A method and device for training cognitive information of football players

Abstract

The present application discloses a method and device for cognitive information training for soccer players. While a soccer player is watching a soccer training simulation video, the method obtains the player's eye movement index data and physiological characteristic data. Based on the player's eye movement index data and soccer training program information, actual training index data corresponding to different soccer training programs is established. The actual training index data is compared with preset reference index data to obtain comparison data. The physiological characteristic data is input into a preset SVM model to determine whether the player is in a state of attention and readiness. If the comparison data does not meet the preset training requirements and / or the player does not appear to be in a state of attention and readiness, the playback speed of the soccer training simulation video is adjusted to retrain the player. The above method enhances the training efficiency of soccer players.

Description

Technical Field

[0001] The present application relates to the field of cognitive training technology, and in particular to a method and equipment for cognitive information training of football players. Background Art

[0002] Skilled football players usually have a unique "sense of the ball" and "awareness" when facing complex game scenarios. Converted into a scientific expression method of cognitive information processing, skilled football players' attention focus, attention transfer methods and information integration processing patterns in complex game scenarios are quite different from those of unskilled football players.

[0003] Traditionally, football training mainly relies on real-life training on the field to acquire football confrontation skills. However, traditional training methods lack effective assessment and training methods for football players' "awareness" of action responses, resulting in slow improvement in training performance and a lack of training targets. Summary of the Invention

[0004] The embodiments of the present application provide a method and device for cognitive information training of football players, which are used to solve the following technical problems: traditional training methods lack effective evaluation and training methods for the "awareness" of football players' action responses, resulting in slow improvement in training performance and lack of training targets.

[0005] The embodiments of this application adopt the following technical solutions:

[0006] The present application provides a method for cognitive information training for soccer players. The method comprises: obtaining eye movement index data and physiological characteristic data of a soccer player to be trained while the soccer player to be trained watches a soccer training simulation video; wherein the eye movement index data includes at least one of gaze point information, gaze transfer trajectory, and gaze distribution ratio information; and the physiological characteristic data includes at least one of pupil dilation, heart rate, and heart rate variability; establishing actual training index data corresponding to different soccer training programs based on the eye movement index data and soccer training program information of the soccer player to be trained; comparing the actual training index data with preset reference index data to obtain comparison data; inputting the physiological characteristic data into a preset SVM model to determine whether the soccer player to be trained is in an attention readiness state; and if the comparison data does not meet preset training requirements and / or the soccer player to be trained does not appear in an attention readiness state, adjusting the playback speed of the soccer training simulation video to retrain the soccer player to be trained.

[0007] The embodiment of the present application uses artificial intelligence eye tracking technology to obtain eye movement index data of football trainees to be trained, combines it with the cognitive information of skilled football players, establishes reference index data, and compares the cognitive information of the trainees with the reference index data. In addition, the embodiment of the present application can train the trainees' attention preparation by obtaining the physiological characteristic data of football trainees to be trained. The embodiment of the present application enhances the efficiency and precise targeting of the "awareness" training of football players by actively compensating and prompting the parts that do not meet the standards. In addition, the embodiment of the present application solves the problem of the lack of objective and quantitative "awareness" training methods for football players by training the "awareness" of action responses of football players in a virtual environment.

[0008] In one implementation of the present application, actual training index data corresponding to different football training projects are established based on the eye movement index data of the football trainee to be trained and the football training project information, specifically including: establishing actual training index data corresponding to the long-range passing situation based on the gaze distribution ratio data in the eye movement index data; and establishing actual training index data corresponding to the competitive game situation based on the first gaze point information and the first gaze transfer trajectory in the eye movement index data; wherein the first gaze point information and the first gaze transfer trajectory are both related to the eye movement index data of the football trainee to be trained when watching a football competitive game simulation video; and establishing actual training index data corresponding to the dribbling attack situation based on the second reference gaze point information and the second gaze transfer trajectory in the eye movement index data; wherein the second gaze point information and the second gaze transfer trajectory are both related to the eye movement index data of the football trainee to be trained when watching a dribbling attack simulation video.

[0009] In one implementation of the present application, the actual training index data is compared with the preset reference index data to obtain comparison data, specifically including: comparing the actual training index data corresponding to the long-range passing situation with the preset reference index data corresponding to the long-range passing situation to obtain first comparison data; and comparing the actual training index data corresponding to the confrontation game situation with the preset reference index data corresponding to the confrontation game situation to obtain second comparison data; and comparing the actual training index data corresponding to the dribbling attack situation with the preset reference index data corresponding to the dribbling attack situation to obtain third comparison data.

[0010] In one implementation of the present application, actual training indicator data corresponding to the confrontation game situation is compared with preset reference indicator data corresponding to the confrontation game situation to obtain second comparison data, specifically including: obtaining a first random variable entropy value based on the actual training indicator data corresponding to the confrontation game situation and a preset function; comparing the first random variable entropy value with the first preset reference random variable entropy value to obtain second comparison data; wherein the first random variable entropy value is related to the gaze transfer trajectory corresponding to the football trainee to be trained when watching a football confrontation game simulation video.

[0011] In one implementation of the present application, actual training index data corresponding to the dribbling attack situation is compared with preset reference index data corresponding to the dribbling attack situation to obtain third comparison data, specifically including: obtaining a second random variable entropy value based on the actual training index data corresponding to the dribbling attack situation and a preset function; comparing the second random variable entropy value with the second preset reference random variable entropy value to obtain third comparison data; wherein the second random variable entropy value is related to the gaze transfer trajectory corresponding to the football trainee to be trained when watching the dribbling attack simulation video.

[0012] In one implementation of the present application, before obtaining the eye movement index data and physiological characteristic data of the football trainees to be trained when they watch a football training simulation video, the method further includes: when the sample football players watch a football game simulation video, obtaining the reference physiological characteristic data of the sample football players when a sudden change in the situation occurs in the simulation video; determining the attention readiness corresponding to the sample football players when a sudden change in the situation occurs in the simulation video; wherein the attention readiness is related to whether the sample football players have an action response; using the reference physiological characteristic time series distribution within a preset time period as input, and using a binary classification variable of whether the sample football players have attention preparation as output, to train the preset classification model to obtain a preset SVM model.

[0013] In one implementation of the present application, physiological characteristic data is input into a preset SVM model to determine whether the football student to be trained is in an attention readiness state, specifically including: determining the physiological characteristic time series distribution corresponding to the physiological characteristic data within a preset time period; inputting the physiological characteristic time series distribution into the preset SVM model; and classifying the physiological characteristic time series distribution through the preset SVM model to output the attention readiness state corresponding to the football student to be trained.

[0014] In one implementation of the present application, when the comparison data does not meet the preset training requirements and / or the football trainee to be trained does not show an attention and readiness state, the playback speed of the football game simulation video is adjusted to retrain the football trainee to be trained, specifically including: when the comparison data does not meet the preset training requirements, based on the gaze point information corresponding to the football trainee to be trained, determining the reference video image area, marking the reference video image area, and reducing the playback speed of the marked video to retrain the football trainee to be trained; and / or when the football trainee to be trained does not show an attention and readiness state, reminding the training football trainee through the preset display screen, and reducing the playback speed of the current simulation video to retrain the football trainee to be trained.

[0015] In one implementation of the present application, after re-training the football trainee, the method further includes: re-acquiring comparison data until the comparison data meets the preset training requirements, eliminating the annotation to complete the current training; and / or re-acquiring the physiological characteristic data of the football trainee corresponding to the speed-adjusted simulation video, and re-inputting the physiological characteristic data into the preset SVM model, and when the preset SVM model outputs attention preparation, eliminating the reminder information on the preset display screen to complete the current training.

[0016] An embodiment of the present application provides a cognitive information training device for football players, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so as to enable the at least one processor to: obtain eye movement index data and physiological characteristic data of the football student to be trained while the football student to be trained watches a football game simulation video; wherein the eye movement index data includes at least one of gaze point information, gaze transfer trajectory, and gaze distribution ratio information; and the physiological characteristic data includes at least one of pupil dilation degree, heart rate, and heart rate variability; based on the eye movement index data and football training program information of the football student to be trained, establishing actual training index data corresponding to different football training programs; comparing the actual training index data with preset reference index data to obtain comparison data; inputting the physiological characteristic data into a preset SVM model to determine whether the football student to be trained is in an attention readiness state; and if the comparison data does not meet the preset training requirements and / or the football student to be trained does not appear in an attention readiness state, adjusting the playback speed of the football game simulation video to retrain the football student to be trained.

[0017] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: the embodiments of the present application use artificial intelligence eye tracking technology to obtain eye movement index data of football trainees to be trained, combine it with the cognitive information of skilled football players, establish reference index data, and compare the cognitive information of the trainees with the reference index data. In addition, the embodiments of the present application can train the trainees' attention preparation by obtaining the physiological characteristic data of football trainees to be trained. The embodiments of the present application enhance the efficiency and precise targeting of the "awareness" training of football players by actively paying attention to and prompting the parts that do not meet the standards. In addition, the embodiments of the present application solve the problem of the lack of objective and quantitative "awareness" training methods for football players by training the "awareness" of action responses of football players in a virtual environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments described in the present application. For those skilled in the art, other drawings can be obtained based on these drawings without inventive work. In the drawings:

[0019] Figure 1 A flowchart of a method for cognitive information training for football players provided in an embodiment of the present application;

[0020] Figure 2 This is a structural diagram of a soccer player cognitive information training device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] The embodiments of the present application provide a method and device for cognitive information training of football players.

[0022] In order to enable those skilled in the art to better understand the technical solutions in this application, the following will clearly and completely describe the technical solutions in the embodiments of this application in conjunction with the drawings in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0023] Skilled football players usually have a unique "sense of the ball" and "awareness" when facing complex game scenarios. Converted into a scientific expression method of cognitive information processing, skilled football players pay attention to key points, attention transfer methods and information integration processing patterns when processing complex game scenarios, which are quite different from those of unskilled football players.

[0024] Traditionally, football training mainly relies on real-life training on the field to acquire football confrontation skills. However, traditional training methods lack effective assessment and training methods for football players' "awareness" of action responses, resulting in slow improvement in training performance and a lack of training targets.

[0025] In order to solve the above problems, the embodiment of the present application provides a method and equipment for cognitive information training of football players. Through artificial intelligence eye tracking technology, the eye movement index data of the football trainee to be trained is obtained, and the reference index data is established in combination with the cognitive information of skilled football players, and the cognitive information of the trainee is compared with the reference index data. In addition, the embodiment of the present application can train the trainee's attention preparation by obtaining the physiological characteristic data of the football trainee to be trained. The embodiment of the present application enhances the efficiency and precise targeting of the "awareness" training of football players by actively paying attention to and prompting the parts that do not meet the standards. In addition, the embodiment of the present application solves the problem of the lack of objective and quantitative "awareness" training methods for football players by training the "awareness" of action responses of football players in a virtual environment.

[0026] The technical solutions proposed in the embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0027] Figure 1 This is a flow chart of a method for training football players’ cognitive information provided in the embodiment of the present application. Figure 1 As shown, the football player cognitive information training method includes the following steps:

[0028] S101. When a football trainee to be trained watches a football training simulation video, eye movement index data and physiological characteristic data of the football trainee to be trained are obtained.

[0029] In one embodiment of the present application, the football player cognitive information training device in the embodiment of the present application includes: a football attention information passive compensation auxiliary training system and a football attention readiness insufficient intelligent recognition system.

[0030] In one embodiment of the present application, in a football attention information passive compensation auxiliary training system, it is first necessary to obtain preset reference index data, and compare the preset reference index data with the index data of the football student to be trained, so as to obtain the training effect of the football player to be trained, and adjust the playback speed of the simulation video used during training to achieve a better training effect on the football student to be trained.

[0031] Specifically, when obtaining the preset reference indicator data, multiple professional football players with many years of experience can be selected as subjects. For example, ten full-time football players from a provincial sports team with at least five years of training experience can be selected as subjects. Their attention distribution and attention shift characteristics during the game under simulated conditions can be collected as a training reference standard.

[0032] Furthermore, under simulated conditions, a set of simulated videos of the corresponding playing field and opponent scenes were played to the subjects. The videos were displayed using a VR helmet, and eye movement index data was collected using an eye tracker. The collected eye movement indicators included: gaze point, gaze transfer trajectory, and gaze distribution ratio. After multiple sets of experiments, the eye movement index data obtained were described as follows:

[0033] The gaze point (GP) refers to the area of the scene where the fovea of the eye stays for more than 1635ms.

[0034] The Saccadic Rail (SR) refers to the trajectory of the change from one fixation point (GP1) to another fixation point (GP2). There is no third fixation point between the two fixations. The line between the two fixations is the SR indicator.

[0035] The rate of gaze points (RoGP) refers to the distribution ratio of the gaze time length formed by two different groups of gaze points on the same scene image.

[0036] Furthermore, preset reference index data is established based on the collected eye movement index data. After measuring each of the 10 football players described in step 1 for 60 trials, a total of 600 valid data sets are obtained, and preset reference index data is established. The preset reference index data is described as follows:

[0037] Long-range pass: The proportion of peripheral vision attention allocation is greater than the opponent's attention allocation

[0038] RoGP edge >RoGP competioner

[0039] Adversarial game: A gaze shift occurs and a transfer trajectory SR appears, which is defined as a random variable x. The probability of occurrence of the random variable of the transfer is defined as the proportion of the variable to the total number of SRs that appear in the adversarial game process. The entropy of the random variable is defined as:

[0040]

[0041] The value range of H(x) is adaptively calculated. When it is higher than the value range, compensation occurs.

[0042] Attack with the ball: A gaze shift occurs and a transfer trajectory SR appears, which is defined as a random variable y. The probability of occurrence of the random variable of the transfer is defined as the proportion of the variable to the total number of SRs that appear during the attack with the ball. The entropy of the random variable is defined as:

[0043]

[0044] The value range of H(y) is adaptively calculated. When it is higher than this value range, compensation occurs.

[0045] In one embodiment of the present application, while a sample football player is watching a simulated football game video, reference physiological characteristic data of the sample football player is obtained when a sudden change in the situation occurs in the simulated video. The corresponding attention readiness of the sample football player in response to the sudden change in the situation in the simulated video is determined, where the attention readiness is related to whether the sample football player exhibits an action response. A preset classification model is trained using the time series distribution of the reference physiological characteristics within a preset time period as input and a binary variable indicating whether the sample football player exhibits attention readiness as output to obtain the preset SVM model.

[0046] Specifically, attention readiness refers to whether athletes can effectively and quickly identify sudden situations and orient their attention when sudden changes in the situation occur during football training. During the process of attention orientation, the degree of pupil dilation, heart rate, and heart rate variability indicators of football players will change.

[0047] In preliminary experiments, 10 soccer players were selected for a simulation experiment, each undergoing 30 trials. A dataset of 300 physiological activation patterns corresponding to the failure to generate effective attentional preparation was collected under these simulated scenarios. The dataset included features such as pupil dilation (PD), heart rate (HR), and heart rate variability (HRV). The time series distribution of these physiological characteristics during the 0-1567ms period between stimulus onset served as input data, and the output was a binary variable indicating whether attentional preparation was generated. The objective criterion for judgment was whether an action response occurred: no action response corresponded to "no attentional preparation," while a action response corresponded to "yes" attentional preparation.

[0048] The specific calculation model of the relationship between input and output is described as follows: Use the SVM model to establish the correlation between the input data PD, HR, HRV and the "yes" judgment, so as to minimize the loss function:

[0049]

[0050] 30 data were extracted from the training set for verification, and the discrimination accuracy of the classifier was higher than 92%.

[0051] In one embodiment of the present application, a soccer training simulation video is played for a soccer trainee, and eye movement indicator data and physiological characteristic data of the soccer trainee are obtained. The eye movement indicator data includes at least one of gaze point information, gaze shift trajectory, and gaze distribution ratio information, and the physiological characteristic data includes at least one of pupil dilation, heart rate, and heart rate variability. The obtained eye movement indicator data and physiological characteristic data are compared with preset reference indicator data to determine the training effect of the soccer trainee.

[0052] S102: Based on the eye movement index data of the football student to be trained and the football training program information, actual training index data corresponding to different football training programs are established.

[0053] In one embodiment of the present application, actual training indicator data corresponding to a long-range pass situation is established based on gaze distribution ratio data in the eye movement indicator data. Furthermore, actual training indicator data corresponding to a competitive game situation is established based on first gaze point information and a first gaze transfer trajectory in the eye movement indicator data, wherein both the first gaze point information and the first gaze transfer trajectory are related to the eye movement indicator data of a soccer player to be trained while watching a simulated soccer competitive game video. Furthermore, actual training indicator data corresponding to a dribbling attack situation is established based on second reference gaze point information and a second gaze transfer trajectory in the eye movement indicator data, wherein both the second gaze point information and the second gaze transfer trajectory are related to the eye movement indicator data of a soccer player to be trained while watching a simulated dribbling attack video.

[0054] Specifically, based on the preset reference indicator data, the eye movement indicator data of the football trainee to be trained is analyzed and processed to match the preset reference indicator data. Specifically, based on the eye movement indicator data of the football trainee to be trained, data corresponding to three situations: long-range passing, confrontation game, and dribbling attack is established.

[0055] S103: Compare the actual training index data with the preset reference index data to obtain comparison data.

[0056] In one embodiment of the present application, actual training indicator data corresponding to a long-range pass situation is compared with preset reference indicator data corresponding to the long-range pass situation to obtain first comparison data. Furthermore, actual training indicator data corresponding to a competitive game situation is compared with preset reference indicator data corresponding to the competitive game situation to obtain second comparison data. Furthermore, actual training indicator data corresponding to a dribbling offense situation is compared with preset reference indicator data corresponding to the dribbling offense situation to obtain third comparison data.

[0057] Furthermore, in the case of long-range passing, based on the gaze distribution ratio information of the football student to be trained, the gaze distribution ratio of the peripheral edge vision is obtained to be greater than the opponent's gaze distribution ratio, and the data is compared with the preset reference indicator data corresponding to the preset range passing situation to obtain the first comparison data.

[0058] Specifically, based on actual training indicator data corresponding to the competitive game and a preset function, a first random variable entropy value is obtained. The first random variable entropy value is compared with a first preset reference random variable entropy value to obtain second comparison data. The first random variable entropy value is correlated with the gaze shift trajectory of the soccer trainee while watching a simulated soccer competitive game video.

[0059] Specifically, based on actual training indicator data corresponding to a dribbling attack scenario and a preset function, a second random variable entropy value is obtained. The second random variable entropy value is compared with a second preset reference random variable entropy value to obtain third comparison data. The second random variable entropy value is correlated with the gaze shift trajectory of the soccer player being trained while watching a simulated dribbling attack video.

[0060] Based on preset functions

[0061]

[0062] During the competitive game and dribbling offense, each gaze shift and shift trajectory (SR) of the football student to be trained is defined as a random variable x. The probability of occurrence of this random variable is defined as the ratio of this variable to the total number of SRs that occur during the competitive game, thereby obtaining the entropy value of the random variable. The entropy value corresponding to the football student to be trained is compared with the entropy value in the preset reference indicator data to determine whether the current football student has met the training standard.

[0063] S104: Input the physiological characteristic data into a preset SVM model to determine whether the football student to be trained is in an attention readiness state.

[0064] In one embodiment of the present application, a physiological characteristic time series distribution corresponding to physiological characteristic data within a preset time period is determined. The physiological characteristic time series distribution is input into a preset SVM model. The preset SVM model classifies the physiological characteristic time series distribution to output an attention readiness state corresponding to the soccer student to be trained.

[0065] Specifically, after obtaining the physiological characteristic data of the soccer student to be trained, this data is input into a preset SVM model. Determining whether the soccer student is in a state of attentional readiness requires examining whether the student is in a state of attentional readiness within a short period of time after the onset of an emergency situation. Therefore, the preset SVM model determines whether attentional readiness is present within 0-1567ms after the onset of the stimulus.

[0066] It should be noted that the embodiment of the present application preferably determines whether attention preparation occurs within the time period of 0-1567ms. In application, the time period can be changed according to the actual training situation, and the embodiment of the present application does not impose any limitation on this.

[0067] S105. If the compared data does not meet the preset training requirements and / or the football student to be trained does not show an attention readiness state, the playback speed of the football training simulation video is adjusted to retrain the football student to be trained.

[0068] In one embodiment of the present application, if the comparison data does not meet the preset training requirements, a reference video image area is determined based on the gaze point information corresponding to the soccer student to be trained, and the reference video image area is marked. The playback speed of the marked video is reduced to allow the soccer student to be trained again. And / or if the soccer student to be trained does not show a state of attention and readiness, the soccer student is reminded via a preset display screen, and the playback speed of the current simulation video is reduced to allow the soccer student to be trained again.

[0069] Specifically, when a student's training data differs from the pre-set reference data during simulated training, the system automatically activates the attention enhancement mechanism, highlighting the areas of inattention and slowing down the simulated training video by 0.75 times to assist with training. The system then measures the student's proficiency. When the training data from the pre-set reference data for that training scenario no longer differs from the pre-set reference data, the highlight disappears, ending the training for that scenario and starting the next one.

[0070] Furthermore, a pre-trained classifier is used to determine whether attention preparation occurs 0-1567ms after the stimulus appears. When attention preparation does not occur, the system display prompts the football player and replays the simulation video at 0.75 times the speed to train the football player's attention preparation.

[0071] In one embodiment of the present application, the comparison data is reacquired until it meets the preset training requirements, at which point the annotation is removed to complete the current training. Furthermore, the physiological characteristic data of the soccer student to be trained corresponding to the speed-adjusted simulated video is reacquired and re-input into the preset SVM model. If the preset SVM model outputs a warning message indicating readiness, the reminder message on the preset display screen is removed to complete the current training.

[0072] Specifically, after slowing down the video playback speed, the eye movement index data and physiological characteristic data of the soccer players in training are re-acquired. The acquired eye movement index data is used to establish the actual training index data, which is then re-compared with the preset reference index data. The annotations in the video are removed when the error between the re-acquired data and the preset reference index data meets the preset error condition. Secondly, the acquired physiological characteristic data is re-input into the preset SVM model. If the preset SVM determines that the attention readiness state occurs 0-1567ms after the stimulus appears, the reminder message on the preset display screen is removed, and the current scene training is completed, and the next training session begins.

[0073] Figure 2 This is a schematic diagram of the structure of a soccer player cognitive information training device provided in an embodiment of the present application. Figure 2 As shown, the cognitive information training device for football players includes:

[0074] at least one processor; and,

[0075] a memory communicatively connected to the at least one processor; wherein,

[0076] The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to:

[0077] When a soccer student to be trained watches a soccer game simulation video, eye movement index data and physiological characteristic data of the soccer student to be trained are obtained; wherein the eye movement index data includes at least one of gaze point information, gaze transfer trajectory, and gaze distribution ratio information; and the physiological characteristic data includes at least one of pupil dilation degree, heart rate, and heart rate variability;

[0078] Based on the eye movement index data of the football student to be trained and the football training project information, establishing actual training index data corresponding to different football training projects;

[0079] Comparing the actual training index data with the preset reference index data to obtain comparison data;

[0080] Inputting the physiological characteristic data into a preset SVM model to determine whether the football student to be trained is in an attention readiness state;

[0081] When the comparison data does not meet the preset training requirements and / or the football student to be trained does not show an attention readiness state, the playback speed of the football game simulation video is adjusted to retrain the football student to be trained.

[0082] The various embodiments in this application are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the device, apparatus, and non-volatile computer storage medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simple. For relevant portions, refer to the descriptions of the method embodiments.

[0083] The foregoing description describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0084] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the embodiments of the present application may have various modifications and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for training football players' cognitive information, characterized in that: The method comprises: When the sample football players watch a football game simulation video, obtaining reference physiological characteristic data of the sample football players when a sudden change in the situation occurs in the simulation video; Determining the attention readiness of the sample football player when a sudden change in the situation occurs in the simulated video; wherein the attention readiness is related to whether the sample football player has an action response; When a soccer student to be trained watches a soccer training simulation video, eye movement index data and physiological characteristic data of the soccer student to be trained are obtained; wherein the eye movement index data includes at least one of gaze point information, gaze transfer trajectory, and gaze distribution ratio information; and the physiological characteristic data includes at least one of pupil dilation degree, heart rate, and heart rate variability; Establishing actual training indicator data corresponding to different football training items based on the eye movement indicator data of the football student to be trained and the football training item information, specifically including establishing actual training indicator data corresponding to long-range passing situations based on the gaze distribution ratio data in the eye movement indicator data; and Based on the first gaze point information and the first gaze transfer trajectory in the eye movement index data, actual training index data corresponding to the competitive game situation is established; wherein the first gaze point information and the first gaze transfer trajectory are both related to the eye movement index data of the football trainee to be trained when watching the football competitive game simulation video; and based on the second reference gaze point information and the second gaze transfer trajectory in the eye movement index data, actual training index data corresponding to the dribbling attack situation is established; wherein the second gaze point information and the second gaze transfer trajectory are both related to the eye movement index data of the football trainee to be trained when watching the dribbling attack simulation video; Comparing the actual training index data with the preset reference index data to obtain comparison data; Inputting the physiological characteristic data into a preset SVM model to determine whether the soccer student to be trained is in an attention readiness state, specifically comprising determining a physiological characteristic time series distribution corresponding to the physiological characteristic data within a preset time period; inputting the physiological characteristic time series distribution into the preset SVM model; and classifying the physiological characteristic time series distribution using the preset SVM model to output an attention readiness state corresponding to the soccer student to be trained; When the comparison data does not meet the preset training requirements and / or the football student to be trained does not show an attention readiness state, the playback speed of the football training simulation video is adjusted to re-train the football student to be trained. Specifically, when the comparison data does not meet the preset training requirements, a reference video image area is determined based on the gaze point information corresponding to the football student to be trained, the reference video image area is marked, and the playback speed of the marked video is reduced to re-train the football student to be trained.

2. A soccer player cognitive information training method according to claim 1, characterized in that: The comparing the actual training index data with the preset reference index data to obtain comparison data specifically includes: Comparing the actual training index data corresponding to the long-range pass situation with the preset reference index data corresponding to the long-range pass situation to obtain first comparison data; and Comparing the actual training indicator data corresponding to the adversarial game situation with the preset reference indicator data corresponding to the adversarial game situation to obtain second comparison data; and The actual training index data corresponding to the dribbling attack situation is compared with the preset reference index data corresponding to the dribbling attack situation to obtain third comparison data.

3. A soccer player cognitive information training method according to claim 2, characterized in that: The actual training indicator data corresponding to the confrontation game situation is compared with the preset reference indicator data corresponding to the confrontation game situation to obtain the second comparison data, specifically including: Obtaining an entropy value of a first random variable based on actual training indicator data corresponding to the adversarial game and a preset function; Comparing the first random variable entropy value with a first preset reference random variable entropy value to obtain second comparison data; The entropy value of the first random variable is related to the gaze transfer trajectory of the football trainee to be trained when watching a football confrontation game simulation video.

4. A soccer player cognitive information training method according to claim 2, characterized in that: The actual training index data corresponding to the dribbling attack situation is compared with the preset reference index data corresponding to the dribbling attack situation to obtain third comparison data, specifically including: Based on the actual training indicator data corresponding to the dribbling offense and the preset function, the entropy value of the second random variable is obtained; Comparing the second random variable entropy value with a second preset reference random variable entropy value to obtain third comparison data; The entropy value of the second random variable is related to the gaze transfer trajectory of the football trainee to be trained when watching a simulated video of dribbling offense.

5. A soccer player cognitive information training method according to claim 1, characterized in that: Before obtaining the eye movement index data and physiological characteristic data of the football trainee when the football trainee is watching the football training simulation video, the method further includes: The reference physiological characteristic time series distribution within a preset time period is used as input, and the binary classification variable of whether the sample football player has generated attention preparation is used as output, and the preset classification model is trained to obtain the preset SVM model.

6. A soccer player cognitive information training method according to claim 1, characterized in that: When the comparison data does not meet the preset training requirement and / or the football student to be trained does not show an attention readiness state, the playback speed of the football game simulation video is adjusted to retrain the football student to be trained, specifically including: In the case that the football trainee to be trained does not show an attention and preparation state, the football trainee to be trained is reminded through a preset display screen, and the playback speed of the current simulation video is reduced so that the football trainee to be trained is retrained.

7. A soccer player cognitive information training method according to claim 1, characterized in that: After retraining the football student to be trained, the method further includes: Reacquire comparison data until the comparison data meets the preset training requirements, then remove the annotation to complete the current training; and / or The physiological characteristic data of the football student to be trained corresponding to the speed-adjusted simulation video is re-acquired, and the physiological characteristic data is re-input into the preset SVM model. When the preset SVM model outputs that there is attention preparation, the reminder information on the preset display screen is eliminated to complete the current training.

8. A soccer player cognitive information training device comprising: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to: When the sample football players watch a football game simulation video, obtaining reference physiological characteristic data of the sample football players when a sudden change in the situation occurs in the simulation video; Determining the attention readiness of the sample football player when a sudden change in the situation occurs in the simulated video; wherein the attention readiness is related to whether the sample football player has an action response; When a soccer student to be trained watches a soccer game simulation video, eye movement index data and physiological characteristic data of the soccer student to be trained are obtained; wherein the eye movement index data includes at least one of gaze point information, gaze transfer trajectory, and gaze distribution ratio information; and the physiological characteristic data includes at least one of pupil dilation degree, heart rate, and heart rate variability; Establishing actual training indicator data corresponding to different football training items based on the eye movement indicator data of the football student to be trained and the football training item information, specifically including establishing actual training indicator data corresponding to long-range passing situations based on the gaze distribution ratio data in the eye movement indicator data; and Based on the first gaze point information and the first gaze transfer trajectory in the eye movement index data, actual training index data corresponding to the competitive game situation is established; wherein the first gaze point information and the first gaze transfer trajectory are both related to the eye movement index data of the football trainee to be trained when watching the football competitive game simulation video; and based on the second reference gaze point information and the second gaze transfer trajectory in the eye movement index data, actual training index data corresponding to the dribbling attack situation is established; wherein the second gaze point information and the second gaze transfer trajectory are both related to the eye movement index data of the football trainee to be trained when watching the dribbling attack simulation video; Comparing the actual training index data with the preset reference index data to obtain comparison data; Inputting the physiological characteristic data into a preset SVM model to determine whether the soccer student to be trained is in an attention readiness state, specifically comprising determining a physiological characteristic time series distribution corresponding to the physiological characteristic data within a preset time period; inputting the physiological characteristic time series distribution into the preset SVM model; and classifying the physiological characteristic time series distribution using the preset SVM model to output an attention readiness state corresponding to the soccer student to be trained; When the comparison data does not meet the preset training requirements and / or the football student to be trained does not show an attention readiness state, the playback speed of the football game simulation video is adjusted to re-train the football student to be trained. Specifically, when the comparison data does not meet the preset training requirements, a reference video image area is determined based on the gaze point information corresponding to the football student to be trained, the reference video image area is marked, and the playback speed of the marked video is reduced to re-train the football student to be trained.

Images