A risk warning method for sports training injuries of athletes

Abstract

The present invention discloses a risk warning method for sports training injuries of athletes, which belongs to the field of sports risk warning technology and includes the following steps: S1: collecting limb movement information and limb movement trajectory of athletes in a sports training state, and determining the sports training information of the athletes in the sports training state; S2: pre-processing the collected sports training information of the athletes in the sports training state, and determining sports training characterization data of the athletes in the sports training state; S3: analyzing and evaluating the sports training characterization data of the athletes in the sports training state. The present invention solves the existing problem that it is impossible to provide timely risk warnings for sports training injuries of athletes, resulting in poor sports training effects of athletes. The present invention can provide timely risk warnings for sports training injuries of athletes, avoid injuries to athletes during sports training, facilitate the prevention of sports training injuries of athletes, and improve the sports training effects of athletes.

Description

Technical Field

[0001] The present invention relates to the technical field of sports risk warning, and in particular to a risk warning method for sports training injuries of athletes. Background Art

[0002] Sports training refers to planned sports activities organized under the guidance of coaches to improve the competitive ability and sports performance of athletes. It is an important part of competitive sports. The main participants in sports training are athletes and coaches, rather than general sports participants. It is an organized and planned activity process whose purpose is to improve the training level and lay the foundation for achieving sports results.

[0003] Chinese patent publication number CN106709235A discloses a method and device for processing sports training data. The method uses software to implement intelligent coaching, customizes sports training plans for users, and combines sports parameters and sports status data to increase the dimensionality of sports training data, greatly improving the accuracy of sports data processing, making sports training supervision more efficient and enhancing the user experience. However, the patent has the following drawbacks:

[0004] Existing athletes cannot provide timely risk warnings for sports training injuries during sports training, which makes athletes prone to injuries during sports training, is not conducive to the prevention of sports training injuries, and makes the sports training effect of athletes poor. Summary of the Invention

[0005] The purpose of the present invention is to provide a risk warning method for sports training injuries of athletes, which can provide timely risk warning for sports training injuries of athletes, avoid injuries to athletes during sports training, facilitate the prevention of sports training injuries of athletes, improve the sports training effect of athletes, and solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A method for early warning of sports training injury risks for athletes, comprising the following steps:

[0008] S1: collecting the limb movement information and limb movement trajectory of the athlete in the exercise training state in real time, and determining the exercise training information of the athlete in the exercise training state;

[0009] S2: pre-processing the collected sports training information of the athlete in the sports training state to determine sports training representation data of the athlete in the sports training state;

[0010] S3: Analyze and evaluate the sports training characterization data of the athlete in the sports training state, and determine a sports training analysis and evaluation result based on the sports training of the athlete;

[0011] S4: Conduct in-depth analysis on the sports training analysis and assessment results based on the sports training of athletes, determine a sports training injury risk warning method based on the sports training of athletes, and conduct risk warning for sports training injuries of athletes based on the sports training injury risk warning method.

[0012] Preferably, in S1, the exercise training information of the athlete in the exercise training state is determined, and the following operations are performed:

[0013] Based on high-definition cameras, the body movements of athletes in the state of exercise training are acquired in real time to determine the body movement information of athletes in the state of exercise training;

[0014] Based on the three-axis acceleration sensor and gyroscope, the limb movement of the athlete in the exercise training state is acquired in real time to determine the limb movement trajectory of the athlete in the exercise training state;

[0015] Based on the real-time acquired limb movement information and limb movement trajectory, the exercise training information of the athlete in the exercise training state is determined.

[0016] Preferably, the limb movements of the athlete in the exercise training state are acquired in real time based on a high-definition camera to determine the limb movement information of the athlete in the exercise training state, including:

[0017] Control high-definition cameras to collect real-time videos of athletes’ body movements;

[0018] Performing frame processing on the limb movement video to obtain a frame image corresponding to the limb movement video;

[0019] Segmenting the frame image into a background image and a limb image, and removing the background image to obtain a target limb image;

[0020] Performing grayscale processing on the target limb image to obtain a grayscale processed target limb image;

[0021] Extracting the grayscale value of each pixel block corresponding to the limb part in the target limb image after the grayscale processing;

[0022] The grayscale threshold is set using the grayscale value of each pixel block in the target limb image after the grayscale processing; wherein the grayscale threshold is obtained by the following formula:

[0023]

[0024] Among them, H y represents the grayscale threshold; H0 represents the preset grayscale threshold reference value; n represents the number of pixel blocks corresponding to the limb part in the target limb image; H i Represents the grayscale value of the i-th pixel block;

[0025] Adjusting the grayscale values of pixel blocks in the grayscale-processed target limb image that are higher than the grayscale threshold to a first target grayscale value, and adjusting the grayscale values of pixel blocks in the grayscale-processed target limb image that are lower than the grayscale threshold to a second target grayscale value, to obtain a preprocessed target limb image;

[0026] The processed target limb image is input into a convolutional neural network model with a motion recognition function to recognize the limb motion information of the limb, thereby obtaining the limb motion information of the athlete.

[0027] Preferably, the grayscale values of pixel blocks in the grayscale processed target limb image that are higher than the grayscale threshold are adjusted to a first target grayscale value, and the grayscale values of pixel blocks in the grayscale processed target limb image that are lower than the grayscale threshold are adjusted to a second target grayscale value, to obtain a preprocessed target limb image, comprising:

[0028] Extracting the grayscale value of each pixel block in the target limb image after the grayscale processing;

[0029] Extracting the grayscale threshold;

[0030] The first target grayscale value and the second target grayscale value are set using the grayscale value and the grayscale threshold of each pixel block in the target limb image after the grayscale processing; wherein the first target grayscale value and the second target grayscale value are obtained by the following formula:

[0031]

[0032]

[0033] Among them, H y01 and H y02 Respectively represent the first target grayscale value and the second target grayscale value; H y represents the grayscale threshold; H0 represents the preset grayscale threshold reference value; m1 represents the number of pixel blocks in the target limb image before grayscale processing whose grayscale values are higher than the preset grayscale threshold reference value; m2 represents the number of pixel blocks in the target limb image before grayscale processing whose grayscale values are not higher than the preset grayscale threshold reference value; H giThe grayscale value of the i-th pixel in the pixel block whose grayscale value in the target limb image before grayscale processing is higher than the preset grayscale threshold reference value; H di The grayscale value of the i-th pixel in the pixel block representing the target limb image before grayscale processing is not higher than the preset grayscale threshold reference value; H gp The average grayscale value of the pixel blocks in the target limb image before grayscale processing, whose grayscale values are higher than the preset grayscale threshold reference value; H dp The average grayscale value of the pixel blocks in the target limb image before grayscale processing is not higher than the preset grayscale threshold reference value;

[0034] Adjusting the grayscale values of pixel blocks in the grayscale-processed target limb image that are higher than the grayscale threshold to a first target grayscale value;

[0035] Adjusting the grayscale values of pixel blocks below the grayscale threshold in the grayscale-processed target limb image to a second target grayscale value;

[0036] When the grayscale values of all pixel blocks representing limb information of the target limb image are adjusted, the preprocessed target limb image is obtained.

[0037] Preferably, in S2, the collected sports training information of the athletes in the sports training state is pre-processed by performing the following operations:

[0038] Acquiring sports training information of athletes in sports training status;

[0039] Based on the sequential retrieval method, the sports training information of athletes in their sports training states is retrieved one by one;

[0040] Filtering out some sports training information that is not valuable for early warning of sports training injury risks for athletes from the sports training information;

[0041] Identify some sports training information that is valuable for early warning of sports training injury risks for athletes;

[0042] Based on the mutual exclusivity principle, the identified sports training information that is valuable for early warning of sports training injuries to athletes is grouped;

[0043] Sports training information groups with different attribute types are determined, and each sports training information group contains sports training information with the same attribute type.

[0044] Preferably, in S2, the collected sports training information of the athletes in the sports training state is pre-processed, and the following operations are further performed:

[0045] Acquire sports training information groups with different attribute types;

[0046] Based on the internal sorting method, the sports training information with the same attribute type stored in each sports training information group is uniformly sorted;

[0047] determining a sports training information set having an arranged order;

[0048] Extracting features from the sports training information set to determine sports training feature data;

[0049] Based on the edge computing method, edge computing is performed on the sports training feature data to determine the sports training representation data of the athletes in the sports training state.

[0050] Preferably, in S3, the sports training characterization data of the athlete in the sports training state is analyzed and evaluated, and the following operations are performed:

[0051] Acquiring sports training representation data of athletes in sports training status;

[0052] Based on the sports training representation data, indexing pre-set sports training standard data for analyzing and evaluating the sports training representation data;

[0053] Obtaining indexed pre-set sports training standard data for analyzing and evaluating sports training representation data, and extracting the sports training standard data;

[0054] Based on the sports training standard data, the sports training representation data is analyzed and evaluated to determine the sports training analysis and evaluation results based on the sports training of the athletes.

[0055] Preferably, in S3, the sports training analysis and evaluation results based on the sports training of the athlete are determined, and the following operations are performed:

[0056] Acquiring sports training representation data and sports training standard data;

[0057] Analyze and evaluate sports training representation data based on sports training standard data;

[0058] In the case where the sports training characterization data is within the sports training standard data range, the sports training analysis and assessment result based on the sports training of the athlete is determined to be that there is no risk of injury in the sports training of the athlete in the sports training state;

[0059] In the case where the sports training characterization data is not within the range of sports training standard data, the sports training analysis and assessment result based on the sports training of the athlete is determined to be that there is a risk of injury in the sports training of the athlete in the sports training state.

[0060] Preferably, in S4, the sports training analysis and evaluation results based on the sports training of the athletes are deeply mined and analyzed, and the following operations are performed:

[0061] Obtain sports training analysis and assessment results based on sports training of sports personnel;

[0062] Based on data mining technology, the results of sports training analysis and assessment based on sports personnel's sports training are deeply mined and analyzed to determine the causes of sports training injury risks based on sports personnel's sports training;

[0063] Based on the causes of sports training injury risks, a sports training injury risk warning method based on sports training for athletes is determined.

[0064] Preferably, in S4, a sports training injury risk warning method based on sports training of athletes is determined, and the following operations are performed:

[0065] Conduct in-depth analysis of the results of sports training analysis and assessment based on sports personnel's sports training;

[0066] In the case where there is no injury risk in sports training, the sports training injury risk warning method based on sports training of athletes is determined to be unnecessary for sports training injury risk warning of athletes:

[0067] In the case of injury risk during sports training, the sports training injury risk warning method based on sports training of athletes is determined to provide sports training injury risk warning to athletes, identify risk situations, and guide athletes to perform correct sports training to avoid sports training injuries.

[0068] Obtain a sports training injury risk warning method based on sports training of athletes, and provide risk warning for sports training injuries of athletes based on the sports training injury risk warning method.

[0069] Compared with the prior art, the present invention has the following beneficial effects:

[0070] The present invention determines the sports training information of the athletes in the sports training state by collecting limb movement information and limb movement trajectory of athletes in the sports training state in real time, pre-processes the collected sports training information of the athletes in the sports training state, determines sports training characterization data of the athletes in the sports training state, analyzes and evaluates the sports training characterization data of the athletes in the sports training state, determines sports training analysis and evaluation results based on the sports training of the athletes, conducts in-depth mining and analysis on the sports training analysis and evaluation results based on the sports training of the athletes, determines a sports training injury risk warning method based on the sports training of the athletes, and provides risk warning for sports training injuries of the athletes based on the sports training injury risk warning method. It can provide timely risk warning for sports training injuries of the athletes, avoid injuries to the athletes during sports training, be beneficial to the prevention of sports training injuries of the athletes, and improve the sports training effect of the athletes. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 This is a flow chart of the risk warning method for sports training injuries for athletes of the present invention;

[0072] Figure 2 This is an algorithm flow chart of the risk warning method for sports training injuries for athletes of the present invention. DETAILED DESCRIPTION

[0073] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0074] In order to solve the problem that athletes cannot receive timely risk warnings for sports training injuries during their current training, which makes athletes more susceptible to injuries during training, is not conducive to preventing sports training injuries, and results in poor training results, please refer to Figure 1-Figure 2 , this embodiment provides the following technical solutions:

[0075] A method for early warning of sports training injury risks for athletes, comprising the following steps:

[0076] S1: collecting the limb movement information and limb movement trajectory of the athlete in the exercise training state in real time, and determining the exercise training information of the athlete in the exercise training state;

[0077] In this embodiment, as a preferred technical solution of the present invention, in S1, the exercise training information of the athlete in the exercise training state is determined, and the following operations are performed:

[0078] Based on high-definition cameras, the body movements of athletes in the state of exercise training are acquired in real time to determine the body movement information of athletes in the state of exercise training;

[0079] Based on the three-axis acceleration sensor and gyroscope, the limb movement of the athlete in the exercise training state is acquired in real time to determine the limb movement trajectory of the athlete in the exercise training state;

[0080] Based on the real-time acquired limb movement information and limb movement trajectory, the exercise training information of the athlete in the exercise training state is determined.

[0081] By adopting the above technical solution, the limb movement information and limb movement trajectory of the athlete in the sports training state can be obtained through a high-definition camera, a three-axis acceleration sensor and a gyroscope. Based on the limb movement information and limb movement trajectory obtained in real time, the sports training information of the athlete in the sports training state can be determined, which is convenient for risk warning of sports training injuries to the athlete.

[0082] Specifically, based on the high-definition camera, the body movements of the athlete in the exercise training state are acquired in real time to determine the body movement information of the athlete in the exercise training state, including:

[0083] Control high-definition cameras to collect real-time videos of athletes’ body movements;

[0084] Performing frame processing on the limb movement video to obtain a frame image corresponding to the limb movement video;

[0085] Segmenting the frame image into a background image and a limb image, and removing the background image to obtain a target limb image;

[0086] Performing grayscale processing on the target limb image to obtain a grayscale processed target limb image;

[0087] Extracting the grayscale value of each pixel block corresponding to the limb part in the target limb image after the grayscale processing;

[0088] The grayscale threshold is set using the grayscale value of each pixel block in the target limb image after the grayscale processing; wherein the grayscale threshold is obtained by the following formula:

[0089]

[0090] Among them, H yrepresents the grayscale threshold; H0 represents the preset grayscale threshold reference value; n represents the number of pixel blocks corresponding to the limb part in the target limb image; H i Represents the grayscale value of the i-th pixel block;

[0091] Adjusting the grayscale values of pixel blocks in the grayscale-processed target limb image that are higher than the grayscale threshold to a first target grayscale value, and adjusting the grayscale values of pixel blocks in the grayscale-processed target limb image that are lower than the grayscale threshold to a second target grayscale value, to obtain a preprocessed target limb image;

[0092] The processed target limb image is input into a convolutional neural network model with a motion recognition function to recognize the limb motion information of the limb, thereby obtaining the limb motion information of the athlete.

[0093] The technical effect of the above technical solution is that by controlling a high-definition camera to capture real-time video of an athlete's limb movements and performing frame processing, image segmentation, and grayscale processing on it, the technical solution can obtain real-time information on the athlete's limb movements. This helps coaches and athletes to promptly understand the athlete's training status and make corresponding adjustments.

[0094] Accuracy: By pre-processing the target limb image using grayscale thresholds and identifying limb motion information using a convolutional neural network model with motion recognition capabilities, this technical solution can improve the accuracy of acquired limb motion information. This helps to more accurately assess the training effects of athletes and identify potential problems.

[0095] Automation: This technology reduces manual intervention and subjective judgment by automatically processing and analyzing body movement videos, improving the objectivity and consistency of data processing. This helps reduce human error and improve work efficiency.

[0096] Scalability: By utilizing a convolutional neural network model for action recognition, this technology can adapt to the needs of different athletes, sports, and training scenarios. This helps improve the system's adaptability and scalability.

[0097] Refinement: By segmenting the frame image into background and limb images, removing the background image to obtain the target limb image, and performing grayscale processing and analysis on the target limb image, this technical solution can capture and analyze the details of the athlete's limb movements in greater detail. This helps to more comprehensively understand the athlete's training status and identify potential problems.

[0098] Safety: By monitoring athletes' body movements in real time, this technology can help prevent and reduce sports injuries. Coaches and athletes can adjust training plans and methods based on this information to ensure athlete safety and health.

[0099] Specifically, the grayscale values of pixel blocks in the grayscale processed target limb image that are higher than the grayscale threshold are adjusted to a first target grayscale value, and the grayscale values of pixel blocks in the grayscale processed target limb image that are lower than the grayscale threshold are adjusted to a second target grayscale value, to obtain a preprocessed target limb image, including:

[0100] Extracting the grayscale value of each pixel block in the target limb image after the grayscale processing;

[0101] Extracting the grayscale threshold;

[0102] The first target grayscale value and the second target grayscale value are set using the grayscale value and the grayscale threshold of each pixel block in the target limb image after the grayscale processing; wherein the first target grayscale value and the second target grayscale value are obtained by the following formula:

[0103]

[0104]

[0105] Among them, H y01 and H y02 Respectively represent the first target grayscale value and the second target grayscale value; H y represents the grayscale threshold; H0 represents the preset grayscale threshold reference value; m1 represents the number of pixel blocks in the target limb image before grayscale processing whose grayscale values are higher than the preset grayscale threshold reference value; m2 represents the number of pixel blocks in the target limb image before grayscale processing whose grayscale values are not higher than the preset grayscale threshold reference value; H gi The grayscale value of the i-th pixel in the pixel block whose grayscale value in the target limb image before grayscale processing is higher than the preset grayscale threshold reference value; H di The grayscale value of the i-th pixel in the pixel block representing the target limb image before grayscale processing is not higher than the preset grayscale threshold reference value; H gp The average grayscale value of the pixel blocks in the target limb image before grayscale processing, whose grayscale values are higher than the preset grayscale threshold reference value; H dp The average grayscale value of the pixel blocks in the target limb image before grayscale processing is not higher than the preset grayscale threshold reference value;

[0106] Adjusting the grayscale values of pixel blocks in the grayscale-processed target limb image that are higher than the grayscale threshold to a first target grayscale value;

[0107] Adjusting the grayscale values of pixel blocks below the grayscale threshold in the grayscale-processed target limb image to a second target grayscale value;

[0108] When the grayscale values of all pixel blocks representing limb information of the target limb image are adjusted, the preprocessed target limb image is obtained.

[0109] The technical effect of the above technical solution is: enhancing image contrast: by adjusting the grayscale values of pixel blocks above the grayscale threshold in the grayscale processed target limb image to a first target grayscale value, and adjusting the grayscale values of pixel blocks below the grayscale threshold to a second target grayscale value, this technical solution can enhance image contrast. This helps better present the contours and details of limb movements.

[0110] Data reduction: This technology reduces the amount of image data by thresholding the image and adjusting the grayscale values of pixel blocks to two target grayscale values. This helps reduce the time and space required for data processing and improves processing efficiency.

[0111] Improved processing speed: By converting images into black and white binary images, this technology can reduce the computational complexity and time complexity of image processing. This helps increase processing speed and reduce latency.

[0112] Convenient for subsequent processing: By converting the image into a black and white binary image, this technical solution can facilitate subsequent image processing tasks.

[0113] Enhanced image stability: By adjusting the grayscale values of pixel blocks to two target grayscale values, this technology can reduce image noise and interference. This helps to enhance image stability and improve image quality.

[0114] Improved recognition accuracy: By converting images into black and white binary images, this technology can highlight the contours and details of body movements, thereby improving the accuracy of body movement recognition. This helps to more accurately identify the body movement information of athletes.

[0115] S2: pre-processing the collected sports training information of the athlete in the sports training state to determine sports training representation data of the athlete in the sports training state;

[0116] In this embodiment, as a preferred technical solution of the present invention, in S2, the collected sports training information of the athletes in the sports training state is pre-processed by performing the following operations:

[0117] Acquiring sports training information of athletes in sports training status;

[0118] Based on the sequential retrieval method, the sports training information of athletes in their sports training states is retrieved one by one;

[0119] Filtering out some sports training information that is not valuable for early warning of sports training injury risks for athletes from the sports training information;

[0120] Identify some sports training information that is valuable for early warning of sports training injury risks for athletes;

[0121] Based on the mutual exclusivity principle, the identified sports training information that is valuable for early warning of sports training injuries to athletes is grouped;

[0122] Determining sports training information groups with different attribute types, wherein each sports training information group stores sports training information with the same attribute type;

[0123] Based on the internal sorting method, the sports training information with the same attribute type stored in each sports training information group is uniformly sorted;

[0124] determining a sports training information set having an arranged order;

[0125] Extracting features from the sports training information set to determine sports training feature data;

[0126] Based on the edge computing method, edge computing is performed on the sports training feature data to determine the sports training representation data of the athletes in the sports training state.

[0127] By adopting the above-mentioned technical scheme, the sports training information of the athletes in the sports training state is obtained, and the sports training information of the athletes in the sports training state is retrieved one by one, and some sports training information that is valuable for the risk warning of sports training injuries to the athletes is determined, which can improve the processing efficiency of the sports training information. Based on the principle of mutual exclusivity, the determined part of the sports training information that is valuable for the risk warning of sports training injuries to the athletes is grouped, and sports training information groups with different attribute types are determined. The sports training information with the same attribute type stored in each sports training information group is uniformly sorted to determine a sports training information set with an arrangement order, and feature extraction is performed on the sports training information set to determine sports training feature data. Based on the edge computing method, edge computing is performed on the sports training feature data to determine the sports training representation data of the athletes in the sports training state, which facilitates the analysis and evaluation of the sports training representation data.

[0128] S3: Analyze and evaluate the sports training characterization data of the athlete in the sports training state, and determine a sports training analysis and evaluation result based on the sports training of the athlete;

[0129] In this embodiment, as a preferred technical solution of the present invention, in S3, the sports training characterization data of the athlete in the sports training state is analyzed and evaluated, and the following operations are performed:

[0130] Acquiring sports training representation data of athletes in sports training status;

[0131] Based on the sports training representation data, indexing pre-set sports training standard data for analyzing and evaluating the sports training representation data;

[0132] Obtaining indexed pre-set sports training standard data for analyzing and evaluating sports training representation data, and extracting the sports training standard data;

[0133] Based on the sports training standard data, the sports training representation data is analyzed and evaluated to determine the sports training analysis and evaluation results based on the sports training of the athletes.

[0134] In this embodiment, as a preferred technical solution of the present invention, in S3, the sports training analysis and evaluation results based on the sports training of the athlete are determined, and the following operations are performed:

[0135] Acquiring sports training representation data and sports training standard data;

[0136] Analyze and evaluate sports training representation data based on sports training standard data;

[0137] In the case where the sports training characterization data is within the sports training standard data range, the sports training analysis and assessment result based on the sports training of the athlete is determined to be that there is no risk of injury in the sports training of the athlete in the sports training state;

[0138] In the case where the sports training characterization data is not within the range of sports training standard data, the sports training analysis and assessment result based on the sports training of the athlete is determined to be that there is a risk of injury in the sports training of the athlete in the sports training state.

[0139] S4: Conduct in-depth analysis on the sports training analysis and assessment results based on the sports training of athletes, determine a sports training injury risk warning method based on the sports training of athletes, and conduct risk warning for sports training injuries of athletes based on the sports training injury risk warning method.

[0140] In this embodiment, as a preferred technical solution of the present invention, in S4, the sports training analysis and evaluation results based on the sports training of the athletes are deeply mined and analyzed, and the following operations are performed:

[0141] Obtain sports training analysis and assessment results based on sports training of sports personnel;

[0142] Based on data mining technology, the results of sports training analysis and assessment based on sports personnel's sports training are deeply mined and analyzed to determine the causes of sports training injury risks based on sports personnel's sports training;

[0143] Based on the causes of sports training injury risks, a sports training injury risk warning method based on sports training for athletes is determined.

[0144] In this embodiment, as a preferred technical solution of the present invention, in S4, a sports training injury risk warning method based on sports training of athletes is determined, and the following operations are performed:

[0145] Conduct in-depth analysis of the results of sports training analysis and assessment based on sports personnel's sports training;

[0146] In the case where there is no injury risk in sports training, the sports training injury risk warning method based on sports training of athletes is determined to be unnecessary for sports training injury risk warning of athletes:

[0147] In the case of injury risk during sports training, the sports training injury risk warning method based on sports training of athletes is determined to provide sports training injury risk warning to athletes, identify risk situations, and guide athletes to perform correct sports training to avoid sports training injuries.

[0148] Obtain a sports training injury risk warning method based on sports training of athletes, and provide risk warning for sports training injuries of athletes based on the sports training injury risk warning method.

[0149] Specifically, a risk warning method for sports training injuries of athletes is used to carry out risk warning for sports training injuries of athletes. The risk warning situation of sports training injuries of athletes is shown in Table 1:

[0150] Table 1: Risk warning of sports training injuries for athletes

[0151]

[0152] Therefore, the limb movement information and limb movement trajectory of the athletes in the sports training state are collected in real time, the sports training information of the athletes in the sports training state is determined, the collected sports training information of the athletes in the sports training state is preprocessed, the sports training representation data of the athletes in the sports training state is determined, the sports training representation data of the athletes in the sports training state is analyzed and evaluated, the sports training analysis and evaluation results based on the athletes' sports training are determined, the sports training analysis and evaluation results based on the athletes' sports training are deeply mined and analyzed, and a sports training injury risk warning method based on the athletes' sports training is determined. Based on the sports training injury risk warning method, risk warning of sports training injuries of athletes is carried out, which can provide timely risk warning of sports training injuries of athletes, avoid injuries of athletes during sports training, be beneficial to the prevention of sports training injuries of athletes, and improve the sports training effect of athletes.

[0153] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0154] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A risk warning method for sports training injuries of athletes, characterized in that: The following steps are involved: S1: collecting the limb movement information and limb movement trajectory of the athlete in the exercise training state in real time, and determining the exercise training information of the athlete in the exercise training state; S2: pre-processing the collected sports training information of the athlete in the sports training state to determine sports training representation data of the athlete in the sports training state; S3: Analyze and evaluate the sports training characterization data of the athlete in the sports training state, and determine a sports training analysis and evaluation result based on the sports training of the athlete; S4: Conduct in-depth mining and analysis on the sports training analysis and assessment results based on the sports training of athletes, determine a sports training injury risk warning method based on the sports training of athletes, and provide risk warning for sports training injuries of athletes based on the sports training injury risk warning method; The body movements of athletes in the state of exercise training are acquired in real time based on high-definition cameras to determine the body movement information of athletes in the state of exercise training, including: Control high-definition cameras to collect real-time videos of athletes’ body movements; Performing frame processing on the limb movement video to obtain a frame image corresponding to the limb movement video; Segmenting the frame image into a background image and a limb image, and removing the background image to obtain a target limb image; Performing grayscale processing on the target limb image to obtain a grayscale processed target limb image; Extracting the grayscale value of each pixel block corresponding to the limb part in the target limb image after the grayscale processing; The grayscale threshold is set using the grayscale value of each pixel block in the target limb image after the grayscale processing; wherein the grayscale threshold is obtained by the following formula: Among them, H y represents the grayscale threshold; H0 represents the preset grayscale threshold reference value; n represents the number of pixel blocks corresponding to the limb part in the target limb image; H i Represents the grayscale value of the i-th pixel block; Adjusting the grayscale values of pixel blocks in the grayscale-processed target limb image that are higher than the grayscale threshold to a first target grayscale value, and adjusting the grayscale values of pixel blocks in the grayscale-processed target limb image that are lower than the grayscale threshold to a second target grayscale value, to obtain a preprocessed target limb image; The processed target limb image is input into a convolutional neural network model with a motion recognition function to recognize the limb motion information of the limb, thereby obtaining the limb motion information of the athlete.

2. A risk warning method for sports training injuries of athletes according to claim 1, characterized in that: In S1, the exercise training information of the athlete in the exercise training state is determined, and the following operations are performed: Based on high-definition cameras, the body movements of athletes in the state of exercise training are acquired in real time to determine the body movement information of athletes in the state of exercise training; Based on the three-axis acceleration sensor and gyroscope, the limb movement of the athlete in the exercise training state is acquired in real time to determine the limb movement trajectory of the athlete in the exercise training state; Based on the real-time acquired limb movement information and limb movement trajectory, the exercise training information of the athlete in the exercise training state is determined.

3. The method for early warning of sports training injury risk for athletes according to claim 2, characterized in that: The method comprises: adjusting the grayscale values of pixel blocks in the grayscale processed target limb image that are higher than the grayscale threshold to a first target grayscale value, and adjusting the grayscale values of pixel blocks in the grayscale processed target limb image that are lower than the grayscale threshold to a second target grayscale value, to obtain a preprocessed target limb image, including: Extracting the grayscale value of each pixel block in the target limb image after the grayscale processing; Extracting the grayscale threshold; The first target grayscale value and the second target grayscale value are set using the grayscale value and the grayscale threshold of each pixel block in the target limb image after the grayscale processing; wherein the first target grayscale value and the second target grayscale value are obtained by the following formula: Among them, H y01 and H y02 Respectively represent the first target grayscale value and the second target grayscale value; H y represents the grayscale threshold; H0 represents the preset grayscale threshold reference value; m1 represents the number of pixel blocks in the target limb image before grayscale processing whose grayscale values are higher than the preset grayscale threshold reference value; m2 represents the number of pixel blocks in the target limb image before grayscale processing whose grayscale values are not higher than the preset grayscale threshold reference value; H gi The grayscale value of the i-th pixel in the pixel block whose grayscale value in the target limb image before grayscale processing is higher than the preset grayscale threshold reference value; H di The grayscale value of the i-th pixel in the pixel block representing the target limb image before grayscale processing is not higher than the preset grayscale threshold reference value; H gp The average grayscale value of the pixel blocks in the target limb image before grayscale processing, whose grayscale values are higher than the preset grayscale threshold reference value; H dp The average grayscale value of the pixel blocks in the target limb image before grayscale processing is not higher than the preset grayscale threshold reference value; Adjusting the grayscale values of pixel blocks in the grayscale-processed target limb image that are higher than the grayscale threshold to a first target grayscale value; Adjusting the grayscale values of pixel blocks below the grayscale threshold in the grayscale-processed target limb image to a second target grayscale value; When the grayscale values of all pixel blocks representing limb information of the target limb image are adjusted, the preprocessed target limb image is obtained.

4. The method for early warning of sports training injury risk for athletes according to claim 3, characterized in that: In S2, the collected sports training information of the athletes in the sports training state is pre-processed by performing the following operations: Acquiring sports training information of athletes in sports training status; Based on the sequential retrieval method, the sports training information of athletes in their sports training states is retrieved one by one; Filtering out some sports training information that is not valuable for early warning of sports training injury risks for athletes from the sports training information; Identify some sports training information that is valuable for early warning of sports training injury risks for athletes; Based on the mutual exclusivity principle, the identified sports training information that is valuable for early warning of sports training injuries to athletes is grouped; Sports training information groups with different attribute types are determined, and each sports training information group contains sports training information with the same attribute type.

5. The method for early warning of sports training injury risk for athletes according to claim 4, characterized in that: In S2, the collected sports training information of the athletes in the sports training state is pre-processed, and the following operations are further performed: Acquire sports training information groups with different attribute types; Based on the internal sorting method, the sports training information with the same attribute type stored in each sports training information group is uniformly sorted; determining a sports training information set having an arranged order; Extracting features from the sports training information set to determine sports training feature data; Based on the edge computing method, edge computing is performed on the sports training feature data to determine the sports training representation data of the athletes in the sports training state.

6. The method for early warning of sports training injury risk for athletes according to claim 5, characterized in that: In S3, the sports training characterization data of the athlete in the sports training state is analyzed and evaluated, and the following operations are performed: Acquiring sports training representation data of athletes in sports training status; Based on the sports training representation data, indexing pre-set sports training standard data for analyzing and evaluating the sports training representation data; Obtaining indexed pre-set sports training standard data for analyzing and evaluating sports training representation data, and extracting the sports training standard data; Based on the sports training standard data, the sports training representation data is analyzed and evaluated to determine the sports training analysis and evaluation results based on the sports training of the athletes.

7. The method for early warning of sports training injury risk for athletes according to claim 6, characterized in that: In S3, the sports training analysis and evaluation results based on the sports training of the athlete are determined, and the following operations are performed: Acquiring sports training representation data and sports training standard data; Analyze and evaluate sports training representation data based on sports training standard data; In the case where the sports training characterization data is within the sports training standard data range, the sports training analysis and assessment result based on the sports training of the athlete is determined to be that there is no risk of injury in the sports training of the athlete in the sports training state; In the case where the sports training characterization data is not within the range of sports training standard data, the sports training analysis and assessment result based on the sports training of the athlete is determined to be that there is a risk of injury in the sports training of the athlete in the sports training state.

8. The method for early warning of sports training injury risk for athletes according to claim 7, characterized in that: In S4, the sports training analysis and evaluation results based on the sports training of the athletes are deeply mined and analyzed, and the following operations are performed: Obtain sports training analysis and assessment results based on sports training of sports personnel; Based on data mining technology, the results of sports training analysis and assessment based on sports personnel's sports training are deeply mined and analyzed to determine the causes of sports training injury risks based on sports personnel's sports training; Based on the causes of sports training injury risks, a sports training injury risk warning method based on sports training for athletes is determined.

9. The method for early warning of sports training injury risk for athletes according to claim 8, characterized in that: In S4, a sports training injury risk warning method based on sports training of athletes is determined, and the following operations are performed: Conduct in-depth analysis of the results of sports training analysis and assessment based on sports personnel's sports training; In the case where there is no injury risk in sports training, the sports training injury risk warning method based on sports training of athletes is determined to be unnecessary for sports training injury risk warning of athletes: In the case of injury risk during sports training, the sports training injury risk warning method based on sports training of athletes is determined to provide sports training injury risk warning to athletes, identify risk situations, and guide athletes to perform correct sports training to avoid sports training injuries. Obtain a sports training injury risk warning method based on sports training of athletes, and provide risk warning for sports training injuries of athletes based on the sports training injury risk warning method.

Images