Monitoring method, device, equipment and medium based on skin impedance and exercise volume

Abstract

The present invention relates to the field of health monitoring technology, specifically to a monitoring method, device, equipment and medium based on skin impedance and exercise volume, wherein the method is as follows: real-time acquisition of user skin impedance and exercise volume data, and conversion into a data sequence; setting an initial sliding window, including a first window for monitoring skin impedance and a second window for monitoring exercise volume; acquiring newly added data points and change characteristics in the data sequence, assigning weights, and adjusting the window size; dividing the data sequence into multiple time segments according to the time series, assigning weight values, and adjusting the window position; based on the adjusted position and size, re-sliding the window to obtain the data distribution. Calculate the correlation index between skin impedance and exercise volume, and evaluate the user's health status. The present application achieves accurate monitoring and evaluation of the user's health status by acquiring and analyzing skin impedance and exercise volume data in real time, combined with dynamically adjusted sliding window technology.

Description

Technical Field

[0001] The present invention relates to the technical field of health monitoring, and in particular to a monitoring method, device, equipment and medium based on skin impedance and exercise volume. Background Art

[0002] Existing health monitoring technologies still have some shortcomings. Specifically, most current health monitoring devices and methods rely mainly on a single physiological parameter for health assessment, such as heart rate, blood pressure, etc. However, human health is a complex and multidimensional system, and monitoring of a single physiological parameter often cannot fully reflect a person's health status.

[0003] In order to solve the above problems, the prior art has taken some measures. For example, the public document CN108784671A discloses a wearable body surface physiological and biochemical parameter monitoring system: "Monitoring wristband, control tag and intelligent terminal. The present invention obtains the subject's motion posture information and exercise time to calculate the energy consumption and exercise intensity of the exercise process, obtains the subject's skin temperature, the ambient temperature of the environment and the pulse count information, obtains the subject's bioelectrical impedance information, the electrical signal of electrolytes, the electrical signal of glucose, and the electrical signal of lactic acid, and then determines the subject's degree of dehydration, fatigue and health through comprehensive analysis of the motion parameter model, and gives rest, medical treatment or first aid advice and understands the health status." It can be seen from the above public documents that although the prior art has achieved monitoring of the wearer's health status to a certain extent, it is only by simply monitoring and analyzing multiple physiological parameters, and cannot achieve dynamic tracking of individual health status, resulting in limitations in the accuracy and reliability of health monitoring, and thus cannot provide more accurate and personalized health advice. Summary of the invention

[0004] The main purpose of the present invention is to provide a monitoring method, device, equipment and medium based on skin impedance and exercise volume, aiming to overcome the technical problem that the prior art cannot accurately and dynamically monitor health conditions.

[0005] In order to achieve the above-mentioned invention problem, the present invention proposes a monitoring method based on skin impedance and exercise amount, the method comprising:

[0006] Acquire the user's skin impedance data and exercise data in real time, and convert the skin impedance data and exercise data into a data sequence in real time;

[0007] Setting an initial sliding window, wherein the initial sliding window includes a first sliding window and a second sliding window, the first sliding window is used to monitor the skin impedance data, and the second sliding window is used to monitor the exercise volume data;

[0008] Acquire a change feature between a newly added data point and an initial data point in the data sequence, assign a corresponding weight to the change feature between the newly added data point and the initial data point, and adjust the sizes of the first sliding window and the second sliding window based on the weight;

[0009] Acquire a time series included in the data series, divide the data series according to the time series to obtain a plurality of time segments, assign corresponding weight values ​​to the plurality of time segments, and adjust positions of the first sliding window and the second sliding window respectively according to the weight values;

[0010] The first sliding window and the second sliding window are re-slid on the data sequence based on the adjusted position as the starting point and the adjusted size as the number of window bits to obtain the distribution of the skin impedance data and the exercise amount data on the data sequence;

[0011] A correlation index between skin impedance and exercise volume is calculated based on the distribution, and the user's health status is evaluated based on the correlation index.

[0012] Furthermore, the step of acquiring the user's skin impedance data and exercise volume data in real time and converting the skin impedance data and exercise volume data into a data sequence in real time includes:

[0013] Collect the user's skin impedance data and exercise data in real time based on sensors;

[0014] Based on the local Hough algorithm, the collected skin impedance data and motion data are filtered and denoised in real time;

[0015] The skin impedance data and exercise volume data after filtering and noise reduction are sorted in chronological order to form a continuous data sequence, wherein each data point contains information of the skin impedance data and exercise volume data.

[0016] Furthermore, the step of setting an initial sliding window includes:

[0017] Setting a preset number of bits as the size of the initial sliding window;

[0018] According to the preset number of bits, two sliding windows of equal length are set on the data sequence, which serve as a first sliding window and a second sliding window respectively;

[0019] Initialize the positions of the first sliding window and the second sliding window to cover the beginning part of the data sequence.

[0020] Furthermore, the step of obtaining the change characteristics between the newly added data points and the initial data points in the data sequence, assigning corresponding weights to the change characteristics between the newly added data points and the initial data points, and adjusting the sizes of the first sliding window and the second sliding window based on the weights includes:

[0021] Calculating the rate of change between the newly added data point and the initial data point based on the difference between the newly added data point and the initial data point in the data sequence;

[0022] Assigning a weight value according to the change rate, wherein the weight value is inversely proportional to the magnitude of the change rate;

[0023] Based on the weight value, adjusting the sizes of the first sliding window and the second sliding window, so that in the area with a larger change rate, the size of the sliding window is reduced, and in the area with a smaller change rate, the size of the sliding window is increased;

[0024] The calculation expression is: ,in, is the size of the sliding window at time t, and Respectively represent the change rate of skin impedance data and exercise volume data at time t, and It is a preset weight coefficient used to balance the contribution of skin impedance data and motion data when adjusting the sliding window size.

[0025] Further, the step of obtaining a time series included in the data series, dividing the data series according to the time series to obtain a plurality of time segments, assigning corresponding weight values ​​to the plurality of time segments, and adjusting the positions of the first sliding window and the second sliding window respectively according to the weight values ​​includes:

[0026] Extracting the timestamp corresponding to each data point in the data sequence to form a time series;

[0027] Dividing the time series into a plurality of time segments according to a preset time interval;

[0028] Assigning corresponding weight values ​​to the plurality of time segments, and adjusting the positions of the first sliding window and the second sliding window respectively according to the weight values ​​based on a preset algorithm;

[0029] Wherein, the expression of the preset algorithm is: ,in, Represents the probability distribution of the sliding window position y given the time series x, Represents from position Transfer to location When The weight value of the time point, T is the total length of the time series, and paths represents all possible sliding window position paths. Represents all possible sliding window position combinations.

[0030] Furthermore, the step of re-sliding the first sliding window and the second sliding window on the data sequence based on the adjusted positions as the starting points and the adjusted sizes as the window bits to obtain the distribution of the skin impedance data and the exercise amount data on the data sequence includes:

[0031] Re-determining the starting point and the ending point of the first sliding window and the second sliding window on the data sequence according to the adjusted position and size;

[0032] Slide on the data sequence according to the new starting point and ending point to obtain the skin impedance data and exercise volume data within the window;

[0033] Statistical features of the skin impedance data and exercise volume data within a calculation window are obtained to obtain distribution of the skin impedance data and exercise volume data on the data sequence, wherein the statistical features at least include a mean value, a standard deviation, a median, a maximum value, and a minimum value.

[0034] Furthermore, the step of calculating a correlation index between skin impedance and exercise amount according to the distribution, and evaluating the user's health condition according to the correlation index includes:

[0035] Calculate the linear correlation between the skin impedance data and the exercise volume data, wherein the linear correlation value is between -1 and 1, the closer the absolute value is to 1, the stronger the correlation is, and the sign indicates positive correlation or negative correlation;

[0036] Dividing the linear correlation degree value into different intervals based on multiple preset thresholds;

[0037] The user's health status is evaluated according to the health status evaluation standards corresponding to the different intervals, wherein each interval corresponds to a health status, and the health status at least includes normal, good and abnormal.

[0038] The present invention also provides a monitoring device based on skin impedance and exercise amount, comprising:

[0039] A first acquisition module is used to acquire the user's skin impedance data and exercise volume data in real time, and convert the skin impedance data and exercise volume data into a data sequence in real time;

[0040] A setting module, used to set an initial sliding window, wherein the initial sliding window includes a first sliding window and a second sliding window, the first sliding window is used to monitor the skin impedance data, and the second sliding window is used to monitor the exercise volume data;

[0041] A first adjustment module is used to obtain the change characteristics between the newly added data points and the initial data points in the data sequence, assign corresponding weights to the change characteristics between the newly added data points and the initial data points, and adjust the sizes of the first sliding window and the second sliding window based on the weights;

[0042] a second adjustment module, configured to obtain a time series included in the data series, divide the data series according to the time series to obtain a plurality of time segments, assign corresponding weight values ​​to the plurality of time segments, and adjust positions of the first sliding window and the second sliding window respectively according to the weight values;

[0043] A second acquisition module is used to slide the first sliding window and the second sliding window again on the data sequence based on the adjusted position as a starting point and the adjusted size as the number of window bits, so as to obtain the distribution of the skin impedance data and the exercise amount data on the data sequence;

[0044] The evaluation module is used to calculate the correlation index between skin impedance and exercise amount according to the distribution, and evaluate the user's health status according to the correlation index.

[0045] The present invention further provides a computer device, which includes a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above method when executing the computer program.

[0046] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the above method is implemented.

[0047] Beneficial effects:

[0048] The monitoring method based on skin impedance and exercise volume proposed in this application first obtains the user's skin impedance data and exercise volume data in real time, and converts these data into a data sequence, which can reflect the user's physiological state in many aspects; by setting the initial sliding window, adjusting the size of the window according to the data change characteristics, and adjusting the position of the window according to the time series, the efficiency and response speed of monitoring are improved, so that health monitoring is no longer limited to data collection under specific time periods or environmental conditions, but can continuously track and analyze the changes in the user's physiological state, realize dynamic tracking of the user's health status, more accurately capture the user's health changes, and improve the accuracy and reliability of health monitoring. In addition, by re-sliding the first sliding window and the second sliding window on the data sequence based on the adjusted position and size, the distribution of skin impedance data and exercise volume data on the data sequence is obtained, which can more intuitively show the changing trend of the user's health status. Finally, the user's health status is evaluated based on the correlation index between skin impedance and exercise volume, which can provide users with more accurate and personalized health advice.

[0049] In summary, the monitoring method based on skin impedance and exercise volume of the present invention, by real-time acquisition and analysis of skin impedance and exercise volume data, and combined with dynamically adjusted sliding window technology, realizes accurate monitoring and evaluation of the user's health status, providing users with a more comprehensive and personalized health monitoring experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a schematic diagram of the steps of a monitoring method based on skin impedance and exercise volume in one embodiment of the present invention;

[0051] Figure 2 It is a schematic block diagram of the structure of a monitoring device based on skin impedance and exercise amount according to an embodiment of the present invention;

[0052] Figure 3 is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention;

[0053] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0055] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "one", "above", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present invention refers to the presence of features, integers, steps, operations, elements, modules, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, modules, components, and / or groups thereof. It should be understood that when an element is said to be "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any module and all combinations of one or more associated listed items.

[0056] Those skilled in the art will understand that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art in the field to which the present invention belongs. It should also be understood that terms such as those defined in common dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined as here.

[0057] Reference Figure 1 The embodiment of the present invention provides a monitoring method based on skin impedance and exercise volume, comprising the following steps:

[0058] S1: Acquire the user's skin impedance data and exercise volume data in real time, and convert the skin impedance data and exercise volume data into a data sequence in real time;

[0059] In step S1, the skin impedance can preferably be measured by a bioimpedance sensor, which can detect tiny current changes on the skin, thereby inferring the resistance of the skin. The motion data can be obtained by an accelerometer, a gyroscope or other motion sensors, which can measure the user's motion state, posture and activity intensity. Preferably, the above sensor can be integrated into a device, which can be a handheld device, a wearable device or a smart textile embedded in clothing. For skin impedance data, it can be collected at a high frequency to capture subtle resistance changes, such as dozens of times per second. For motion data, the collection frequency can be adjusted according to the application scenario to balance the relationship between data volume and battery life, and the above data is pre-processed including filtering, removing motion artifacts, correcting sensor deviations, etc. For example, skin impedance data may be affected by poor electrode contact or skin color differences, and signal processing methods such as interpolation are performed to eliminate these effects. After acquiring and pre-processing the data, the skin impedance data and the motion data are converted into a unified data sequence format, and the data is preferably standardized into a consistent time series to ensure that the data is aligned at the same time point and has the same time resolution. For example, all data samples are converted to millisecond-level timestamps and interpolated or truncated according to the preset data collection interval.

[0060] S2: setting an initial sliding window, wherein the initial sliding window includes a first sliding window and a second sliding window, the first sliding window is used to monitor the skin impedance data, and the second sliding window is used to monitor the exercise volume data;

[0061] In step S2, the size and position of the initial sliding window are set according to preset rules and conditions. For example, a window with a fixed length of N can be selected and moved in sequence in the data sequence, one or more data points are moved each time, and N is a positive integer; for the first sliding window, its main function is to monitor the skin impedance data, which is an important indicator reflecting the conductivity of human skin. By monitoring this data, the moisture content of human skin, blood circulation and other information can be understood, thereby inferring the health status of the human body. Therefore, when setting the first sliding window, it is set based on the characteristics of the skin impedance data, such as the fluctuation range and change speed of the data, so as to ensure that the window can accurately capture the change trend of the skin impedance data; for the second sliding window, its function is to monitor the exercise data, which can reflect the intensity and frequency of human activities and is an important basis for evaluating the health status of the human body and the effect of exercise. When setting the second sliding window, it is set based on the characteristics of the exercise data, such as the continuity and periodicity of the data, so that the window can effectively capture the change characteristics of the exercise data.

[0062] In a specific embodiment, for the first sliding window, it can be set to a window with a length of 7 data points, which moves sequentially in the skin impedance data sequence, moving one data point each time. The sliding window is [255 255 256 256257 257 258], and then moves to [256 256 257 257 258 258 259], and so on. Such a setting can capture short-term changes in skin impedance data while avoiding the impact of excessive data fluctuations on monitoring results. For the second sliding window, it can be set to a window with a length of 10 data points, which moves in sequence in the motion data sequence, two data points each time, and the sliding window is [120 125 130 135 140 145 150 155 160 165], and then moves to [125 130 135 140 145 150 155 160 165 170], and so on. Such a setting can capture the long-term trend of the motion data, while taking into account the continuity and periodicity of human motion, and improving the accuracy of monitoring. It is worth noting that the above windows are examples. The specific units of the first sliding window can be ohms or millivolts, and the specific units of the second sliding window can be steps, distance or heart rate, etc. The specific values ​​and units should be determined according to the actual application scenario and sensor type, depending on the specific units and value ranges of skin impedance and motion in the actual measurement.

[0063] S3: Obtaining change features between the newly added data points and the initial data points in the data sequence, assigning corresponding weights to the change features between the newly added data points and the initial data points, and adjusting the sizes of the first sliding window and the second sliding window based on the weights;

[0064] In step S3, the above steps have preliminarily determined the size and position of the sliding window, but in order to more accurately capture the changes in skin impedance data and exercise data, it is necessary to dynamically adjust the size of the sliding window according to the change characteristics between the newly added data points and the initial data points. First, analyze the difference between the newly added data points and the initial data points, as well as the change trend of these differences over time. For skin impedance data, if the difference is large or the change trend is obvious, it means that the skin state has changed significantly. At this time, it is necessary to reduce the first sliding window to capture these changes more finely. On the contrary, if the difference is small or the change trend is stable, the first sliding window can be appropriately increased to reduce the impact of data noise. For exercise data, if the newly added data points show a sudden increase or decrease in activity intensity, it may indicate that the user is doing strenuous exercise or resting. At this time, the second sliding window should be reduced to more accurately reflect these changes. In the period when the activity is relatively stable, the second sliding window can be expanded to smooth data fluctuations. In order to determine the adjustment range of the sliding window, corresponding weights can be assigned to the change characteristics. The weight can be determined based on the size and duration of the change characteristics, as well as similar patterns in historical data. For example, if a sudden change in skin impedance lasts for a period of time, the weight of this change feature should be higher, resulting in a larger adjustment of the sliding window. Similarly, if the exercise data shows that the user suddenly starts a long-distance run, this strong change in activity should also be given a higher weight. Finally, based on these weights, the adjustment amount of the sliding window can be calculated, and the sizes of the first sliding window and the second sliding window can be adjusted accordingly. This dynamic adjustment mechanism can ensure that the sliding window can always accurately reflect the changing trend of the data, thereby improving the accuracy and reliability of health monitoring.

[0065] S4: obtaining a time series included in the data series, dividing the data series according to the time series to obtain a plurality of time segments, assigning corresponding weight values ​​to the plurality of time segments, and adjusting positions of the first sliding window and the second sliding window respectively according to the weight values;

[0066] In step S4, the time series information in the data sequence is used to finely adjust the positions of the first sliding window and the second sliding window by dividing the time segments and assigning weight values. First, the data sequence is divided into multiple time segments according to the continuity and change characteristics of the time series. These time segments can be fixed time periods or unequal time periods automatically divided according to specific events or conditions. Each time segment represents the data change pattern within a specific time period. Next, a corresponding weight value is assigned to each time segment, and the determination of the weight value can be based on multiple factors, such as the fluctuation amplitude of the data within the time segment, the persistence of the change trend, and the correlation with the health status or sports performance. For example, if the skin impedance data shows a significant upward trend within a certain time segment, this may indicate an increase in skin moisture content or an improvement in blood circulation, so a higher weight value can be assigned. Similarly, if the exercise volume data suddenly increases within a certain time segment, it may indicate that the user has performed high-intensity exercise, which should also be assigned a higher weight. With the time segments and corresponding weight values, the positions of the first sliding window and the second sliding window can be adjusted according to this information. For the first sliding window, if the weight value of a certain time segment is high and the skin impedance data in the segment changes significantly, the window can be moved to the segment to more accurately capture the change. For the second sliding window, if the exercise data of a certain time segment is particularly prominent, the window can also be moved to the segment to reflect the user's exercise status. Through this time series-based sliding window position adjustment, the temporal change pattern of skin impedance data and exercise data can be better tracked and reflected, thereby providing more accurate and useful information for health monitoring.

[0067] S5: The first sliding window and the second sliding window are re-slid on the data sequence based on the adjusted positions as the starting points and the adjusted sizes as the window bits to obtain the distribution of the skin impedance data and the exercise amount data on the data sequence;

[0068] In step S5, according to the adjustment of the previous steps, the size and position of the first sliding window and the second sliding window have been optimized, and these adjusted sliding windows are applied to the data sequence to obtain the distribution of skin impedance data and exercise data on the sequence. First, based on the adjusted position, the first sliding window and the second sliding window are placed at the corresponding starting points of the data sequence respectively. Then, according to the adjusted size, that is, the number of window bits, the two sliding windows are moved in sequence on the data sequence. For the first sliding window, it will slide on the skin impedance data sequence, capture the data points in each window, and analyze the distribution and change trend of these points. Through continuous sliding, the distribution of skin impedance data on the entire sequence can be obtained, including its fluctuation range, change trend and possible periodic changes. Similarly, the second sliding window will also perform a similar sliding operation on the exercise data sequence to obtain the distribution of exercise data, which includes not only statistics such as the average value, maximum value and minimum value of the data, but also further analyzes the fluctuation pattern, periodicity and correlation with other health indicators of the data. By reapplying the sliding window, the changes in skin impedance data and exercise volume data in the data series can be captured more accurately, thereby providing more comprehensive and in-depth information for health monitoring.

[0069] S6: Calculate a correlation index between skin impedance and exercise amount according to the distribution, and evaluate the user's health status according to the correlation index.

[0070] In step S6, the distribution of the skin impedance data and the amount of exercise data obtained in the previous step is used to calculate the correlation index between them, so as to evaluate the health status of the user. First, the correlation between the two data sequences is calculated. The correlation index can quantify the linear relationship or monotonic relationship between the skin impedance and the amount of exercise. When calculating the correlation index, it is calculated based on the local and global information provided by the sliding window. By comparing the correlation changes in different time segments or different sliding window positions, the changing trend of the user's health status can be more deeply understood. When the correlation index is obtained, the user's health status is evaluated according to these indicators. For example, if there is a significant positive correlation between skin impedance and the amount of exercise, it means that the user's skin condition and exercise performance promote each other and are in a good health state. On the contrary, if the correlation is weak or negatively correlated, it means that the user needs to adjust the exercise method or pay attention to skin health and other issues. In this way, personalized health advice and feedback can be provided to users based on the correlation index of skin impedance and exercise data to help them better manage and improve their health status. In summary, by dynamically adjusting the sliding window size, dividing time segments and assigning weight values, re-sliding the window to obtain data distribution, and calculating correlation indicators to evaluate health status, comprehensive and accurate monitoring and analysis of the user's health status can be achieved.

[0071] The monitoring method based on skin impedance and exercise volume proposed in this application first obtains the user's skin impedance data and exercise volume data in real time, and converts these data into a data sequence, which can reflect the user's physiological state in many aspects; by setting the initial sliding window, adjusting the size of the window according to the data change characteristics, and adjusting the position of the window according to the time series, the efficiency and response speed of monitoring are improved, so that health monitoring is no longer limited to data collection under specific time periods or environmental conditions, but can continuously track and analyze the changes in the user's physiological state, realize dynamic tracking of the user's health status, more accurately capture the user's health changes, and improve the accuracy and reliability of health monitoring. In addition, by re-sliding the first sliding window and the second sliding window on the data sequence based on the adjusted position and size, the distribution of skin impedance data and exercise volume data on the data sequence is obtained, which can more intuitively show the changing trend of the user's health status. Finally, the user's health status is evaluated based on the correlation index between skin impedance and exercise volume, which can provide users with more accurate and personalized health advice.

[0072] In summary, the monitoring method based on skin impedance and exercise volume of the present invention, by real-time acquisition and analysis of skin impedance and exercise volume data, and combined with dynamically adjusted sliding window technology, realizes accurate monitoring and evaluation of the user's health status, providing users with a more comprehensive and personalized health monitoring experience.

[0073] In another embodiment, after obtaining the distribution of skin impedance data and exercise data, a statistical learning method or a machine learning algorithm can be used to fit the data in the sliding window, and a mathematical model can be constructed according to the trend and law of historical data to predict the skin impedance and exercise data in the future. By continuously adjusting the parameters and structure of the model, the accuracy and reliability of the prediction can be improved. In the process of fitting the sliding window, other health indicators or personal information, such as age, gender, eating habits, etc., can also be combined to improve the accuracy of the prediction. This additional information can provide more context and background knowledge for the model, which helps to capture more factors related to health status. When a prediction model for fitting the sliding window is established, the future health status can be predicted based on the user's current data. This can help users discover potential health problems in a timely manner and take corresponding measures to intervene in advance. For example, if the prediction results show that the user's skin impedance may decrease in the future, the user can be reminded to pay attention to moisturizing and sun protection to maintain the health of the skin. By combining the technology of fitting the sliding window, the monitoring method based on skin impedance and exercise volume can not only accurately assess the user's current health status, but also predict the future health status, providing users with more comprehensive and forward-looking health management services. This will help users better understand their health status, detect and respond to potential health problems in a timely manner, and improve their quality of life.

[0074] In one embodiment, the step of acquiring the user's skin impedance data and exercise data in real time and converting the skin impedance data and exercise data into a data sequence in real time includes:

[0075] Collect the user's skin impedance data and exercise data in real time based on sensors;

[0076] Based on the local Hough algorithm, the collected skin impedance data and motion data are filtered and denoised in real time;

[0077] The skin impedance data and exercise volume data after filtering and noise reduction are sorted in chronological order to form a continuous data sequence, wherein each data point contains information of the skin impedance data and exercise volume data.

[0078] In the above embodiment, the skin impedance data and exercise volume data of the user are collected in real time by the sensor, which ensures the accuracy and real-time performance of the data. The sensor can continuously monitor the skin impedance and exercise volume of the user, and transmit the collected data to the subsequent processing unit. The sensor can capture the subtle changes in the skin impedance and exercise volume of the user, providing reliable data support for health monitoring, and filtering and noise reduction processing are performed on the collected skin impedance data and exercise volume data in real time based on the local Hough algorithm, which can remove noise and interference in the data and improve the signal-to-noise ratio of the data. Through filtering and noise reduction processing, the noise influence caused by the sensor itself and environmental factors can be eliminated, making the data more accurate and reliable. At the same time, real-time filtering and noise reduction processing can also reduce the delay of data processing and ensure the real-time performance of health monitoring. After filtering and noise reduction processing, the skin impedance data and exercise volume data are sorted in chronological order to form a continuous data sequence. Each data point contains information about the skin impedance data and exercise volume data, which can fully reflect the user's physiological state. In summary, through the steps of real-time collection, filtering, noise reduction and sorting to form a data sequence, accurate, reliable and continuous skin impedance and exercise volume data can be obtained, providing strong data support for subsequent health monitoring and evaluation. This will help achieve more precise and personalized health management and improve users' quality of life and health.

[0079] In another embodiment, the sensor includes a skin impedance sensor and a motion sensor, wherein the skin impedance sensor is used to measure the user's skin impedance data in real time, and the motion sensor is used to obtain the user's exercise data in real time. The skin impedance sensor, also known as the EDA sensor, reflects the changes in the activity of the autonomic nervous system by measuring the changes in the conductance of the skin surface. The activation of the autonomic nervous system is closely related to the emotional state. For example, emotional reactions such as anxiety, tension and excitement will cause changes in skin conductance. The motion sensor may include a pressure sensor for real-time detection of the user's steps and postures, thereby inferring the user's exercise volume. The pressure sensor can be integrated into the user's shoes, bracelets or other wearable devices, and the user's steps and exercise intensity can be calculated by detecting the pressure changes generated when the user walks or runs. Combining the data of the skin impedance sensor and the motion sensor, the user's emotional state and exercise volume can be fully understood. In addition, in order to further improve the accuracy and reliability of health monitoring, the present application can also introduce other types of sensors for multimodal data acquisition. For example, a heart rate sensor, a blood oxygen sensor, etc. can be added to monitor the user's heart rate and blood oxygen saturation and other physiological indicators in real time. These physiological indicators can reflect the user's cardiovascular health status and respiratory function, complement each other with skin impedance and exercise data, and jointly construct a portrait of the user's health status. Through the fusion analysis of multimodal data, the user's health status can be more comprehensively evaluated, and more accurate and personalized health advice can be provided to the user. At the same time, taking into account the individual differences between different users, this application can also personalize the monitoring method according to the user's personal characteristics and historical data. For example, the size and position of the sliding window can be adjusted according to factors such as the user's age, gender, weight, and height to adapt to the physiological characteristics of different users. In addition, a personalized health model can be built based on the user's historical data to predict the health status in the future. These personalized adjustments can further improve the accuracy and reliability of health monitoring and meet the personalized needs of users.

[0080] In another embodiment, an environmental sensor is also included for real-time monitoring of the environmental conditions of the user. The environmental sensor may include a temperature sensor, a humidity sensor, a light sensor, and an air quality sensor, etc. These sensors can sense environmental factors such as temperature, humidity, light intensity, and air quality around the user in real time. For example, a high temperature and high humidity environment may cause the user to sweat more and reduce skin impedance, and changes in light intensity and air quality may also affect the user's emotional state and exercise volume. By monitoring these environmental factors in real time and combining skin impedance and exercise volume data, the user's health status can be more accurately assessed and targeted health advice can be provided to the user. In addition, the environmental sensor can also be used to trigger specific health monitoring tasks. For example, when it is detected that the user has entered an environment with poor air quality, the frequency of collecting skin impedance data can be automatically increased to more sensitively capture the user's possible physiological reactions. Alternatively, in the case of low light intensity, the user can be reminded to increase the amount of exercise to improve the body's activity and metabolism. In summary, by introducing environmental sensors, the monitoring method based on skin impedance and exercise volume of the present application can more comprehensively consider the impact of environmental factors on user health and provide more accurate and personalized health management and advice. This will help users better understand their health status and take appropriate measures to maintain and improve their health. At the same time, this also reflects the innovation and practicality of this application in the field of health management, providing users with more comprehensive and forward-looking health management services.

[0081] In one embodiment, the step of setting an initial sliding window includes:

[0082] Setting a preset number of bits as the size of the initial sliding window;

[0083] According to the preset number of bits, two sliding windows of equal length are set on the data sequence, which serve as a first sliding window and a second sliding window respectively;

[0084] Initialize the positions of the first sliding window and the second sliding window to cover the beginning part of the data sequence.

[0085] In the above embodiment, a fixed number of bits is preset, which determines the size of the initial sliding window. The preset number of bits can be determined according to the time granularity of the physiological state change to be monitored, reflecting the degree of refinement of health data monitoring. By setting a suitable preset number of bits, it can be ensured that the sliding window can capture slight changes in the user's physiological state without being too sensitive and introducing too much noise. Subsequently, two sliding windows of equal length are set on the data sequence, respectively named the first sliding window and the second sliding window. The initial sizes of the two windows are determined according to the preset number of bits mentioned above, and they will slide along the data sequence to analyze the changes in the user's skin impedance and exercise data in real time. Finally, the positions of the two sliding windows are initialized so that they cover the starting part of the data sequence. In this way, when the user's physiological state is monitored, the sliding window can start working immediately to capture and analyze the user's initial health data. As the data is continuously acquired and updated, the sliding window will continue to slide on the data sequence to track and analyze the changes in the user's physiological state. In this way, the initial sliding window is set and its position and size are initialized. This lays the foundation for subsequent health monitoring and evaluation, enabling the position and size of the sliding window to be dynamically adjusted according to the user's real-time data, thereby achieving comprehensive and accurate monitoring and analysis of the user's health status.

[0086] In one embodiment, the step of obtaining the change characteristics between the newly added data points and the initial data points in the data sequence, assigning corresponding weights to the change characteristics between the newly added data points and the initial data points, and adjusting the sizes of the first sliding window and the second sliding window based on the weights includes:

[0087] Calculating the rate of change between the newly added data point and the initial data point based on the difference between the newly added data point and the initial data point in the data sequence;

[0088] Assigning a weight value according to the change rate, wherein the weight value is inversely proportional to the magnitude of the change rate;

[0089] Based on the weight value, adjusting the sizes of the first sliding window and the second sliding window, so that in the area with a larger change rate, the size of the sliding window is reduced, and in the area with a smaller change rate, the size of the sliding window is increased;

[0090] The calculation expression is: ,in, is the size of the sliding window at time t, and Respectively represent the change rate of skin impedance data and exercise volume data at time t, and It is a preset weight coefficient used to balance the contribution of skin impedance data and motion data when adjusting the sliding window size.

[0091] In the above embodiment, first, the rate of change between the newly added data points and the initial data points in the data sequence is calculated. This rate of change reflects the degree of change of the physiological state over a period of time. A weight value is assigned to it according to the size of the rate of change, and an inverse relationship is adopted, that is, the larger the rate of change, the smaller the weight value; the smaller the rate of change, the larger the weight value. This design is based on the following considerations: when the physiological state changes drastically, it is hoped that the sliding window can follow this change more closely so as to capture and respond to possible health problems in a timely manner; and when the physiological state changes more slowly, the size of the sliding window can be appropriately relaxed to reduce unnecessary calculations and responses. Then, based on this weight value, the size of the first sliding window and the second sliding window is adjusted. Specifically, in areas with a large rate of change, the size of the sliding window is reduced to more accurately capture subtle changes in the physiological state; and in areas with a small rate of change, the size of the sliding window is increased to reduce sensitivity to noise and reduce computational complexity.

[0092] In a specific embodiment, the calculation expression combines the skin impedance data change rate at the current moment , Movement volume data change rate And the size of the sliding window at the last moment To dynamically adjust the size of the sliding window at the current moment .in, and It is a preset weight coefficient used to balance the influence of different data when adjusting the sliding window size. By adjusting these weight coefficients, the performance of the algorithm can be optimized according to the needs of the actual application scenario. This method of dynamically adjusting the sliding window size can adaptively adjust the window size according to the degree of change of the physiological state, thereby more accurately reflecting the health status of the user. Secondly, by introducing the change rate of skin impedance data and exercise data as the basis for weight adjustment, the subtle changes in the physiological state can be better captured and the impact of noise on the performance of the algorithm can be reduced. Finally, by balancing the role of different data when adjusting the sliding window size through preset weight coefficients, the algorithm can be made more flexible and configurable to adapt to the needs and application scenarios of different users. It should be noted that the calculation expression in the above embodiment is only a possible implementation method, and the specific implementation method can be adjusted and optimized according to the needs of the actual application scenario. For example, the size of the sliding window can be dynamically adjusted according to the changing characteristics of other physiological parameters or behavioral data, or a more complex algorithm model can be introduced to improve the accuracy and robustness of the algorithm.

[0093] In one embodiment, the step of acquiring a time series included in the data series, dividing the data series according to the time series to obtain a plurality of time segments, assigning corresponding weight values ​​to the plurality of time segments, and adjusting the positions of the first sliding window and the second sliding window respectively according to the weight values ​​includes:

[0094] Extracting the timestamp corresponding to each data point in the data sequence to form a time series;

[0095] Dividing the time series into a plurality of time segments according to a preset time interval;

[0096] Assigning corresponding weight values ​​to the plurality of time segments, and adjusting the positions of the first sliding window and the second sliding window respectively according to the weight values ​​based on a preset algorithm;

[0097] Wherein, the expression of the preset algorithm is: ,in, Represents the probability distribution of the sliding window position y given the time series x, Represents from position Transfer to location When The weight value of the time point, T is the total length of the time series, and paths represents all possible sliding window position paths. Represents all possible sliding window position combinations.

[0098] In the above embodiment, the data sequence is first analyzed in time, and a clear time series is formed by extracting the timestamp corresponding to each data point, which helps to understand the temporal distribution and trend of the user's physiological state changes. Then, according to the preset time interval, this time series is divided into multiple time segments. Each time segment represents a specific time interval, contains the user's physiological state data during this period, and analyzes the user's physiological state changes in different time periods in more detail. Next, a corresponding weight value is assigned to each time segment. This weight value is derived based on factors such as the change rate and stability of the physiological state data within the time segment. The size of the weight value reflects the importance of the time segment in the user's physiological state changes. By assigning different weight values ​​to different time segments, it is possible to better capture and highlight those time periods that have an important impact on the user's physiological state changes. After obtaining the time segments and their corresponding weight values, a preset algorithm is used to adjust the positions of the first sliding window and the second sliding window. This preset algorithm is a weight-based probability model. The probability distribution of the sliding windows at different positions is calculated according to the weight value of each time segment. By maximizing this probability distribution, the sliding window position that best suits the current physiological state change can be found. Such an adjustment strategy can ensure that the sliding window always remains in a position that can most effectively capture and analyze physiological state changes. Specifically, the probability distribution of the sliding window position is calculated. In this formula, P(y|x) represents the probability distribution of the sliding window position y given the time series x. This probability distribution is based on the weight value of each time segment. Calculated, the weight value reflects the change from the previous position Move to current location At a specific point in time The importance of the sliding window is calculated by the sliding window position calculation method. In this way, the continuous changes of the user's physiological state in time can be captured, and how these changes affect the position of the sliding window. Next, all possible sliding window position paths are considered. These paths represent different ways of moving the sliding window in the time series. Each path has its corresponding probability, which is calculated based on the weight values ​​of all time segments on the path. By comparing the probabilities of these paths, the most likely path can be found, that is, the most likely way of moving the sliding window. Then all possible sliding window position combinations are considered. This is because the sliding window can be at any position in the time series, not just on some preset specific paths. Therefore, it is necessary to calculate the probabilities of all possible position combinations to ensure that the globally optimal sliding window position is found. Finally, according to the output of the preset algorithm, the positions of the first sliding window and the second sliding window are adjusted. This process is iterative. Each iteration updates the position of the sliding window according to the new data and time series. In this way, the position of the sliding window can be adaptively adjusted to better adapt to the changes in the user's physiological state. In general, this embodiment provides a sliding window position adjustment method based on time series analysis and weight adjustment. By analyzing and dividing the data series in time, it is possible to more deeply understand the changing rules of the user's physiological state, and to highlight those important time periods by assigning different weight values ​​to different time segments. Then, the position of the sliding window is adjusted using a weighted probability model to ensure that the sliding window always remains in a position that can most effectively capture and analyze changes in physiological state. This method can improve the efficiency and accuracy of data processing and provide a more reliable basis for the analysis and prediction of the user's physiological state.

[0099] In one scenario embodiment, it is considered that there may be a certain periodicity in the daily activity pattern and physiological state changes of the user, such as daily work and rest, exercise and stillness. Therefore, when obtaining the time series in the data sequence, these periodic features can be further used to optimize the division and adjustment of the sliding window. Specifically, the periodic pattern in the change of the user's physiological state can be first identified, such as the physiological indicators of the user presenting similar change trends in a fixed time period every day. Then, according to these periodic patterns, the time series is divided into more accurate periodic time segments. In each periodic time segment, according to factors such as the rate of change and stability of the physiological state data, corresponding weight values ​​are assigned to different time periods. For example, in the afternoon time segment, since the user may be awake and active, the weight value of the time period can be relatively high. In the late night time segment, since the user may be in a resting or sleeping state, the weight value of the time period can be relatively low. In this way, the changes in the physiological state of the user in different time periods can be more accurately reflected, and the position of the sliding window can be adjusted accordingly, so that the key physiological state in the periodic changes can be captured more accurately, thereby improving the accuracy of health monitoring and evaluation.

[0100] In one embodiment, the step of re-sliding the first sliding window and the second sliding window on the data sequence based on the adjusted positions as the starting points and the adjusted sizes as the number of window bits to obtain the distribution of the skin impedance data and the exercise amount data on the data sequence includes:

[0101] Re-determining the starting point and the ending point of the first sliding window and the second sliding window on the data sequence according to the adjusted position and size;

[0102] Slide on the data sequence according to the new starting point and ending point to obtain the skin impedance data and exercise volume data within the window;

[0103] Statistical features of the skin impedance data and exercise volume data within a calculation window are obtained to obtain distribution of the skin impedance data and exercise volume data on the data sequence, wherein the statistical features at least include a mean value, a standard deviation, a median, a maximum value, and a minimum value.

[0104] In the above embodiment, after determining the adjusted position and size of the sliding window, an actual sliding operation is performed on the data sequence according to these parameters to obtain the distribution of the skin impedance data and the amount of exercise data on the data sequence. Specifically, according to the adjusted position and size, the starting point and the ending point of the first sliding window and the second sliding window on the data sequence are re-determined, and the starting index and the ending index of the sliding window are calculated to ensure that the window can cover a suitable data range. By setting a new starting point and an ending point, it can be ensured that the sliding window can accurately capture the key information of the user's physiological state change. According to the new starting point and the ending point, the sliding window slides on the data sequence, and the sliding window moves on the data sequence according to the set step size (for example, point by point or segment by segment), and each movement covers a different data subset. During the sliding process, the skin impedance data and the amount of exercise data in the window will be extracted for subsequent analysis and processing. Then, the statistical characteristics of the skin impedance data and exercise volume data in the window are calculated. The statistical characteristics can quantitatively describe the distribution of the data in the window, including the mean, standard deviation, median, maximum value and minimum value, etc. The statistical characteristics can reflect the changes in the user's physiological state in a specific time period, such as the degree of fluctuation of skin impedance, the intensity of exercise volume, etc. By analyzing these statistical characteristics, the user's health status can be further understood, providing a basis for subsequent health assessment and recommendations. Through the above steps, the position and size of the sliding window can be dynamically adjusted, and the data sequence can be re-slid based on the adjusted parameters to obtain the distribution of skin impedance data and exercise volume data in the data sequence. This dynamic adjustment strategy enables the health monitoring and evaluation system to more accurately adapt to the changes in the physiological state of different users, and improve the accuracy and effectiveness of monitoring and evaluation.

[0105] In one embodiment, the step of calculating a correlation index between skin impedance and exercise amount according to the distribution, and evaluating the user's health condition according to the correlation index includes:

[0106] Calculate the linear correlation value between the skin impedance data and the exercise volume data, wherein the linear correlation value is between -1 and 1, the closer the absolute value is to 1, the stronger the correlation is, and the sign indicates positive correlation or negative correlation;

[0107] Dividing the linear correlation degree value into different intervals based on multiple preset thresholds;

[0108] The user's health status is evaluated according to the health status evaluation standards corresponding to the different intervals, wherein each interval corresponds to a health status, and the health status at least includes normal, good and abnormal.

[0109] In the above embodiment, by calculating the linear correlation value between the skin impedance data and the exercise amount data, the correlation between the two can be quantitatively evaluated. The closer the linear correlation value is to 1 or -1, the stronger the linear relationship between the skin impedance and the exercise amount, that is, the more consistent or opposite their changing trends are; while close to 0, it means that the linear relationship between the two is weak and there is no obvious changing trend. According to the calculated linear correlation value, it can be compared with multiple preset thresholds to divide the linear correlation value into different intervals. Each interval corresponds to a specific health status assessment standard, which can reflect the impact of the relationship between skin impedance and exercise amount on the user's health status. For example, the linear correlation value may indicate that the user's health status is normal in a certain interval, while in another interval it may indicate that the user's health status is good or abnormal. Finally, according to the interval to which the user's data belongs, the health status of the user can be quickly evaluated. This evaluation result can provide users with personalized health advice and guidance to help them better manage their health. In this way, the user's health status can be accurately and quickly evaluated based on the correlation index between skin impedance and exercise amount, providing users with more personalized and accurate health management services.

[0110] In a specific embodiment, the range of the linear correlation degree value is determined, that is, -1 to 1. Then, multiple preset thresholds can be set according to actual needs, and these thresholds divide the range of the linear correlation degree value into different intervals. For example, the following thresholds can be set: -0.8, -0.4, 0, 0.4 and 0.8, and the linear correlation degree value is divided into the following intervals: [-1, -0.8), [-0.8, -0.4), [-0.4, 0), [0, 0.4), [0.4, 0.8) and [0.8, 1]. Then, the corresponding health status assessment standard is set for each interval. For example, the following standards can be set: when the linear correlation value is in the interval of [-1, -0.8), it indicates that there is a strong negative correlation between the user's skin impedance and the amount of exercise, indicating that the user's skin condition is abnormal during exercise, and the health status is assessed as "abnormal"; when the linear correlation value is in the interval of [-0.8, -0.4), it indicates that there is a strong negative correlation between the user's skin impedance and the amount of exercise, but it may not reach the abnormal level, and the health status is assessed as "needs attention"; when the linear correlation value is in the interval of [-0.4, 0), it indicates that there is a weak negative correlation between the user's skin impedance and the amount of exercise, which may be a normal physiological reaction, and the health status is assessed as "needs attention". The health status is evaluated as "normal"; when the linear correlation value is in the interval [0, 0.4), it means that there is a weak positive correlation between the user's skin impedance and the amount of exercise, which is also a normal physiological reaction. At this time, the health status is evaluated as "normal"; when the linear correlation value is in the interval [0.4, 0.8), it means that there is a strong positive correlation between the user's skin impedance and the amount of exercise, indicating that exercise has a positive effect on skin health, and the health status is evaluated as "good"; when the linear correlation value is in the interval [0.8, 1], it means that there is a strong positive correlation between the user's skin impedance and the amount of exercise, indicating that exercise has a significant positive effect on skin health, and the health status is evaluated as "excellent". Through such interval division and setting of health status evaluation standards, a more accurate and personalized evaluation of the user's health status can be made according to the linear correlation value between the user's skin impedance and the amount of exercise. At the same time, such evaluation results can also serve as an important basis for providing personalized health advice and guidance to users.

[0111] It should be noted that the above is only an example of a possible interval division and health status assessment standard. In actual applications, it can be adjusted and optimized according to actual conditions to adapt to different application scenarios and user needs. At the same time, other possible influencing factors, such as the user's age, gender, physical condition, etc., need to be considered to provide a more comprehensive and accurate health status assessment result.

[0112] In another embodiment, after outputting the user's health status, more detailed health advice can be provided in combination with the user's personal data and daily habits. For example, for users whose health status is assessed as "needing attention" or "abnormal", they can be advised to adjust their exercise mode, exercise intensity or exercise frequency to improve the relationship between skin impedance and exercise volume. For users whose health status is assessed as "good" or "excellent", they can be encouraged to continue their existing exercise habits and appropriately increase their exercise volume to further promote skin health. In addition, suitable sports, exercise time and exercise environment can be recommended to them based on the user's personal data and daily habits to help them formulate a more reasonable exercise plan. At the same time, in order to better track and evaluate the user's health status, the user's skin impedance and exercise volume data can be regularly collected and statistically analyzed. By comparing the data changes in different time periods, it is possible to understand whether the user's health status has improved and which factors may affect the health status. In this way, more accurate and personalized health management services can be provided to them based on the actual situation of the user. In addition, it is also possible to consider introducing other physiological parameters, such as heart rate, blood pressure, etc., and conduct a comprehensive analysis with skin impedance and exercise volume data to more comprehensively evaluate the user's health status. By comprehensively considering multiple physiological parameters, we can more accurately understand the user's physical condition and provide them with more scientific and effective health management suggestions. In summary, by combining the user's personal information, daily habits and other physiological parameters, we can make a more comprehensive and accurate assessment of the user's health status and provide them with more personalized and precise health management services. This helps users better understand their physical condition, adjust their lifestyle and exercise habits in a timely manner, and promote physical and mental health development.

[0113] Reference Figure 2 , a monitoring device based on skin impedance and exercise volume, comprising:

[0114] The first acquisition module 100 is used to acquire the user's skin impedance data and exercise data in real time, and convert the skin impedance data and exercise data into a data sequence in real time;

[0115] A setting module 200 is used to set an initial sliding window, wherein the initial sliding window includes a first sliding window and a second sliding window, the first sliding window is used to monitor the skin impedance data, and the second sliding window is used to monitor the exercise volume data;

[0116] A first adjustment module 300 is used to obtain a change feature between a newly added data point and an initial data point in the data sequence, assign a corresponding weight to the change feature between the newly added data point and the initial data point, and adjust the sizes of the first sliding window and the second sliding window based on the weight;

[0117] A second adjustment module 400 is used to obtain a time series included in the data series, divide the data series according to the time series to obtain multiple time segments, assign corresponding weight values ​​to the multiple time segments, and adjust the positions of the first sliding window and the second sliding window respectively according to the weight values;

[0118] A second acquisition module 500 is used to slide the first sliding window and the second sliding window again on the data sequence based on the adjusted position as a starting point and the adjusted size as the number of window bits, to obtain the distribution of the skin impedance data and the exercise amount data on the data sequence;

[0119] The evaluation module 600 is used to calculate the correlation index between skin impedance and exercise amount according to the distribution, and evaluate the health status of the user according to the correlation index.

[0120] In this embodiment, by acquiring the user's skin impedance data and exercise data in real time and converting these data into a data sequence, the user's physiological state can be reflected in multiple aspects; by setting the initial sliding window, adjusting the window size according to the data change characteristics, and adjusting the window position according to the time series, the monitoring efficiency and response speed are improved, so that health monitoring is no longer limited to data collection under specific time periods or environmental conditions, but can continuously track and analyze the user's physiological state changes, realize dynamic tracking of the user's health status, more accurately capture the user's health changes, and improve the accuracy and reliability of health monitoring. In addition, by re-sliding the first sliding window and the second sliding window on the data sequence based on the adjusted position and size, the distribution of skin impedance data and exercise data on the data sequence is obtained, which can more intuitively show the changing trend of the user's health status. Finally, by evaluating the user's health status based on the correlation index between skin impedance and exercise volume, more accurate and personalized health advice can be provided to the user.

[0121] Based on the same idea as the method in the above-mentioned embodiment, the monitoring device based on skin impedance and exercise amount provided in the present application can implement the method in the above-mentioned embodiment. For the convenience of explanation, the structural schematic diagram of the device embodiment only shows the parts related to the embodiment of the present application. Those skilled in the art can understand that the illustrated structure does not constitute a limitation on the device, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0122] Reference Figure 3 In an embodiment of the present application, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 3As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as monitoring based on skin impedance and exercise volume. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a monitoring method based on skin impedance and exercise volume is implemented.

[0123] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, a monitoring method based on skin impedance and exercise volume is implemented, including the steps of: acquiring skin impedance data and exercise volume data of a user in real time, and converting the skin impedance data and exercise volume data into a data sequence in real time; setting an initial sliding window, wherein the initial sliding window includes a first sliding window and a second sliding window, the first sliding window is used to monitor the skin impedance data, and the second sliding window is used to monitor the exercise volume data; acquiring the change characteristics between the newly added data points and the initial data points in the data sequence, assigning corresponding weights to the change characteristics between the newly added data points and the initial data points, and Adjust the sizes of the first sliding window and the second sliding window based on the weight; obtain a time series included in the data series, and divide the data series according to the time series to obtain multiple time segments, assign corresponding weight values ​​to the multiple time segments, and adjust the positions of the first sliding window and the second sliding window respectively according to the weight values; use the first sliding window and the second sliding window as the starting point based on the adjusted position and the adjusted size as the number of window bits, and re-slide on the data series to obtain the distribution of the skin impedance data and the exercise volume data on the data series; calculate the correlation index between skin impedance and exercise volume based on the distribution, and evaluate the user's health status based on the correlation index.

[0124] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in this application and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0125] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A monitoring method based on skin impedance and exercise volume, characterized in that: The method comprises: Acquire the user's skin impedance data and exercise data in real time, and convert the skin impedance data and exercise data into a data sequence in real time; Setting an initial sliding window, wherein the initial sliding window includes a first sliding window and a second sliding window, the first sliding window is used to monitor the skin impedance data, and the second sliding window is used to monitor the exercise volume data; Acquire a change feature between a newly added data point and an initial data point in the data sequence, assign a corresponding weight to the change feature between the newly added data point and the initial data point, and adjust the sizes of the first sliding window and the second sliding window based on the weight; Acquire a time series included in the data series, divide the data series according to the time series to obtain a plurality of time segments, assign corresponding weight values ​​to the plurality of time segments, and adjust positions of the first sliding window and the second sliding window respectively according to the weight values; The first sliding window and the second sliding window are re-slid on the data sequence based on the adjusted position as the starting point and the adjusted size as the number of window bits to obtain the distribution of the skin impedance data and the exercise amount data on the data sequence; Calculating a correlation index between skin impedance and exercise amount according to the distribution, and evaluating the user's health status according to the correlation index; The step of obtaining the change characteristics between the newly added data points and the initial data points in the data sequence, assigning corresponding weights to the change characteristics between the newly added data points and the initial data points, and adjusting the sizes of the first sliding window and the second sliding window based on the weights includes: Calculating the rate of change between the newly added data point and the initial data point based on the difference between the newly added data point and the initial data point in the data sequence; Assigning a weight value according to the change rate, wherein the weight value is inversely proportional to the magnitude of the change rate; Based on the weight value, adjusting the sizes of the first sliding window and the second sliding window; The calculation expression is: ,in, is the size of the sliding window at time t, and Respectively represent the change rate of skin impedance data and exercise volume data at time t, and It is a preset weight coefficient used to balance the contribution of skin impedance data and motion data when adjusting the sliding window size.

2. The monitoring method based on skin impedance and exercise volume according to claim 1, characterized in that: The step of acquiring the user's skin impedance data and exercise volume data in real time and converting the skin impedance data and exercise volume data into a data sequence in real time includes: Collect the user's skin impedance data and exercise data in real time based on sensors; Based on the local Hough algorithm, the collected skin impedance data and motion data are filtered and denoised in real time; The skin impedance data and exercise volume data after filtering and noise reduction are sorted in chronological order to form a continuous data sequence, wherein each data point contains information of the skin impedance data and exercise volume data.

3. The monitoring method based on skin impedance and exercise volume according to claim 1, characterized in that: The step of setting an initial sliding window includes: Setting a preset number of bits as the size of the initial sliding window; According to the preset number of bits, two sliding windows of equal length are set on the data sequence, which serve as a first sliding window and a second sliding window respectively; Initialize the positions of the first sliding window and the second sliding window to cover the beginning part of the data sequence.

4. The monitoring method based on skin impedance and exercise volume according to claim 1, characterized in that: The step of obtaining a time series included in the data series, dividing the data series according to the time series to obtain a plurality of time segments, assigning corresponding weight values ​​to the plurality of time segments, and adjusting the positions of the first sliding window and the second sliding window respectively according to the weight values ​​includes: Extracting the timestamp corresponding to each data point in the data sequence to form a time series; Dividing the time series into a plurality of time segments according to a preset time interval; Assigning corresponding weight values ​​to the plurality of time segments, and adjusting the positions of the first sliding window and the second sliding window respectively according to the weight values ​​based on a preset algorithm; The expression of the preset algorithm is: ,in, Represents the probability distribution of the sliding window position y given the time series x, Represents from position Transfer to location When The weight value of the time point, T is the total length of the time series, and paths represents all possible sliding window position paths. Represents all possible sliding window position combinations.

5. The monitoring method based on skin impedance and exercise volume according to claim 1, characterized in that: The step of re-sliding the first sliding window and the second sliding window on the data sequence based on the adjusted positions as the starting points and the adjusted sizes as the number of window bits to obtain the distribution of the skin impedance data and the exercise amount data on the data sequence includes: Re-determining the starting point and the ending point of the first sliding window and the second sliding window on the data sequence according to the adjusted position and size; Slide on the data sequence according to the new starting point and ending point to obtain the skin impedance data and exercise volume data within the window; Statistical features of the skin impedance data and exercise volume data within a calculation window are obtained to obtain distribution of the skin impedance data and exercise volume data on the data sequence, wherein the statistical features at least include a mean value, a standard deviation, a median, a maximum value, and a minimum value.

6. The monitoring method based on skin impedance and exercise volume according to claim 1, characterized in that: The step of calculating the correlation index between skin impedance and exercise amount according to the distribution, and evaluating the health status of the user according to the correlation index, comprises: Calculate the linear correlation value between the skin impedance data and the exercise volume data, wherein the linear correlation value is between -1 and 1, the closer the absolute value is to 1, the stronger the correlation is, and the sign indicates positive correlation or negative correlation; Dividing the linear correlation degree value into different intervals based on multiple preset thresholds; The user's health status is evaluated according to the health status evaluation standards corresponding to the different intervals, wherein each interval corresponds to a health status, and the health status at least includes normal, good and abnormal.

7. A monitoring device based on skin impedance and exercise volume, used to implement the method according to any one of claims 1 to 6, characterized in that: include: A first acquisition module is used to acquire the user's skin impedance data and exercise volume data in real time, and convert the skin impedance data and exercise volume data into a data sequence in real time; A setting module, used to set an initial sliding window, wherein the initial sliding window includes a first sliding window and a second sliding window, the first sliding window is used to monitor the skin impedance data, and the second sliding window is used to monitor the exercise volume data; A first adjustment module is used to obtain the change characteristics between the newly added data points and the initial data points in the data sequence, assign corresponding weights to the change characteristics between the newly added data points and the initial data points, and adjust the sizes of the first sliding window and the second sliding window based on the weights; a second adjustment module, configured to obtain a time series included in the data series, divide the data series according to the time series to obtain a plurality of time segments, assign corresponding weight values ​​to the plurality of time segments, and adjust positions of the first sliding window and the second sliding window respectively according to the weight values; A second acquisition module is used to slide the first sliding window and the second sliding window again on the data sequence based on the adjusted position as a starting point and the adjusted size as the number of window bits, so as to obtain the distribution of the skin impedance data and the exercise amount data on the data sequence; The evaluation module is used to calculate the correlation index between skin impedance and exercise amount according to the distribution, and evaluate the user's health status according to the correlation index.

8. A computer device, characterized in that: The method comprises a processor, a memory and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images