Control method of fitness training system, computer readable medium and electronic equipment
By obtaining and analyzing users' physiological, emotional and training information in real time, and using machine learning models to generate and adjust fitness training plans, the problem that existing systems cannot be personalized for training is solved, and the training effect and safety are improved.
Patent Information
- Application Number
- CN202411150666.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-21
- Publication Date
- 2024-11-12
AI Technical Summary
The existing smart wearable fitness training system cannot generate appropriate training plans based on the user's personalized situation, resulting in poor training results and increased risk of sports injury.
By obtaining the user's real-time physiological information, emotional information and training information, extracting physiological characteristics, emotional characteristics and training characteristics, inputting preset machine learning models, generating a preliminary training plan, and adjusting based on real-time data to optimize the training intensity and type, Match the current status of the user.
It realizes intelligent generation of a training plan that matches the overall status of the user, reduces the risk of sports injury, and improves training enthusiasm and effectiveness.
Smart Images

Figure CN118942628A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of fitness data processing, and in particular, relates to a control method of a fitness training system, a computer-readable medium and an electronic device. Background Art
[0002] At present, smart wearable devices have become essential equipment for most sports enthusiasts to conduct fitness training. Existing fitness training systems of smart wearable devices can collect the user's heart rate to provide basic sports tracking and feedback functions, such as steps, calorie consumption, and heart rate curves. However, the fitness training system in the related art lacks the ability to intelligently generate personalized training plans. The system cannot formulate appropriate plans according to the user's own situation, resulting in poor training results for users and the risk of sports injuries.
[0003] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present application, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention
[0004] The object of the present invention is to provide a control method of a fitness training system, a computer-readable medium and an electronic device, so as to solve the problem in the related art that a personalized fitness training plan cannot be generated for a user.
[0005] According to one aspect of an embodiment of the present application, a method for controlling a fitness training system is provided, the method comprising:
[0006] Acquire the user's real-time physiological information, real-time emotional information and real-time training information. The real-time physiological information is used to reflect the user's real-time physical state, the emotional information is used to reflect the user's real-time emotional state, and the real-time training information is used to reflect the user's real-time training performance;
[0007] Extracting the user's physiological characteristics from the real-time physiological information, extracting the user's emotional characteristics from the real-time emotional information, and identifying the user's training characteristics from the real-time training information;
[0008] Input physiological characteristics, emotional characteristics and training characteristics into a preset machine learning model to obtain a preliminary training plan for the user;
[0009] Based on real-time physiological information, real-time emotional information and real-time training information, corresponding adjustment strategies are adopted to adjust the initial training plan.
[0010] In an embodiment provided in the present application, a preliminary training plan includes an initial training type and an initial training intensity. Physiological characteristics, emotional characteristics, and training characteristics are input into a preset machine learning model to obtain a preliminary training plan for the user, including: inputting physiological characteristics and emotional characteristics into a first machine learning model to determine the user's initial training type; inputting physiological characteristics, emotional characteristics, and training characteristics into a second machine learning model to determine the user's initial training intensity.
[0011] In an embodiment provided in the present application, a corresponding adjustment strategy is used to adjust the initial training plan based on real-time physiological information, real-time emotional information and real-time training information, including: when the real-time physiological information exceeds the preset physiological indicator range, the user is guided to perform the first designated training according to the first adjustment plan; when the real-time emotional information reflects that the user is in the first state, the user is guided to perform the second designated training according to the second adjustment plan; based on the real-time training information of the historical period, the user's historical training information is obtained; according to the historical training information, the initial training plan is adjusted using the corresponding adjustment strategy.
[0012] In an embodiment provided in the present application, a corresponding adjustment strategy is adopted to adjust the preliminary training plan according to historical training information, including: extracting the user's training performance data from the historical training information; when the training performance data exceeds the expected performance data, adjusting the preliminary training plan by an exponential progressive strategy; when the training performance data meets the expected performance data, adjusting the preliminary training plan by a linear progressive strategy; when the training performance data is close to the limit performance data, adjusting the preliminary training plan by a logarithmic progressive strategy.
[0013] In an embodiment provided by the present application, the method provided by the present application also includes: obtaining the user's long-term training goals and historical physiological information; based on the historical training information and historical physiological information, converting the long-term training goals into quantitative indicators; the quantitative indicators refer to the training indicators of the user in a specified time period; inputting the long-term training goals and historical training information into the optimization model to obtain the user's target training intensity; based on the quantitative indicators and the target training intensity, adjusting the preliminary training plan.
[0014] In an embodiment provided in the present application, the method provided in the present application also includes: obtaining the user's target training type; obtaining the energy consumption rate per unit time corresponding to the target training type; calculating the basic calorie consumption according to the energy consumption rate per unit time corresponding to the target training type and the estimated training duration; based on the user's target training intensity and physical fitness, adjusting the basic calorie consumption to obtain the estimated calorie consumption.
[0015] In an embodiment provided in the present application, the method provided in the present application also includes: evaluating the priority of training actions in the preliminary training plan based on real-time physiological information, real-time emotional information and real-time training information; and adjusting the execution order of the training actions according to the priority evaluation results of the training actions.
[0016] In an embodiment provided in the present application, a first weight corresponding to the physiological characteristic and a second weight corresponding to the emotional characteristic are obtained; and a comprehensive score of the user's emotional characteristic vector is determined based on the physiological characteristic, the first weight, the emotional characteristic, and the second weight.
[0017] According to one aspect of an embodiment of the present application, a computer medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the control method of the fitness training system provided by any embodiment of the present application is implemented.
[0018] According to one aspect of an embodiment of the present application, an electronic device is provided, including: a processor; a memory for storing executable instructions of the processor; the processor executes the executable instructions to enable the electronic device to implement the control method of the fitness training system provided by any embodiment of the present application.
[0019] In the technical solution of the present application, by acquiring the user's real-time physiological information, real-time emotional information and real-time training information, the real-time physiological information is used to reflect the user's real-time physical state, the emotional information is used to reflect the user's real-time emotional state, and the real-time training information is used to reflect the user's real-time training performance; by extracting the user's physiological characteristics from the real-time physiological information, extracting the user's emotional characteristics from the real-time emotional information, and identifying the user's training characteristics from the real-time training information, the user's training state can be converted into training data to facilitate subsequent data integration; the physiological characteristics, emotional characteristics and training characteristics are input into a preset machine learning model to obtain the user's preliminary training plan; based on the real-time physiological information, real-time emotional information and real-time training information, the preliminary training plan is adjusted using corresponding adjustment strategies, thereby comprehensively considering the impact of the user's physiological state and emotional state on training performance, and intelligently generating a preliminary training plan that matches the user's overall state, and the training plan can also be adjusted in real time during the training process to enhance the user's training enthusiasm and training effect.
[0020] It should be understood that the above general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0022] Figure 1 The flowchart of the control method of the fitness training system provided in one embodiment of the present application is schematically shown.
[0023] Figure 2 The schematic diagram of the exponential progressive strategy provided by an embodiment of the present application is schematically shown.
[0024] Figure 3 The schematic diagram of the linear progressive strategy provided by an embodiment of the present application is schematically shown.
[0025] Figure 4 The following is a schematic diagram of a logarithmic progressive strategy provided by an embodiment of the present application.
[0026] Figure 5 The structural block diagram of an electronic device provided by an embodiment of the present application is schematically shown.
[0027] Figure 6 The structure block diagram of a computer system for implementing an electronic device according to an embodiment of the present application is schematically shown. DETAILED DESCRIPTION
[0028] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be more comprehensive and complete and fully convey the concept of example embodiments to those skilled in the art.
[0029] In addition, the features, structures or characteristics described in the present application may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known methods, devices, realizations or operations are not shown or described in detail to avoid blurring the various aspects of the present application.
[0030] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.
[0031] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.
[0032] Traditional fitness training systems often set up fixed training plans, such as matching entry-level, advanced or senior-level training plans according to training duration, training frequency, training intensity and basic physical data of users. However, each person's physical functions are different. For example, some users suffer from injuries, and suitable training plans cannot be divided into simple entry-level, advanced or senior levels, but require targeted training plans. However, the fixed training plans of current fitness training systems cannot be adaptively modified, and steps need to be skipped manually during each training, which is not conducive to users focusing on the training process. In related technologies, fitness training systems lack a real-time feedback adjustment mechanism, and the training content does not match the user's current state, and the user's expected training goals cannot be achieved, or the user cannot complete the training content, lacks a sense of training accomplishment, and it is difficult to maintain long-term training enthusiasm and regularity. In order to solve the above problems, the present application provides a control method, a computer-readable medium and an electronic device for a fitness training system, such as Figure 1 As shown, the control method of the fitness training system includes S110 to S140, and the specific process is as follows.
[0033] S110. Acquire the user's real-time physiological information, real-time emotional information, and real-time training information. The real-time physiological information is used to reflect the user's real-time physical state, the emotional information is used to reflect the user's real-time emotional state, and the real-time training information is used to reflect the user's real-time training performance.
[0034] Specifically, real-time physiological information may include real-time heart rate, heart rate variability (HRV), and core temperature. Real-time heart rate is the total number of times the user's heart beats within a specified time interval. Heart rate variability is the square of the difference between all heartbeat intervals and the average heartbeat interval, summed up and divided by N-1, and finally taking the square root. The specific calculation formula is heart rate variability Where N represents the total number of heartbeat intervals, RR i represents the i-th heartbeat interval, RR- It represents the average value of all heartbeat intervals. The core area temperature refers to the temperature of the core area such as the heart or chest and abdomen. Emotional information can be obtained by analyzing the user's expression through the camera. For example, emotional information can be the accuracy of facial expression recognition. The accuracy of facial expression recognition is the proportion of correctly recognized emotional expressions in the recognition results of all emotional expressions within a specified time interval. The specific calculation formula for facial expression recognition accuracy is: TP (True Positives) refers to the number of emotional expressions correctly identified as positive, TN (True Negatives) refers to the number of emotional expressions correctly identified as negative, FP (False Positives) refers to the number of emotional expressions incorrectly identified as positive, and FN (False Negatives) refers to the number of emotional expressions incorrectly identified as negative. Real-time training information is data collected during real-time exercise, such as the user's posture, movement frequency, movement amplitude, and training duration, which can reflect the user's real-time training performance.
[0035] S120: extracting the user's physiological characteristics from the real-time physiological information, extracting the user's emotional characteristics from the real-time emotional information, and identifying the user's training characteristics from the real-time training information.
[0036] Specifically, physiological characteristics include average heart rate (Average Heart Rate, AvgHR), peak-to-valley ratio of heart rate, time series characteristics and frequency domain characteristics of HRV. Among them, the time series characteristics of HRV include the standard deviation of all normal sinus beat intervals (NN), such as SDNN, the root mean square value RMSSD of the difference between all adjacent NN intervals, and the standard deviation SDSD of the difference between all adjacent NN intervals. The frequency domain characteristics of HRV include power spectral density (PSD) and the ratio of low frequency power (LF) to high frequency power (HF), among which the frequency band of low frequency power is 0.04-0.15Hz, and the frequency band of high frequency power is 0.15-0.4Hz. Emotional characteristics can be the changes in the user's facial action units within a specified time captured by facial expression recognition technology, or they can be the features of the user's voice signal extracted by voice analysis technology, such as pitch, volume, and speech speed, which can reflect the user's emotional state. The training features may be the motion data corresponding to the user's real-time exercise type. For example, when the user is doing cycling training, the real-time training information may include cadence, real-time speed, pedaling efficiency, and real-time power. Or when the user is doing running training, the real-time training information may include cadence, stride, running speed, acceleration, and running posture.
[0037] S130: Input the physiological characteristics, emotional characteristics and training characteristics into a preset machine learning model to obtain a preliminary training plan for the user.
[0038] Specifically, the preset machine learning model can be a random forest model or a gradient boosting machine. The preliminary training plan includes the training type, training duration, training intensity, and training frequency recommended for the user. For example, if the user's physiological characteristics indicate that the user's maximum oxygen uptake is low, the user's training type is a more soothing training such as jogging; or if the user's emotional characteristics indicate that the user is currently more excited, and the training characteristics indicate that the user has completed the training action specification, then the training duration and (or) training intensity in the preliminary training plan are increased. The preset machine learning model can convert physiological characteristics, emotional characteristics, and training characteristics into quantitative parameters. For example, the physiological characteristics are input into the preset machine learning model to obtain the corresponding physiological quantitative values. Correspondingly, the emotional characteristics and training characteristics are input into the preset machine learning model to obtain emotional quantitative values and training quantitative values. The physiological quantitative values, emotional quantitative values, and training quantitative values are combined to match the appropriate training type from various training types, and set the training duration, training intensity, and training frequency.
[0039] In an embodiment provided in the present application, a preliminary training plan includes an initial training type and an initial training intensity. Physiological characteristics, emotional characteristics, and training characteristics are input into a preset machine learning model to obtain a preliminary training plan for the user, including: inputting physiological characteristics and emotional characteristics into a first machine learning model to determine the user's initial training type; inputting physiological characteristics, emotional characteristics, and training characteristics into a second machine learning model to determine the user's initial training intensity.
[0040] Specifically, the initial training type is a training type suitable for the user in the current state, and the initial training intensity is a training intensity suitable for the user in the current state. For example, the user's physiological feature is the user's real-time heart rate, and the emotional feature is the user's facial expression recognition accuracy. The real-time heart rate and the facial expression recognition accuracy are input into the first machine learning model, and the output initial training type is jogging. Assume that in the first machine learning model, different real-time heart rates have different training types, and different facial expression recognition accuracy rates also have different training types. The initial training type output by the first machine learning model is a cross-training type of real-time heart rate and facial expression recognition accuracy. Similarly, in the second machine learning model, the physiological characteristics, emotional characteristics, and training characteristics all have corresponding training intensities, and the initial training intensity output by the second machine learning model is the cross-training intensity of the physiological characteristics, emotional characteristics, and training characteristics.
[0041] In another embodiment, the initial training intensity calculation formula may be set, such as initial training intensity Intensity = (β0 + β1 × Avg_HR + β2 × HRV) / HRV max , where β0, β1 and β2 are regression coefficients determined by historical training data, Avg_HR is the average heart rate, HRV is the real-time heart rate, and HRVmax The following is an explanation with specific values, assuming that β0 is 50, β1 is 0.7, β2 is 0.05, Avg_HR is 150, HRV is 60, and HRV max is 200, then the initial training intensity
[0042] S140: Based on the real-time physiological information, the real-time emotional information and the real-time training information, the preliminary training plan is adjusted using a corresponding adjustment strategy.
[0043] Specifically, the adjustment strategy can be a set of methods for adjusting the speed of change of training intensity, or a set of methods for adjusting the type of training. For example, if the user's real-time training information indicates that the user's training performance is poor, the speed of increasing the training intensity is slowed down; or if the user's real-time emotional information indicates that the user is currently in a low mood, the explosive training in the preliminary training plan is adjusted to soothing aerobic training. These method sets for adjusting the preliminary training plan according to the user's real-time state are adjustment strategies. It should be understood that the user's physical state and emotional state during the training process are changing in real time, and the corresponding training performance is also easily affected by the physical state and emotional state. Therefore, after the user trains according to the preliminary training plan, the corresponding adjustment strategy is used to adjust the preliminary training plan according to the real-time physiological information, real-time emotional information and real-time training information, so that the training plan is in line with the user's current state, reducing the risk of sports injuries to the user, matching the appropriate training plan to teach the user to train, and improving the user's training effect and training enthusiasm.
[0044] In the technical solution of the present application, by acquiring the user's real-time physiological information, real-time emotional information and real-time training information, the real-time physiological information is used to reflect the user's real-time physical state, the emotional information is used to reflect the user's real-time emotional state, and the real-time training information is used to reflect the user's real-time training performance; by extracting the user's physiological characteristics from the real-time physiological information, extracting the user's emotional characteristics from the real-time emotional information, and identifying the user's training characteristics from the real-time training information, the user's training state can be converted into training data to facilitate subsequent data integration; the physiological characteristics, emotional characteristics and training characteristics are input into a preset machine learning model to obtain the user's preliminary training plan; based on the real-time physiological information, real-time emotional information and real-time training information, the preliminary training plan is adjusted using corresponding adjustment strategies, thereby comprehensively considering the impact of the user's physiological state and emotional state on training performance, and intelligently generating a preliminary training plan that matches the user's overall state, and the training plan can also be adjusted in real time during the training process to enhance the user's training enthusiasm and training effect.
[0045] In an embodiment provided in the present application, a corresponding adjustment strategy is used to adjust the initial training plan based on real-time physiological information, real-time emotional information and real-time training information, including: when the real-time physiological information exceeds the preset physiological indicator range, the user is guided to perform the first designated training according to the first adjustment plan; when the real-time emotional information reflects that the user is in the first state, the user is guided to perform the second designated training according to the second adjustment plan; based on the real-time training information of the historical period, the user's historical training information is obtained; according to the historical training information, the initial training plan is adjusted using the corresponding adjustment strategy.
[0046] Specifically, the real-time physiological information exceeds the preset physiological indicator range, which may mean that the real-time physiological information is greater than the preset physiological indicator, or it may mean that the real-time physiological information is less than the preset physiological indicator. For example, the preset physiological indicator range includes the heart rate indicator range, and the heart rate indicator range is 100-150bpm. Then the real-time heart rate exceeds the heart rate indicator range, including the real-time heart rate less than 100bpm, and also including the real-time heart rate greater than 150bpm. The following describes the process of guiding users to perform designated training in accordance with the first adjustment plan or the second adjustment plan through specific scenarios. For example, the initial training plan includes 30 minutes of jogging, 50 meters of exercise, 50 meters, 200 meters and 800 meters of interval running, with a 3-minute rest between each training item. For example, during jogging training, the user's preset heart rate index range is 90-145bpm, while the user's real-time heart rate is 160bpm, indicating that the user's real-time heart rate is too fast. The possible reason is that the real-time step frequency exceeds the jogging frequency by 150-160 steps / minute. At this time, the first adjustment plan is to guide the user to reduce the step frequency to 150-160 steps / minute, so that the user can slowly reduce the heart rate to the preset heart rate index corresponding to the jogging training. Or when the user is training according to the preliminary training plan, the fitness training system of the present application determines that the user is in a negative or painful negative emotional state based on the real-time emotional information of the user during the interval running of 800 meters, indicating that the current training content may be difficult for the user, or the user's current emotional state is not good and is not suitable for intense training projects. At this time, the second adjustment plan is to guide the user to perform more soothing training projects such as jogging or walking, so that the user can soothe the emotion and mobilize the user's training enthusiasm. By recording the real-time training information of historical time, the historical training information can be obtained. From the user's historical training information, the user's sports performance in a specified period can be analyzed. Then, according to the historical training information, the corresponding adjustment strategy is adopted to adjust the preliminary training plan, and the preliminary training plan can be adjusted according to the user's historical sports performance. For example, if the user's historical sports performance is excellent, it means that the user has good adaptability to the training items in the preliminary training plan. In order to achieve better training results, the preliminary training plan can be adjusted according to the user's historical sports performance. For example, when the training item includes resistance training, the weight of each training set can be increased to increase the training intensity, so that the user can gradually adapt to higher intensity training.
[0047] In an embodiment provided in the present application, a corresponding adjustment strategy is adopted to adjust the preliminary training plan according to historical training information, including: extracting the user's training performance data from the historical training information; when the training performance data exceeds the expected performance data, adjusting the preliminary training plan by an exponential progressive strategy; when the training performance data meets the expected performance data, adjusting the preliminary training plan by a linear progressive strategy; when the training performance data is close to the limit performance data, adjusting the preliminary training plan by a logarithmic progressive strategy.
[0048] Specifically, the training performance data can be quantified based on the user's historical training information. For example, based on the training posture in the historical training information, analyze whether the user has achieved the standard training posture to determine the user's control and coordination ability over the muscle groups in each part; or analyze the user's endurance performance based on the training duration in the historical training information; or analyze the user's explosive power performance based on the training intensity in the historical training information. Based on the type of training performance data, obtain the corresponding expected performance data, and then compare the training performance data with the expected performance data. Figure 2 As shown in the figure, the exponential progressive strategy means that as the training date increases, the change trend of a training parameter in the initial training plan shows an exponential growth pattern, that is, the training parameter changes rapidly as the training date increases. Figure 3 As shown in the figure, the linear progressive strategy means that as the training date increases, the change trend of a training parameter in the initial training plan shows a linear growth pattern, that is, the training parameter and the training date basically show the same proportion of growth. Figure 4 As shown, the logarithmic progressive strategy means that as the training date increases, the change trend of a training parameter in the preliminary training plan presents a logarithmic growth pattern, that is, as the training date increases, the growth rate of the training parameter becomes slower and slower, and finally tends to a certain stable value, corresponding to the user approaching the training goal or the limit performance of human function. For example, the training performance data of a user includes a training time of 2 hours and a training intensity of 10kg dumbbell weight, and the corresponding expected performance data is a training time of 1.5 hours and a training intensity of 10kg dumbbell weight. By comparing the training performance data and the expected performance data of the user, it can be seen that the training time of the user exceeds the expected performance data, and the training intensity meets the expected performance data. Then the training time of the user can be adjusted using an exponential progressive strategy to quickly adjust the training time in the preliminary training plan. If the training intensity of the user has maintained the preset training cycle, and when the linear progressive strategy is used to adjust the training intensity, the user cannot reach the preset performance data, indicating that the training performance data is the current limit performance data of the user. In addition, by acquiring the extreme performance data of other users corresponding to the basic body data of the user, the extreme performance data of the user can be assisted in determining.
[0049] In an embodiment provided by the present application, the method provided by the present application also includes: obtaining the user's long-term training goals and historical physiological information; based on the historical training information and historical physiological information, converting the long-term training goals into quantitative indicators; the quantitative indicators refer to the training indicators of the user in a specified time period; inputting the long-term training goals and historical training information into the optimization model to obtain the user's target training intensity; based on the quantitative indicators and the target training intensity, adjusting the preliminary training plan.
[0050] Specifically, the long-term training goal is a training goal of a specified duration set by the user, such as losing 5 catties in half a year. Quantitative indicators include training indicators such as daily calorie consumption, daily calorie intake, training items, training duration and training intensity in a specified time period. The long-term training goal is converted into a quantitative indicator, and the long-term training goal can be allocated to daily diet and each training according to the specified duration set by the user. The corresponding quantitative indicators can be determined in combination with the human weight loss law of the database. For example, the intake of high-sugar and high-fat foods is limited throughout the weight loss cycle, and the proportion of coarse grain intake is increased in the early stage to improve the user's dietary structure and intestinal environment. Then, the user's training level can be determined based on the user's historical training information, and the long-term training goal and historical training information are input into the optimization model. If the historical training information reflects that the user's training level is low and high-intensity training cannot be completed in the early stage, the target training intensity of the user is obtained in combination with the long-term training goal. The target training intensity can include the training intensity in each training cycle during the training process of the specified duration. Finally, based on the quantitative indicators and the target training intensity, the corresponding training parameters in the preliminary training plan are adjusted so that the training plan meets the user's training goals and athletic ability.
[0051] In an embodiment provided in the present application, the method provided in the present application also includes: obtaining the user's target training type; obtaining the energy consumption rate per unit time corresponding to the target training type; calculating the basic calorie consumption according to the energy consumption rate per unit time corresponding to the target training type and the estimated training duration; based on the user's target training intensity and physical fitness, adjusting the basic calorie consumption to obtain the estimated calorie consumption.
[0052] Specifically, the target training type can be the training type set in the preliminary training plan. The target training type can be determined according to the user's athletic ability. For example, if the user wants to train aerobic capacity, the target training type of the user is set as running in the preliminary training plan. Then, when determining the estimated calorie consumption of the user, it is first necessary to obtain the energy consumption rate per unit time and the estimated training duration corresponding to the running training. For example, if the user performs running training for 30 minutes, the target training intensity is 70%, the user weighs 70 kg, and the energy consumption rate per unit time of running (or metabolic equivalent) is 9, then the basic calorie consumption is 9×30=270 kcal. The basic calorie consumption is adjusted based on the target training intensity to obtain 270×70%=189 kcal, and the final estimated calorie consumption is 189×70=13230 kcal.
[0053] In an embodiment provided in the present application, the method provided in the present application also includes: evaluating the priority of training actions in the preliminary training plan based on real-time physiological information, real-time emotional information and real-time training information; and adjusting the execution order of the training actions according to the priority evaluation results of the training actions.
[0054] Specifically, based on real-time physiological information, real-time emotional information and real-time training information, the user's real-time physical function, real-time emotional state and real-time athletic performance can be determined, thereby determining the user's sensitivity to each training action. For example, training actions A and training action B train the same muscle groups, but the training feedback when the user performs training action A is more obvious than the training feedback of training action B, indicating that training action A is more important for the training effect of the user. Therefore, the priority evaluation result of training action A is adjusted to high priority, and then based on the high priority of training action A, the execution order of training action A is adjusted to the first, so as to ensure that the user can give priority to training parts that are more sensitive to body reactions or important during training, thereby improving training efficiency and safety.
[0055] For example, the priority evaluation result is reflected by the priority score. i =Duration i +Importance i ×Ur.gency i , where Duration i represents the estimated duration of the i-th training action, Importance i Indicates the importance of the i-th training action, Urgency i Indicates the urgency of the i-th training action. i It can be determined based on the user's long-term training goals and historical training data, which includes historical physiological information, historical emotional information, and historical training information. i The user's real-time physiological information and real-time emotional state can be evaluated. For example, if the user is doing running training, if the user's real-time physiological information shows that the user's current heart rate is too high, the urgency value of the training action of resting or reducing the cadence is increased to guide the user to reduce the heart rate to a specified range.
[0056] In an embodiment provided in the present application, a first weight corresponding to the physiological characteristic and a second weight corresponding to the emotional characteristic are obtained; and a comprehensive score of the user's emotional characteristic vector is determined based on the physiological characteristic, the first weight, the emotional characteristic, and the second weight.
[0057] Specifically, physiological characteristics can also reflect the user's emotional state. For example, when the user is excited or nervous, the real-time heart rate is higher; or the user's emotional state can be analyzed through the time domain characteristics or frequency domain characteristics of the heart rate. Therefore, physiological characteristics can be integrated when calculating the comprehensive score of the user's emotional feature vector. The comprehensive score of the emotional feature vector is used to evaluate the user's real-time training status so that the user can understand his or her real-time overall status. For example, the physiological feature is HRV_SDNN, the emotional feature is Expression_Accuracy, the first weight is w1, the second weight is w2, and the emotional feature vector comprehensive score Emotion_Score = HRV_SDNN×w1+Expression Accuracy ×w2. The first weight and the second weight are obtained through an optimization algorithm, such as a genetic algorithm or a gradient descent algorithm, etc., to set the estimated target emotional feature vector comprehensive score in the training model, and then input the physiological feature samples and the emotional feature samples into the training model to optimize the first weight and the second weight. It should be understood that the first weight and the second weight are only used to distinguish the weights corresponding to the physiological features and the emotional features, and are not limited to only two weight values when calculating the comprehensive score of the emotional feature vector. In another embodiment, the emotional features include the user's voice features, and the user's emotional state can be determined by analyzing the user's voice information. For example, if the user's voice features reflect that the user's current speaking speed is faster, it tends to determine that the user is in an excited state; or if the user's voice features reflect that the user's voice is lower when speaking, it tends to determine that the user is in a calm state, etc.
[0058] The electronic equipment of this application is introduced below, such as Figure 5 As shown, the present application provides an electronic device 500, which includes: a processor 510 and a memory 520, the memory 520 is used to store executable instructions of the processor; the processor 510 executes the executable instructions to enable the electronic device to implement the control method of the fitness training system provided by any embodiment of the present application.
[0059] Specifically, the control method of the fitness training system provided in the present application is stored in the memory 520 of the electronic device 500, and the control method of the fitness training system provided in the present application is executed by the processor 510 to intelligently generate a personalized training plan for the user, so as to scientifically guide the user's fitness training process, avoid the risk of sports injuries to the user, and provide the user with comprehensive fitness training suggestions and training feedback.
[0060] It should be known that the specific implementation content of the electronic device in the present application has been explained in detail in the corresponding method embodiment and will not be repeated here.
[0061] Figure 6The structure block diagram of a computer system for implementing an electronic device according to an embodiment of the present application is schematically shown.
[0062] It should be noted that Figure 6 The computer system 600 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0063] like Figure 6 As shown, the computer system 600 includes a processor 601, which can be a CPU (Central Processing Unit) or an MCU (Microcontroller Unit). The processor 601 can perform various appropriate actions and processes according to the program stored in the read-only memory 602 (Read-Only Memory, ROM) or the program loaded from the storage part 608 to the random access memory 603 (Random Access Memory, RAM). In the random access memory 603, various programs and data required for system operation are also stored. The processor 601, the read-only memory 602 and the random access memory 603 are connected to each other through a bus 604. The input / output interface 605 (Input / Output interface, i.e., I / O interface) is also connected to the bus 604.
[0064] The following components are connected to the input / output interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a local area network card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the input / output interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed so that a computer program read therefrom is installed into the storage section 608 as needed.
[0065] In particular, according to an embodiment of the present application, the process described in each method flow chart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer readable medium, and the computer program contains a program code for executing the method shown in the flow chart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the processor 601, various functions defined in the system of the present application are executed.
[0066] It should be noted that the computer-readable medium shown in the embodiment of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by an instruction execution system, device or device or used in combination with it. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.
[0067] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0068] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.
[0069] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation method of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the implementation method according to the present application.
[0070] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary technical means in the art that are not disclosed in the present application.
[0071] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.
Claims
1. A control method for a fitness training system, characterized in that: include: Acquire the user's real-time physiological information, real-time emotional information and real-time training information, wherein the real-time physiological information is used to reflect the user's real-time physical state, the emotional information is used to reflect the user's real-time emotional state, and the real-time training information is used to reflect the user's real-time training performance; Extracting physiological characteristics of the user from the real-time physiological information, extracting emotional characteristics of the user from the real-time emotional information, and identifying training characteristics of the user from the real-time training information; Inputting the physiological characteristics, the emotional characteristics and the training characteristics into a preset machine learning model to obtain a preliminary training plan for the user; Based on the real-time physiological information, the real-time emotional information and the real-time training information, the preliminary training plan is adjusted using a corresponding adjustment strategy.
2. The control method of the fitness training system according to claim 1, characterized in that: The preliminary training plan includes an initial training type and an initial training intensity. The inputting of the physiological characteristics, the emotional characteristics and the training characteristics into a preset machine learning model to obtain a preliminary training plan for the user includes: Inputting the physiological characteristics and the emotional characteristics into a first machine learning model to determine an initial training type of the user; The physiological characteristics, the emotional characteristics and the training characteristics are input into a second machine learning model to determine the initial training intensity of the user.
3. The control method of the fitness training system according to claim 1, characterized in that: The adjusting the preliminary training plan by using a corresponding adjustment strategy based on the real-time physiological information, the real-time emotional information and the real-time training information includes: When the real-time physiological information exceeds the preset physiological index range, preferentially guiding the user to perform a first designated training according to a first adjustment plan; When the real-time emotion information reflects that the user is in the first state, preferentially guiding the user to perform the second designated training according to the second adjustment plan; Based on the real-time training information of the historical period, obtaining the historical training information of the user; According to the historical training information, the preliminary training plan is adjusted using a corresponding adjustment strategy.
4. The control method of the fitness training system according to claim 3, characterized in that: The step of adjusting the preliminary training plan according to the historical training information by using a corresponding adjustment strategy includes: extracting training performance data of the user from the historical training information; When the training performance data exceeds the expected performance data, the preliminary training plan is adjusted using an exponential progression strategy; When the training performance data meets the expected performance data, the preliminary training plan is adjusted using a linear progressive strategy; When the training performance data approaches the limit performance data, the preliminary training plan is adjusted using a logarithmic progression strategy.
5. The control method of the fitness training system according to claim 3, characterized in that: The method further comprises: Obtain the user's long-term training goals and historical physiological information; Based on the historical training information and the historical physiological information, the long-term training goal is converted into a quantitative index; the quantitative index refers to the training index of the user in a specified time period; Inputting the long-term training goal and the historical training information into an optimization model to obtain a target training intensity for the user; The preliminary training plan is adjusted based on the quantitative indicator and the target training intensity.
6. The control method of the fitness training system according to claim 1, characterized in that: The method further comprises: Get the user's target training type; Obtaining the energy consumption rate per unit time corresponding to the target training type; Calculating basal calorie consumption according to the energy consumption rate per unit time and the estimated training duration corresponding to the target training type; Based on the user's target training intensity and physical fitness, the basic calorie consumption is adjusted to obtain an estimated calorie consumption.
7. The control method of the fitness training system according to claim 1, characterized in that: The method further comprises: Based on the real-time physiological information, the real-time emotional information and the real-time training information, evaluating the priority of the training actions in the preliminary training plan; According to the priority evaluation result of the training actions, the execution order of the training actions is adjusted.
8. The control method of the fitness training system according to claim 1, characterized in that: The method further comprises: Obtaining a first weight corresponding to the physiological feature and a second weight corresponding to the emotional feature; A comprehensive score of the user's emotion feature vector is determined according to the physiological feature, the first weight, the emotion feature and the second weight.
9. A computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the control method of the fitness training system according to any one of claims 1 to 8 is implemented.
10. An electronic device, characterized in that: include: processor; A memory, configured to store executable instructions of the processor; The processor executes the executable instructions to enable the electronic device to implement the control method of the fitness training system as described in any one of claims 1 to 8.
Citation Information
Cited By
Physical training virtual simulation practical training system based on machine learning
CN119139679A
