WO2023216270A1 - 热量消耗估算方法、装置及存储介质 - Google Patents

热量消耗估算方法、装置及存储介质 Download PDF

Info

Publication number
WO2023216270A1
WO2023216270A1 PCT/CN2022/092877 CN2022092877W WO2023216270A1 WO 2023216270 A1 WO2023216270 A1 WO 2023216270A1 CN 2022092877 W CN2022092877 W CN 2022092877W WO 2023216270 A1 WO2023216270 A1 WO 2023216270A1
Authority
WO
WIPO (PCT)
Prior art keywords
heart rate
target user
calorie consumption
increment
current
Prior art date
Application number
PCT/CN2022/092877
Other languages
English (en)
French (fr)
Inventor
皮特
姚丽峰
高国松
Original Assignee
北京小米移动软件有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京小米移动软件有限公司 filed Critical 北京小米移动软件有限公司
Priority to PCT/CN2022/092877 priority Critical patent/WO2023216270A1/zh
Priority to CN202280004302.9A priority patent/CN117412704A/zh
Publication of WO2023216270A1 publication Critical patent/WO2023216270A1/zh

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/024—Detecting, measuring or recording pulse rate or heart rate

Definitions

  • the present disclosure relates to the field of human-computer interaction, and in particular, to a method, device and storage medium for estimating heat consumption.
  • a wearable device is a portable device that is worn directly on the body or integrated into the user's clothes. Its product forms are diverse, such as smart watches, smart bracelets, smart glasses, smart helmets, etc.
  • sensors in wearable devices that can collect physiological signals of the human body, such as heart rate and other signals, to monitor the user's health indicators.
  • the user's caloric consumption during exercise is the calorie consumption.
  • the calculation of calorie consumption in related technologies is not accurate enough.
  • the present disclosure provides a method, device and storage medium for estimating heat consumption.
  • a caloric consumption estimation method including:
  • the first calorie consumption increment of the target user in the current period is determined, wherein the current period is the previous moment from the current moment. The period between to the current moment;
  • the total calorie consumption information of the target user during exercise is determined, wherein the exercise process includes the process from the start time of exercise to the current time.
  • the method also includes:
  • the motion state characteristic information of the target user at the current moment is determined, wherein the motion state characteristic information is used to represent that the target user is in a steady state stage of motion at the current moment. Still in the exercise recovery stage;
  • Determining the total calorie consumption information of the target user during exercise according to the second calorie consumption increment includes:
  • the total calorie consumption information is determined according to the target calorie consumption increment.
  • determining the motion state characteristic information of the target user at the current moment based on the heart rate at the current moment includes:
  • the time window includes the period from the designated time to the current time, and the designated time is earlier than the current time;
  • the motion state characteristic information of the target user at the current moment is determined.
  • determining the motion state characteristic information of the target user at the current moment according to the number of heart rate drop moments includes:
  • the preset conditions include: the number of the heart rate drop moments Greater than the preset quantity threshold, the ratio between the number of heart rate drop moments and the number of moments in the time window is greater than the preset proportion threshold.
  • determining the target calorie consumption increment of the target user in the current period based on the motion state characteristic information and the second calorie consumption increment includes:
  • the motion state characteristic information represents that the target user is in a steady state stage of motion at the current moment, then the second calorie consumption increment is used as the target calorie consumption increment;
  • the motion state characteristic information represents that the target user is in the exercise recovery stage at the current moment. If the motion state characteristic information represents that the target user is in the exercise recovery stage at the current moment, then based on the second calorie consumption increment, the heart rate at the current moment, the maximum heart rate during exercise, and the preset resting time Resting heart rate, determine the target calorie consumption increment.
  • determining the target calorie consumption increment based on the second calorie consumption increment, the heart rate at the current moment, the maximum heart rate during exercise, and a preset resting heart rate includes:
  • the ratio between the current heart rate increment and the maximum heart rate increment is used as the heat suppression factor
  • the target heat consumption increment is determined based on the second heat consumption increment and the heat suppression factor.
  • the physiological characteristic information of the target user includes the weight and age of the target user
  • the first caloric consumption is determined based on the average intensity information, the weight of the target user, the preset base weight, the heart rate at the current moment, the preset resting heart rate, and the age gain corresponding to the age of the target user. Increment.
  • the average intensity information corresponding to the type information is obtained in the following manner:
  • the physiological characteristic information includes the weight and age of the first user;
  • the first actual calorie consumption increment the first heart rate, the preset resting heart rate, the weight of the first user, the preset basic weight, and the age corresponding to the age of the first user Gain, fitting out the average intensity information.
  • modifying the first calorie consumption increment according to the calorie consumption estimation model to obtain the second calorie consumption increment of the target user in the current period includes:
  • the calorie consumption estimation model is trained in the following manner:
  • the heat consumption estimation model is a gated cycle unit model.
  • the method also includes:
  • the current basal metabolic information of the target user is determined based on the calorie consumption of the current exercise, and the current basal metabolic information is displayed, wherein the current basal metabolic information is greater than The target user's basal metabolic information before this exercise.
  • a heat consumption estimating device including:
  • a heart rate acquisition module used to acquire the heart rate of the target user at the current moment and the physiological characteristic information of the target user
  • the first determination module is configured to determine the first calorie consumption increment of the target user in the current period based on the heart rate at the current moment and the physiological characteristic information of the target user, wherein the current period is from the current period. The period between the previous moment of the current moment and the current moment;
  • a second determination module configured to correct the first heat consumption increment according to the heat consumption estimation model to obtain the second heat consumption increment of the target user in the current period
  • a total calorie determination module configured to determine the total calorie consumption information of the target user during exercise according to the second calorie consumption increment, wherein the exercise process includes the process from the start time of exercise to the current moment.
  • the device also includes:
  • a state determination module configured to determine the motion state characteristic information of the target user at the current moment according to the heart rate at the current moment, wherein the motion state characteristic information is used to characterize the motion state characteristic information of the target user at the current moment. Is it in the steady-state phase of exercise or the recovery phase of exercise?
  • the total heat determination module includes:
  • a first determination sub-module configured to determine the target calorie consumption increment of the target user in the current period based on the motion state characteristic information and the second calorie consumption increment;
  • the second determination sub-module is used to determine the total calorie consumption information according to the target calorie consumption increment.
  • the status determination module includes:
  • the time determination submodule is used for each time in the time window corresponding to the current time, if the heart rate of the target user at this time is less than the heart rate of the target user at the previous time of this time, then the The time is used as the heart rate decrease time, wherein the time window includes the period from the designated time to the current time, and the designated time is earlier than the current time;
  • the state determination submodule is used to determine the motion state characteristic information of the target user at the current moment according to the number of the heart rate drop moments.
  • the state determination submodule is configured to determine that the target user is in the exercise recovery stage at the current moment if the number of heart rate drop moments meets at least one of the preset conditions, wherein:
  • the preset conditions include: the number of the heart rate decreasing moments is greater than a preset quantity threshold, and the ratio between the number of the heart rate decreasing moments and the number of moments in the time window is greater than the preset proportion threshold.
  • the first determination sub-module includes:
  • a third determination sub-module configured to use the second calorie consumption increment as the target calorie consumption increment if the motion state characteristic information represents that the target user is in a steady state stage of motion at the current moment;
  • the fourth determination sub-module is used to determine whether the target user is in the exercise recovery stage at the current moment according to the second calorie consumption increment, the heart rate at the current moment, and the exercise process if the motion state characteristic information indicates that the target user is in the exercise recovery stage at the current moment.
  • the maximum heart rate and the preset resting heart rate are used to determine the target calorie consumption increment.
  • the fourth determination sub-module includes:
  • the current heart rate increment determination submodule is used to determine the current heart rate increment based on the preset resting heart rate and the heart rate at the current moment;
  • the maximum heart rate increment determination submodule is used to determine the maximum heart rate increment during exercise based on the maximum heart rate and the preset resting heart rate;
  • the heat suppression factor determination submodule is used to use the ratio between the current heart rate increment and the maximum heart rate increment as the heat suppression factor
  • a heat increment determination submodule configured to determine the target heat consumption increment based on the second heat consumption increment and the heat suppression factor.
  • the physiological characteristic information of the target user includes the weight and age of the target user
  • the first determination module includes:
  • the acquisition sub-module is used to obtain the type information of the current exercise performed by the target user, and the average intensity information corresponding to the pre-stored type information;
  • the fifth determination sub-module is used to determine the age gain corresponding to the average intensity information, the weight of the target user, the preset basic weight, the heart rate at the current moment, the preset resting heart rate, and the age of the target user. , determine the first heat consumption increment.
  • the average intensity information corresponding to the type information is obtained through the following module:
  • the first information acquisition module is used to acquire the physiological characteristic information of the first user who performs the exercise corresponding to the type of information, as well as the first heart rate and the first actual calorie consumption increment when the first user is in the steady state stage of exercise, wherein, the physiological characteristic information of the first user includes the weight and age of the first user;
  • a fitting module configured to calculate the first actual calorie consumption increment, the first heart rate, the preset resting heart rate, the first user's weight, the preset base weight, the first The age gain corresponding to the user's age is used to fit the average intensity information.
  • the second determination module is used to:
  • the calorie consumption estimation model is trained through the following modules:
  • the second information acquisition module is used to acquire the physiological characteristic information of the second user in the exercise state, as well as the second heart rate and the second actual calorie consumption increment of the second user in the exercise state;
  • a priori information determination module configured to determine the prior calorie consumption of the second user based on the physiological characteristic information of the second user and the second heart rate;
  • a training module configured to input the second user's physiological characteristic information, the second heart rate, the prior calorie consumption, and the second actual calorie consumption increment into a deep learning network model, and perform The learning network model is trained to obtain the caloric consumption estimation model.
  • the device also includes:
  • a basal metabolism determination module configured to determine the current basal metabolism information of the target user based on the calorie consumption of the target user's current exercise after the target user finishes exercising, and display the current basal metabolism information, wherein, The current basal metabolic information is greater than the basal metabolic information of the target user before this exercise.
  • a heat consumption estimating device including:
  • Memory used to store instructions executable by the processor
  • the processor is configured to: execute the steps of the method provided in the first aspect of the embodiment of the present disclosure.
  • a computer-readable storage medium on which computer program instructions are stored.
  • the program instructions are executed by a processor, the steps of the caloric consumption estimation method provided by the first aspect of the present disclosure are implemented. .
  • the first calorie consumption increment of the target user in the current period is determined, taking into account the user's physiological characteristic information, that is, considering individual differences, it is possible to Reduce individual differences in caloric consumption estimates, making the determined first caloric consumption increment more accurate. Then, according to the caloric consumption estimation model, the first caloric consumption increment is corrected to obtain the second caloric consumption increment of the target user in the current period.
  • the calorie consumption estimation model can construct a complex nonlinear relationship between heart rate and calorie consumption. The calorie consumption estimation model can solve the problem of scene dependence and can adapt to complex and changeable sports scenes.
  • the first calorie The consumption increment as the prior information of the calorie consumption estimation model, can improve the accuracy of the second calorie consumption increment output by the calorie consumption estimation model, thereby improving the accuracy of the target user's total calorie consumption information during exercise.
  • FIG. 1 is a flow chart of a method for estimating heat consumption according to an exemplary embodiment.
  • FIG. 2 is a flow chart of a method for estimating heat consumption according to an exemplary embodiment.
  • FIG. 3 is a flowchart of a method for determining motion state characteristic information of a target user at the current moment according to an exemplary embodiment.
  • FIG. 4 is a flowchart of a method for determining a target calorie consumption increment during the exercise recovery stage according to an exemplary embodiment.
  • FIG. 5 is a flowchart of a method for determining the first calorie consumption increment of a target user in the current period according to an exemplary embodiment.
  • Figure 6 is a schematic diagram of the internal structure of the gated cycle unit model.
  • Figure 7 is a schematic diagram of the results of the heat consumption estimation test.
  • FIG. 8 is a block diagram of a heat consumption estimating device according to an exemplary embodiment.
  • FIG. 9 is a block diagram of a device for caloric consumption estimation according to an exemplary embodiment.
  • heart rate-based linear regression method based on heart rate
  • different models need to be regressed in different sports scenes (such as walking, running, climbing, cycling, swimming, playing ball, etc.).
  • sports scenes such as walking, running, climbing, cycling, swimming, playing ball, etc.
  • different models need to be transformed.
  • the regression model is used to estimate calorie consumption, but the scene adaptability is poor.
  • the present disclosure provides a calorie consumption estimation method, device and storage medium, which are suitable for calorie consumption estimation in different sports scenarios, reduce individual differences in calorie consumption estimation, and improve the accuracy of calorie consumption estimation. Embodiments of the present disclosure will be described in detail below.
  • the caloric consumption estimation method provided by the present disclosure can be applied to wearable devices, such as smart watches, smart bracelets and other devices.
  • wearable devices such as smart watches, smart bracelets and other devices.
  • the wearable device can calculate the energy consumption in real time. Collect the user's heart rate and calculate the user's calorie consumption during exercise.
  • the caloric consumption estimation method provided by the present disclosure can be applied to a terminal that establishes a connection relationship with a wearable device, such as a user's mobile phone, tablet computer, and other devices.
  • the wearable device can transmit the collected user heart rate to the device in real time.
  • the terminal can obtain the user's heart rate and calculate the user's calorie consumption during exercise.
  • FIG. 1 is a flow chart of a method for estimating heat consumption according to an exemplary embodiment. As shown in FIG. 1 , the method may include S101 to S104.
  • the target user is a user wearing a wearable device.
  • the wearable device can collect the target user's heart rate according to the preset sampling frequency.
  • the preset sampling frequency is 1HZ, then the wearable device can collect the target user's heart rate every 1 second. Heart rate.
  • the target user's physiological characteristic information includes, for example, the target user's weight, age, gender and other information. It should be noted that the target user can fill in the physiological characteristic information such as weight and age on the wearable device or terminal. With the user's authorization, the wearable device or terminal can obtain the physiological characteristic information of the target user.
  • the current period is the period from the previous moment to the current moment. For example, take thirty moments t1, t2, t3,..., t28, t29, t30 from front to back as an example. For example, the current moment is t30, and the current period is from t29 to t30. period, the increment of caloric consumption in the current period is the caloric consumption of the target user from time t29 to time t30.
  • the first calorie consumption increment is corrected according to the calorie consumption estimation model to obtain the second calorie consumption increment of the target user in the current period.
  • the calorie consumption estimation model can be a deep learning network model.
  • the calorie consumption estimation model can construct a complex nonlinear relationship between heart rate and calorie consumption.
  • the calorie consumption estimation model can solve the problem of scene dependence and can adapt to For complex and changeable sports scenes, on the other hand, using the first caloric consumption increment as the prior information of the caloric consumption estimation model can improve the accuracy of the second caloric consumption increment output by the caloric consumption estimation model.
  • the target user's first calorie consumption increment in the current period can be quickly determined, and individual differences can be reduced.
  • the calorie consumption estimation model can adapt to complex and changeable sports. scene to achieve adaptive motion scenes.
  • the total calorie consumption information of the target user during exercise is determined based on the second calorie consumption increment.
  • the movement process includes the process from the start time of the movement to the current time.
  • the target user can click the start exercise button on the wearable device or terminal, and can also select the type of exercise he or she is doing, such as jogging, mountain climbing, cross-country running, etc., and the target user triggers the start exercise button.
  • the moment of pressing the button can be used as the start moment of exercise.
  • the moment when the user wears the wearable device can also be used as the start time of exercise.
  • the user's caloric consumption can be estimated regardless of whether the user is in exercise or daily office status.
  • the calorie consumption increment and total calorie consumption information may be represented by calories.
  • the first calorie consumption increment of the target user in the current period is determined, taking into account the user's physiological characteristic information, that is, considering individual differences, it is possible to Reduce individual differences in caloric consumption estimates, making the determined first caloric consumption increment more accurate. Then, according to the caloric consumption estimation model, the first caloric consumption increment is corrected to obtain the second caloric consumption increment of the target user in the current period.
  • the calorie consumption estimation model can construct a complex nonlinear relationship between heart rate and calorie consumption. The calorie consumption estimation model can solve the problem of scene dependence and can adapt to complex and changeable sports scenes.
  • the first calorie The consumption increment as the prior information of the calorie consumption estimation model, can improve the accuracy of the second calorie consumption increment output by the calorie consumption estimation model, thereby improving the accuracy of the target user's total calorie consumption information during exercise.
  • Figure 2 is a flow chart of a method for estimating heat consumption according to an exemplary embodiment. As shown in Figure 2, the method includes S201 to S206.
  • S201 obtain the target user's heart rate at the current moment and the target user's physiological characteristic information.
  • the implementation of this step may be as S101.
  • S202 determine the first calorie consumption increment of the target user in the current period based on the heart rate at the current moment and the physiological characteristic information of the target user.
  • the implementation of this step may be as S102.
  • the first calorie consumption increment is corrected according to the calorie consumption estimation model to obtain the second calorie consumption increment of the target user in the current period.
  • the implementation of this step may be as S103.
  • the motion state characteristic information of the target user at the current moment is determined.
  • the motion state feature information is used to characterize whether the target user is in the motion steady state stage or the motion recovery stage at the current moment.
  • the target calorie consumption increment of the target user in the current period is determined based on the motion state characteristic information and the second calorie consumption increment.
  • total calorie consumption information is determined based on the target calorie consumption increment.
  • S104 may include S205 and S206. It should be noted that there is no restriction on the execution order of each step shown in Figure 2. For example, S204 can also be executed before S202 or S203. The execution order shown in Figure 2 is only an example.
  • the start-up stage of exercise is the stage when exercise is just beginning. This stage is short and consumes less calories.
  • the stationary stage of exercise is the stage where breathing and heart rate fluctuations are small and relatively stable, such as the running stage at a constant speed. Since the start-up stage of exercise takes a long time, It is short and consumes less calories, so the exercise startup phase and the exercise plateau phase are regarded as the exercise steady state phase in this disclosure.
  • athletes will frequently run at different speeds and take short breaks to recover their physical strength. This stage when the speed is significantly reduced or exercise is paused to restore physical strength, can be regarded as the exercise recovery stage.
  • the characteristic information of the target user's movement status at the current moment can be determined based on the heart rate at the current moment.
  • a classifier model such as a Bayesian classifier model, can be pre-trained, and the heart rate at the current moment is input into the classifier model.
  • the classifier model can output whether the target user is in a stable state of exercise at the current moment. The state stage or the exercise recovery stage.
  • FIG 3 is a flowchart of a method for determining the motion state characteristic information of a target user at the current moment according to an exemplary embodiment.
  • S204 may include S2041 and S2042.
  • the time window includes the period from the specified time to the current time, and the specified time is earlier than the current time.
  • the motion state characteristic information of the target user at the current moment is determined based on the number of heart rate drop moments.
  • the heart rate shows an obvious downward trend.
  • the heart rate collected by the wearable device is jittery, and the heart rate is not during the exercise recovery stage. It is strictly declining. A brief decrease in heart rate does not mean that it is in the exercise recovery stage. The heart rate needs to continue to maintain a downward trend to indicate that it is in the exercise recovery stage.
  • a sliding time window can be used to detect whether the user is currently in the steady state phase of exercise or the recovery phase of exercise.
  • the thirty moments from front to back are t1, t2, t3, ..., t28, t29, and t30.
  • the current moment is, for example, t30.
  • the length of the time window can be set in advance, for example, as 30 seconds, correspondingly the designated time can be time t1, for example, the length of the time window is set to 20 seconds, correspondingly the designated time can be time t10, this disclosure does not limit the length of the time window.
  • the time window corresponding to the current time t30 includes the period from t1 to t30.
  • the wearable device collects the heart rate of the target user in real time.
  • the wearable device or terminal has already obtained the heart rate of the target user at each moment before the current moment. . That is, when the target user's heart rate at time t30 is obtained, the wearable device or terminal has already obtained the heart rate of the target user at time t1, t2, t3, ..., t28, and t29 respectively.
  • time t30 can be used as the heart rate decrease time. If the target user's heart rate at time t29 is less than the heart rate at time t28, then time t29 can be used as the heart rate decrease time. If the target user is at If the heart rate at time t28 is greater than or equal to the heart rate at time t27, then time t28 is not regarded as the heart rate decreasing moment. The judgment of whether other times are regarded as the heart rate decreasing moment will not be described again.
  • the motion state characteristic information of the target user at the current moment can be determined based on the number of heart rate drop moments.
  • the implementation of S2042 above can be as follows:
  • the preset conditions include: the number of heart rate drop moments is greater than the preset quantity threshold, and the number of heart rate drop moments is greater than the preset number threshold. The ratio between the number and the number of moments in the time window is greater than the preset proportion threshold.
  • the preset quantity threshold can be set in advance and can be set according to the length of the time window. For example, the length of the time window is 30 seconds, and the preset quantity threshold can be set to 24.
  • the preset proportion threshold can also be set in advance, for example, set to 80%. If the number of heart rate drop moments meets at least one of the preset conditions, that is, one of the preset conditions is met or both conditions are met at the same time, it can indicate that the target user's heart rate continues to maintain a downward trend within the time window, and the target user's current The movement speed may be significantly reduced or even the movement may be suspended to restore physical energy. It can be determined that the target user is in the movement recovery stage at the current moment.
  • the preset quantity threshold or the ratio between the number of heart rate drop moments and the number of moments in the time window is less than or equal to the preset proportion threshold, it can indicate that the target user's heart rate is not within the time window. If an obvious decrease occurs and the target user does not slow down, it can be determined that the target user is in the steady state stage of motion at the current moment.
  • the time window includes the period from the specified moment to the current moment.
  • the specified moment is earlier than the current moment.
  • the number of moments when the heart rate drops through the time window can reflect whether the user's heart rate in the recent period is in a stable state or in a stable state. Continue to maintain a downward trend, thereby accurately determining the target user's motion status characteristic information at the current moment.
  • the implementation of S205 may be:
  • the motion state characteristic information represents that the target user is in the steady state stage of motion at the current moment, then the second calorie consumption increment is used as the target calorie consumption increment;
  • the target calorie consumption increment is determined based on the second calorie consumption increment, the heart rate at the current moment, the maximum heart rate during exercise, and the preset resting heart rate.
  • the second calorie consumption increment output by the calorie consumption estimation model can be directly used as the target calorie consumption increment.
  • the rate of energy consumption during the exercise recovery stage will be higher than the resting basal metabolism, but lower than the steady-state stage of exercise.
  • the heart rate during the exercise recovery phase will decrease, it will still be at a relatively high level.
  • the caloric consumption has decreased, and the second caloric consumption increment output by the caloric consumption estimation model may appear. The problem of overestimation of caloric expenditure predictions.
  • the target user in order to make the estimation of caloric consumption in the exercise recovery phase more accurate, if the target user is currently in the exercise recovery phase, based on the second caloric consumption increment, the heart rate at the current moment, the maximum heart rate during exercise, and the preset resting Heart rate, determine target calorie consumption increment.
  • the method of determining the target caloric consumption increment during the exercise recovery phase can be shown in Figure 4, including S2051 to S2054.
  • the current heart rate increment is determined based on the preset resting heart rate and the heart rate at the current moment.
  • the difference between the heart rate at the current moment and the preset resting heart rate can be used as the current heart rate increment.
  • the maximum heart rate increment during exercise is determined based on the maximum heart rate and the preset resting heart rate.
  • the difference between the maximum heart rate during exercise and the preset resting heart rate can be used as the maximum heart rate increment.
  • the heat suppression factor ⁇ can be determined by the following formula (1):
  • hr is the heart rate at the current moment
  • hr_rest is the preset resting heart rate
  • hr_max is the maximum heart rate during exercise.
  • the target heat consumption increment is determined based on the second heat consumption increment and the heat suppression factor.
  • the product of the initial heat consumption increment and the heat suppression factor may be used as the target heat consumption increment.
  • the above-mentioned maximum heart rate during exercise is updated in real time during the exercise.
  • the caloric suppression factor the increase in caloric consumption during the exercise recovery phase is suppressed, which can avoid the caloric consumption during the exercise recovery phase. overestimation and improve the accuracy of caloric consumption estimation.
  • the total calorie consumption information can be determined based on the target calorie consumption increment.
  • the current time is t30.
  • the target user's total calorie consumption from the start of exercise to t29 has been calculated. Therefore, the target calorie consumption increment is calculated by adding the target user's total calorie consumption from the start of exercise to t29. By adding up the caloric consumption, the total caloric consumption information of the target user from the start of exercise to the current moment can be obtained.
  • the target user's physiological characteristic information may include the target user's weight and age.
  • the implementation of S102 can be shown in Figure 5, including S1021 and S1022.
  • the target user when preparing to exercise, can click the start exercise button on the wearable device or terminal, and can also select the type of exercise he/she is doing, such as jogging, mountain climbing, cross-country running, etc., according to the target Through the user's selection operation, the wearable device or terminal can obtain information about the type of exercise currently performed by the target user. In another embodiment, the wearable device or terminal can determine the type of exercise currently performed by the target user based on the heart rate variation characteristics of the target user.
  • the target user's heart rate fluctuations are relatively gentle, the target user may be currently performing For uniform-speed exercise, such as treadmill running, if the target user's heart rate fluctuates strongly, the target user may be currently performing variable-speed exercise, such as mountain climbing, cross-country running, etc.
  • the wearable device or terminal can pre-store average intensity information corresponding to multiple sports. For example, average intensity information A1 for jogging, average intensity information A2 for mountain climbing, average intensity information A3 for cross-country running, and average intensity information for cycling can be stored. Strength information A4, etc.
  • the average intensity information corresponding to the type information can be obtained in the following manner:
  • the physiological characteristic information of the first user who performs exercise corresponding to the type information, as well as the first heart rate and the first actual calorie consumption increment when the first user is in the steady state stage of exercise, wherein the physiological characteristic information of the first user includes the first User’s weight and age;
  • the average intensity information is fitted according to the age gain corresponding to the first actual calorie consumption increment, the first heart rate, the preset resting heart rate, the first user's weight, the preset basic weight, and the first user's age.
  • a model between heart rate and caloric consumption increment is established based on the physiological characteristics of high linear correlation between heart rate and caloric consumption during steady-state exercise. For example, by fitting the average intensity information of jogging, the first heart rate and the first actual calorie consumption increment of the first jogging user during the steady state phase of exercise can be collected. The first actual calorie consumption increment can be obtained by The professional cardiopulmonary testing system calculates the caloric consumption of the first user during the collection period (such as 1 second) during which the first heart rate is collected through gas exchange. In order to reduce individual differences, the physiological characteristic information of the first user can also be obtained, and the physiological characteristic information includes the weight and age of the first user. Among them, a large amount of information about the first user who jogs can be collected to make the average intensity information fitted more accurate.
  • normalized parameters can be used when building the model.
  • the ratio between the first user's weight and the preset base weight can be used as a weight increase multiple.
  • the preset base weight can be preset, for example, 60kg.
  • the difference between the first heart rate and the preset resting heart rate can be used as the heart rate increment, and the preset resting heart rate can also be preset.
  • the age gain is the change in metabolic rate corresponding to age changes based on human physiological basis. It is an empirical value ranging from 0.95 to 1.12. The age gain can be set to a fixed value within this range.
  • the average intensity information can be fitted through the following model (2):
  • Calories_delta' is the first actual caloric consumption increment
  • A is the average intensity information
  • weight_multiple' weight'/weight_basic
  • weight' is the weight of the first user
  • weight_basic is the preset basic weight
  • hr_add' hr'-hr_rest
  • hr' is the first heart rate
  • hr_rest is the preset resting heart rate
  • age_gain' is the age gain corresponding to the age of the first user.
  • the first calorie consumption increment is determined based on the average intensity information, the weight of the target user, the preset base weight, the heart rate at the current moment, the preset resting heart rate, and the age gain corresponding to the age of the target user.
  • the first caloric consumption increment Calories_delta can be determined through the following model (3):
  • weight_multiple weight/weight_basic
  • weight is the weight of the target user
  • weight_basic is the default basic weight
  • hr_add hr–hr_rest
  • hr is the heart rate at the current moment
  • hr_rest is the default resting heart rate
  • age_gain is the age corresponding to the target user age gain.
  • the physiological characteristic information of the target user is taken into account.
  • the physiological characteristic information includes, for example, the weight and age of the target user. That is, considering individual differences, the individual difference in caloric consumption estimation can be reduced, so that the first caloric consumption increment is The estimation is more accurate.
  • Using the first calorie consumption increment as the input of the calorie consumption estimation model can provide accurate prior information for the calorie consumption estimation model.
  • the implementation of S103 may be: input the physiological characteristic information of the target user, the heart rate at the current moment and the first calorie consumption increment into the calorie consumption estimation model, and obtain the second calorie consumption increment output by the calorie consumption estimation model. quantity.
  • the calorie consumption estimation model can be trained in the following ways:
  • the second user's physiological characteristic information, second heart rate, prior calorie consumption, and second actual calorie consumption increment are input into the deep learning network model, and the deep learning network model is trained to obtain a calorie consumption estimation model.
  • the second user's physiological characteristic information may include the second user's weight, age, gender and other information.
  • the second actual caloric consumption increment may be calculated through gas exchange through a professional cardiopulmonary testing system, that is, the caloric consumption of the second user within a collection period (such as 1 second) during which the second heart rate is collected.
  • the prior calorie consumption of the second user is determined.
  • the prior calorie consumption is obtained by taking into account the second user's physiological characteristic information, and can avoid individual differences.
  • the second user's physiological characteristic information, second heart rate, prior calorie consumption, and second actual calorie consumption increment are input into the deep learning network model, and the back propagation algorithm can be used to optimize and train the matrix in the deep learning network model. , the caloric consumption estimation model is obtained when training is completed.
  • the heat consumption estimation model may be a gated recurrent unit model (GRU, gated recurrent unit).
  • GRU gated recurrent unit model
  • the GRU model has great advantages in dealing with time series problems. It introduces cell state to save long-term memory and improves the defect of RNN (Recurrent Neural Network) that can only save short-term memory.
  • RNN Recurrent Neural Network
  • the GRU model improves the problem of high computational complexity of the LSTM (Long Short-Term Memory, Long Short-Term Memory Network) deep learning algorithm, making the prediction delay as small as possible.
  • Using the GRU model to build a mapping model between heart rate and caloric consumption can improve the estimation accuracy compared to other machine learning, and is better able to handle the problem of switching between different sports scenes.
  • the GRU model is initialized, and then the GRU model is trained.
  • FIG. 6 is a schematic diagram of the internal structure of the gated cyclic unit model.
  • update gate and reset gate.
  • the input variables only need to undergo vector calculation twice.
  • zt represents the update gate, which is used to control the degree to which the state information from the previous moment enters the current state. The larger the value of the update gate, the more state information from the previous moment will be introduced.
  • rt represents the reset gate, and the control will come from the previous moment. The information of one state is written into the current temporary cell state. The smaller the reset gate is, the less information is written from the previous state.
  • the GRU model can also realize the function of storing long and short-term memory, and its prediction process is as shown in the following formulas (4) to (8):
  • ⁇ is the sigmoid layer, including the sigmoid function, and its expression is as shown in formula (9):
  • the tanh layer contains the tanh function, whose expression is shown in formula (10):
  • e is the Hadamard Product, which means the corresponding elements in the operation matrix are multiplied, so the two multiplication matrices are required to be of the same type.
  • Wr is the weight matrix of the reset gate
  • Wz is the weight matrix of the update gate
  • Wo is the weight matrix of the output.
  • ht and ht-1 respectively represent the output of the cell state storing long-term memory at time t and t-1. Represents the output of the candidate state at time t.
  • Initialize the parameters of the LSTM deep learning network reset the weight matrix Wr of the gate, update the weight matrix Wz of the gate, and the weight matrix of the candidate state.
  • the output weight matrix Wo is initialized to a random number between 0 and 1.
  • the GRU model is trained: input the second user's physiological characteristic information, second heart rate, prior calorie consumption, and second actual calorie consumption increment into the deep learning network model, and the back propagation algorithm can be used Optimize and train the matrix in the deep learning network model, and obtain the calorie consumption estimation model when the training is completed.
  • the number of training iterations is set to epoch
  • the loss function is loss
  • the optimizer is optimizer
  • the number of samples selected for one training is batch size.
  • the GRU model needs to learn the reset gate rt, update gate zt and temporary state during training.
  • LSTM needs to learn the input gate it, the output gate ot, the forget gate ft and the temporary state.
  • GRU model training requires fewer iteration parameters than LSTM.
  • the heat consumption estimation model in this disclosure can be a gated loop unit model, that is, a GRU model.
  • the caloric consumption estimation method provided by this disclosure may also include:
  • the current basal metabolic information of the target user is determined based on the target user's calorie consumption during this exercise, and the current basal metabolic information is displayed.
  • the current basal metabolic information is greater than the target user's basal metabolism before this exercise. information.
  • basal metabolism refers to the energy metabolism under the basic state of the human body.
  • Exercise can improve the basal metabolism of the human body. The greater the intensity of exercise, the higher the calories consumed, and the higher the level of improvement in basal metabolism.
  • the method of calculating the basal metabolic information can refer to related technologies, for example, based on the target user's current basal metabolic information. Determine a coefficient for the caloric consumption of each exercise, and multiply the original basal metabolic information by this coefficient to obtain the current basal metabolic information. Since exercise can improve the basal metabolic level of the human body, the current basal metabolic information of the target user after the end of this exercise Greater than the target user’s basal metabolic information before this exercise.
  • Figure 7 is a schematic diagram of the results of the heat consumption estimation test.
  • 100 pieces of exercise data were collected for walking and running (including indoor walking, indoor running, outdoor walking, and outdoor running).
  • the exercise time length included three levels: 10 minutes, 30 minutes, and 60 minutes; the exercise types were collected 20 pieces of sports data were collected for mountain climbing, including five peaks of different heights, and the exercise time ranged from 20 minutes to 180 minutes; 40 pieces of exercise data were collected for cycling, including four different cycling venues, involving Professional cycling venues and non-professional cycling roads (such as outdoor roads).
  • the ages of the subjects in the above trials ranged from 18 to 43 years old.
  • the caloric consumption increment obtained based on physiological characteristic information is used as the prior information of the deep learning network model, and the model is optimized and trained to avoid the problem of individual differences in caloric estimation.
  • optimized deep learning is used The model estimates caloric consumption, and the error can be reduced by 27% to 43%.
  • FIG. 8 is a block diagram of a heat consumption estimating device according to an exemplary embodiment. As shown in Figure 8, the device 700 may include:
  • the heart rate acquisition module 701 is used to acquire the heart rate of the target user at the current moment and the physiological characteristic information of the target user;
  • the first determination module 702 is configured to determine the first calorie consumption increment of the target user in the current period according to the heart rate at the current moment and the physiological characteristic information of the target user, wherein the current period is from The period between the previous time of the current time and the current time;
  • the second determination module 703 is configured to correct the first calorie consumption increment according to the calorie consumption estimation model to obtain the second calorie consumption increment of the target user in the current period;
  • the total calorie determination module 704 is used to determine the total calorie consumption information of the target user during exercise according to the second calorie consumption increment, wherein the exercise process includes the process from the start time of exercise to the current moment. .
  • the device 700 also includes:
  • a state determination module configured to determine the motion state characteristic information of the target user at the current moment according to the heart rate at the current moment, wherein the motion state characteristic information is used to characterize the motion state characteristic information of the target user at the current moment. Is it in the steady-state phase of exercise or the recovery phase of exercise?
  • the total heat determination module 704 includes:
  • a first determination sub-module configured to determine the target calorie consumption increment of the target user in the current period based on the motion state characteristic information and the second calorie consumption increment;
  • the second determination sub-module is used to determine the total calorie consumption information according to the target calorie consumption increment.
  • the status determination module includes:
  • the time determination submodule is used for each time in the time window corresponding to the current time, if the heart rate of the target user at this time is less than the heart rate of the target user at the previous time of this time, then the The time is used as the heart rate decrease time, wherein the time window includes the period from the designated time to the current time, and the designated time is earlier than the current time;
  • the state determination submodule is used to determine the motion state characteristic information of the target user at the current moment according to the number of the heart rate drop moments.
  • the state determination submodule is configured to determine that the target user is in the exercise recovery stage at the current moment if the number of heart rate drop moments meets at least one of the preset conditions, wherein:
  • the preset conditions include: the number of the heart rate decreasing moments is greater than a preset quantity threshold, and the ratio between the number of the heart rate decreasing moments and the number of moments in the time window is greater than the preset proportion threshold.
  • the first determination sub-module includes:
  • a third determination sub-module configured to use the second calorie consumption increment as the target calorie consumption increment if the motion state characteristic information represents that the target user is in a steady state stage of motion at the current moment;
  • the fourth determination sub-module is used to determine whether the target user is in the exercise recovery stage at the current moment according to the second calorie consumption increment, the heart rate at the current moment, and the exercise process if the motion state characteristic information indicates that the target user is in the exercise recovery stage at the current moment.
  • the maximum heart rate and the preset resting heart rate are used to determine the target calorie consumption increment.
  • the fourth determination sub-module includes:
  • the current heart rate increment determination submodule is used to determine the current heart rate increment based on the preset resting heart rate and the heart rate at the current moment;
  • the maximum heart rate increment determination submodule is used to determine the maximum heart rate increment during exercise based on the maximum heart rate and the preset resting heart rate;
  • the heat suppression factor determination submodule is used to use the ratio between the current heart rate increment and the maximum heart rate increment as the heat suppression factor
  • a heat increment determination submodule configured to determine the target heat consumption increment based on the second heat consumption increment and the heat suppression factor.
  • the physiological characteristic information of the target user includes the weight and age of the target user
  • the first determination module 702 includes:
  • the acquisition sub-module is used to obtain the type information of the current exercise performed by the target user, and the average intensity information corresponding to the pre-stored type information;
  • the fifth determination sub-module is used to determine the age gain corresponding to the average intensity information, the weight of the target user, the preset basic weight, the heart rate at the current moment, the preset resting heart rate, and the age of the target user. , determine the first heat consumption increment.
  • the average intensity information corresponding to the type information is obtained through the following module:
  • the first information acquisition module is used to acquire the physiological characteristic information of the first user who performs the exercise corresponding to the type of information, as well as the first heart rate and the first actual calorie consumption increment when the first user is in the steady state stage of exercise, wherein, the physiological characteristic information of the first user includes the weight and age of the first user;
  • a fitting module configured to calculate the first actual calorie consumption increment, the first heart rate, the preset resting heart rate, the first user's weight, the preset base weight, the first The age gain corresponding to the user's age is used to fit the average intensity information.
  • the second determination module 703 is used to:
  • the calorie consumption estimation model is trained through the following modules:
  • the second information acquisition module is used to acquire the physiological characteristic information of the second user in the exercise state, as well as the second heart rate and the second actual calorie consumption increment of the second user in the exercise state;
  • a priori information determination module configured to determine the prior calorie consumption of the second user based on the physiological characteristic information of the second user and the second heart rate;
  • a training module configured to input the second user's physiological characteristic information, the second heart rate, the prior calorie consumption, and the second actual calorie consumption increment into a deep learning network model, and perform The learning network model is trained to obtain the caloric consumption estimation model.
  • the device also includes:
  • a basal metabolism determination module configured to determine the current basal metabolism information of the target user based on the calorie consumption of the target user's current exercise after the target user finishes exercising, and display the current basal metabolism information, wherein, The current basal metabolic information is greater than the basal metabolic information of the target user before this exercise.
  • the present disclosure also provides a computer-readable storage medium on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the heat consumption estimation method provided by the present disclosure are implemented.
  • FIG. 9 is a block diagram of a device 800 for caloric consumption estimation according to an exemplary embodiment.
  • the device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, or the like.
  • the device 800 may include one or more of the following components: a processing component 802, a memory 804, a power component 806, a multimedia component 808, an audio component 810, an input/output (I/O) interface 812, a sensor component 814, and communications component 816.
  • Processing component 802 generally controls the overall operations of device 800, such as operations associated with display, phone calls, data communications, camera operations, and recording operations.
  • the processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above-mentioned caloric consumption estimation method.
  • processing component 802 may include one or more modules that facilitate interaction between processing component 802 and other components.
  • processing component 802 may include a multimedia module to facilitate interaction between multimedia component 808 and processing component 802.
  • Memory 804 is configured to store various types of data to support operations at device 800 . Examples of such data include instructions for any application or method operating on device 800, contact data, phonebook data, messages, pictures, videos, etc.
  • Memory 804 may be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EEPROM), Programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.
  • SRAM static random access memory
  • EEPROM electrically erasable programmable read-only memory
  • EEPROM erasable programmable read-only memory
  • EPROM Programmable read-only memory
  • PROM programmable read-only memory
  • ROM read-only memory
  • magnetic memory flash memory, magnetic or optical disk.
  • Power component 806 provides power to various components of device 800.
  • Power components 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to device 800 .
  • Multimedia component 808 includes a screen that provides an output interface between the device 800 and the user.
  • the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user.
  • the touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide action.
  • multimedia component 808 includes a front-facing camera and/or a rear-facing camera.
  • the front camera and/or the rear camera may receive external multimedia data.
  • Each front-facing camera and rear-facing camera can be a fixed optical lens system or have a focal length and optical zoom capabilities.
  • Audio component 810 is configured to output and/or input audio signals.
  • audio component 810 includes a microphone (MIC) configured to receive external audio signals when device 800 is in operating modes, such as call mode, recording mode, and speech recognition mode. The received audio signal may be further stored in memory 804 or sent via communication component 816 .
  • audio component 810 also includes a speaker for outputting audio signals.
  • the I/O interface 812 provides an interface between the processing component 802 and a peripheral interface module, which may be a keyboard, a click wheel, a button, etc. These buttons may include, but are not limited to: Home button, Volume buttons, Start button, and Lock button.
  • Sensor component 814 includes one or more sensors that provide various aspects of status assessment for device 800 .
  • the sensor component 814 can detect the open/closed state of the device 800, the relative positioning of components, such as the display and keypad of the device 800, and the sensor component 814 can also detect a change in position of the device 800 or a component of the device 800. , the presence or absence of user contact with the device 800 , device 800 orientation or acceleration/deceleration and temperature changes of the device 800 .
  • Sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact.
  • Sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications.
  • the sensor component 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
  • Communication component 816 is configured to facilitate wired or wireless communication between apparatus 800 and other devices.
  • Device 800 may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof.
  • the communication component 816 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel.
  • the communications component 816 also includes a near field communications (NFC) module to facilitate short-range communications.
  • NFC near field communications
  • the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.
  • RFID radio frequency identification
  • IrDA infrared data association
  • UWB ultra-wideband
  • Bluetooth Bluetooth
  • apparatus 800 may be configured by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable Gate array (FPGA), controller, microcontroller, microprocessor or other electronic components are implemented for performing the above heat consumption estimation method.
  • ASICs application specific integrated circuits
  • DSPs digital signal processors
  • DSPDs digital signal processing devices
  • PLDs programmable logic devices
  • FPGA field programmable Gate array
  • controller microcontroller, microprocessor or other electronic components are implemented for performing the above heat consumption estimation method.
  • a non-transitory computer-readable storage medium including instructions such as a memory 804 including instructions, which can be executed by the processor 820 of the device 800 to complete the above-described heat consumption estimation method is also provided.
  • the non-transitory computer-readable storage medium may be ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.
  • a computer program product comprising a computer program executable by a programmable device, the computer program having a function for performing the above when executed by the programmable device.
  • the code part of the calorie consumption estimation method.

Abstract

本公开涉及一种热量消耗估算方法、装置及存储介质，该方法包括：获取目标用户在当前时刻的心率，以及目标用户的生理特征信息；根据当前时刻的心率和目标用户的生理特征信息，确定目标用户在当前时段内的第一热量消耗增量；根据热量消耗估算模型，对所述第一热量消耗增量进行修正，以得到所述目标用户在所述当前时段内的第二热量消耗增量；根据第二热量消耗增量，确定目标用户在运动过程中的总热量消耗信息，该运动过程包括从运动开始时刻至当前时刻的过程。通过上述技术方案，能够适应复杂多变的运动场景，降低热量消耗估算的个体差异性，且提高热量消耗估算的准确性。

Description

热量消耗估算方法、装置及存储介质 技术领域
本公开涉及人机交互领域，尤其涉及一种热量消耗估算方法、装置及存储介质。
背景技术
随着科技的不断发展，可穿戴设备渐渐进入到了人们的日常生活中。可穿戴设备即直接穿在身上，或是整合到用户衣服上的一种便携式设备，其产品形态多种多样，例如智能手表、智能手环、智能眼镜、智能头盔等等。可穿戴设备中有许多的传感器，能够采集人体的生理学信号，例如心率等信号，从而对用户的健康指标进行监测，其中在关于运动的指标监测中，用户在运动过程中的热量消耗即卡路里消耗，成为人们日益关注的对象，然而相关技术中对热量消耗的计算不够准确。
发明内容
为克服相关技术中存在的问题，本公开提供一种热量消耗估算方法、装置及存储介质。
根据本公开实施例的第一方面，提供一种热量消耗估算方法，包括：
获取目标用户在当前时刻的心率，以及所述目标用户的生理特征信息；
根据所述当前时刻的心率和所述目标用户的生理特征信息，确定所述目标用户在当前时段内的第一热量消耗增量，其中，所述当前时段为从所述当前时刻的上一时刻至所述当前时刻之间的时段；
根据热量消耗估算模型，对所述第一热量消耗增量进行修正，以得到所述目标用户在所述当前时段内的第二热量消耗增量；
根据所述第二热量消耗增量，确定所述目标用户在运动过程中的总热量消耗信息，其中，该运动过程包括从运动开始时刻至所述当前时刻的过程。
可选地，所述方法还包括：
根据所述当前时刻的心率，确定所述目标用户在所述当前时刻的运动状态特征信息，其中，所述运动状态特征信息用于表征所述目标用户在所述当前时刻是处于运动稳态阶段还是运动恢复阶段；
所述根据所述第二热量消耗增量，确定所述目标用户在运动过程中的总热量消耗信息，包括：
根据所述运动状态特征信息和所述第二热量消耗增量，确定所述目标用户在所述当前时段内的目标热量消耗增量；
根据所述目标热量消耗增量，确定所述总热量消耗信息。
可选地，所述根据所述当前时刻的心率，确定所述目标用户在所述当前时刻的运动状态特征信息，包括：
针对所述当前时刻对应的时间窗口中的每一时刻，若所述目标用户在该时刻的心率小于所述目标用户在该时刻的上一时刻的心率，则将该时刻作为心率下降时刻，其中，所述时间窗口包括从指定时刻至所述当前时刻之间的时段，所述指定时刻早于所述当前时刻；
根据所述心率下降时刻的数量，确定所述目标用户在所述当前时刻的运动状态特征信息。
可选地，所述根据所述心率下降时刻的数量，确定所述目标用户在所述当前时刻的 运动状态特征信息，包括：
若所述心率下降时刻的数量满足预设条件中的至少一者，则确定所述目标用户在所述当前时刻处于运动恢复阶段，其中，所述预设条件包括：所述心率下降时刻的数量大于预设数量阈值、所述心率下降时刻的数量与所述时间窗口中时刻数量之间的比值大于预设占比阈值。
可选地，所述根据所述运动状态特征信息和所述第二热量消耗增量，确定所述目标用户在所述当前时段内的目标热量消耗增量，包括：
若所述运动状态特征信息表征所述目标用户在所述当前时刻处于运动稳态阶段，则将所述第二热量消耗增量作为所述目标热量消耗增量；
若所述运动状态特征信息表征所述目标用户在所述当前时刻处于运动恢复阶段，则根据所述第二热量消耗增量、所述当前时刻的心率、运动过程中的最大心率、预设静息心率，确定所述目标热量消耗增量。
可选地，所述根据所述第二热量消耗增量、所述当前时刻的心率、运动过程中的最大心率、预设静息心率，确定所述目标热量消耗增量，包括：
根据所述预设静息心率和所述当前时刻的心率，确定当前心率增量；
根据所述最大心率和所述预设静息心率，确定运动过程中的最大心率增量；
将所述当前心率增量和所述最大心率增量之间的比值，作为热量抑制因子；
根据所述第二热量消耗增量和所述热量抑制因子，确定所述目标热量消耗增量。
可选地，所述目标用户的生理特征信息包括所述目标用户的体重和年龄；
所述根据所述当前时刻的心率和所述目标用户的生理特征信息，确定所述目标用户在当前时段内的第一热量消耗增量，包括：
获取所述目标用户当前进行的运动的类型信息，以及预先存储的所述类型信息对应的平均强度信息；
根据所述平均强度信息、所述目标用户的体重、预设基础体重、所述当前时刻的心率、预设静息心率、所述目标用户的年龄对应的年龄增益，确定所述第一热量消耗增量。
可选地，所述类型信息对应的平均强度信息是通过如下方式得到的：
获取进行所述类型信息对应运动的第一用户的生理特征信息，以及所述第一用户处于运动稳态阶段时的第一心率和第一实际热量消耗增量，其中，所述第一用户的生理特征信息包括所述第一用户的体重和年龄；
根据所述第一实际热量消耗增量、所述第一心率、所述预设静息心率、所述第一用户的体重、所述预设基础体重、所述第一用户的年龄对应的年龄增益，拟合出所述平均强度信息。
可选地，所述根据热量消耗估算模型，对所述第一热量消耗增量进行修正，以得到所述目标用户在所述当前时段内的第二热量消耗增量，包括：
将所述目标用户的生理特征信息、所述当前时刻的心率和所述第一热量消耗增量输入至所述热量消耗估算模型中，得到所述热量消耗估算模型输出的所述第二热量消耗增量。
可选地，所述热量消耗估算模型是通过如下方式训练得到的：
获取处于运动状态的第二用户的生理特征信息，以及所述第二用户处于运动状态时的第二心率和第二实际热量消耗增量；
根据所述第二用户的生理特征信息和所述第二心率，确定所述第二用户的先验热量消耗；
将所述第二用户的生理特征信息、所述第二心率、所述先验热量消耗、所述第二实际热量消耗增量输入至深度学习网络模型中，对所述深度学习网络模型进行训练，以得 到所述热量消耗估算模型。
可选地，所述热量消耗估算模型为门控循环单元模型。
可选地，所述方法还包括：
在所述目标用户结束运动后，根据所述目标用户本次运动的热量消耗量确定所述目标用户的当前基础代谢信息，并展示所述当前基础代谢信息，其中，所述当前基础代谢信息大于所述目标用户在本次运动前的基础代谢信息。
根据本公开实施例的第二方面，提供一种热量消耗估算装置，包括：
心率获取模块，用于获取目标用户在当前时刻的心率，以及所述目标用户的生理特征信息；
第一确定模块，用于根据所述当前时刻的心率和所述目标用户的生理特征信息，确定所述目标用户在当前时段内的第一热量消耗增量，其中，所述当前时段为从所述当前时刻的上一时刻至所述当前时刻之间的时段；
第二确定模块，用于根据热量消耗估算模型，对所述第一热量消耗增量进行修正，以得到所述目标用户在所述当前时段内的第二热量消耗增量；
总热量确定模块，用于根据所述第二热量消耗增量，确定所述目标用户在运动过程中的总热量消耗信息，其中，该运动过程包括从运动开始时刻至所述当前时刻的过程。
可选地，所述装置还包括：
状态确定模块，用于根据所述当前时刻的心率，确定所述目标用户在所述当前时刻的运动状态特征信息，其中，所述运动状态特征信息用于表征所述目标用户在所述当前时刻是处于运动稳态阶段还是运动恢复阶段；
所述总热量确定模块，包括：
第一确定子模块，用于根据所述运动状态特征信息和所述第二热量消耗增量，确定所述目标用户在所述当前时段内的目标热量消耗增量；
第二确定子模块，用于根据所述目标热量消耗增量，确定所述总热量消耗信息。
可选地，所述状态确定模块，包括：
时刻确定子模块，用于针对所述当前时刻对应的时间窗口中的每一时刻，若所述目标用户在该时刻的心率小于所述目标用户在该时刻的上一时刻的心率，则将该时刻作为心率下降时刻，其中，所述时间窗口包括从指定时刻至所述当前时刻之间的时段，所述指定时刻早于所述当前时刻；
状态确定子模块，用于根据所述心率下降时刻的数量，确定所述目标用户在所述当前时刻的运动状态特征信息。
可选地，所述状态确定子模块用于：若所述心率下降时刻的数量满足预设条件中的至少一者，则确定所述目标用户在所述当前时刻处于运动恢复阶段，其中，所述预设条件包括：所述心率下降时刻的数量大于预设数量阈值、所述心率下降时刻的数量与所述时间窗口中时刻数量之间的比值大于预设占比阈值。
可选地，所述第一确定子模块，包括：
第三确定子模块，用于若所述运动状态特征信息表征所述目标用户在所述当前时刻处于运动稳态阶段，则将所述第二热量消耗增量作为所述目标热量消耗增量；
第四确定子模块，用于若所述运动状态特征信息表征所述目标用户在所述当前时刻处于运动恢复阶段，则根据所述第二热量消耗增量、所述当前时刻的心率、运动过程中的最大心率、预设静息心率，确定所述目标热量消耗增量。
可选地，所述第四确定子模块，包括：
当前心率增量确定子模块，用于根据所述预设静息心率和所述当前时刻的心率，确定当前心率增量；
最大心率增量确定子模块，用于根据所述最大心率和所述预设静息心率，确定运动过程中的最大心率增量；
热量抑制因子确定子模块，用于将所述当前心率增量和所述最大心率增量之间的比值，作为热量抑制因子；
热量增量确定子模块，用于根据所述第二热量消耗增量和所述热量抑制因子，确定所述目标热量消耗增量。
可选地，所述目标用户的生理特征信息包括所述目标用户的体重和年龄；
所述第一确定模块，包括：
获取子模块，用于获取所述目标用户当前进行的运动的类型信息，以及预先存储的所述类型信息对应的平均强度信息；
第五确定子模块，用于根据所述平均强度信息、所述目标用户的体重、预设基础体重、所述当前时刻的心率、预设静息心率、所述目标用户的年龄对应的年龄增益，确定所述第一热量消耗增量。
可选地，所述类型信息对应的平均强度信息是通过如下模块得到的：
第一信息获取模块，用于获取进行所述类型信息对应运动的第一用户的生理特征信息，以及所述第一用户处于运动稳态阶段时的第一心率和第一实际热量消耗增量，其中，所述第一用户的生理特征信息包括所述第一用户的体重和年龄；
拟合模块，用于根据所述第一实际热量消耗增量、所述第一心率、所述预设静息心率、所述第一用户的体重、所述预设基础体重、所述第一用户的年龄对应的年龄增益，拟合出所述平均强度信息。
可选地，所述第二确定模块用于：
将所述目标用户的生理特征信息、所述当前时刻的心率和所述第一热量消耗增量输入至所述热量消耗估算模型中，得到所述热量消耗估算模型输出的所述第二热量消耗增量。
可选地，所述热量消耗估算模型是通过如下模块训练得到的：
第二信息获取模块，用于获取处于运动状态的第二用户的生理特征信息，以及所述第二用户处于运动状态时的第二心率和第二实际热量消耗增量；
先验信息确定模块，用于根据所述第二用户的生理特征信息和所述第二心率，确定所述第二用户的先验热量消耗；
训练模块，用于将所述第二用户的生理特征信息、所述第二心率、所述先验热量消耗、所述第二实际热量消耗增量输入至深度学习网络模型中，对所述深度学习网络模型进行训练，以得到所述热量消耗估算模型。
可选地，所述装置还包括：
基础代谢确定模块，用于在所述目标用户结束运动后，根据所述目标用户本次运动的热量消耗量确定所述目标用户的当前基础代谢信息，并展示所述当前基础代谢信息，其中，所述当前基础代谢信息大于所述目标用户在本次运动前的基础代谢信息。
根据本公开实施例的第三方面，提供一种热量消耗估算装置，包括：
处理器；
用于存储处理器可执行指令的存储器；
其中，所述处理器被配置为：执行本公开实施例第一方面提供的所述方法的步骤。
根据本公开实施例的第四方面，提供一种计算机可读存储介质，其上存储有计算机程序指令，该程序指令被处理器执行时实现本公开第一方面所提供的热量消耗估算方法的步骤。
本公开的实施例提供的技术方案可以包括以下有益效果：
通过上述技术方案，根据目标用户在当前时刻的心率和目标用户的生理特征信息，确定目标用户在当前时段内的第一热量消耗增量，考虑用户的生理特征信息，即考虑个体差异问题，能够降低热量消耗估算的个体差异性，使得确定出的第一热量消耗增量更准确。之后根据热量消耗估算模型，对第一热量消耗增量进行修正，以得到目标用户在当前时段内的第二热量消耗增量。一方面，热量消耗估算模型可以构建心率与热量消耗量之间复杂的非线性关系，热量消耗估算模型可以解决场景依赖的问题，能够适应复杂多变的运动场景，另一方面，将第一热量消耗增量作为热量消耗估算模型的先验信息，能够提高热量消耗估算模型输出的第二热量消耗增量的准确性，从而提高目标用户在运动过程中的总热量消耗信息的准确性。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本公开。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本公开的实施例，并与说明书一起用于解释本公开的原理。
图1是根据一示例性实施例示出的一种热量消耗估算方法的流程图。
图2是根据一示例性实施例示出的一种热量消耗估算方法的流程图。
图3是根据一示例性实施例示出的一种确定目标用户在当前时刻的运动状态特征信息的方法的流程图。
图4是根据一示例性实施例示出的一种在运动恢复阶段确定目标热量消耗增量的方法的流程图。
图5是根据一示例性实施例示出的一种确定目标用户在当前时段内的第一热量消耗增量的方法的流程图。
图6是门控循环单元模型的内部结构示意图。
图7是热量消耗估算试验结果示意图。
图8是根据一示例性实施例示出的热量消耗估算装置的框图。
图9是根据一示例性实施例示出的一种用于热量消耗估算的装置的框图。
具体实施方式
这里将详细地对示例性实施例进行说明，其示例表示在附图中。下面的描述涉及附图时，除非另有表示，不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本公开相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本公开的一些方面相一致的装置和方法的例子。
需要说明的是，本申请中所有获取信号、信息或数据的动作都是在遵照所在地国家相应的数据保护法规政策的前提下，并获得由相应装置所有者给予授权的情况下进行的。
目前，估算用户在运动过程中的热量消耗即卡路里消耗的方法主要有以下几种：基于心率的线性回归方法、基于心率的机器学习模型或深度学习模型、基于加速度的热量消耗估计。其中，在基于心率的线性回归方法中，需要在不同的运动场景(如走路、跑步、爬山、骑行、游泳、打球等)下分别回归出不同的模型，在切换运动场景时，需要变换不同的回归模型来进行热量消耗的估算，场景适应性较差。
有鉴于此，本公开提供一种热量消耗估算方法、装置及存储介质，适用于不同运动场景的热量消耗估算，且降低热量消耗估算的个体差异性，提高热量消耗估算的准确性。以下对本公开的实施方式进行详细说明。
需要说明的是，在一实施例中，本公开提供的热量消耗估算方法可以应用于可穿戴 设备，如智能手表、智能手环等设备，用户佩戴可穿戴设备的情况下，可穿戴设备能够实时采集用户的心率，并计算用户在运动过程中的热量消耗。在另一实施例中，本公开提供的热量消耗估算方法可以应用于与可穿戴设备建立连接关系的终端，如用户的手机、平板电脑等设备，可穿戴设备可以将采集的用户心率实时传输给终端，终端可获取到用户的心率并计算用户在运动过程中的热量消耗。
图1是根据一示例性实施例示出的一种热量消耗估算方法的流程图，如图1所示，该方法可包括S101至S104。
在S101中，获取目标用户在当前时刻的心率，以及目标用户的生理特征信息。
其中，目标用户为佩戴可穿戴设备的用户，可穿戴设备可按照预设采样频率采集目标用户的心率，例如预设采样频率为1HZ，则可穿戴设备可每隔1秒钟采集一次目标用户的心率。
目标用户的生理特征信息例如包括目标用户的体重、年龄、性别等信息。需要说明的是，目标用户可以在可穿戴设备或终端上填写自己的体重和年龄等生理特征信息，在经过用户授权的情况下，可穿戴设备或终端可获取到目标用户的生理特征信息。
在S102中，根据当前时刻的心率和目标用户的生理特征信息，确定目标用户在当前时段内的第一热量消耗增量。
其中，当前时段为从当前时刻的上一时刻至当前时刻之间的时段。示例地，以从前到后依次为t1、t2、t3、……、t28、t29、t30三十个时刻为例进行说明，例如当前时刻为t30时刻，当前时段为从t29时刻至t30时刻之间的时段，当前时段内的热量消耗增量即为目标用户从t29时刻至t30时刻的热量消耗量。
相关技术中在进行热量消耗估算时，并未考虑个体差异的问题，不同的用户，即使在进行相同的运动，他们消耗的热量也可能是不同的。人体在运动时，影响热量消耗的因素有多种，例如，完成同一项运动，体重较重的用户需要对外做更多的功才能完成，体重对于热量消耗的影响很大，另外，年龄会影响身体的新陈代谢速度，也会影响运动时热量的消耗。因此本公开中，在进行热量消耗估算时，考虑用户的生理特征信息，即考虑个体差异问题，能够降低热量消耗估算的个体差异性，使得热量消耗的估算更加准确。
在S103中，根据热量消耗估算模型，对第一热量消耗增量进行修正，以得到目标用户在当前时段内的第二热量消耗增量。
运动场景有多种，每一种运动场景下的人体热量消耗的特点是不一样的，例如室内跑步机跑步时，人体热量消耗可能是一个较为稳定的状态，而踢足球、打篮球等球类运动消耗的热量可能是非常不稳定的，具有爆发性和多次恢复性，可能可穿戴设备事先无法获得用户的运动场景，因此需要热量估算方法对于运动场景是可以自适应的。
本公开中，热量消耗估算模型可以为深度学习网络模型，一方面，热量消耗估算模型可以构建心率与热量消耗量之间复杂的非线性关系，热量消耗估算模型可以解决场景依赖的问题，能够适应复杂多变的运动场景，另一方面，将第一热量消耗增量作为热量消耗估算模型的先验信息，能够提高热量消耗估算模型输出的第二热量消耗增量的准确性。
这样，根据当前时刻的心率和目标用户的生理特征信息，能够快速确定目标用户在当前时段内的第一热量消耗增量，且能够减小个体差异，热量消耗估算模型能够适应复杂多变的运动场景，实现运动场景自适应。
在S104中，根据第二热量消耗增量，确定目标用户在运动过程中的总热量消耗信息。
其中，该运动过程包括从运动开始时刻至当前时刻的过程。示例地，在准备进行运动时，目标用户可在可穿戴设备或终端上点击开始运动按钮，并且还可以选择自己进行 的运动的运动类型，如慢跑、登山、越野跑等，目标用户触发开始运动按钮的时刻，可作为运动开始时刻。另外，也可将用户佩戴可穿戴设备的时刻作为运动开始时刻，即使用户没有点击开始运动按钮，无论用户处于运动状态还是日常办公状态，均可对用户的热量消耗进行估算。示例地，热量消耗增量、总热量消耗信息可通过卡路里来进行表示。
通过上述技术方案，根据目标用户在当前时刻的心率和目标用户的生理特征信息，确定目标用户在当前时段内的第一热量消耗增量，考虑用户的生理特征信息，即考虑个体差异问题，能够降低热量消耗估算的个体差异性，使得确定出的第一热量消耗增量更准确。之后根据热量消耗估算模型，对第一热量消耗增量进行修正，以得到目标用户在当前时段内的第二热量消耗增量。一方面，热量消耗估算模型可以构建心率与热量消耗量之间复杂的非线性关系，热量消耗估算模型可以解决场景依赖的问题，能够适应复杂多变的运动场景，另一方面，将第一热量消耗增量作为热量消耗估算模型的先验信息，能够提高热量消耗估算模型输出的第二热量消耗增量的准确性，从而提高目标用户在运动过程中的总热量消耗信息的准确性。
图2是根据一示例性实施例示出的一种热量消耗估算方法的流程图，如图2所示，该方法包括S201至S206。
在S201中，获取目标用户在当前时刻的心率，以及目标用户的生理特征信息。该步骤的实施方式可如S101。
在S202中，根据当前时刻的心率和目标用户的生理特征信息，确定目标用户在当前时段内的第一热量消耗增量。该步骤的实施方式可如S102。
在S203中，根据热量消耗估算模型，对第一热量消耗增量进行修正，以得到目标用户在当前时段内的第二热量消耗增量。该步骤的实施方式可如S103。
在S204中，根据当前时刻的心率，确定目标用户在当前时刻的运动状态特征信息。其中，运动状态特征信息用于表征目标用户在当前时刻是处于运动稳态阶段还是运动恢复阶段。
在S205中，根据运动状态特征信息和第二热量消耗增量，确定目标用户在当前时段内的目标热量消耗增量。
在S206中，根据目标热量消耗增量，确定总热量消耗信息。
上述S104可包括S205和S206。需要说明的是，对于图2所示的各个步骤的执行顺序不做限制，例如S204也可在S202或S203之前执行，图2所示的执行顺序仅为示例。
其中，用户在运动时通常经历运动启动阶段、运动平稳阶段、运动恢复阶段。运动启动阶段即刚开始运动的阶段，该阶段时间较短且消耗的热量较少，运动平稳阶段即呼吸和心率波动较小、相对平稳的阶段，例如匀速跑步阶段，由于运动启动阶段的时间较短且消耗的热量较少，因此本公开中将运动启动阶段和运动平稳阶段作为运动稳态阶段。在户外长跑、越野跑、登山等场景中，运动者会经常性的变速跑以及短暂休息以恢复体力，这种速度大幅降低或者运动暂停以恢复体力的阶段，可作为运动恢复阶段。
由于在不同运动阶段，用户的心率不同，且心率随运动阶段的变化而变化，因此可根据当前时刻的心率，确定目标用户在当前时刻的运动状态特征信息。在一可选实施例中，可预先训练一分类器模型，如贝叶斯分类器模型，将当前时刻的心率输入至分类器模型中，分类器模型可输出目标用户在当前时刻是处于运动稳态阶段还是运动恢复阶段。
图3是根据一示例性实施例示出的一种确定目标用户在当前时刻的运动状态特征信息的方法的流程图，如图3所示，S204可包括S2041和S2042。
在S2041中，针对当前时刻对应的时间窗口中的每一时刻，若目标用户在该时刻的心率小于目标用户在该时刻的上一时刻的心率，则将该时刻作为心率下降时刻。其中，时间窗口包括从指定时刻至当前时刻之间的时段，指定时刻早于当前时刻。
在S2042中，根据心率下降时刻的数量，确定目标用户在当前时刻的运动状态特征信息。
在运动过程中，当运动速度出现大幅度降低或是出现暂停运动以恢复体能时，心率表现为明显的下降趋势，但是可穿戴设备采集到的心率是具有抖动性的，在运动恢复阶段心率并非是严格下降的，心率短暂下降也并不代表是处于运动恢复阶段，需要心率持续保持下降趋势才能说明此时处于运动恢复阶段。
因此本公开中可以采用滑动时间窗口的方式，检测用户当前是处于运动稳态阶段还是运动恢复阶段。示例地，以从前到后依次为t1、t2、t3、……、t28、t29、t30三十个时刻为例进行说明，当前时刻例如为t30时刻，时间窗口的长度可以预先设置，例如设置为30秒，相应地指定时刻可以为t1时刻，例如时间窗口的长度设置为20秒，相应地指定时刻可以为t10时刻，本公开对于时间窗口的长度不做限制。以指定时刻为t1时刻为例，当前时刻t30对应的时间窗口包括从t1至t30之间的时段。
值得说明的是，可穿戴设备是实时采集目标用户的心率，在获取到目标用户在当前时刻的心率时，对于目标用户在当前时刻之前的各个时刻的心率，可穿戴设备或终端均已经获取到。即在获取到目标用户在t30时刻的心率时，对于目标用户分别在t1、t2、t3、……、t28、t29时刻的心率，可穿戴设备或终端均已经获取到。
如果目标用户在t30时刻的心率小于t29时刻的心率，那么t30时刻可作为心率下降时刻，如果目标用户在t29时刻的心率小于t28时刻的心率，那么t29时刻可作为心率下降时刻，如果目标用户在t28时刻的心率大于或等于t27时刻的心率，那么t28时刻不作为心率下降时刻，其他时刻是否作为心率下降时刻的判断不再赘述。
在确定出时间窗口中哪些时刻作为心率下降时刻后，可根据心率下降时刻的数量，确定目标用户在当前时刻的运动状态特征信息，上述S2042的实施方式可以为：
若心率下降时刻的数量满足预设条件中的至少一者，则确定目标用户在当前时刻处于运动恢复阶段，其中，预设条件包括：心率下降时刻的数量大于预设数量阈值、心率下降时刻的数量与时间窗口中时刻数量之间的比值大于预设占比阈值。
其中，预设数量阈值可预先设置，并可根据时间窗口的长度设置，示例地，时间窗口的长度为30秒，该预设数量阈值可设置为24。预设占比阈值也可预先设置，例如设置为80％。如果心率下降时刻的数量满足预设条件中的至少一者，即满足预设条件之一或同时满足这两个条件，可表征目标用户在时间窗口内的心率持续保持下降趋势，目标用户当前的运动速度可能出现大幅度降低甚至是暂停运动以恢复体能，可确定目标用户在当前时刻处于运动恢复阶段。如果心率下降时刻的数量小于或等于预设数量阈值，或者心率下降时刻的数量与时间窗口中时刻数量之间的比值小于或等于预设占比阈值，可表征目标用户在时间窗口内的心率未发生明显的下降，目标用户未降速运动，可确定目标用户在当前时刻处于运动稳态阶段。
通过上述技术方案，时间窗口包括从指定时刻至当前时刻之间的时段，指定时刻早于当前时刻，通过时间窗口中心率下降时刻的数量，可反映用户在最近时段内的心率是处于平稳状态还是持续保持下降趋势，从而准确确定目标用户在当前时刻的运动状态特征信息。
在一实施例中，S205的实施方式可以为：
若运动状态特征信息表征目标用户在当前时刻处于运动稳态阶段，则将第二热量消耗增量作为目标热量消耗增量；
若运动状态特征信息表征目标用户在当前时刻处于运动恢复阶段，则根据第二热量消耗增量、当前时刻的心率、运动过程中的最大心率、预设静息心率，确定目标热量消耗增量。
如果目标用户当前处于运动稳态阶段，可直接将热量消耗估算模型输出的第二热量消耗增量作为目标热量消耗增量。
如果目标用户当前处于运动恢复阶段，由于运动后过氧消耗(EPOC)的存在，在运动恢复阶段能量消耗的速率是会高于静息时的基础代谢，但是会低于运动稳态阶段的。运动恢复阶段的心率虽然会下降，但是仍然会处于一个比较高的水平，此时心率虽然处于一个较高水平，但是热量消耗已经降低，热量消耗估算模型输出的第二热量消耗增量可能会出现热量消耗预测高估的问题。
本公开中，为了使得运动恢复阶段的热量消耗估算更加准确，若目标用户当前处于运动恢复阶段，则根据第二热量消耗增量、当前时刻的心率、运动过程中的最大心率、预设静息心率，确定目标热量消耗增量。在运动恢复阶段确定目标热量消耗增量的方式可如图4所示，包括S2051至S2054。
在S2051中，根据预设静息心率和当前时刻的心率，确定当前心率增量。
示例地，可将当前时刻的心率与预设静息心率之间的差值，作为当前心率增量。
在S2052中，根据最大心率和预设静息心率，确定运动过程中的最大心率增量。
示例地，可将运动过程中的最大心率和预设静息心率之间的差值，作为最大心率增量。
在S2053中，将当前心率增量和最大心率增量之间的比值，作为热量抑制因子。
热量抑制因子η可通过如下公式(1)确定：
Figure PCTCN2022092877-appb-000001
其中，hr为当前时刻的心率，hr_rest为预设静息心率，hr_max为运动过程中的最大心率。
在S2054中，根据第二热量消耗增量和热量抑制因子，确定目标热量消耗增量。
示例地，可将初始热量消耗增量与热量抑制因子的乘积，作为目标热量消耗增量。
其中，上述的运动过程中的最大心率，是在运动进行的过程中实时更新的，这样，通过热量抑制因子，对运动恢复阶段的热量消耗增量做抑制策略，可以避免运动恢复阶段热量消耗量的高估，提高热量消耗估算的准确性。
在确定出目标用户在当前时段内的目标热量消耗增量后，可根据目标热量消耗增量，确定总热量消耗信息。
示例地，当前时刻为t30时刻，在当前时刻，目标用户从运动开始时刻至t29时刻的总热量消耗量已经计算出来，因此将目标热量消耗增量与目标用户从运动开始时刻至t29时刻的总热量消耗量相加，可得出目标用户从运动开始时刻至当前时刻的总热量消耗信息。
在一示例中，目标用户的生理特征信息可包括目标用户的体重和年龄。相应地，S102的实施方式可如图5所示，包括S1021和S1022。
在S1021中，获取目标用户当前进行的运动的类型信息，以及预先存储的类型信息对应的平均强度信息。
在一实施例中，在准备进行运动时，目标用户可在可穿戴设备或终端上点击开始运动按钮，并且还可以选择自己进行的运动的运动类型，如慢跑、登山、越野跑等，根据目标用户的选择操作，可穿戴设备或终端可获取到目标用户当前进行的运动的类型信息。在另一实施例中，可穿戴设备或终端可根据目标用户的心率变化特征，确定目标用户当前进行的运动的类型信息，例如，如果目标用户的心率波动较为平缓，目标用户当前进行的可能是匀速运动，如跑步机跑步，如果目标用户的心率波动较强烈，目标用户当前 进行的可能是变速运动，如爬山、越野跑等。可穿戴设备或终端中可预先存储有多种运动分别对应的平均强度信息，例如可存储有慢跑的平均强度信息A1、登山的平均强度信息A2、越野跑的平均强度信息A3、骑行的平均强度信息A4，等等。
在一实施例中，类型信息对应的平均强度信息可以是通过如下方式得到的：
获取进行类型信息对应运动的第一用户的生理特征信息，以及第一用户处于运动稳态阶段时的第一心率和第一实际热量消耗增量，其中，第一用户的生理特征信息包括第一用户的体重和年龄；
根据第一实际热量消耗增量、第一心率、预设静息心率、第一用户的体重、预设基础体重、第一用户的年龄对应的年龄增益，拟合出平均强度信息。
本公开中，结合运动稳态时心率与热量消耗高度线性相关性的生理学特性，建立心率与热量消耗增量之间的模型。示例地，例如拟合慢跑的平均强度信息，可收集进行慢跑的第一用户在运动稳态阶段时的第一心率和第一实际热量消耗增量，该第一实际热量消耗增量可以是通过专业心肺测试系统通过气体交换计算出的，即采集到该第一心率的采集周期(如1秒)内第一用户的热量消耗量。为了降低个体差异，还可获取第一用户的生理特征信息，该生理特征信息包括第一用户的体重和年龄。其中，可收集大量进行慢跑的第一用户的信息，以使得拟合出的平均强度信息更准确。
为了降低个体差异，建立模型时可采用归一化的参数。第一用户的体重与预设基础体重之间的比值可作为体重增加倍数，预设基础体重可预先设置，例如设置为60kg。第一心率与预设静息心率之差可作为心率增量，预设静息心率也可预先设置。年龄增益为根据人体生理学基础依据按照年龄变化对应的代谢速率的变化，为经验值，范围从0.95至1.12，年龄增益可设置为该范围内的固定值。
示例地，可通过如下模型(2)拟合出平均强度信息：
Calories_delta'＝A*weight_multiple'*hr_add'*age_gain'    (2)
其中，Calories_delta’为第一实际热量消耗增量，A为平均强度信息，weight_multiple’＝weight’/weight_basic，weight’为第一用户的体重，weight_basic为预设基础体重，hr_add’＝hr’–hr_rest，hr’为第一心率，hr_rest为预设静息心率，age_gain’为第一用户的年龄对应的年龄增益。在拟合平均强度信息时，Calories_delta’、weight_multiple’、hr_add’、age_gain’均为已知，通过模型(2)可拟合出平均强度信息A。拟合出其他运动类型的平均强度信息的方式与之类似。
在S1022中，根据平均强度信息、目标用户的体重、预设基础体重、当前时刻的心率、预设静息心率、目标用户的年龄对应的年龄增益，确定第一热量消耗增量。
示例地，可通过如下模型(3)确定第一热量消耗增量Calories_delta：
Calories_delta＝A*weight_multiple*hr_add*age_gain    (3)
其中，weight_multiple＝weight/weight_basic，weight为目标用户的体重，weight_basic为预设基础体重，hr_add＝hr–hr_rest，hr为当前时刻的心率，hr_rest为预设静息心率，age_gain为目标用户的年龄对应的年龄增益。在确定第一热量消耗增量Calories_delta时，A、weight_multiple、hr_add、age_gain均为已知，由此确定出第一热量消耗增量。
通过上述技术方案，考虑目标用户的生理特征信息，该生理特征信息例如包括目标用户的体重和年龄，即考虑个体差异问题，能够降低热量消耗估算的个体差异性，使得第一热量消耗增量的估算更加准确，将第一热量消耗增量作为热量消耗估算模型的输入，可以为热量消耗估算模型提供准确的先验信息。
本公开中，S103的实施方式可以为：将目标用户的生理特征信息、当前时刻的心率和第一热量消耗增量输入至热量消耗估算模型中，得到热量消耗估算模型输出的第二热 量消耗增量。
其中，热量消耗估算模型可以是通过如下方式训练得到的：
获取处于运动状态的第二用户的生理特征信息，以及第二用户处于运动状态时的第二心率和第二实际热量消耗增量；
根据第二用户的生理特征信息和第二心率，确定第二用户的先验热量消耗；
将第二用户的生理特征信息、第二心率、先验热量消耗、第二实际热量消耗增量输入至深度学习网络模型中，对深度学习网络模型进行训练，以得到热量消耗估算模型。
示例地，第二用户的生理特征信息可包括第二用户的体重、年龄、性别等信息。该第二实际热量消耗增量可以是通过专业心肺测试系统通过气体交换计算出的，即采集到该第二心率的采集周期(如1秒)内第二用户的热量消耗量。根据第二用户的生理特征信息和第二心率，确定第二用户的先验热量消耗，该先验热量消耗是考虑了第二用户的生理特征信息得到的，能够避免个体差异性。将第二用户的生理特征信息、第二心率、先验热量消耗、第二实际热量消耗增量输入至深度学习网络模型中，可以采用反向传播算法对深度学习网络模型中的矩阵进行优化训练，训练完成时得到热量消耗估算模型。
本公开中，为建立运动场景自适应的热量消耗估算模型，热量消耗估算模型可以为门控循环单元模型(GRU，gated recurrent Unit)。GRU模型在处理时间序列问题上具有很大的优势，引入细胞态保存长期记忆，改进了RNN(Recurrent Neural Network)循环神经网络只能保存短期记忆的缺陷。同时GRU模型改善了LSTM(Long Short-Term Memory，长短期记忆网络)深度学习算法计算复杂度高的问题，使得预测时延迟尽可能的小。使用GRU模型构建心率与热量消耗之间的映射模型，能够相较于其他机器学习提高估计精度，且更能够处理不同运动场景切换的问题。值得说明的是，以下训练参数仅作为示例，不构成对本公开实施方式的限制，首先对GRU模型进行初始化，然后对GRU模型进行训练，迭代次数例如取M＝256，损失函数loss＝mae(平均绝对误差)，优化器选择Adam优化器，一次训练所选取的样本数为batch size＝16。
图6是门控循环单元模型的内部结构示意图，如图6所示，GRU模型中使用两个门：更新门和重置门，输入变量只需要经过两次向量计算。其中zt代表更新门，用于控制从前一刻起的状态信息进入当前状态的程度，更新门的值越大，则引入来自前一时刻的更多状态信息，rt代表重置门，控制将来自前一状态的信息写入当前暂存细胞态，重置门越小，从前一状态写入的信息就越少。GRU模型同样能够实现储存长短期记忆的功能，其预测过程如下公式(4)至(8)所示：
r t＝σ(W r·[h t-1，x t])    (4)
z t＝σ(W z·[h t-1，x t])    (5)
Figure PCTCN2022092877-appb-000002
Figure PCTCN2022092877-appb-000003
y t＝σ(W o·h t)    (8)
其中，σ为sigmoid层，包含sigmoid函数，其表达式如公式(9)所示：
Figure PCTCN2022092877-appb-000004
tanh层包含tanh函数，其表达式如公式(10)所示：
Figure PCTCN2022092877-appb-000005
e是Hadamard Product，也就是操作矩阵中对应的元素相乘，因此要求两个相乘矩阵是同型的。Wr是重置门的权重矩阵，Wz是更新门的权重矩阵，
Figure PCTCN2022092877-appb-000006
是候选态的权重矩阵，Wo是输出的权重矩阵。ht、ht-1分别表示储存长期记忆的细胞态在t和t-1时刻的输出。
Figure PCTCN2022092877-appb-000007
表示候选态在t时刻的输出。
初始化LSTM深度学习网络的参数：将重置门的权重矩阵Wr、更新门的权重矩阵Wz、候选态的权重矩阵
Figure PCTCN2022092877-appb-000008
输出的权重矩阵Wo初始化为0至1之间的随机数。设置GRU深度学习网络的输入层神经元个数为M，层数设置为i，每一层的输出作为下一层的输入。GRU模型初始化完成之后对GRU模型进行训练：将第二用户的生理特征信息、第二心率、先验热量消耗、第二实际热量消耗增量输入至深度学习网络模型中，可以采用反向传播算法对深度学习网络模型中的矩阵进行优化训练，训练完成时得到热量消耗估算模型。其中设置训练迭代次数为epoch，损失函数为loss，优化器为optimizer，一次训练所选取的样本数为batch size。本实施例中取M＝256，i＝2，epoch＝50，loss＝mae(平均绝对误差)，optimizer＝Adam(Adam优化器)，batch size＝16。
由上述公式可知，GRU模型在训练时需要学习重置门rt、更新门zt以及暂存态
Figure PCTCN2022092877-appb-000009
三套参数，GRU模型总的参数数量公式为：总参数＝3*隐藏层参数*(输入层参数+偏置参数+输出层参数)。而LSTM在训练时需要学习输入门it、输出门ot、遗忘门ft以及暂存态
Figure PCTCN2022092877-appb-000010
四套参数，LSTM总的参数数量公式为：总参数＝4*隐藏层参数*(输入层参数+偏置参数+输出层参数)。GRU模型训练时需要学习迭代的参数比LSTM少，因此GRU模型训练比LSTM快，收敛迭代次数比LSTM少。LSTM在预测时输入的肌电特征需要经过七次复杂的向量计算才能得出最终的估计角度，而GRU模型在线预测时只需要五次向量计算即可得到最终的估计角度，GRU模型在线预测的时效性也是优于LSTM模型的。因此无论是训练阶段还是预测阶段，GRU模型的时效性均优于LSTM模型，故本公开中热量消耗估算模型可以为门控循环单元模型即GRU模型。
本公开提供的热量消耗估算方法还可包括：
在目标用户结束运动后，根据目标用户本次运动的热量消耗量确定目标用户的当前基础代谢信息，并展示当前基础代谢信息，其中，当前基础代谢信息大于目标用户在本次运动前的基础代谢信息。
其中，基础代谢是指人体基础状态下的能量代谢，运动可以提高人体的基础代谢，运动强度越大，消耗的热量越高，基础代谢提高的水平也越高，在目标用户结束运动后，可根据目标用户本次运动的热量消耗量确定目标用户的当前基础代谢信息，并在可穿戴设备或终端上展示该当前基础代谢信息，计算基础代谢信息的方式可参照相关技术，例如根据目标用户本次运动的热量消耗量确定一个系数，将原基础代谢信息与该系数相乘得到当前基础代谢信息，由于运动可以提高人体的基础代谢水平，因此目标用户在本次运动结束后的当前基础代谢信息大于目标用户在本次运动前的基础代谢信息。
图7是热量消耗估算试验结果示意图。在试验中，采集运动类型为走跑(包含室内走路、室内跑步、室外走路、室外跑步)的运动数据100条，其中运动时间长度包含10分钟、30分钟、60分钟三个等级；采集运动类型为爬山的运动数据20条，包含五个不同高度的山峰，运动时间长度从20分钟至180分钟不等；采集运动类型为骑行的运动数 据40条，包含四种不同的骑行场地，涉及专业骑行场地以及非专业骑行道路(如户外马路)。上述试验中受试者的年龄跨度从18到43岁。
本公开中采用根据生理特征信息得到的热量消耗增量作为深度学习网络模型的先验信息，对模型进行优化训练，避免热量估算时个体差异性的问题，如图7所示，采用优化深度学习模型对热量消耗进行估算，误差可下降27％至43。
基于同一发明构思，本公开还提供一种热量消耗估算装置，图8是根据一示例性实施例示出的热量消耗估算装置的框图，如图8所示，该装置700可包括：
心率获取模块701，用于获取目标用户在当前时刻的心率，以及所述目标用户的生理特征信息；
第一确定模块702，用于根据所述当前时刻的心率和所述目标用户的生理特征信息，确定所述目标用户在当前时段内的第一热量消耗增量，其中，所述当前时段为从所述当前时刻的上一时刻至所述当前时刻之间的时段；
第二确定模块703，用于根据热量消耗估算模型，对所述第一热量消耗增量进行修正，以得到所述目标用户在所述当前时段内的第二热量消耗增量；
总热量确定模块704，用于根据所述第二热量消耗增量，确定所述目标用户在运动过程中的总热量消耗信息，其中，该运动过程包括从运动开始时刻至所述当前时刻的过程。
可选地，所述装置700还包括：
状态确定模块，用于根据所述当前时刻的心率，确定所述目标用户在所述当前时刻的运动状态特征信息，其中，所述运动状态特征信息用于表征所述目标用户在所述当前时刻是处于运动稳态阶段还是运动恢复阶段；
所述总热量确定模块704，包括：
第一确定子模块，用于根据所述运动状态特征信息和所述第二热量消耗增量，确定所述目标用户在所述当前时段内的目标热量消耗增量；
第二确定子模块，用于根据所述目标热量消耗增量，确定所述总热量消耗信息。
可选地，所述状态确定模块，包括：
时刻确定子模块，用于针对所述当前时刻对应的时间窗口中的每一时刻，若所述目标用户在该时刻的心率小于所述目标用户在该时刻的上一时刻的心率，则将该时刻作为心率下降时刻，其中，所述时间窗口包括从指定时刻至所述当前时刻之间的时段，所述指定时刻早于所述当前时刻；
状态确定子模块，用于根据所述心率下降时刻的数量，确定所述目标用户在所述当前时刻的运动状态特征信息。
可选地，所述状态确定子模块用于：若所述心率下降时刻的数量满足预设条件中的至少一者，则确定所述目标用户在所述当前时刻处于运动恢复阶段，其中，所述预设条件包括：所述心率下降时刻的数量大于预设数量阈值、所述心率下降时刻的数量与所述时间窗口中时刻数量之间的比值大于预设占比阈值。
可选地，所述第一确定子模块，包括：
第三确定子模块，用于若所述运动状态特征信息表征所述目标用户在所述当前时刻处于运动稳态阶段，则将所述第二热量消耗增量作为所述目标热量消耗增量；
第四确定子模块，用于若所述运动状态特征信息表征所述目标用户在所述当前时刻处于运动恢复阶段，则根据所述第二热量消耗增量、所述当前时刻的心率、运动过程中的最大心率、预设静息心率，确定所述目标热量消耗增量。
可选地，所述第四确定子模块，包括：
当前心率增量确定子模块，用于根据所述预设静息心率和所述当前时刻的心率，确定当前心率增量；
最大心率增量确定子模块，用于根据所述最大心率和所述预设静息心率，确定运动过程中的最大心率增量；
热量抑制因子确定子模块，用于将所述当前心率增量和所述最大心率增量之间的比值，作为热量抑制因子；
热量增量确定子模块，用于根据所述第二热量消耗增量和所述热量抑制因子，确定所述目标热量消耗增量。
可选地，所述目标用户的生理特征信息包括所述目标用户的体重和年龄；
所述第一确定模块702，包括：
获取子模块，用于获取所述目标用户当前进行的运动的类型信息，以及预先存储的所述类型信息对应的平均强度信息；
第五确定子模块，用于根据所述平均强度信息、所述目标用户的体重、预设基础体重、所述当前时刻的心率、预设静息心率、所述目标用户的年龄对应的年龄增益，确定所述第一热量消耗增量。
可选地，所述类型信息对应的平均强度信息是通过如下模块得到的：
第一信息获取模块，用于获取进行所述类型信息对应运动的第一用户的生理特征信息，以及所述第一用户处于运动稳态阶段时的第一心率和第一实际热量消耗增量，其中，所述第一用户的生理特征信息包括所述第一用户的体重和年龄；
拟合模块，用于根据所述第一实际热量消耗增量、所述第一心率、所述预设静息心率、所述第一用户的体重、所述预设基础体重、所述第一用户的年龄对应的年龄增益，拟合出所述平均强度信息。
可选地，所述第二确定模块703用于：
将所述目标用户的生理特征信息、所述当前时刻的心率和所述第一热量消耗增量输入至所述热量消耗估算模型中，得到所述热量消耗估算模型输出的所述第二热量消耗增量。
可选地，所述热量消耗估算模型是通过如下模块训练得到的：
第二信息获取模块，用于获取处于运动状态的第二用户的生理特征信息，以及所述第二用户处于运动状态时的第二心率和第二实际热量消耗增量；
先验信息确定模块，用于根据所述第二用户的生理特征信息和所述第二心率，确定所述第二用户的先验热量消耗；
训练模块，用于将所述第二用户的生理特征信息、所述第二心率、所述先验热量消耗、所述第二实际热量消耗增量输入至深度学习网络模型中，对所述深度学习网络模型进行训练，以得到所述热量消耗估算模型。
可选地，所述装置还包括：
基础代谢确定模块，用于在所述目标用户结束运动后，根据所述目标用户本次运动的热量消耗量确定所述目标用户的当前基础代谢信息，并展示所述当前基础代谢信息，其中，所述当前基础代谢信息大于所述目标用户在本次运动前的基础代谢信息。
关于上述实施例中的装置，其中各个模块执行操作的具体方式已经在有关该方法的实施例中进行了详细描述，此处将不做详细阐述说明。
本公开还提供一种计算机可读存储介质，其上存储有计算机程序指令，该程序指令被处理器执行时实现本公开提供的热量消耗估算方法的步骤。
图9是根据一示例性实施例示出的一种用于热量消耗估算的装置800的框图。例如，装置800可以是移动电话，计算机，数字广播终端，消息收发设备，游戏控制台，平板设备，医疗设备，健身设备，个人数字助理等。
参照图9，装置800可以包括以下一个或多个组件：处理组件802，存储器804，电 力组件806，多媒体组件808，音频组件810，输入/输出(I/O)的接口812，传感器组件814，以及通信组件816。
处理组件802通常控制装置800的整体操作，诸如与显示，电话呼叫，数据通信，相机操作和记录操作相关联的操作。处理组件802可以包括一个或多个处理器820来执行指令，以完成上述的热量消耗估算方法的全部或部分步骤。此外，处理组件802可以包括一个或多个模块，便于处理组件802和其他组件之间的交互。例如，处理组件802可以包括多媒体模块，以方便多媒体组件808和处理组件802之间的交互。
存储器804被配置为存储各种类型的数据以支持在装置800的操作。这些数据的示例包括用于在装置800上操作的任何应用程序或方法的指令，联系人数据，电话簿数据，消息，图片，视频等。存储器804可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，如静态随机存取存储器(SRAM)，电可擦除可编程只读存储器(EEPROM)，可擦除可编程只读存储器(EPROM)，可编程只读存储器(PROM)，只读存储器(ROM)，磁存储器，快闪存储器，磁盘或光盘。
电力组件806为装置800的各种组件提供电力。电力组件806可以包括电源管理系统，一个或多个电源，及其他与为装置800生成、管理和分配电力相关联的组件。
多媒体组件808包括在所述装置800和用户之间的提供一个输出接口的屏幕。在一些实施例中，屏幕可以包括液晶显示器(LCD)和触摸面板(TP)。如果屏幕包括触摸面板，屏幕可以被实现为触摸屏，以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。所述触摸传感器可以不仅感测触摸或滑动动作的边界，而且还检测与所述触摸或滑动操作相关的持续时间和压力。在一些实施例中，多媒体组件808包括一个前置摄像头和/或后置摄像头。当装置800处于操作模式，如拍摄模式或视频模式时，前置摄像头和/或后置摄像头可以接收外部的多媒体数据。每个前置摄像头和后置摄像头可以是一个固定的光学透镜系统或具有焦距和光学变焦能力。
音频组件810被配置为输出和/或输入音频信号。例如，音频组件810包括一个麦克风(MIC)，当装置800处于操作模式，如呼叫模式、记录模式和语音识别模式时，麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器804或经由通信组件816发送。在一些实施例中，音频组件810还包括一个扬声器，用于输出音频信号。
I/O接口812为处理组件802和外围接口模块之间提供接口，上述外围接口模块可以是键盘，点击轮，按钮等。这些按钮可包括但不限于：主页按钮、音量按钮、启动按钮和锁定按钮。
传感器组件814包括一个或多个传感器，用于为装置800提供各个方面的状态评估。例如，传感器组件814可以检测到装置800的打开/关闭状态，组件的相对定位，例如所述组件为装置800的显示器和小键盘，传感器组件814还可以检测装置800或装置800一个组件的位置改变，用户与装置800接触的存在或不存在，装置800方位或加速/减速和装置800的温度变化。传感器组件814可以包括接近传感器，被配置用来在没有任何的物理接触时检测附近物体的存在。传感器组件814还可以包括光传感器，如CMOS或CCD图像传感器，用于在成像应用中使用。在一些实施例中，该传感器组件814还可以包括加速度传感器，陀螺仪传感器，磁传感器，压力传感器或温度传感器。
通信组件816被配置为便于装置800和其他设备之间有线或无线方式的通信。装置800可以接入基于通信标准的无线网络，如WiFi，2G或3G，或它们的组合。在一个示例性实施例中，通信组件816经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中，所述通信组件816还包括近场通信(NFC)模块， 以促进短程通信。例如，在NFC模块可基于射频识别(RFID)技术，红外数据协会(IrDA)技术，超宽带(UWB)技术，蓝牙(BT)技术和其他技术来实现。
在示例性实施例中，装置800可以被一个或多个应用专用集成电路(ASIC)、数字信号处理器(DSP)、数字信号处理设备(DSPD)、可编程逻辑器件(PLD)、现场可编程门阵列(FPGA)、控制器、微控制器、微处理器或其他电子元件实现，用于执行上述热量消耗估算方法。
在示例性实施例中，还提供了一种包括指令的非临时性计算机可读存储介质，例如包括指令的存储器804，上述指令可由装置800的处理器820执行以完成上述热量消耗估算方法。例如，所述非临时性计算机可读存储介质可以是ROM、随机存取存储器(RAM)、CD-ROM、磁带、软盘和光数据存储设备等。
在另一示例性实施例中，还提供一种计算机程序产品，该计算机程序产品包含能够由可编程的装置执行的计算机程序，该计算机程序具有当由该可编程的装置执行时用于执行上述的热量消耗估算方法的代码部分。
本领域技术人员在考虑说明书及实践本公开后，将容易想到本公开的其它实施方案。本申请旨在涵盖本公开的任何变型、用途或者适应性变化，这些变型、用途或者适应性变化遵循本公开的一般性原理并包括本公开未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的，本公开的真正范围和精神由下面的权利要求指出。
应当理解的是，本公开并不局限于上面已经描述并在附图中示出的精确结构，并且可以在不脱离其范围进行各种修改和改变。本公开的范围仅由所附的权利要求来限制。

Claims (15)

  1. 一种热量消耗估算方法，其特征在于，包括：
    获取目标用户在当前时刻的心率，以及所述目标用户的生理特征信息；
    根据所述当前时刻的心率和所述目标用户的生理特征信息，确定所述目标用户在当前时段内的第一热量消耗增量，其中，所述当前时段为从所述当前时刻的上一时刻至所述当前时刻之间的时段；
    根据热量消耗估算模型，对所述第一热量消耗增量进行修正，以得到所述目标用户在所述当前时段内的第二热量消耗增量；
    根据所述第二热量消耗增量，确定所述目标用户在运动过程中的总热量消耗信息，其中，该运动过程包括从运动开始时刻至所述当前时刻的过程。
  2. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    根据所述当前时刻的心率，确定所述目标用户在所述当前时刻的运动状态特征信息，其中，所述运动状态特征信息用于表征所述目标用户在所述当前时刻是处于运动稳态阶段还是运动恢复阶段；
    所述根据所述第二热量消耗增量，确定所述目标用户在运动过程中的总热量消耗信息，包括：
    根据所述运动状态特征信息和所述第二热量消耗增量，确定所述目标用户在所述当前时段内的目标热量消耗增量；
    根据所述目标热量消耗增量，确定所述总热量消耗信息。
  3. 根据权利要求2所述的方法，其特征在于，所述根据所述当前时刻的心率，确定所述目标用户在所述当前时刻的运动状态特征信息，包括：
    针对所述当前时刻对应的时间窗口中的每一时刻，若所述目标用户在该时刻的心率小于所述目标用户在该时刻的上一时刻的心率，则将该时刻作为心率下降时刻，其中，所述时间窗口包括从指定时刻至所述当前时刻之间的时段，所述指定时刻早于所述当前时刻；
    根据所述心率下降时刻的数量，确定所述目标用户在所述当前时刻的运动状态特征信息。
  4. 根据权利要求3所述的方法，其特征在于，所述根据所述心率下降时刻的数量，确定所述目标用户在所述当前时刻的运动状态特征信息，包括：
    若所述心率下降时刻的数量满足预设条件中的至少一者，则确定所述目标用户在所述当前时刻处于运动恢复阶段，其中，所述预设条件包括：所述心率下降时刻的数量大于预设数量阈值、所述心率下降时刻的数量与所述时间窗口中时刻数量之间的比值大于预设占比阈值。
  5. 根据权利要求2所述的方法，其特征在于，所述根据所述运动状态特征信息和所述第二热量消耗增量，确定所述目标用户在所述当前时段内的目标热量消耗增量，包括：
    若所述运动状态特征信息表征所述目标用户在所述当前时刻处于运动稳态阶段，则将所述第二热量消耗增量作为所述目标热量消耗增量；
    若所述运动状态特征信息表征所述目标用户在所述当前时刻处于运动恢复阶段，则根据所述第二热量消耗增量、所述当前时刻的心率、运动过程中的最大心率、预设静息心率，确定所述目标热量消耗增量。
  6. 根据权利要求5所述的方法，其特征在于，所述根据所述第二热量消耗增量、所述当前时刻的心率、运动过程中的最大心率、预设静息心率，确定所述目标热量消耗增量，包括：
    根据所述预设静息心率和所述当前时刻的心率，确定当前心率增量；
    根据所述最大心率和所述预设静息心率，确定运动过程中的最大心率增量；
    将所述当前心率增量和所述最大心率增量之间的比值，作为热量抑制因子；
    根据所述第二热量消耗增量和所述热量抑制因子，确定所述目标热量消耗增量。
  7. 根据权利要求1所述的方法，其特征在于，所述目标用户的生理特征信息包括所述目标用户的体重和年龄；
    所述根据所述当前时刻的心率和所述目标用户的生理特征信息，确定所述目标用户在当前时段内的第一热量消耗增量，包括：
    获取所述目标用户当前进行的运动的类型信息，以及预先存储的所述类型信息对应的平均强度信息；
    根据所述平均强度信息、所述目标用户的体重、预设基础体重、所述当前时刻的心率、预设静息心率、所述目标用户的年龄对应的年龄增益，确定所述第一热量消耗增量。
  8. 根据权利要求7所述的方法，其特征在于，所述类型信息对应的平均强度信息是通过如下方式得到的：
    获取进行所述类型信息对应运动的第一用户的生理特征信息，以及所述第一用户处于运动稳态阶段时的第一心率和第一实际热量消耗增量，其中，所述第一用户的生理特征信息包括所述第一用户的体重和年龄；
    根据所述第一实际热量消耗增量、所述第一心率、所述预设静息心率、所述第一用户的体重、所述预设基础体重、所述第一用户的年龄对应的年龄增益，拟合出所述平均强度信息。
  9. 根据权利要求1所述的方法，其特征在于，所述根据热量消耗估算模型，对所述第一热量消耗增量进行修正，以得到所述目标用户在所述当前时段内的第二热量消耗增量，包括：
    将所述目标用户的生理特征信息、所述当前时刻的心率和所述第一热量消耗增量输入至所述热量消耗估算模型中，得到所述热量消耗估算模型输出的所述第二热量消耗增量。
  10. 根据权利要求1所述的方法，其特征在于，所述热量消耗估算模型是通过如下方式训练得到的：
    获取处于运动状态的第二用户的生理特征信息，以及所述第二用户处于运动状态时的第二心率和第二实际热量消耗增量；
    根据所述第二用户的生理特征信息和所述第二心率，确定所述第二用户的先验热量消耗；
    将所述第二用户的生理特征信息、所述第二心率、所述先验热量消耗、所述第二实际热量消耗增量输入至深度学习网络模型中，对所述深度学习网络模型进行训练，以得到所述热量消耗估算模型。
  11. 根据权利要求1-10中任一项所述的方法，其特征在于，所述热量消耗估算模型为门控循环单元模型。
  12. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    在所述目标用户结束运动后，根据所述目标用户本次运动的热量消耗量确定所述目标用户的当前基础代谢信息，并展示所述当前基础代谢信息，其中，所述当前基础代谢信息大于所述目标用户在本次运动前的基础代谢信息。
  13. 一种热量消耗估算装置，其特征在于，包括：
    心率获取模块，用于获取目标用户在当前时刻的心率，以及所述目标用户的生理特征信息；
    第一确定模块，用于根据所述当前时刻的心率和所述目标用户的生理特征信息，确 定所述目标用户在当前时段内的第一热量消耗增量，其中，所述当前时段为从所述当前时刻的上一时刻至所述当前时刻之间的时段；
    第二确定模块，用于根据热量消耗估算模型，对所述第一热量消耗增量进行修正，以得到所述目标用户在所述当前时段内的第二热量消耗增量；
    总热量确定模块，用于根据所述第二热量消耗增量，确定所述目标用户在运动过程中的总热量消耗信息，其中，该运动过程包括从运动开始时刻至所述当前时刻的过程。
  14. 一种热量消耗估算装置，其特征在于，包括：
    处理器；
    用于存储处理器可执行指令的存储器；
    其中，所述处理器被配置为：执行权利要求1～12中任一项所述方法的步骤。
  15. 一种计算机可读存储介质，其上存储有计算机程序指令，其特征在于，该程序指令被处理器执行时实现权利要求1～12中任一项所述方法的步骤。
PCT/CN2022/092877 2022-05-13 2022-05-13 热量消耗估算方法、装置及存储介质 WO2023216270A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2022/092877 WO2023216270A1 (zh) 2022-05-13 2022-05-13 热量消耗估算方法、装置及存储介质
CN202280004302.9A CN117412704A (zh) 2022-05-13 2022-05-13 热量消耗估算方法、装置及存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/092877 WO2023216270A1 (zh) 2022-05-13 2022-05-13 热量消耗估算方法、装置及存储介质

Publications (1)

Publication Number Publication Date
WO2023216270A1 true WO2023216270A1 (zh) 2023-11-16

Family

ID=88729500

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/092877 WO2023216270A1 (zh) 2022-05-13 2022-05-13 热量消耗估算方法、装置及存储介质

Country Status (2)

Country Link
CN (1) CN117412704A (zh)
WO (1) WO2023216270A1 (zh)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101518444A (zh) * 2008-02-28 2009-09-02 株式会社岛野 消耗热量测定装置,消耗热量测定方法以及消耗热量测定用预先处理方法
US20160166195A1 (en) * 2014-12-15 2016-06-16 Katarzyna Radecka Energy and Food Consumption Tracking for Weight and Blood Glucose Control
CN107405110A (zh) * 2015-12-22 2017-11-28 皇家飞利浦有限公司 用于估计人的能量消耗的设备、系统和方法

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101518444A (zh) * 2008-02-28 2009-09-02 株式会社岛野 消耗热量测定装置,消耗热量测定方法以及消耗热量测定用预先处理方法
US20160166195A1 (en) * 2014-12-15 2016-06-16 Katarzyna Radecka Energy and Food Consumption Tracking for Weight and Blood Glucose Control
CN107405110A (zh) * 2015-12-22 2017-11-28 皇家飞利浦有限公司 用于估计人的能量消耗的设备、系统和方法

Also Published As

Publication number Publication date
CN117412704A (zh) 2024-01-16

Similar Documents

Publication Publication Date Title
US11032512B2 (en) Server and operating method thereof
US9848823B2 (en) Context-aware heart rate estimation
US10694994B2 (en) Techniques for jointly calibrating load and aerobic capacity
WO2017181555A1 (zh) 目标按摩设备的控制方法及装置
WO2020007183A1 (zh) 视频数据处理方法、装置和存储介质
CN109194879A (zh) 拍照方法、装置、存储介质及移动终端
CN107997767A (zh) 用于识别用户活动的方法及其电子设备
CN109800325A (zh) 视频推荐方法、装置和计算机可读存储介质
US20220067383A1 (en) Method and apparatus for video clip extraction, and storage medium
CN108633249B (zh) 一种生理信号质量判断方法及装置
WO2022048573A1 (zh) 挥杆动作检测方法及可穿戴设备
CN105138567B (zh) 信息处理方法及装置
WO2021042364A1 (zh) 拍摄图像的方法和装置
CN113643787A (zh) 健身课程推送方法和装置
WO2022161037A1 (zh) 一种用户确定方法、电子设备和计算机可读存储介质
CN111178298A (zh) 人体关键点检测方法、装置、电子设备及存储介质
WO2023040449A1 (zh) 利用健身动作触发客户端操作指令
CN110706784A (zh) 卡路里摄入量计算方法、装置、系统、设备以及存储介质
WO2023216270A1 (zh) 热量消耗估算方法、装置及存储介质
WO2021036954A1 (zh) 一种智能语音播放方法及设备
CN111382599A (zh) 一种图像处理方法、装置和电子设备
CN113244565A (zh) 跳绳手柄、跳绳、跳绳的计数确定方法
CN114969490A (zh) 一种训练课程推荐方法及设备
CN110533006B (zh) 一种目标跟踪方法、装置及介质
WO2023216266A1 (zh) 热量消耗估算方法、装置及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22941220

Country of ref document: EP

Kind code of ref document: A1