Exercise guidance method and related device

By acquiring user movement information and dynamically calculating decay factors and remaining time, the problem of users being unable to predict race results in real time is solved, enabling real-time feedback and pace adjustment to ensure the ideal finishing time.

WO2026236897A1PCT designated stage Publication Date: 2026-11-19SUUNTO SPORTS TECHNOLOGY (DONGGUAN) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2025/094390
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Filing Date
2025-05-12
Publication Date
2026-11-19

AI Technical Summary

Technical Problem

In speed sports, users cannot predict in real time whether they can achieve their target performance, which makes it impossible to effectively adjust speed during the competition to avoid physical exhaustion or overexertion.

Method used

By acquiring user activity information, including pace, distance, and time, the system dynamically calculates decay factors, estimates remaining time and finish time, and provides real-time feedback to adjust pace.

Benefits of technology

Users can monitor in real time whether they have exceeded or fallen short of their target time, and adjust their pace to avoid exhaustion and achieve their ideal finishing time.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2025094390_19112026_PF_FP_ABST
    Figure CN2025094390_19112026_PF_FP_ABST
Patent Text Reader

Abstract

An exercise guidance method and a related device. The exercise guidance method comprises: acquiring user exercise information, wherein the user exercise information includes pace information, distance information, and time information, the distance information includes remaining distance information, and the time information includes elapsed time information; determining attenuation factors of a user on the basis of the user exercise information; estimating a remaining time of the user on the basis of the remaining distance information, the pace information, and the attenuation factors; and obtaining an estimated finish time of the user on the basis of the remaining time of the user and the elapsed time information. By dynamically calculating the remaining time and the finish time during the exercise, the user can know, in real time, whether the estimated finish time of the user is longer than or shorter than a target time. The real-time feedback can help the user better manage race pace, avoid physical exhaustion or excessive exertion by adjusting the pace, and finally achieve a desired finish time.
Need to check novelty before this filing date? Find Prior Art

Description

Exercise guidance methods and related equipment Technical Field

[0001] This application relates to the fields of computer and communication technology, and more specifically, to a method for guiding sports and related equipment. Background Technology

[0002] For speed sports with distance and pace targets (such as track and field, cycling, swimming, and skiing), users may want to know approximately how long the exercise will last. Take a marathon as an example.

[0003] Suppose a user's first half-marathon time is 2:35:00. When participating in a second half-marathon, the user might set a goal of 2:10:00. However, from the start to the end of the race, the user cannot predict whether they will be able to achieve their desired time.

[0004] By the time users realize they are too slow, it may be too late.

[0005] Because we don't know how fast a user will run the part they haven't finished, no manufacturer dares to give a user a prediction of their race performance during exercise. However, we've overlooked the fact that users can adjust their speed within their physical capabilities.

[0006] We should provide scientific guidance so that users can achieve better and more satisfactory results. Summary of the Invention

[0007] The embodiments of this application provide a method and related equipment for sports guidance, which can at least to some extent overcome the limitations of providing scientific guidance to users so that they can achieve better results.

[0008] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0009] According to one aspect of the embodiments of this application, a sports guidance method is provided, comprising: acquiring user sports information, the user sports information including pace information, distance information and time information, the distance information including remaining distance information, and the time information including elapsed time information; determining a user's decay factor based on the user sports information; estimating the user's remaining time based on the remaining distance information, the pace information and the decay factor; and obtaining the user's estimated completion time based on the user's remaining time and the elapsed time information.

[0010] In some embodiments of this application, the pace information includes current pace information; determining the user's attenuation factor based on the user's movement information specifically includes: obtaining a preliminary estimated time based on the remaining distance information and the current pace information; and determining the attenuation factor for each predetermined time period based on the preliminary estimated time.

[0011] In some embodiments of this application, estimating the user's remaining time based on the remaining distance information, the pace information, and the attenuation factor specifically includes: correcting the pace information within each predetermined time period based on the user's current pace information according to the attenuation factor for each predetermined time period, to obtain the corrected pace corresponding to each predetermined time period; and estimating the user's remaining time based on the corrected pace and the remaining distance information.

[0012] In some embodiments of this application, the distance information further includes the target distance; determining the user's attenuation factor based on the user's motion information specifically includes: obtaining the proportion of the user's uncompleted distance based on the target distance and the remaining distance information; and determining the attenuation factor based on the proportion of the user's uncompleted distance.

[0013] In some embodiments of this application, the pace information includes pace information within the current predetermined time interval; the step of estimating the user's remaining time based on the remaining distance information, the pace information, and the attenuation factor specifically includes: determining the current average pace based on the pace information within the current predetermined time interval; determining the average attenuation pace based on the current average pace and the attenuation factor; and obtaining the user's remaining time based on the remaining distance information and the average attenuation pace.

[0014] In some embodiments of this application, the time information further includes the target completion time; after obtaining the user's estimated completion time based on the user's remaining time and the time already used, the exercise guidance method further includes: obtaining a recommended pace based on the user's estimated completion time, the target completion time, the pace information, and the decay factor.

[0015] In some embodiments of this application, after obtaining the user's estimated completion time based on the user's remaining time and the time already used, the exercise guidance method further includes: in response to the end of the exercise function, determining whether the remaining distance information is greater than a predetermined distance threshold; if the remaining distance information is greater than the predetermined distance threshold, displaying the user's estimated completion time on the exercise end interface; if the remaining distance information is not greater than the predetermined distance threshold, displaying the user's actual completion time on the exercise end interface.

[0016] In some embodiments of this application, the user motion information further includes the user's physiological motion information from the start of the exercise to the present, and the pace information includes the user's pace information from the start of the exercise to the present. The step of determining the user's attenuation factor based on the user motion information specifically includes: sorting the user's physiological motion information from the start of the exercise to the present by time to form a time sequence of physiological motion information; sorting the user's pace information from the start of the exercise to the present by time to form a time sequence of user pace information; and inputting the time sequence of physiological motion information, the time sequence of user pace information, and the remaining distance information into an attenuation prediction model to obtain the attenuation factor.

[0017] In some embodiments of this application, the attenuation prediction model includes a temporal feature extraction layer, a fusion feature interaction layer, and an attenuation factor prediction layer. The step of inputting the temporal sequence of exercise physiological information, the temporal sequence of user pace information, and the remaining distance information into the attenuation prediction model to obtain the attenuation factor specifically includes: inputting the temporal sequence of exercise physiological information and the temporal sequence of user pace information into the temporal feature extraction layer to extract temporal features, obtaining fused temporal features; concatenating the fused temporal features with the remaining distance information and inputting the result into the fusion feature interaction layer for feature enhancement, obtaining enhanced fused features; and inputting the enhanced fused features into the attenuation factor prediction layer to obtain the attenuation factor.

[0018] In some embodiments of this application, the temporal feature extraction layer includes a bidirectional LSTM network, a Transformer encoder, and a self-attention network. The step of inputting the temporal sequence of the exercise physiological information and the temporal sequence of the user pace information into the temporal feature extraction layer to extract temporal features and obtain fused temporal features specifically includes: inputting the temporal sequence of the exercise physiological information into the bidirectional LSTM network to capture long-term dependencies, obtaining temporal features of the exercise physiological information; inputting the temporal sequence of the user pace information into the Transformer encoder to capture periodicity and abrupt changes in the temporal sequence, obtaining temporal features of the user pace information; and fusing the temporal features of the exercise physiological information and the temporal features of the user pace information through the self-attention network to obtain fused temporal features.

[0019] In some embodiments of this application, the exercise guidance method further includes: acquiring historical exercise data of the user to obtain a user exercise behavior sample set, wherein the user exercise behavior sample set contains multiple user exercise behavior samples, each user exercise behavior sample corresponds to a segment of exercise behavior of the user, and includes the user pace information time sequence, user pace information time sequence and remaining distance information of the user in the segment of exercise behavior, and each is marked with a corresponding decay factor label; inputting each of the user exercise behavior samples in the user exercise behavior sample set into the decay prediction model one by one to obtain the corresponding decay factor; updating the parameters of the decay prediction model according to the decay factor and the decay factor label until a predetermined termination condition is met, stopping training, and obtaining a trained decay prediction model.

[0020] According to one aspect of the embodiments of this application, a sports guidance device is provided, characterized in that the sports guidance device includes: a sports information acquisition module, used to acquire user sports information, the user sports information including pace information, distance information and time information, the distance information including remaining distance information, and the time information including elapsed time information; a decay factor determination module, used to determine the user's decay factor based on the user sports information; a remaining time estimation module, used to estimate the user's remaining time based on the remaining distance information, the pace information and the decay factor; and a completion time estimation module, used to obtain the user's estimated completion time based on the user's remaining time and the elapsed time information.

[0021] In some embodiments of this application, the pace information includes current pace information; the attenuation factor determination module specifically includes: a preliminary estimated time submodule, used to obtain a preliminary estimated time based on the remaining distance information and the current pace information; and a stage attenuation factor submodule, used to determine the attenuation factor for each predetermined time period based on the preliminary estimated time.

[0022] In some embodiments of this application, the remaining time estimation module specifically includes: a pace information correction submodule, which corrects the pace information in each predetermined time period based on the attenuation factor of each predetermined time period and the user's current pace information to obtain the corrected pace corresponding to each predetermined time period; and a remaining time estimation submodule, which estimates the user's remaining time based on the corrected pace and remaining distance information.

[0023] In some embodiments of this application, the distance information further includes the target distance; the attenuation factor determination module specifically includes: a distance ratio determination submodule, used to obtain the proportion of the user's incomplete distance based on the target distance and the remaining distance information; and an attenuation factor determination submodule, used to determine the attenuation factor based on the proportion of the user's incomplete distance.

[0024] In some embodiments of this application, the pace information includes pace information within the current predetermined time interval; the remaining time estimation module specifically includes: a current average pace submodule, used to determine the current average pace based on the pace information within the current predetermined time interval; an average decay pace submodule, used to determine the average decay pace based on the current average pace and the decay factor; and a user remaining time submodule, used to obtain the user's remaining time based on the remaining distance information and the average decay pace.

[0025] In some embodiments of this application, the time information further includes the target completion time, and the exercise guidance device further includes: a pace recommendation module, used to obtain a recommended pace based on the user's estimated completion time, the target completion time, the pace information, and the decay factor.

[0026] In some embodiments of this application, the exercise guidance device further includes: a remaining distance determination module, configured to determine whether the remaining distance information is greater than a predetermined distance threshold in response to the end of the exercise function; a first display module, configured to display the user's estimated completion time on the exercise end interface if the remaining distance information is greater than the predetermined distance threshold; and a second display module, configured to display the user's actual completion time on the exercise end interface if the remaining distance information is not greater than the predetermined distance threshold.

[0027] In some embodiments of this application, the user motion information further includes the user's physiological motion information from the start of the exercise to the present, and the pace information includes the user's pace information from the start of the exercise to the present; the attenuation factor determination module specifically includes: a physiological information time series submodule, used to sort the user's physiological motion information from the start of the exercise to the present according to time to form a physiological motion information time series; a pace information time series submodule, used to sort the user's pace information from the start of the exercise to the present according to time to form a pace information time series; and an attenuation model prediction submodule, used to input the physiological motion information time series, the pace information time series, and the remaining distance information into the attenuation prediction model to obtain the attenuation factor.

[0028] In some embodiments of this application, the attenuation prediction model includes a temporal feature extraction layer, a fusion feature interaction layer, and an attenuation factor prediction layer; the attenuation model prediction submodule specifically includes: a temporal feature fusion unit, used to input the temporal sequence of the exercise physiological information and the temporal sequence of the user pace information into the temporal feature extraction layer to extract temporal features, thereby obtaining fused temporal features; a fusion feature enhancement unit, used to concatenate the fused temporal features with the remaining distance information and input them into the fusion feature interaction layer for feature enhancement, thereby obtaining enhanced fused features; and an attenuation factor prediction unit, used to input the enhanced fused features into the attenuation factor prediction layer to obtain the attenuation factor.

[0029] In some embodiments of this application, the temporal feature extraction layer includes a bidirectional LSTM network, a Transformer encoder, and a self-attention network; the temporal feature fusion unit specifically includes: a bidirectional LSTM network subunit, used to input the temporal data of the exercise physiological information into the bidirectional LSTM network to capture long-term dependencies, thereby obtaining temporal features of the exercise physiological information; a Transformer encoder subunit, used to input the temporal data of the user pace information into the Transformer encoder to capture periodic and abrupt features in the temporal data, thereby obtaining temporal features of the user pace information; and a temporal feature fusion subunit, used to fuse the temporal features of the exercise physiological information and the temporal features of the user pace information through the self-attention network, thereby obtaining fused temporal features.

[0030] In some embodiments of this application, the exercise guidance device further includes: a sample acquisition module, used to acquire historical exercise data of the user to obtain a user exercise behavior sample set, wherein the user exercise behavior sample set contains multiple user exercise behavior samples, each user exercise behavior sample corresponds to a segment of exercise behavior of the user, and includes the user pace information time sequence, user pace information time sequence and remaining distance information of the user in the segment of exercise behavior, and each is marked with a corresponding decay factor label; a sample input module, used to input each of the user exercise behavior samples in the user exercise behavior sample set into the decay prediction model one by one to obtain the corresponding decay factor; and a parameter update module, used to update the parameters of the decay prediction model according to the decay factor and the decay factor label until a predetermined termination condition is met, stop training, and obtain a trained decay prediction model.

[0031] According to one aspect of the embodiments of this application, a computer-readable medium is provided having a computer program stored thereon, which, when executed by a processor, implements the motion guidance method as described in the above embodiments.

[0032] According to one aspect of the embodiments of this application, an electronic device is provided, including: one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement the motion guidance method as described in the above embodiments.

[0033] According to one aspect of the embodiments of this application, a computer program product is provided, including one or more computer programs that, when executed by one or more processors, implement the steps of the motion guidance method as described above.

[0034] In some embodiments of this application, the technical solutions provide that, by dynamically calculating the remaining time and finishing time during the race, users can understand in real time whether they have exceeded or fallen short of their target time. This real-time feedback helps users better control the pace of the race, adjust their pace to avoid exhaustion or overexertion, and ultimately achieve their ideal finishing time.

[0035] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0036] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0037] Figure 1 shows a schematic diagram of an exemplary system architecture to which the technical solutions of the embodiments of this application can be applied.

[0038] Figure 2 shows a flowchart of a sports guidance method provided in an embodiment of this application.

[0039] Figure 3 shows a flowchart of a specific implementation of step S200 in the motion guidance method according to the embodiment corresponding to Figure 2.

[0040] Figure 4 shows a flowchart of a specific implementation of step S230 in the motion guidance method according to the embodiment corresponding to Figure 3.

[0041] Figure 5 shows a schematic diagram of the motion interface during the motion process provided in an embodiment of this application.

[0042] Figure 6 shows a flowchart of another exercise guidance method provided in an embodiment of this application.

[0043] Figure 7 shows a schematic diagram of the first motion interface after the motion ends, provided in an embodiment of this application.

[0044] Figure 8 shows a schematic diagram of the second motion interface after the motion ends, provided in an embodiment of this application.

[0045] Figure 9 shows a schematic diagram of the structure of a motion guidance device provided in an embodiment of this application.

[0046] Figure 10 shows a schematic diagram of the structure of the electronic device provided in an embodiment of this application. Detailed Implementation

[0047] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary 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 to make this application more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art.

[0048] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0049] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.), and signals involved in the embodiments of this specification are all authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. For example, the object characteristics, interactive behavior characteristics, and user information involved in this specification were all obtained with full authorization.

[0050] 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 can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0051] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0052] Figure 1 shows a schematic diagram of an exemplary system architecture to which the technical solutions of the embodiments of this application can be applied.

[0053] As shown in Figure 1, the system architecture may include terminal devices (one or more of the following shown in Figure 1: smartphone 101, tablet computer 102, and portable computer 103; desktop computers, etc.), a network 104, and a server 105. The network 104 serves as the medium for providing a communication link between the terminal devices and the server 105. The network 104 may include various connection types, such as wired communication links, wireless communication links, etc.

[0054] It should be understood that the number of terminal devices, networks, and servers in Figure 1 is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be used. For example, server 105 could be a server cluster composed of multiple servers.

[0055] Users can interact with server 105 via network 104 using terminal devices to receive or send messages, etc. Server 105 can be a server providing various services. For example, a user can upload user exercise information to server 105 using terminal device 103 (or terminal device 101 or 102). The user exercise information includes pace information, distance information, and time information. The distance information includes remaining distance information, and the time information includes elapsed time information. Server 105 can determine the user's decay factor based on the user's exercise information; estimate the user's remaining time based on the remaining distance information, pace information, and decay factor; and obtain the user's estimated completion time based on the user's remaining time and elapsed time information.

[0056] It should be noted that the exercise guidance method provided in this application embodiment is generally executed by server 105, and correspondingly, the exercise guidance device is generally disposed in server 105. However, in other embodiments of this application, the terminal device may also have similar functions to the server, thereby executing the exercise guidance scheme provided in this application embodiment.

[0057] The implementation details of the technical solutions in the embodiments of this application are described in detail below:

[0058] Figure 2 shows a flowchart of a motion guidance method according to an embodiment of this application. This motion guidance method can be executed by a server, which may be the server shown in Figure 1. Referring to Figure 2, the motion guidance method includes at least:

[0059] S100, acquire user motion information, the user motion information includes pace information, distance information and time information, the distance information includes remaining distance information, and the time information includes time elapsed information.

[0060] S200, determine the user's attenuation factor based on the user's motion information.

[0061] S300: Based on the remaining distance information, the pace information, and the attenuation factor, estimate the user's remaining time.

[0062] S400: Based on the user's remaining time and the time already used, obtain the user's estimated completion time.

[0063] In the embodiments of this application, by dynamically calculating the remaining time and completion time during the exercise, users can know in real time whether they have exceeded or fallen short of the target time. This real-time feedback helps users better control the pace of the race, adjust their pace to avoid exhaustion or overexertion, and ultimately achieve their ideal completion time.

[0064] Since each user's physical exertion level varies, a dynamic variable called a "decrease factor" is used to personalize the prediction model, making the estimated time more closely match the actual situation. This means that even on the same track and over the same distance, different users can receive unique feedback based on their own physical condition and pace.

[0065] The S100 uses devices such as smart bracelets, running watches, or smartphones to acquire users' exercise data in real time. This data includes pace (current running speed), distance (distance already run and distance remaining), and time information (time elapsed). This information is typically acquired via GPS or motion sensors and transmitted to the analysis system.

[0066] In the S200, the decay factor can be determined based on the user's remaining running distance (usually provided by GPS) combined with historical exercise data and physiological models. The decay factor reflects the gradual decline in the user's physical strength as exercise time increases, and usually requires a large amount of exercise data and statistical analysis to determine the user's specific decay rate.

[0067] Specifically, in the first embodiment of this application, the specific implementation of step S200 can be found in the following embodiment. This embodiment is a detailed description of step S200 in the exercise guidance method shown in the corresponding embodiment of FIG2. In the exercise guidance method, the pace information includes current pace information, and step S200 may include the following steps:

[0068] Based on the remaining distance information and the current pace information, a preliminary estimated time is obtained.

[0069] Based on the preliminary estimated time, the attenuation factor for each predetermined time period is determined.

[0070] In this embodiment, by comprehensively considering the effects of remaining distance, current pace, and decay factor, this method can achieve a more accurate prediction of the athlete's completion time. This prediction not only considers the current state of the exercise but also dynamically predicts physical fatigue, making the prediction result closer to reality. The decay factor is dynamically adjusted with changes in time and exercise state, ensuring that it can reflect the athlete's actual physical changes in real time, helping the athlete to adjust pace in a timely manner and optimize exercise results. Through personalized settings of the decay factor, customized guidance can be provided for different users' exercise characteristics, thereby improving exercise efficiency and the likelihood of achieving the goal.

[0071] Specifically, in some embodiments, the preliminary estimated time is obtained by dividing the remaining distance information by the current pace. In other embodiments, the time obtained by dividing the remaining distance information by the current pace is multiplied by an adjustment factor to extend the preliminary estimated time to be close to the actual time. This adjustment factor can be understood as the reciprocal of the average attenuation factor of the remaining distance. Therefore, it can also be that the current pace is processed by averaging the attenuation factor before obtaining the preliminary estimated time.

[0072] Therefore, the adjustment coefficient or average attenuation factor is related to the remaining distance information. In some embodiments, the adjustment coefficient or average attenuation factor and the remaining distance information can be obtained from the user's historical motion data. It can be a formula, table or model, which is not limited here.

[0073] When the initial estimated time has not been adjusted by an adjustment factor or average attenuation factor, the initial estimated time can be divided into multiple predetermined time periods based on predetermined time windows. Each predetermined time period corresponds to the same distance. After fixing each predetermined time period as a time period of equal distance length (or a distance segment of equal distance length), the attenuation factors within each predetermined time period are multiplied in chronological order to obtain the attenuation factor for each predetermined time period. In other words, the pace of each predetermined time period is reduced by the corresponding attenuation factor based on the pace of the previous time period.

[0074] For example, in one embodiment, the initial estimated time is 5 minutes, the predetermined time window is 1 minute, and the pace decreases by 0.1% per minute. Therefore, the attenuation factor is 1 - 0.1% = 99.9%. The initial time can be divided into 5 time periods based on 1 minute, and the distance corresponding to each of these 5 time periods is 'a'. These 5 time periods can then be fixed as 5 predetermined time periods with a distance length of 'a'. By multiplying the attenuation factors within each predetermined time period, the attenuation factors for each predetermined time period, ordered by time, can be obtained as 99.9%, (99.9%)2, (99.9%)3, (99.9%)4, and (99.9%)5.

[0075] After the attenuation factor is adjusted, the distances corresponding to each predetermined time period are still the same, but the times are no longer the same, but the sum of their total distances is still equal to the remaining distance.

[0076] When the initial estimated time has been adjusted by an adjustment factor or average attenuation factor, the initial estimated time can be divided into multiple time periods, each a predetermined time window. These predetermined time periods are then fixed to an equal length. The attenuation factors within each time period are multiplied sequentially to obtain the attenuation factor for each predetermined time period.

[0077] When adjusting the attenuation factor, the time of each predetermined time period remains unchanged, but the distance will be shortened due to the adjustment of the attenuation factor. Therefore, when estimating the user's remaining time, it is necessary to make the sum of the total distance of each predetermined time period equal to the remaining distance. Thus, the last predetermined time period can be a segmented time period.

[0078] Similarly, when the initial estimated time has not been adjusted by the adjustment coefficient or the average decay factor, a predetermined number of time periods can be added to cover the remaining completion time, based on the multiple time periods obtained in the form of predetermined time windows, so as to fix each predetermined time period to a time period of equal length.

[0079] Specifically, in the second embodiment of this application, the specific implementation of step S200 can be found in the following embodiment. This embodiment is a detailed description of step S200 in the exercise guidance method shown in the corresponding embodiment of FIG2. In the exercise guidance method, the distance information further includes the target distance, and step S200 may include the following steps:

[0080] Based on the target distance and the remaining distance information, the percentage of the user's incomplete journey is obtained.

[0081] The attenuation factor is determined based on the proportion of distances not completed by the user.

[0082] In this embodiment, the logic of target distance → incomplete percentage → attenuation factor is used to adapt to different distance sports goals (such as a 5km run, half marathon, and full marathon), automatically adjusting the attenuation model. For example, in a 5km run, the attenuation factor is smaller when there are 2km remaining (40% incomplete percentage) (energy is easier to maintain); in a full marathon, the attenuation factor is larger when there are 20km remaining (50% incomplete percentage) (energy consumption increases). This solves the problem of the inability of a single attenuation rule to adapt to different target scenarios. In long-distance sports (such as marathons), users can intuitively perceive the difficulty of the remaining challenge through the incomplete percentage, and combined with the attenuation factor adjustment strategy (such as actively accelerating when the remaining percentage is >50%, and maintaining the pace when it is <30%), avoid the common problem of excessive consumption in the early stage and inability to complete the task in the later stage, improving the controllability of goal achievement.

[0083] Specifically, the attenuation factor mentioned above can be obtained by the following formula:

[0084] Where p is the attenuation factor, R l S represents the percentage of uncompleted distance for the user. a S represents the target distance. l This is the remaining distance information.

[0085] Assuming the user has completed 80% of the journey, substituting this into the above formula yields an attenuation factor of 1 - (1 - 0.8) / 10 = 0.98.

[0086] Specifically, in the third embodiment of this application, the specific implementation of step S200 can be found in the following embodiment. This embodiment is a detailed description of step S200 in the exercise guidance method shown in the corresponding embodiment of FIG2. In the exercise guidance method, the pace information includes current pace information and previous pace information. The previous pace information is the pace information before the current moment. Step S200 may include the following steps:

[0087] Based on the current pace information and the previous pace information, determine the speed change parameters.

[0088] The user's attenuation factor is determined based on the speed change parameters.

[0089] In this embodiment, the temporal characteristics (such as rate of change and trend) of the previous pace are used to quantify physical fatigue, enabling the device to sense the user's fatigue state in real time. By adjusting the differential decay factor, pace suggestions that match the user's actual physical changes are provided (such as prompting "accelerate 0.2km / h to compensate for the decay" when decelerating). By processing pace data within a fixed time or distance window, computational efficiency and prediction accuracy are balanced, making it suitable for real-time exercise guidance scenarios such as smartwatches and fitness apps.

[0090] The pace information can include pace information from several moments before the current moment, including the previous moment, or it can include only the pace information from the previous moment.

[0091] When the previous pace information includes pace information from several moments before the current moment, including the previous moment, the user's previous attenuation sequence can be determined based on the current pace information and the previous pace information; then, the speed change parameters can be determined based on the previous attenuation sequence.

[0092] By analyzing the initial attenuation timeline, it can be determined whether the user's current attenuation pattern is gradual or abrupt. Gradual attenuation refers to a pace that increases uniformly over time (e.g., slowing down by 5 seconds per kilometer), with the attenuation factor increasing linearly. Abrupt attenuation refers to a sudden drop in pace (e.g., due to exhaustion, the pace suddenly decreases from 5 min 00 s / km to 5 min 30 s / km), with the attenuation factor immediately increasing significantly and triggering a warning.

[0093] Specifically, a velocity difference sequence can be obtained by measuring the velocity difference between each time point and the time point before that time point. By processing the velocity difference sequence, velocity change parameters can be obtained. Then, based on the velocity change parameters, weighted changes are performed to obtain the attenuation factor.

[0094] When the initial pace information only includes the pace information of the previous moment, the ratio of the pace information of the previous moment to the pace information of the current moment can be used as the speed change parameter. After further parameter adjustment, the user attenuation factor can be obtained.

[0095] Specifically, in some embodiments, the specific implementation of step S200 can be referred to Figure 3. Figure 3 is a detailed description of step S200 in the exercise guidance method shown in the embodiment corresponding to Figure 2. In the exercise guidance method, the user exercise information also includes the user's exercise physiological information from the start of exercise to the present, and the pace information includes the user's pace information from the start of exercise to the present. Step S200 may include the following steps:

[0096] S210 sorts the user's exercise physiological information from the start of exercise to the present time according to time, forming a time sequence of exercise physiological information.

[0097] S220 sorts the user's pace information from the start of exercise to the current time according to time, forming a time sequence of user pace information.

[0098] S230, input the exercise physiological information time series, user pace information time series and remaining distance information into the attenuation prediction model to obtain the attenuation factor.

[0099] In this embodiment, by synchronously analyzing the time series of exercise physiological information (such as heart rate and blood oxygen) and pace time series, a physiological threshold-triggered decay mode can be achieved (e.g., when the heart rate is consistently >165 beats / minute, the pace decreases by 0.1 km / h every 5 minutes). When the user's physiological state is abnormal (e.g., a sudden spike in heart rate), the model immediately updates the decay factor and provides early warning of potential risks (e.g., if the current heart rate is 180 beats / minute, maintaining this intensity will result in a 15% decrease in pace for the remaining 5 km). Users can adjust their strategies accordingly to avoid physical exhaustion.

[0100] In S210, exercise physiological information typically includes data such as heart rate, respiratory rate, and blood oxygen saturation. Electronic devices collect this data in real time and arrange it chronologically to form a time-series of exercise physiological information. This data reflects the user's physiological changes during exercise and helps assess the user's physical exertion and exercise intensity.

[0101] In S220, pace information refers to the distance or speed a user runs per unit of time during exercise. Electronic devices record the pace at each point in time and sort this data chronologically to form the temporal sequence of pace information. Pace information reflects the user's exercise rhythm and can reveal fatigue and trends during exercise.

[0102] In S230, temporal data on exercise physiology, pace, and remaining distance are input into a decay prediction model. This model analyzes this data to calculate a decay factor. The decay factor represents the degree of performance decline in the user's current state, such as the depletion of energy and a decrease in pace over time. This decay factor is predicted in real-time based on dynamic changes in the user's exercise physiology, pace, and remaining distance. This factor helps adjust the estimated completion time, making the prediction more consistent with the actual exercise state.

[0103] It should be noted that the attenuation factor predicted by the attenuation prediction model can be a single attenuation factor value or a series of attenuation factors arranged in chronological order.

[0104] Specifically, in some embodiments, the detailed implementation of step S230 can be referred to Figure 4. Figure 4 is a detailed description of step S230 in the motion guidance method shown in the embodiment corresponding to Figure 3. In the motion guidance method, the attenuation prediction model includes a temporal feature extraction layer, a fusion feature interaction layer, and an attenuation factor prediction layer. Step S230 may include the following steps:

[0105] S232, the time sequence of exercise physiological information and the time sequence of user pace information are input into the time sequence feature extraction layer to extract time sequence features and obtain fused time sequence features.

[0106] S234, the fused temporal features and the remaining distance information are concatenated and then input into the fusion feature interaction layer for feature enhancement to obtain enhanced fusion features.

[0107] S236, The enhanced fusion feature is input into the attenuation factor prediction layer to obtain the attenuation factor.

[0108] In this embodiment, by introducing three levels of processing—temporal feature extraction, fusion feature interaction, and decay factor prediction—the process of athletic decay can be accurately modeled at different time points and under different exercise states. The prediction of the decay factor makes the estimation of completion time more accurate, avoiding the large-scale errors found in traditional methods. By integrating information on the user's physiological state, exercise rhythm, and remaining exercise volume, the prediction can be dynamically adjusted according to real-time changes during exercise, ensuring that guidance and adjustments during exercise conform to the athlete's actual physical condition and performance.

[0109] In S232, the temporal feature extraction layer focuses on capturing the dynamic correlation between physiological indicators and pace, avoiding the loss of temporal patterns caused by static splicing. For example, after a sustained increase in heart rate of 10 beats per minute, it can be determined that the average pace has decreased by 0.2 km / h.

[0110] Specifically, for processing time-series information, LSTM / GRU networks or Temporal Convolutional Networks (TCNs) can be used. LSTM / GRU networks can capture long-range dependencies, such as the impact of heart rate changes on pace over the next 5 minutes. TCN networks can handle variable-length time-series data and are suitable for streaming data updated in real-time during exercise.

[0111] Specifically, in some embodiments, the specific implementation of step S232 can be referred to the following embodiments. This embodiment is a detailed description of step S232 in the motion guidance method shown in the corresponding embodiment of Figure 4. In the motion guidance method, the temporal feature extraction layer includes a bidirectional LSTM network, a Transformer encoder, and a self-attention network. Step S232 may include the following steps:

[0112] The temporal input of the exercise physiological information is fed into a bidirectional LSTM network to capture long-term dependencies, thereby obtaining the temporal features of the exercise physiological information.

[0113] The user pace information is input into a Transformer encoder to capture the periodicity and abrupt changes in the timing sequence, thereby obtaining the timing features of the user pace information.

[0114] By fusing the temporal features of the aforementioned exercise physiological information and the temporal features of the user's pace information through a self-attention network, a fused temporal feature is obtained.

[0115] In this embodiment, the bidirectional LSTM network captures long-term dependencies of physiological indicators such as heart rate through bidirectional information flow. For example, a sustained increase in heart rate 30 minutes ago indicates current lactate accumulation, leading to accelerated pace decay, necessitating adjustment of the decay factor. The Transformer encoder utilizes a self-attention mechanism to capture periodic and abrupt changes in pace timing, reducing the error in capturing pace fluctuations by approximately 22%. Self-attention fusion makes the fused features more targeted by dynamically allocating weights to physiological and pace features. For instance, when the remaining distance is short, the weight of pace abrupt changes on the decay factor is increased.

[0116] Periodic characteristics in pacing can include accelerating every 5 minutes or slowing down by 1 min / km every 5 minutes. Abrupt characteristics in pacing can include sudden deceleration, which may indicate exhaustion.

[0117] The above embodiments, by separating the extraction paths of physiological and pacing characteristics, can quantitatively analyze the contribution of different factors to attenuation, providing users with more interpretable exercise suggestions.

[0118] In S234, the fusion feature interaction layer explicitly models the interaction between temporal dynamic features and static pressure of remaining distance (e.g., for every 1km increase in remaining distance, the decay factor corresponding to the same heart rate level increases by 0.05%), enabling the model to distinguish between mid-course fatigue and fatigue caused by pressure in the later stages.

[0119] Specifically, the fused temporal features and residual distance information can be concatenated, and a fully connected layer can be used to learn the non-linear relationship between features through a multilayer perceptron (MLP). Then, attention weights of the residual distance on the temporal features can be introduced (e.g., the longer the residual distance, the more the model pays attention to whether the recent heart rate is abnormal). Finally, an enhanced fused feature is obtained, which contains the interaction information between the temporal dynamic features and the residual distance.

[0120] In S236, single-layer or multi-layer fully connected layers can be used to map enhanced fusion features to attenuation factors through linear layers, and the output range can be limited by activation functions. Furthermore, post-processing of the prediction results can be performed using exercise physiology principles to avoid prediction anomalies caused by extreme values.

[0121] Post-processing constraints may include a minimum attenuation factor of 120% of the user's historical maximum attenuation rate.

[0122] It should be noted that the training method for the above-mentioned attenuation prediction model can refer to the following embodiment. The specific training steps for the above-mentioned attenuation prediction model include:

[0123] The user's historical motion data is obtained to obtain a user motion behavior sample set. The user motion behavior sample set contains multiple user motion behavior samples. Each user motion behavior sample corresponds to a segment of the user's motion behavior and includes the user's pace information time sequence, user pace information time sequence, and remaining distance information in that segment of motion behavior. All samples are also marked with a corresponding decay factor label.

[0124] Each user motion behavior sample in the user motion behavior sample set is input into the attenuation prediction model to obtain the corresponding attenuation factor.

[0125] The parameters of the attenuation prediction model are updated according to the attenuation factor and the attenuation factor label until a predetermined termination condition is met, at which point training stops and a trained attenuation prediction model is obtained.

[0126] In this embodiment, by training with a large number of users' own historical samples, the model can identify the decay patterns of users in different scenarios, making the model more targeted. At the same time, as the user's exercise level improves, the decline in physical strength will also slow down, and new data continuously updates the model parameters, ensuring that the decay prediction consistently matches the user's current state.

[0127] In the embodiments of this application, during training, a user motion behavior sample set containing multiple user motion behavior samples can be obtained first. Each user motion behavior sample contains the user's pace information time sequence, user pace information time sequence, and remaining distance information in that segment of motion behavior, and is labeled with a corresponding decay factor label. Then, the multiple user motion behavior samples are divided into a training set, a validation set, and a test set according to a predetermined ratio. Then, the parameters of the encoder and decoder in the decay prediction model are adjusted and determined based on the user motion behavior samples included in the training set, validation set, and test set, to obtain the trained decay prediction model.

[0128] It should be noted that in the aforementioned user motion behavior sample set, each sample is obtained from the user's historical motion data. Specifically, the user's historical motion data includes motion data from multiple segments of the user's historical motion. Each segment of the historical motion data is randomly cut according to a predetermined window threshold, resulting in two segments of motion data: a sample segment before the cut-off point time and a labeled segment after the cut-off point time. The attenuation factor of the labeled segment can be determined based on the data of the labeled segment. This attenuation factor is used as the label for the preceding sample segment, thus obtaining user motion behavior samples labeled with the corresponding attenuation factor.

[0129] It should be noted that the user motion behavior samples mentioned above include those with interfering and blank items, in order to improve the model's ability to identify interfering and blank items. During post-processing of the time-series data, the time-series data generated from the user's pace information time-series, the user pace information time-series, and the remaining distance information imaging image of that user's motion behavior segment with interfering and blank items are removed, thereby filtering out interfering and blank items.

[0130] When training the model, the user motion behavior sample set can be divided into a training set, a validation set, and a test set. Then, the model is trained based on the training set, validated based on the validation set, and tested based on the test set to obtain a trained decay prediction model.

[0131] Before training based on the training set, the user's pace information time series, user pace information time series, and remaining distance information image samples in the training set for this user's movement behavior can be preprocessed. Preprocessing includes image resizing, normalization, data augmentation, and class encoding.

[0132] The specific methods for data augmentation include performing sequential transformations on time-series data and arbitrarily changing the cut-off points of time-series data. These operations can better expand the form of the user's pace information time sequence, user pace information time sequence, and remaining distance information in that segment of the user's movement behavior.

[0133] In some embodiments, GAN networks can also be used to generate data that is difficult to identify but not easily obtained, such as user pace information timing, user pace information timing and remaining distance information in the user's movement behavior, where there are data conflicts or data distortions. This helps the algorithm model to accurately identify user pace information timing, user pace information timing and remaining distance information in the user's movement behavior, helps to reduce false identification and false negative identification, and helps to improve the accuracy of the model in identifying user pace information timing, user pace information timing and remaining distance information in the user's movement behavior in special data.

[0134] After obtaining the enhanced training set, the decay prediction model can be trained based on the enhanced training set, and the parameters and weights in the network can be updated.

[0135] Specifically, the user's pace information time series, pace information time series, and remaining distance information image samples from the training set during this movement segment are input into the attenuation prediction model to obtain the attenuation factor output by the attenuation prediction model. The attenuation factor and its label are compared to calculate the loss function. Then, the stochastic gradient descent method is used to minimize the loss function. The parameters and weights in the attenuation prediction model are updated by backpropagation until the loss function meets a predetermined condition, such as convergence or falling below a predetermined threshold.

[0136] In some embodiments, the attenuation factor includes an attenuation factor value or an attenuation factor time series, and the attenuation factor label may include at least one of an attenuation factor value label or an attenuation factor time series label. The loss function is obtained by comparing the attenuation factor value with the attenuation factor value label and / or by comparing the attenuation factor time series with the attenuation factor time series label.

[0137] After training, the decay prediction network with updated parameters from the training set can be validated using a validation set. Specifically, the decay prediction network is tuned based on the validation set data, and the model parameters for that stage are output when the loss function meets predetermined conditions. If the loss function does not meet the predetermined conditions, hyperparameters such as the learning rate are automatically adjusted, and the next round of network model training is performed.

[0138] When the loss function computed on the validation set meets predetermined conditions, the parameters and weights can be retained, and then the retained parameters are tested based on the test set. Specifically, the input test set data enables the decay prediction network with retained parameters and weights to output a decay factor and model weights. By comparing the model loss and corresponding weights across multiple epochs, the model weights with the minimum loss are output, thus determining the trained decay prediction model.

[0139] After obtaining the trained decay prediction model, the decay factor can be predicted based on the decay prediction model.

[0140] Furthermore, data augmentation is not required for the input data in the validation and test sets.

[0141] In S300, the remaining time is calculated based on the remaining distance, current pace information, and attenuation factor. This calculation not only considers the current pace but also incorporates the influence of the attenuation factor, making the model more accurate.

[0142] Specifically, in the first embodiment of this application, the specific implementation of step S300 can be found in the following embodiment. This embodiment is a detailed description of step S300 in the exercise guidance method shown in the corresponding embodiment of FIG2. In the exercise guidance method, step S300 may include the following steps:

[0143] Based on the attenuation factor for each predetermined time period, the pace information within each predetermined time period is corrected using the user's current pace information to obtain the corrected pace for each predetermined time period.

[0144] Based on the corrected pace and remaining distance information, the user's remaining time is estimated.

[0145] In this embodiment, the dynamic adjustment of the decay factor enables the method to update the remaining time prediction in real time based on the user's exercise progress, providing personalized exercise strategy guidance. Exercisers can adjust their exercise intensity promptly based on the corrected pace information, avoiding physical exhaustion.

[0146] Specifically, as described above, when each predetermined time period is fixed as a time period of equal distance length, the corresponding attenuation factor is applied to each time period of equal distance length to obtain the corrected pace. Then, based on the distance length and corrected pace corresponding to each predetermined time period, the corrected time consumption corresponding to each predetermined time period is obtained. The corrected time consumption corresponding to all predetermined time periods is accumulated to obtain the user's remaining time.

[0147] When all predetermined time periods are of equal length, a corresponding attenuation factor is applied to each equal-length time period to obtain a corrected pace. Then, based on the length of each predetermined time period and the corrected pace, the corrected distance for each predetermined time period is obtained. The corrected distances for each predetermined time period are accumulated sequentially, and the corresponding times for each predetermined time period are also accumulated sequentially, until the accumulated corrected distance reaches the remaining distance. At this point, it is determined whether the accumulated corrected distance equals the remaining distance. If they do, the accumulated time is the estimated remaining time for the user.

[0148] If it is not equal to (i.e. greater than), then the last accumulated scheduled time period is split according to the difference between the accumulated corrected distance and the remaining distance. The resulting split time period is added to the previous time periods and then equal to the remaining distance. At this point, the user's remaining time is obtained.

[0149] Specifically, in the second embodiment of this application, the specific implementation of step S300 can be found in the following embodiment. This embodiment is a detailed description of step S300 in the exercise guidance method shown in the corresponding embodiment of FIG2. In the exercise guidance method, the pace information includes pace information within the current predetermined time interval, and step S300 may include the following steps:

[0150] The current average pace is determined based on the pace information within the current predetermined time interval.

[0151] The average attenuation pace is determined based on the current average pace and the attenuation factor.

[0152] The remaining time for the user is obtained based on the remaining distance information and the average attenuation pace.

[0153] In this embodiment, short-term fluctuations are filtered out by using an average pace over a time window, making the prediction model more robust (e.g., if a user temporarily slows down due to road conditions, the system will not misinterpret this as a decline in physical strength and over-adjust the prediction). The length of the time window (e.g., 5 seconds / 10 seconds) can be dynamically adjusted according to the type of exercise (e.g., 5 seconds for short-distance exercise, 10 seconds for long-distance exercise), balancing real-time performance and stability. For example, in a marathon, a 10-second time window can reflect pace changes promptly while avoiding frequent corrections caused by short-term fluctuations such as breathing adjustments.

[0154] Specifically, the remaining user time mentioned above can be obtained using the following formula:

[0155] Where ETE represents the user's remaining time, v p For average decay pace, S l For the remaining distance information, v ave R is the current average pace, p is the attenuation factor, and R is the current average pace. l This represents the percentage of the user's incomplete journey.

[0156] Specifically, for example, within a 10-second time window, the pace is sampled every 2 seconds to obtain 5 values: 5min06s / km, 5min04s / km, 5min00s / km, 5min04s / km, and 5min05s / km, thus obtaining the current average pace of 5min04s / km.

[0157] Continuing, taking a decay factor of 0.98 and a current average pace of 5 min 04 s / km as an example, the average decaying pace would be approximately 5 min 10 s / km. If the remaining distance is 4.22 km, then the user's remaining time would be 21 min 48 s.

[0158] In S400, the estimated finishing time is calculated by combining the elapsed time and the remaining time. This time can be updated in real time and adjusted based on the user's actual performance.

[0159] After obtaining the estimated finish time, it can be displayed on the electronic device's screen, as shown in Figure 5. 501 represents the completed exercise volume, 502 represents the real-time pace, 503 represents the completion progress bar, 504 represents the real-time heart rate, and 505 represents the estimated finish time. The estimated finish time is displayed in a larger, more prominent font centered at the bottom center of the screen, making it easier for users to notice and thus guiding them on how to adjust their current pace.

[0160] In some embodiments of this application, after S400, as shown in FIG6, the motion guidance method further includes:

[0161] S602, in response to the end of the motion function, determine whether the remaining distance information is greater than a predetermined distance threshold.

[0162] S604, if the remaining distance information is greater than the predetermined distance threshold, the user's estimated completion time will be displayed on the end of the exercise interface.

[0163] S606 If the remaining distance information is not greater than the predetermined distance threshold, the user's actual completion time will be displayed on the end-of-race interface.

[0164] In this embodiment, a flexible performance display is achieved through threshold judgment. For example, if a runner stops midway through a half marathon, the estimated finishing time is displayed when there are 5km remaining, allowing the user to assess the likelihood of finishing the race. If the runner stops when there are 10m remaining, the actual finishing time is displayed, which is closer to the actual completion situation. This solves the problem of information distortion caused by the one-size-fits-all display method and improves the user's acceptance of the exercise results.

[0165] By combining the relationship between remaining distance and threshold, users can quickly determine whether the timing of the interruption affects the reference value of the score, enhancing the practicality of the exercise data. If the remaining distance is greater than the threshold, the user knows that they have not completed most of the goal, and the interface shown in Figure 7 is displayed; if the remaining distance is less than the threshold, the user knows that they are close to completing the goal and the actual score is valid, and the interface shown in Figure 8 is displayed.

[0166] It should be noted that the predetermined distance threshold is generally set to less than 100m, such as 1m, 10m, or 50m. This is mainly to compensate for positioning errors of electronic devices. Additionally, when a user is close to completing the race but hasn't finished, assuming they have completed it gives them confidence and enhances the user experience, in order to approximate the actual completion status. In ultra-long-distance sports (such as orienteering and marathons), the predetermined distance threshold can be set to 1km.

[0167] In some embodiments of this application, the aforementioned time information also includes the target completion time. Therefore, after S400, the exercise guidance method further includes:

[0168] A recommended pace is obtained based on the user's estimated finish time, the target finish time, the pace information, and the decay factor.

[0169] In this embodiment, the overall goal is broken down into phased pace requirements (e.g., maintaining 5 min 0.5 s / km for the remaining 10km) and dynamically adjusted according to the attenuation factor (e.g., 5 min 1.5 s / km is acceptable for the last 3km due to increased physical fatigue).

[0170] For example, if the target completion time is 3 hours and the current estimated time is 3 hours and 10 minutes, the initial calculation suggests increasing the current pace by 0.2 km / h. After considering the decay factor, it is recommended to accelerate to 4 min 55 s / km for the first 5 km and maintain 5 min 05 s / km for the next 5 km. Compared to maintaining a pace of 4 min 55 s / km throughout the race, this method avoids the problem of users collapsing due to exhaustion in the latter half. It should be noted that in this embodiment, the recommended pace can be updated in real-time, every minute or second, to ensure that users can adjust their pace accordingly.

[0171] The following describes an embodiment of the apparatus described in this application, which can be used to execute the motion guidance method described above. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the motion guidance method described above.

[0172] Figure 9 shows a block diagram of a motion guidance device according to an embodiment of this application.

[0173] Referring to FIG9, a sports guidance device 900 according to an embodiment of the present application includes: a sports information acquisition module 910, a decay factor determination module 920, a remaining time estimation module 930, and a completion time estimation module 940.

[0174] The exercise information acquisition module 910 is used to acquire user exercise information, including pace information, distance information, and time information. The distance information includes remaining distance information, and the time information includes elapsed time information. The decay factor determination module 920 is used to determine the user's decay factor based on the user's exercise information. The remaining time estimation module 930 is used to estimate the user's remaining time based on the remaining distance information, the pace information, and the decay factor. The completion time estimation module 940 is used to obtain the user's estimated completion time based on the user's remaining time and elapsed time information.

[0175] In some embodiments of this application, the pace information includes current pace information; the attenuation factor determination module specifically includes: a preliminary estimated time submodule, used to obtain a preliminary estimated time based on the remaining distance information and the current pace information; and a stage attenuation factor submodule, used to determine the attenuation factor for each predetermined time period based on the preliminary estimated time.

[0176] In some embodiments of this application, the remaining time estimation module specifically includes: a pace information correction submodule, which corrects the pace information in each predetermined time period based on the attenuation factor of each predetermined time period and the user's current pace information to obtain the corrected pace corresponding to each predetermined time period; and a remaining time estimation submodule, which estimates the user's remaining time based on the corrected pace and remaining distance information.

[0177] In some embodiments of this application, the distance information further includes the target distance; the attenuation factor determination module specifically includes: a distance ratio determination submodule, used to obtain the proportion of the user's incomplete distance based on the target distance and the remaining distance information; and an attenuation factor determination submodule, used to determine the attenuation factor based on the proportion of the user's incomplete distance.

[0178] In some embodiments of this application, the pace information includes pace information within the current predetermined time interval; the remaining time estimation module specifically includes: a current average pace submodule, used to determine the current average pace based on the pace information within the current predetermined time interval; an average decay pace submodule, used to determine the average decay pace based on the current average pace and the decay factor; and a user remaining time submodule, used to obtain the user's remaining time based on the remaining distance information and the average decay pace.

[0179] In some embodiments of this application, the time information further includes the target completion time, and the exercise guidance device further includes: a pace recommendation module, used to obtain a recommended pace based on the user's estimated completion time, the target completion time, the pace information, and the decay factor.

[0180] In some embodiments of this application, the exercise guidance device further includes: a remaining distance determination module, configured to determine whether the remaining distance information is greater than a predetermined distance threshold in response to the end of the exercise function; a first display module, configured to display the user's estimated completion time on the exercise end interface if the remaining distance information is greater than the predetermined distance threshold; and a second display module, configured to display the user's actual completion time on the exercise end interface if the remaining distance information is not greater than the predetermined distance threshold.

[0181] In some embodiments of this application, the user motion information further includes the user's physiological motion information from the start of the exercise to the present, and the pace information includes the user's pace information from the start of the exercise to the present; the attenuation factor determination module specifically includes: a physiological information time series submodule, used to sort the user's physiological motion information from the start of the exercise to the present according to time to form a physiological motion information time series; a pace information time series submodule, used to sort the user's pace information from the start of the exercise to the present according to time to form a pace information time series; and an attenuation model prediction submodule, used to input the physiological motion information time series, the pace information time series, and the remaining distance information into the attenuation prediction model to obtain the attenuation factor.

[0182] In some embodiments of this application, the attenuation prediction model includes a temporal feature extraction layer, a fusion feature interaction layer, and an attenuation factor prediction layer; the attenuation model prediction submodule specifically includes: a temporal feature fusion unit, used to input the temporal sequence of the exercise physiological information and the temporal sequence of the user pace information into the temporal feature extraction layer to extract temporal features, thereby obtaining fused temporal features; a fusion feature enhancement unit, used to concatenate the fused temporal features with the remaining distance information and input them into the fusion feature interaction layer for feature enhancement, thereby obtaining enhanced fused features; and an attenuation factor prediction unit, used to input the enhanced fused features into the attenuation factor prediction layer to obtain the attenuation factor.

[0183] In some embodiments of this application, the temporal feature extraction layer includes a bidirectional LSTM network, a Transformer encoder, and a self-attention network; the temporal feature fusion unit specifically includes: a bidirectional LSTM network subunit, used to input the temporal data of the exercise physiological information into the bidirectional LSTM network to capture long-term dependencies, thereby obtaining temporal features of the exercise physiological information; a Transformer encoder subunit, used to input the temporal data of the user pace information into the Transformer encoder to capture periodic and abrupt features in the temporal data, thereby obtaining temporal features of the user pace information; and a temporal feature fusion subunit, used to fuse the temporal features of the exercise physiological information and the temporal features of the user pace information through the self-attention network, thereby obtaining fused temporal features.

[0184] In some embodiments of this application, the exercise guidance device further includes: a sample acquisition module, used to acquire historical exercise data of the user to obtain a user exercise behavior sample set, wherein the user exercise behavior sample set contains multiple user exercise behavior samples, each user exercise behavior sample corresponds to a segment of exercise behavior of the user, and includes the user pace information time sequence, user pace information time sequence and remaining distance information of the user in the segment of exercise behavior, and each is marked with a corresponding decay factor label; a sample input module, used to input each of the user exercise behavior samples in the user exercise behavior sample set into the decay prediction model one by one to obtain the corresponding decay factor; and a parameter update module, used to update the parameters of the decay prediction model according to the decay factor and the decay factor label until a predetermined termination condition is met, stop training, and obtain a trained decay prediction model.

[0185] In the embodiments of this application, by dynamically calculating the remaining time and completion time during the exercise, users can know in real time whether they have exceeded or fallen short of the target time. This real-time feedback helps users better control the pace of the race, adjust their pace to avoid exhaustion or overexertion, and ultimately achieve their ideal completion time.

[0186] Figure 10 shows a schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application.

[0187] It should be noted that the computer system of the electronic device shown in Figure 10 is only an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0188] As shown in Figure 10, the computer system includes a Central Processing Unit (CPU) 1801, which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) 1802 or programs loaded from storage portion 1808 into Random Access Memory (RAM) 1803, such as performing the methods described in the above embodiments. The RAM 1803 also stores various programs and data required for system operation. The CPU 1801, ROM 1802, and RAM 1803 are interconnected via a bus 1804. An Input / Output (I / O) interface 1805 is also connected to the bus 1804.

[0189] The following components are connected to I / O interface 1805: an input section 1806 including a keyboard, mouse, etc.; an output section 1807 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 1808 including a hard disk, etc.; and a communication section 1809 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 1809 performs communication processing via a network such as the Internet. A drive 1810 is also connected to I / O interface 1805 as needed. Removable media 1811, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 1810 as needed so that computer programs read from them can be installed into storage section 1808 as needed.

[0190] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1809, and / or installed from removable medium 1811. When the computer program is executed by central processing unit (CPU) 1801, it performs various functions defined in the system of this application.

[0191] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. The transmitted data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0192] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0193] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0194] In another aspect, this application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the methods described in the above embodiments.

[0195] This specification also provides a computer program product that stores at least one instruction, which is loaded by the processor and executed as described in the embodiments shown in Figures 1 to 8 above. For details of the execution process, please refer to the specific description of the embodiments shown in Figures 1 to 8, which will not be repeated here.

[0196] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0197] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, touch terminal, or network device, etc.) to execute the method according to the embodiments of this application.

[0198] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0199] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method of coaching an athletic performance, characterized by, The motion guiding method comprises: acquiring user motion information, the user motion information comprising pace information, distance information and time information, the distance information comprising remaining distance information, and the time information comprising used time information; determining a user's attenuation factor according to the user motion information; estimating the user's remaining time according to the remaining distance information, the pace information and the attenuation factor; obtaining the user's estimated finish time according to the user's remaining time and the used time information.

2. The exercise guidance method according to claim 1, characterized by, The pace information comprises current pace information. The determination of the user's attenuation factor according to the user motion information specifically comprises: obtaining a preliminary estimated time according to the remaining distance information and the current pace information; determining the attenuation factor of each predetermined time period according to the preliminary estimated time.

3. The exercise guidance method of claim 2, wherein, The determination of the attenuation factor of each predetermined time period according to the preliminary estimated time specifically comprises: segmenting the preliminary estimated time into a plurality of predetermined time periods in units of a predetermined time window; fixing each of the predetermined time periods as a time period of equal distance length; multiplying the attenuation factors in each of the predetermined time periods in time sequence to obtain the attenuation factor of each predetermined time period.

4. The exercise guidance method of claim 2, wherein, The preliminary estimated time is obtained by adjusting a coefficient. The determination of the attenuation factor of each predetermined time period according to the preliminary estimated time specifically comprises: segmenting the preliminary estimated time into a plurality of time periods in units of a predetermined time window; fixing each of the time periods as a time period of equal time length; multiplying the attenuation factors in each of the time periods in time sequence to obtain the attenuation factor of each predetermined time period.

5. The exercise guidance method of claim 2, wherein, The estimation of the user's remaining time according to the remaining distance information, the pace information and the attenuation factor specifically comprises: correcting the pace information in each predetermined time period based on the user's current pace information according to the attenuation factor of each predetermined time period to obtain a corrected pace corresponding to each predetermined time period; estimating the user's remaining time according to the corrected pace and the remaining distance information.

6. The exercise guidance method of claim 1, wherein, The distance information further comprises target distance information. The determination of the user's attenuation factor according to the user motion information specifically comprises: obtaining a user's unfinished distance ratio according to the target distance information and the remaining distance information; determining the attenuation factor according to the user's unfinished distance ratio.

7. The exercise guidance method according to claim 6, wherein The pace information comprises pace information in a current predetermined time interval. The estimation of the user's remaining time according to the remaining distance information, the pace information and the attenuation factor specifically comprises: determining a current average pace according to the pace information in the current predetermined time interval; determining an average attenuation pace according to the current average pace and the attenuation factor; obtaining the user's remaining time according to the remaining distance information and the average attenuation pace.

8. The exercise guidance method of claim 1, wherein, The pace information comprises current pace information and previous pace information, the previous pace information being pace information before the current time. The determination of the user's attenuation factor according to the user motion information specifically comprises: According to the current pace information and the previous pace information, a speed change parameter is determined; According to the speed change parameter, a decay factor of the user is determined.

9. The exercise guidance method of claim 8, wherein, The determination of the speed change parameter according to the current pace information and the previous pace information specifically includes: According to the current pace information and the previous pace information, a previous decay time sequence of the user is determined; According to the previous decay time sequence, the speed change parameter is determined.

10. The exercise guidance method according to any one of claims 1 to 9, characterized by, The time information further includes a target finish time; after the user's estimated finish time is obtained according to the user's remaining time and the used time information, the sports guidance method further includes: According to the user's estimated finish time, the target finish time, the pace information and the decay factor, a recommended pace is obtained.

11. The exercise guidance method of claim 1, wherein, After the user's estimated finish time is obtained according to the user's remaining time and the used time information, the sports guidance method further includes: In response to the end of the sports function, it is determined whether the remaining distance information is greater than a predetermined distance threshold; If the remaining distance information is greater than the predetermined distance threshold, the user's estimated finish time is displayed on the sports end interface; If the remaining distance information is not greater than the predetermined distance threshold, the user's actual finish time is displayed on the sports end interface.

12. The exercise guidance method of claim 1, wherein, The user's sports information further includes the user's sports physiological information from the start of the sports to the present, and the pace information includes the user's pace information from the start of the sports to the present; The determination of the decay factor of the user according to the user's sports information specifically includes: The user's sports physiological information from the start of the sports to the present is sorted by time to form a sports physiological information time sequence; The user's pace information from the start of the sports to the present is sorted by time to form a user's pace information time sequence; The sports physiological information time sequence, the user's pace information time sequence and the remaining distance information are input into a decay estimation model to obtain the decay factor.

13. The exercise guidance method of claim 12, wherein, The decay estimation model includes a time sequence feature extraction layer, a fusion feature interaction layer and a decay factor prediction layer; The input of the sports physiological information time sequence and the user's pace information time sequence into the time sequence feature extraction layer to extract time sequence features to obtain fusion time sequence features, the concatenation of the fusion time sequence features and the remaining distance information and the input of the concatenated features into the fusion feature interaction layer for feature enhancement to obtain enhanced fusion features, and the input of the enhanced fusion features into the decay factor prediction layer to obtain the decay factor. The time sequence feature extraction layer includes a bidirectional LSTM network, a Transformer encoder and a self-attention network; The input of the sports physiological information time sequence into the bidirectional LSTM network to capture long-term dependencies to obtain sports physiological information time sequence features, the input of the user's pace information time sequence into the Transformer encoder to capture periodicity and mutation features in the time sequence to obtain user's pace information time sequence features, and the input of the sports physiological information time sequence features and the user's pace information time sequence features into the self-attention network to obtain fusion time sequence features. ​ 14. The exercise guidance method of claim 13, wherein, ​ ​ ​ ​ The self-attention network is used to fuse the motion physiological information time sequence feature and the user pace information time sequence feature to obtain a fused time sequence feature.

15. The exercise guidance method of claim 13, wherein, The fused time sequence feature and the remaining distance information are spliced, and a fully connected layer is used to learn a non-linear relationship between the features through a multi-layer perception. The attention weight of the time sequence feature is introduced to the remaining distance to obtain an enhanced fused feature. The motion guidance method further includes:

16. The exercise guidance method of claim 12, wherein, Obtaining user historical motion data to obtain a user motion behavior sample set, the user motion behavior sample set including a plurality of user motion behavior samples, each user motion behavior sample corresponding to a motion behavior of the user and including user pace information time sequence, user pace information time sequence and remaining distance information of the user in the motion behavior, and being marked with a corresponding decay factor label; Each user motion behavior sample in the user motion behavior sample set is input into a decay estimation model one by one to obtain a corresponding decay factor; The decay estimation model is parameter updated according to the decay factor and the decay factor label until a predetermined end condition is met, the training is stopped, and a trained decay estimation model is obtained. The motion guidance device includes:

17. A sports coaching device, characterised in that, A motion information acquisition module is configured to acquire user motion information, the user motion information including pace information, distance information and time information, the distance information including remaining distance information, and the time information including used time information; A decay factor determination module is configured to determine a user decay factor based on the user motion information; A remaining time estimation module is configured to estimate a user remaining time based on the remaining distance information, the pace information and the decay factor; A finish time estimation module is configured to obtain a user estimated finish time based on the user remaining time and the used time information. The computer program is executed by a processor to implement the motion guidance method of any one of claims 1-11.

18. A computer readable medium having stored thereon a computer program, characterized in that, It includes:

19. An electronic device, comprising: One or more processors; A storage device is configured to store one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the motion guidance method of any one of claims 1-16. The one or more computer programs are executed by one or more processors to implement the steps of the motion guidance method of any one of claims 1-16.

20. A computer program product comprising one or more computer programs, ​