TWI807893B - Method and device for predicting sports performance, and computer readable storage medium - Google Patents

Abstract

Embodiments of the disclosure provide a method and device for predicting sports performance, and a computer readable storage medium. The method includes: collecting motion data of a user in a process of the user performing a specific action through a wearable device; and in response to determining that the motion data match an action characteristics of the specific action, predicting at least one athletic performance of the user performing at least one other action based on the motion data.

Description

Sports performance estimation method, device and computer-readable storage medium

The present invention relates to a motion detection technology, and in particular to a motion performance estimation method, device and computer-readable storage medium.

In modern society, it is quite common to use special equipment to detect motion of users. For example, in the prior art, a technical means has been proposed to let the user wear some measuring device to obtain the relevant motion data of the user through the motion detection element (such as an inertial measurement unit) in the measuring device.

However, in some situations, limited by venues or other factors, users may not be able to actually or frequently perform certain sports events or measure sports performance (eg 50-meter sprint, long jump) by themselves or easily. Therefore, if it is possible to design a technical solution that can predict the user's performance in other sports based on the exercise data of the user performing a certain sport, it should help to improve the convenience of motion detection. And the intensity and method of training can be adjusted at any time according to sports performance.

In view of this, the present invention provides a sports performance estimation method, device and computer-readable storage medium, which can be used to solve the above technical problems.

An embodiment of the present invention provides a method for estimating sports performance, which is suitable for a sports performance estimating device, comprising: collecting motion data of a user during a specific action through a wearable device; and estimating at least one sports performance of the user performing at least one other action based on the motion data in response to determining that the motion data conforms to the action characteristics of the specific action.

An embodiment of the present invention provides an exercise performance estimation device, which includes a storage circuit and a processor. The storage circuit stores a program code. The processor is coupled to the storage circuit, and accesses the program code to execute: collecting motion data of a user during performing a specific action through a wearable device; and predicting at least one motion performance of the user performing at least one other motion based on the motion data in response to determining that the motion data conforms to the motion characteristics of the specific motion.

An embodiment of the present invention provides a computer-readable storage medium. The computer-readable storage medium records an executable computer program, and the executable computer program is loaded by an exercise performance estimation device to perform the following steps: collecting exercise data of a user during the execution of a specific action through a wearable device; and estimating at least one exercise performance of the user performing at least one other action based on the exercise data in response to determining that the exercise data conforms to the action characteristics of the specific action.

100: Sports performance prediction device

102: storage circuit

104: Processor

301: user

399:Wearable devices

411~415: Acceleration change interval

421~426: Speed change interval

421a~426a: speed data

431~436: Displacement change interval

431a~436a: displacement data

510:First Linear Regression Model

520:Second Linear Regression Model

530: Third Linear Regression Model

PH1~PH5: Action stage

S210, S220: steps

FIG. 1 is a schematic diagram of a sports performance prediction device according to an embodiment of the present invention.

FIG. 2 is a flowchart of a method for estimating sports performance according to an embodiment of the present invention.

FIG. 3 is a schematic diagram illustrating a squat jump performed by a user according to an embodiment of the present invention.

FIG. 4A is exemplary acceleration data measured during a user performing a squat jump.

FIG. 4B is exemplary velocity data measured during a user performing a squat jump.

FIG. 4C is, for example, exemplary displacement data measured when the user performs a squat jump action.

FIG. 5A is a schematic diagram showing the regression relationship between the sports performance of the squat jump and the standing long jump according to the first embodiment of the present invention.

FIG. 5B is a schematic diagram of the regression relationship between the squat jump and the sports performance of the 50-meter sprint shown in FIG. 5A .

FIG. 5C is a schematic diagram of the regression relationship between the standing long jump action and the 50-meter sprint action shown in FIG. 5A and FIG. 5B .

Please refer to FIG. 1 , which is a schematic diagram of a sports performance estimation device according to an embodiment of the present invention. In different embodiments, the athletic performance prediction device 100 can be implemented as various smart devices and/or computer devices connected to a wearable device (such as a smart bracelet, a smart watch, a smart ring, sensors located on the wrist, palm or finger, or other similar wearable devices). In some embodiments, the athletic performance prediction device 100 can also be integrated with the aforementioned wearable device into the same device, but it is not limited thereto.

In FIG. 1 , an athletic performance prediction device 100 includes a storage circuit 102 and a processor 104 . The storage circuit 102 is, for example, any type of fixed or removable random access memory (Random Access Memory, RAM), read-only memory (Read-Only Memory, ROM), flash memory (Flash memory), hard disk or other similar devices or a combination of these devices, and can be used to record a plurality of program codes or modules.

The processor 104 is coupled to the storage circuit 102 and may be a general-purpose processor, a special-purpose processor, a conventional processor, a digital signal processor, multiple microprocessors, one or more microprocessors combined with a digital signal processor core, a controller, a microcontroller, an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or any other type of product. Body circuits, state machines, Advanced RISC Machine (ARM) based processors, and the like.

In the embodiment of the present invention, the processor 104 can access the modules and program codes recorded in the storage circuit 102 to implement the sports performance prediction method proposed by the present invention, and the details are described below.

Please refer to FIG. 2 , which is a flowchart of a method for estimating sports performance according to an embodiment of the present invention. The method of this embodiment can be executed by the sports performance estimation device 100 shown in FIG. 1 , and the details of each step in FIG. 2 will be described below with the components shown in FIG. 1 .

In step S210 , the processor 104 collects motion data of the user during a specific action through the wearable device. In different embodiments, the above-mentioned wearable device can be worn on different parts of the user's body in response to the specific motion considered. Moreover, the above-mentioned wearable device may be provided with a motion detection element (such as an inertial measurement unit), and the motion data measured by the motion detection element may be used as the motion data, but it is not limited thereto.

For ease of illustration, embodiments of the present invention assume that the specific motion considered is a counter movement jump (CMJ) motion. In this case, the aforementioned wearable device (such as a watch, bracelet or ring) can be worn on the user's hand accordingly, but is not limited thereto. In the embodiment of the present invention, in order to make the motion data measured from the user more accurate, the user can execute the squat jump action according to a specific principle upon request.

Please refer to FIG. 3 , which is a schematic diagram of a squat jump performed by a user according to an embodiment of the present invention. In FIG. 3 , the user 301 can wear the wearable device 399 on his hand (eg, wrist), and sequentially execute the five action stages PH1-PH5 shown in FIG. 3 to complete a squat jump action.

In the action phase PH1 (which can be understood as a static phase), the user 301 needs to raise his hands forward and remain still for several seconds, for example at least 2 seconds. In the action phase PH2 (which can be understood as the swinging down phase of one hand), the user 301 needs to swing his hand down/back, and at the same time squat down to prepare for jumping. In the action phase PH3 (which can be understood as a hand swinging up phase), the user 301 needs to swing his hand upwards/forwards to generate momentum to drive his body upwards. In the action phase PH4 (which can be understood as a stagnation phase), the user 301 can take off and stay in the air in response to the upward momentum generated in the action phase PH3. In the action phase PH5 (which can be understood as a landing phase), the user 301 can land and maintain the posture with hands raised for several seconds, for example at least 2 seconds.

In other embodiments, the user 301 can perform other corresponding action stages corresponding to the different specific actions considered, which is not limited to the aspect shown in FIG. 3 .

In an embodiment of the present invention, the wearable device 399 can measure corresponding motion data corresponding to the action phases PH1-PH5 shown in FIG. 3 , such as acceleration data, velocity data, and displacement data during the squat jump action performed by the user 301, but it is not limited thereto.

Please refer to FIG. 4A to FIG. 4C , wherein FIG. 4A is, for example, exemplary acceleration data measured during the user's squatting and jumping action, and FIG. 4B is, for example, exemplary velocity data measured during the user's squatting and jumping action, and FIG. 4C is, for example, exemplary displacement data measured during the user's squatting and jumping action.

In an embodiment of the present invention, after obtaining the acceleration data in FIG. 4A , the processor 104 may, for example, integrate the acceleration data in FIG. 4A (and corresponding filtering operation) to obtain the velocity data in Fig. 4B. In addition, the processor 104 can also integrate the velocity data in FIG. 4B to obtain the displacement data in FIG. 4C , but it is not limited thereto.

In an embodiment of the present invention, after obtaining the data shown in FIG. 4A , FIG. 4B and FIG. 4C , the processor 104 can determine whether the motion data conforms to the motion characteristics of the squat jumping motion.

In one embodiment, the processor 104 may include judging whether the acceleration data includes a specific acceleration change interval, whether the velocity data includes a specific speed change interval, and/or whether the displacement data includes a specific displacement change interval, so as to determine whether the motion data conforms to the action characteristics of the squat jumping action.

In the embodiment of the present invention, the considered specific acceleration change interval may sequentially include, for example, a first acceleration change interval, a second acceleration change interval, a third acceleration change interval, a fourth acceleration change interval and a fifth acceleration change interval. In one embodiment, the average value and standard deviation of the acceleration data in the first acceleration change interval are smaller than the corresponding average value threshold (for example, 0.5g, where g is the gravitational acceleration) and standard deviation threshold (for example, 0.1g). The acceleration data in the second acceleration change interval includes at least the first acceleration data lower than the first acceleration threshold value (eg -25m/s^2). The acceleration data in the third acceleration change interval includes at least second acceleration data lower than the second acceleration threshold value (eg -125m/s^2). The acceleration data in the fifth acceleration change interval includes at least third acceleration data higher than a third acceleration threshold value (for example, 25m/s^2).

In an embodiment of the present invention, the first, second, third, fourth and The fifth acceleration change interval can be understood as corresponding to the static stage, the hand down stage, the hand up stage, the stagnation stage and the landing stage, respectively. That is, if the user 301 has correctly performed the squat jump action according to the process shown in FIG. 3 , the measured acceleration data will correspondingly include the above-mentioned first, second, third E, fourth and fifth acceleration change intervals in sequence.

In FIG. 4A , the acceleration data shown can be divided into acceleration change intervals 411 - 415 . It can be seen from FIG. 4A that the average value and standard deviation of the acceleration data in the acceleration change interval 411 are respectively less than the corresponding average value threshold value (for example, 0.5g, g is the acceleration of gravity) and the standard deviation threshold value (for example, 0.1g); the acceleration data in the acceleration change interval 412 includes at least acceleration data lower than the first acceleration threshold value (for example, -25m/s^2). The acceleration data in the acceleration change interval 413 at least includes acceleration data lower than the second acceleration threshold value (eg -125m/s^2). The acceleration data in the acceleration variation interval 415 at least includes acceleration data higher than a third acceleration threshold (for example, 25 m/s^2). It can be seen that the acceleration change intervals 411 - 415 may respectively correspond to the above-mentioned first, second, third, fourth and fifth acceleration change intervals. In this case, the acceleration data in FIG. 4A may be determined to include a specific acceleration variation interval.

In another embodiment, the acceleration change interval only needs to consider the above-mentioned first acceleration change interval corresponding to the static stage, and consider the following specific speed change interval and specific displacement change interval to determine that the motion data conforms to the action characteristics of the squat jumping action

In an embodiment of the present invention, the specific speed variation interval considered is such as It may sequentially include a first speed change interval, a second speed change interval, a third speed change interval, a fourth speed change interval, a fifth speed change interval and a sixth speed change interval. In an embodiment, the speed data in the first speed change interval at least includes first speed data lower than a first speed threshold (eg -0.4m/s). The second speed change interval includes at least second speed data higher than a second speed threshold (for example, 0.5 m/s). The third speed range at least includes third speed data lower than a third speed threshold (eg -1m/s). The fourth speed change interval includes at least fourth speed data higher than a fourth speed threshold (for example, 1.5 m/s). The fifth speed change interval includes at least fifth speed data lower than a fifth speed threshold (for example, 0.25m/s). The sixth speed change interval includes at least sixth speed data higher than a sixth speed threshold (for example, 0.25m/s).

In the embodiment of the present invention, if the user 301 has correctly performed the squat jumping action according to the flow shown in FIG. 3 , the measured speed data will correspondingly include the above-mentioned first, second, third, fourth, fifth and sixth speed change intervals in sequence.

In FIG. 4B , the speed data shown can be divided into speed change intervals 421 - 426 . It can be seen from FIG. 4B that the speed variation interval 421 (corresponding to, for example, a trough) at least includes speed data 421 a lower than the first speed threshold (eg, −0.4 m/s). The speed change interval 422 (eg, a peak following the speed change interval 421 ) at least includes speed data 422 a higher than a second speed threshold (eg, 0.5 m/s). The speed change interval 423 (for example, a trough following the speed change interval 422 ) at least includes speed data 423 a lower than a third speed threshold (for example, −1 m/s). Speed change interval 424 (which is, for example, a peak following the speed change interval 423) At least speed data 424a higher than the fourth speed threshold (for example, 1.5m/s) is included. The speed change interval 425 (for example, a trough appearing after the speed change interval 424 ) at least includes speed data 425 a lower than a fifth speed threshold value (for example, 0.25 m/s). The speed change interval 426 (eg, a peak following the speed change interval 425 ) at least includes speed data 426 a higher than a sixth speed threshold (eg, 0.25 m/s). It can be seen that, the speed change intervals 421 - 426 may respectively correspond to the above-mentioned first, second, third, fourth, fifth and sixth speed change intervals. In this case, the speed data in FIG. 4B may be determined to include a certain speed change interval.

In an embodiment of the present invention, the considered specific displacement change interval may include, for example, the first displacement change interval, the second displacement change interval, the third displacement change interval, the fourth displacement change interval, the fifth displacement change interval, and the sixth displacement change interval. In an embodiment, the displacement data in the first displacement variation interval at least includes first displacement data lower than a first displacement threshold (eg, −0.1 m). The displacement data in the second displacement change interval includes at least second displacement data higher than the first displacement data. The displacement data in the third displacement change interval includes at least third displacement data lower than the first displacement data. The fourth displacement change interval includes at least fourth displacement data higher than the first displacement data. The fifth displacement variation interval includes at least fifth displacement data higher than the fourth displacement data. The sixth displacement change interval includes at least sixth displacement data lower than the fifth displacement data.

In the embodiment of the present invention, if the user 301 has correctly performed the squat jump action according to the process shown in FIG. 3 , the measured displacement data will correspondingly include the above-mentioned first, second, third, fourth, fifth and sixth displacement change intervals in sequence.

In FIG. 4C , the displacement data shown can be divided into displacement change intervals 431 - 436 . It can be seen from FIG. 4C that the displacement data in the displacement change interval 431 (for example, corresponding to a trough) includes at least displacement data 431 a lower than the first displacement threshold value (for example, −0.1 m). The displacement data in the displacement variation interval 432 (which corresponds to, for example, a peak following the displacement variation interval 431 ) at least includes displacement data 432a higher than the displacement data 431a. The displacement data in the displacement variation interval 433 (which corresponds to, for example, a trough following the displacement variation interval 432 ) at least includes displacement data 433 a lower than the displacement data 431 a. The displacement variation interval 434 (for example, corresponding to a peak following the displacement variation interval 433 ) at least includes displacement data 434 a higher than the displacement data 431 a. The displacement variation interval 435 (for example, corresponding to a peak appearing after the displacement variation interval 434 ) at least includes displacement data 435 a higher than the displacement data 434 a. The displacement variation interval 436 (eg, corresponding to a trough following the displacement variation interval 435 ) at least includes displacement data 436 a lower than the displacement data 435 a. It can be seen that the displacement variation intervals 431 to 436 may respectively correspond to the above-mentioned first, second, third, fourth, fifth and sixth displacement variation intervals. In this case, the displacement data in FIG. 4C may be determined to include a specific displacement variation interval.

In one embodiment, in response to determining that the acceleration data includes the above-mentioned specific acceleration change interval, the velocity data includes the above-mentioned specific speed change interval, and the displacement data includes the above-mentioned specific displacement change interval, the processor 104 may accordingly determine that the above-mentioned motion data conforms to the action characteristics of the squat jump action, otherwise, it may determine that the above-mentioned motion data does not conform to the action characteristics of the squat jump action, but it is not limited thereto.

In step S220, in response to determining that the motion data conforms to a specific action (for example The processor 104 predicts at least one movement performance of the user 301 performing at least one other movement based on the movement characteristics such as the squat jump movement.

In the first embodiment, other movements considered include, for example, standing long jump (SLJ) movements, but are not limited thereto. In this case, the processor 104 may, for example, determine the jump height of the squat jump performed by the user 301 based on the motion data.

For example, after obtaining the displacement data in FIG. 4C , the processor 104 may, for example, know the jump height (indicated by H1) of the user 301 performing the squat jump action based on the difference between the displacement data 435a (for example, corresponding to the highest point of the air stage) and the displacement data 436a (for example, corresponding to the landing stage), but it is not limited thereto.

After that, the processor 104 can obtain a first correlation between the squat jump and the standing long jump, and estimate the jumping distance (indicated by D1 ) of the user 301 performing the standing long jump based on the jump height H1 and the first correlation.

In the first embodiment, the first correlation between the squat jump action and the standing long jump action can be embodied as a regression relationship between the sports performance of the two actions.

Please refer to FIG. 5A , which is a schematic diagram of the regression relationship between the squat jumping motion and the standing long jump motion according to the first embodiment of the present invention.

In FIG. 5A , each data point shown may be, for example, corresponding to different users who belong to the same group as the user 301 (for example, belong to a certain age range, gender, etc.) or may be different users regardless of groups performing squat jumps and standing long jumps. In the first embodiment, the processor 104 can perform regression analysis on the data points in FIG. 5A to obtain the motion table of the squat jump and the standing long jump. The regressive relationship between the two is used as the first correlation mentioned above.

In the first embodiment, the above-mentioned first correlation can be characterized as a first linear regression model 510, which can have the form of "a*H1+b=D1", where a and b are regression coefficients, but not limited thereto. For example, in the scenario of Figure 5A, a is about 3.3858, and b is about 87.3836.

Based on this, after the jump height H1 is measured by the processor 104, it can be substituted into the first linear regression model 510 to estimate the jump distance D1.

In the second embodiment, in addition to the standing long jump action, other actions considered may also include a sprint action corresponding to a specified distance (eg, 50m) (hereinafter referred to as a 50-meter sprint), but it is not limited thereto. In this case, the processor 104 may, for example, obtain the second correlation between the squat jump, the standing long jump, and the 50-meter sprint. Afterwards, the processor 104 estimates the running time (referred to as T1 ) for the user 301 to complete the specified distance with the sprint action based on the jump height H1 , the jump distance D1 and the above-mentioned second correlation.

In the second embodiment, the processor 104 can first obtain the correlation between the squat jump action and the 50-meter sprint (which can be embodied as the regression relationship between the sports performance between the squat jump action and the 50-meter sprint action) and the correlation between the standing long jump action and the 50-meter sprint (which can be expressed as the regression relationship between the standing long jump action and the 50-meter sprint action), and then obtain the above-mentioned second correlation.

Please refer to Figure 5B and Figure 5C, wherein Figure 5B is a schematic diagram of the regression relationship between the squat jump action and the 50-meter sprint shown in Figure 5A, and Figure 5C is based on the standing long jump action and the 50-meter sprint shown in Figure 5A and Figure 5B Schematic diagram of the regression relationship between exercise performance.

In FIG. 5B , each data point shown may be, for example, corresponding to different users who belong to the same group as the user 301 or different users regardless of the group performing squat jumps and 50-meter sprints. In FIG. 5C , each data point shown corresponds to the sports performance of standing long jump and 50-meter sprint performed by different users who belong to the same group as user 301 or different users regardless of groups.

In the second embodiment, the processor 104 may perform regression analysis on the data points in FIG. 5B to obtain the regression relationship between the squat jumping action and the sports performance of the 50-meter sprint, which may be characterized as a second linear regression model 520 , for example. In addition, the processor 104 can perform regression analysis on the data points in FIG. 5C to obtain the regression relationship between the standing long jump action and the sports performance of the 50-meter sprint, which can be characterized as a third linear regression model 530 , for example.

In the second embodiment, for example, the processor 104 may perform multiple regression analysis based on the first, second, and third linear regression models 510 , 520 , and 530 to obtain the second correlation among the squat jump, the standing long jump, and the 50-meter sprint.

In the second embodiment, the above-mentioned second correlation can be characterized as a fourth linear regression model, and it can have the form of "c*H1+d*D1+e=T1", wherein c, d, e are regression coefficients, but not limited thereto. In the scenarios of Figures 5A and 5B, c is about -0.03586, d is about -0.0199, and e is about 12.9281.

In the third embodiment, the processor 104 can obtain the correlation between the squat jump action and the 50-meter sprint (which can be embodied as a regression relationship between the sports performance between the squat jump action and the 50-meter sprint action), so as to obtain the squat jump action and the 50-meter sprint A third correlation between runs, which can be characterized, for example, by the second linear regression model 520 described above.

Based on this, after the processor 104 measures the jump height H1 and estimates the jump distance D1, it can be substituted into the above-mentioned fourth linear regression model to estimate the running time T1. In another embodiment, it can also be substituted into the above-mentioned second linear regression model to estimate running time T1

In an embodiment of the present invention, the above-mentioned linear regression models for the correlation among the squat jump, the standing long jump and the 50-meter sprint can be respectively generated from the sports performance data of different groups of users. In another embodiment, the above-mentioned linear regression model can also be generated from the sports performance data of users regardless of groups.

In an embodiment of the present invention, the user can select a suitable group through the user interface, and the processor 104 can select the corresponding linear regression model according to the user's selection. In another embodiment, the processor 104 can automatically select a linear regression model suitable for the user according to the personal information input by the user in advance, such as but not limited to age, gender and other information.

Through experiments, the statistical error values of jumping distance D1 and running time T1 estimated by the present invention are both lower than 10%.

The invention further provides a computer-readable storage medium for implementing the sports performance estimation method. The computer-readable storage medium is comprised of a plurality of program instructions (eg, setup program instructions and deploy program instructions) implemented therein. These program instructions can be loaded into the athletic performance estimating device 100 and executed by the athletic performance estimating device 100, so as to perform the above-mentioned athletic performance estimating method and the athletic performance estimating device 100. Function.

To sum up, the embodiment of the present invention may be based on whether the user's motion data conforms to the motion characteristics of the considered specific motion (eg squat jump motion). If so, the embodiment of the present invention may further estimate the user's sports performance in performing other actions (such as standing long jump and/or 50-meter sprint) based on the above-mentioned exercise data. In this way, even if the user is unable to perform certain actions for some reason, the embodiment of the present invention can still predict the user's exercise performance of these unable to perform actions based on the user's exercise data in other actions, thereby improving the convenience and flexibility of motion detection.

Although the present invention has been disclosed as above with the embodiments, it is not intended to limit the present invention. Anyone with ordinary knowledge in the technical field may make some changes and modifications without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention should be defined by the scope of the appended patent application as the criterion.

S210, S220: steps

Claims (17)

A method for estimating sports performance, suitable for a device for estimating sports performance, comprising: Collecting motion data of a user during a specific movement through a wearable device; and In response to determining that the motion data conforms to the motion characteristics of the specific motion, at least one motion performance of the user performing at least one other motion is estimated based on the motion data. The method as claimed in claim 1, wherein the wearable device is worn on the user's hand. The method as described in claim 1, wherein the specific action is a squat jumping action, the motion data includes acceleration data, velocity data, and displacement data during the user's execution of the specific action, and the method further includes: In response to determining that the acceleration data includes a specific acceleration change interval, the velocity data includes a specific speed change interval, and the displacement data includes a specific displacement change interval, it is determined that the motion data conforms to the motion feature of the specific motion. The method as claimed in claim 3, wherein the specific acceleration change intervals include a first acceleration change interval; and an average value and a standard deviation of the acceleration data in the first acceleration change interval are respectively smaller than a corresponding average value threshold and a standard deviation threshold. The method as described in claim 3, wherein the specific speed change intervals include a first speed change interval, a second speed change interval, a third speed change interval, a fourth speed change interval, a fifth speed change interval and a sixth speed change interval; The speed data in the first speed change interval includes at least a first speed data lower than a first speed threshold value, the speed data in the second speed change interval includes at least a second speed data higher than a second speed threshold value, the speed data in the third speed change interval includes at least a third speed data lower than a third speed threshold value, the fourth speed change interval includes at least a fourth speed data higher than a fourth speed threshold value, the fifth speed change interval includes at least a fifth speed data lower than a fifth speed threshold value, and the sixth speed change interval includes at least one speed data. A sixth speed data higher than a sixth speed threshold. The method as described in claim 3, wherein the specific displacement change intervals include a first displacement change interval, a second displacement change interval, a third displacement change interval, a fourth displacement change interval, a fifth displacement change interval and a sixth displacement change interval; The displacement data in the first displacement variation interval includes at least a first displacement data lower than a first displacement threshold value, the displacement data in the second displacement variation interval includes at least a second displacement data higher than the first displacement data, the displacement data in the third displacement variation interval includes at least a third displacement data lower than the first displacement data, the fourth displacement variation interval includes at least a fourth displacement data higher than the first displacement data, the fifth displacement variation interval includes at least a fifth displacement data higher than the fourth displacement data, and the sixth displacement variation interval includes at least a sixth displacement data lower than the fifth displacement data. displacement data. The method according to claim 1, wherein the specific action is a squat jump action, the at least one other action includes a standing long jump action, and the step of estimating the at least one athletic performance of the user performing the at least one other action based on the exercise data includes: determining a jump height for the user to perform the squat jump action based on the motion data; obtaining a first correlation between the squat jump motion and the standing long jump motion; and A jump distance for the user to perform the standing long jump action is estimated based on the jump height and the first correlation. The method according to claim 7, wherein the at least one other action further comprises a sprint action corresponding to a specified distance, and the method further comprises: obtaining a second correlation between the squat jump motion, the standing long jump motion, and the sprint motion; and A running time for the user to complete the specified distance with the sprint action is estimated based on the jump height, the jump distance and the second correlation. A device for predicting sports performance, comprising: a storage circuit storing a program code; and A processor, coupled to the storage circuit, accesses the program code to execute: Collecting motion data of a user during a specific movement through a wearable device; and In response to determining that the motion data conforms to the motion characteristics of the specific motion, at least one motion performance of the user performing at least one other motion is estimated based on the motion data. The device as claimed in claim 9, wherein the wearable device is worn on the user's hand. The device as described in claim 9, wherein the specific action is a squat jumping action, the motion data includes acceleration data, velocity data, and displacement data during the user's execution of the specific action, and the processor further executes: In response to determining that the acceleration data includes a specific acceleration change interval, the velocity data includes a specific speed change interval, and the displacement data includes a specific displacement change interval, it is determined that the motion data conforms to the motion feature of the specific motion. The device as claimed in claim 11, wherein the specific acceleration change intervals include a first acceleration change interval; and an average value and a standard deviation of the acceleration data in the first acceleration change interval are respectively smaller than a corresponding average value threshold and a standard deviation threshold. The device as described in claim 11, wherein the specific speed change intervals include a first speed change interval, a second speed change interval, a third speed change interval, a fourth speed change interval, a fifth speed change interval and a sixth speed change interval; The speed data in the first speed change interval includes at least a first speed data lower than a first speed threshold value, the speed data in the second speed change interval includes at least a second speed data higher than a second speed threshold value, the speed data in the third speed change interval includes at least a third speed data lower than a third speed threshold value, the fourth speed change interval includes at least a fourth speed data higher than a fourth speed threshold value, the fifth speed change interval includes at least a fifth speed data lower than a fifth speed threshold value, and the sixth speed change interval includes at least a fifth speed data value lower than a fifth speed threshold value. A sixth speed data higher than a sixth speed threshold. The device as described in claim 11, wherein the specific displacement change intervals include a first displacement change interval, a second displacement change interval, a third displacement change interval, a fourth displacement change interval, a fifth displacement change interval and a sixth displacement change interval; The displacement data in the first displacement variation interval includes at least a first displacement data lower than a first displacement threshold value, the displacement data in the second displacement variation interval includes at least a second displacement data higher than the first displacement data, the displacement data in the third displacement variation interval includes at least a third displacement data lower than the first displacement data, the fourth displacement variation interval includes at least a fourth displacement data higher than the first displacement data, the fifth displacement variation interval includes at least a fifth displacement data higher than the fourth displacement data, and the sixth displacement variation interval includes at least a sixth displacement data lower than the fifth displacement data. displacement data. The device according to claim 9, wherein the specific action is a squat jump action, the at least one other action includes a standing long jump action, and the processor executes: determining a jump height for the user to perform the squat jump action based on the motion data; obtaining a first correlation between the squat jump motion and the standing long jump motion; and A jump distance for the user to perform the standing long jump action is estimated based on the jump height and the first correlation. The device according to claim 15, wherein the at least one other action further includes a sprint action corresponding to a specified distance, and the processor further executes: obtaining a second correlation between the squat jump motion, the standing long jump motion, and the sprint motion; and A running time for the user to complete the specified distance with the sprint action is estimated based on the jump height, the jump distance and the second correlation. A computer-readable storage medium, the computer-readable storage medium records an executable computer program, and the executable computer program is loaded by an exercise performance estimation device to perform the following steps: Collecting motion data of a user during a specific movement through a wearable device; and In response to determining that the motion data conforms to the motion characteristics of the specific motion, at least one motion performance of the user performing at least one other motion is estimated based on the motion data.

Images