Activity level evaluation method and related equipment

Through a personalized stratification model, the user's heart rate data for one week is used to screen activity intensity, and MET*hours is used to calculate activity volume. This solves the problem of inaccurate assessment in existing technologies and achieves a more accurate and simple activity level assessment.

CN120678404APending Publication Date: 2025-09-23HONOR DEVICE CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202410289338.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-03-13
Publication Date
2025-09-23

AI Technical Summary

Technical Problem

Existing technologies cannot align with international standards and are inaccurate when calculating user activity levels. Traditional questionnaire evaluation methods are cumbersome to operate and provide a poor user experience.

Method used

Through a personalized hierarchical model, the user's heart rate data from the past week is used to screen the heart rates of low activity intensity and medium-to-high activity intensity, and the activity volume is calculated iteratively using MET*hours as the unit, and evaluated in combination with international standards.

Benefits of technology

The accuracy and objectivity of activity level assessment are improved, the assessment results are more in line with the user's actual physical condition, and the operation process is simplified.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120678404A_ABST
    Figure CN120678404A_ABST
Patent Text Reader

Abstract

The invention provides an activity level evaluation method and related equipment, and belongs to the technical field of terminals. The method comprises the following steps: screening a first heart rate of a user under low activity intensity and a second heart rate of the user under medium and high activity intensity according to walking heart rates in heart rate data of the user in the past one week; acquiring a weekly activity level assessment result of the user according to the first heart rate and the second heart rate by using an activity level assessment hierarchical model, the activity level assessment hierarchical model including a first activity level assessment model corresponding to low activity intensity and a second activity level assessment model corresponding to medium and high activity intensity, the activity acquisition module is used for acquiring the corresponding activity amount according to the heart rate, and the unit of the activity amount is Meide MET multiplied by time. According to the method, an activity level analysis result of a user is obtained by taking weekly activity data as an analysis unit through a personalized hierarchical model, so that the problem that an activity level evaluation result cannot be in butt joint with an international standard and is inaccurate is solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of terminal technology, and in particular to a method for evaluating activity levels and related equipment. Background Art

[0002] Daily calorie consumption is often a key concern for users seeking to lose weight, monitor activity levels (or exercise levels) to maintain health, and more. However, calculating activity levels on a daily basis is easily affected by the external environment and the user's exercise habits. Furthermore, the data is limited and cannot objectively and accurately reflect the user's true activity status.

[0003] Currently, calculating and evaluating a user's weekly activity level using a unit called a "metabolism equivalent of energy" (MET) multiplied by an hour (also known as MET*hours, MET*h, or METs*h) has been proven to be scientifically sound and in line with internationally accepted standards. However, the gold standard for this evaluation method is a questionnaire that requires users to recall their physical activity over a week. This is not only less reliable, but also cumbersome and user-friendly.

[0004] Therefore, how to provide an activity level assessment method that can be connected with international standards and provide users with more accurate activity level assessment results has become an urgent problem to be solved. Summary of the Invention

[0005] An embodiment of the present application provides a method and related equipment for activity level assessment, which uses a personalized hierarchical model to obtain the user's activity level analysis results in a rolling iterative manner with weekly activity data as the analysis unit, so as to solve the problem that the activity level assessment results cannot be connected with international standards and are inaccurate.

[0006] This application provides a method for activity level assessment, which screens a user's first heart rate at low activity intensity and a second heart rate at medium-to-high activity intensity based on the user's walking heart rate data from the past week. The method utilizes an activity level assessment hierarchical model to obtain the user's weekly activity level assessment result based on the first heart rate and the second heart rate. The activity level hierarchical model includes a first activity level assessment model corresponding to low activity intensity and a second activity level assessment model corresponding to medium-to-high activity intensity, and is used to obtain the corresponding activity amount based on the heart rate, where the unit of activity amount is MET multiplied by time. This method uses a personalized hierarchical model to obtain the user's activity level analysis results using weekly activity data as the analysis unit, thereby resolving the problem that activity level assessment results cannot be aligned with international standards and are inaccurate.

[0007] In a first aspect, a method for evaluating an activity level is provided, which is applied to an electronic device and includes:

[0008] Acquire heart rate data of a user for at least the past week, wherein the heart rate data includes the user's walking heart rate;

[0009] filtering, based on the walking heart rate, a first heart rate corresponding to the low activity intensity of the user in the past week and a second heart rate corresponding to the medium to high activity intensity of the user in the past week;

[0010] Using an activity level assessment hierarchical model, the weekly activity level assessment result of the user is obtained according to the first heart rate and the second heart rate. The activity level hierarchical model includes a first activity level assessment model corresponding to the low activity intensity and a second activity level assessment model corresponding to the medium and high activity intensity. The first activity level assessment model is used to obtain the activity amount at the low activity intensity according to the first heart rate, and the second activity level assessment model is used to obtain the activity amount at the medium and high activity intensity according to the second heart rate. The units of the activity amount at the low activity intensity and the activity amount at the medium and high activity intensity are METs multiplied by time.

[0011] Among them, the activities in this application can also be described as sports.

[0012] In one possible implementation, a user's walking heart rate refers to the heart rate per minute (HRP) value detected by a smartwatch or phone while the user is walking at a steady pace. If multiple walking heart rate values ​​are obtained in a single day, the average of these values ​​can be calculated and used as the basis for classifying activity intensity.

[0013] In one possible implementation, activity levels can be expressed as metabolic equivalents (METs), which can correspond to a weekly total. METs multiplied by time can be expressed, for example, as METs*h, which is METs multiplied by hours. METs and METs have the same meaning, differing only in their format.

[0014] In a possible implementation, the first activity level assessment model may correspond to the HR-METs model 1 below; and the second activity level assessment model may correspond to the HR-METs model 2 below.

[0015] According to the activity level assessment method provided by this implementation, the user's historical heart rate data and activity intensity data in the past week are used as input samples, and a personalized activity level stratification model adapted to the user's physical condition is used to iteratively calculate the user's activity volume in a week in units of MET*hours. The user's physical activity level is then evaluated according to international standards for physical activity levels, thereby providing the user with activity assessment results that are more in line with the actual physical condition, and improving the objectivity and accuracy of the activity assessment results.

[0016] In conjunction with the first aspect, in certain implementations of the first aspect, screening, based on the walking heart rate, a first heart rate corresponding to the user's low activity intensity over the past week and a second heart rate corresponding to the user's medium to high activity intensity over the past week, specifically includes:

[0017] Filtering the first heart rate in the past week that is lower than or equal to the walking heart rate from the heart rate data;

[0018] The second heart rate that is higher than the walking heart rate in the past week is filtered from the heart rate data.

[0019] The first heart rate corresponds to a low activity intensity, and the second heart rate corresponds to a medium to high activity intensity. The first heart rate and the second heart rate can be input data for obtaining a user activity level assessment after the activity level assessment hierarchical model is established.

[0020] In one possible implementation, after obtaining the user's heart rate, it can be determined whether the heart rate is greater than the user's walking heart rate. If the heart rate is less than or equal to the walking heart rate, it means that the heart rate is a heart rate corresponding to low activity intensity, and the corresponding activity amount can be subsequently calculated using the first activity level assessment model; if the heart rate is greater than the walking heart rate, it means that the heart rate is a heart rate corresponding to medium-to-high activity intensity, and the corresponding activity amount can be subsequently calculated using the second activity level assessment model.

[0021] In conjunction with the first aspect, in certain implementations of the first aspect, screening the second heart rate in the past week that is higher than the walking heart rate from the heart rate data specifically includes:

[0022] Get the user's speed for at least the past week;

[0023] Obtaining a third heart rate in a stable state based on the speed and the heart rate data, wherein, in the stable state: a change in the user's heart rate within a preset time period is less than or equal to a first threshold, and a change in the user's speed within the preset time period is less than or equal to a second threshold;

[0024] The second heart rate that is higher than the walking heart rate is filtered out from the third heart rates.

[0025] It should be understood that in the process of obtaining user activity level assessment results based on the activity level assessment hierarchical model, for situations of high activity intensity, the heart rate in a stable state can be first filtered based on the speed and heart rate, and the heart rate in the stable state corresponds to the third heart rate; and then the heart rate in medium to high activity intensity can be obtained from the heart rate in the stable state, and the heart rate in medium to high activity intensity can correspond to the second heart rate.

[0026] In a possible implementation, the preset duration may be, for example, 1 minute, the first threshold may be, for example, ±10 bpm, and the second threshold may be, for example, ±1 km / h.

[0027] In conjunction with the first aspect, in certain implementations of the first aspect, obtaining the user's weekly activity level result based on the first heart rate and the second heart rate using the activity level stratification model specifically includes:

[0028] inputting the first heart rate of the past week into the first activity level assessment model;

[0029] obtaining the activity amount at the low activity intensity output by the first activity level assessment model; and

[0030] inputting the second heart rate of the past week into the second activity level assessment model;

[0031] Obtaining the activity amount at the medium-high activity intensity output by the second activity level assessment model;

[0032] Adding the activity amount at the low activity intensity and the activity amount at the medium to high activity intensity to obtain the total activity amount for the past week;

[0033] The user's weekly activity level assessment result is obtained based on the total activity amount of the past week.

[0034] In conjunction with the first aspect, in certain implementations of the first aspect, obtaining the user's weekly activity level assessment result based on the total activity amount of the past week specifically includes:

[0035] Obtaining a weekly physical activity coefficient of the user based on the total activity amount of the past week and a preset coefficient;

[0036] The weekly activity level assessment result of the user is obtained based on the physical activity weekly coefficient, wherein the weekly activity level assessment result is used to indicate the level of activity level of the user in the past week, and different ranges of the physical activity weekly coefficient correspond to different activity level levels.

[0037] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes:

[0038] Course recommendation information is displayed, where the course recommendation information is associated with the weekly activity level assessment result.

[0039] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes:

[0040] Recording the activity change trend of the user;

[0041] The prompt information of the activity amount change trend is displayed, and the prompt information is used to indicate the activity amount change trend and the weekly activity level assessment results corresponding to the activity amount of the user at different stages.

[0042] In conjunction with the first aspect, in certain implementations of the first aspect, the heart rate data further includes the user's resting heart rate, and the method further includes:

[0043] Obtaining a resting metabolic equivalent corresponding to the resting heart rate;

[0044] Obtaining the fourth heart rate of the user at low activity intensity over the past week and the low activity intensity metabolic equivalent corresponding to the fourth heart rate, where the units of the resting metabolic equivalent and the low activity intensity metabolic equivalent are METs multiplied by time;

[0045] Linear fitting is performed on the resting heart rate and the resting metabolic equivalent data pair, and the fourth heart rate and the low activity intensity metabolic equivalent data pair to establish the first activity level assessment model.

[0046] It should be understood that the fourth heart rate may refer to the heart rate corresponding to low activity intensity during the training of the activity level assessment hierarchical model, and the fourth heart rate may be used as training data for the activity level assessment hierarchical model.

[0047] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes:

[0048] On a daily basis, linear fitting rolling iterations are performed on the user's resting heart rate and resting metabolic equivalent data pair, as well as the fourth heart rate and low-activity intensity metabolic equivalent data pair corresponding to the user in the past week, to update the first activity level assessment model.

[0049] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes:

[0050] Get the speed reported by the user for at least the past week;

[0051] A fifth heart rate in a stable state and a metabolic equivalent corresponding to the fifth heart rate are screened according to the heart rate data and the speed, wherein, in the stable state: a change amplitude of the user's heart rate is less than or equal to a first threshold at least within a preset time period, and a change amplitude of the user's speed is less than or equal to a second threshold at least within the preset time period.

[0052] The fifth heart rate may refer to the heart rate corresponding to high activity intensity in the training activity level assessment hierarchical model process.

[0053] In one implementation, the stable state may specifically include: within a preset time length (such as 1 minute), the user's heart rate jump is less than or equal to a first threshold (such as ±10bpm), and within the preset time length, the user's speed jump is less than or equal to a second threshold (such as ±1Km / h).

[0054] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes:

[0055] selecting a sixth heart rate from the fifth heart rate that is higher than the walking heart rate;

[0056] Obtain the metabolic equivalent of the medium to high activity intensity corresponding to the sixth heart rate.

[0057] It should be understood that the sixth heart rate may refer to the heart rate corresponding to medium to high activity intensity in a stable state. The sixth heart rate may refer to the heart rate corresponding to high activity intensity during the training of the activity level assessment hierarchical model, and the sixth heart rate may serve as training data for the activity level assessment hierarchical model.

[0058] By screening and obtaining the heart rate and its corresponding metabolic equivalent in a steady state, the screened data pairs can be used to train the activity level assessment model under medium and high activity intensities. Since these data pairs do not include data under low activity intensities and are data under medium and high activity intensities in a steady state, the accuracy of the activity level assessment model under high activity intensities can be guaranteed.

[0059] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes:

[0060] Perform linear fitting on the sixth heart rate and the medium-to-high activity intensity metabolic equivalent data pair to establish the second activity level assessment model.

[0061] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes:

[0062] On a daily basis, linear fitting rolling iteration is performed on the sixth heart rate and the medium-to-high activity intensity metabolic equivalent data pair corresponding to the user in the past week to update the second activity level assessment model.

[0063] In a second aspect, an electronic device is provided, comprising:

[0064] processor;

[0065] Memory;

[0066] The memory stores a computer program, which includes instructions. When the instructions are executed by the processor, the electronic device executes the method described in any implementation of the first aspect.

[0067] In a third aspect, a system for activity level assessment is provided, the system comprising a smart wearable device, a smart terminal and a cloud-side server, wherein the smart wearable device is used to collect the user's heart rate data and speed, the smart terminal is used to obtain the heart rate data and speed sent by the smart wearable device, and send the heart rate data and speed to the cloud-side server, and the cloud-side server is used to execute the method described in any implementation method of the first aspect above.

[0068] In a fourth aspect, a chip system is provided, which includes a processing circuit, a receiving pin and a transmitting pin; wherein the receiving pin, the transmitting pin and the processing circuit communicate with each other through an internal connection path, and the processing circuit executes the method described in any implementation method of the first aspect above to control the receiving pin to receive signals and control the transmitting pin to send signals.

[0069] In a fifth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer-executable program instructions, and when the computer-executable program instructions are run on a computer, the computer executes the method as described in any implementation method of the first aspect above.

[0070] In a sixth aspect, a computer program product is provided, comprising a computer program code, which, when executed on a computer, causes the computer to execute the method described in any one of the implementations of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1A A schematic diagram of a system architecture applicable to a method for activity level assessment provided in an embodiment of the present application.

[0072] Figure 1B A schematic diagram of the principle of a model for obtaining metabolic equivalents (METs) corresponding to heart rate provided in an embodiment of the present application.

[0073] Figure 2 A schematic structural diagram of an electronic device provided in an embodiment of the present application.

[0074] Figure 3 A software structure block diagram of a smart terminal 100 provided in an embodiment of the present application.

[0075] Figure 4 A schematic flow chart of a method for activity level assessment provided in an embodiment of the present application.

[0076] Figures 5A to 5C Schematic diagram of a GUI that may be involved in the implementation of some activity level assessment methods provided in the embodiments of the present application.

[0077] Figure 6 A schematic diagram of an HR-METs model 1 provided in an embodiment of the present application.

[0078] Figure 7 A schematic diagram of a method for obtaining heart rate in a stable state provided in an embodiment of the present application.

[0079] Figure 8 A schematic diagram of a HR-METs model 2 provided in an embodiment of the present application.

[0080] Figure 9 A schematic diagram of an activity level hierarchical model provided in an embodiment of the present application.

[0081] Figures 10A to 10C GUI schematic diagrams that may be involved in the implementation of other activity level assessment methods provided in the embodiments of the present application.

[0082] Figure 11 A schematic flow chart of another method for activity level assessment provided in an embodiment of the present application.

[0083] Figure 12 A schematic flow chart of another method for activity level assessment provided in an embodiment of the present application. DETAILED DESCRIPTION

[0084] It should be noted that the terms used in the implementation methods section of the embodiments of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application. In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this article is merely a way to describe the association relationship of associated obstacles, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, unless otherwise specified, "multiple" means two or more than two, "at least one" and "one or more" mean one, two or more than two.

[0085] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly specifying the number of the technical features indicated. Therefore, the definition of "first" and "second" features may explicitly or implicitly include one or more of the features.

[0086] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in yet other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0087] The following specific embodiments are used to describe the technical solution of the present application in detail. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0088] Combined with the introduction in the background technology, in smart wearable devices, the user's daily activity level is usually automatically quantified in the form of personal scores, that is, the user's activity level is calculated using daily data as the unit of measurement, rather than using MET*hours as the unit of measurement that is common to international standards. Therefore, it is impossible to evaluate the user's activity level using international standards, and it is not convenient for users to compare their personal activity data with international standards. In addition, some common activity level calculation schemes generally assign corresponding coefficients to the heart rate value based on the interval to which the user's heart rate belongs during activity, and then calculate the user's activity level based on the normalized result of the heart rate and coefficient. However, this heart rate interval derived from empirical values ​​lacks personalized consideration of the user's physical condition, cannot cover all people, and does not take into account the stage-by-stage changes in physical condition caused by physical changes such as user fatigue. Therefore, these activity level calculation schemes cannot provide users with an activity level that is consistent with the user's actual physical condition.

[0089] In view of this, an embodiment of the present application provides a method for activity level assessment, which takes the user's historical heart rate data and activity intensity data for the past week as input samples, utilizes a personalized activity level stratification model adapted to the user's physical condition, and iteratively calculates the user's activity volume within a week in units of MET*hours. Then, the user's physical activity level is evaluated according to the international standards for physical activity levels, thereby providing the user with activity assessment results that are more in line with the actual physical condition, and improving the objectivity and accuracy of the activity level assessment results.

[0090] For example, Figure 1AFIG. 1 is a schematic diagram of a system architecture applicable to a method for evaluating activity levels provided in an embodiment of the present application. The system architecture 10 may include a smart terminal 100 , a smart wearable device 200 , and a cloud-side server 300 .

[0091] In some embodiments, the smart terminal 100 may be a device that provides data connectivity to a user, such as a handheld device or vehicle-mounted device with wireless connectivity. A smart terminal may also be referred to as a terminal device, user device, user terminal, or mobile device. The smart terminal 100 may be a variety of electronic devices, including, for example, a mobile phone, tablet computer, laptop computer, PDA, mobile internet device (MID), virtual reality (VR) device, augmented reality (AR) device, and the like. The specific form of the smart terminal is not limited in this embodiment of the present application.

[0092] The smart terminal 100 can be used to interact with the user. For example, the smart terminal 100 can display activity level assessment results, long-term tracking results of the user's activity level, activity suggestions, and recommend relevant courses to the user based on the user's activity level assessment results through an application (App).

[0093] The smart terminal 100 can establish a first communication link with the smart wearable device 200 through an existing communication protocol or other communication protocols that may be used in the future, and exchange data with the smart terminal 100 through the first communication link. For example, the communication method between the smart terminal 100 and the smart wearable device 200 may include Bluetooth (BT) communication, wireless fidelity (Wi-Fi) communication, near field communication (NFC), etc., which is not limited in the embodiments of the present application.

[0094] In addition, the smart terminal 100 can also establish a second communication link with the cloud-side server 300 via an existing communication protocol or other communication protocols that may be developed in the future, and exchange data with the cloud-side server 300 via this second communication link. For example, the smart terminal 100 can report acquired user activity data and vital sign data to the cloud-side server 300 via the second communication link, so that the cloud-side server 300 can analyze and evaluate the user's activity level. After the cloud-side server 300 obtains the user's activity level assessment results, it can also send the activity level assessment results to the smart terminal 100 via the second communication link, so that the smart terminal 100 can display the results to the user.

[0095] In some embodiments, the smart wearable device 200 may be a wearable device that can be used to monitor a user's activity data and vital signs data, such as real-time monitoring of the user's speed, acceleration, heart rate, oxygen uptake, etc. The smart wearable device 200 can be bound to the smart terminal 100 through a user account, password, etc., and can synchronize the real-time acquired activity data and vital signs data to the app of the smart terminal 100 through the first communication link.

[0096] In some embodiments, the cloud-side server 300 can be used to establish a personalized activity level stratification model adapted to the user's physical condition based on the acquired user activity data and vital sign data, and use the established activity level stratification model to analyze and evaluate the user's activity level. The activity data here may include data such as speed and acceleration, and the vital sign data may include the user's heart rate data. The activity level stratification model here may include a first activity level assessment model (or HR-METs model 1) corresponding to low activity intensity and a second activity level assessment model (or HR-METs model 2) corresponding to medium-to-high activity intensity. The basis for dividing low activity intensity and medium-to-high activity intensity may include the user's walking heart rate (wHR). The walking heart rate refers to the heart rate per minute value detected by a smartwatch or mobile phone when the user is walking at a steady speed. If multiple walking heart rate values ​​are obtained in a single day, the average of the multiple walking heart rate values ​​can be calculated and used as the basis for dividing activity intensity. In addition, the metabolic equivalents corresponding to the multiple walking heart rate values ​​can be averaged and defined as the average metabolic equivalent (w-METs) or walking METs; or, the metabolic equivalent corresponding to the average walking heart rate value can be obtained and defined as walking METs. If the user's heart rate during the activity is lower than or equal to the user's walking heart rate, the intensity category corresponding to the activity can be regarded as low activity intensity; if the user's heart rate during the activity is higher than the user's walking heart rate, the intensity category corresponding to the activity can be regarded as medium-high activity intensity. However, the classification of user activities can also be based on other conditions, such as speed stability, etc. This will be introduced in the following embodiments of this application and will not be described in detail here.

[0097] For example, the cloud-side server 300 can obtain the heart rate data reported by the smart terminal 100 through the second communication link, and obtain the user's resting heart rate, resting METs, walking heart rate, and walking METs based on the heart rate data. Then, the cloud-side server 300 can filter out the heart rate at low activity intensity and its corresponding METs data pairs (denoted as heart rate-METs, or (heart rate, METs)) and the heart rate at medium to high activity intensity and its corresponding METs data pairs. The cloud-side server 300 can also train a first activity level assessment model corresponding to low activity intensity based on the resting heart rate and its corresponding resting METs and the (heart rate, METs) data pairs at low activity intensity; and can also train a second activity level assessment model corresponding to medium to high activity intensity based on the (heart rate, METs) data pairs at medium to high activity intensity. Using the trained first activity level assessment model and the second activity level assessment model, and based on the acquired user activity data and vital sign data, the cloud-side server 300 can obtain the user's activity level assessment results corresponding to the past week, and send the activity level assessment results to the smart terminal 100 through the second communication link.

[0098] For example, Figure 1B FIG. 1 is a schematic diagram of a model principle for obtaining metabolic equivalents (METs) corresponding to heart rate provided in an embodiment of the present application. Specifically, the following steps may be included:

[0099] S101A, obtain basic user information.

[0100] Among them, the user's basic information may include the user's height, weight, age, gender, etc.

[0101] S101B collects the user's heart rate data and speed data through smart wearable devices.

[0102] Among them, the smart wearable device can collect the user's heart rate data and speed data through the heart rate sensor and acceleration sensor installed on it. The user's heart rate data may include the user's real-time heart rate, and the user's speed data may include the user's speed and acceleration, etc.

[0103] S102: Send the user's basic information and the user's heart rate data and speed data to the cloud server, and store them on the cloud server.

[0104] In some embodiments, after the smart wearable device collects the user's heart rate data and speed data, it can send the heart rate data and speed data to the cloud-side device through the smart terminal, such as the smart wearable device sends the heart rate data and speed data to the terminal device through a first communication link, and then the terminal device sends the heart rate data and speed data to the cloud-side server through a second communication link.

[0105] S103, inputting the user's basic information, heart rate data, and speed data into a machine learning module, which includes a mapping relationship between heart rate and MET.

[0106] It should be noted that the machine learning module can be a module in the cloud-side server, and the machine learning module includes a model for obtaining MET (hereinafter referred to as the MET prediction model). The MET prediction model can use the mapping relationship between heart rate and MET to obtain the corresponding metabolic equivalent MET based on the user's heart rate and other data. In actual applications, in the process of obtaining MET according to the MET prediction model, in addition to the core indicator of heart rate, the input data can also include other types of data, such as user activity data. The establishment of the MET prediction model relies on the collection of gold standard data. Generally speaking, when establishing the MET prediction model, a gas metabolism meter can be used as a gold standard device to measure and obtain the user's heart rate, speed, acceleration, MET value and other data at the same time stamp, and the user's basic information, heart rate, speed data and measured MET value are fitted by machine learning methods to obtain the MET prediction model. Therefore, the MET prediction model can include a mapping relationship between data such as heart rate and speed and MET value. When applied, the corresponding MET value can be obtained based on the heart rate and speed data.

[0107] S104, obtaining the MET value of activity intensity per unit time output by the machine learning module.

[0108] The activity intensity MET value here can also be described as metabolic equivalent MET.

[0109] S105: Obtain heart rate and its corresponding MET data pair.

[0110] The data pairs here may correspond to the (heart rate, MET) data pairs in the following embodiments of this application.

[0111] In some embodiments, after the cloud-side server obtains the user's basic information, heart rate data, and speed data in step S102, it can use them as input data (for the machine learning module) to directly obtain the (heart rate, MET) data pair in step S105.

[0112] It should be noted that the method of obtaining the corresponding MET based on the heart rate introduced in the embodiment of the present application is only an example. In actual applications, the user's heart rate and its corresponding MET can also be obtained by other methods, and the embodiment of the present application does not limit this.

[0113] For ease of understanding, the following embodiments are introduced by taking the smart terminal 100 as a mobile phone and the smart wearable device 200 as a smart watch as an example. However, in actual applications, the device types of the smart terminal 100 and the smart wearable device 200 are not limited to this.

[0114] For example, Figure 2 , which is a schematic structural diagram of an electronic device provided in an embodiment of the present application. The electronic device may correspond to the smart terminal 100 in the embodiment of the present application, or may correspond to the smart wearable device 200 in the embodiment of the present application. It should be noted that, Figure 2 The structure of the electronic device shown in the embodiment is only an example. In actual applications, the electronic device may have more or fewer components, and the embodiments of the present application are not limited to this.

[0115] The electronic device may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, an earphone interface 170D, a sensor module 180, a button 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc. The sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, an air pressure sensor 180C, a magnetic sensor 180D, an acceleration sensor 180E, a distance sensor 180F, a proximity light sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, an ambient light sensor 180L, a bone conduction sensor 180M, etc.

[0116] It is understood that the structures illustrated in the embodiments of the present invention do not constitute specific limitations on the electronic device. In other embodiments of the present application, the electronic device may include more or fewer components than shown, or may combine or separate certain components, or arrange the components differently. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0117] The processor 110 may include one or more processing units. For example, the processor 110 may include an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU). The different processing units may be independent devices or integrated into one or more processors.

[0118] The controller can be the nerve center and command center of the electronic device. The controller can generate operation control signals based on instruction operation codes and timing signals to complete the control of instruction fetching and execution.

[0119] Processor 110 may also include a memory for storing instructions and data. In some embodiments, the memory in processor 110 is a cache memory. This memory can store instructions or data that have just been used or are being recycled by processor 110. If processor 110 needs to use the same instruction or data again, it can directly access the memory. This avoids duplicate accesses, reduces processor 110 latency, and thus improves system efficiency.

[0120] In some embodiments, the processor 110 may include one or more interfaces. The interfaces may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface.

[0121] It is understood that the interface connection relationship between the modules illustrated in the embodiments of the present invention is only a schematic illustration and does not constitute a structural limitation of the electronic device. In other embodiments of the present application, the electronic device may also adopt different interface connection methods in the above embodiments, or a combination of multiple interface connection methods.

[0122] The charging management module 140 is used to receive charging input from a charger. The charger can be a wireless charger or a wired charger. In some wired charging embodiments, the charging management module 140 can receive charging input from the wired charger via the USB interface 130. In some wireless charging embodiments, the charging management module 140 can receive wireless charging input via the wireless charging coil of the electronic device. While charging the battery 142, the charging management module 140 can also provide power to the terminal through the power management module 141.

[0123] The power management module 141 is used to connect the battery 142, the charging management module 140 and the processor 110. The power management module 141 receives input from the battery 142 and / or the charging management module 140, and provides power to the processor 110, the internal memory 121, the external memory, the display 194, the camera 193, and the wireless communication module 160. The power management module 141 can also be used to monitor parameters such as battery capacity, battery cycle count, and battery health status (leakage, impedance). In some other embodiments, the power management module 141 can also be set in the processor 110. In other embodiments, the power management module 141 and the charging management module 140 can also be set in the same device.

[0124] The wireless communication function of the electronic device can be implemented through antenna 1, antenna 2, mobile communication module 150, wireless communication module 160, modem processor and baseband processor.

[0125] Antenna 1 and Antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in an electronic device can be used to cover a single or multiple communication frequency bands. Different antennas can also be reused to improve antenna utilization. For example, antenna 1 can be reused as a diversity antenna for a wireless local area network. In other embodiments, the antennas can be used in conjunction with a tuning switch.

[0126] The mobile communication module 150 can provide solutions for wireless communications including 2G / 3G / 4G / 5G applied in electronic devices. The mobile communication module 150 may include at least one filter, a switch, a power amplifier, a low noise amplifier (LNA), etc. The mobile communication module 150 can receive electromagnetic waves from the antenna 1, and filter, amplify, and process the received electromagnetic waves, and transmit them to the modulation and demodulation processor for demodulation. The mobile communication module 150 can also amplify the signal modulated by the modulation and demodulation processor, and convert it into electromagnetic waves for radiation through the antenna 1. In some embodiments, at least some of the functional modules of the mobile communication module 150 can be set in the processor 110. In some embodiments, at least some of the functional modules of the mobile communication module 150 can be set in the same device as at least some of the modules of the processor 110.

[0127] The modem processor may include a modulator and a demodulator. The modulator is used to modulate the low-frequency baseband signal to be transmitted into a medium-high frequency signal. The demodulator is used to demodulate the received electromagnetic wave signal into a low-frequency baseband signal. The demodulator then transmits the demodulated low-frequency baseband signal to the baseband processor for processing. After being processed by the baseband processor, the low-frequency baseband signal is passed to the application processor. The application processor outputs a sound signal through an audio device (not limited to the speaker 170A, the receiver 170B, etc.) or displays an image or video through the display screen 194. In some embodiments, the modem processor may be an independent device. In other embodiments, the modem processor may be independent of the processor 110 and be set in the same device as the mobile communication module 150 or other functional modules.

[0128] The wireless communication module 160 can provide wireless communication solutions for electronic devices, including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared (IR), etc. The wireless communication module 160 can be one or more devices that integrate at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via the antenna 2, frequency modulates and filters the electromagnetic wave signals, and sends the processed signals to the processor 110. The wireless communication module 160 can also receive the signal to be sent from the processor 110, frequency modulate it, amplify it, and convert it into electromagnetic waves for radiation through the antenna 2.

[0129] In some embodiments, the antenna 1 of the electronic device is coupled to the mobile communication module 150, and the antenna 2 is coupled to the wireless communication module 160, so that the electronic device can communicate with the network and other devices through wireless communication technology. The wireless communication technology may include global system for mobile communications (GSM), general packet radio service (GPRS), code division multiple access (CDMA), wideband code division multiple access (WCDMA), time-division code division multiple access (TD-SCDMA), long term evolution (LTE), BT, GNSS, WLAN, NFC, FM, and / or IR technology. The GNSS may include global positioning system (GPS), global navigation satellite system (GLONASS), Beidou navigation satellite system (BDS), quasi-zenith satellite system (QZSS) and / or satellite based augmentation system (SBAS).

[0130] The electronic device implements a display function through a GPU, a display screen 194 , and an application processor, etc. The display screen 194 is used to display images, videos, etc.

[0131] The electronic device can realize the shooting function through the ISP, camera 193, video codec, GPU, display 194 and application processor.

[0132] Digital signal processors (DSPs) are used to process digital signals. Besides digital image signals, they can also process other digital signals. For example, when an electronic device selects a frequency, the DSP performs a Fourier transform on the frequency energy. Video codecs compress or decompress digital video. The NPU is a neural network (NN) computing processor. By drawing on the structure of biological neural networks, such as the transmission patterns between neurons in the human brain, it can rapidly process input information and continuously self-learn.

[0133] The external memory interface 120 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device. The external memory card communicates with the processor 110 via the external memory interface 120 to implement data storage. For example, files such as music and videos can be stored on the external memory card. The internal memory 121 can be used to store computer-executable program code, including instructions.

[0134] The electronic device can implement audio functions such as music playback and recording through the audio module 170, the speaker 170A, the receiver 170B, the microphone 170C, the headphone jack 170D, and the application processor.

[0135] The pressure sensor 180A is used to sense pressure signals and convert them into electrical signals. The gyroscope sensor 180B can be used to determine the active posture of the electronic device. The magnetic sensor 180D includes a Hall effect sensor. The electronic device can use the magnetic sensor 180D to detect the opening and closing of the flip cover. The acceleration sensor 180E can detect the magnitude of the electronic device's acceleration in various directions (generally three axes). When the electronic device is stationary, it can detect the magnitude and direction of gravity. It can also be used to identify the terminal's posture and is used in applications such as landscape and portrait screen switching and pedometers. The proximity light sensor 180G can include, for example, a light-emitting diode (LED) and a light detector, such as a photodiode. The LED can be an infrared LED. The electronic device emits infrared light through the LED. The ambient light sensor 180L is used to sense the brightness of the ambient light. The electronic device can adaptively adjust the brightness of the display screen 194 based on the perceived ambient light brightness. The fingerprint sensor 180H is used to collect fingerprints. The temperature sensor 180J is used to detect temperature. The touch sensor 180K is also called a "touch panel." Touch sensor 180K can be mounted on display screen 194. Together, touch sensor 180K and display screen 194 form a touch screen, also known as a "touch screen." Touch sensor 180K is used to detect touch operations applied to or near it. Bone conduction sensor 180M can capture vibration signals.

[0136] In addition, the electronic device also includes an air pressure sensor 180C and a distance sensor 180F. The air pressure sensor 180C is used to measure air pressure. In some embodiments, the electronic device calculates altitude using the air pressure value measured by the air pressure sensor 180C to assist in positioning and navigation.

[0137] Distance sensor 180F is used to measure distance. The electronic device can measure distance using infrared or laser. In some embodiments, when shooting a scene, the electronic device can use distance sensor 180F to measure distance to achieve fast focus.

[0138] For example, the software system of the smart terminal 100 can adopt a layered architecture, an event-driven architecture, a micro-kernel architecture, a microservice architecture, or a cloud architecture. In the embodiment of the present application, the Android system with a layered architecture is used as an example to illustrate the software structure of the smart terminal 100. Figure 3 It is a software structure block diagram of a smart terminal 100 provided in an embodiment of the present application.

[0139] A layered architecture divides software into several layers, each with distinct roles and responsibilities. Layers communicate with each other through software interfaces. In some embodiments, the Android system is divided into four layers: application layer, application framework layer, Android runtime, system library, kernel layer, hardware abstraction layer (HAL), and hardware layer.

[0140] The application layer can include a series of application packages. Figure 3 As shown, the application package may include applications such as camera, calendar, map, WLAN, music, short message, Bluetooth, video, social, gallery, navigation, etc.

[0141] The application framework layer provides application programming interface (API) and programming framework for the applications in the application layer. The application framework layer includes some predefined functions. Figure 3 As shown, the application framework layer may include a window manager, a content provider, a phone manager, a resource manager, a notification manager, a view system, and the like.

[0142] The window manager is used to manage window programs. The window manager can obtain the display size, determine whether there is a status bar, lock the screen, take screenshots, etc.

[0143] Content providers are used to store and retrieve data and make it accessible to applications. The data may include videos, images, audio, calls made and received, browsing history and bookmarks, phone books, etc.

[0144] The view system includes visual controls, such as those for displaying text and images. The view system is used to build applications. A display interface can consist of one or more views. For example, a display interface containing a text notification icon might include a view for displaying text and a view for displaying images.

[0145] The phone manager is used to provide communication functions of the smart terminal 100, such as management of call status (including answering, hanging up, etc.).

[0146] The resource manager provides various resources for applications, such as localized strings, icons, images, layout files, video files, and so on.

[0147] The Notification Manager allows applications to display notifications in the status bar. These messages can be displayed briefly and then disappear automatically, without requiring user interaction. For example, the Notification Manager can be used to notify users of completed downloads and message reminders. The Notification Manager can also display notifications in the top status bar as icons or scrolling text, such as notifications from background applications, or as dialog windows on the screen. Examples include displaying text messages in the status bar, emitting alert sounds, vibrating the terminal, or flashing indicator lights.

[0148] Android Runtime includes core libraries and a virtual machine. Android runtime is responsible for scheduling and management of the Android system.

[0149] The core library consists of two parts: one is the function that needs to be called by the Java language, and the other is the Android core library.

[0150] The application layer and application framework layer run in a virtual machine. The virtual machine executes the Java files in the application layer and application framework layer as binary files. The virtual machine is responsible for managing the object lifecycle, stack management, thread management, security and exception management, and garbage collection.

[0151] The system library can include multiple functional modules, such as surface manager, media library, 3D graphics processing library (such as OpenGL ES), 2D graphics engine (such as SGL), etc.

[0152] The surface manager is used to manage the display subsystem and provide fusion of 2D and 3D layers for multiple applications.

[0153] The media library supports playback and recording of a variety of common audio and video formats, as well as static image files. The media library can support a variety of audio and video encoding formats, such as: MPEG4, H.264, MP3, AAC, AMR, JPG, PNG, etc.

[0154] The 3D graphics processing library is used to implement 3D graphics drawing, image rendering, compositing, and layer processing.

[0155] A 2D graphics engine is a drawing engine for 2D drawings.

[0156] The kernel layer is the layer between hardware and software. The kernel layer includes at least display driver, camera sensor driver, audio driver, and sensor driver.

[0157] For example, Figure 4 , which is a schematic flow chart of obtaining activity level assessment based on an activity level hierarchical model provided by an embodiment of the present application.

[0158] It should be noted that the execution subject of this process can be a cloud-side server, a mobile phone, or a smart watch, and this embodiment of the application does not limit this. For ease of understanding, the following is an example of the execution subject of this process being a cloud-side server. The process may specifically include the following steps:

[0159] S401, obtaining basic information of the user.

[0160] The basic information of the user may include, for example, the user's age, gender, weight, height, etc.

[0161] In some embodiments, there are multiple ways to obtain user basic information, such as: Method (1), the mobile phone obtains the basic information manually input by the user through the sports health APP installed on it, for example, Figure 5A and Figure 5BAs shown, when a user registers and uses the Sports Health APP for the first time, he or she enters his or her basic information through the relevant interface; then, the mobile phone uploads the basic information to the cloud-side server via the second communication link. Method (2): The mobile phone automatically reads the basic information of the user stored locally. If the user has already entered his or her basic information in other apps or when registering a mobile phone account, the mobile phone stores the basic information in the local space; when the user basic information needs to be read again, the mobile phone can automatically read it from the local space after obtaining the user's authorization; then, the mobile phone can upload the basic information of the user to the cloud-side server via the second communication link. Method (3): The cloud-side server automatically reads the basic information of the user stored in the cloud or stored in a third-party device. For example, the cloud-side server can obtain the basic information of the user from the mobile phone or smart watch in advance and store it in the cloud-side space. When the cloud-side server obtains the user's first registration and use of the Sports Health APP, it can automatically read the basic information of the user stored in the cloud-side space or read the basic information of the user from the third-party device after obtaining the user's authorization.

[0162] It should be noted that the above-mentioned method of obtaining basic user information is only an example. In actual applications, the basic user information can also be obtained through other methods, and the embodiments of the present application do not limit this.

[0163] S402: Obtain the user's resting heart rate, walking heart rate, and walking METs over the past week.

[0164] In some embodiments, when the activity level assessment function is first turned on, the mobile phone or smart watch may display a prompt message to the user, prompting that the user's activity data and vital signs data for one week need to be collected when using the function for the first time. Figure 5C As shown, when the user turns on the activity level assessment function on the mobile phone for the first time (such as when registering to use the sports health APP for the first time), the mobile phone interface may display a prompt message "To ensure the accuracy of the activity level assessment results, at least 7 days of activity data and vital signs data need to be collected. Please wear the smart watch as much as possible." When the user clicks the confirmation button below the prompt message, the mobile phone obtains authorization to collect the user's activity data and vital signs data, and can collect and accumulate the user's activity data and vital signs data.

[0165] It should be noted that when the user activity data obtained is less than one week, the mobile phone and smart watch may not provide the activity level assessment results to the user until sufficient (at least one week) activity data is obtained, and then provide the activity level assessment results to the user.

[0166] In some embodiments, while a user is wearing a smartwatch, the smartwatch can periodically collect the user's activity data and vital sign data, including speed, heart rate, and other information during activity. The smartwatch can then transmit the collected data to the mobile phone via a first communication link, which then uploads the data to a cloud-side server. After receiving the user's activity and vital sign data, the cloud-side server can train an activity level stratification model corresponding to the user based on this data and / or assess the user's activity level based on the trained activity level stratification model.

[0167] In some embodiments, the smart watch can collect activity data and vital sign data of the user in different states, such as the user's resting heart rate in a quiet state, the walking heart rate and walking speed in a walking state, the jogging heart rate and running speed in a jogging state, etc.

[0168] S403 : Fitting is performed based on the user's resting heart rate, resting METs, and the heart rate at low activity intensity and its corresponding METs to obtain HR-METs model 1 .

[0169] Among them, the resting heart rate is also called the resting heart rate, which refers to the number of heartbeats per minute of the user in a quiet state of wakefulness and inactivity. Resting METs refers to metabolic equivalents (rest-METs) in a resting state. In an embodiment of the present application, resting METs can be defined as an initial value, for example, set to 1 MET. The heart rate at low activity intensity may refer to a heart rate that is lower than or equal to the walking heart rate. METs at low activity intensity may refer to METs corresponding to a heart rate that is lower than or equal to the walking heart rate. Walking heart rate refers to the number of heartbeats per minute of the user in a stable walking state. Walking METs refers to the activity equivalent corresponding to the walking heart rate. Since each user's physical condition is different, the resting heart rate, resting METs, walking heart rate and walking METs corresponding to different users may also be different.

[0170] In some embodiments, a smartwatch or mobile phone can detect the user's heart rate per minute while walking at a steady pace. If multiple walking heart rate values ​​are obtained in a single day, the average of these multiple walking heart rate values ​​can be taken and used as the basis for classifying activity intensity (i.e., corresponding to the walking heart rate mentioned above). In addition, the metabolic equivalents corresponding to the multiple walking heart rate values ​​can be averaged and defined as average metabolic equivalents (w-METs) or walking METs; alternatively, the metabolic equivalent corresponding to the average walking heart rate values ​​can be obtained and defined as walking METs.

[0171] In some embodiments, the process of fitting and obtaining the HR-METs model 1 based on the resting heart rate, resting METs, heart rate at low activity intensity and its corresponding METs may include: determining the resting heart rate corresponding to the user in a quiet state (such as the user's heart rate when the speed is 0) based on the acquired vital sign data and activity data, and defining the METs corresponding to the resting heart rate as an initial value, for example, setting it to 1 MET; and, obtaining the walking heart rate corresponding to the user in a walking state (such as the user's heart rate at walking speed) and the walking METs corresponding to the walking heart rate based on the acquired vital sign data and activity data; obtaining a first activity heart rate with a heart rate value between the resting heart rate and the walking heart rate range and a first METs corresponding to the first activity heart rate, that is, obtaining a (first activity heart rate, first METs) data pair corresponding to the low activity intensity; in a similar manner, the (resting heart rate, resting METs) data pair and the (first activity heart rate, first METs) data pair for each day of the week can be obtained. The resting heart rate included in the daily (resting heart rate, resting METs) data pair can be the average of resting heart rates measured multiple times each day, and the resting METs can be the MET value corresponding to the average resting heart rate. The first heart rate included in the daily (first activity heart rate, first METs) data pair can be the average of heart rates corresponding to multiple low-intensity activities each day, and the first METs can be the MET value corresponding to the average of these heart rates. HR-METs model 1 can then be obtained by fitting the (resting heart rate, resting METs) data pairs and (first activity heart rate, first METs) data pairs for each day of the week (a total of 14 data pairs).

[0172] Optionally, since the user may perform multiple low-intensity activities every day, there may be multiple (first activity heart rate, first METs) data pairs corresponding to the low activity intensity every day. Assuming that there are m (first activity heart rate, first METs) data pairs corresponding to the low activity intensity in a week, and m is an integer greater than or equal to 1, then linear fitting can be performed based on the (resting heart rate, resting METs) data pairs and m groups of (first activity heart rate, first METs) data pairs to obtain the HR-METs model 1 corresponding to the user at low activity intensity. The (resting heart rate, resting METs) data pair here can be the average value of the resting heart rate in a week and its corresponding MET value, in which case there is one (resting heart rate, resting METs) data pair; or it can be the average value of the resting heart rate corresponding to each day of the week and its corresponding MET value, in which case there are seven (resting heart rate, resting METs) data pairs. Exemplarily, the HR-METs model 1 obtained by fitting can be, for example, as follows Figure 6 As shown, Figure 6 The number of data pairs shown (i.e., the number of points in the figure) is only an example. Figure 8The number of data pairs shown (ie, the number of points in the figure) is only an example and is not intended to be limiting.

[0173] In some embodiments, the cloud-side server can obtain the HR-METs model 1 through a rolling iteration. Specifically, the cloud-side server can periodically obtain the user's activity data and vital sign data, for example, obtaining the user's speed and heart rate reported by the mobile phone every 10 minutes. The cloud-side server then stores the user's activity data and vital sign data. The cloud-side server can then perform rolling iterations on the HR-METs model 1 at a specific time each day based on the stored user activity data and vital sign data from the past week. For example, if the cloud-side server obtains the HR-METs model 1 at 00:00 on March 8, 2024, using the user's activity data and vital sign data from March 1 to March 7, 2024, then the cloud-side server can iteratively update the HR-METs model 1 24 hours later at 00:00 on March 9, 2024, using the user's activity data and vital sign data from March 2 to March 8, 2024.

[0174] It can be understood that since the HR-METs model 1 is trained and acquired through rolling iterations, the training data used to establish the HR-METs model 1 is constantly enriched and updated. Therefore, the method used to establish the HR-METs model 1 in the embodiment of the present application can overcome the problem of poor accuracy of the activity level model due to thin training data, and can also overcome the adverse effects on the accuracy of the activity level model caused by the stage-by-stage changes in the user's physical condition.

[0175] It should be noted that the activity intensity corresponding to HR-METs model 1 is low intensity, that is, HR-METs model 1 is applicable to situations where the user's heart rate is low (such as a heart rate value greater than or equal to the resting heart rate and less than or equal to the walking heart rate). The data used to train HR-METs model 1 can be the user's resting heart rate and its corresponding resting METs, the heart rate at low activity intensity and its corresponding METs. Before training HR-METs model 1, heart rate data that is lower than or equal to the walking heart rate (that is, heart rate data at low activity intensity) can be screened out based on the obtained user's physical information, and the corresponding METs can be obtained based on this heart rate data; then, the heart rate at low activity intensity and its corresponding METs can be used for linear fitting to obtain HR-METs model 1.

[0176] For example, the embodiment of the present application only introduces the HR-METs model 1 which is an activity level assessment model corresponding to low activity intensity obtained by linear fitting based on (heart rate, METs) data. In actual applications, the HR-METs model 1 can also be obtained by fitting through other algorithms, such as by nonlinear fitting, and the embodiment of the present application does not limit this.

[0177] S404: Obtain the user's activity records for the past week.

[0178] The activity record may include the user's activity type (such as walking, running, climbing, etc.) and information such as the user's speed, acceleration, and time during the activity.

[0179] In some embodiments, when the model training process is executed by the cloud-side server, the method for obtaining the user's activity records for the past week may include: method (1), the smart watch collects the user's activity data in real time and periodically sends the activity data to the mobile phone, such as sending activity data to the mobile phone once every minute; after the mobile phone receives the activity data, it can periodically send it to the cloud-side server. Method (2), the smart watch collects the user's activity data in real time and periodically sends the activity data to the mobile phone, such as sending activity data to the mobile phone once every minute; after the mobile phone receives the activity data, it determines whether the time corresponding to the accumulated historical activity data covers one week. If it is determined that the time corresponding to the historical activity data it receives is less than one week, the mobile phone can store the activity data in the local space of the mobile phone until at least one week of historical activity data is accumulated, and then the mobile phone sends the activity data to the cloud-side server; thereafter, the mobile phone can periodically send the acquired activity data to the cloud-side server.

[0180] S405 , extracting the heart rate and its corresponding METs in a stable state based on the user's activity records in the past week.

[0181] It should be noted that this step is only explained by taking the extraction of the heart rate in a steady state and its corresponding METs based on the user's activity records in the past week as an example. In actual applications, if at least one of the following conditions is met: there are no activity records in the past week, the number of activity records in the past week is less than a certain number (such as 3), and the number of (activity heart rate, metabolic equivalent) data pairs is less than a certain number (such as 7), then the corresponding activity records in a longer historical period can be called to extract the heart rate in a steady state and its corresponding METs, for example, the activity records of the past 30 days can be called. If at least one of the above conditions is still not met after calling the activity records in a longer historical period, then the subsequent activity level calculation and activity level assessment cannot be performed, and the user can be prompted through the mobile phone or smart watch, such as by displaying a prompt message on the interface saying "Insufficient activity records, unable to provide activity level assessment results".

[0182] In some embodiments, before extracting the heart rate in a stable state and its corresponding METs, it is possible to first determine which activity states belong to a stable state. This process may include: based on the acquired user's heart rate, determining which heart rate values ​​satisfy the requirement that the change within a preset time period does not exceed a first threshold, and determining which activity speeds within the preset time period do not exceed a second threshold. Then, the user state corresponding to the preset time period is a stable state, the user heart rate corresponding to the preset time period is the heart rate in a stable state, and the METs corresponding to the heart rate in a stable state are the METs in a stable state. Afterwards, the user's heart rate corresponding to the preset duration in each stable state can be averaged as the active heart rate corresponding to the timestamp (for example, recorded as E-HR1); and the metabolic equivalents at the corresponding timestamp can be averaged as the average metabolic equivalent corresponding to the timestamp (for example, recorded as E-MET1); then, the (active heart rate, metabolic equivalent) data pair corresponding to the timestamp is obtained as (E-HR1, E-MET1); in a similar manner, n groups of (active heart rate, metabolic equivalent) data within the past week can be obtained, where n is an integer greater than or equal to 1. For example, the n groups of (active heart rate, metabolic equivalent) data pairs within the past week are shown in Table 1:

[0183] Table 1

[0184]

[0185]

[0186] As an example, Figure 7As shown, a method for obtaining the heart rate in a stable state may include: setting a time window with a preset time length (such as 1 minute), and sliding the time window over time; using the time window as a unit, calculating whether the change amplitude of the user's heart rate in the time window exceeds a first threshold, such as calculating whether the difference between the maximum heart rate and the minimum heart rate in the time window exceeds the first threshold; if the heart rate change amplitude (or heart rate jump) does not exceed the first threshold, then continuing to calculate whether the change amplitude of the activity speed in the time window exceeds a second threshold, such as calculating whether the difference between the maximum speed and the minimum speed in the time window exceeds the second threshold; if the activity speed change amplitude (or activity speed jump) does not exceed the second threshold, then determining that the activity state corresponding to the time window is a stable state, the heart rate data in the time window is the heart rate in the stable state, and the METs corresponding to the heart rate are the METs in the stable state.

[0187] In some embodiments, in order to obtain a stable state in different time periods, the time window can be periodically slid, for example, the time window is slid once every first time period (that is, the sliding period is the first time period), the heart rate and activity speed corresponding to each time period are obtained, and then whether it is a stable state is determined based on the heart rate and activity speed in each time period. The first time period can be less than the preset time period corresponding to the time window, for example, the first time period is 10s or 30s, and the preset time period is 1min; or, optionally, the first time period can be the same as the preset time period, for example, both are 1min. For example, assuming that the time range corresponding to a time window (recorded as the first time window) is: 10:00:00-10:01:00, and the sliding period is 30s, then the time range corresponding to the next time window adjacent to the first time window (recorded as the second time window) is: 10:00:30-10:01:30. If both of the two adjacent time windows correspond to stable states, then it can be determined that the state corresponding to the time range of 10:00:00-10:01:30 is stable. Subsequently, the activity data and vital sign data corresponding to the stable state can be collected.

[0188] Alternatively, optionally, when performing a steady-state analysis, it is necessary to collect the vital sign data and activity data corresponding to each time window. When it is determined that the state corresponding to the time window is a steady state, the vital sign data and activity data corresponding to the time window can also be recorded as data in the steady state. If the data in the steady state obtained in this way are repeated, for example, the heart rate data corresponding to the first time window and the heart rate data (and METs) corresponding to the second time window are repeated (the heart rate data and METs corresponding to the first time window and the second time window within 10:00:30-10:01:00 are repeated), then in order to avoid redundant data calculation, the repeated data can also be deduplicated.

[0189] Alternatively, assuming the preset duration corresponding to the time window and the first duration corresponding to the sliding period are both 1 minute, and the time range corresponding to one time window (denoted as the third time window) is 10:00:00-10:01:00, then the time range corresponding to the next adjacent time window (denoted as the fourth time window) is 10:01:00-10:02:00. Since the duration of the interval between adjacent time windows (i.e., the first duration) is equal to the preset duration corresponding to the time window, data duplication will not occur. Therefore, if the data in the steady state is recorded in units of time windows, there is no need to deduplicate the duplicate data.

[0190] It should be noted that the first duration described above is only an example. In actual applications, in order to obtain a more accurate stable state, the first duration can also be set to a finer granularity, such as setting the first duration to 1s or 2s, etc. The embodiments of this application do not limit this.

[0191] It should also be noted that the steady-state heart rate and its corresponding METs obtained in this step can include heart rate data with values ​​lower than or equal to the user's walking heart rate, and METs data lower than or equal to the walking METs. They can also include heart rate data with values ​​higher than the user's walking heart rate, and METs data higher than the walking METs. In other words, the steady-state heart rate and METs data obtained in this step can correspond to different numerical ranges and are not divided by numerical value.

[0192] S406 , screening the heart rate and its corresponding METs in a stable state according to the walking heart rate and walking METs, and obtaining the heart rate and its corresponding METs under medium to high activity intensity.

[0193] It should be noted that the stable state in the embodiment of the present application may specifically refer to the state corresponding to the following: within a preset time period (such as 1 minute continuously) under medium to high activity intensity, the user's heart rate does not exceed a first threshold value (such as ±10bpm), and within the preset time period, the user's activity speed does not exceed a second threshold value (such as ±1km / h). The medium to high activity intensity mentioned in the embodiment of the present application may refer to activities corresponding to a heart rate higher than the walking heart rate, or activities corresponding to a heart rate higher than a certain percentage of the maximum heart rate (such as 64%), such as HR>64%HR max .

[0194] Since HR-METs model 2 corresponds to the user's medium to high activity intensity, in order to obtain a more accurate HR-METs model 2, training to obtain the heart rate and its corresponding METs of the HR-METs model 2 requires the corresponding data of the user at medium to high activity intensity. Therefore, before using the steady-state heart rate and METs to train the model, the steady-state data can be screened to obtain the heart rate and its corresponding METs at medium to high activity intensity as valid data.

[0195] In some embodiments, the process of obtaining the heart rate and corresponding METs at moderate to high activity intensities may include: using the user's walking heart rate as a boundary, filtering out heart rate data with a value greater than the walking heart rate from the steady-state heart rate data as the effective heart rate; and obtaining the corresponding METs based on the effective heart rate as the effective METs. Alternatively, the user's walking heart rate may be obtained, and the corresponding walking METs may be obtained based on the walking heart rate. Then, using the user's walking heart rate and walking METs as boundaries, filtering out heart rates greater than the walking heart rate from the steady-state heart rate data and METs data as the effective heart rate and METs, respectively.

[0196] S407 , obtaining HR-METs model 2 based on the heart rate and its corresponding METs at moderate to high activity intensities.

[0197] In some embodiments, the process of obtaining the HR-METs model 2 based on the heart rate and its corresponding METs at medium to high activity intensities may include: obtaining the user's (walking heart rate, walking METs) data pair, and N groups of (second activity heart rate, second METs) data pairs at medium to high activity intensities, the N groups of (second activity heart rate, second METs) data pairs being, for example, data pairs after screening the above n groups of (activity heart rate, metabolic equivalents), where N is an integer greater than or equal to 1; performing linear fitting based on the (walking heart rate, walking METs) data pair and the N groups of (second activity heart rate, second METs) data pairs to obtain the HR-METs model 2 corresponding to the user at medium to high activity intensities. Exemplarily, the HR-METs model 2 obtained by fitting may be, for example, as follows Figure 8 shown.

[0198] In some embodiments, the cloud-side server can obtain HR-METs Model 2 through a rolling iteration. Specifically, the cloud-side server can periodically obtain the user's activity data and vital sign data, for example, obtaining the user's speed and heart rate reported by the mobile phone every 10 minutes. The cloud-side server then stores the user's activity data and vital sign data. Each day, the cloud-side server can perform rolling iterations on HR-METs Model 2 based on the stored user activity data and vital sign data from the past week. For example, if the cloud-side server obtains HR-METs Model 2 at 00:00 on March 8, 2024, using the user's activity data and vital sign data from March 1 to March 7, 2024, then the cloud-side server can iteratively update HR-METs Model 2 24 hours later at 00:00 on March 9, 2024, using the user's activity data and vital sign data from March 2 to March 8, 2024.

[0199] It can be understood that since the HR-METs model 2 is trained and acquired through rolling iterations, the training data used to establish the HR-METs model 2 is constantly enriched and updated. Therefore, the method used to establish the HR-METs model 2 in the embodiment of the present application can overcome the problem of poor accuracy of the activity level model due to thin training data, and can also overcome the adverse effects on the accuracy of the activity level model caused by the stage-by-stage changes in the user's physical condition.

[0200] Afterwards, the HR-METs model 1 and the HR-METs model 2 obtained through training can be integrated to obtain an activity level hierarchical model. For example, the activity level hierarchical model can be as follows: Figure 9As shown. The heart rate corresponding to point B is the walking heart rate, meaning that the state at point B is the user's walking state. When the user's activity intensity is lower than or equal to the walking intensity, the HR-METs model 1 in the activity level stratification model can be used to assess the user's activity level. When the user's activity intensity is higher than the walking intensity, the HR-METs model 2 in the activity level stratification model can be used to assess the user's activity level. The parameter used to characterize activity intensity can be the user's heart rate.

[0201] It is understood that the data used to train the activity level stratification model in the embodiment of the present application is the user's physical sign data and activity data. Therefore, the activity level stratification model obtained through training is a personalized model adapted to the user's physical condition. After the activity level stratification model is established, the activity level of the user can be evaluated using the activity level stratification model. Exemplarily, the process of evaluating the user's activity level using the activity level stratification model may include the following steps S408 to S412:

[0202] S408: Determine whether the user's heart rate is greater than the walking heart rate.

[0203] In some embodiments, the user's heart rate here may refer to the heart rate data periodically reported by the mobile phone side to the cloud side server.

[0204] Among them, if the user's heart rate is less than or equal to the walking heart rate, that is, the judgment result of this step is "no", then step S409A can be executed next; if the user's heart rate is greater than the walking heart rate, that is, the judgment result of this step is "yes", then step S409B can be executed next.

[0205] S409A, calling HR-METs model 1 to obtain the user's activity level.

[0206] When the user's heart rate is less than or equal to the walking heart rate, it means that the user's current activity status is low-intensity activity. At this time, it is appropriate to call the corresponding HR-METs model 1 to obtain the user's activity amount.

[0207] In some embodiments, the cloud-side server may input the user's heart rate into the HR-METs model 1 and obtain the first activity amount corresponding to the low activity intensity output by the HR-METs model 1.

[0208] S409B, call HR-METs model 2 to obtain the user's activity level.

[0209] When the user's heart rate is greater than the walking heart rate, it means that the user's current activity status is medium to high intensity. At this time, it is appropriate to call the corresponding HR-METs model 2 to obtain the user's activity amount.

[0210] In some embodiments, the cloud-side server may input the user's heart rate into the HR-METs model 2 and obtain the second activity amount corresponding to the medium-high activity intensity output by the HR-METs model 2.

[0211] S410, cumulatively calculating the user's activity volume TWM for one week.

[0212] In some embodiments, the cloud-side server can cumulatively calculate the user's total activity volume TWM for the past week based on the first activity volume corresponding to the low activity intensity and the second activity volume corresponding to the medium-high activity intensity. The unit of the TWM can be METs*h / week multiplied by the hour per week. Specifically, the cloud-side server can add at least one activity volume result of the user at low activity intensity and at least one activity volume result at medium-high activity intensity in the past week to obtain the total activity volume TWM for the past week (24h*7d), in METs*h or METs*h.

[0213] In some embodiments, the cloud-side server may calculate the user's activity volume TWM for the past week on a rolling iterative basis on a daily basis, that is, calculate the total activity volume for the past week every day, and evaluate the user's activity level.

[0214] In some embodiments, if there is no corresponding user activity data for one or more days in the past week, then this day or these days can be regarded as the default state, that is, when calculating the total activity amount of the past week, it is calculated only based on the existing activity data and heart rate data.

[0215] In one possible implementation, the user's activity level can be evaluated based on the user's total activity volume TWM over the past week. For example, the evaluation results corresponding to different activity volumes can be shown in Table 2 below:

[0216] Table 2

[0217]

[0218] Afterwards, targeted course recommendations and / or long-term tracking of physical activity levels can be made to the user based on the user's activity level assessment results.

[0219] Alternatively, the user's activity level may be evaluated using a physical activity weekly coefficient K. In this case, the following steps S411 and S412 may be performed:

[0220] S411, calculate the physical activity weekly coefficient K.

[0221] In some embodiments, the physical activity weekly coefficient K can be calculated using the following formula (1-1):

[0222] K=TWM / a(1-1)

[0223] Wherein, K is the weekly physical activity coefficient; TWM is the total activity of the user in the past week; a is a preset coefficient, which can be 168, for example.

[0224] S412: Obtain the user's activity level assessment result based on the physical activity weekly coefficient K.

[0225] In a possible implementation, the activity level assessment results corresponding to different physical activity week coefficients K may be shown in the following Table 3, for example:

[0226] Table 3

[0227]

[0228] Afterwards, targeted course recommendations and / or long-term tracking of physical activity levels can be made to the user based on the user's activity level assessment results.

[0229] In some embodiments, smart watches and mobile phones can display activity level assessment results to users through the sports health APP. The activity level results may include the user's weekly activity volume TWM and / or physical activity weekly coefficient K, and may also include activity level assessment results, that is, the activity level level (too low, average, on target, high), etc.

[0230] In addition, smartwatches and mobile phones can also recommend relevant courses to users through the Sports Health app based on the user's activity level assessment results, such as physical fitness programs and muscle building and fat loss programs. When users click the corresponding control for a relevant course, they can enter the course details page.

[0231] For example, Figure 10A and Figure 10B As shown, a scenario in which a user views the activity level evaluation results in a mobile phone may be: Figure 10A As shown, the user clicks the sports health APP icon 1001 on the APP page of the mobile phone; after the mobile phone receives the user's click operation on the sports health APP icon 1001, in response to the click operation, the following is displayed Figure 10B The activity level assessment result display interface shown in the figure may include the current date, the user's weekly activity amount (unit may be METs*h) (e.g. Figure 10B The weekly activity volume is 185 METs*h, and the activity level level corresponding to the weekly activity volume (such as Figure 10B activity level shown is too low), and health reminders for activity level that week (such as Figure 10BAs shown in the figure, "Long periods of sitting and little movement increase the risk of heart disease, diabetes, obesity and other diseases. Increasing weekly physical activity can reduce the above risks. Increasing activity during work hours is a good start: getting up once an hour, going for a walk at lunch time, or taking the stairs instead of the elevator will increase your physical activity level."). In addition, the activity level assessment result display interface can also include a relevant course recommendation module, which can include relevant courses that match the user's weekly activity level, such as physical fitness program courses and muscle gain and fat loss program courses. Users can choose to enter the corresponding course details page to learn and practice according to their needs.

[0232] In some embodiments, after a user joins a related course, the user's activity level can also be tracked over a long period of time. For example, after a user joins a muscle-building and fat-reducing program, the user's body fat percentage and activity level can be recorded, and the long-term trend of body fat percentage and activity level as well as the level of activity level at different stages (such as too low, average, meeting the standard, etc.) can be displayed to the user through the sports health APP. For example, a long-term tracking trend of body fat percentage and activity level can be as follows: Figure 10C shown.

[0233] According to the method for activity level assessment provided in the embodiment of the present application, the user's historical heart rate data and activity intensity data for the past week are used as input samples, and a personalized activity level stratification model adapted to the user's physical condition is used to iteratively calculate the user's activity volume within a week in units of MET*hours. Then, the user's physical activity level is evaluated according to the international standards for physical activity levels, thereby providing the user with activity assessment results that are more in line with the actual physical condition, and improving the objectivity and accuracy of the activity assessment results.

[0234] It should be noted that the above Figure 4 The process shown in the embodiment is only introduced by first training to obtain HR-METs model 1 and then training to obtain HR-METs model 2. However, in actual applications, HR-METs model 1 and HR-METs model 2 can be trained at the same time, or HR-METs model 2 can be trained first and then HR-METs model 1 can be trained. The embodiments of the present application are not limited to this.

[0235] In order to better understand the method for evaluating activity levels provided in the embodiments of the present application, the following Figure 11 This article introduces the process of simultaneously training HR-METs Model 1 and HR-METs Model 2.

[0236] For example, Figure 11 , which is another schematic flow chart of obtaining activity level assessment based on an activity level hierarchical model provided by an embodiment of the present application.

[0237] It should be noted that the execution subject of this process can be a cloud-side server, a mobile phone, or a smart watch, and this embodiment of the application does not limit this. For ease of understanding, the following is an example of the execution subject of this process being a cloud-side server. The process may specifically include the following steps:

[0238] S1101, obtaining basic information of the user.

[0239] S1102: Obtain the user's resting heart rate, walking heart rate, and walking METs over the past week.

[0240] S1103A: Fit the user's resting heart rate, resting METs, and the heart rate at low activity intensity and its corresponding METs to obtain HR-METs model 1.

[0241] Here, step S1102 and step S1103A may be iterated in a rolling manner, for example, with a daily period.

[0242] S1103B, obtain the user's activity records for the past week.

[0243] S1104: Extract the heart rate and its corresponding METs in a stable state based on the user's activity records in the past week.

[0244] S1105 , screening the heart rate and its corresponding METs in a stable state based on the walking heart rate and walking METs, and obtaining the heart rate and its corresponding METs under medium to high activity intensity.

[0245] S1106 , obtaining HR-METs model 2 based on the heart rate and its corresponding METs at medium to high activity intensities.

[0246] S1107: Determine whether the user's heart rate is greater than the walking heart rate.

[0247] Among them, if the user's heart rate is less than or equal to the walking heart rate, that is, the judgment result of this step is "no", then step S1108A can be executed next; if the user's heart rate is greater than the walking heart rate, that is, the judgment result of this step is "yes", then step S1108B can be executed next.

[0248] S1108A: Call HR-METs model 1 to obtain the user's activity level.

[0249] S1108B: Call HR-METs model 2 to obtain the user's activity level.

[0250] S1109, cumulatively calculating the user's activity volume TWM for one week.

[0251] S1110, calculating the physical activity weekly coefficient K.

[0252] S1111 , obtaining a user's activity level assessment result based on the physical activity weekly coefficient K.

[0253] The detailed description of each step in this embodiment can be found in Figure 4 The relevant contents in the embodiments will not be repeated here.

[0254] In some embodiments, after the above steps are performed, course-oriented recommendations and / or long-term tracking of physical activity levels may be provided to the user based on the user's activity level assessment results.

[0255] In some embodiments, smart watches and mobile phones can display activity level assessment results to users through the sports health APP. The activity level results may include the user's weekly activity volume TWM and / or physical activity weekly coefficient K, and may also include activity level assessment results, that is, the activity level level (too low, average, on target, high), etc.

[0256] In addition, smartwatches and mobile phones can also recommend relevant courses to users through the Sports Health app based on the user's activity level assessment results, such as physical fitness programs and muscle building and fat loss programs. When users click the corresponding control for a relevant course, they can enter the course details page.

[0257] According to the method for activity level assessment provided in the embodiment of the present application, the user's historical heart rate data and activity intensity data for the past week are used as input samples, and a personalized activity level stratification model adapted to the user's physical condition is used to iteratively calculate the user's activity volume within a week in units of MET*hours. Then, the user's physical activity level is evaluated according to the international standards for physical activity levels, thereby providing the user with activity assessment results that are more in line with the actual physical condition, and improving the objectivity and accuracy of the activity assessment results.

[0258] For example, Figure 12 FIG. 1 is a schematic flow chart of another embodiment of the present application for obtaining an activity level assessment based on an activity level hierarchical model. The flow chart can be applied to electronic devices such as cloud-side servers, smart terminals, or smart wearable devices, and specifically includes the following steps:

[0259] S1201, obtaining the user's heart rate data for at least the past week, where the heart rate data includes the user's walking heart rate.

[0260] S1202: Filter, based on the walking heart rate, a first heart rate corresponding to a low activity intensity of the user in the past week and a second heart rate corresponding to a medium to high activity intensity of the user in the past week.

[0261] S1203, using the activity level assessment hierarchical model, obtain the user's weekly activity level assessment result according to the first heart rate and the second heart rate, the activity level hierarchical model includes a first activity level assessment model and a second activity level assessment model, the first activity level assessment model is used to obtain the amount of activity at low activity intensity according to the first heart rate, and the second activity level assessment model is used to obtain the amount of activity at medium and high activity intensity according to the second heart rate, and the units of the amount of activity at low activity intensity and the amount of activity at medium and high activity intensity are METs multiplied by time.

[0262] In some embodiments, a user's walking heart rate refers to the heart rate per minute value detected by a smartwatch or mobile phone while the user is walking at a steady pace. If multiple walking heart rate values ​​are obtained in a single day, the average of these multiple walking heart rate values ​​can be calculated and used as the basis for classifying activity intensity.

[0263] In a possible implementation, the MET multiplied by the time may be, for example, METs*h, that is, the MET value multiplied by hours.

[0264] In a possible implementation, the first activity level assessment model may correspond to the HR-METs model 1 below; and the second activity level assessment model may correspond to the HR-METs model 2 below.

[0265] In some embodiments, the filtering of the first heart rate corresponding to the user's low activity intensity in the past week and the second heart rate corresponding to the user's medium to high activity intensity in the past week based on the walking heart rate specifically includes: filtering out the first heart rate that is lower than or equal to the walking heart rate in the past week from the heart rate data; and filtering out the second heart rate that is higher than the walking heart rate in the past week from the heart rate data.

[0266] In one possible implementation, after obtaining the user's heart rate, it can be determined whether the heart rate is greater than the user's walking heart rate. If the heart rate is less than or equal to the walking heart rate, it means that the heart rate is a heart rate corresponding to low activity intensity, and the corresponding activity amount can be subsequently calculated using the first activity level assessment model; if the heart rate is greater than the walking heart rate, it means that the heart rate is a heart rate corresponding to medium-to-high activity intensity, and the corresponding activity amount can be subsequently calculated using the second activity level assessment model.

[0267] In some embodiments, filtering the second heart rate that is higher than the walking heart rate in the past week from the heart rate data specifically includes: obtaining the speed of the user for at least the past week; obtaining a third heart rate in a stable state based on the speed and the heart rate data, wherein, in the stable state: the change in the user's heart rate within a preset time period is less than or equal to a first threshold, and the change in the user's speed within the preset time period is less than or equal to a second threshold; filtering the second heart rate that is higher than the walking heart rate from the third heart rate.

[0268] In a possible implementation, the preset duration may be, for example, 1 minute, the first threshold may be, for example, ±10 bpm, and the second threshold may be, for example, ±1 km / h.

[0269] In some embodiments, the use of the activity level stratification model to obtain the user's weekly activity level activity results based on the first heart rate and the second heart rate specifically includes: inputting the first heart rate of the past week into the first activity level assessment model; obtaining the activity amount at the low activity intensity output by the first activity level assessment model; and inputting the second heart rate of the past week into the second activity level assessment model; obtaining the activity amount at the medium and high activity intensity output by the second activity level assessment model; adding the activity amount at the low activity intensity and the activity amount at the medium and high activity intensity to obtain the total activity amount of the past week; and obtaining the user's weekly activity level assessment result based on the total activity amount of the past week.

[0270] In some embodiments, obtaining the user's weekly activity level assessment result based on the total activity amount of the past week specifically includes: obtaining the user's physical activity weekly coefficient based on the total activity amount of the past week and a preset coefficient; obtaining the user's weekly activity level assessment result based on the physical activity weekly coefficient, wherein the weekly activity level assessment result is used to indicate the level of the user's activity level in the past week, and different ranges of the physical activity weekly coefficient correspond to different activity level levels.

[0271] In some embodiments, the method further comprises: displaying course recommendation information, wherein the course recommendation information is associated with the weekly activity level assessment result.

[0272] In some embodiments, the method further includes: recording the activity level change trend of the user; displaying prompt information of the activity level change trend, wherein the prompt information is used to indicate the activity level change trend and the weekly activity level assessment results corresponding to the activity level of the user at different stages.

[0273] In some embodiments, the heart rate data also includes the user's resting heart rate, and the method also includes: obtaining the resting metabolic equivalent corresponding to the resting heart rate; obtaining the user's fourth heart rate at low activity intensity in the past week and the low activity intensity metabolic equivalent corresponding to the fourth heart rate, the unit of the resting metabolic equivalent and the low activity intensity metabolic equivalent being MET multiplied by time; performing linear fitting on the resting heart rate and resting metabolic equivalent data pair, and the fourth heart rate and low activity intensity metabolic equivalent data pair to establish the first activity level assessment model.

[0274] In some embodiments, the method further includes: performing linear fitting rolling iterations on the user's resting heart rate and resting metabolic equivalent data pair, and the fourth heart rate and low activity intensity metabolic equivalent data pair corresponding to the user in the past week on a daily basis to update the first activity level assessment model.

[0275] In some embodiments, the method further includes: obtaining the user's speed for at least the past week; screening the fifth heart rate in a stable state and the metabolic equivalent corresponding to the fifth heart rate based on the heart rate data and the speed, wherein, in the stable state: the user's heart rate has a change amplitude less than or equal to a first threshold at least within a preset time period, and the user's speed has a change amplitude less than or equal to a second threshold at least within the preset time period.

[0276] In some embodiments, the method further includes: selecting a sixth heart rate that is higher than the walking heart rate from the fifth heart rate; and obtaining a medium-to-high activity intensity metabolic equivalent corresponding to the sixth heart rate.

[0277] In some embodiments, the method further includes: performing linear fitting on the sixth heart rate and the medium-to-high activity intensity metabolic equivalent data pair to establish the second activity level assessment model.

[0278] In some embodiments, the method further includes: performing linear fitting rolling iteration on the sixth heart rate and the medium-to-high activity intensity metabolic equivalent data pair corresponding to the user in the past week on a daily basis to update the second activity level assessment model.

[0279] According to the activity level assessment method provided by this implementation, the user's historical heart rate data and activity intensity data in the past week are used as input samples, and a personalized activity level stratification model adapted to the user's physical condition is used to iteratively calculate the user's activity volume in a week in units of MET*hours. The user's physical activity level is then evaluated according to international standards for physical activity levels, thereby providing the user with activity assessment results that are more in line with the actual physical condition, and improving the objectivity and accuracy of the activity assessment results.

[0280] Based on the same technical concept, an embodiment of the present application also provides an electronic device, including a processor; a memory; the memory stores a computer program, and the computer program includes instructions. When the instructions are executed by the processor, the electronic device performs one or more steps in any of the above methods.

[0281] Based on the same technical concept, an embodiment of the present application also provides a chip system, which includes: a processing circuit, a receiving pin and a transmitting pin; wherein, the receiving pin, the transmitting pin and the processing circuit communicate with each other through an internal connection path, and the processing circuit executes one or more steps in any of the above methods to control the receiving pin to receive signals and control the transmitting pin to send signals.

[0282] Based on the same technical concept, an embodiment of the present application also provides a computer-readable storage medium, which stores computer-executable program instructions. When the computer-executable program instructions are executed on a computer, the computer or processor executes one or more steps in any of the above methods.

[0283] Based on the same technical concept, an embodiment of the present application also provides a computer program product containing instructions, wherein the computer program product includes computer program code. When the computer program code is run on a computer, the computer or processor executes one or more steps in any of the above methods.

[0284] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted via the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)).

[0285] Those skilled in the art will appreciate that all or part of the process steps in the above-described method embodiments can be implemented by a computer program instructing the relevant hardware. The program can be stored in a computer-readable storage medium, and when executed, the program can include the process steps in the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

[0286] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for activity level assessment, characterized in that: Used in electronic equipment, including: Acquire heart rate data of a user for at least the past week, wherein the heart rate data includes the user's walking heart rate; filtering, based on the walking heart rate, a first heart rate corresponding to the low activity intensity of the user in the past week and a second heart rate corresponding to the medium to high activity intensity of the user in the past week; Using an activity level assessment hierarchical model, the weekly activity level assessment result of the user is obtained according to the first heart rate and the second heart rate. The activity level hierarchical model includes a first activity level assessment model and a second activity level assessment model. The first activity level assessment model is used to obtain the activity amount at the low activity intensity according to the first heart rate, and the second activity level assessment model is used to obtain the activity amount at the medium and high activity intensity according to the second heart rate. The units of the activity amount at the low activity intensity and the activity amount at the medium and high activity intensity are MET multiplied by time.

2. The method according to claim 1, characterized in that The filtering, based on the walking heart rate, of the first heart rate corresponding to the low activity intensity of the user in the past week and the second heart rate corresponding to the medium to high activity intensity of the user in the past week specifically includes: Filtering the first heart rate in the past week that is lower than or equal to the walking heart rate from the heart rate data; The second heart rate that is higher than the walking heart rate in the past week is filtered from the heart rate data.

3. The method according to claim 2, characterized in that The step of screening the heart rate data for the second heart rate that is higher than the walking heart rate in the past week specifically includes: Get the user's speed for at least the past week; Obtaining a third heart rate in a stable state based on the speed and the heart rate data, wherein, in the stable state: a change in the user's heart rate within a preset time period is less than or equal to a first threshold, and a change in the user's speed within the preset time period is less than or equal to a second threshold; The second heart rate that is higher than the walking heart rate is filtered out from the third heart rates.

4. The method according to any one of claims 1 to 3, characterized in that The obtaining of the user's weekly activity level result based on the first heart rate and the second heart rate using the activity level stratification model specifically includes: inputting the first heart rate of the past week into the first activity level assessment model; obtaining the activity amount at the low activity intensity output by the first activity level assessment model; and inputting the second heart rate of the past week into the second activity level assessment model; Obtaining the activity amount at the medium-high activity intensity output by the second activity level assessment model; Adding the activity amount at the low activity intensity and the activity amount at the medium to high activity intensity to obtain the total activity amount for the past week; The user's weekly activity level assessment result is obtained based on the total activity amount of the past week.

5. The method according to claim 4, characterized in that The obtaining of the user's weekly activity level assessment result based on the total activity amount of the past week specifically includes: Obtaining a weekly physical activity coefficient of the user based on the total activity amount of the past week and a preset coefficient; The weekly activity level assessment result of the user is obtained based on the physical activity weekly coefficient, wherein the weekly activity level assessment result is used to indicate the level of activity level of the user in the past week, and different ranges of the physical activity weekly coefficient correspond to different activity level levels.

6. The method according to claim 5, characterized in that The method further comprises: Course recommendation information is displayed, where the course recommendation information is associated with the weekly activity level assessment result.

7. The method according to claim 6, characterized in that The method further comprises: Recording the activity change trend of the user; The prompt information of the activity amount change trend is displayed, and the prompt information is used to indicate the activity amount change trend and the weekly activity level assessment results corresponding to the activity amount of the user at different stages.

8. The method according to any one of claims 1 to 7, characterized in that The heart rate data also includes the user's resting heart rate, and the method further includes: Obtaining a resting metabolic equivalent corresponding to the resting heart rate; Obtaining the fourth heart rate of the user at low activity intensity over the past week and the low activity intensity metabolic equivalent corresponding to the fourth heart rate, where the units of the resting metabolic equivalent and the low activity intensity metabolic equivalent are METs multiplied by time; Linear fitting is performed on the resting heart rate and the resting metabolic equivalent data pair, and the fourth heart rate and the low activity intensity metabolic equivalent data pair to establish the first activity level assessment model.

9. The method according to claim 8, characterized in that The method further comprises: On a daily basis, linear fitting rolling iterations are performed on the user's resting heart rate and resting metabolic equivalent data pair, as well as the fourth heart rate and low-activity intensity metabolic equivalent data pair corresponding to the user in the past week, to update the first activity level assessment model.

10. The method according to any one of claims 1 to 9, characterized in that The method further comprises: Get the speed reported by the user for at least the past week; A fifth heart rate in a stable state and a metabolic equivalent corresponding to the fifth heart rate are screened according to the heart rate data and the speed, wherein, in the stable state: a change amplitude of the user's heart rate is less than or equal to a first threshold at least within a preset time period, and a change amplitude of the user's speed is less than or equal to a second threshold at least within the preset time period.

11. The method according to claim 10, characterized in that The method further comprises: selecting a sixth heart rate from the fifth heart rate that is higher than the walking heart rate; Obtain the metabolic equivalent of the medium to high activity intensity corresponding to the sixth heart rate.

12. The method according to claim 11, characterized in that The method further comprises: Perform linear fitting on the sixth heart rate and the medium-to-high activity intensity metabolic equivalent data pair to establish the second activity level assessment model.

13. The method according to claim 11, characterized in that The method further comprises: On a daily basis, linear fitting rolling iteration is performed on the sixth heart rate and the medium-to-high activity intensity metabolic equivalent data pair corresponding to the user in the past week to update the second activity level assessment model.

14. An electronic device, characterized in that: include: processor; Memory; The memory stores a computer program, which includes instructions. When the instructions are executed by the processor, the electronic device performs the method according to any one of claims 1 to 13.

15. A system for assessing activity levels, characterized in that: The system includes a smart wearable device, a smart terminal and a cloud-side server, wherein the smart wearable device is used to collect the user's heart rate data and speed, the smart terminal is used to obtain the heart rate data and speed sent by the smart wearable device, and send the heart rate data and speed to the cloud-side server, and the cloud-side server is used to execute the method according to any one of claims 1 to 13.

16. A chip system, characterized in that: The chip system includes a processing circuit, a receiving pin and a transmitting pin; wherein the receiving pin, the transmitting pin and the processing circuit communicate with each other through an internal connection path, and the processing circuit executes the method described in any one of claims 1 to 13 to control the receiving pin to receive signals and control the transmitting pin to send signals.

17. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable program instructions, which, when executed on a computer, enable the computer to perform the method according to any one of claims 1 to 13.

Citation Information

Cited By

  • Metabolic equivalent driven endurance training intensity gradient generation system and method thereof

    CN121354803A