CN113208576A - PAI value calculation method, device, equipment and storage medium - Google Patents

PAI value calculation method, device, equipment and storage medium Download PDF

Info

Publication number
CN113208576A
CN113208576A CN202110139450.9A CN202110139450A CN113208576A CN 113208576 A CN113208576 A CN 113208576A CN 202110139450 A CN202110139450 A CN 202110139450A CN 113208576 A CN113208576 A CN 113208576A
Authority
CN
China
Prior art keywords
heart rate
sample
maximum
information
sleep
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Withdrawn
Application number
CN202110139450.9A
Other languages
Chinese (zh)
Inventor
史明澍
朱国康
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Anhui Huami Health Technology Co Ltd
Original Assignee
Anhui Huami Health Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Anhui Huami Health Technology Co Ltd filed Critical Anhui Huami Health Technology Co Ltd
Priority to CN202110139450.9A priority Critical patent/CN113208576A/en
Publication of CN113208576A publication Critical patent/CN113208576A/en
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/024—Detecting, measuring or recording pulse rate or heart rate
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/024—Detecting, measuring or recording pulse rate or heart rate
    • A61B5/02405—Determining heart rate variability
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/48—Other medical applications
    • A61B5/4806—Sleep evaluation
    • A61B5/4809—Sleep detection, i.e. determining whether a subject is asleep or not
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/48—Other medical applications
    • A61B5/4806—Sleep evaluation
    • A61B5/4812—Detecting sleep stages or cycles
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/48—Other medical applications
    • A61B5/4806—Sleep evaluation
    • A61B5/4815—Sleep quality
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment

Abstract

The application provides a PAI value calculation method, a PAI value calculation device, PAI value calculation equipment and a storage medium, which relate to the technical field of data processing, wherein the method comprises the following steps: monitoring a request for starting a personal athletic performance index (PAI), and calculating user data information under the condition that a resting heart rate measurement condition is not met to obtain a resting heart rate and a maximum heart rate; the PAI value is calculated from the resting heart rate and the maximum heart rate. Therefore, the accuracy and individuation of the calculation of the resting heart rate and the maximum heart rate are improved, and the personal exercise function index PAI is more accurately calculated to reflect the real exercise health condition of the individual.

Description

PAI value calculation method, device, equipment and storage medium
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a PAI value calculating method, apparatus, device, and storage medium.
Background
Generally, a personal athletic performance index, PAI, (personal Activity intelligence) is a method of converting a PAI value into a meaningful health risk index, which enables effective quantitative evaluation of an individual's exercise amount, thereby bringing a health benefit to a user.
In the related art, the personal athletic performance index PAI is calculated by the resting heart rate, the maximum heart rate, and the like, and therefore, two parameters, namely the resting heart rate and the maximum heart rate, are important for accurately calculating the personal athletic performance index PAI. However, the maximum heart rate is estimated according to the age of the user, and it is difficult to express the individual difference and to use the default heart rate value, which causes the calculation of the personal motor function index PAI to be biased.
Disclosure of Invention
The present application aims to solve at least to some extent one of the above mentioned technical problems.
Therefore, a first objective of the present application is to provide a PAI value calculating method, which solves the technical problems of low efficiency and poor precision of the resting heart rate and maximum heart rate calculating method in the prior art, and improves the accuracy and personalization of the resting heart rate and maximum heart rate calculation, so that the personal athletic performance index PAI is more accurately calculated to reflect the real exercise health condition of an individual.
A second object of the present application is to provide a PAI value calculating apparatus.
A third object of the present application is to propose a computer device.
A fourth object of the present application is to propose a non-transitory computer-readable storage medium.
To achieve the above object, an embodiment of a first aspect of the present application provides a PAI value calculating method, including: monitoring a request for starting a personal athletic performance index (PAI), and detecting whether a resting heart rate measurement condition is met; under the condition that the resting heart rate measuring condition is not met, calculating user data information to obtain a resting heart rate and a maximum heart rate; a PAI value is calculated from the resting heart rate and the maximum heart rate.
In an embodiment of the application, the calculating the user data information to obtain the resting heart rate and the maximum heart rate includes: acquiring sleep data and exercise data in a preset time period, and calculating based on the received registration information, the sleep data and the exercise data through a trained resting heart rate calculation model to obtain a resting heart rate; calculating based on the registration information through a trained maximum motion calculation model to obtain the maximum motion amount; and calculating based on the registration information and the maximum exercise amount through a trained maximum heart rate calculation model to obtain the maximum heart rate.
In an embodiment of the application, when the sleep data and the exercise data in the preset time period are not acquired, the rest heart rate is acquired by calculating based on the received registration information through a trained rest heart rate calculation model. Therefore, the resting heart rate can be directly calculated based on the registration information, and the calculation efficiency is improved.
In an embodiment of the application, the obtaining of the resting heart rate by the trained resting heart rate calculation model based on the received registration information, the sleep data, and the exercise data includes: calculating a sleep field statistical characteristic and an exercise field statistical characteristic according to the sleep data and the exercise data; acquiring height, weight, age and body mass index according to the registration information, and carrying out standardization processing on the height, weight, age and body mass index to acquire static information characteristics; and inputting the static information characteristics, the sleep field statistical characteristics and the motion field statistical characteristics into the trained resting heart rate calculation model for calculation to obtain the resting heart rate. Therefore, the trained resting heart rate calculation model is used for calculating based on the registration information, the sleep data and the movement data to acquire the resting heart rate, and the accuracy and individuation of the resting heart rate acquisition are further improved.
In an embodiment of the present application, before the obtaining a resting heart rate through the calculation performed by the trained resting heart rate calculation model based on the received registration information, the sleep data, and the exercise data, the method further includes: acquiring a plurality of registration information samples, and sleep information and movement information within a preset time period corresponding to each registration information sample; carrying out standardization processing on the numerical characteristic samples in each registration information sample through a preset formula to obtain static information characteristic samples; coding the gender characteristics in the registration sample information and the sleep information and the motion information in the preset time period corresponding to each registration information sample to obtain a gender characteristic sample, a sleep characteristic sample and a motion characteristic sample; obtaining a rest heart rate sample in the preset time period; training according to the static information characteristic sample, the gender characteristic sample, the sleep characteristic sample, the movement characteristic sample and the rest heart rate sample through a neural network to generate the rest heart rate calculation model. Therefore, the sleep information and the movement information in the preset time period corresponding to the registration information samples and the resting heart rate samples are trained through the neural network, and a resting heart rate calculation model is obtained to improve the efficiency and the accuracy of subsequent resting heart rate calculation.
In an embodiment of the present application, the PAI value calculating method further includes: acquiring sleep data samples and motion data samples within the preset time period through the wearable equipment; performing statistical characteristic calculation on the sleep data sample and the motion data sample to obtain a sleep field statistical characteristic sample and a motion field statistical characteristic sample; training according to the static information characteristic sample, the gender characteristic sample, the sleep field statistical characteristic sample and the motion field statistical characteristic sample through a neural network to generate the resting heart rate calculation model. Therefore, the sleep data sample, the motion data sample and the resting heart rate sample collected based on the registration information sample and the wearable device are trained through the neural network, and a resting heart rate calculation model is obtained to improve the efficiency and the accuracy of subsequent resting heart rate calculation.
In an embodiment of the present application, before the obtaining of the maximum amount of motion through the calculation by the trained maximum motion calculation model based on the registration information, the method further includes: acquiring a user information sample and a historical maximum activity sample within a preset time period through wearable equipment, and training according to the user information sample and the historical maximum activity sample through a neural network to generate the maximum motion calculation model; and/or acquiring a user information sample and the maximum aerobic velocity from an external database, determining a maximum activity sample according to the maximum aerobic velocity, and training according to the user information sample and the maximum activity sample through a neural network to generate the maximum motion calculation model. Therefore, the maximum motion calculation model is trained, and the maximum motion amount can be rapidly calculated and obtained.
In one embodiment of the application, a maximum heart rate sample is obtained, and a maximum heart rate calculation model is generated through a gradient lifting model according to the maximum activity sample, the registration information and the maximum heart rate sample. Therefore, the maximum heart rate calculation model is trained, the maximum heart rate can be calculated and obtained quickly, the personal motor function index PAI can be calculated more accurately, and the real exercise health condition of an individual can be reflected.
To achieve the above object, a second aspect of the present application provides a PAI value calculating apparatus, including: the detection module is used for monitoring a request for starting a personal athletic performance index (PAI) and detecting whether a resting heart rate measurement condition is met; the first acquisition module is used for calculating user data information under the condition that the resting heart rate measurement condition is not met, and acquiring a resting heart rate and a maximum heart rate; and the first calculation module is used for calculating the PAI value according to the rest heart rate and the maximum heart rate.
In an embodiment of the application, the first obtaining module includes: the first calculation unit is used for acquiring sleep data and exercise data in a preset time period, and calculating based on the received registration information, the sleep data and the exercise data through a trained resting heart rate calculation model to obtain a resting heart rate; the second calculation unit is used for calculating based on the registration information through a trained maximum motion calculation model to obtain the maximum motion amount; and the third calculation unit is used for calculating based on the registration information and the maximum exercise amount through a trained maximum heart rate calculation model and acquiring the maximum heart rate.
In an embodiment of the application, the first calculating unit is further configured to calculate based on the received registration information through a trained resting heart rate calculating model when the sleep data and the exercise data in the preset time period are not acquired, and acquire the resting heart rate.
In an embodiment of the application, the first computing unit is specifically configured to: calculating a sleep field statistical characteristic and an exercise field statistical characteristic according to the sleep data and the exercise data; acquiring height, weight, age and body mass index according to the registration information, and carrying out standardization processing on the height, weight, age and body mass index to acquire static information characteristics; and inputting the static information characteristics, the sleep field statistical characteristics and the motion field statistical characteristics into the trained resting heart rate calculation model for calculation to obtain the resting heart rate.
In an embodiment of the present application, the apparatus further includes: the second acquisition module is used for acquiring a plurality of registration information samples, and sleep information and movement information within a preset time period corresponding to each registration information sample; the processing module is used for carrying out standardization processing on the numerical characteristic samples in each registration information sample through a preset formula to obtain static information characteristic samples; the encoding module is used for encoding the gender characteristics in the registered sample information and the sleep information and the motion information in the preset time period corresponding to each registered information sample to obtain a gender characteristic sample, a sleep characteristic sample and a motion characteristic sample; the third acquisition module is used for acquiring a resting heart rate sample in the preset time period; and the first training module is used for training according to the static information characteristic sample, the gender characteristic sample, the sleep characteristic sample, the movement characteristic sample and the rest heart rate sample through a neural network to generate the rest heart rate calculation model.
In an embodiment of the present application, the PAI value calculating apparatus further includes: the second acquisition module is used for acquiring sleep data samples and motion data samples in the preset time period through the wearable equipment; the fourth calculation module is used for performing statistical characteristic calculation on the sleep data samples and the motion data samples to obtain sleep field statistical characteristic samples and motion field statistical characteristic samples; and the second training module is used for training according to the static information characteristic sample, the gender characteristic sample, the sleep field statistical characteristic sample and the motion field statistical characteristic sample through a neural network to generate the static heart rate calculation model.
In an embodiment of the present application, the apparatus further includes: the third training module is used for acquiring a user information sample and a historical maximum activity sample within a preset time period through wearable equipment, and training according to the user information sample and the historical maximum activity sample through a neural network to generate the maximum motion calculation model; and/or the fourth training module is used for acquiring the user information sample and the maximum aerobic velocity from an external database, determining the maximum activity sample according to the maximum aerobic velocity, and training according to the user information sample and the maximum activity sample through a neural network to generate the maximum motion calculation model.
In an embodiment of the present application, the PAI value calculating apparatus further includes: the fourth acquisition module is used for acquiring a maximum heart rate sample; and the fifth training module is used for generating the maximum heart rate calculation model according to the maximum activity sample, the registration information and the maximum heart rate sample through a gradient lifting model.
To achieve the above object, a third aspect of the present application provides a computer device, including: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the PAI value calculating method as described in the above embodiments when executing the computer program.
To achieve the above object, a fourth aspect of the present application provides a non-transitory computer-readable storage medium, wherein instructions of the storage medium, when executed by a processor, enable the processor to implement the PAI value calculating method as described in the above embodiments.
The technical scheme provided by the application at least has the following beneficial technical effects:
monitoring a request for starting a personal athletic performance index (PAI), and calculating user data information under the condition that a resting heart rate measurement condition is not met to obtain a resting heart rate and a maximum heart rate; the PAI value is calculated from the resting heart rate and the maximum heart rate. Therefore, the accuracy and the individuation of PAI value calculation are improved, so that the personal motor function index PAI is more accurately calculated to reflect the real exercise health condition of the individual.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flow chart illustrating a PAI value calculation method provided in an embodiment of the present application;
FIG. 2 is a flow chart illustrating another PAI value calculation method provided in an embodiment of the present application;
FIG. 3 is a flow chart illustrating another PAI value calculation method provided in an embodiment of the present application;
FIG. 4 is an exemplary diagram of a method for constructing a resting heart rate calculation model provided by an embodiment of the present application;
FIG. 5 is an exemplary diagram of a method for constructing a resting heart rate calculation model provided by an embodiment of the present application;
FIG. 6 is an exemplary diagram of a PAI value calculation method provided by an embodiment of the present application;
FIG. 7 is a flow chart illustrating another PAI value calculation method provided in an embodiment of the present application;
FIG. 8 is a diagram illustrating an example of constructing a maximum motion calculation model according to an embodiment of the present disclosure;
FIG. 9 is a flow chart illustrating a further method for calculating a PAI value provided in an embodiment of the present application;
FIG. 10 is a diagram illustrating an example of constructing a maximum motion calculation model according to an embodiment of the present application;
FIG. 11 is a flow chart illustrating a PAI value calculation method provided in an embodiment of the present application;
fig. 12 is a schematic structural diagram of a PAI value calculating apparatus according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application.
A PAI value calculation method, apparatus, device, and storage medium according to embodiments of the present application are described below with reference to the accompanying drawings. The PAI value calculating method according to the embodiment of the present application may be executed by any portable terminal device, where the terminal device may be a hardware device with various operating systems, such as a mobile phone, a tablet computer, a personal digital assistant, and a wearable device, and the wearable device may be an intelligent bracelet, an intelligent watch, an intelligent glasses, and the like.
Fig. 1 is a flow chart illustrating a PAI value calculating method provided in an embodiment of the present application. As shown in fig. 1, the PAI value calculating method includes:
step 101, monitoring a request for turning on a personal athletic performance index, PAI, and detecting whether a resting heart rate measurement condition is met.
In the embodiment of the present application, a request for turning on a personal athletic performance index PAI may be initiated according to a related instruction, or a request for automatically turning on the personal athletic performance index PAI when a preset condition is met, it can be understood that, when the request for turning on the personal athletic performance index PAI indicates that a related PAI value needs to be obtained to calculate the personal athletic performance index PAI, the present application is mainly directed to how to obtain the calculation of the resting heart rate and the maximum heart rate after the request for turning on the personal athletic performance index PAI.
In the present example, the related patent CN107077523A calculates the personal motor function index PAI according to age, gender, resting heart rate and real-time heart rate through formulas (1) - (8).
Specifically, the method comprises the following steps:
Figure BDA0002928015020000061
V＝a2，1，3+a2，1，4(1-e-Z) (2)
Figure BDA0002928015020000062
Figure BDA0002928015020000063
Figure BDA0002928015020000064
HRth＝RHR+HRR×0.2 (6)
HRR＝MHR-RHR (7)
MHR＝a2，1，6-a2，1，7×age (8)
wherein HR (t) is real-time heart rate; t is the integration time; RHR represents the user's resting heart rate; age represents the age of the user; { a2,1,i1,2, 7 is a set of coefficients that need to be statistically calibrated for different ethnic groups of people.
In this application embodiment, receive and open personal motion performance index PAI request, whether detect at first satisfies the resting heart rate measurement condition, that is to say if satisfy the resting heart rate measurement condition, can directly acquire the resting heart rate through wearable equipment direct detection, what this application mainly aimed at is how to acquire the resting heart rate under the condition that does not satisfy the resting heart rate measurement condition.
And 102, under the condition that the resting heart rate measurement condition is not met, calculating the user data information, and acquiring the resting heart rate and the maximum heart rate.
And 103, calculating the PAI value according to the resting heart rate and the maximum heart rate.
In the embodiment of the application, the sleep data and the movement data in the preset time period are collected, and the rest heart rate is obtained by calculating based on the received registration information, the sleep data and the movement data through a trained rest heart rate calculation model; calculating based on the registration information through a trained maximum motion calculation model to obtain the maximum motion amount; and calculating based on the registration information and the maximum exercise amount through a trained maximum heart rate calculation model to obtain the maximum heart rate.
In the embodiment of the present application, the PAI value may be obtained by substituting the obtained resting heart rate and the maximum heart rate into the above equations (1) to (8).
In summary, in the PAI value calculating method of this embodiment, by monitoring the request for starting the PAI index, the user data information is calculated under the condition that the resting heart rate measurement condition is not satisfied, and the resting heart rate and the maximum heart rate are obtained; the PAI value is calculated from the resting heart rate and the maximum heart rate. Therefore, the accuracy and individuation of the calculation of the resting heart rate and the maximum heart rate are improved, and the personal exercise function index PAI is more accurately calculated to reflect the real exercise health condition of the individual.
Fig. 2 is a flow chart illustrating another PAI value calculating method provided in the embodiments of the present application. As shown in fig. 2, the PAI value calculating method includes:
in step 201, a request for turning on a personal athletic performance index PAI is monitored to detect whether a resting heart rate measurement condition is satisfied.
In the embodiment of the present application, a request for turning on a personal athletic performance index PAI may be initiated according to a related instruction, or a request for automatically turning on the personal athletic performance index PAI when a preset condition is met, it can be understood that, when the request for turning on the personal athletic performance index PAI indicates that a related PAI value needs to be obtained to calculate the personal athletic performance index PAI, the present application is mainly directed to how to obtain the calculation of the resting heart rate and the maximum heart rate after the request for turning on the personal athletic performance index PAI.
In the present example, the related patent CN107077523A calculates the personal motor function index PAI according to age, gender, resting heart rate and real-time heart rate through formulas (1) - (8).
Specifically, the method comprises the following steps:
Figure BDA0002928015020000071
V＝a2，1，3+a2，1，4(1-e-Z) (2)
Figure BDA0002928015020000072
Figure BDA0002928015020000073
Figure BDA0002928015020000074
HRth＝RHR+HRR×0.2 (6)
HRR＝MHR-RHR (7)
MHR＝a2，1，6-a2，1，7×age (8)
wherein HR (t) is real-time heart rate; t is the integration time; RHR represents the user's resting heart rate; age represents the age of the user; { a2,1,i1,2, 7 is a set of coefficients that need to be statistically calibrated for different ethnic groups of people.
In this application embodiment, receive and open personal motion performance index PAI request, whether detect at first satisfies the resting heart rate measurement condition, that is to say if satisfy the resting heart rate measurement condition, can directly acquire the resting heart rate through wearable equipment direct detection, what this application mainly aimed at is how to acquire the resting heart rate under the condition that does not satisfy the resting heart rate measurement condition.
Step 202, under the condition that the resting heart rate measuring condition is not met, acquiring sleep data and exercise data in a preset time period, and calculating based on the received registration information, the sleep data and the exercise data through a trained resting heart rate calculation model to obtain the resting heart rate.
In the embodiment of the application, the rest heart rate is the number of beats per minute of a human body in a waking and inactive state.
In the embodiment of the present application, the preset time period may be one week, one month, or the like, and is specifically selected according to an application scenario.
In the embodiment of the application, the trained resting heart rate calculation model is used for calculating based on the received registration information, sleep data and motion data to obtain resting heart rates in various ways, and as a possible implementation manner, the sleeping field statistical characteristics and the motion field statistical characteristics are calculated according to the sleep data and the motion data, the height, the weight, the age and the body quality index are obtained according to the registration information, and the height, the weight, the age and the body quality index are subjected to standardization processing to obtain the static information characteristics; and inputting the static information characteristics, the sleep field statistical characteristics and the motion field statistical characteristics into a trained resting heart rate calculation model for calculation to obtain the resting heart rate.
It is understood that the resting heart rate calculation model is trained in advance, and the specific training process is described in detail later.
It should be noted that when the sleep data and the exercise data within the preset time period are not acquired, the trained resting heart rate calculation model is used for calculating based on the received registration information to acquire the resting heart rate, more specifically, the height, the weight, the age and the body mass index are acquired according to the registration information, and the height, the weight, the age and the body mass index are subjected to standardization processing to acquire the static information characteristics; and inputting the static information characteristics into the trained resting heart rate calculation model for calculation to obtain the resting heart rate.
And 203, calculating based on the registration information through the trained maximum exercise calculation model to obtain the maximum exercise amount, and calculating based on the registration information and the maximum exercise amount through the trained maximum heart rate calculation model to obtain the maximum heart rate.
In step 204, a PAI value is calculated based on the resting heart rate and the maximum heart rate.
In the embodiment of the present application, when the user reaches the maximum exercise intensity that the user can bear, the measured heart rate value is the maximum heart rate.
In the embodiment of the present application, the trained maximum exercise calculation model is calculated based on the registration information to obtain the maximum exercise amount, and it can be understood that the maximum exercise calculation model is a relationship between the registration information and the maximum exercise amount trained in advance, and the specific training process is described in detail later.
Further, the trained maximum heart rate calculation model is used for calculating based on the registration information and the maximum exercise amount to obtain the maximum heart rate, and it can be understood that the maximum exercise calculation model is a relationship among the registration information, the maximum exercise amount and the maximum heart rate which are trained in advance, and the specific training process is described in detail later.
In the embodiment of the present application, the PAI value may be obtained by substituting the obtained resting heart rate and the maximum heart rate into the above equations (1) to (8).
In summary, in the PAI value calculating method of this embodiment, by monitoring the request for starting the PAI, and under the condition that the condition for measuring the resting heart rate is not satisfied, the sleep data and the exercise data within the preset time period are collected, and the trained resting heart rate calculation model is used for calculating based on the received registration information, the sleep data and the exercise data, so as to obtain the resting heart rate; calculating based on the registration information through a trained maximum motion calculation model to obtain the maximum motion amount; and calculating based on the registration information and the maximum exercise amount through a trained maximum heart rate calculation model, acquiring the maximum heart rate, and calculating the PAI value according to the resting heart rate and the maximum heart rate. Therefore, the accuracy and individuation of the calculation of the resting heart rate and the maximum heart rate are improved, and the personal exercise function index PAI is more accurately calculated to reflect the real exercise health condition of the individual.
Based on the above description, it can be appreciated that the resting heart rate calculation model needs to be trained in advance, which is described in detail below in conjunction with fig. 3-5.
Fig. 3 is a flow chart illustrating another PAI value calculating method provided in the embodiments of the present application. As shown in fig. 3, the PAI value calculating method includes:
step 301, obtaining a plurality of registration information samples, and sleep information and exercise information within a preset time period corresponding to each registration information sample.
In this application embodiment, for a new user, historical data information of the wearable device is not available, and generally, the exercise condition and the sleep condition of the individual have a certain correlation with the resting heart rate of the individual, so that the accuracy of resting heart rate evaluation can be improved by collecting the two pieces of information.
Thus, obtaining a sample of registration information includes, in addition to: the height, weight, age, sex, body mass index BMI, and the like, and can also be used for obtaining sleep information and exercise information.
For example, the first problem: ask you how the last week of exercise: regular, occasional, infrequent movements; the second problem is that: ask you how the sleep status of the last week: good, general, poor.
Step 302, performing standardization processing on the numerical characteristic samples in each registration information sample through a preset formula to obtain static information characteristic samples.
In this embodiment of the application, the preset formula may be selectively set according to application scenario requirements, for example, the numerical characteristic sample height, weight, age, and body mass index BMI are numerical characteristics, and are normalized by using the Z score, as shown in the following formula (1):
z-score＝(X–μ)/s(1)
wherein X is a certain numerical characteristic, mu is the average value of the characteristic, and s is the standard deviation.
And 303, coding the gender characteristics in the information of each registration sample and the sleep information and the motion information in the preset time period corresponding to each registration information sample to obtain a gender characteristics sample, a sleep characteristics sample and a motion characteristics sample.
In the embodiment of the present application, the gender characteristics in each piece of registration sample information, and the sleep information and the exercise information in the preset time period corresponding to each piece of registration information sample are encoded, for example, for three classification characteristics, i.e., gender, exercise and sleep condition, one-hot (one hot) codes are used to obtain the gender characteristics sample, the sleep characteristics sample and the exercise characteristics sample.
And step 304, obtaining a resting heart rate sample in a preset time period, training according to the static information characteristic sample, the gender characteristic sample, the sleep characteristic sample, the movement characteristic sample and the resting heart rate sample through a neural network, and generating a resting heart rate calculation model.
In the embodiment of the present application, the resting heart rate sample may use a resting heart rate average value within a preset time period.
Therefore, as shown in fig. 4, the processed static information feature sample, gender feature sample, sleep feature sample, and exercise feature sample are used as input, and the rest heart rate sample is used as output to construct a rest heart rate calculation model.
Based on the above description, for a new user, the historical data information of the wearable device is not available, the sleep data sample and the motion data sample need to be acquired through questionnaires and other manners, for a user who uses the wearable device, the sleep data sample and the motion data sample in a preset time period can be acquired through the wearable device, statistical feature calculation is performed on the sleep data sample and the motion data sample, the sleep field statistical feature sample and the motion field statistical feature sample are acquired, training is performed according to the static information feature sample, the gender feature sample, the sleep field statistical feature sample and the motion field statistical feature sample through a neural network, and a resting heart rate calculation model is generated.
In the embodiment of the present application, the sleep data sample may be one or more of a light sleep time period, a deep sleep time period, a wake-up time period during sleep, a sleep start time, a sleep end time, a total sleep time period, a wake-up time score during sleep, a deep sleep ratio, a sleep time score, a sleep onset time score, a sleep quality score, a sleep onset time period, and the like.
In an embodiment of the present application, the exercise data sample may be one or more of total calories consumed, total distance run, total length of walk, total number of steps, total calories run, total distance walked, high intensity exercise activity amount, low intensity exercise activity amount, number of steps run, time run, number of fast steps, time fast steps, number of slow steps, time slow steps, and the like.
In the embodiment of the present application, for the sleep data samples and the exercise data samples, statistical features, such as one or more of a maximum value, a minimum value, an average value, a median, a standard deviation, a skewness, a kurtosis, and the like, are extracted for the time window according to a preset period, such as one week.
Therefore, as shown in fig. 5, a resting heart rate calculation model is constructed by taking a resting heart rate sample (for example, using a resting heart rate average value in a preset time period) as an output and taking a resting information feature sample, a gender feature sample, a sleep field statistical feature sample and a motion field statistical feature sample as inputs.
It should be noted that the neural network may be set according to application scenario requirements, such as a fully-connected neural network, a convolutional neural network, and the like.
Therefore, under the condition that the resting heart rate measurement condition of the wearable device is not met, the resting heart rate is estimated through the resting heart rate calculation model, the purpose that multidimensional information such as activity, sleeping conditions, height, weight, age, gender, BMI and the like is used is achieved, the resting heart rate of a user is estimated, the personal exercise function index PAI is more accurately calculated, and the real exercise health condition of an individual is reflected.
Based on the trained resting heart rate calculation model, the use can be selected based on different application scenarios, for example, as shown in fig. 6, registration information is acquired (step 601), when a new user uses the PAI function, exercise and sleep condition information required in the resting heart rate calculation model is collected in advance (step 602), under the condition that the measurement condition of the daytime resting heart rate algorithm is met (step 603), the daytime resting heart rate algorithm is preferentially adopted to directly measure (step 604), if the measurement condition is not met, whether the user has wearable device information for 7 days is further checked (step 605), if the measurement condition is met, the resting heart rate is estimated by using the resting heart rate calculation model DNN-b of fig. 5 (step 607), and if the measurement condition is not met, the resting heart rate is estimated by using the resting heart rate calculation model DNN-a of fig. 4 (step 606).
Since the resting heart rate is updated every day, it is necessary to perform the condition determination again to obtain the resting heart rate calculation model each time the date is changed.
Based on the above description, it can be appreciated that the maximum motion calculation model needs to be trained in advance, which is described in detail below in conjunction with fig. 7-10.
Fig. 7 is a flow chart illustrating a PAI value calculating method according to an embodiment of the present disclosure. As shown in fig. 7, the PAI value calculating method includes:
step 701, collecting a user information sample and a historical maximum activity sample within a preset time period through a wearable device.
And step 702, training through a neural network according to the user information sample and the historical maximum activity sample to generate a maximum motion calculation model.
In the embodiment of the present application, in most types of exercise, the exercise intensity reaches a maximum value when the amount of activity of the user (calculated by the acceleration sensor) reaches a maximum.
Therefore, through big data statistical analysis of the wearable device, for different individuals, the records of the maximum activity amount in the historical data of the individual are counted, that is, the user information sample and the historical maximum activity amount sample are obtained, as shown in fig. 8, the height, the weight, the age, the body mass index BMI of the user information sample are used as input, the historical maximum activity amount sample is used as output, and the maximum exercise calculation model is trained.
Fig. 9 is a flowchart illustrating a PAI value calculating method according to an embodiment of the present application. As shown in fig. 9, the PAI value calculation method includes:
step 901, obtaining a user information sample and a maximum aerobic speed from an external database, and determining a maximum activity sample according to the maximum aerobic speed.
And step 902, training according to the user information sample and the maximum activity sample through a neural network to generate a maximum motion calculation model.
In the embodiment of the present application, the correlation between height, weight, age, sex and maximum activity amount is obtained through an external database, that is, the maximum aerobic velocity is measured through a endurance race physical ability test, the maximum aerobic velocity can be mapped to the corresponding maximum activity amount sample through an activity amount calculation method of an acceleration sensor of a wearable device, as shown in fig. 10, the user information sample height, weight, age, and body mass index BMI are used as inputs, the maximum activity amount sample is determined according to the maximum aerobic velocity and used as an output, and a maximum exercise calculation model is trained.
Based on the above description, it can be appreciated that the maximum heart rate calculation model needs to be trained in advance, as described in detail below in connection with fig. 11.
Fig. 11 is a flowchart illustrating a PAI value calculating method according to an embodiment of the present application. As shown in fig. 11, the PAI value calculation method includes:
in step 1101, a maximum heart rate sample is obtained.
Step 1102, generating a maximum heart rate calculation model according to the maximum activity sample, the registration information and the maximum heart rate sample through a gradient lifting model.
In the embodiment of the present application, a mapping relationship between the maximum activity sample and the maximum heart rate sample is constructed, and it can be understood that when the activity of the exercise of the user increases (for example, the running pace increases), the heart rate value also increases, for example, a Gradient lifting model xgboost (extreme Gradient boosting) is used to establish a regression model as shown in formula (2):
hrT＝XGBoost(age、gender、weight、height、BMI、activityT) (2)
wherein age, gender, height, weight and BMI are the age, gender, height, weight and body mass index of the registration information; activityTIs the maximum activity of the opening movement pattern at a certain time T, hrTIs an output value corresponding to the heart rate value at time T.
Therefore, registration information and data acquired by wearable equipment are fused, and the maximum heart rate and resting heart rate evaluation model is established, so that the accuracy and individuation of calculation of the resting heart rate and the maximum heart rate are improved, the PAI is more accurately calculated, and the real exercise health condition of an individual is reflected.
In order to implement the above embodiments, the present application also proposes a PAI value calculating apparatus.
Fig. 12 is a schematic structural diagram of a PAI value calculating apparatus according to an embodiment of the present application.
As shown in fig. 12, the PAI value calculating means includes: a detection module 1210, a first acquisition module 1220, and a first calculation module 1230.
The detecting module 1210 is configured to monitor a request for turning on a personal athletic performance index PAI, and detect whether a resting heart rate measurement condition is satisfied.
The first obtaining module 1220 is configured to calculate the user data information and obtain the resting heart rate and the maximum heart rate under the condition that the resting heart rate measurement condition is not satisfied.
A first calculating module 1230 for calculating the PAI value based on the resting heart rate and the maximum heart rate.
In an embodiment of the present application, the first obtaining module 1220 includes: the first calculation unit is used for acquiring sleep data and exercise data in a preset time period, and calculating based on the received registration information, the sleep data and the exercise data through a trained resting heart rate calculation model to obtain a resting heart rate; the second calculation unit is used for calculating based on the registration information through a trained maximum motion calculation model to obtain the maximum motion amount; and the third calculation unit is used for calculating based on the registration information and the maximum exercise amount through a trained maximum heart rate calculation model and acquiring the maximum heart rate.
In an embodiment of the application, the first calculating unit is further configured to calculate based on the received registration information through a trained resting heart rate calculating model when the sleep data and the exercise data in the preset time period are not acquired, and acquire the resting heart rate.
In an embodiment of the present application, the first calculating unit is specifically configured to calculate a sleep field statistical characteristic and an exercise field statistical characteristic according to the sleep data and the exercise data; acquiring height, weight, age and body mass index according to the registration information, and carrying out standardization processing on the height, weight, age and body mass index to acquire static information characteristics; and inputting the static information characteristics, the sleep field statistical characteristics and the motion field statistical characteristics into a trained resting heart rate calculation model for calculation to obtain the resting heart rate.
In one embodiment of the present application, the PAI value calculating apparatus further comprises: the second acquisition module is used for acquiring a plurality of registration information samples, and sleep information and movement information within a preset time period corresponding to each registration information sample; the processing module is used for carrying out standardization processing on the numerical characteristic samples in each registration information sample through a preset formula to obtain static information characteristic samples; the encoding module is used for encoding the gender characteristics in the registered sample information and the sleep information and the motion information in the preset time period corresponding to each registered information sample to obtain a gender characteristic sample, a sleep characteristic sample and a motion characteristic sample; the third acquisition module is used for acquiring a resting heart rate sample in the preset time period; and the first training module is used for training according to the static information characteristic sample, the gender characteristic sample, the sleep characteristic sample, the movement characteristic sample and the rest heart rate sample through a neural network to generate the rest heart rate calculation model.
In one embodiment of the present application, the PAI value calculating apparatus further comprises: the second acquisition module is used for acquiring sleep data samples and motion data samples in the preset time period through the wearable equipment; the fourth calculation module is used for performing statistical characteristic calculation on the sleep data samples and the motion data samples to obtain sleep field statistical characteristic samples and motion field statistical characteristic samples; and the second training module is used for training according to the static information characteristic sample, the gender characteristic sample, the sleep field statistical characteristic sample and the motion field statistical characteristic sample through a neural network to generate the static heart rate calculation model.
In one embodiment of the present application, the PAI value calculating apparatus further comprises: the third training module is used for acquiring a user information sample and a historical maximum activity sample within a preset time period through wearable equipment, and training according to the user information sample and the historical maximum activity sample through a neural network to generate the maximum motion calculation model; and/or the fourth training module is used for acquiring the user information sample and the maximum aerobic velocity from an external database, determining the maximum activity sample according to the maximum aerobic velocity, and training according to the user information sample and the maximum activity sample through a neural network to generate the maximum motion calculation model.
In one embodiment of the present application, the PAI value calculating apparatus further comprises: the fourth acquisition module is used for acquiring a maximum heart rate sample; and the fifth training module is used for generating the maximum heart rate calculation model according to the maximum activity sample, the registration information and the maximum heart rate sample through a gradient lifting model.
It should be noted that the foregoing explanation of the embodiment of the PAI value calculating method is also applicable to the PAI value calculating apparatus of this embodiment, and will not be described again here.
In summary, the PAI value calculating apparatus of this embodiment calculates the user data information by monitoring the request for starting the PAI index, and under the condition that the resting heart rate measurement condition is not satisfied, obtains the resting heart rate and the maximum heart rate; the PAI value is calculated from the resting heart rate and the maximum heart rate. Therefore, the accuracy and individuation of the calculation of the resting heart rate and the maximum heart rate are improved, and the personal exercise function index PAI is more accurately calculated to reflect the real exercise health condition of the individual.
To achieve the above embodiments, the present application further proposes a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the PAI value calculating method according to the above embodiments is implemented.
To achieve the above embodiments, the present application also proposes a non-transitory computer-readable storage medium in which instructions are enabled to perform the PAI value calculation method described in the above embodiments when executed by a processor.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.

Claims (18)

1. A PAI value calculation method, comprising:
monitoring a request for starting a personal athletic performance index (PAI), and detecting whether a resting heart rate measurement condition is met;
under the condition that the resting heart rate measuring condition is not met, calculating user data information to obtain a resting heart rate and a maximum heart rate;
a PAI value is calculated from the resting heart rate and the maximum heart rate.
2. The method of claim 1, wherein the calculating the user data information to obtain a resting heart rate and a maximum heart rate comprises:
acquiring sleep data and exercise data in a preset time period, and calculating based on the received registration information, the sleep data and the exercise data through a trained resting heart rate calculation model to obtain a resting heart rate;
calculating based on the registration information through a trained maximum motion calculation model to obtain the maximum motion amount;
and calculating based on the registration information and the maximum exercise amount through a trained maximum heart rate calculation model to obtain the maximum heart rate.
3. The PAI value calculating method of claim 2, further comprising:
and when the sleep data and the movement data in the preset time period cannot be acquired, calculating based on the received registration information through a trained resting heart rate calculation model to obtain the resting heart rate.
4. The PAI value computing method of claim 2, wherein the obtaining a resting heart rate through the trained resting heart rate computing model computing based on the received registration information, the sleep data, and the athletic data comprises:
calculating a sleep field statistical characteristic and an exercise field statistical characteristic according to the sleep data and the exercise data;
acquiring height, weight, age and body mass index according to the registration information, and carrying out standardization processing on the height, weight, age and body mass index to acquire static information characteristics;
and inputting the static information characteristics, the sleep field statistical characteristics and the motion field statistical characteristics into the trained resting heart rate calculation model for calculation to obtain the resting heart rate.
5. The PAI value computing method of claim 2, wherein prior to obtaining a resting heart rate from the computing by the trained resting heart rate computing model based on the received registration information, the sleep data, and the athletic data, further comprising:
acquiring a plurality of registration information samples, and sleep information and movement information within a preset time period corresponding to each registration information sample;
carrying out standardization processing on the numerical characteristic samples in each registration information sample through a preset formula to obtain static information characteristic samples;
coding the gender characteristics in the registration sample information and the sleep information and the motion information in the preset time period corresponding to each registration information sample to obtain a gender characteristic sample, a sleep characteristic sample and a motion characteristic sample;
obtaining a rest heart rate sample in the preset time period;
training according to the static information characteristic sample, the gender characteristic sample, the sleep characteristic sample, the movement characteristic sample and the rest heart rate sample through a neural network to generate the rest heart rate calculation model.
6. The PAI value calculating method of claim 5, further comprising:
acquiring sleep data samples and motion data samples within the preset time period through the wearable equipment;
performing statistical characteristic calculation on the sleep data sample and the motion data sample to obtain a sleep field statistical characteristic sample and a motion field statistical characteristic sample;
training according to the static information characteristic sample, the gender characteristic sample, the sleep field statistical characteristic sample and the motion field statistical characteristic sample through a neural network to generate the resting heart rate calculation model.
7. The PAI value calculating method as claimed in claim 2, wherein before the obtaining of the maximum amount of motion by the trained maximum motion calculation model based on the registration information, further comprises:
acquiring a user information sample and a historical maximum activity sample within a preset time period through wearable equipment, and training according to the user information sample and the historical maximum activity sample through a neural network to generate the maximum motion calculation model; and/or the presence of a gas in the gas,
obtaining a user information sample and a maximum aerobic speed from an external database, determining a maximum activity sample according to the maximum aerobic speed, and training according to the user information sample and the maximum activity sample through a neural network to generate the maximum motion calculation model.
8. The PAI value calculating method of claim 7, further comprising:
obtaining a maximum heart rate sample;
and generating the maximum heart rate calculation model according to the maximum activity sample, the registration information and the maximum heart rate sample through a gradient lifting model.
9. A PAI value calculating apparatus, comprising:
the detection module is used for monitoring a request for starting a personal athletic performance index (PAI) and detecting whether a resting heart rate measurement condition is met;
the first acquisition module is used for calculating user data information under the condition that the resting heart rate measurement condition is not met, and acquiring a resting heart rate and a maximum heart rate;
and the first calculation module is used for calculating the PAI value according to the rest heart rate and the maximum heart rate.
10. The PAI value computing apparatus of claim 9, wherein the first obtaining module comprises:
the first calculation unit is used for acquiring sleep data and exercise data in a preset time period, and calculating based on the received registration information, the sleep data and the exercise data through a trained resting heart rate calculation model to obtain a resting heart rate;
the second calculation unit is used for calculating based on the registration information through a trained maximum motion calculation model to obtain the maximum motion amount;
and the third calculation unit is used for calculating based on the registration information and the maximum exercise amount through a trained maximum heart rate calculation model and acquiring the maximum heart rate.
11. The PAI value calculation apparatus of claim 10,
the first calculating unit is further used for calculating based on the received registration information through a trained resting heart rate calculating model when the sleep data and the motion data in the preset time period are not acquired, and obtaining the resting heart rate.
12. The PAI value computing apparatus of claim 10, wherein the first computing unit is to:
calculating a sleep field statistical characteristic and an exercise field statistical characteristic according to the sleep data and the exercise data;
acquiring height, weight, age and body mass index according to the registration information, and carrying out standardization processing on the height, weight, age and body mass index to acquire static information characteristics;
and inputting the static information characteristics, the sleep field statistical characteristics and the motion field statistical characteristics into the trained resting heart rate calculation model for calculation to obtain the resting heart rate.
13. The PAI value computing apparatus of claim 10, further comprising:
the second acquisition module is used for acquiring a plurality of registration information samples, and sleep information and movement information within a preset time period corresponding to each registration information sample;
the processing module is used for carrying out standardization processing on the numerical characteristic samples in each registration information sample through a preset formula to obtain static information characteristic samples;
the encoding module is used for encoding the gender characteristics in the registered sample information and the sleep information and the motion information in the preset time period corresponding to each registered information sample to obtain a gender characteristic sample, a sleep characteristic sample and a motion characteristic sample;
the third acquisition module is used for acquiring a resting heart rate sample in the preset time period;
and the first training module is used for training according to the static information characteristic sample, the gender characteristic sample, the sleep characteristic sample, the movement characteristic sample and the rest heart rate sample through a neural network to generate the rest heart rate calculation model.
14. The PAI value computing apparatus of claim 13, further comprising:
the second acquisition module is used for acquiring sleep data samples and motion data samples in the preset time period through the wearable equipment;
the fourth calculation module is used for performing statistical characteristic calculation on the sleep data samples and the motion data samples to obtain sleep field statistical characteristic samples and motion field statistical characteristic samples;
and the second training module is used for training according to the static information characteristic sample, the gender characteristic sample, the sleep field statistical characteristic sample and the motion field statistical characteristic sample through a neural network to generate the static heart rate calculation model.
15. The PAI value computing apparatus of claim 10, further comprising:
the third training module is used for acquiring a user information sample and a historical maximum activity sample within a preset time period through wearable equipment, and training according to the user information sample and the historical maximum activity sample through a neural network to generate the maximum motion calculation model; and/or the presence of a gas in the gas,
and the fourth training module is used for acquiring the user information sample and the maximum aerobic speed from an external database, determining the maximum activity sample according to the maximum aerobic speed, training according to the user information sample and the maximum activity sample through a neural network, and generating the maximum motion calculation model.
16. The PAI value computing apparatus of claim 15, further comprising:
the fourth acquisition module is used for acquiring a maximum heart rate sample;
and the fifth training module is used for generating the maximum heart rate calculation model according to the maximum activity sample, the registration information and the maximum heart rate sample through a gradient lifting model.
17. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the PAI value calculating method as claimed in any one of claims 1 to 8 when executing the computer program.
18. A non-transitory computer-readable storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the PAI value calculation method as recited in any one of claims 1 to 8.
CN202110139450.9A 2021-02-01 2021-02-01 PAI value calculation method, device, equipment and storage medium Withdrawn CN113208576A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110139450.9A CN113208576A (en) 2021-02-01 2021-02-01 PAI value calculation method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110139450.9A CN113208576A (en) 2021-02-01 2021-02-01 PAI value calculation method, device, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN113208576A true CN113208576A (en) 2021-08-06

Family

ID=77084621

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110139450.9A Withdrawn CN113208576A (en) 2021-02-01 2021-02-01 PAI value calculation method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113208576A (en)

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150374240A1 (en) * 2014-06-26 2015-12-31 Salutron, Inc. Heart Rate Inference Based On Accelerometer And Cardiac Model
CN106203484A (en) * 2016-06-29 2016-12-07 北京工业大学 A kind of human motion state sorting technique based on classification layering
CN106333667A (en) * 2013-06-03 2017-01-18 飞比特公司 Wearable heart rate monitor
CN107041740A (en) * 2016-02-05 2017-08-15 南京国雅信息科技有限公司 Animal heart rate monitoring system and the Heart Rate States recognition methods based on neutral net
CN107077523A (en) * 2014-03-20 2017-08-18 比特斯达克有限公司 Health risk index is determined
CN206534629U (en) * 2016-11-30 2017-10-03 中南民族大学 Health monitoring bracelet and system
CN109567778A (en) * 2017-09-29 2019-04-05 脸谱科技有限责任公司 Heart rate monitor apparatus
CN110457995A (en) * 2019-06-26 2019-11-15 山东师范大学 A kind of human motion amount estimation method based on computer vision and system
CN110840401A (en) * 2019-11-15 2020-02-28 浪潮电子信息产业股份有限公司 Heart rate value measuring method, device and equipment and readable storage medium
CN111208508A (en) * 2019-12-25 2020-05-29 珠海格力电器股份有限公司 Motion quantity measuring method and device and electronic equipment
CN111643066A (en) * 2019-04-30 2020-09-11 上海铼锶信息技术有限公司 Low-power-consumption resting heart rate detection method and wearable device

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106333667A (en) * 2013-06-03 2017-01-18 飞比特公司 Wearable heart rate monitor
CN107077523A (en) * 2014-03-20 2017-08-18 比特斯达克有限公司 Health risk index is determined
US20150374240A1 (en) * 2014-06-26 2015-12-31 Salutron, Inc. Heart Rate Inference Based On Accelerometer And Cardiac Model
CN107041740A (en) * 2016-02-05 2017-08-15 南京国雅信息科技有限公司 Animal heart rate monitoring system and the Heart Rate States recognition methods based on neutral net
CN106203484A (en) * 2016-06-29 2016-12-07 北京工业大学 A kind of human motion state sorting technique based on classification layering
CN206534629U (en) * 2016-11-30 2017-10-03 中南民族大学 Health monitoring bracelet and system
CN109567778A (en) * 2017-09-29 2019-04-05 脸谱科技有限责任公司 Heart rate monitor apparatus
CN111643066A (en) * 2019-04-30 2020-09-11 上海铼锶信息技术有限公司 Low-power-consumption resting heart rate detection method and wearable device
CN110457995A (en) * 2019-06-26 2019-11-15 山东师范大学 A kind of human motion amount estimation method based on computer vision and system
CN110840401A (en) * 2019-11-15 2020-02-28 浪潮电子信息产业股份有限公司 Heart rate value measuring method, device and equipment and readable storage medium
CN111208508A (en) * 2019-12-25 2020-05-29 珠海格力电器股份有限公司 Motion quantity measuring method and device and electronic equipment

Similar Documents

Publication Publication Date Title
RU2757048C1 (en) Method and system for assessing the health of the human body based on the large-volume sleep data
US10512423B2 (en) Determining energy expenditure of a user
US11915825B2 (en) Systems and methods of analyte measurement analysis
US20090171165A1 (en) Sleep evaluation device and sleep evaluation method therefor
RU2602676C2 (en) Fever detection apparatus
CN108601566B (en) Mental stress evaluation method and device
CN112043252B (en) Emotion recognition system and method based on respiratory component in pulse signal
CN111513726B (en) System for evaluating AMS risk based on IHT dynamic performance
CN113171080B (en) Energy metabolism evaluation method and system based on wearable sensing information fusion
CN112582067A (en) Age estimation model training and age estimation method and device based on big data
JP2008086479A (en) Physical activity measuring system
CN112472052A (en) Weight prediction method, device and equipment based on personal motor function index (PAI)
CN111870250A (en) User state monitoring method and device, computing equipment and computer storage medium
CN113208576A (en) PAI value calculation method, device, equipment and storage medium
CN113456027B (en) Sleep parameter assessment method based on wireless signals
KR101483218B1 (en) Activity diagnosis apparatus
CN112786185B (en) Blood pressure health state acquisition method, device and system
Moreno-Pino et al. Heterogeneous Hidden Markov Models for Sleep Activity Recognition from Multi-Source Passively Sensed Data
CN115770028A (en) Blood pressure detection method, system, device and storage medium
CN112967802A (en) Linear fusion model training and age estimation method and device for estimating physiological age
CN113288133A (en) Method, apparatus, storage medium, and processor for predicting blood glucose level
CN108742538B (en) Physical sign measuring method based on big data and artificial intelligence and medical robot system
JP2018166632A (en) Health management device
RU129681U1 (en) SYSTEM FOR DETERMINING THE FUNCTIONAL CONDITION OF A GROUP OF FEEDBACK PEOPLE
RU2763700C1 (en) Method for monitoring the hydration of a living organism

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
WW01 Invention patent application withdrawn after publication

Application publication date: 20210806

WW01 Invention patent application withdrawn after publication