METHOD AND APPARATUS FOR PREDICTING A RACE TIME

Abstract

A system and method for predicting and optimizing an athlete's race performance using a wearable device is disclosed. The method involves measuring intermediate times at predetermined distances utilizing an inertial sensor and/or positional sensor within the wearable device. A race profile, modeled as a non-linear function of time over distance, is retrieved from stored historical race data of multiple athletes. The system determines a predicted race time based on the retrieved race profile and real-time performance data, calculates a probability score indicating the likelihood of achieving a preset target time, and provides real-time feedback through the wearable device. The system further incorporates machine learning models to classify race profiles, refine predictions based on environmental conditions, and adapt pacing recommendations based on detected fatigue indicators. The method enables the athlete to optimize effort distribution and race strategy dynamically, improving performance outcomes through real-time analysis and adaptive recommendations.

Claims

1. A method for predicting and optimizing race performance of an athlete using a wearable device, the method comprising: measuring intermediate times at predetermined distances using an inertial sensor and/or positional sensor in the wearable device; retrieving a race profile, defined as a non-linear function of time over distance, based on stored historical data of previous races by multiple athletes; determining a race time prediction based on the retrieved race profile and current intermediate times; calculating a probability score indicating a likelihood of achieving a pre-set target time; and displaying on the wearable device at least one of: (i) the predicted race time, (ii) a probability of achieving a target time, or (iii) a pace adjustment recommendation.

2. A wearable device for predicting performance of an athlete, comprising: an inertial sensor and/or a positional sensor for detecting intermediate times during a race; a processing unit configured to retrieve a race profile as a non-linear function of time over distance; a memory module storing predefined race profiles derived from previous athletes' performance data; and a display interface configured to provide real-time feedback, including race time prediction, probability of meeting a target time, and pace adjustment recommendations.

3. A method for dynamically adjusting an athlete's race strategy based on real-time data, comprising: continuously measuring real-time physiological and positional data of an athlete during a race, including speed, heart rate, and stride length; classifying a race pattern of the athlete as one of multiple predefined race profiles; adjusting a recommended pace for the athlete and effort distribution based on deviations from the predefined race profile; and displaying an updated race time prediction based on the adjusted pace and real-time environmental conditions.

4. The method of claim 1, wherein the race profile retrieval is based on machine learning classification, using historical race data to predict a most likely performance pattern for the athlete.

5. The method of claim 1, further comprising automatically adjusting the recommended pace based on detected environmental factors such as temperature, humidity, or altitude.

6. The wearable device of claim 2, wherein the processing unit dynamically updates the race profile classification every predetermined distance to refine the accuracy of race time predictions.

7. The wearable device of claim 2, further comprising a haptic feedback module configured to provide real-time vibration alerts when the athlete exceeds or falls below an optimal pace range.

8. The method of claim 3, wherein the classification of an athlete's current race pattern is determined using a neural network model trained on historical race data.

9. The method of claim 1, wherein past training performance of the athlete is used as an additional input to refine race time prediction.

10. The method of claim 3, wherein the athlete is prompted to input a subjective fatigue level during the race, and this input is factored into the prediction model.

11. The wearable device of claim 2, wherein the display interface provides color-coded pacing alerts to indicate whether the athlete is on track, exceeding, or lagging behind an optimal pace.

12. The method of claim 1, further comprising the step of transmitting intermediate time data to a remote server for real-time performance tracking by coaches or trainers.

13. The method of claim 1, wherein the race profile selection process is adjusted based on race-specific factors, such as course elevation, expected weather conditions, or starting congestion.

14. The method of claim 3, wherein the optimal race strategy is adjusted based on detected fatigue indicators, including heart rate variability, declining stride efficiency, or cadence irregularities.

15. The wearable device of claim 2, further comprising a voice assistant module that provides real-time audio updates on race performance and strategy adjustments.

16. The method of claim 1, further comprising storing race data post-race for analysis and generating improved race profiles for future use.

17. The method of claim 3, further comprising dynamically adjusting the probability calculation model using reinforcement learning to improve accuracy over time.

18. The method of claim 1, wherein the recommended pace adjustment is displayed as a real-time range of speeds, with an optimal range highlighted for the athlete.

19. The method of claim 3, further comprising detecting and categorizing athlete stress levels based on heart rate trends and stride fluctuations.

20. The method of claim 1, wherein the wearable device is configured to recommend pre-race warm-up intensity based on historical training data of the athlete.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0062] The invention will be better understood with the aid of the description of an embodiment given by way of example and illustrated by the figures, in which:

[0063] FIG. 1 is a chart showing average running times over various common distances as a function of VO2max.

[0064] FIG. 2 shows a race profile t=f(d) for a good marathoner (top chart) and for a less good marathoner (bottom chart). The time is normalized so that all athletes finish the race in a normalized time=20.0

[0065] FIG. 3 shows 7 different race profiles. Each full line is made up of segments between average intermediate times measured for all athletes in each group. The dotted lines are binomial functions that best approximates each sequence of average intermediate values. The vertical axis indicates variations from the ideal race ran at constant speed, in percent.

[0066] FIG. 4 is an example of information displayed on a wearable device before a race.

[0067] FIG. 5 is an example of information displayed on a wearable device before a race after the entry of some basic data by the athlete.

[0068] FIG. 6 is an example of information displayed on a wearable device during a race, showing the predicted time at the end of the race.

[0069] FIG. 7 is an example of information displayed on a wearable device during a race, showing the current speed and indicating whether this speed is in a recommended range.

[0070] FIG. 8 is an example of information displayed on a wearable device during a race, showing the current instantaneous power developed by the athlete and indicating whether this power is in a recommended range.

[0071] FIG. 9 is an example of information displayed on a wearable device during a race, showing the current regularity of pace and indicating whether this regularity is in a recommended range.

[0072] FIG. 10 is an example of information displayed on a wearable device during a race, showing two parameters (here cadence and stride length) that could be varied within two ranges in order to run at a recommended pace.

[0073] FIG. 11 illustrates an example of possible wearable device according to the invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0074] FIG. 1 is a chart indicating the time needed by runners in order to run over a variety of common distances, as a function of their VO2max. Those charts are known as such and frequently used by many runners in order to determine the optimal pace. They don't consider the race profile, such as for example the deviations from the predicted time when a runner starts to fast or too slowly.

[0075] FIG. 2 shows two charts representing race profiles of one good group or athletes (top) and of one less good group of athletes (bottom). Race profiles from a large number of athletes are collected and grouped into clusters so as to define a limited number of race profiles. The grouping may be based on the relative difference between the expected time at the end of the race (and possibly at each intermediate time) and the actual time, in percent. A clustering system, such as for example a self-learning system, for example a neural network, trained with example races of runners, may be used. Alternatively, race profiles may be manually clustered in order to define a limited number of predefined race profiles.

[0076] The race profiles may be gender dependent. The race profiles may also be race dependent. For example, a race profile may be defined for the New York marathon, and a second race profile may be defined for the New York marathon.

[0077] The times are preferably normalized before the grouping. In the example, the times are normalized as a function of the expected race time, so that the time target for each athlete is a common value, 20 in this example. Therefore, a race profile can be computed from intermediate times of athletes of different levels but having similar relative deviations at each intermediate time. For example, two athletes targeting a race time of 2h30 and 5 hours respectively may both be assigned to a common race profile corresponding to fast starters. Race profiles are therefore independent of the level of the athlete.

[0078] Examples of race profiles are illustrated in FIG. 5, and may be stored as an array in a wearable device used by the athlete during a competition. Alternatively, or in addition, the races profiles may be converted in equations, such as for example polynomial equations, that approximate best the values measured in each group.

[0079] During a race, the processing unit in the athlete's device determines the actual current time at a plurality of distances measured with an inertial sensor or location system, and determines from those current times a predefined, standardized race profile that best matches the measured values.

[0080] Even if the standardized race profiles are level independent, the race profile assigned to an athlete depends on his level (such as for example his VO2max value, or an expected time previously indicated by or determined for the athlete). For example, an athlete who needs a given time to run the first kilometer may be assigned a race profile fast starter, while another athlete with a better level but running the first kilometer at the same speed might be assigned a different race profile, for example a race profile corresponding to slow starter.

[0081] The assignment of race profile may be changed during the race. For example, a runner might be classified as a fast starter after two kilometers, and as an average runner after ten kilometers (for example if he applied a correction).

[0082] The number of standardized race profiles may be higher at the end of the race than at the beginning.

[0083] The selected race profile may also depend on physiological measures of the athlete during the race. For example, the processing unit may detect that an athlete is exhausted after 30 kilometers and assign him a race profile grouping athletes exhausted after 30 kilometers. Alternatively, those measures are used as correction or ponderation of a previously selected race profile.

[0084] Other athlete-dependent parameters may be considered for this assignment, such as the athlete size, weight, age, gender, biomechanical and/or physiological parameters, etc.

[0085] Alternatively, or in addition, the device might also determine an optimal race profile for the athlete, in order to achieve a desired or best time. This optimal race profile might depend on the previously known level of the athlete. It might be adapted during the race, based on measured intermediate times. It might also depend on the race.

[0086] In addition, environmental parameters such as temperature, humidity, etc. could be retrieved from the Internet and considered and used for determining the optimal and/or current race profile.

[0087] Those environment-dependent parameters might be used for the selection of the current race profile the athlete is following. For example, the software in the wearable device might select a race profile corresponding to fast starters when the temperature is hot, even if the athlete is starting at a speed that would be considered normal under other weather conditions.

[0088] Those environment-dependent parameters might also be used for the selection of the optimal race profile the athlete should follow.

[0089] Some race profiles may be dependent on individual races. For example, a set of standard race profiles might be prepared for the New York marathon, and a different set of race profiles for the Berlin marathon. An athlete needs to indicate the race he is doing and the software in his wearable device will then select, after a few kilometers, one of the race profiles corresponding to this race that the athlete seems to follow, based on his level or expected end time and on his first intermediate times. Alternatively, the race is determined automatically, based for example on indication from a GPS and/or calendar.

[0090] In an embodiment of the invention, the predicted race profiles are determined during a race with a neuronal network or another self-learning structure. In this embodiment, parameters of the athlete such as his intermediate times, and possibly his level, target time, and/or physiological parameters such as pulse rate, instantaneous power, regularity, environmental parameters, etc., are input to a neuronal network or self-learning structure trained with corresponding parameters from previous races performed by another athlete. The neuronal network or self-learning structure outputs predicted race profiles for the current athlete, or information such as predicted next intermediate and end time, probability to achieve a given target, and/or instructions for adaptations of the pace.

[0091] FIG. 6 illustrates an example of possible wearable device 4 according to an embodiment of the invention. In this embodiment, the wearable comprises two components: an acceleration measuring device 3, and a user interface module 5. Both components may also be integrated in one device.

[0092] The acceleration measuring device 3 is preferably intended to be worn on the athlete's body. In the embodiment of FIG. 11, it is worn close or in fixed relation to the athlete centre of mass, for example on his torso or on his head. In another embodiment, it is worn on the wrist, on a shoe, in a headset. It comprises for example a 3-axis MEMS-based accelerometer, for measuring the accelerations of the athlete along three axis and his speed along the anteroposterior axis. The device 3 may also, optionally, include a 3-axis gyroscope. The device 3 may also include a positional receiver, such as a GPS, Glonass and/or Magellan receiver, for determining the position and speed of the athlete, and thus determining when intermediate times needs to be measured.

[0093] The acceleration measuring device 3 preferably also comprises a microprocessor unit, or a microcontroller, or a FPGA module, which can read the raw data from the accelerometer and perform some processing algorithms on these data, for example in order to filter noise.

[0094] The accelerations measured with the device 3 are preferably converted into accelerations of the athlete's centre of mass along the vertical, posterioanterior and mediolateral axis; for example, the vertical direction may be roughly determined during the flight phase as the only acceleration to which the athlete is exposed, while the posterioanterior direction is the main direction of progression in the horizontal plane.

[0095] The device 3 further preferably includes a wireless interface, such as a Bluetooth, ZigBee, WiFi or ANT interface, for transmitting the processed acceleration data to a remote device such as the user interface device 5, and for receiving commands from this remote device.

[0096] The user interface device 5 may be for example a wristwatch, a smartphone, a head-up display, a headset, etc. It also includes a processor for further processing the data received from the device 3, and for determining the above described various powers. A display and/or an audio interface can be used for presenting the power information to the athlete.

[0097] FIG. 4 illustrates an example of information displayed on the wearable device, for example on his wristwatch, smartphone or on a display of the acceleration measuring device. This information is displayed before the race and allows the athlete to select a distance (here a marathon), a specific race (here the New York marathon), and an objective for the race (here 3 h 30). Other parameters such an athlete level, weight, 10 age, gender etc. might be entered with this screen or retrieved from an athlete profile stored in the wearable device and previously entered or otherwise determined.

[0098] This display also indicates a probability that the given target (here 3 h 30) will be achieved. If this target is realistic and/or in line with the athlete level as indicated or determined with previous races (for example his VO2max), the probability will be 100%.

[0099] FIG. 5 illustrates another information displayed by the user's wearable device after the information of FIG. 4. It includes a summary of the previously entered information, as well as a recommendation. The recommendation might be generic and identical for all races, all distances and/or all runners. It might also be a recommendation specific for the user, for his target (for example your target is ambitious, we recommend to start at a pace of 12 km/h), and/or take physiological and/or environmental conditions into account (for example temperature will be warm. Drink enough before and during the race).

[0100] FIG. 6 illustrates an example of information displayed on the wearable device during the race. The software module has already collected a few intermediate times, as well as possibly other parameters, and determined a likely race profile the athlete is following. By extrapolating this profile, and possibly applying corrections depending on the parameters, the module estimates and indicates the predicted time at end of the race. The display might also indicate the current speed or pace of the athlete and indicate whether this speed/pace is the recommended range, too fast or too slow. The module might also indicate a probability that the previously indicated target (3 h 30) can still be achieved.

[0101] FIG. 7 illustrates another example of information displayed on the wearable device during the race, indicating the race time and the current pace of the athlete. The display preferably also indicates whether the athlete is too fast or too slow. In a preferred embodiment, the device displays a range of recommended pace on a scale, for example a range of recommended pace on a slider. The slider may display the current pace as a single value (here 15.2 km/h) and a range of recommended pace (for example here between 16.5 and 18.6 km/h). This recommended pace range might correspond to an optimal race profile for the specific athlete's level and/or for the specific race.

[0102] FIG. 8 illustrates another example of information displayed on the wearable device during the race, indicating the current instantaneous power developed by the athlete, his time and whether the power is in a displayed recommended range in order to achieve the target. Since the instantaneous power is directly related to energy, it has been found that managing power during a race, instead of managing speed, is a more efficient way of controlling his effort in order to achieve a target or, during a training session, to obtain the best possible training result.

[0103] FIG. 9 illustrates another example of information displayed on the wearable device during the race, indicating the current regularity of the athlete, his time and whether the regularity is in a recommended range that is displayed on the diagram. Regularity might be defined as the speed regularity.

[0104] It is also possible to compute and display one, or a plurality of parameters that the athlete could adjust in order to achieve an optimal pace. For example, the display could indicate the current stride length, and/or the current cadence, which both could be adjusted in order to change the pace of the athlete.

[0105] FIG. 10 shows an example of diagram showing both the current cadence (c) and stride length (sl) as well as a recommended range for those two parameters, in order to achieve a pace recommended for the athlete at the current distance of the race. This diagram could be computed and displayed on the device. Other widgets, including circular ones, could be considered.

[0106] Other parameters might be displayed during a race, with an indication whether the parameter is in the recommended range for a specific athlete and/or in order to achieve a time target.

[0107] The steps of the above described method might be executed by a processor in a wearable device of the athlete, or in a remote server. The processor might include a classifier module, for example a software classifier, in order to classify the current race profile. The classifier might use a self-learning structure, such as a neural network, which might be trained in a remote equipment.