Riding training data correction method and system based on intelligent riding glasses

Abstract

The invention discloses a riding training data correction method and system based on intelligent riding glasses, and the method comprises the steps: collecting positioning, inertia, power and heart rate data, and obtaining time sequence data including speed, displacement increment, power, heart rate and traffic signal state through combining forward vision and environmental acoustic signals; when the speed is lower than a first speed threshold value, the displacement increment is lower than a first displacement threshold value, and the traffic signal state is detected to be red light or power is lower than a power threshold value, a red light waiting section is determined; in the red light waiting section, time accumulation in speed and speed setting calculation in the time period is paused, and heart rate and power changes are independently recorded to represent a recovery state; after the red light waiting section is finished, the average speed, the allocation speed and the training load index are corrected based on the advancing data without the red light waiting section, and the individualized training intensity parameters are updated according to the recovery state data. According to the technical scheme, the credibility of training data and the effectiveness of training guidance can be improved.

Description

Technical Field

[0001] This invention relates to the field of smart cycling glasses, and in particular to a method and system for correcting cycling training data based on smart cycling glasses. Background Technology

[0002] In urban cycling training scenarios, existing smart cycling devices and platforms mostly use automatic pauses or post-travel time statistics based on speed thresholds to reduce the impact of stationary periods such as red lights on average speed and pace. However, such methods are difficult to distinguish between waiting at red lights and slow uphill or slow traffic conditions, which can easily lead to misjudgments. At the same time, the waiting period is regarded as inactive, so physiological recovery information such as heart rate recovery and low power output during the waiting period is ignored, resulting in systematic deviations in indicators such as power per unit distance and training load, and causing the subsequent training intensity settings to be mismatched with the rider's actual recovery state. Summary of the Invention

[0003] The purpose of this application is to propose a method and system for correcting cycling training data based on smart cycling glasses, so as to solve the technical problem that the waiting time at red lights affects the real training data.

[0004] To address the aforementioned technical problems, this application provides a method for correcting cycling training data based on smart cycling glasses, employing the following technical solution: A method for correcting cycling training data based on smart cycling glasses includes the following steps: Collect positioning, inertial, power, and heart rate data, and combine them with forward vision and ambient acoustic signals to obtain time-series data including velocity, displacement increment, power, heart rate, and traffic signal status; When the speed is lower than the first speed threshold and the displacement increment is lower than the first displacement threshold, and the traffic signal status is detected as red or the power is lower than the power threshold, it is determined to be a red light waiting segment; During the red light waiting period, the time accumulation in speed and pace calculations is paused, and heart rate and power changes are recorded independently to characterize the recovery status. After the red light waiting period ends, the average speed, pace, and training load indicators are adjusted based on the travel data excluding the red light waiting period, and the individualized training intensity parameters are updated based on the recovery status data.

[0005] In one possible implementation, the step of determining a red light waiting segment when the speed is lower than a first speed threshold, the displacement increment is lower than a first displacement threshold, and the traffic signal status is detected as red or the power is lower than a power threshold, specifically includes: Within a sliding time window, if the speed is lower than the first speed threshold and the displacement increment is lower than the first displacement threshold, and at least two of the three types of signals (traffic signal status, power and heart rate behavior, and environmental acoustic characteristics) consistently point to the waiting state and the duration is not less than the stop duration threshold, then it is determined to enter the red light waiting segment. After entering, a freeze window is set. Within the freeze window, even if the instantaneous speed briefly exceeds the first speed threshold, the red light waiting state is maintained to suppress jitter misjudgment.

[0006] In one possible implementation, the step of determining a red light waiting segment when the speed is lower than a first speed threshold, the displacement increment is lower than a first displacement threshold, and the traffic signal status is detected as red or the power is lower than a power threshold, further includes: The location coordinates of the current position are compared with a preset set of intersection areas. When the location coordinates are located in any intersection area and the traffic signal status is red, the effectiveness of the determination of the red light waiting segment is enhanced. When the location coordinates do not belong to any intersection area, at least one of the following conditions must be met simultaneously: speed and displacement conditions, as well as environmental acoustic or power behavior signals, in order to be determined as a red light waiting section.

[0007] In one possible implementation, in the step of pausing the time accumulation of the red light waiting period in speed and pace calculation and independently recording heart rate and power changes to characterize the recovery state, the recovery state is parameterized as a recovery feature vector, which includes at least the heart rate decrease rate, the duration of the red light waiting period, and the average power during the red light waiting period. The recovery efficiency index is calculated based on the recovery feature vector. The recovery efficiency index is established by the ratio of the heart rate decrease to the duration of the decrease, and is normalized by combining the ratio of the mean power to the individual baseline power.

[0008] In one possible implementation, in the step of correcting the average speed, pace, and training load indicators based on the travel data excluding the red light waiting period after the red light waiting period ends, and updating the individualized training intensity parameters based on the recovery status data, the individualized training intensity parameters are updated using a gated exponential weighting method, specifically including: When the recovery efficiency index is below the lower threshold, the individualized training intensity parameter is reduced and the target power or target heart rate range for the next training interval is narrowed. When the recovery efficiency index is within the threshold range, the individualized training intensity parameter remains unchanged; When the recovery efficiency index is higher than the upper threshold, the individualized training intensity parameter is slightly increased under the safety limit constraint.

[0009] In one possible implementation, before the steps of correcting the average speed, pace, and training load indicators based on the travel data excluding the red light waiting period after the red light waiting period ends, and updating the individualized training intensity parameters based on the recovery status data, the method further includes: The time spent waiting at red lights will be included in the recovery time, but not in the advance time. The average speed, pace, and training load indicators are calculated during the advance time, and the recovery feature vector and recovery efficiency index are continuously accumulated during the recovery time. The start and end times and segment labels of the red light waiting segment are recorded in the data structure for use in training metric correction and individualized training intensity parameter updates.

[0010] In one possible implementation, the first speed threshold, the stop duration threshold, and the power threshold are dynamically adjusted based on the environmental conditions of the day and recent training records. When the traffic signal status is unavailable or its reliability is below a preset threshold, a conservative threshold combination of speed and displacement increment is used to maintain the red light waiting segment determination.

[0011] To address the aforementioned technical problems, this application also provides a cycling training data correction system based on smart cycling glasses, employing the following technical solution: A cycling training data correction system based on smart cycling glasses includes: The acquisition module is configured to acquire positioning, inertial, power, and heart rate data, and combine them with forward vision and ambient acoustic signals to obtain time-series data including velocity, displacement increment, power, heart rate, and traffic signal status. The determination module is configured to determine a red light waiting segment when the speed is lower than a first speed threshold and the displacement increment is lower than a first displacement threshold, and the traffic signal status is detected as red or the power is lower than a power threshold. The recording module is configured to pause the accumulation of time in speed and pace calculations during the red light waiting period and independently record heart rate and power changes to characterize the recovery status. The correction module is configured to correct the average speed, pace, and training load indices based on the travel data excluding the red light waiting period after the red light waiting period ends, and update the individualized training intensity parameters based on the recovery status data.

[0012] To address the aforementioned technical problems, this application also provides a computer device that employs the following technical solution: A computer device includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor executes the computer-readable instructions to implement the steps of the cycling training data correction method based on cycling smart glasses as described above.

[0013] To address the aforementioned technical problems, this application also provides a computer-readable storage medium, employing the technical solution described below: A computer-readable storage medium storing computer-readable instructions, which, when executed by a processor, implement the steps of the cycling training data correction method based on cycling smart glasses as described above.

[0014] Compared with the prior art, the embodiments of this application have the following main advantages: The cycling training data correction method disclosed in this application, based on smart cycling glasses, accumulates and retains the recovery state during the pause time in the red light waiting period. Combined with the correction of the riding data after the red light waiting period ends and the update of individualized training intensity parameters, it can accurately eliminate the interference of red lights on urban roads and effectively utilize physiological recovery information. This makes the average speed, pace and training load indicators closer to the actual driving performance, and matches the subsequent training intensity with the rider's current recovery ability, thereby improving the overall credibility of training data and the effectiveness of training guidance. Attached Figure Description

[0015] To more clearly illustrate the solutions in this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a flowchart of an embodiment of the cycling training data correction method based on cycling smart glasses according to this application; Figure 2 This is a schematic diagram of a structure of an embodiment of a cycling training data correction system based on cycling smart glasses according to this application; Figure 3 This is a schematic diagram of the structure of one embodiment of the computer device according to this application. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0018] refer to Figure 1This document illustrates a flowchart of an embodiment of a cycling training data correction method based on cycling smart glasses according to this application. The method is implemented on cycling smart glasses equipped with positioning, inertial, forward vision, and environmental acoustic acquisition capabilities. The glasses establish a data link wirelessly with a power meter and a heart rate sensor. The method includes the following steps: Step S101: Collect positioning, inertial, power, and heart rate data, and combine them with forward vision and ambient acoustic signals to obtain time-series data including velocity, displacement increment, power, heart rate, and traffic signal status.

[0019] In this embodiment, the electronic device running on the cycling training data correction method based on cycling smart glasses can send or receive data via wired or wireless connection. It should be noted that the aforementioned wireless connection methods may include, but are not limited to, 3G / 4G / 5G connections, WiFi connections, Bluetooth connections, WiMAX connections, Zigbee connections, UWB (ultra wideband) connections, and other currently known or future known wireless connection methods.

[0020] In this embodiment, the glasses system clock is used as a unified time base to time-align positioning and inertial data from GNSS or vision-inertial fusion modules, power and heart rate data from power meters and heart rate sensors, and forward visual and ambient acoustic signals from cameras and microphones. Velocity is calculated from the position change and time difference within adjacent sampling periods, with the displacement increment being the path length increment for that period. If necessary, inertial data is used to perform short-term smoothing of the velocity to suppress urban environmental jitter. Traffic signal status is determined based on forward visual and ambient acoustic signals: the visual side classifies video frames as red / non-red and outputs confidence levels; the acoustic side uses low-frequency energy distribution and steady-state noise patterns as auxiliary cues, outputting the traffic signal status when the confidence level meets a threshold. Power and heart rate are acquired at their respective sampling frequencies and interpolated to the system time base, thereby forming synchronized time-series data including velocity, displacement increment, power, heart rate, and traffic signal status.

[0021] Step S102: When the speed is lower than the first speed threshold and the displacement increment is lower than the first displacement threshold, and the traffic signal status is detected as red or the power is lower than the power threshold, it is determined to be a red light waiting segment.

[0022] In this embodiment, red light waiting periods are identified based on time-series data. Within a sliding time window, when the speed is lower than a first speed threshold and the displacement increment is lower than a first displacement threshold, and the traffic signal status is detected as red or the power is lower than a power threshold, it is considered that the waiting characteristics are met. To avoid misjudgment caused by instantaneous braking, the condition must be met for a preset stopping duration. The two basic thresholds are used to characterize the stationary characteristics where the distance is almost constant, while the traffic signal status or low power condition is used to characterize non-propelling behavior caused by a red light at an intersection. The combination of the two distinguishes red light waiting from situations such as slow uphill driving or congested traffic. The thresholds can be set according to equipment calibration or empirical values. For example, the first speed threshold can be on the order of 1 m / s, the first displacement threshold can be on the order of 1 m / sampling period, the power threshold can be 30 W or a certain proportion of the functional threshold power, and the stopping duration can be on the order of 3 s. However, these values ​​are only for implementation examples and do not limit the scope of protection.

[0023] Step S103: During the red light waiting period, pause the time accumulation in speed and pace calculations for this period, and independently record heart rate and power changes to characterize the recovery status.

[0024] In this embodiment, the time accumulation in speed and pace calculations is paused during this period, meaning this period is removed from the denominator of the average speed or pace calculation, while the original record of distance accumulation is maintained. This avoids systematic deviations in speed and pace caused by increased time while the distance remains constant. Simultaneously, heart rate and power changes during this period are recorded independently and continuously to characterize the recovery state. The recovery state is not limited to a single indicator, but typically includes at least the decrease in heart rate over time and whether power is at a low level close to rest. For ease of subsequent use, the start and end timestamps, duration, and corresponding heart rate and power sequences of this waiting period can be stored in the data structure, without changing the basic processing method of pausing time accumulation while retaining physiological change records.

[0025] Step S104: After the red light waiting period ends, the average speed, pace and training load indicators are corrected based on the travel data excluding the red light waiting period, and the individualized training intensity parameters are updated based on the recovery status data.

[0026] In this embodiment, when the red light waiting period ends—that is, when the aforementioned entry conditions are no longer met or the traffic signal status changes from red to non-red—the termination time of that period is locked, and training indicators are corrected and individualized training intensity parameters are updated accordingly. The training indicator correction recalculates the average speed and pace based on the travel data excluding the red light waiting period, ensuring that statistics reflect true propulsion efficiency. The training load indicator is also calculated based on travel data, thus avoiding interference from low or zero power during the waiting period on load assessment. The update of individualized training intensity parameters uses recovery status as input: for example, if the heart rate shows a sufficient decrease within a reasonable duration and power remains at a low level during the waiting period, it indicates good recovery, and the subsequent target intensity can be maintained or slightly increased; if the heart rate decrease is insufficient or recovery is slow, the subsequent target intensity is appropriately lowered or the target range is tightened. Updates can be implemented using threshold triggering or slightly limited weighted methods to ensure that parameter changes match the rider's current recovery ability and avoid excessive fluctuations.

[0027] The above processes can all run in real time on the glasses, completing data collection, red light waiting segment identification, statistical caliber adjustment, and parameter updates. The corrected average speed, pace, training load indicators, and prompts related to individualized training intensity parameters are then presented to the rider through the glasses interface. For example, the sampling period is 1 second, the first speed threshold is set to 1 m / s, the first displacement threshold is set to 1 m / cycle, the power threshold is set to 30 W, and the stop duration is 3 seconds. The rider waits at an intersection for 35 seconds, during which the speed and displacement increments are close to zero, the traffic light status is determined to be red, the average power is approximately 10 W, and the heart rate drops from 170 bpm to 154 bpm. The system removes this 35 seconds from the denominator of the speed and pace calculations, recalculates the average speed and pace based on the travel time, and uses the heart rate and power changes recorded during the waiting segment as the recovery state. If the heart rate drop is slightly lower than the preset target, the target intensity for subsequent intervals is slightly reduced, and a prompt is given to delay the start of high-intensity intervals. Therefore, under complex urban road conditions, it can simultaneously achieve accurate correction of performance statistics and individualized matching of training guidance, thus solving the problem of training data deviation and intensity setting mismatch caused by waiting at red lights.

[0028] This application accumulates and retains the recovery state during the pause time in the red light waiting period, and combines the correction of the riding data after the red light waiting period ends with the update of individualized training intensity parameters. This enables the accurate elimination of red light interference in urban roads and the effective use of physiological recovery information, making the average speed, pace and training load indicators closer to the actual driving performance, and matching the subsequent training intensity with the rider's current recovery ability, thereby improving the overall credibility of training data and the effectiveness of training guidance.

[0029] In some optional implementations of this embodiment, the step of determining a red light waiting segment when the speed is lower than a first speed threshold and the displacement increment is lower than a first displacement threshold, and the traffic signal status is detected as red or the power is lower than a power threshold, specifically includes: Within a sliding time window, if the speed is lower than the first speed threshold and the displacement increment is lower than the first displacement threshold, and at least two of the three types of signals (traffic signal status, power and heart rate behavior, and environmental acoustic characteristics) consistently point to the waiting state and the duration is not less than the stop duration threshold, then it is determined to enter the red light waiting segment. After entering, a freeze window is set. Within the freeze window, even if the instantaneous speed briefly exceeds the first speed threshold, the red light waiting state is maintained to suppress jitter misjudgment.

[0030] In this embodiment, the system aligns the time of each sensor channel with a unified time base. Within a sliding time window of, for example, 2–5 seconds, it calculates the ground speed and displacement increment in real time. When the speed remains below a first speed threshold and the displacement increment remains below a first displacement threshold, the "almost no movement" stationary characteristic is established. Simultaneously, it obtains at least two types of evidence consistently pointing to "waiting" from three types of signals, such as a red light traffic signal, power below a power threshold and no upward trend in heart rate, and low wind noise and steady-state vehicle-pedestrian noise in the ambient acoustics. If the above combined conditions consistently reach the stop duration threshold, it is confirmed as a red light waiting segment. To avoid frequent state reversals caused by instantaneous fluctuations during starting / stopping, a freeze window is set after entering the red light waiting segment. Within this window, even if the instantaneous speed briefly exceeds the first speed threshold, the red light waiting segment state is maintained. After the window ends, the system determines whether to exit based on the aforementioned combined conditions, thereby significantly reducing judgment jitter.

[0031] This application achieves high accuracy and stability in identifying red light waiting sections under complex road conditions by simultaneously employing static features of velocity and displacement, combined with at least two types of consistent evidence from traffic signal status, power and heart rate behavior, and environmental acoustic features, and by using a frozen window to suppress jitter. This significantly reduces misjudgments and frequent switching in scenarios such as uphill slow speeds, congested traffic, and starting and stopping.

[0032] In some optional implementations of this embodiment, the step of determining a red light waiting segment when the speed is lower than a first speed threshold and the displacement increment is lower than a first displacement threshold, and the traffic signal status is detected as red or the power is lower than a power threshold, further includes: The location coordinates of the current position are compared with a preset set of intersection areas. When the location coordinates are located in any intersection area and the traffic signal status is red, the effectiveness of the determination of the red light waiting segment is enhanced. When the location coordinates do not belong to any intersection area, at least one of the following conditions must be met simultaneously: speed and displacement conditions, as well as environmental acoustic or power behavior signals, in order to be determined as a red light waiting section.

[0033] In this embodiment, a set of intersection areas composed of polygons or buffer zones is pre-stored in the device. During each sampling period, the system compares the location coordinates with this set using a point-to-domain relationship. When the comparison result shows that the location is in any intersection area and the traffic signal status is identified as red, it indicates that the geographical scene matches the visual judgment, thereby enhancing the effectiveness of the joint judgment (e.g., no longer requiring additional corroboration from environmental acoustics or power behavior). Conversely, when the location coordinates are not in any intersection area, to avoid misjudging congestion or slow traffic as red light waiting, in addition to the static condition of speed and displacement, at least one corroborating condition indicating waiting must be met in environmental acoustic features or power and heart rate behavior before it can be determined that the location has entered a red light waiting segment. This comparison and differentiation threshold setting reliably distinguishes typical scenarios of being at an intersection with a red light from low-speed / stationary scenarios outside intersections, improving the overall accuracy and robustness of the judgment.

[0034] This application enhances the effectiveness of judgment in typical intersection red light scenarios by comparing the positioning coordinates with a preset set of intersection areas and linking them with traffic signal status. In non-intersection scenarios, it increases the strictness of entry conditions, balancing recall and accuracy. This further reduces the risk of non-intersection stationary or low-speed situations being misjudged as red light waiting sections, and improves overall robustness.

[0035] In some optional implementations of this embodiment, in the step of pausing the time accumulation in speed and pace calculation during the red light waiting period and independently recording heart rate and power changes to characterize the recovery state, the recovery state is parameterized as a recovery feature vector, which includes at least the heart rate decrease rate, the duration of the red light waiting period, and the average power during the red light waiting period. The recovery efficiency index is calculated based on the recovery feature vector. The recovery efficiency index is established by the ratio of the heart rate decrease to the duration of the decrease, and is normalized by combining the ratio of the mean power to the individual baseline power.

[0036] In this embodiment, the system continuously records the time series of heart rate and power within each time interval identified as a red light waiting period. It calculates the rate of heart rate decline over time using linear fitting or equivalent monotonicity constraints, while simultaneously accumulating the duration of the waiting period and calculating the average power during that period. These three factors together constitute the recovery feature vector. To facilitate subsequent quantitative use, a recovery efficiency index is established based on the ratio of the heart rate decline magnitude to the duration of the waiting period. This index is then normalized by combining the ratio of the average power during that period to the individual's baseline power (which can be estimated from the warm-up phase or historical data), ensuring the index falls within a comparable numerical range. This parameterized representation fully preserves the main physiological information of the recovery process while avoiding the bias caused by a single threshold.

[0037] This application parameterizes the recovery state into a recovery feature vector and calculates the recovery efficiency index, thereby enabling quantitative characterization and standardized comparison of the physiological recovery process during the red light waiting period. It retains key information such as the rate of heart rate decline, duration, and average power, while facilitating low-latency and low-computing-power driving of subsequent index corrections and individualized training intensity parameter updates, thus improving data utilization and online decision-making efficiency.

[0038] In some optional implementations of this embodiment, in the steps described above, after the red light waiting period ends, the average speed, pace, and training load indicators are corrected based on the travel data excluding the red light waiting period, and the individualized training intensity parameters are updated based on the recovery status data. Specifically, the individualized training intensity parameters are updated using a gated exponential weighting method, including: When the recovery efficiency index is below the lower threshold, the individualized training intensity parameter is reduced and the target power or target heart rate range for the next training interval is narrowed. When the recovery efficiency index is within the threshold range, the individualized training intensity parameter remains unchanged; When the recovery efficiency index is higher than the upper threshold, the individualized training intensity parameter is slightly increased under the safety limit constraint.

[0039] In this embodiment, the system calculates a recovery efficiency index at the end of each red light waiting period and compares it with preset upper and lower thresholds. When the index is below the lower threshold, it indicates insufficient recovery, so the individualized training intensity parameter is adjusted downwards and the target power or target heart rate range for the next training interval is correspondingly reduced. When the index is within the threshold range, it is considered that the current intensity matches the recovery capacity, and the parameter remains unchanged. When the index is above the upper threshold, it indicates sufficient recovery, so the parameter is slightly adjusted upwards under a safety limit constraint. The index weighting is reflected in the weighted synthesis of historical parameters and the current adjustment amount to ensure smooth changes; the gating is reflected in allowing effective adjustments only when the parameters exceed the limit or enter the improvement range, thus balancing sensitivity and stability.

[0040] This application employs a gating index weighted update mechanism based on the recovery efficiency index to ensure that individualized training intensity parameters are adjusted in a controlled manner only when recovery is insufficient or sufficient. The update magnitude is smooth and controllable, avoiding parameter oscillations and over-response. This ensures that the target power or target heart rate range for the next training interval is consistent with the rider's immediate recovery level, thereby improving training safety and completion quality.

[0041] In some optional implementations of this embodiment, before the steps of correcting the average speed, pace, and training load indicators based on the travel data excluding the red light waiting period after the red light waiting period ends, and updating the individualized training intensity parameters based on the recovery status data, the method further includes: The time spent waiting at red lights will be included in the recovery time, but not in the advance time. The average speed, pace, and training load indicators are calculated during the advance time, and the recovery feature vector and recovery efficiency index are continuously accumulated during the recovery time. The start and end times and segment labels of the red light waiting segment are recorded in the data structure for use in training metric correction and individualized training intensity parameter updates.

[0042] In this embodiment, the system maintains two sets of parallel measurement axes. One is the advancement time axis, which only accumulates the effective time of non-red light waiting periods and calculates the average speed, pace, and training load indicators based on effective movement data. The other is the recovery time axis, which only accumulates the time of red light waiting periods and accumulates the recovery feature vector and recovery efficiency index of each period for physiological recovery assessment and subsequent parameter updates. Each red light waiting period records the start and end times, duration, and segment label in the data structure for segment retrieval and access during settlement statistics and parameter updates. By separating advancement time and recovery time, the interference of red light waiting on advancement indicators is eliminated, while the valuable information of the recovery process for training decisions is fully preserved.

[0043] This application distinguishes between advance time and recovery time and records the start and end boundaries and segment labels of the red light waiting segment in the data structure. This ensures that advance-related statistical indicators are calculated based solely on valid travel data and are not affected by the red light waiting segment. At the same time, the continuously accumulated recovery feature vector and recovery efficiency index are used for physiological evaluation, achieving consistency and traceability in statistical caliber, which facilitates subsequent analysis and verification.

[0044] In some optional implementations of this embodiment, the first speed threshold, the stop duration threshold, and the power threshold are dynamically adjusted based on the environmental conditions of the day and recent training records; When the traffic signal status is unavailable or its reliability is below a preset threshold, a conservative threshold combination of speed and displacement increment is used to maintain the red light waiting segment determination.

[0045] In this embodiment, without changing the threshold type and judgment logic, the system periodically analyzes the distribution characteristics of speed, displacement increment, and duration of several recent red light waiting segments and non-waiting segments, and makes small adaptive fine-tuning of the thresholds in combination with the noise level and sensor stability of the day. For example, the first speed threshold and power threshold are brought close to the robust quantiles of their empirical distributions, so that the entry conditions are neither too lenient nor too strict. When the traffic signal status is unavailable or its reliability is lower than the threshold due to lighting, obstruction, or other reasons, in order to maintain the conservatism and consistency of the algorithm, it temporarily does not rely on this type of signal, but adopts a stricter combination of speed and displacement increment (such as a lower speed threshold and a longer stop duration threshold) to maintain the red light waiting segment judgment capability. After the traffic signal status is restored to usable, it returns to the conventional multi-source consistency judgment path.

[0046] This application dynamically corrects the first speed threshold, the stop duration threshold, and the power threshold based on the environmental conditions of the day and recent training records. When the traffic signal status is unavailable, a conservative threshold combination is used to maintain the judgment. This adapts to external changes such as lighting, obstruction, and signal noise, taking into account both the risk of misjudgment and usability, and ensuring that the red light waiting segment recognition and training data correction process remains stable under different working conditions.

[0047] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing related hardware through computer-readable instructions. These computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, optical disk, or read-only memory (ROM), or random access memory (RAM).

[0048] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0049] Further reference Figure 2 As a response to the above Figure 1The implementation of the method shown in this application provides an embodiment of a cycling training data correction system based on cycling smart glasses. This system embodiment is similar to... Figure 1 Corresponding to the method embodiments shown, the system can be specifically applied to various electronic devices.

[0050] like Figure 2 As shown, the cycling training data correction system 200 based on cycling smart glasses described in this embodiment includes: a data acquisition module 201, a determination module 202, a recording module 203, and a correction module 204. Wherein: The acquisition module 201 is configured to acquire positioning, inertial, power and heart rate data, and combine them with forward vision and ambient acoustic signals to obtain time-series data including velocity, displacement increment, power, heart rate and traffic signal status. The determination module 202 is configured to determine a red light waiting segment when the speed is lower than a first speed threshold and the displacement increment is lower than a first displacement threshold, and the traffic signal status is detected as red or the power is lower than a power threshold. The recording module 203 is configured to pause the accumulation of time in speed and pace calculations during the red light waiting period and independently record heart rate and power changes to characterize the recovery status. The correction module 204 is configured to correct the average speed, pace and training load indicators based on the travel data excluding the red light waiting period after the red light waiting period ends, and update the individualized training intensity parameters based on the recovery status data.

[0051] The cycling training data correction system based on smart cycling glasses provided in this embodiment of the invention can realize all the processes of the cycling training data correction method based on smart cycling glasses in the above embodiments. The functions and technical effects of each module in the device are the same as those of the cycling training data correction method based on smart cycling glasses in the above embodiments, and will not be repeated here.

[0052] To address the aforementioned technical problems, embodiments of this application also provide a computer device. Please refer to [link / reference needed]. Figure 3 , Figure 3 This is a basic structural block diagram of the computer device in this embodiment.

[0053] The computer device 3 includes a memory 31, a processor 32, and a network interface 33 that are interconnected via a system bus. It should be noted that only the computer device 3 with components 31-33 is shown in the figure; however, it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively. Those skilled in the art will understand that the computer device described here is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0054] The computer device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device can interact with the user via a keyboard, mouse, remote control, touchpad, or voice control.

[0055] The memory 31 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 31 may be an internal storage unit of the computer device 3, such as the hard disk or memory of the computer device 3. In other embodiments, the memory 31 may also be an external storage device of the computer device 3, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 3. Of course, the memory 31 may include both the internal storage unit and its external storage device of the computer device 3. In this embodiment, the memory 31 is typically used to store the operating system and various application software installed on the computer device 3, such as computer-readable instructions for a cycling training data correction method based on cycling smart glasses. In addition, the memory 31 can also be used to temporarily store various types of data that have been output or will be output.

[0056] In some embodiments, the processor 32 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other data processing chip. The processor 32 is typically used to control the overall operation of the computer device 3. In this embodiment, the processor 32 is used to execute computer-readable instructions stored in the memory 31 or to process data, for example, to execute computer-readable instructions for the cycling training data correction method based on cycling smart glasses.

[0057] The network interface 33 may include a wireless network interface or a wired network interface, which is typically used to establish communication connections between the computer device 3 and other electronic devices.

[0058] This application also provides another embodiment, namely, providing a computer-readable storage medium storing computer-readable instructions that can be executed by at least one processor to cause the at least one processor to perform the steps of the cycling training data correction method based on cycling smart glasses as described above.

[0059] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0060] The above are merely preferred embodiments of this application and are not intended to limit this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for correcting cycling training data based on smart cycling glasses, characterized in that, Includes the following steps: Collect positioning, inertial, power, and heart rate data, and combine them with forward vision and ambient acoustic signals to obtain time-series data including velocity, displacement increment, power, heart rate, and traffic signal status; When the speed is lower than the first speed threshold and the displacement increment is lower than the first displacement threshold, and the traffic signal status is detected as red or the power is lower than the power threshold, it is determined to be a red light waiting segment; During the red light waiting period, the time accumulation in speed and pace calculations is paused, and heart rate and power changes are recorded independently to characterize the recovery status. After the red light waiting period ends, the average speed, pace, and training load indicators are adjusted based on the travel data excluding the red light waiting period, and the individualized training intensity parameters are updated based on the recovery status data.

2. The method for correcting cycling training data based on smart cycling glasses according to claim 1, characterized in that, The step of determining a red light waiting segment when the speed is lower than a first speed threshold, the displacement increment is lower than a first displacement threshold, and the traffic signal status is detected as red or the power is lower than a power threshold, specifically includes: Within a sliding time window, if the speed is lower than the first speed threshold and the displacement increment is lower than the first displacement threshold, and at least two of the three types of signals (traffic signal status, power and heart rate behavior, and environmental acoustic characteristics) consistently point to the waiting state and the duration is not less than the stop duration threshold, then it is determined to enter the red light waiting segment. After entering, a freeze window is set. Within the freeze window, even if the instantaneous speed briefly exceeds the first speed threshold, the red light waiting state is maintained to suppress jitter misjudgment.

3. The method for correcting cycling training data based on smart cycling glasses according to claim 2, characterized in that, The step of determining a red light waiting segment when the speed is lower than a first speed threshold, the displacement increment is lower than a first displacement threshold, and the traffic signal status is detected as red or the power is lower than a power threshold, further includes: The location coordinates of the current position are compared with a preset set of intersection areas. When the location coordinates are located in any intersection area and the traffic signal status is red, the effectiveness of the determination of the red light waiting segment is enhanced. When the location coordinates do not belong to any intersection area, at least one of the following conditions must be met simultaneously: speed and displacement conditions, as well as environmental acoustic or power behavior signals, in order to be determined as a red light waiting section.

4. The method for correcting cycling training data based on smart cycling glasses according to claim 1, characterized in that, In the step of pausing the time accumulation in speed and pace calculation during the red light waiting period and independently recording heart rate and power changes to characterize the recovery state, the recovery state is parameterized as a recovery feature vector, which includes at least the heart rate decrease rate, the duration of the red light waiting period, and the average power during the red light waiting period. The recovery efficiency index is calculated based on the recovery feature vector. The recovery efficiency index is established by the ratio of the heart rate decrease to the duration of the decrease, and is normalized by combining the ratio of the mean power to the individual baseline power.

5. The method for correcting cycling training data based on smart cycling glasses according to claim 1, characterized in that, In the step of correcting the average speed, pace, and training load indicators based on the travel data excluding the red light waiting period after the red light waiting period ends, and updating the individualized training intensity parameters based on the recovery status data, the individualized training intensity parameters are updated using a gated exponential weighting method, specifically including: When the recovery efficiency index is below the lower threshold, the individualized training intensity parameter is reduced and the target power or target heart rate range for the next training interval is narrowed. When the recovery efficiency index is within the threshold range, the individualized training intensity parameter remains unchanged; When the recovery efficiency index is higher than the upper threshold, the individualized training intensity parameter is slightly increased under the safety limit constraint.

6. The method for correcting cycling training data based on smart cycling glasses according to claim 5, characterized in that, Before the steps of correcting the average speed, pace, and training load indices based on the travel data excluding the red light waiting period after the red light waiting period ends, and updating the individualized training intensity parameters based on the recovery status data, the method further includes: The time spent waiting at red lights will be included in the recovery time, but not in the advance time. The average speed, pace, and training load indicators are calculated during the advance time, and the recovery feature vector and recovery efficiency index are continuously accumulated during the recovery time. The start and end times and segment labels of the red light waiting segment are recorded in the data structure for use in training metric correction and individualized training intensity parameter updates.

7. The method for correcting cycling training data based on smart cycling glasses according to claim 2, characterized in that, The first speed threshold, the stop duration threshold, and the power threshold are dynamically adjusted based on the environmental conditions of the day and recent training records; When the traffic signal status is unavailable or its reliability is below a preset threshold, a conservative threshold combination of speed and displacement increment is used to maintain the red light waiting segment determination.

8. A cycling training data correction system based on smart cycling glasses, characterized in that, include: The acquisition module is configured to acquire positioning, inertial, power, and heart rate data, and combine them with forward vision and ambient acoustic signals to obtain time-series data including velocity, displacement increment, power, heart rate, and traffic signal status. The determination module is configured to determine a red light waiting segment when the speed is lower than a first speed threshold and the displacement increment is lower than a first displacement threshold, and the traffic signal status is detected as red or the power is lower than a power threshold. The recording module is configured to pause the accumulation of time in speed and pace calculations during the red light waiting period and independently record heart rate and power changes to characterize the recovery status. The correction module is configured to correct the average speed, pace, and training load indices based on the travel data excluding the red light waiting period after the red light waiting period ends, and update the individualized training intensity parameters based on the recovery status data.

9. A computer device, characterized in that, The system includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor executes the computer-readable instructions to implement the steps of the cycling training data correction method based on cycling smart glasses as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the cycling training data correction method based on cycling smart glasses as described in any one of claims 1 to 7.

Images