A method and apparatus for analyzing a football player's performance

Abstract

The present application relates to the technical field of artificial intelligence, and discloses a football player competition analysis method and device, the present application uses the tracking data of football competition to form the analysis summary of the energy metabolism, running speed distribution, different speed interval running distance, ball holding time and running hot area of the player in the whole game, so as to evaluate the individual physical condition of the player and the enthusiasm in the game, and forms the radar chart of different dimension related events of the player based on the event data, so as to realize the behavior analysis of the specific style of the player. In addition, the present application uses the event data and tracking data of football competition to realize the individual style mining of the player in dealing with different events, the scoring of different positions, and the comprehensive analysis of the contribution to the team, generates the analysis report of football competition based on the target theme, so as to provide a comprehensive and more dimensional evaluation and analysis method, and further can fully tap the potential of young players, so as to cultivate the players in a more scientific way.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, in particular to a football player game analysis method and device. BACKGROUND

[0002] Football is very popular among young people in China. Various youth training teams or campus teams and social training institutions organize football games of various scales and forms, not only to stimulate the enthusiasm of young people in football, but also to discover young players with training potential through various types of games. Therefore, how to scientifically evaluate young football players is crucial.

[0003] In related technologies, the evaluation method of young football players is a common way for coaches and event judges to make subjective evaluations. By observing and recording the situations of young people participating in different games and daily training, players of different abilities are selected to enter teams of different levels. This method relies too much on the experience accumulation of coaches and event judges, and it is difficult to give relatively objective and reliable evaluation standards and results. Another way is to conduct result-based statistics on each game to measure the basic performance of young players, such as the number of shots, goals, passes, and pass success rate of each player. This method reflects the performance of young players to some extent. However, this method reflects the ability of players too single-sidedly, and the aspects that can be evaluated are relatively one-sided, and cannot fully consider the different physical abilities and style characteristics of young players. SUMMARY

[0004] Therefore, the present application provides a football player game analysis method and device to solve the problems of difficulty in giving relatively objective and reliable evaluation standards and results, and reflecting the ability of players too single-sidedly, and the aspects that can be evaluated are relatively one-sided, and cannot fully consider the different physical abilities and style characteristics of young players.

[0005] In a first aspect, the present application provides a football player game analysis method, 1. A football player game analysis method, the method comprising:

[0006] Obtaining tracking data, event data, and game data of multiple players participating in a target theme football game; wherein the tracking data records the positions and speeds of the multiple players and the ball on the field, as well as the team to which the ball possession belongs, the event data records the entire process of the game in chronological order, and the game data records the game information according to the date and time of the game;

[0007] Preprocessing the tracking data, event data, and game data;

[0008] Based on the pre-processed tracking data and event data, analyze each player's game energy metabolism data, running speed distribution data, different speed running interval data, ball holding time data, running hot zone data, radar distribution data;

[0009] Based on the pre-processed event data, analyze each player's individual passing style based on different types of events, each player's performance behavior score in different active positions on the court, and each player's collective contribution value in the game;

[0010] Based on the game energy metabolism data, running speed distribution data, different speed running interval data, ball holding time data, running hot zone data, radar distribution data, each player's individual passing style based on different types of events, each player's performance behavior score in different active positions on the court, and each player's collective contribution value in the game, generate an analysis report for the target theme football game.

[0011] In an optional implementation, the tracking data, event data and game data are pre-processed, including:

[0012] According to the date and time of the game, the tracking data, event data and game data of the same game of the target theme football game are sequentially aligned, filtered and cleaned for preprocessing.

[0013] In an optional implementation, according to the date and time of the game, the tracking data, event data and game data of the same game of the target theme football game are sequentially aligned, filtered and cleaned for preprocessing, including:

[0014] Obtain the player list, jersey number, home and away team identification in the game information;

[0015] Align and unify the fields of the player list, jersey number, home and away team identification in the tracking data and event data;

[0016] Filter the tracking data based on the number of data frames;

[0017] Filter the tracking data based on the player position coordinates in the tracking data;

[0018] Fix the tracking data after filtering according to the preset frame number;

[0019] Clean the tracking data after fixing;

[0020] According to the event time recorded in each frame of the event data, convert the event data into tracking data corresponding to the frame number;

[0021] The tracking data corresponding to the event data converted into frame numbers is located to the corresponding tracking data segment, and the position of the player in the event data and the position of the player in the tracking data are compared to determine whether the record in the event data is obviously abnormal:

[0022] If the position of the player in the event data and the position of the player in the tracking data differ within a preset range, it is determined that the record in the event data is normal.

[0023] If the event data exceeds the preset range, it is determined that the record in the event data is abnormal, and the abnormal data is excluded.

[0024] In an optional embodiment, the match energy metabolism data, running speed distribution data, different speed running interval data, ball holding time data, running hot zone data, and radar distribution data of each player are analyzed, including:

[0025] Based on the speed of each player at each time in the preprocessed tracking data, the acceleration of each player at each time is calculated.

[0026] Based on the acceleration of each player at each time, the energy metabolism data of the player is presented, and a first data graph is drawn by the numerical value at each time.

[0027] Based on the preprocessed tracking data, the preprocessed tracking data is filtered and counted according to low-speed, medium-speed and high-speed running, and the running distance in different speed intervals is calculated to analyze the running ability of different players.

[0028] Based on the preprocessed tracking data, the ball holding time of the home and away teams in the first half and the second half or in different game stages is calculated according to the ball holding field, and a second data graph is drawn; or, the ball holding team is located through the ball holding identifier of each frame, the player currently holding the ball is determined by the distance between the player and the ball, and if the ball is passed out by any player, the ball holding right still belongs to the passing player, then the ball holding time of each player is calculated based on the time before the next event and the ball holding start time of the passing player.

[0029] The preprocessed tracking data is obtained to present the running hot zone of each player in the form of a heat map, and then different players of different positions and styles are analyzed differently.

[0030] According to the comparison needs of different coaches for multi-dimensional abilities of players, radar distribution data of the same player with different abilities is formed, and the radar distribution data includes physical abilities such as maximum acceleration, maximum speed, maximum consumption load, ball holding time of any player, or the number of passes, the number of successful passes, the number of intercepts, and the number of shots.

[0031] In an optional embodiment, based on the preprocessed event data, the individual passing style of each player based on different types of events, the performance behavior score of each player at different active positions on the court, and the collective contribution value of each player in the current game are analyzed, including:

[0032] Clustering different types of passing sub-events using non-negative matrix factorization;

[0033] Calculating the distribution weight of each player in each passing sub-event to evaluate the individual style of each player;

[0034] Generating a visual display of the individual style of each player based on the needs of the coach;

[0035] Based on the preprocessed event data, the active positions of multiple players on the court are classified;

[0036] Based on the event type and result of different active positions, the performance score of the player at different positions is given;

[0037] Based on the preprocessed event data, based on the shot or goal event, the entire passing chain before the shot is traced back, the expected goal value or expected threat value of each player on the passing chain is calculated to evaluate the contribution value of each player to the shot or goal event, and the expected goal value or expected threat value of each player in the entire game is combined and counted to measure the contribution value of each player to the team in the current game;

[0038] The collective contribution value of the player to the target theme football game is evaluated by counting the number of times the expected goal value or expected threat value ranking appears in the top five in multiple games, and a third data graph is generated.

[0039] In an optional embodiment, the football player game analysis method in the embodiments of the present disclosure further includes:

[0040] Obtaining video data of multiple players participating in the target theme football game to assist in reviewing the key segments after the game.

[0041] According to a second aspect, the embodiments of the present disclosure provide a football player game analysis device, the device comprising:

[0042] A data acquisition module for acquiring tracking data, event data and game data of multiple players participating in a target theme football game; wherein the tracking data records the positions and speeds of the multiple players and the ball on the court, as well as the team to which the ball possession belongs, the event data records the entire process of the game in chronological order, and the game data records the game information according to the date and time of the game;

[0043] A data processing module for preprocessing the tracking data, event data and game data;

[0044] The first analysis module is configured to analyze, based on the preprocessed tracking data and the event data, match energy metabolism data, running speed distribution data, different speed running interval data, ball possession time data, running hot zone data, and radar distribution data of each player.

[0045] The second analysis module is configured to analyze, based on the preprocessed event data, individual pass style of each player based on different types of events, performance behavior score of each player at different active positions on the court, and collective contribution value of each player in the match.

[0046] The report generation module is configured to generate an analysis report of the target theme football match based on the match energy metabolism data, the running speed distribution data, the different speed running interval data, the ball possession time data, the running hot zone data, the radar distribution data, the individual pass style of each player based on different types of events, the performance behavior score of each player at different active positions on the court, and the collective contribution value of each player in the match.

[0047] According to a third aspect, the embodiments of the present disclosure provide a computer device, comprising:

[0048] The memory and the processor are connected with each other in communication, the memory stores computer instructions, and the processor executes the computer instructions to perform the football player match analysis method in the first aspect or any of the implementation manners of the first aspect.

[0049] According to a fourth aspect, the embodiments of the present disclosure provide a computer readable storage medium, which stores computer instructions, and the computer instructions are used to make a computer execute the football player match analysis method in the first aspect or any of the implementation manners of the first aspect.

[0050] According to a fifth aspect, the embodiments of the present disclosure provide a computer program product, which comprises computer instructions, and the computer instructions are used to make a computer execute the football player match analysis method in the first aspect or any of the implementation manners of the first aspect.

[0051] The technical scheme of the present disclosure has the following advantages:

[0052] The application relates to the technical field of artificial intelligence, and discloses a football player competition analysis method and device, which uses tracking data of a football competition to form an analysis and summary of energy metabolism, running speed distribution, running distance in different speed intervals, ball holding time and running hot area of a player in a whole game, so as to evaluate the individual physical condition of the player and the enthusiasm of the player in the game, and form a radar chart of different-dimension related events of the player based on event data, so as to realize behavior analysis of a specific style of the player. In addition, the application uses event data and tracking data of the football competition to realize individual style mining of the player in dealing with different events, scoring of different positions and comprehensive analysis of contribution of the player to the team, generate an analysis report of the football competition based on a target theme, so as to provide a comprehensive and multi-dimension evaluation and analysis mode, and further sufficiently mine the potential of a young player, so as to cultivate the player in a more scientific way. BRIEF DESCRIPTION OF DRAWINGS

[0053] In order to more clearly illustrate the specific embodiments of the application or the technical solutions in the prior art, the drawings needed to be used in the specific embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0054] Figure 1 is a flowchart of a football player competition analysis method according to an embodiment of the application;

[0055] Figure 2 is a flowchart of a football player competition analysis method according to an embodiment of the application;

[0056] Figure 3 is a flowchart of another football player competition analysis method according to an embodiment of the application;

[0057] Figure 4 is a flowchart of another football player competition analysis method according to an embodiment of the application;

[0058] Figure 5 is a flowchart of another football player competition analysis method according to an embodiment of the application;

[0059] Figure 6 is a schematic diagram of different types of pass sub-events according to an embodiment of the application;

[0060] Figure 7 is a schematic diagram of division results obtained by clustering all active positions of a player in a certain competition according to an embodiment of the application;

[0061] Figure 8is a structural block diagram of a football player competition analysis device according to an embodiment of the present application;

[0062] Figure 9 is a hardware structure schematic diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0063] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0064] According to an embodiment of the present application, a football player competition analysis method embodiment is provided. It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown.

[0065] In the present embodiment, a football player competition analysis method is provided, which can be used in the mobile terminal described above, such as a mobile phone, a tablet computer, etc. Figure 1 is a flowchart of a football player competition analysis method according to an embodiment of the present application, as shown in Figure 1 The flowchart includes the following steps:

[0066] Step S101, acquiring tracking data, event data and competition data of a plurality of players participating in a target theme football competition; wherein the tracking data records the positions and speeds of the plurality of players and the ball on the field, and the team to which the ball possession belongs, the event data records the entire process of the whole game in time sequence, and the competition data records the competition information according to the date and time of the competition.

[0067] Specifically, the plurality of players in the embodiments of the present application can be young football players. According to the requirements of football competition, the number of participating athletes is usually 22, i.e. 11 players of the home team and 11 players of the away team. The target theme football competition is, for example, the 2024 "certain cup" competition. Therefore, the plurality of players participating in the target theme football competition can be considered as the competitions or the same type of competitions participated in by a plurality of young people in the same period, for example, U13 players participating in the "certain cup competition" in 2024.

[0068] Further, the tracking data in the embodiments of the present disclosure can be collected by a wearable device with UWB or GPS, which can be extracted from the competition video through computer vision technology, and the data collection frequency can be 10 Hz or 25 Hz, that is, 10 frames or 25 frames of data per second, each frame of data records the positions and speeds of a plurality of (22) players and the ball on the court at this moment, and the ownership of the ball possession at this moment. A coordinate system is established with a certain point at the four corners of the court or the center of the court as the origin, and the coordinates of the players and the ball can be represented as two-dimensional and three-dimensional coordinates according to the coordinate system. Among them, the coordinates of the players are represented as two-dimensional coordinates, and the coordinates of the home team players can be represented as The speed of the players can be represented as where i = 1, 2, …, 11 represents the 11 players of the home team; the coordinates of the players of the away team can be represented as The speed of the players can be represented as i = 1, 2, …, 11 represents the 11 players of the home team; the coordinates of the players of the away team can be represented as ball (x, y, z), and the speed of the ball can be represented as vel ball (x, y, z), where the coordinates of the players and the ball of the home and away teams are scalars, and the speeds are vectors; the ball possession can be represented as ball_control, ball_control = 1 if the home team has the ball possession, ball_control = -1 if the away team has the ball possession, and ball_control = 0 if no one has the ball possession. control

[0069] In addition, the event data in the embodiments of the present disclosure records all important events occurring in the entire competition in time sequence, such as passing, interception, dribbling, shooting, scoring, etc. Each piece of data (a frame) is an important event, and the information contained includes the type of event, the time and position of occurrence, the names and jersey numbers of the related players, etc. Due to the interval and randomness of the events to a certain extent, the recording frequency of the event data is not fixed, that is, the number of data frames is not according to a fixed time interval, but the event data still has a time sequence, for example, the event data from the starting frame to the ending frame is recorded according to the time progress of the competition; at the same time, the data has continuity, for example, the next frame of the “passing” event must be an event type closely related to passing, such as “cutting”, “intercepting”, “receiving the ball”, etc. The event type field is represented by type, if a frame of data is a shooting event, then this event type = ‘shot’. The data format, data volume, degree of detail of competition recording, and field representation of event data collected by different data vendors are different, but in general, all the key events occurring in the entire competition are recorded. The competition data records the date and time of the competition

[0070] In step S102, the tracking data, event data and competition data are preprocessed.

[0071] ​Specifically, in the embodiments of the present disclosure, the tracking data, event data and match data of multiple matches can be data cleaned and data aligned.

[0072] By way of example, the embodiments of the present disclosure can align and data clean the tracking data, event data and match data of the same match according to the date, time and match information of the match.

[0073] In step S103, based on the preprocessed tracking data and event data, the match energy metabolism data, running speed distribution data, different speed running interval data, ball holding time data, running hot zone data and radar distribution data of each player are analyzed.

[0074] Specifically, the first analysis module (basic analysis module) in the football player match analysis device analyzes the match energy metabolism data, running speed distribution data, different speed running interval data, ball holding time data, running hot zone data and radar distribution data of each player based on the preprocessed tracking data and event data. The match energy metabolism data, running speed distribution data, different speed running interval data and ball holding time data of each player are used to evaluate the individual ability of the player. The running hot zone data and radar distribution data of each player are used to evaluate the match enthusiasm of the player.

[0075] The embodiments of the present disclosure use the tracking data of the football match to analyze and summarize the match energy metabolism, running speed distribution, different speed interval running distance, ball holding time and running hot zone of the player to evaluate the individual physical condition of the player and the enthusiasm of the player in the match. The event data is used to form the radar chart of the player in different dimensions to realize the behavior analysis of the specific style of the player.

[0076] In step S104, based on the preprocessed event data, the individual pass style of each player based on different types of events, the performance behavior score of each player in different active positions on the field and the collective contribution value of each player in the match are analyzed.

[0077] Specifically, the second analysis module (high-level analysis module) in the football player match analysis device analyzes the individual pass style of each player based on different types of events, the performance behavior score of each player in different active positions on the field and the collective contribution value of each player in the match based on the preprocessed event data.

[0078] The high-level analysis module in the embodiments of the present disclosure uses the event data and tracking data of the football match to realize the individual style mining of the player in dealing with different events, the scoring of different positions and the comprehensive analysis of the contribution of the player to the team.

[0079] Step S105, based on the competition energy metabolism data, running speed distribution data, different speed running interval data, ball holding time data, running hot zone data, radar distribution data, each player's individual passing style based on different types of events, each player's performance behavior score in different active positions on the court, and each player's collective contribution value in the game, generate an analysis report of the target theme football game.

[0080] By analyzing the various data of the players through the above-mentioned basic analysis module and high-level analysis module, an analysis report based on the target theme football game is generated to provide a more comprehensive and multi-dimensional evaluation and analysis method, which can fully tap the potential of young players and train them in a more scientific way.

[0081] As shown in Figure 2 , it is a schematic diagram of analyzing various data of multiple players through the basic analysis module and the high-level analysis module.

[0082] In an optional implementation, the tracking data, event data and competition data are preprocessed, including: aligning, filtering and cleaning the tracking data, event data and competition data of the same game of the target theme football game in sequence according to the date and time of the game.

[0083] By aligning, filtering and cleaning the tracking data, event data and competition data, the accuracy of the data is ensured, which is conducive to accurately analyzing the individual ability, competition enthusiasm, individual physical condition, individual passing style, collective contribution value and performance behavior score of multiple players.

[0084] In this embodiment, a football player game analysis method is provided, which can be used in mobile terminals such as mobile phones, tablet computers, etc. Figure 3 is a flowchart of the football player game analysis method according to an embodiment of the present application, as shown in Figure 3 , the tracking data, event data and competition data of the same game of the target theme football game are aligned, filtered and cleaned in sequence according to the date and time of the game, including the following steps:

[0085] Step S301, obtaining the player list, jersey number, home and away team identification in the game information.

[0086] Specifically, the game information comes from the competition data, and the game information is specific information recorded according to the date and time of the game, which contains the player list, jersey number, home team identification and away team identification.

[0087] Step S302, aligning and unifying the fields of the player list, jersey number, home and away team identification in the tracking data and event data.

[0088] Specifically, the player list, the jersey number, and the home and away team identification information in the match information data are used to align and unify the tracking data and the corresponding fields in the event data.

[0089] In step S303, the tracking data is filtered based on the data frame number to remove obviously erroneous and out-of-order frames.

[0090] Specifically, because the tracking data collected by the wearable device with GPS or UWB has problems such as unstable data collection frequency, frame loss, and out-of-order, the obviously erroneous and out-of-order frames can be removed according to the data frame number.

[0091] In step S304, the tracking data is filtered based on the player position coordinates in the tracking data to remove out-of-order frames.

[0092] Specifically, the obviously jumping out-of-order frames are removed according to the player position coordinates, for example, if the position of a player or multiple players in the consecutive frame number jumps obviously (not consistent with the continuous running of the player), the data is removed; and the required tracking data frequency is determined.

[0093] In step S305, the tracking data after filtering is fixed according to a preset frame number.

[0094] Specifically, according to the required tracking data frequency, if the collected frame number per second is greater than 10 frames, 10 frames of complete information are randomly selected for fixing. Complete information means that the frame contains the positions and speeds of the ball and the records of the possession of the ball by multiple players (22 players) on the court; if the collected frame number per second is less than 10 frames, the data is enhanced by linear difference to complete 10 frames per second. The preset frame number in the embodiment of the disclosure is determined in combination with the actual needs, and therefore, the preset frame number can also be 35 frames, and the fixing method is the same as the above-mentioned 10 frame fixing method.

[0095] In step S306, the tracking data after fixing is cleaned.

[0096] Specifically, after the tracking data according to the preset frame number is fixed, if 10 Hz is used for fixing, then the data cleaning is performed according to 10 frames per second.

[0097] In step S307, the event data is converted into tracking data corresponding to the frame number according to the event time recorded in each frame of the event data.

[0098] In step S308, the event data converted into tracking data corresponding to the frame number is located to the corresponding tracking data segment, and the position of the player in the event data is compared with the position of the player in the tracking data to determine whether the record in the event data is obviously abnormal.

[0099] Specifically, for handling outliers in event data, the event time recorded in each frame of the event data is first converted into the corresponding number of tracking data frames. Then, the corresponding tracking data segment is located, and the player's position in the event data is compared with the player's position in the tracking data to determine whether there are obvious anomalies in the event data recording.

[0100] Step S309: If the difference between the player's position in the event data and the player's position in the tracking data is within a preset range, then the record in the event data is determined to be without anomalies.

[0101] Step S310: If the event data exceeds the preset range, the records in the event data are determined to be abnormal, and the abnormal data is removed.

[0102] For example, the preset range can be within ±10 meters to determine whether an anomaly has occurred. For instance, if the difference between the player's position (horizontal and vertical coordinates) between the event data and the tracking data is within ±10 meters, it can be determined that there is no anomaly. If it exceeds ±10 meters, the event data record is determined to be abnormal and needs to be removed. In this way, tracking data and event data for multiple matches can be obtained after preprocessing.

[0103] By aligning, filtering, and cleaning preprocessing tracking data, event data, and match data, the accuracy of the data is ensured, which in turn facilitates accurate analysis of multiple players' individual abilities, match enthusiasm, individual physical condition, individual passing style, collective contribution value, and performance behavior ratings.

[0104] This embodiment provides a method for analyzing football player matches, which can be used on mobile terminals such as mobile phones and tablets. Figure 4 This is a flowchart of a football player match analysis method according to an embodiment of the present invention, such as... Figure 4 As shown, step S103 above, based on the preprocessed tracking data and event data, analyzes each player's match energy metabolism data, running speed distribution data, running interval data at different speeds, ball possession time data, running hot zone data, and radar distribution data, including:

[0105] Step S1031: Calculate the acceleration of each player at each moment based on the velocity of each player at each moment in the preprocessed tracking data.

[0106] Specifically, since the tracking data includes each player's time at each moment and their corresponding speed at that moment, the formula is used to... This allows us to calculate the acceleration of each player at every moment.

[0107] Step S1032: Based on the acceleration of each player at each moment, present the player's energy metabolism data and draw the values ​​at each moment to form the first data graph.

[0108] Specifically, the energy metabolism of the player is presented by acceleration, so as to reflect the physical condition of the player. The presentation form can be a broken line graph formed by the value at each moment, or a column chart formed by averaging in a period of time, etc. The broken line graph and the column chart are the first data graph in the above description.

[0109] In step S1033, the preprocessed tracking data is filtered and counted according to low-speed, medium-speed and high-speed running, and the running distances in different speed intervals are calculated to analyze the running ability of different players based on the preprocessed tracking data.

[0110] Specifically, low-speed, medium-speed and high-speed can be defined based on different coaches. According to the definition of low-speed, medium-speed and high-speed running by different coaches, the tracking data is filtered and counted, and the running distances in different speed intervals are calculated to analyze the running ability of different players.

[0111] In step S1034, the preprocessed tracking data is used to calculate the ball possession time of the home and away teams in the first and second halves or different game stages according to the ball possession field, and a second data graph is drawn; or, the ball possession team is located by the ball possession identifier of each frame, the player currently in possession of the ball is determined by the distance between the player and the ball, and if the ball is passed out by any player, the ball possession right still belongs to the passing player, then the ball possession time of each player is calculated based on the time before the next event and the ball possession start time of the passing player.

[0112] Specifically, based on the preprocessed tracking data, the ball possession time of the home and away teams in the first and second halves or different game stages can be calculated by the ball_control field, and presented in the form of a pie chart or a column chart. The pie chart or column chart is the second data graph.

[0113] Alternatively, the ball possession team can also be located by the ball possession identifier of each frame, and the player currently in possession of the ball is determined by the distance between the player and the ball. If the ball is passed out by any player, the ball possession right still belongs to the passing player before the next event (cut-off, receiving the ball, etc.). The ball possession time of each player is calculated based on the ball possession start time and the time before the next event, so as to compare and analyze the ball possession ability of different players. The presentation form can be a pie chart or a column chart, which is the second data graph in the above description.

[0114] In step S1035, the preprocessed tracking data is obtained, and the running hot zone of each player is presented in the form of a heat map, so as to differentially analyze players of different positions and styles.

[0115] Based on the preprocessed tracking data, the running heat map of each player is presented, and then the differences between players in different positions and styles are analyzed.

[0116] Step S1036: Based on the different coaches' needs for comparing players' multi-dimensional abilities, radar distribution data for the same player with different abilities is generated. The radar distribution data includes any player's physical abilities such as maximum acceleration, maximum speed, maximum energy expenditure, and ball control time, or the number of passes, number of successful passes, number of interceptions, and number of shots.

[0117] Specifically, based on the different coaches' needs for comparing players' multi-dimensional abilities, a radar distribution calculation can be formed for different abilities of the same player. For example, a player's physical abilities such as maximum acceleration, maximum speed, maximum metabolic energy, and ball control time, or his technical abilities such as the number of passes, the number of successful passes, the number of interceptions, and the number of shots can be compared. Alternatively, a comparison of one or more dimensions of ability of different players can be formed, such as comparing the running, passing, and interception abilities of several players on the home team.

[0118] Among them, maximum metabolic energy can be calculated by using the player speed recorded in the tracking data to calculate the energy consumption of each player, reflecting the differences in physical fitness among different players in the game, and comparing the energy consumption of exercise under different speed changes. For example, maximum metabolic energy can be calculated using the following formula.

[0119] a>0, cost=0.102×((a) 2 +96.2) 0.5 )×(4.03×a+3.6×e (-0.408)×a );

[0120] a<0, cost=0.102×((a) 2 +96.2) 0.5 )×((-0.85)×a+3.6×e 1.33×a );

[0121] a = 0, cost = 0. Here, a is the acceleration, and cost is the maximum metabolic energy.

[0122] In addition, the maximum acceleration and maximum speed can be calculated from the speed in the tracking data. The ball possession time can be calculated in the manner mentioned in step S1034 above. The number of passes, the number of successful passes, the number of interceptions, and the number of shots can be obtained from the event data.

[0123] The embodiment of the present disclosure forms an analysis summary of the energy metabolism, running speed distribution, running distance in different speed intervals, ball possession time, and running hot zone of a player in a whole game by using tracking data of a football game, so as to evaluate the individual physical condition and activity of each player in the game, and forms a radar chart of different dimensions of events of a player based on event data, so as to realize behavior analysis of a specific style of each player.

[0124] In the embodiment, a football player game analysis method is provided, which can be used in mobile terminals such as mobile phones, tablet computers and the like. Figure 5 The flowchart of the football player game analysis method according to the embodiment of the present disclosure is shown in FIG. 4, and the step S104 is based on the preprocessed event data to analyze the individual pass style of each player based on different types of events, the performance behavior score of each player in different active positions on the court, and the collective contribution value of each player in the game, including: Figure 5

[0125] The step S1041 clusters different types of pass sub-events by using a non-negative matrix factorization method.

[0126] Specifically, different types of pass sub-events are defined by using a non-negative matrix factorization method according to the analysis requirements of a coach for style types, for example, the pass sub-events are divided into sub-types such as dangerous pass, key pass, and back line pass, so as to form a classification of different event occurrence positions. Figure 6 As shown in FIG. 5, a schematic diagram of a pass sub-event is shown, and the red area represents a pass position.

[0127] The step S1042 calculates the distribution weight of each player in each pass sub-event, so as to evaluate the individual style of each player.

[0128] Specifically, the distribution weight of each player in these types is calculated based on the formed classification of different event occurrence positions, so as to evaluate the individual style of the player.

[0129] The step S1043 generates a visual display diagram of the individual style of each player based on the requirements of the coach.

[0130] Specifically, different visual displays are formed according to the requirements of the coach, and the visual display diagram of the individual style includes a heat map or a scatter plot.

[0131] The step S1044 classifies the active positions of multiple players on the court based on the preprocessed event data.

[0132] Specifically, the active positions of multiple players on the court are classified based on the preprocessed event data. As shown in FIG. 6, a schematic diagram of the active positions of multiple players on the court is shown. Figure 7 ​The diagram shows the division result obtained by clustering all active positions of a player in a certain cup competition.

[0133] Step S1045, performance scores of the player in different positions are given based on the event types and results of different active positions.

[0134] Specifically, performance scores of multiple players in different positions are given according to the event types and results of different positions (such as whether the pass is successful, whether the ball is intercepted), so as to mine the strengths and weaknesses of the players.

[0135] Step S1046, based on the preprocessed event data, the expected goal value or expected threat value of each player on the pass chain is calculated based on the shooting or goal event to evaluate the contribution value of each player to the shooting or goal event, and the expected goal value or expected threat value of each player in the whole game is combined and counted to measure the contribution value of each player to the team in the game.

[0136] Specifically, based on the preprocessed event data, the expected goal value xG or expected threat value xT of each player on the pass chain is calculated based on the shooting (not in) or goal event to evaluate the contribution value of each player to the shooting (not in) or goal event, and the xG value or xT value of each player in the whole game is combined and counted to measure the contribution value of each player to the team in the game.

[0137] Step S1047, the collective contribution value of the player to the target theme football game is evaluated by counting the number of times the expected goal value or expected threat value ranks in the top five in multiple games, and a third data diagram is generated.

[0138] Specifically, the collective contribution value of the player to the competition or cup is evaluated by counting the number of times the xG or xT value ranks in the top five in multiple games, and the presentation form is a pie chart or a bar chart, i.e. the third data diagram in the above.

[0139] The embodiments of the present disclosure implement the personal style mining of players in handling different events, the scoring of different positions, and the comprehensive analysis of the contribution to the team by using the event data and tracking data of football games by performing the above steps S1041-S1047, which is beneficial to fully mine the potential of the players and cultivate the players in a more scientific way.

[0140] In an optional implementation, the football player game analysis method in the embodiments of the present disclosure further includes: obtaining video data of multiple players participating in the target theme football game to assist in the review of key segments after the game.

[0141] Specifically, the game video can be a full-view game recording or a tactical-view game recording, which is used to assist the review of key segments after the game and the comparison and analysis with the data segment visualization.

[0142] A football player game analysis device is also provided in the embodiment, which is used to realize the above-mentioned embodiments and preferred embodiments, and will not be described again. As used below, the term "module" can be a combination of software and / or hardware that realizes a predetermined function. Although the device described in the following embodiments is preferably realized in software, the realization of hardware or a combination of software and hardware is also possible and conceived.

[0143] The embodiment provides a football player game analysis device, which comprises: Figure 8 as shown in the figure, comprising:

[0144] A data acquisition module 81 is configured to acquire tracking data, event data and game data of a plurality of players participating in a target theme football game, wherein the tracking data records the positions and speeds of the plurality of players and a ball on a court, and a team to which a ball possession right belongs, the event data records an entire process of the game according to a time sequence, and the game data records game information according to a date and a time of the game;

[0145] A data processing module 82 is configured to pre-process the tracking data, the event data and the game data;

[0146] A first analysis module 83 is configured to analyze, based on the pre-processed tracking data and the event data, game energy metabolism data, running speed distribution data, different speed running interval data, ball holding time data, running hot zone data and radar distribution data of each player;

[0147] A second analysis module 84 is configured to analyze, based on the pre-processed event data, individual pass style of each player based on different types of events, performance behavior scores of each player at different activity positions on the court and collective contribution values of each player in the game;

[0148] A report generation module 85 is configured to generate an analysis report of the target theme football game based on the game energy metabolism data, the running speed distribution data, the different speed running interval data, the ball holding time data, the running hot zone data, the radar distribution data, the individual pass style of each player based on different types of events, the performance behavior scores of each player at different activity positions on the court and the collective contribution values of each player in the game.

[0149] In an optional embodiment, the data processing module 82 comprises:

[0150] The data processing submodule is configured to sequentially align, filter, and clean the tracking data, the event data, and the match data of the same match of the target theme football match according to the date and time of the match.

[0151] In an optional implementation, the data processing submodule comprises:

[0152] The data acquisition unit is configured to acquire the player list, the jersey number, and the home and away team identification in the match information.

[0153] The data alignment unit is configured to align and unify the fields of the player list, the jersey number, and the home and away team identification in the tracking data and the event data.

[0154] The first filtering unit is configured to filter the error out-of-order frames of the tracking data based on the data frame number.

[0155] The second filtering unit is configured to filter the out-of-order frames of the tracking data based on the player position coordinates in the tracking data.

[0156] The data fixing unit is configured to fix the tracking data after filtering according to a preset frame number.

[0157] The data cleaning unit is configured to clean the tracking data after fixing.

[0158] The data tracking unit is configured to convert the event data into tracking data corresponding to the frame number according to the event time recorded in each frame of the event data.

[0159] The first recording unit is configured to locate the event data converted into tracking data corresponding to the frame number to the corresponding tracking data segment, and compare the position of the player in the event data with the position of the player in the tracking data to determine whether the record in the event data is obviously abnormal.

[0160] The second recording unit is configured to perform abnormal processing, and if the position of the player in the event data and the position of the player in the tracking data differ within a preset range, it is determined that the record in the event data is not abnormal.

[0161] The abnormality elimination unit is configured to determine that the record in the event data is abnormal if the event data exceeds the preset range, and eliminate the abnormal data.

[0162] In an optional implementation, the first analysis module 83 comprises:

[0163] The acceleration data calculation submodule is configured to calculate the acceleration of each player at each time based on the speed of each player at each time in the preprocessed tracking data.

[0164] The first data graph generating submodule is configured to present energy metabolism data of each player based on the acceleration of each player at each moment, and draw a first data graph based on the numerical value at each moment.

[0165] The running ability data analysis submodule is configured to filter and count the preprocessed tracking data according to low-speed, medium-speed and high-speed running, and calculate running distances in different speed intervals, so as to analyze the running ability of different players based on the preprocessed tracking data.

[0166] The player ball possession time calculation submodule is configured to calculate the ball possession time of the home team and the away team in the first half and the second half or in different game stages according to the ball possession field based on the preprocessed tracking data, and draw a second data graph, or locate the ball possession team through the ball possession identifier of each frame, determine the player currently possessing the ball by the distance between the player and the ball, and calculate the ball possession time of each player if the ball is passed out by any player and the ball possession right still belongs to the passing player, and the time before the next event occurs and the ball possession start time of the passing player.

[0167] The player data difference analysis submodule is configured to obtain the preprocessed tracking data, present the running hot zone of each player in the form of a heat map, and then perform differential analysis on players of different positions and styles.

[0168] The radar distribution data generating submodule is configured to form radar distribution data of the same player with different abilities according to the comparison requirements of different coaches on the multi-dimensional abilities of players, and the radar distribution data includes physical abilities such as the maximum acceleration, the maximum speed, the maximum consumption load and the ball possession time of any player, or the number of passes, the number of successful passes, the number of interceptions and the number of shots.

[0169] In an optional implementation, the second analysis module 84 includes:

[0170] The data clustering submodule is configured to cluster different types of pass sub-events by using a non-negative matrix factorization method.

[0171] The style evaluation submodule is configured to calculate the distribution weight of each player in each pass sub-event, so as to evaluate the personal style of each player.

[0172] The data display submodule is configured to generate a visual display graph of the personal style of each player based on the requirements of the coach.

[0173] The data classification submodule is configured to classify the activity positions of multiple players on the court based on the preprocessed event data.

[0174] The data scoring submodule is configured to give a performance score of a player at different positions based on the event type and result of different activity positions.

[0175] The player contribution value calculation sub-module is configured to calculate an expected goal value or an expected threat value of each player on a pass chain based on a shot or a goal event and a preprocessed event data, evaluate a contribution value of each player to the shot or the goal event, and combine the expected goal value or the expected threat value of each player in a whole game to measure a contribution value of each player to a team in the game.

[0176] The data graph generation sub-module is configured to evaluate a collective contribution value of a player to a target theme football game by counting a number of times that an expected goal value or an expected threat value ranks in a top five in multiple games, and generate a third data graph.

[0177] In an optional embodiment, the football player game analysis method in the embodiment of the present disclosure further includes:

[0178] The video data acquisition sub-module is configured to acquire video data of multiple players participating in a target theme football game to assist in reviewing key segments after the game.

[0179] Further function descriptions of the above modules and units are the same as those of the corresponding embodiments, and will not be described here.

[0180] The football player game analysis apparatus in the embodiment is in the form of a functional unit. The unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and a memory executing one or more software or fixed programs, and / or other devices that can provide the above functions.

[0181] The embodiment of the present disclosure also provides a computer device with the football player game analysis apparatus.

[0182] Please refer to Figure 9 , Figure 9 is a structural schematic diagram of a computer device provided by an optional embodiment of the present disclosure, as Figure 9As shown, the computer device includes one or more processors 10, memory 20, and interfaces 30 for external devices such as a keyboard and a mouse and peripheral devices such as disk devices or other storage devices. One or more busses 10 can be used to implement the interface between the various internal and external components and can be implemented using any one or more of a variety of bus technologies including a System bus, PCI, SCSI, AGP, Super- I / O bus, etc. Furthermore, various buses can be used in front side buses, back side buses, and other bus configurations based on any bus or messaging technology known to those skilled in the art. Figure 9 The processor 10 is used in the embodiments below as an example.

[0183] The processor 10 can be a central processing unit, a network processor, or a combination thereof. The processor 10 can further include a hardware chip. The hardware chip can be an application specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device can be a complex programmable logic device, a field programmable logic device, a general array logic, or any combination thereof.

[0184] The memory 20 stores instructions that can be executed by the at least one processor 10, so that the at least one processor 10 implements the method shown in the above embodiments.

[0185] The memory 20 can include a program region and a data region. The program region can store an operating system and application programs required by at least one function. The data region can store data created according to the use of the computer device, etc. In addition, the memory 20 can include a high-speed random access memory, and can further include a non-transitory memory such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some alternative embodiments, the memory 20 can optionally include a memory disposed remotely with respect to the processor 10, and these remote memories can be connected to the computer device through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0186] The memory 20 can include a volatile memory such as a random access memory, and can also include a non-volatile memory such as a flash memory, a hard disk, or a solid state disk. The memory 20 can further include a combination of the above-mentioned kinds of memories.

[0187] The computer device further includes a communication interface 30 for communication with other devices or communication networks.

[0188] The embodiments of the present application further provide a computer readable storage medium, and the method according to the embodiments of the present application can be implemented in hardware, firmware, or recorded in a storage medium, or stored in a remote storage medium or a non-transitory machine readable storage medium and downloaded to a local storage medium through network, so that the method described herein can be processed by such software on a storage medium using a general purpose computer, a special purpose processor, or programmable or special hardware. The storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid state disk, etc. Further, the storage medium can also include a combination of the above-mentioned memories. It can be understood that the computer, the processor, the microprocessor controller, or the programmable hardware includes a storage component that can store or receive software or computer code, when the software or computer code is accessed and executed by the computer, the processor, or the hardware, the method shown in the above embodiments is implemented.

[0189] Part of the present application can be applied as a computer program product, for example, computer program instructions, when executed by a computer, the operation of the computer can invoke or provide the method and / or technical solutions according to the present application. Those skilled in the art should understand that the form of computer program instructions in computer readable medium includes but is not limited to source file, executable file, installation package file, etc. Correspondingly, the way of computer program instructions executed by computer includes but is not limited to: the computer directly executes the instructions, or the computer compiles the instructions and then executes the corresponding compiled program, or the computer reads and executes the instructions, or the computer reads and installs the instructions and then executes the corresponding installed program. Here, the computer readable medium can be any available computer readable storage medium or communication medium accessible to the computer.

[0190] Although the embodiments of the present application are described in conjunction with the accompanying drawings, various modifications and changes can be made by those skilled in the art without departing from the spirit and scope of the present application, and such modifications and changes fall within the scope defined by the appended claims.

Claims

1. A method of analyzing a football player's game, characterized by, The method comprises: acquiring tracking data, event data and match data of a plurality of players participating in a target theme football match; wherein the tracking data records the positions and speeds of the plurality of players and the ball on the pitch, and the team to which the ball possession belongs, the event data records the entire process of the match in time sequence, and the match data records the match information according to the date and time of the match; preprocessing the tracking data, the event data and the match data; based on the preprocessed tracking data and the event data, analyzing the match energy metabolism data, the running speed distribution data, the different speed running interval data, the ball possession time data, the running hot zone data and the radar distribution data of each player; based on the preprocessed event data, analyzing the personal passing style of each player based on different types of events, the performance behavior score of each player at different active positions on the pitch, and the collective contribution value of each player in the match; based on the match energy metabolism data, the running speed distribution data, the different speed running interval data, the ball possession time data, the running hot zone data, the radar distribution data, the personal passing style of each player based on different types of events, the performance behavior score of each player at different active positions on the pitch, and the collective contribution value of each player in the match, generating an analysis report of the target theme football match; analyzing the match energy metabolism data, the running speed distribution data, the different speed running interval data, the ball possession time data, the running hot zone data and the radar distribution data of each player, comprising: based on the speed of each player at each time in the preprocessed tracking data, calculating the acceleration of each player at each time; based on the acceleration of each player at each time, presenting the energy metabolism data of the player, and drawing a first data graph formed by the numerical value at each time; based on the preprocessed tracking data, filtering and counting the preprocessed tracking data according to low-speed, medium-speed and high-speed running, calculating the running distance in different speed intervals, and analyzing the running ability of different players; based on the preprocessed tracking data, calculating the ball possession time of the home and away teams in the first half and the second half or in different match stages according to the ball possession field, and drawing a second data graph; or, positioning the ball possession team through the ball possession identifier of each frame, determining the player currently controlling the ball through the distance between the player and the ball, and if the ball is passed out by any player, the ball possession right still belongs to the passing player, then the ball possession time of each player is calculated based on the time before the next event and the ball possession start time of the passing player; acquiring the preprocessed tracking data to present the running hot zone of each player in the form of a heat map, and then differentially analyzing players of different positions and styles; forming radar distribution data of different abilities of the same player according to the comparison requirements of different coaches for the multi-dimensional abilities of the player, the radar distribution data comprising the maximum acceleration, maximum speed, maximum consumption load, ball possession time physical ability of any player, or the number of passes, the number of successful passes, the number of interceptions and the number of shots.

2. The method of claim 1, wherein, The tracking data, the event data and the match data are preprocessed, including: The tracking data, the event data and the match data of the same game of the target theme football game are sequentially aligned, filtered and cleaned according to the date and time of the game.

3. The method of claim 2, wherein, The tracking data, the event data and the match data of the same game of the target theme football game are sequentially aligned, filtered and cleaned according to the date and time of the game, including: Obtaining the player list, jersey number, home and away team identification in the match information; Aligning and unifying the fields of the player list, jersey number, home and away team identification in the tracking data and the event data; Filtering the tracking data based on the number of data frames; Filtering the tracking data based on the player position coordinates in the tracking data; Fixing the tracking data after filtering according to the preset frame number; Cleaning the tracking data after fixing; Converting the event data into tracking data corresponding to the frame number according to the event time recorded in each frame of the event data; Locating the event data converted into tracking data corresponding to the frame number to the corresponding tracking data segment, and comparing the positions of the players in the event data and the tracking data to determine whether the records in the event data are obviously abnormal: If the positions of the players in the event data and the tracking data differ within a preset range, it is determined that the records in the event data are normal. If the event data exceeds the preset range, it is determined that the records in the event data are abnormal, and the abnormal data is excluded.

4. The method of claim 1, wherein, Based on the preprocessed event data, the individual pass style of each player based on different types of events, the performance behavior score of each player at different activity positions on the court, and the collective contribution value of each player in the game are analyzed, including: Clustering different types of pass sub-events using non-negative matrix factorization; Calculating the distribution weight of each player in each pass sub-event to evaluate the individual style of each player; Generating a visual display diagram of the individual style of each player based on the needs of the coach; Based on the preprocessed event data, the activity positions of the players on the court are classified; Based on the event type and result of different activity positions, the performance score of the players at different positions is given; Based on the preprocessed event data, the expected goal value or expected threat value of each player on the pass chain is calculated by tracing back the entire pass chain before shooting, to evaluate the contribution value of each player to the shooting or goal event, and the expected goal value or expected threat value of each player in the entire game is combined and counted to measure the contribution value of each player to the team in the game. The collective contribution value of the player to the target theme football game is evaluated by counting the number of times the expected goal value or expected threat value ranking appears in the top five in multiple games, and a third data graph is generated.

5. The soccer player match analysis method according to any one of claims 1 to 4, characterized by, Also includes: Acquire video data of multiple players participating in a target theme football match to assist in reviewing key segments after the match.

6. A soccer player match analysis device characterized by comprising: The device comprises: a data acquisition module configured to acquire tracking data, event data, and match data of multiple players participating in a target theme football match, wherein the tracking data records positions and speeds of the multiple players and a ball on a football field, and a team to which a ball possession right belongs, the event data records an entire process of the match in a time sequence, and the match data records match information according to a date and a time of the match; a data processing module configured to pre-process the tracking data, the event data, and the match data; a first analysis module configured to analyze, based on the pre-processed tracking data and the event data, match energy metabolism data, running speed distribution data, different speed running interval data, ball possession time data, running hot zone data, and radar distribution data of each player; a second analysis module configured to analyze, based on the pre-processed event data, individual pass style of each player based on different types of events, performance behavior scores of each player at different active positions on the football field, and collective contribution values of each player in the match; a report generation module configured to generate an analysis report of the target theme football match based on the match energy metabolism data, the running speed distribution data, the different speed running interval data, the ball possession time data, the running hot zone data, the radar distribution data, the individual pass style of each player based on different types of events, the performance behavior scores of each player at different active positions on the football field, and the collective contribution values of each player in the match; the first analysis module comprises: an acceleration data calculation submodule configured to calculate an acceleration of each player at each time based on a speed of each player at each time in the pre-processed tracking data; a first data graph generation submodule configured to present energy metabolism data of the player based on the acceleration of each player at each time, and draw a first data graph formed by numerical values at each time; a running ability data analysis submodule configured to filter and count the pre-processed tracking data according to low-speed, medium-speed, and high-speed running based on the pre-processed tracking data, and calculate running distances in different speed intervals to analyze running abilities of different players; a player ball possession time calculation submodule configured to calculate ball possession times of home and away teams in upper and lower halves or different match stages according to a ball possession field based on the pre-processed tracking data, and draw a second data graph, or to locate a ball possession team through a ball possession identifier of each frame, to determine a player currently possessing the ball through a distance between the player and the ball, and to calculate a ball possession time of each player if the ball is passed out by any player, the ball possession right still belongs to the passing player, and a time before a next event occurs and a ball possession start time of the passing player; a player data difference analysis submodule configured to acquire the pre-processed tracking data, and present a running hot zone of each player in a heat map, and then to analyze players at different positions and styles differently. The radar distribution data generation submodule is used to form radar distribution data of the same player with different abilities according to the comparison requirements of different coaches on the multi-dimensional abilities of the player, and the radar distribution data includes the maximum acceleration, maximum speed, maximum consumption load, ball control time physical ability of any player, or the number of passes, the number of successful passes, the number of intercepts, and the number of shots.

7. A computer device, characterized by Comprise: A memory and a processor, which are in communication connection with each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the football player game analysis method in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions, and the computer instructions are used to make the computer execute the football player game analysis method in any one of claims 1 to 5.

9. A computer program product, characterised in that, The computer instructions are used to make the computer execute the football player game analysis method in any one of claims 1 to 5.

Images