Physical and psychological health record information management method and system based on big data model

Abstract

The invention discloses a physical and psychological health record information management method and system based on a big data model, and relates to the technical field of physical and psychological health monitoring and early warning, and the method comprises the following steps: obtaining basic body information and disease information of a user, and screening basic similar users of the user; personalized physiological indexes of the user are set according to the disease information of the user, and first exercise physiological information of the exercise state of the user is collected; carrying out anomaly screening processing and feature extraction processing to obtain physiological anomaly data and physiological feature data; physical and psychological health monitoring and early warning are carried out on the user; the physical and psychological health monitoring and early warning method and device solve the problems that when the physical and psychological health of the user is monitored and early warned through a wearable device in an existing physical and psychological health monitoring and early warning technology, potential user body change information in historical physiological data is ignored, and accurate physical and psychological health monitoring and early warning cannot be provided for the user through the physiological data of the user in the historical motion state.

Description

Technical Field

[0001] The present invention relates to the technical field of physical and mental health monitoring and early warning, and specifically to a method and system for managing physical and mental health file information based on a big data model. Background Art

[0002] The physical and mental health monitoring and early warning technology is a comprehensive technology that integrates multiple disciplines and technical means, aiming to monitor the physiological and psychological states of individuals in real time or regularly, and to discover potential health risks or abnormal conditions in advance through data analysis and model algorithms, etc., so as to take intervention measures in a timely manner.

[0003] When the existing physical and mental health monitoring and early warning technology monitors and warns the physical and mental health of users through wearable devices, it often only conducts warning analysis based on the data collected at that time, and considers the historical data that has been collected as outdated, and only issues a warning when abnormal data is detected. At this time, the user's body often has problems; this means that it is impossible to discover potential health risks in advance when the body has not yet shown abnormal symptoms; however, the physical changes of users are a slow process, and the historical data contains the long-term physical change information of users, which is of great value for understanding the user's physical condition and health trend; at the same time, when the human body is in a moving state, potential physical defects are more likely to be exposed. However, the motion state data is interfered by various factors such as exercise intensity, type, and environment, and the changes are complex. The existing technology is difficult to accurately identify abnormal points in these changing data and cannot effectively mine the physical and mental health information behind the motion data; therefore, when the existing physical and mental health monitoring and early warning technology monitors and warns the physical and mental health of users through wearable devices, it ignores the potential user physical change information in the historical physiological data and cannot provide accurate physical and mental health monitoring and early warning for users through the physiological data of users in the historical motion state. Summary of the Invention

[0004] The present invention aims to solve at least one of the technical problems in the existing technology to some extent. By obtaining the basic physical information and disease information of users, and screening for basically similar users of the users; setting personalized physiological indicators for users according to the disease information of users, and collecting the first exercise physiological information of the user's motion state; and performing abnormal screening processing and feature extraction processing to obtain physiological abnormal data and physiological feature data; and then conducting physical and mental health monitoring and early warning for users; to solve the problem that when the existing physical and mental health monitoring and early warning technology monitors and warns the physical and mental health of users through wearable devices, it ignores the potential user physical change information in the historical physiological data and cannot provide accurate physical and mental health monitoring and early warning for users through the physiological data of users in the historical motion state.

[0005] To achieve the above object, in a first aspect, the present application provides a method for managing physical and mental health file information based on a big data model, including the following steps: Obtain the user's basic physical information and disease information, and screen for the user's basic similar users; Set the user's personalized physiological indicators according to the user's disease information, and collect the first exercise physiological information of the user's exercise status; Perform abnormal screening processing and feature extraction processing based on the user's first exercise physiological information to obtain physiological abnormal data and physiological feature data; Monitor and give early warnings about the user's physical and mental health based on the physiological abnormal data and physiological feature data.

[0006] Furthermore, obtaining the user's basic physical information and disease information, and screening for the user's basic similar users includes the following sub-steps: Obtain the user's gender, age, height, and weight through a wearable device, and obtain the heart rate range and blood oxygen saturation range of the user in a quiet state, denoted as [AX1, AX2] and [AY1, AY2] in sequence, which are recorded as the user's basic physical information; At the same time, obtain whether the user is ill and the type of illness, which is recorded as the user's disease information; According to the user's basic physical information, set the age similarity threshold as v1, the height similarity threshold as v2, and the weight similarity threshold as v3; mark other users with the same gender as the user and who simultaneously satisfy that the age difference is less than or equal to a1, the height difference is less than or equal to a2, and the weight difference is less than or equal to a3 as the reference similar users of the user.

[0007] Furthermore, obtaining the user's basic physical information and disease information, and screening for the user's basic similar users also includes the following sub-steps: For any one of the user's reference similar users, obtain the heart rate range and blood oxygen saturation range of the reference similar user in a quiet state, denoted as [BX1, BX2] and [BY1, BY2] in sequence. If the reference similar user and the corresponding user have the same type of disease or are both not ill at the same time, and simultaneously satisfy that [BX1, BX2] ∩ [AX1, AX2] exists, and [(XAB2 - XAB1) / (AX2 - AX1)] ≥ k0, and [BY1, BY2] ∩ [AY1, AY2] exists, and [(YAB2 - YAB1) / (AY2 - AY1)] ≥ k0, then mark the reference similar user as the basic similar user of the corresponding user; where [XAB1, XAB2] = [BX1, BX2] ∩ [AX1, AX2], [YAB1, YAB2] = [BY1, BY2] ∩ [AY1, AY2], and k0 is the set ratio threshold; repeat to screen all the basic similar users of the user.

[0008] Further, setting the user's personalized physiological indicators according to the user's disease information and collecting the first exercise physiological information of the user's exercise state includes the following sub-steps: Set the user's personalized physiological indicators according to whether the user is ill and the type of illness. If the user has a respiratory disease, set the user's personalized physiological indicator as the respiratory rate; if the user has a cardiovascular disease, set the user's personalized physiological indicator as the blood pressure; otherwise, set the user's personalized physiological indicator as the body temperature; Obtain the average heart rate, average blood oxygen saturation, and average personalized physiological indicators of the user in a quiet state through a wearable device; And obtain the user's exercise state. When the user starts to exercise, obtain the heart rate, blood oxygen saturation, personalized physiological indicators, collection time, and exercise type at the first time interval, which are recorded as the user's first exercise physiological information, and the first time interval is t1.

[0009] Further, performing abnormal screening processing and feature extraction processing on the user's first exercise physiological information to obtain physiological abnormal data and physiological feature data includes the following sub-steps: For the first exercise physiological information collected by the user during any exercise, sort the heart rate, blood oxygen saturation, and personalized physiological indicators according to the collection time respectively to obtain the first heart rate sequence, the first blood oxygen sequence, and the first personalized sequence, and perform rate-of-change processing respectively to obtain the first heart rate change sequence, the first blood oxygen change sequence, and the first personalized change sequence in sequence, and perform abnormal screening processing; the rate-of-change processing includes: denoting any data value in the corresponding sequence as AR i , and calculate the corresponding change sequence according to the rate-of-change formula respectively. The rate-of-change formula is as follows: , where AR i+1 represents the data value at the next moment corresponding to AR i , AU i represents the corresponding rate of change; The abnormal screening processing includes the first abnormal screening and the second abnormal screening. The first abnormal screening includes: setting the first heart rate threshold, the first blood oxygen threshold, and the first personalized threshold. For any data value in the first heart rate change sequence, the first blood oxygen change sequence, and the first personalized change sequence, if it is greater than the corresponding first heart rate threshold, the first blood oxygen threshold, and the first personalized threshold, it is marked as the corresponding abnormal change value of the collection.

[0010] Further, performing abnormal screening processing and feature extraction processing based on the user's first exercise physiological information to obtain physiological abnormal data and physiological feature data also includes the following sub-steps: Perform a second anomaly screening on the first heart rate change sequence, the first blood oxygen change sequence, and the first personality change sequence that have completed the first anomaly screening, including: for any change sequence that has completed the first anomaly screening, denote it as the pre-screened change sequence; set the sliding window size to p0 and the sliding step size to p1, and let the sliding window slide on the pre-screened change sequence. Each time it slides, calculate the mean and standard deviation of the data within the sliding window, and denote them as Q1 and Q2 in sequence; and judge all the data within the sliding window. If Q0 ∉ [Q1 - p2 * Q2, Q1 + p2 * Q2], where Q0 is any data within the sliding window and p2 is the set number of thresholds, then mark the corresponding data as the initial anomaly change value; For any initial anomaly change value in the first heart rate change sequence, the first blood oxygen change sequence, and the first personality change sequence, denote the position of the initial anomaly change value in the corresponding change sequence as the anomaly position, and denote the anomaly position together with the upper L positions and the lower L positions of the anomaly position as the initial anomaly region corresponding to the initial anomaly change value; If the initial anomaly change value satisfies that there are other initial anomaly change values in the corresponding regions of the other two change sequences that the initial anomaly region where the initial anomaly change value is located does not belong to, then mark the initial anomaly change value as a physical anomaly change value, otherwise mark the initial anomaly change value as a collection anomaly change value; After completing the anomaly screening process, mark the corresponding data of any collection anomaly change value or physical anomaly change value in the first heart rate sequence, the first blood oxygen sequence, and the first personality sequence as a collection anomaly value or a physical anomaly change value. After completion, obtain the second heart rate sequence, the second blood oxygen sequence, and the second personality sequence, and denote the second heart rate sequence, the second blood oxygen sequence, and the second personality sequence as physiological anomaly data.

[0011] Furthermore, performing anomaly screening processing and feature extraction processing based on the user's first exercise physiological information to obtain physiological anomaly data and physiological feature data further includes the following sub-steps: Perform feature extraction processing on the second heart rate sequence, the second blood oxygen sequence, and the second personality sequence respectively, and obtain the corresponding heart rate feature data, blood oxygen feature data, and personality feature data in sequence. Denote the heart rate feature data, blood oxygen feature data, and personality feature data as physiological feature data; The feature extraction process includes: For any sequence denoted as the first basic sequence, remove the acquisition outliers in the first basic sequence and sort them in ascending order according to the data size to obtain the second basic sequence. If the second basic sequence corresponds to the second blood oxygen sequence, obtain the z% of the data with the smallest value in the second basic sequence; otherwise, obtain the z% of the data with the largest value in the second basic sequence. Then calculate the average value, denoted as the exercise physiological maximum value MR. Calculate the corresponding feature data through the exercise feature formula, and the exercise feature formula is as follows: , where WR represents the corresponding feature data, and HR represents the average value of the physiological index corresponding to MR in the quiet state.

[0012] Furthermore, the physical and mental health monitoring and early warning of the user based on the physiological abnormal data and physiological feature data includes the following sub-steps: Set the first time length as T0; within the first time length, count the heart rate feature data, blood oxygen feature data, and personality feature data of each exercise of the user and classify them according to the exercise type; for the heart rate feature data, blood oxygen feature data, and personality feature data corresponding to the same exercise type, take the acquisition time as the horizontal axis and the data size as the vertical axis respectively, make a scatter plot on the plane coordinate system, and perform linear fitting respectively to obtain the slopes of the corresponding fitting lines, denoted as the heart rate feature slope GK1, the blood oxygen feature slope GK2, and the personality feature slope GK3 in sequence; Obtain the slopes of the fitting lines corresponding to all the basic similar users of the user when doing the same exercise within the corresponding first time length, and sort them in ascending order according to the slope size, denoted as the first heart rate slope sequence, the first blood oxygen slope sequence, and the first personality slope sequence respectively, and perform reference slope extraction processing respectively to obtain the heart rate reference slope, the blood oxygen reference slope, and the personality reference slope; denoted as CK1, CK2, and CK3 respectively, and denote [CK1*k1, CK1 / k1], [CK2*k1, CK2 / k1], and [CK3*k1, CK3 / k1] as the heart rate reference slope range, the blood oxygen reference slope range, and the personality reference slope range respectively, where k1 is the set ratio; The reference slope extraction processing includes: Set the ratio threshold as k2%, for any slope sequence, remove the data of the smallest (1 - k2) / 2% and the largest (1 - k2) / 2% of the data, and calculate the average value of the remaining data, denoted as the corresponding reference slope; If GK1 is not within [CK1*k1, CK1 / k1], or GK2 is not within [CK2*k1, CK2 / k1], or GK3 is not within [CK3*k1, CK3 / k1], then send the corresponding physiological index early warning information to the user.

[0013] Further, the physical and mental health monitoring and early warning of users based on physiological abnormality data and physiological characteristic data further includes the following sub-steps: Record the user's last three exercises in order from the nearest to the farthest as the recent exercise A, the recent exercise B, and the recent exercise C respectively; obtain the number of each physical abnormality change value in the physiological abnormality data corresponding to the recent exercise A, the recent exercise B, and the recent exercise C respectively, and record them in order as AEj, BEj, and CEj respectively; where j = {1, 2, 3}, and j = 1, j = 2, and j = 3 represent the second heart rate sequence, the second blood oxygen sequence, and the second personality sequence in order. And calculate the total number of recent exercise abnormalities using the total abnormality formula. The total abnormality formula is as follows: , where XEj is the total number of recent exercise abnormalities, n1, n2, and n3 are weight coefficients, n1 > n2 > n3, and n1 + n2 + n3 = 1; Set the corresponding abnormal time threshold TEj. If XEj * t1 > TEj, send the corresponding physiological index early warning information to the user.

[0014] In a second aspect, the present application provides a physical and mental health file information management system based on a big data model, including a user data module, an information collection module, an information processing module, and a monitoring and early warning module; The user data module is used to obtain the user's basic physical information and disease information, and screen the user's basic similar users; The information collection module includes a personality selection unit and a data collection unit. The personality selection unit sets the user's personalized physiological indexes according to the user's disease information, and the data collection unit is used to collect the first exercise physiological information of the user's exercise state; The information processing module is used to perform abnormal screening processing and feature extraction processing on the user's first exercise physiological information to obtain physiological abnormality data and physiological characteristic data; The monitoring and early warning module performs physical and mental health early warning on the user according to the physiological abnormality data and the physiological characteristic data.

[0015] Advantages of the present invention: The present invention obtains the user's basic physical information and disease information, and screens the user's basic similar users; sets the user's personalized physiological indexes according to the user's disease information, and collects the first exercise physiological information of the user's exercise state; performs abnormal screening processing and feature extraction processing based on the user's first exercise physiological information to obtain physiological abnormality data and physiological characteristic data; performs physical and mental health monitoring and early warning on the user according to the physiological abnormality data and the physiological characteristic data; can use the physiological data of the user's historical exercise state to discover potential health risks in the body in advance, and provide accurate physical and mental health monitoring and early warning for the user; The present invention sets personalized physiological indicators for users according to whether the users are ill and the type of illness. The advantages are that it can accurately focus on the key physiological characteristics of users, improve the quality of early warning, make the early warning more accurate, and to a certain extent reduce the monitoring of irrelevant indicators, thus reducing the device power consumption of wearable devices; by calculating the change rate of physiological indicators to analyze and process the data of users in the exercise state, the advantages are that the physiological data in the exercise state is easily affected by various factors, such as the instantaneous change of environmental temperature, exercise intensity, etc.; calculating the change rate can, to a certain extent, eliminate the influence of these short-term and accidental factors and improve the accuracy of abnormal analysis; by comparing and analyzing the data of the user and the data of basically similar users in the historical exercise state, some early signs of potential health problems can be found. Through the comparison and analysis, abnormalities can be detected before the disease develops to the stage of obvious symptoms, thus improving the timeliness of early warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a schematic block diagram of the system of the present invention; Figure 2 is a flowchart of the steps of the method of the present invention; Figure 3 is a flowchart of abnormal screening and processing of the present invention; Figure 4 is a schematic diagram of a sliding window of the present invention; Figure 5 is a schematic diagram of the structure of an electronic device of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0018] Embodiment 1. Please refer to Figure 1 As shown, the present application provides a physical and mental health record information management system based on a big data model, including a user data module, an information collection module, an information processing module, and a monitoring and early warning module; The user data module is used to obtain the basic physical information and disease information of the user and screen the basically similar users of the user; The user data module is configured with a user data strategy. The user data strategy includes: obtaining the user's gender, age, height, and weight through a wearable device, and obtaining the heart rate range and blood oxygen saturation range of the user in a quiet state, which are respectively recorded as [AX1, AX2] and [AY1, AY2] in sequence, and recorded as the basic physical information of the user; Simultaneously obtain whether the user is ill and the type of illness, which is recorded as the user's disease information; According to the user's basic physical information, set the age similarity threshold as v1, the height similarity threshold as v2, and the weight similarity threshold as v3; mark other users who have the same gender as the user and simultaneously satisfy that the age difference is less than or equal to a1, the height difference is less than or equal to a2, and the weight difference is less than or equal to a3 as the reference similar users of the user; in this embodiment, v1 = 3 years old, v2 = 5 cm, v3 = 6 kg. For example, user one, male, 27 years old, 178 cm, 59 kg; user two, male, 30 years old, 180 cm, 62 kg; then user one and user two are reference similar users to each other; For any reference similar user of the user, obtain the heart rate range and blood oxygen saturation range of the reference similar user in the quiet state, and record them as [BX1, BX2] and [BY1, BY2] in sequence. If the reference similar user and the corresponding user have the same type of disease or neither of them is ill, and simultaneously satisfy that [BX1, BX2] ∩ [AX1, AX2] exists, and [(XAB2 - XAB1) / (AX2 - AX1)] ≥ k0, and [BY1, BY2] ∩ [AY1, AY2] exists, and [(YAB2 - YAB1) / (AY2 - AY1)] ≥ k0, then mark the reference similar user as the basic similar user of the corresponding user; where [XAB1, XAB2] = [BX1, BX2] ∩ [AX1, AX2], [YAB1, YAB2] = [BY1, BY2] ∩ [AY1, AY2], and k0 is the set ratio threshold; repeat the screening to obtain all the basic similar users of the user; in this embodiment, k0 is 0.7, that is, the coincidence degree of the range of the same physiological indicators between the reference similar user and the user should be 70%. For example, for a certain user, [AX1, AX2] = [63, 75], [AY1, AY2] = [98, 100], and for a certain reference similar user of the user, [BX1, BX2] = [65, 72], [BY1, BY2] = [97, 100], then [XAB1, XAB2] = [63, 72], [YAB1, YAB2] = [98, 100], then [(XAB2 - XAB1) / (AX2 - AX1)] = (72 - 63) / (75 - 63) = 0.75 ≥ 0.7, [(YAB2 - YAB1) / (AY2 - AY1)] = (100 - 98) / (100 - 98) = 1 ≥ 0.7, so mark the reference similar user as the basic similar user; In the specific implementation process, if the age, height, and weight of the user are too large or too small, resulting in too few or no basic similar users for the user, the corresponding similarity threshold and ratio threshold can be appropriately relaxed; by screening the user's basic similar users, the individual's relative abnormal situation in their own group can be more keenly detected, and a health index reference range more in line with the characteristics of this specific population can be established for subsequent processing.

[0019] The information collection module includes a personality selection unit and a data collection unit. The personality selection unit sets the user's personalized physiological indicators according to the user's disease information, and the data collection unit is used to collect the first exercise physiological information of the user's exercise state. The personality selection unit is configured with a personality selection strategy. The personality selection strategy includes: setting the user's personalized physiological indicators according to whether the user is ill and the type of illness. If the user has a respiratory system disease, the user's personalized physiological indicator is set to the respiratory rate; if the user has a cardiovascular system disease, the user's personalized physiological indicator is set to blood pressure; otherwise, the user's personalized physiological indicator is set to body temperature. Different diseases have a major impact on different physiological systems of the body. For patients with respiratory system diseases, the respiratory rate is a key indicator reflecting the functional state of the respiratory system and can directly reflect the changes in respiratory function. Setting blood pressure as the personalized physiological indicator for cardiovascular system diseases is because blood pressure fluctuations are closely related to the occurrence and development of cardiovascular diseases. For other situations, setting body temperature as the personalized physiological indicator is because body temperature can reflect the overall health state of the body to a certain extent, and many infectious diseases or inflammations will first manifest as abnormal body temperature. The data collection unit is configured with a data collection strategy. The data collection strategy includes: obtaining the average heart rate, average blood oxygen saturation, and average personalized physiological indicator of the user in a quiet state through a wearable device. And obtain the user's exercise state. When the user starts to exercise, the heart rate, blood oxygen saturation, personalized physiological indicator, collection time, and exercise type obtained at the first time interval are recorded as the user's first exercise physiological information. The first time interval is t1. In this embodiment, t1 is 10 seconds. In the specific implementation process, the wearable device can collect data such as acceleration, angular velocity, and heart rate during exercise through sensors such as acceleration sensors, gyroscopes, and heart rate sensors, and then analyze these data and compare them with the pre-stored exercise feature model to determine the exercise state and type.

[0020] The information processing module is used to perform abnormal screening processing and feature extraction processing on the user's first exercise physiological information to obtain physiological abnormal data and physiological feature data. An information processing module is configured with an information processing strategy. The information processing strategy includes: for the first exercise physiological information collected during any exercise of a user, sorting the heart rate, blood oxygen saturation, and personalized physiological indicators according to the collection time respectively to obtain a first heart rate sequence, a first blood oxygen sequence, and a first personalized sequence, and performing a rate of change processing on each of them in sequence to obtain a first heart rate change sequence, a first blood oxygen change sequence, and a first personalized change sequence, and performing an abnormal screening process; the rate of change processing includes: denoting any data value in the corresponding sequence as AR i , and calculating the corresponding change sequence according to the rate of change formula respectively. The rate of change formula is as follows: , where AR i+1 represents the data value at the next moment corresponding to AR i , and AU i represents the corresponding rate of change; Please refer to Figure 3 as shown. The abnormal screening process includes a first abnormal screening and a second abnormal screening. The first abnormal screening includes: setting a first heart rate threshold, a first blood oxygen threshold, and a first personalized threshold. For any data value in the first heart rate change sequence, the first blood oxygen change sequence, and the first personalized change sequence, if it is greater than the corresponding first heart rate threshold, first blood oxygen threshold, and first personalized threshold, it is marked as the corresponding abnormal collection change value; the first abnormal screening mainly screens out the extreme values collected due to collection errors. These data are generally very extreme. Then, the first heart rate threshold, the first blood oxygen threshold, and the first personalized threshold can be set according to the actual application scenario. For example, when a normal person exercises, the heart rate may increase by about 10 to 20 times per minute. Then, the first heart rate threshold can be set at 50 times / minute; Perform a second abnormal screening on the first heart rate change sequence, the first blood oxygen change sequence, and the first personalized change sequence that have completed the first abnormal screening, including: for any change sequence that has completed the first abnormal screening, denote it as the pre-screened change sequence; please refer to Figure 4 as shown. Set the sliding window size to p0 and the sliding step size to p1. Let the sliding window slide on the pre-screened change sequence. Each time it slides, calculate the mean and standard deviation of the data within the sliding window, and denote them as Q1 and Q2 in sequence; and judge all the data within the sliding window. If Q0∉[Q1 - p2*Q2, Q1 + p2*Q2], where Q0 is any data within the sliding window and p2 is the set number of thresholds, then mark the corresponding data as the initial abnormal change value; in this embodiment, the sliding window size p0 is 6, that is, 6 data, the sliding step size is 2, and p2 = 2; that is, each time it slides two data; setting the sliding window can dynamically adjust the threshold according to local data, adapt to the physiological data in a changing trend of the exercise state, and can effectively reduce noise interference, detect abnormal fluctuations in the global and local ranges, and provide accurate and reliable reference data for subsequent early warnings; For any initial abnormal change value in the first heart rate change sequence, the first blood oxygen change sequence, and the first personality change sequence, record the position of the initial abnormal change value in the corresponding change sequence as the abnormal position, and record the abnormal position together with the upper L positions and the lower L positions of the abnormal position as the initial abnormal area corresponding to the initial abnormal change value; If the initial abnormal change value satisfies that there are other initial abnormal change values in the corresponding areas of the other two change sequences to which the initial abnormal area where the initial abnormal change value is located does not belong, then mark the initial abnormal change value as a physical abnormal change value, otherwise mark the initial abnormal change value as a collection abnormal change value; in this embodiment, L = 1. For example, if the 3rd data in a first heart rate change sequence is an initial abnormal change value, then record the 2nd, 3rd, and 4th positions as the initial abnormal area. If there are physical abnormal change values at the 2nd, 3rd, and 4th positions in the corresponding first blood oxygen change sequence and the first personality change sequence, then mark the initial abnormal change value as a physical abnormal change value, otherwise if there is an abnormality at the corresponding position in only one sequence or there is no abnormality in both sequences, then mark it as a collection abnormal change value. Because if the data abnormality is caused by a physical abnormality, it is usually accompanied by abnormalities in other indicators, and considering the advance or lag of each indicator, the initial abnormal area is set; After completing the abnormal screening process, mark the data corresponding to any collection abnormal change value or physical abnormal change value in the first heart rate sequence, the first blood oxygen sequence, and the first personality sequence as a collection abnormal value or a physical abnormal change value. After completion, obtain the second heart rate sequence, the second blood oxygen sequence, and the second personality sequence, and record the second heart rate sequence, the second blood oxygen sequence, and the second personality sequence as physiological abnormal data; Perform feature extraction processing on the second heart rate sequence, the second blood oxygen sequence, and the second personality sequence respectively, and obtain the corresponding heart rate feature data, blood oxygen feature data, and personality feature data in sequence. Record the heart rate feature data, blood oxygen feature data, and personality feature data as physiological feature data; The feature extraction processing includes: For any sequence recorded as the first basic sequence, remove the collection abnormal values in the first basic sequence, and arrange them in ascending order according to the data size to obtain the second basic sequence. If the second basic sequence corresponds to the second blood oxygen sequence, then obtain the smallest z% of the data in the second basic sequence, otherwise obtain the largest z% of the data in the second basic sequence; because when starting to exercise, the blood oxygen shows a decreasing trend and other indicators show an increasing trend, and calculate the average value, which is recorded as the exercise physiological maximum value MR; calculate the corresponding feature data through the exercise feature formula, and the exercise feature formula is as follows: , where WR represents the corresponding feature data, and HR represents the average value of the physiological index corresponding to MR in the quiet state; In the specific implementation process, physiological data in a moving state is easily interfered by various factors, such as environmental temperature, instantaneous changes in exercise intensity, etc., resulting in data fluctuations. The data is screened for anomalies by calculating the change rate of physiological indicators, which can, to a certain extent, eliminate the influence of these short-term and accidental factors and more clearly present the internal change trend of the data. For example, during exercise, blood pressure may fluctuate instantaneously due to sudden changes in posture or other reasons. However, by calculating the change rate of blood pressure, this short-term interference can be distinguished from real abnormal blood pressure changes, improving the accuracy of anomaly analysis.

[0021] The monitoring and warning module gives a physical and mental health warning to the user based on the physiological abnormal data and physiological characteristic data. The monitoring and warning module is configured with a monitoring and warning strategy, which includes: setting the first time length as T0; within the first time length, counting the heart rate characteristic data, blood oxygen characteristic data, and personality characteristic data of each exercise of the user and classifying them according to the exercise type; for the heart rate characteristic data, blood oxygen characteristic data, and personality characteristic data corresponding to the same exercise type, taking the acquisition time as the horizontal axis and the data size as the vertical axis respectively, making a scatter plot on the plane coordinate system, and respectively performing linear fitting to obtain the slopes of the corresponding fitting lines, which are respectively denoted as the heart rate characteristic slope GK1, the blood oxygen characteristic slope GK2, and the personality characteristic slope GK3 in sequence. In this embodiment, the first time length T0 is 6 months. And obtain the slopes of the fitting lines corresponding to the same exercise of all the user's basic similar users within the corresponding first time length, and arrange them in ascending order according to the slope size, which are respectively denoted as the first heart rate slope sequence, the first blood oxygen slope sequence, and the first personality slope sequence, and respectively perform reference slope extraction processing to obtain the heart rate reference slope, the blood oxygen reference slope, and the personality reference slope, which are respectively denoted as CK1, CK2, and CK3, and denote [CK1*k1, CK1 / k1], [CK2*k1, CK2 / k1], and [CK3*k1, CK3 / k1] as the heart rate reference slope range, the blood oxygen reference slope range, and the personality reference slope range respectively, where k1 is the set ratio. In this embodiment, k1 is 0.85. The reference slope extraction processing includes: setting the ratio threshold as k2%, corresponding to any one slope sequence, that is, the slope sequences corresponding to the heart rate, blood oxygen, and personalized physiological indicators respectively; removing the smallest (1 - k2) / 2% of the data and the largest (1 - k2) / 2% of the data, and calculating the average value of the remaining data, which is denoted as the corresponding reference slope. In this embodiment, k2 = 60%, that is, retaining the middle 60% of the data, aiming to remove the extreme values at both ends and make the obtained reference slope more accurate. If GK1 is not within [CK1*k1, CK1 / k1], or GK2 is not within [CK2*k1, CK2 / k1], or GK3 is not within [CK3*k1, CK3 / k1], then corresponding physiological index warning information is sent to the user, that is, a warning message is sent as long as one is not within the corresponding range; The user's last three exercises are respectively recorded as the most recent exercise A, the most recent exercise B, and the most recent exercise C in the order from the nearest to the farthest; the number of each physical abnormal change value in the corresponding physiological abnormal data of the most recent exercise A, the most recent exercise B, and the most recent exercise C is respectively obtained and recorded as AEj, BEj, and CEj in order; where j = {1, 2, 3}, j = 1, j = 2, and j = 3 respectively represent the second heart rate sequence, the second blood oxygen sequence, and the second gender sequence in order. For example, AE2 represents the number of physical abnormal change values in the blood oxygen saturation data collected during the most recent exercise A; And the total number of abnormalities in the most recent exercise is calculated using the total abnormality formula. The total abnormality formula is as follows: , where XEj is the total number of abnormalities in the most recent exercise, n1, n2, and n3 are weight coefficients, n1 > n2 > n3, and n1 + n2 + n3 = 1; in this embodiment, n1 = 0.4, n2 = 0.35, n3 = 0.25, because the more recent data is more valuable for reference; A corresponding abnormal time threshold TEj is set. If XEj*t1 > TEj, then corresponding physiological index warning information is sent to the user; TEj can be set according to the actual application scenario, and generally can be set from 30 seconds to 2 minutes; In the specific implementation process, because each person's physical function and exercise response are different, by comparing and analyzing the data of the user and users with basically similar historical exercise states, the common laws and potential risks of people with similar physical conditions or disease histories during exercise can be found. When a similar risk trend of the user is detected, even if the current data has not exceeded the normal range, a warning can be issued in advance to improve the forward-looking nature of the warning.

[0022] Embodiment 2, please refer to Figure 2 As shown, the present application provides a method for managing physical and mental health file information based on a big data model, including the following steps: Step S1, obtaining the user's basic physical information and disease information, and screening the user's basically similar users; Step S1 includes the following sub-steps: Step S101, obtaining the user's gender, age, height, and weight through a wearable device, and obtaining the heart rate range and blood oxygen saturation range of the user in a quiet state, which are respectively recorded as [AX1, AX2] and [AY1, AY2] in order, and recorded as the user's basic physical information; Step S102: Obtain whether the user is ill and the type of illness simultaneously, which is recorded as the user's disease information. Step S103: According to the user's basic physical information, set the age similarity threshold as v1, the height similarity threshold as v2, and the weight similarity threshold as v3; mark other users who have the same gender as the user and whose age difference is less than or equal to a1, height difference is less than or equal to a2, and weight difference is less than or equal to a3 as the reference similar users of the user. Step S104: For any reference similar user of the user, obtain the heart rate range and blood oxygen saturation range of the reference similar user in a quiet state, and record them as [BX1, BX2] and [BY1, BY2] in sequence. Step S105: If the reference similar user and the corresponding user have the same type of disease or neither of them is ill, and at the same time, [BX1, BX2] ∩ [AX1, AX2] exists, and [(XAB2 - XAB1) / (AX2 - AX1)] ≥ k0, and [BY1, BY2] ∩ [AY1, AY2] exists, and [(YAB2 - YAB1) / (AY2 - AY1)] ≥ k0, then mark the reference similar user as the basic similar user of the corresponding user; where [XAB1, XAB2] = [BX1, BX2] ∩ [AX1, AX2], [YAB1, YAB2] = [BY1, BY2] ∩ [AY1, AY2], and k0 is the set ratio threshold; repeat to screen all the basic similar users of the user.

[0023] Step S2: Set the user's personalized physiological index according to the user's disease information, and collect the first exercise physiological information of the user's exercise state; Step S2 includes the following sub-steps: Step S201: Set the user's personalized physiological index according to whether the user is ill and the type of illness. If the user has a respiratory system disease, set the user's personalized physiological index as the respiratory rate; if the user has a cardiovascular system disease, set the user's personalized physiological index as the blood pressure; otherwise, set the user's personalized physiological index as the body temperature. Step S202: Obtain the average heart rate, average blood oxygen saturation, and average personalized physiological index of the user in a quiet state through a wearable device. Step S203: And obtain the user's exercise state, and record the heart rate, blood oxygen saturation, personalized physiological index, collection time, and exercise type obtained at the first time interval when the user starts to exercise as the user's first exercise physiological information, and the first time interval is t1.

[0024] Step S3: Perform abnormal screening processing and feature extraction processing based on the user's first exercise physiological information to obtain physiological abnormal data and physiological feature data; Step S3 includes the following sub-steps: Step S301: For the first exercise physiological information collected during any user exercise, sort the heart rate, blood oxygen saturation, and personalized physiological indicators according to the collection time respectively to obtain the first heart rate sequence, the first blood oxygen sequence, and the first personalized sequence, and perform rate-of-change processing on them respectively to obtain the first heart rate change sequence, the first blood oxygen change sequence, and the first personalized change sequence in sequence, and perform abnormal screening processing; Step S302: The rate-of-change processing includes: Denote any data value in the corresponding sequence as AR i , and calculate the corresponding change sequence according to the rate-of-change formula respectively. The rate-of-change formula is as follows: , where AR i+1 represents the data value at the next moment corresponding to AR i , and AU i represents the corresponding rate of change; Step S303: The abnormal screening processing includes the first abnormal screening and the second abnormal screening. The first abnormal screening includes: Set the first heart rate threshold, the first blood oxygen threshold, and the first personalized threshold. For any data value in the first heart rate change sequence, the first blood oxygen change sequence, and the first personalized change sequence, if it is greater than the corresponding first heart rate threshold, the first blood oxygen threshold, and the first personalized threshold, then mark it as the corresponding abnormal change value for collection; Step S304: Perform the second abnormal screening on the first heart rate change sequence, the first blood oxygen change sequence, and the first personalized change sequence that have completed the first abnormal screening; Step S304 includes the following sub-steps: Step S3041: For any change sequence that has completed the first abnormal screening, denote it as the preliminarily screened change sequence; Set the sliding window size as p0 and the sliding step as p1, and let the sliding window slide on the preliminarily screened change sequence. Calculate the mean and standard deviation of the data within the sliding window each time it slides, and denote them as Q1 and Q2 in sequence; Step S3042: And judge all the data within the sliding window. If Q0 ∉ [Q1 - p2 * Q2, Q1 + p2 * Q2], where Q0 is any data within the sliding window and p2 is the set number of thresholds, then mark the corresponding data as the initial abnormal change value; Step S3043: For any initial abnormal change value in the first heart rate change sequence, the first blood oxygen change sequence, and the first personalized change sequence, denote the position of the initial abnormal change value in the corresponding change sequence as the abnormal position, and denote the abnormal position together with the upper L positions and the lower L positions of the abnormal position as the initial abnormal region corresponding to the initial abnormal change value; Step S3044: If the initial abnormal change value is satisfied, and there are other initial abnormal change values in the corresponding regions of the other two change sequences to which the initial abnormal region where the initial abnormal change value is located does not belong, then mark the initial abnormal change value as a physical abnormal change value; otherwise, mark the initial abnormal change value as a collection abnormal change value. Step S305: After completing the abnormal screening process, mark the data corresponding to any collection abnormal change value or physical abnormal change value in the first heart rate sequence, the first blood oxygen sequence, and the first personality sequence as a collection abnormal value or a physical abnormal change value. After completion, obtain the second heart rate sequence, the second blood oxygen sequence, and the second personality sequence, and record the second heart rate sequence, the second blood oxygen sequence, and the second personality sequence as physiological abnormal data. Step S306: Perform feature extraction processing on the second heart rate sequence, the second blood oxygen sequence, and the second personality sequence respectively, and obtain the corresponding heart rate feature data, blood oxygen feature data, and personality feature data in sequence. Record the heart rate feature data, blood oxygen feature data, and personality feature data as physiological feature data. Step S307: Feature extraction processing; Step S307 includes the following sub-steps: Step S3071: For any sequence denoted as the first basic sequence, remove the collection abnormal values in the first basic sequence and arrange them in ascending order according to the data size to obtain the second basic sequence. Step S3072: If the second basic sequence corresponds to the second blood oxygen sequence, obtain the smallest z% of the data in the second basic sequence; otherwise, obtain the largest z% of the data in the second basic sequence. Step S3073: And calculate the average value, denoted as the exercise physiological maximum value MR; calculate the corresponding feature data through the exercise feature formula, and the exercise feature formula is as follows: , where WR represents the corresponding feature data, and HR represents the average value of the physiological index corresponding to MR in the quiet state.

[0025] Step S4: Conduct physical and mental health monitoring and early warning for the user based on the physiological abnormal data and the physiological feature data; Step S4 includes the following sub-steps: Step S401: Set the first time length to T0; within the first time length, count the heart rate feature data, blood oxygen feature data, and personality feature data of each exercise of the user and classify them according to the exercise type. Step S402: For the heart rate characteristic data, blood oxygen characteristic data, and personality characteristic data corresponding to the same type of exercise, according to the corresponding acquisition time, with the acquisition time as the horizontal axis and the data size as the vertical axis, scatter plots are made on the plane coordinate system respectively, and linear fittings are performed respectively to obtain the slopes of the corresponding fitted lines, which are denoted as the heart rate characteristic slope GK1, the blood oxygen characteristic slope GK2, and the personality characteristic slope GK3 in sequence; Step S403: Obtain the slopes of the fitted lines corresponding to all the user's basic similar users when doing the same exercise within the corresponding first time period, and arrange them in ascending order according to the slope magnitudes, which are denoted as the first heart rate slope sequence, the first blood oxygen slope sequence, and the first personality slope sequence respectively; Step S404: Perform reference slope extraction processing respectively to obtain the heart rate reference slope, the blood oxygen reference slope, and the personality reference slope; which are denoted as CK1, CK2, and CK3 respectively, and denote [CK1*k1, CK1 / k1], [CK2*k1, CK2 / k1], and [CK3*k1, CK3 / k1] as the heart rate reference slope range, the blood oxygen reference slope range, and the personality reference slope range respectively, where k1 is the set ratio; Step S405: The reference slope extraction processing includes: setting the ratio threshold to k2%, for any one slope sequence, removing the smallest (1 - k2) / 2% of the data and the largest (1 - k2) / 2% of the data, and calculating the average value of the remaining data, which is denoted as the corresponding reference slope; Step S406: If GK1 is not within [CK1*k1, CK1 / k1], or GK2 is not within [CK2*k1, CK2 / k1], or GK3 is not within [CK3*k1, CK3 / k1], then send the corresponding physiological index warning information to the user; Step S407: Denote the user's last three exercises as the most recent exercise A, the most recent exercise B, and the most recent exercise C in order from the nearest to the farthest; Step S408: Respectively obtain the number of each body abnormal change value in the physiological abnormal data corresponding to the most recent exercise A, the most recent exercise B, and the most recent exercise C, which are denoted as AEj, BEj, and CEj in sequence; where j = {1, 2, 3}, and j = 1, j = 2, and j = 3 represent the second heart rate sequence, the second blood oxygen sequence, and the second personality sequence in order; Step S409: Calculate the total number of recent exercise abnormalities using the total abnormality formula. The total abnormality formula is as follows: , where XEj is the total number of recent exercise abnormalities, n1, n2, and n3 are weight coefficients, n1 > n2 > n3, and n1 + n2 + n3 = 1; Step S410: Set the corresponding abnormal time threshold TEj. If XEj * t1 > TEj, send the corresponding physiological index warning information to the user.

[0026] Example 3. Please refer to Figure 5 as shown in Figure 5 which illustrates a schematic structural diagram of an electronic device. The electronic device may include: a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete mutual communication through the communication bus. The memory stores computer-readable instructions. The processor can call the instructions in the memory. When the computer-readable instructions are executed by the processor, it runs the steps in the method for managing physical and mental health file information based on a big data model to achieve the following functions: obtain the user's basic physical information and disease information, and screen for the user's basic similar users; set the user's personalized physiological indexes according to the user's disease information, and collect the first exercise physiological information of the user's exercise state; perform abnormal screening processing and feature extraction processing based on the user's first exercise physiological information to obtain physiological abnormal data and physiological feature data; perform physical and mental health monitoring and warning on the user according to the physiological abnormal data and physiological feature data.

[0027] In addition, when the logical instructions in the above-mentioned memory are implemented in the form of software function units and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The foregoing storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs and other various media that can store program codes.

[0028] Embodiment 4. The present application also provides a computer-readable storage medium. The present application provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method for managing physical and mental health record information based on a big data model are run to achieve the following functions: obtaining the basic physical information and disease information of a user, and screening for basic similar users of the user; setting personalized physiological indicators for the user according to the user's disease information, and collecting first exercise physiological information on the user's exercise state; performing abnormal screening processing and feature extraction processing based on the user's first exercise physiological information to obtain physiological abnormal data and physiological feature data; and performing physical and mental health monitoring and early warning on the user according to the physiological abnormal data and physiological feature data.

[0029] Through the description of the above embodiments, the embodiments of the present invention can be provided as a method, a system or a computer program product. Based on such an understanding, the above technical solution, in essence, or the part that makes a contribution to the prior art can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disc, etc., and includes several instructions for causing 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.

[0030] In the embodiments provided by the present application, it should be understood that the disclosed system or method can be implemented in other ways. The above-described embodiments are merely illustrative. For example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation. For another example, multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some communication interfaces. The indirect coupling or communication connection of the system, module and unit can be in an electrical, mechanical or other form.

[0031] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for managing physical and mental health archive information based on a big data model, characterized in that: The steps include: Obtain the user's basic physical information and disease information, and filter the user's basic similar users; Setting the user's personalized physiological index according to the user's disease information, and collecting the first motion physiological information of the user's motion state; Performing abnormal screening and feature extraction based on the user's first motion physiological information to obtain physiological abnormality data and physiological feature data; Conduct physical and mental health monitoring and early warning for users based on abnormal physiological data and physiological characteristic data.

2. The method for managing physical and mental health archive information based on a big data model according to claim 1, characterized in that: Obtaining the user's basic physical information and disease information and screening the user's basic similar users includes the following sub-steps: The user's gender, age, height and weight are obtained through the wearable device, and the user's heart rate range and blood oxygen saturation range in a quiet state are obtained, which are recorded in order as [AX1, AX2] and [AY1, AY2], respectively, and recorded as the user's basic physical information; At the same time, whether the user is ill and the type of illness are obtained and recorded as the user's disease information; According to the user's basic physical information, the age similarity threshold is set to v1, the height similarity threshold is set to v2, and the weight similarity threshold is set to v3; other users who have the same gender as the user and who also meet the conditions that the age difference is less than or equal to a1, the height difference is less than or equal to a2, and the weight difference is less than or equal to a3 are marked as reference similar users of the user.

3. The method for managing physical and mental health archive information based on a big data model according to claim 2, characterized in that: Obtaining the user's basic physical information and disease information and screening the user's basic similar users also includes the following sub-steps: For any reference similar user of the user, obtain the heart rate range of the reference similar user in a quiet state based on the blood oxygen saturation range, which are recorded as [BX1, BX2] and [BY1, BY2] in order. If the reference similar user and the corresponding user suffer from the same type of disease or neither of them suffer from the disease, and at the same time satisfy [BX1, BX2]∩[AX1, AX2] exists, and [(XAB2-XAB1) / (AX2-AX1)]≥k0, and [BY 1, BY2]∩[AY1, AY2] exists, and [(YAB2-YAB1) / (AY2-AY1)]≥k0, then mark the reference similar user as the basic similar user of the corresponding user; where [XAB1, XAB2]=[BX1, BX2]∩[AX1, AX2], [YAB1, YAB2]=[BY1, BY2]∩[AY1, AY2], k0 is the set ratio threshold; repeatedly filter all the basic similar users of the user.

4. The method for managing physical and mental health archive information based on a big data model according to claim 3 is characterized in that: Setting the personalized physiological index of the user according to the disease information of the user and collecting the first motion physiological information of the user's motion state includes the following sub-steps: The user's personalized physiological index is set according to whether the user is ill and the type of illness. If the user suffers from a respiratory disease, the user's personalized physiological index is set to respiratory rate; if the user suffers from a cardiovascular disease, the user's personalized physiological index is set to blood pressure; otherwise, the user's personalized physiological index is set to body temperature; Obtain the user's average heart rate, average blood oxygen saturation, and average personalized physiological indicators in a quiet state through wearable devices; The user's exercise status is obtained, and the heart rate, blood oxygen saturation, personalized physiological indicators, collection time and exercise type obtained at a first time interval when the user starts exercising are recorded as the user's first exercise physiological information, and the first time interval is t1.

5. The method for managing physical and mental health archive information based on a big data model according to claim 4 is characterized in that: Performing abnormal screening and feature extraction on the user's first motion physiological information to obtain physiological abnormality data and physiological feature data includes the following sub-steps: For the first exercise physiological information collected by the user during any exercise, the heart rate, blood oxygen saturation and personalized physiological indicators are sorted according to the collection time to obtain the first heart rate sequence, the first blood oxygen sequence and the first sexual sequence, and the change rate is processed respectively to obtain the first heart rate change sequence, the first blood oxygen change sequence and the first sexual change sequence in order, and perform abnormal screening processing; The rate of change processing includes: recording any data value in the corresponding sequence as AR i , calculate the corresponding change sequence according to the change rate formula, the change rate formula is as follows: , where AR i+1 Representing AR i The corresponding data value at the next moment, AU i represents the corresponding rate of change; The abnormal screening process includes the first abnormal screening and the second abnormal screening. The first abnormal screening includes: setting the first heart rate threshold, the first blood oxygen threshold and the first sexual threshold. For any data value in the first heart rate change sequence, the first blood oxygen change sequence and the first sexual change sequence, if it is greater than the corresponding first heart rate threshold, the first blood oxygen threshold and the first sexual threshold, it is marked as the corresponding collection abnormal change value.

6. The method for managing physical and mental health archive information based on a big data model according to claim 5, characterized in that: Performing abnormal screening and feature extraction based on the user's first motion physiological information to obtain physiological abnormality data and physiological feature data also includes the following sub-steps: The second abnormality screening is performed on the first heart rate change sequence, the first blood oxygen change sequence and the first sexual change sequence that have completed the first abnormality screening, including: for any change sequence that has completed the first abnormality screening, record it as a primary screening change sequence; set the sliding window size to p0, the sliding step to p1, let the sliding window slide on the primary screening change sequence, calculate the mean and standard deviation of the data in the sliding window each time, and record them as Q1 and Q2 in sequence; and judge all the data in the sliding window, if Q0∉[Q1-p2*Q2, Q1+p2*Q2] is satisfied, where Q0 is any data in the sliding window, and p2 is the set threshold number, then mark the corresponding data as the initial abnormal change value; For any initial abnormal change value in the first heart rate change sequence, the first blood oxygen change sequence, and the first sexual change sequence, the position of the initial abnormal change value in the corresponding change sequence is recorded as the abnormal position, and the abnormal position together with the upper L positions of the abnormal position and the lower L positions of the abnormal position are recorded as the initial abnormal area corresponding to the initial abnormal change value; If the initial abnormal change value satisfies that the initial abnormal area where the initial abnormal change value is located has other initial abnormal change values ​​in the corresponding areas of the other two change sequences to which it does not belong, then the initial abnormal change value is marked as a physical abnormal change value, otherwise the initial abnormal change value is marked as a collection abnormal change value; After completing the abnormal screening process, the data corresponding to any abnormal acquisition change value or abnormal body change value in the first heart rate sequence, the first blood oxygen sequence and the first sexual sequence are marked as acquisition abnormal values ​​or abnormal body change values. After completion, the second heart rate sequence, the second blood oxygen sequence and the second sexual sequence are obtained, and the second heart rate sequence, the second blood oxygen sequence and the second sexual sequence are recorded as physiological abnormality data.

7. The method for managing physical and mental health archive information based on a big data model according to claim 6, characterized in that: Performing abnormal screening and feature extraction based on the user's first motion physiological information to obtain physiological abnormality data and physiological feature data also includes the following sub-steps: Performing feature extraction processing on the second heart rate sequence, the second blood oxygen sequence, and the second personality sequence respectively, obtaining corresponding heart rate feature data, blood oxygen feature data, and personality feature data in sequence, and recording the heart rate feature data, blood oxygen feature data, and personality feature data as physiological feature data; The feature extraction process includes: for any sequence, it is recorded as the first basic sequence, the abnormal values ​​in the first basic sequence are removed, and the data are arranged in ascending order according to the data size to obtain the second basic sequence. If the second basic sequence corresponds to the second blood oxygen sequence, the smallest z% of the data of the second basic sequence is obtained, otherwise the largest z% of the data of the second basic sequence is obtained; and the average value is calculated and recorded as the maximum value of sports physiology MR; the corresponding feature data is calculated by the sports feature formula, and the sports feature formula is as follows: , where WR represents the corresponding characteristic data, and HR represents the average value of the corresponding physiological index of MR in a quiet state.

8. The method for managing physical and mental health archive information based on a big data model according to claim 7, characterized in that: Monitoring and warning the user's physical and mental health based on physiological abnormality data and physiological characteristic data includes the following sub-steps: Set the first time length as T0; count the heart rate characteristic data, blood oxygen characteristic data and personality characteristic data of each exercise of the user within the first time length, and classify them according to the exercise type; for the heart rate characteristic data, blood oxygen characteristic data and personality characteristic data corresponding to the same exercise type, according to the corresponding acquisition time, respectively, use the acquisition time as the horizontal axis and the data size as the vertical axis, make a scatter plot on the plane coordinate system, and perform straight line fitting respectively to obtain the slopes of the corresponding fitting lines, which are recorded in order as the heart rate characteristic slope GK1, the blood oxygen characteristic slope GK2 and the personality characteristic slope GK3; And obtain the slopes of the corresponding fitting lines when all basically similar users of the user do the same exercise within the corresponding first time length, and arrange them in ascending order according to the size of the slope, and record them as the first heart rate slope sequence, the first blood oxygen slope sequence and the first personality slope sequence respectively, and perform reference slope extraction processing respectively to obtain the heart rate reference slope, the blood oxygen reference slope and the personality reference slope; record them as CK1, CK2 and CK3 respectively, and record [CK1*k1, CK1 / k1], [CK2*k1, CK2 / k1] and [CK3*k1, CK3 / k1] as the heart rate reference slope range, the blood oxygen reference slope range and the personality reference slope range respectively, where k1 is the set ratio; The reference slope extraction process includes: setting the ratio threshold to k2%, corresponding to any slope sequence, removing the minimum (1-k2) / 2% data and the maximum (1-k2) / 2% data, and calculating the average value of the remaining data, which is recorded as the corresponding reference slope; If GK1 is not in [CK1*k1, CK1 / k1], or GK2 is not in [CK2*k1, CK2 / k1], or GK3 is not in [CK3*k1, CK3 / k1], corresponding physiological indicator warning information is issued to the user.

9. The method for managing physical and mental health archive information based on a big data model according to claim 8, characterized in that: Monitoring and warning the user's physical and mental health based on physiological abnormality data and physiological characteristic data also includes the following sub-steps: The user's three most recent movements are recorded as recent movement A, recent movement B, and recent movement C in order from recent to recent; the number of each abnormal body change value in the physiological abnormality data corresponding to recent movement A, recent movement B, and recent movement C is obtained respectively, and recorded as AEj, BEj, and CEj in order; Wherein j={1, 2, 3}, j=1, j=2 and j=3 represent the second heart rate sequence, the second blood oxygen sequence and the second linear sequence respectively in order; The total anomaly formula is used to calculate the total number of anomalies in recent movements. The total anomaly formula is as follows: , where XEj is the total number of recent motion anomalies, n1, n2 and n3 are weight coefficients, n1>n2>n3, and n1+n2+n3=1; The corresponding abnormal time threshold TEj is set. If XEj*t1>TEj, the corresponding physiological indicator warning information is issued to the user.

10. A physical and mental health archive information management system based on a big data model, used to implement the physical and mental health archive information management method based on a big data model according to any one of claims 1 to 9, characterized in that: It includes user data module, information collection module, information processing module and monitoring and early warning module; The user data module is used to obtain the user's basic physical information and disease information, and screen the user's basic similar users; The information collection module includes a personality selection unit and a data collection unit. The personality selection unit sets the personalized physiological index of the user according to the disease information of the user. The data collection unit is used to collect the first motion physiological information of the user's motion state. The information processing module is used to perform abnormal screening and feature extraction on the user's first motion physiological information to obtain physiological abnormality data and physiological feature data; The monitoring and early warning module provides physical and mental health early warning to the user based on physiological abnormality data and physiological characteristic data.

Images