vital sign data point; Based on the microsecond-level vital sign data points, sorting and integration processing are performed to ensure that the data flow is continuous and orderly, thereby generating a vital sign data stream.

3. The method according to claim 2, characterized in that Based on the preliminary calibration time base, the adaptive time series calibration algorithm is used to continuously monitor and analyze the time offset between the devices, implement dynamic adjustment and optimization, ensure that the data collection timing is highly consistent, and generate a consistent time base, including: Based on the preliminary calibration time reference, continuously monitor the time offset between each device to identify a small time difference between any two devices and generate a time offset monitoring result; Based on the time offset monitoring results, an adaptive time series calibration algorithm is used to model and predict the time series between the devices, and the model prediction value is compared with the actual monitoring value to analyze the deviation and generate accurate correction parameters; Based on the precise correction parameters, considering the equipment response delay and the stability of the adjustment process, designing and generating specific correction instructions, and generating an optimized correction instruction set; Based on the optimized correction instruction set, the time base of each device is adjusted in real time, the time deviation between different devices is gradually reduced, and a consistent time base is generated.

4. The method according to claim 2, characterized in that: The method uses a high-precision timestamp embedding technology based on the consistent time reference to add a microsecond-level unique time tag when each vital sign data point is collected to generate a microsecond-level vital sign data point, including: Based on the consistent time reference, the clocks of each device are synchronized and corrected to ensure that the time of all devices is consistent and generate a synchronized time frame; Based on the synchronous time frame, a high-precision timestamp embedding technology is used to accurately time each vital sign data point at the moment of collection, obtain microsecond time information at the current moment, and generate a microsecond timestamp; Based on the microsecond timestamp, the timestamp is firmly associated with the corresponding vital sign data point by metadata to generate a timestamp associated data point; Based on the timestamp-associated data points, preliminary data collation and verification are performed to generate microsecond-level vital sign data points.

5. The method according to claim 1, characterized in that: Based on the vital signs data stream, a real-time spectrum analysis algorithm is used to monitor and evaluate the stability of the collected signals of each device, automatically adjust the collection frequency and sampling strategy, adopt environmental adaptive adjustment technology, and make real-time adjustments to key parameters according to feedback information to generate a multi-source vital signs data set, including: Based on the vital sign data stream, perform a preliminary quality check to identify obvious anomalies and noise, and generate a preliminary signal quality report; Based on the preliminary signal quality report, use a real-time spectrum analysis algorithm to perform frequency domain analysis, detect noise levels and frequency characteristics, analyze and search for potential interference sources to determine periodic noise and other abnormal components, and generate a detailed signal quality report; Based on the detailed signal quality report, an environmental adaptive adjustment technology is used to adjust key parameters in real time in combination with the current working environment noise level and the equipment operation status to generate an adaptive adjustment data set; Based on the adaptive adjustment data set, the vital sign data of each device and the corresponding timestamp are integrated to improve data consistency and generate a multi-source vital sign data set.

6. The method according to claim 5, characterized in that Based on the preliminary signal quality report, a real-time spectrum analysis algorithm is used to perform frequency domain analysis, detect noise levels and frequency characteristics, analyze and search for potential interference sources, determine periodic noise and other abnormal components, and generate a detailed signal quality report, including: Based on the preliminary signal quality report, preprocess the signal in the vital sign data stream to remove obvious outliers and noise to generate a preprocessed signal; Based on the preprocessed signal, a real-time spectrum analysis algorithm is used to perform frequency domain conversion, detect noise levels and frequency characteristics to identify major frequency components, analyze change trends to search for potential interference sources, comprehensively evaluate overall stability, and generate a spectrum analysis report; Based on the spectrum analysis report and in combination with the preliminary signal quality report, comprehensively evaluate the overall signal stability and generate a comprehensive quality report; Based on the comprehensive quality report, various key indicators and optimization measures are further refined to generate a detailed signal quality report.

7. The method according to claim 1, characterized in that The method of generating a standardized vital sign data report based on the multi-source vital sign data set, combined with corresponding timestamps, and integrated into a unified data format includes: Based on the multi-source vital sign data set, data from different devices are preliminarily sorted to ensure that the timestamp of each data point is accurate, and a time-calibrated data set is generated; Based on the time calibration data set, data format conversion and standardization processing are performed to unify the data into a standard data format, thereby generating a format standardized data set; Based on the standardized data set in the format, data cleaning and outlier detection processing are performed to remove inconsistent and erroneous data points to generate a purified data set; Based on the purified data set and in combination with corresponding timestamps, a visualization chart is introduced to visualize the results and generate a standardized vital sign data report.

8. A vital sign data collection system supporting multi-device synchronization, characterized in that: include: The collection module is used to obtain the patient's vital signs data and various key event data through multiple types of collection devices, and generate personalized synchronization configuration files; An optimization module is used to dynamically adjust and optimize the time base of each device based on the personalized synchronization configuration file by using an adaptive time series calibration algorithm to ensure that the data acquisition timing is highly consistent, and to add microsecond time stamps to all vital sign data points by using high-precision timestamp embedding technology to generate a vital sign data stream; A monitoring module is used to monitor and evaluate the stability of the collected signals of each device based on the vital signs data stream, use a real-time spectrum analysis algorithm, automatically adjust the collection frequency and sampling strategy, adopt environmental adaptive adjustment technology, make real-time adjustments to key parameters according to feedback information, and generate a multi-source vital signs data set; A generation module is used to generate a standardized vital sign data report based on the multi-source vital sign data set, combined with corresponding timestamps, integrated into a unified data format.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a vital sign data collection method supporting multi-device synchronization as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, a vital sign data collection method supporting multi-device synchronization as described in any one of claims 1 to 7 is implemented.

Images