Sports assistance system

Abstract

Provided is a system suitable for assisting professional athletes.　This sports assistance system 1 comprises a database that stores condition data 31 relating to the bodily and / or mental conditions of athletes and training data 32 relating to training performed by the athletes. This system 1, using the data in the database 1, displays a time-series change of exercise loads, a time-series change of physical and mental conditions, and a time-series change of injury risks for an entire team and for individual athletes in a manner that allows comparison. The system 1 comprises an athlete model, and the athlete model models the entire team or the individual athletes, and the athlete model simulates the effects and influence of planned training on the entire team or the individual athletes. The athlete model also provides advice for improving training, condition, performance, and lifestyle to the entire team or to the individual athletes.

Description

Sports Support System

[0001] The present invention relates to a computer-based sports support system for supporting sports teams and athletes (hereinafter sometimes simply referred to as "athletes") in terms of their condition, training, and / or performance.

[0002] For example, Patent Documents 1 to 3 disclose techniques relating to support for athletes.

[0003] Patent Literature 1 describes an exercise support device that collects a user's fatigue and sleep state and determines an exercise plan and exercise menu based on the collected data. The device acquires event information related to the user, acquires information about the practice days leading up to the event, and an exercise menu, and generates an exercise plan using the event information, practice day information, and exercise menu. The device determines the user's fatigue level and fatigue recovery state from pulse wave information at the start and end of sleep, and modifies the exercise menu or exercise plan based on the results of this determination.

[0004] Patent Literature 2 discloses a health management device that determines a user's physical condition based on the user's sleep state. This device acquires sleep information obtained by analyzing the pulse waves of a subject while they are sleeping, acquires training information that indicates the subject's training status, and determines the subject's physical condition, such as whether they are overtraining or recovering from overtraining, based on the acquired sleep information and training information.

[0005] Patent Literature 3 discloses a practice guidance providing device that provides practice guidance to a user. The device records practice feedback information indicating feedback from the user regarding practice execution. The device records self-check information entered by the user as information indicating the user's recent poor condition level, and calculates the user's accumulated poor condition level based on the recorded self-check information. The device determines multiple practice guidance information candidates to provide to the user based on the user's current poor condition level and the user's accumulated poor condition level. The device determines practice guidance information to provide to the user from multiple practice guidance information candidates based on recorded past practice feedback information and transmits the determined practice guidance information to a user terminal. The device receives practice feedback information indicating feedback from the user regarding practice execution based on the practice guidance information from the user terminal.

[0006] JP 2018-33566 A JP 2005-111160 A JP 2022-81036 A

[0007] In the case of professional athletes, they are supported by staff such as managers, coaches, medical supporters, and dietary managers. In this case, not only the athletes themselves but also each member of the staff must be well aware of the athletes' conditions, and appropriate communication must be maintained between the staff members and the athletes.

[0008] In sports teams with multiple players, the staff must be able to accurately understand not only the status of each individual player but also the status of the entire team, and manage them appropriately. The more players on a team, the more difficult it becomes to manage the team as a whole.

[0009] Additionally, the following concerns are often heard from both individual players and the team as a whole: "I can't fully demonstrate what I've learned in practice in matches," "There are many injuries and illnesses, but we don't know the cause," "There is a low level of awareness of the players' condition," and "It's difficult to design the optimal training plan."

[0010] Patent Documents 1 to 3 do not disclose sufficient solutions to these problems.

[0011] One object of the present invention is to provide a system suitable for supporting professional athletes.

[0012] Another object of the present invention is to provide a system for assisting a sports team that includes staff supporting multiple players.

[0013] It is yet another object of the present invention to provide a system that assists in better management of athletes' condition, performance and / or training.

[0014] Further objects of the present invention will become apparent from the following disclosure.

[0015] A sports support system according to one embodiment is a sports support system capable of communicating with one or more athlete terminals used by one or more athletes who make up a team playing a sport and one or more staff terminals used by one or more staff members who support the athletes, and is equipped with a database that stores condition data including one or more condition items related to the athletes' physical and / or mental condition and training data including one or more training items related to the training the athletes perform, and a dashboard control unit that uses the data stored in the database to create a first dashboard that displays team condition information related to the team's condition status and team training information related to the team's training status, and a second dashboard that displays player condition information related to the condition status of each player and player training information related to the training status of each player, and provides the first and second dashboards to each staff terminal and the second dashboard corresponding to each user to each athlete terminal.

[0016] According to one embodiment of the sports support system, the dashboard control unit does not provide the second dashboard corresponding to a player who is not a user of the athlete terminal to the athlete terminal.

[0017] According to one embodiment of the sports support system, the dashboard control unit creates a third dashboard that visualizes the status of the one or more athletes at a glance, and provides the third dashboard to the staff terminal.

[0018] In one embodiment of the sports support system, the dashboard control unit does not provide the third dashboard to each of the athlete terminals.

[0019] In one embodiment of the sports support system, the first dashboard displays the time series changes in the team condition information and the time series changes in the team training information so that they can be compared on the same time axis, and the second dashboard corresponding to each player displays the time series changes in the player condition information and the time series changes in the player training information for each player so that they can be compared.

[0020] According to one embodiment of the sports support system, the training data includes, as the training items, items related to the exercise load of the training performed by the player, and the first dashboard displays, on the same time axis, a time series progression of a first index related to the exercise load of the team based on the training data of the player, a time series progression of a second index related to the physical and / or mental condition of the team based on the condition data of the player, and a time series progression of a third index related to the risk of injury occurring according to the exercise load of the team, all of which are displayed in a comparable manner, and the second dashboard corresponding to each player displays, in a comparable manner, a time series progression of a fourth index related to the exercise load of each player, a time series progression of a fifth index related to the physical and / or mental condition of each player, and a time series progression of a sixth index related to the risk of injury occurring according to the exercise load of each player.

[0021] According to one embodiment of the sports support system, the training data includes, as the training item, an RPE (Rating of Perceived Exertion) input by the player regarding the training performed, the first indicator has a team RPE value regarding the team's RPE based on the RPE input by the player, the third indicator has a team ACWR (Acute: Chronic Workload Ratio) value regarding the team's ACWR based on the RPE input by the player, the fourth indicator has a player RPE value regarding the RPE input by each player, and the sixth indicator has a player ACWR value regarding each player's ACWR based on the RPE input by each player.

[0022] According to one embodiment of the sports support system, the second index has a team condition value that quantifies the physical and mental condition of the team based on the condition data of the players, and the fifth index has a player condition value that quantifies the physical and mental condition of each player based on the condition data of each player.

[0023] According to one embodiment of the sports support system, when the team includes one or more female players, the condition data includes an item related to the menstruation of the female player as the condition item, and the first dashboard displays physiological information related to the menstruation of the female player based on the condition data of the female player.

[0024] According to one embodiment of the sports support system, an alert determination unit is provided that sets an alert condition for each of one or more specified condition items, and determines whether or not an alert is issued for each of the specified condition items in the condition data of each of the players by referring to the corresponding alert condition, and the first dashboard displays team alert information regarding whether or not the team has been alerted based on the alert determination result, and the second dashboard corresponding to each of the players displays player alert information regarding whether or not the each player has been alerted based on the alert determination result.

[0025] According to one embodiment of the sports support system, the database further stores injury data including one or more injury items related to injuries or illnesses suffered by the player, and the first dashboard further displays team injury information related to injuries or illnesses of the team based on the injury data of the player.

[0026] According to one embodiment of the sports support system, the first dashboard displays the time series changes of the team injury information and the time series changes of both or one of the team condition information and the team training information in a manner that allows for comparison.

[0027] According to one embodiment of the sports support system, the database further stores treatment data including one or more treatment items related to medical treatments received by the player, and the first dashboard further displays team treatment information related to medical treatments of the team based on the treatment data of the player.

[0028] In one embodiment of the sports support system, the database further stores physical data including one or more physical items related to the physical performance of the players, the first dashboard further displays team physical information related to the physical performance of the team based on the physical data of the players, and the second dashboard further displays player physical information related to the physical performance of each of the players based on the physical data of each of the players.

[0029] In one embodiment of the sports support system, the first dashboard displays the time series changes in the team physical information and the time series changes in both or either of the team condition information and the team training information so that they can be compared on the same time axis, and the second dashboard corresponding to each player displays the time series changes in the player physical information and the time series changes in both or either of the player condition information and the player training information for each player so that they can be compared.

[0030] In one embodiment of the sports support system, the database further stores stats data including one or more stats items related to the stats of the team and each of the players, the first dashboard further displays team stats information related to the stats of the team based on the stats data of the team, and the second dashboard further displays player stats information related to the stats of each of the players based on the stats data of each of the players.

[0031] In one embodiment of the sports support system, the first dashboard displays the time series changes in the team stats information and the time series changes in both or one of the team condition information and the team training information so that they can be compared, and the second dashboard corresponding to each player displays the time series changes in the player stats information and the time series changes in both or one of the player condition information and the player training information for each player so that they can be compared.

[0032] According to one embodiment of the sports support system, the database further stores physical data including one or more physical items related to the physical performance of the player and stats data including one or more stats items related to the stats of the team and each of the player, the first dashboard further displays team physical information related to the physical performance of the team based on the physical data of the player and team stats information related to the stats of the team based on the stats data of the team, and the second dashboard further displays player physical information related to the physical performance of each player based on the physical data of each player and player stats information related to the stats of each player based on the stats data of each player.

[0033] According to one embodiment of the sports support system, the first dashboard displays the time series changes in the team physical information and the time series changes in the team stats information in a comparable manner, and the second dashboard corresponding to each player displays the time series changes in the player physical information and the time series changes in the player stats information for each player in a comparable manner.

[0034] The sports support system of one embodiment further includes a training planning unit that enables the staff member to plan a training menu, stores the planned training menu in the database as the training item, and provides the planned training menu to the staff terminal and the player terminal, and a training simulator that inputs the planned training menu and estimates the effects of implementing the planned training menu that may appear in the training data or condition data of the team or each player if the planned training menu is implemented by the team or each player.

[0035] In one embodiment of the sports support system, the implementation effect includes ACWR of the team or each of the players that may result from the implementation of the planned training menu.

[0036] According to one embodiment of the sports support system, the database further stores injury data related to injuries or illnesses suffered by the players, physical data related to the physical performance of the players, statistical data related to the respective statistical data of the team and the players, and / or physical growth data related to the physical growth of the players, and the system further includes a training planning unit that enables the staff members to plan training menus, stores the planned training menus in the database as the training items, and provides the planned training menus to the staff terminals and the player terminals, and a training simulator that inputs the planned training menus and estimates the effects of implementing the planned training menus that may appear in the training data, condition data, injury data, physical data, statistical data, and / or physical growth data of the team or each player if the planned training menus are implemented by the team or each player.

[0037] In one embodiment of the sports support system, the training simulator has a player model that has learned the relationship between the training menu actually implemented by the team or each player and the actual implementation effect, and uses the player model to estimate the implementation effect of the planned training menu.

[0038] In one embodiment, the sports support system further includes a training proposer that sets goals for the condition data or the training data of the team or each player, automatically creates a training menu in accordance with the goals, and proposes it to the staff terminal or the player terminal.

[0039] In one embodiment of the sports support system, the database further stores injury data related to injuries or illnesses suffered by the player, physical data related to the player's physical performance, stats data related to the stats of the team and each of the player, and / or physical growth data related to the player's physical growth, and further includes a training proposer that sets goals for the team or each of the players' condition data, training data, injury data, physical data, stats data, and / or physical growth data, automatically creates a training menu according to the goals, and proposes it to the staff terminal or the player terminal.

[0040] According to one embodiment of the sports support system, the database further stores physical data regarding the physical performance of each of the players, sets ranking criteria for the physical data of each of the players, and further includes a physical evaluation unit that ranks the physical data of each of the players in light of the ranking criteria, and is configured to provide the ranking results of each of the players to the staff terminal or the player terminal.

[0041] According to one embodiment of the sports support system, the database further stores stats data regarding the stats of the team or each player, sets evaluation criteria for the stats data, and further includes a stats evaluation unit that evaluates the stats data in light of the evaluation criteria, and is configured to provide the evaluation results of the stats data to the staff terminal or the player terminal.

[0042] In one embodiment of the sports support system, the database further stores injury data relating to injuries or illnesses sustained by the athlete, and further includes an injury prevention section that presents the injury data to the staff terminal, enabling the staff to create a plan to prevent the occurrence of the injury or illness, and a rehabilitation planning section that presents the injury data to the staff terminal, enabling the staff to create a rehabilitation plan for recovery from the injury or illness.

[0043] According to one embodiment of the sports support system, the database stores treatment data regarding medical procedures performed by the staff members on the athletes, and further includes a treatment analysis unit that analyzes the treatment data to create analytical data indicating the number or amount of medical procedures performed for each staff member, and is configured to provide the analytical data to the staff terminal.

[0044] According to one embodiment of the sports support system, the database further stores physical growth data regarding the physical growth of each of the players, and further includes a physical growth prediction unit that predicts the future physical growth of each of the players based on the physical growth data of each of the players, and is configured to provide the predicted physical growth of each of the players to the staff terminal or the player terminal of each of the players.

[0045] 1 is a block diagram showing the hardware configuration of a sports support system according to one embodiment of the present invention. FIG. 2 is a block diagram showing the software configuration of a sports support system according to one embodiment of the present invention. FIG. 3 is a diagram showing examples of data items of various data input from the user terminal of a staff member or a player. FIG. 4 is a block diagram showing the functional configuration of a dashboard control unit. FIG. 5 is a diagram showing an example of a display of a team dashboard. FIG. 6 is a diagram showing an example of a display of a player list dashboard. FIG. 7 is a diagram showing an example of a display of a player dashboard. FIG. 8 is a diagram showing an example of a display of detailed information on the dashboard. FIG. 9 is a block diagram showing the functional configuration of a condition management unit. FIG. 10 is a block diagram showing the functional configuration of a training management unit. FIG. 11 is a block diagram showing the functional configuration of a physical management unit. FIG. 12 is a block diagram showing the functional configuration of a stats management unit. FIG. 13 is a block diagram showing the functional configuration of an injury management unit. FIG. 14 is a block diagram showing the functional configuration of a treatment management unit. FIG. 15 is a block diagram showing the functional configuration of a physical growth management unit. FIG. 16 is a block diagram showing an example of the functional configuration of a player model. FIG. 17 is a block diagram showing another example of the functional configuration of a player model. FIG. 18 is a block diagram showing an example of the functional configuration of a training proposer. FIG. 19 is a block diagram showing another example of the functional configuration of a player model. FIG. 19 is a block diagram showing another example of the functional configuration of a player model. FIG. 19 is a block diagram showing another example of the functional configuration of a player model. FIG. 1 is a block diagram showing another example of the functional configuration of a player model. FIG. 2 is a block diagram showing another example of the functional configuration of a player model. FIG. 3 is a block diagram showing another example of the functional configuration of a player model. FIG. 4 is a block diagram showing another example of the functional configuration of a player model. FIG. 5 is a block diagram showing another example of the functional configuration of a player model. FIG. 6 is a block diagram showing another example of the functional configuration of a player model. FIG. 7 is a block diagram showing another example of the functional configuration of a player model.

[0046] Hereinafter, embodiments will be described with reference to the drawings. These embodiments are exemplary for explaining the present invention, and some omissions and simplifications have been made as appropriate for clarity of explanation. Furthermore, the present invention is not limited to these embodiments, and all applications consistent with the concept of the present invention are included within the technical scope of the present invention.

[0047] Figure 1 is a block diagram showing the hardware configuration of a sports support system according to one embodiment of the present invention. Sports support system 1 (hereinafter sometimes abbreviated as system 1) includes storage 13 that stores a program 15 and a database (DB) 16, a central processing unit (CPU) 11 that executes the program 15 and processes the DB 16, memory 12 used by the CPU 11, and a communication interface 10 that communicates with the outside world via a communication network. For convenience, sports support system 1 is shown in Figure 1 as being composed of a single computer, but sports support system 1 may be realized by multiple computers or may be provided as a cloud server.

[0048] The sports support system 1 and one or more user terminals 2 used by one or more users are connected to each other so as to be able to communicate with each other via a communication network (e.g., the Internet or an intranet) 4. The users may include players as well as staff members such as managers, coaches, medical supporters, and diet managers.

[0049] The user terminal 2 is an information processing terminal used by each athlete and each staff member, such as a personal computer, a mobile phone, a tablet terminal, etc. Depending on whether each user is an athlete or a staff member, the GUI (Graphical User Interface) displayed on the screen of the user terminal 2 for communication between the user and the sports support system 1 is selected as either an athlete GUI or a staff GUI.

[0050] Each athlete can use the athlete GUI to input data regarding their own condition, training results, etc. into the sports support system 1, view data regarding their own condition output from the sports support system 1, and view data regarding their training plan, performance, etc.

[0051] Each staff member can use the staff GUI to input data regarding the management of the condition, training, performance, injuries, etc. of the entire team and individual players into the sports support system 1, and can also view data regarding the condition, training, performance, injuries, etc. of the entire team and individual players.

[0052] The measuring devices 3 are various devices that measure the movement and physical condition of athletes. There are many types of measuring devices 3, including, for example, GNSS devices that measure various movement conditions of athletes using a Global Navigation Satellite System (GNSS), wearable measurement devices that measure various physical conditions of athletes, body composition monitors that measure athletes' body composition, Velocity Based Training (VBT) devices that measure athletes' movement speeds, and IoT balls that measure various movement conditions of balls used by athletes in ball games such as baseball and soccer. Data measured by the measuring devices 3 is typically sent to the sports support system 1 via a user terminal 2 (for example, a user terminal for athletes as shown in the figure, but may also be a user terminal for staff), but may also be input to the sports support system 1 via another route (for example, directly from the measuring devices 3 via a network without going through the user terminal 2).

[0053] Fig. 2 is a block diagram showing the software configuration of a sports support system according to an embodiment of the present invention. Fig. 3 is a diagram showing examples of data items of various data input from the user terminals of staff or athletes.

[0054] As shown in FIG. 2, the sports support system 1 includes a DB 16, a dashboard control unit 20, various management units 21 to 27, and a user I / F .

[0055] The user I / F 28 has a function of receiving various data from the user terminal 2 via the network and passing it to the dashboard control unit 20 and the various management units 21 to 27. The user I / F 28 also has a function of transmitting the various data received from the dashboard control unit 20 and the various management units 21 to 27 to the user terminal 2 via the network.

[0056] The DB 16 has various data sections 30 to 37 necessary for implementing one embodiment of the present invention. The analysis data section 30 stores the analysis data that is the result of analyzing the various data managed by the various management sections 21 to 27 and is to be displayed on the dashboard.

[0057] The condition data section 31 stores condition data managed by the condition management section 21. Condition data is data indicating various physical and / or mental conditions of the athlete, and includes subjective data based on the athlete's subjective opinion and objective data observed objectively, as shown in FIG. 3 . Subjective data may include, for example, data on items such as physical pain, feeling of deep sleep, physical fatigue, mental fatigue, and muscle condition. Objective data may include, for example, data on items such as blood oxygen saturation, heart rate variability, sleep duration, diet, and menstruation.

[0058] The training data section 32 stores training data managed by the training management section 22. Training data is data related to the athlete's training, and includes subjective data and objective data as shown in FIG. 3. Subjective data may include, for example, data related to items such as RPE (Rating of Perceived Exertion). Objective data may include, for example, data related to items such as training menu, training time, GNSS data, and pulse rate during exercise.

[0059] The physical data section 33 stores the physical data managed by the physical management section 23. The physical data is data showing the results of testing and measuring the physical performance of the athlete, such as athletic ability and / or muscle strength, and includes objective data such as that shown in Fig. 3. Examples of objective data include data on various items obtained from health checkups, field tests, muscle strength measurements, body composition scales, VBT devices, etc.

[0060] The stats data unit 34 stores the stats data managed by the stats management unit 24. Stats data is stats, that is, data that indicates, for example, the performance, results, or accomplishments achieved in a match, and includes objective data such as that shown in FIG. 3. Taking soccer as an example, objective data can include data on items such as win rate, goals scored and conceded, number of shots taken, number of shots taken, and corner kicks. The stats data includes data on the stats of the entire team and data on the stats of each player.

[0061] The injury data section 35 stores injury data managed by the injury management section 25. Injury data is data related to a player's injuries and illnesses, and includes objective data such as that shown in Figure 3. Examples of objective data include data related to items such as the facts of the injury or illness, the cause of the injury, the location of the injury or illness, an injury prevention plan, and a rehabilitation plan.

[0062] The treatment data section 36 stores treatment data managed by the treatment management section 26. Treatment data is data related to medical treatment for an athlete's injury or illness, and includes objective data such as that shown in Fig. 3. Examples of objective data include data related to items such as treatment content, treatment site, and treatment time.

[0063] The physical growth data section 37 stores the physical growth data managed by the physical growth management section 27. The physical growth data is data relating to the physical growth of a young player who is in the growth stage, and includes objective data such as that shown in Fig. 3. Examples of the objective data include data relating to items such as gender, age, parental physique, and physical measurements.

[0064] In this specification, the various data items included in the condition data, training data, physical data, stats data, injury data, treatment data, and physical growth data, as illustrated in Figure 3, may be referred to as condition items, training items, physical items, stats items, injury items, treatment items, and physical growth items, respectively.

[0065] As shown in Figure 2, the sports support system 1 includes, as processing functions according to one embodiment of the present invention, a dashboard control unit 20, a condition management unit 21, a training management unit 22, a physical management unit 23, a stats management unit 24, an injury management unit 25, a treatment management unit 26, and a physical growth management unit 27.

[0066] The dashboard control unit 20 analyzes data such as condition, training, physical status, stats, injuries, treatments, and physical growth managed by the various management units 21 to 27, and visualizes the overall team and individual player status and the analysis results in easy-to-read graphs and tables in the form of a dashboard, which is displayed to staff and each player. This allows staff to easily grasp the overall team status and the status of each player, and also allows each player to easily grasp their own status.

[0067] The condition management unit 21 accumulates and manages condition data input by the user (for example, daily condition information input by the player, such as fatigue level, sleep time, and physical pain) in the condition data unit 31. Furthermore, the condition management unit 21 analyzes the condition data and creates analytical data that can be displayed on a dashboard (allowing staff to check the player's condition and allowing the player to check their own condition), and stores this data in the analytical data unit 30. Players can know their own condition, and staff members can know the condition of the entire team or players, and this information can be used to adjust the quantity and quality of training and to provide individual support to players.

[0068] The training management unit 22 accumulates and manages training data input by users (e.g., training menus input by staff members, training results input by athletes, RPE for the training, and / or objective GNSS data in Lenin) in the training data unit 32. Furthermore, the training management unit 22 analyzes the training data, creates analytical data that can be displayed on a dashboard (visualizing the athletes' exercise load and injury risk), and stores the analytical data in the analytical data unit 30. The training data and its analysis results can be used by staff members and / or athletes to manage training and condition and support athletes, for example, by adjusting the training load by calculating backward from exercise intensity, adjusting the training load to maintain good condition by considering the relationship between training and the athletes' condition, or adjusting the quality and quantity of training so that the likelihood of injury does not reach a dangerous level.

[0069] The physical management unit 23 accumulates and manages physical data input by the user (e.g., measurement data for test items arbitrarily determined by each team, such as physical examinations (blood, urine specific gravity, etc.), regular athletic ability tests and / or muscle strength tests, and further measurement data for test items specialized for each sport, such as soccer, baseball, or rugby) in the physical data unit 33. Furthermore, the physical management unit 23 analyzes the physical data to create analytical data that can be displayed on a dashboard, and stores the analytical data in the analytical data unit 30. The physical data and its analysis results can be used by staff members and / or players to manage training and condition and support players, for example, by predicting the relationship between the physical data and training data and adjusting the quality and quantity of training to improve the physical data, or by predicting the relationship between the physical data and condition data and managing the players' condition to obtain desired physical data.

[0070] The stats management unit 24 accumulates and manages stats data input by the user (for example, data input by staff regarding the performance and achievements of the team and each player in a game, etc.) in the stats data unit 34. Furthermore, the stats management unit 24 analyzes the stats data to create analytical data that can be displayed on a dashboard, and stores the analytical data in the analytical data unit 30. The stats data and the analysis results can be used by staff members and / or players to manage training and condition and support players, for example, by inferring the relationship between the stats data and training data and adjusting the quality and quantity of training to improve the stats data, or by inferring the relationship between the stats data and condition data and managing the players' condition to obtain desirable stats data.

[0071] The injury management unit 25 accumulates and manages injury data (such as type of injury, cause, location, and rehabilitation plan) input by the user in the injury data unit 35. Furthermore, the injury management unit 25 analyzes the injury data to create analytical data that can be displayed on a dashboard, and stores the analytical data in the analytical data unit 30. The injury data and its analysis results can be used by staff members and / or players to manage training, condition, and injury management, and to support players, for example, by predicting the relationship between injury and training data to adjust the quality and quantity of training so that the likelihood of injury or illness does not reach a dangerous level, by predicting the relationship between injury data and condition data to manage players' condition so that the likelihood of injury or illness does not reach a dangerous level, by referring to injury or illness history to develop injury prevention plans, and by creating rehabilitation plans depending on the type, location, and severity of injury or illness.

[0072] The treatment management unit 26 accumulates and manages treatment data (records of treatments for injuries) input by the user in the treatment data unit 36. Furthermore, the treatment management unit 26 analyzes the treatment data to create analytical data that can be displayed on a dashboard, and stores the analytical data in the analytical data unit 30. The treatment data and its analysis results can be used by staff and / or athletes to manage injury treatment and support athletes, for example, by sharing information about treatments for athletes' injuries among staff members to seamlessly continue appropriate treatment, or by dividing up treatment tasks among staff members.

[0073] The physical growth management unit 27 accumulates and manages the physical growth data input by the user in the physical growth data unit 37. Furthermore, the physical growth management unit 27 analyzes the physical growth data to create analytical data that can be displayed on a dashboard, and stores the analytical data in the analytical data unit 30. The physical growth data and the analysis results can be used by staff and / or players to manage training and support players, for example, by predicting future physical growth curves, estimating the relationship between physical growth and training, athletic ability, muscle strength, and / or stats data, and creating appropriate training plans.

[0074] Fig. 4 is a block diagram showing the functional configuration of the dashboard control unit. Fig. 5 is a diagram showing an example of a team dashboard display. Fig. 6 is a diagram showing an example of a player list dashboard display. Fig. 7 is a diagram showing an example of a player dashboard display.

[0075] As shown in FIG. 4, the dashboard control unit 20 includes a team dashboard control unit 40, a player list dashboard control unit 41, and a player dashboard control unit 42 as processing functions according to one embodiment of the present invention.

[0076] The team dashboard control unit 40 reads out the analytical data analyzed by the various management units 21 to 27 from the analytical data unit 30, and creates a team dashboard (see FIG. 5 ), which is a dashboard for understanding the overall team situation using the read analytical data, and provides it to the staff's user terminal 2. In this way, displaying the overall team situation to the staff can be useful for managing the entire team. In this embodiment, to protect the privacy of players, the team dashboard is not provided to the players' user terminals 2.

[0077] In this embodiment, a team dashboard such as that shown in FIG. 5 is provided to the staff member's user terminal 2, and various status items for the entire team are displayed on one page. This allows the staff member to easily grasp the status of the entire team. Furthermore, even during busy times such as before training, the staff member can grasp the overall team's trends at a glance. In addition, each status item block can be used to transition to a page showing details of that item, making it easy to access all information using the team dashboard as a starting point.

[0078] Here, the following eight items are examples of items that can be checked on the team dashboard shown in Figure 5. Item 1: Today's participation status This displays the number of players who fall into various statuses related to participation in today's training (participating, participating with restrictions, not participating, etc.). These numbers are entered, for example, by staff. Clicking on each status will take you to the player list dashboard, where you can check the status of each player who falls into that status.

[0079] Item 2: Team Workload This displays the total or average exercise load (e.g., sRPE: session RPE), condition index, and ACWR (as well as Acute and Chronic) of the team's players over time. The displayed content is created by analyzing condition data, training data, etc. Here, RPE is the player's evaluation of the level of training load (strength) perceived by the player on a 10-point scale. sRPE is the value obtained by multiplying the RPE of a training session by the duration (minutes) of that training session. ACWR (Acute: Chronic Workload Ratio) is the ratio of the amount of load a player has performed over the past seven days (Acute load) to the average weekly load performed over the past 28 days (Chronic load). Generally, managing exercise load so that ACWR values ​​fall within the "optimal range" of 0.8 to 1.3 reduces the risk of injury or disability, but exceeding 1.5 (the "dangerous range") increases the risk of injury or disability. A condition index is an index that represents a player's current condition (e.g., a rating scale of 100 ranging from excellent to extremely poor). The condition index can be calculated, for example, by quantifying and integrating condition items related to physical pain and physical and / or mental fatigue using a predetermined statistical calculation method. By comparing the trends in the team's overall sRPE (subjective exercise load), ACWR (an index indicating the likelihood of injury based on exercise load), and condition index (level of physical and / or mental condition) over the same time axis, staff can predict how the team's exercise load is evolving and how it is affecting the players' condition (e.g., pain and fatigue), which can be useful for managing future condition and training.

[0080] Item 3: Injury Status Players who have an injury or illness (including injuries and illnesses) that have not yet recovered are displayed along with the diagnosis of the injury and the expected return date. The display content is created by analyzing injury data. Staff can see who is injured and when they will be able to return, which can be useful for managing future condition and training.

[0081] Item 4: Menstrual Cycle For female players on the team, information related to their menstrual cycle is displayed, such as whether they are menstruating, and if so, how many days since the start of their period, and the average number of days their period lasts. The displayed information is created by analyzing the menstrual data in the condition data. By identifying which players are menstruating and understanding which stage of the menstrual cycle a female player is currently in, staff can use this information to adjust individual training for each female player.

[0082] Item 5: Player Alert Status Displays the number of alerts for the team's players for multiple pre-selected alert items. The number of alerts for each item indicates the number of players who have met the specified alert condition for that item (for example, the alert condition for ACWR is "1.5 or higher," which indicates a danger zone). These display contents are created by analyzing condition data and / or training data. Staff can get a rough idea of ​​the team's condition by understanding the number of alerts for each item. From this block, they can transition to a screen where they can check the detailed status of each item or player.

[0083] Item 6: Treatment status for the previous day This shows the number of treatments (treatments for injuries and illnesses) given to athletes on the previous day. The displayed content is created by analyzing treatment data. Staff can see how many treatments were given on the previous day.

[0084] Item 7: Player data entry status Displays the status of required data entry by players (for example, entry of daily condition data or training data) (for example, how many players have not entered data). By knowing how many players on the team have entered data and how many have not, staff can use this information to interpret the data and to remind players to enter data. Item 8: Overall schedule Displays the schedule for today's team activities.

[0085] 4, the player list dashboard control unit 41 reads out the analytical data analyzed by the various management units 21 to 27 from the analytical data unit 30, and uses the read out analytical data to create a player list dashboard (see FIG. 6), which is a dashboard that lists the statuses and situations of multiple players belonging to a team and makes them visible at a glance, and provides this to the staff's user terminal 2. In this embodiment, in order to protect the privacy of players, the player list dashboard is not provided to the players' user terminals 2.

[0086] In this embodiment, the condition and player status (practice participation status) of all players on a team (or players narrowed down by some criteria) are displayed in a list format using a player list dashboard such as that shown in Figure 6. In the player list dashboard shown in Figure 6, one player box 200 is assigned to each player, and there are multiple player boxes 200 corresponding to multiple players on the team. This allows staff to understand before training who can participate in training, whether any players are in poor condition, and what condition each player is in, and share this information with other staff members to use in managing today's training and condition.

[0087] Examples of items that can be checked on the player list dashboard shown in Figure 6 include, for each player, their status (practice participation status), condition index (an index showing the level of physical and / or mental condition), the numerical values ​​of multiple pre-selected condition items and whether or not there are any alerts, and a comment from the medical staff regarding the player's condition (for example, by displaying the medical staff's impressions of the previous day's treatment, this can be shared with other staff). The arrangement of player boxes may be sorted in order of the condition index numerical value, the number of alerts, player status, etc., and each player's box may be used to transition to a player dashboard showing each player's detailed status.

[0088] 4, the player dashboard control unit 42 reads out the analytical data analyzed by the various management units 21 to 27 from the analytical data unit 30, and uses the read-out analytical data to create a player dashboard (see FIG. 7), which is a dashboard for viewing the status and situation of each player, and provides it to the staff user terminal 2 and the player user terminal 2. In this embodiment, only the player dashboard of each player is displayed on the user terminal 2 of each player, and the three dashboards of the other players are not displayed.

[0089] In this embodiment, a player dashboard such as that shown in FIG. 7 displays each player's basic information, condition data, exercise load data, physical data, and stat data, as well as detailed daily trends in injury and treatment history. Regarding condition data, the daily trends for each of a number of specified condition items are visually displayed, for example, in graph form. Although not shown, if the condition data value for each item indicates a problem (satisfies an alert condition) (e.g., ACWR is 1.5 or higher, which is in the danger zone), an alert mark (e.g., a red or yellow mark) is displayed for that item. This allows staff to grasp the detailed status of all players from the past to the present, and each player can understand their own detailed status from the past to the present and whether or not there are any condition problems. Therefore, staff can utilize this information for detailed management of each player's condition, training, performance, and so on.

[0090] By utilizing dashboards like those described above (Figures 5 to 7), staff can understand the overall team situation and manage the team as a whole, and by understanding the status of each individual player, they can provide support to each individual player. In other words, by making good use of dashboards like those described above, staff can more easily manage teams with a large number of players. Furthermore, by displaying only the status of each player, each player can clearly understand their own situation and use it to improve the effectiveness of their training and match performance, while protecting the privacy of other players.

[0091] 5 to 7 show simplified examples of the display of each dashboard for the sake of explanation, but each dashboard can also display more detailed information. As an example, FIG. 8 shows a detailed example of a team dashboard displaying the daily changes in the training load (session RPE, ACWR) and condition (condition index) of the entire team.

[0092] In this example, the team's overall session RPE is displayed for each type of training (e.g., weight training, skill training, games, etc.), and the team's average ACWR and condition index are displayed overlaid on the same timeline. This detailed comparison of training intensity and condition is useful for staff to appropriately consider, for example, what type of training, at what intensity and volume, should be distributed to maximize the condition index (physical and mental condition) while minimizing injury by controlling ACWR within an appropriate range (1.3-0.8). This detailed information can be displayed for not only the team but also each player, and can also display progress over time, not just days but also months and years.

[0093] Furthermore, training data, condition data, physical data, stats data, injury data, etc. of a team or each player can be understood or displayed using charts, tables, etc., or two or more of the above different types of data can be correlated and displayed (for example, graphs of the time series (e.g., daily) trends of the different types of data can be overlaid or displayed side by side for comparison on the same time axis.) For example, when the time series trends of one or more items of physical data, stats data, and / or injury data are displayed in a comparable manner on a common time axis, staff and / or players can infer, for example, how the type and intensity of training affect the athletic ability, game performance, and / or injuries of the team or each player, or how the condition of the team or each player affects their athletic ability, performance, and / or injuries. Furthermore, for example, if the time series transition of physical data and the time series transition of stats data are displayed in a comparative manner, it is possible to infer how the physical performance shown in the physical data affects the performance shown in the stats data, etc. This is useful for considering how to control the condition and plan training in order to improve the ability or performance of the team or each player.

[0094] 9 is a block diagram showing the functional configuration of the condition management unit. As shown in FIG. 9, the condition management unit 21 includes, as processing functions according to one embodiment of the present invention, a condition input unit 43, an alert determination unit 44, a condition analysis unit 45, and a condition support unit 46. Each player periodically, for example, daily, enters their own condition data for a predetermined number of condition items (illustrated in FIG. 3) into the system 1 from the user terminal 2. A staff member can also enter the player's condition data from the staff terminal 2 on behalf of the player.

[0095] The condition input unit 43 receives the input condition data of each player, organizes it by player and by condition item (example shown in FIG. 3), and stores it in the condition data unit 31.

[0096] The alert determination unit 44 determines whether the condition data for each condition item of each player in the condition data unit 31 meets the alert conditions or criteria (e.g., thresholds) set in advance for each condition item, and whether the condition is met (whether there is a problem). If there is a problem, the alert determination unit 44 records the alert data in association with the corresponding condition data in the condition data unit 31. The alert conditions (thresholds) can be set as different types of values, such as fixed values, ratios (e.g., ratios to the previous day's data value), standard deviations, or fluctuation ranges, depending on the nature of the condition item. For example, thresholds can be set as follows: As an example of determining whether a condition is greater than / less than a fixed value, a body temperature of 37.5°C or higher can be set as the alert condition. As an example of determining whether a condition is greater than / less than a certain percentage from the previous day's value, a weight loss of 2% or more can be set as the alert condition. As an example of determining whether a condition is greater than / less than the average value of the most recent three months' data by a threshold value, a fatigue level deviating downward by more than two standard deviations can be set as the alert condition.

[0097] The condition analysis unit 45 analyzes the condition data in the condition data unit 31, and converts the analysis results, such as the daily progress and the presence or absence of alerts, into analytical data that can be displayed in a visual format such as a graph (for example, in a format displayed on a dashboard such as those shown in FIGS. 5 to 7), and stores this analytical data in the analytical data unit 30. The analytical data is displayed on the user terminals 2 of the staff and players by the dashboard control unit 20 (FIG. 2).

[0098] The condition support section 46 enables each staff member and each player to communicate, via each user terminal 2, messages such as guidance and assistance from the staff member according to the player's condition and messages such as consultations and questions from the player.

[0099] 10 is a block diagram showing the functional configuration of the training management unit 22. As shown in FIG. 10, the training management unit 22 includes, as processing functions according to an embodiment of the present invention, a training planning unit 47, a training result unit 48, a training analysis unit 49, a training simulator 50, and a training proposer 51.

[0100] The training planning unit 47 enables a user, particularly a staff member (or individual player), to use the user terminal 2 to create a training menu for the entire team or each player, for example, for each day from tomorrow onwards. The training menu includes menu items such as the type of training exercise (various types of running, various types of weight training, various skill practice, etc.), the training load (running distance, weight, number of exercises, etc.), and training time (date, time, duration, etc.). The training planning unit 47 allows the user to plan a training menu by selecting each menu item from predetermined options or by typing it in. The training planning unit 47 stores the planned training menu in the training data unit 32 and displays the stored training menu on the user terminal 2 of each player or staff member.

[0101] The training result section 48 inputs the training menu (whether according to the planned menu or a different menu) that each player performed, for example, every day, and the RPE for that training from each player's terminal 2 as training results, and stores them in the training data section 32.

[0102] The training analysis unit 49 calculates the session RPE, ACWR, etc. for each athlete's training results stored in the training data unit 32, performs analysis such as determining whether the ACWR is in a dangerous range above the alert threshold of 1.5, and edits the analysis results into a format that can be visualized and displayed on a dashboard such as those shown in Figures 5 to 8, and stores the analysis data unit 30. The analysis results are displayed on the user terminal 2 by the dashboard control unit 20 (Figure 2).

[0103] The training simulator 50 inputs an arbitrary training menu (e.g., a training menu created by a staff member using the training planning unit 47) and predicts the results or effects that will be obtained by implementing that training menu. Here, the results or effects may be data indicating the direct results or effects of the training, such as the player's RPE (or session RPE) or ACWR, or data indicating the indirect results or effects of the training, such as the player's condition data, physical data, stats data, or injury data that occur after the training. The training simulator 50 has, for example, a player model, which is a mathematical model that simulates at least one player. The training simulator 50 may have multiple individual player models that simulate multiple players belonging to a team, a national player model that simulates an average or representative player, or several player category models that simulate representative or average players in several player categories (e.g., player groups distinguished by player attributes such as gender, age, physique, experience, ranking, and position). A more detailed description of the player models will be provided below.

[0104] In the configuration example shown in FIG. 10 , the training simulator 50 has multiple player models 50A, 50B, and 50C corresponding to multiple players (player A, player B, and player C) on a team. When a user creates a training menu for the next day or later, the user can input the training menu into the training simulator 50. The training simulator 50 then inputs the input training menu into each of the player models 50A, 50B, and 50C, and simulated training results are output from each of the player models 50A, 50B, and 50C. The training simulator 50 provides feedback to the user on the training results from each of the player models 50A, 50B, and 50C, or the training results for the entire team obtained by integrating these results. Based on this feedback, the user can determine the quality of the created training menu. Using the training simulator 50 in this way helps the user create an appropriate training menu.

[0105] The training proposer 51 automatically creates a training menu that meets the training conditions specified by the user and proposes it to the user. Here, the training conditions are, for example, conditions related to training results. Examples of training conditions that can be specified include an ACWR value or value range (e.g., specifying a value of 1.0 or a range of 0.9 to 1.1), not issuing an alert for one or more specific condition items, the data for one or more specific physical items reaching a specific target value by a specific time, the data for one or more specific stat items reaching a specific target value by a specific time, or a training intensity adjustment percentage for each phase of the menstrual cycle (follicular phase, ovulation phase, luteal phase, menstrual phase). The training proposer 51 may be configured to input an existing training menu, such as a training menu created by the user, and modify it to meet the training conditions. Alternatively, the training proposer 51 may be configured to automatically create a menu that meets the training conditions without inputting an existing training menu. A more detailed description of the training proposer 51 will be provided later.

[0106] 11 is a block diagram showing the functional configuration of the physical management unit. As shown in FIG. 11, the physical management unit 23 includes, as processing functions according to one embodiment of the present invention, a physical input unit 52, a physical evaluation unit 53, a physical analysis unit 54, and a physical support unit 55. When each player or staff member periodically or as needed measures predetermined physical items (e.g., body composition, muscle strength, athletic ability, etc.) (illustrated in FIG. 3), the measurement data (physical data) for those physical items is input to the system 1 from the user terminal 2.

[0107] The physical input unit 52 receives the input physical data of each player, organizes it by player and by physical item, and stores it in the physical data unit 33.

[0108] The physical evaluation unit 53 ranks the physical data for each physical item of each player stored in the physical data unit 33 according to a predetermined ranking standard for each physical item (for example, a standard value for weight or body weight ratio in the case of muscle strength data) (e.g., dividing the data into three or five levels). The physical evaluation unit 53 also compares the data for each physical item of each player with a predetermined target value for each physical item to determine the degree to which the target value has been reached, evaluates the data by comparing it with the average or representative value for the team, or compares the data between players. The evaluation results for each item are associated with the data for each item and stored in the physical data unit 33.

[0109] The physical analysis unit 54 analyzes the data for each item in the physical data unit 33, and compiles the analysis results, such as daily changes, comparisons between players, the above-mentioned evaluation results, and the degree of balance in ranking levels between multiple physical items, into analytical data that can be displayed in a visual format such as a line graph, radar chart, or list, and stores the analytical data in the analytical data unit 30. The analytical data is displayed on the user terminals 2 of the staff and players by the dashboard control unit 20 (FIG. 2).

[0110] The physical support unit 55 enables each staff member and each player to communicate, via each user terminal 2, messages such as guidance and assistance from the staff member according to the physical data of the player, and messages such as consultations and questions from the player.

[0111] 12 is a block diagram showing the functional configuration of the stats management unit. As shown in FIG. 12, the stats management unit 24 includes, as processing functions according to one embodiment of the present invention, a stats input unit 56, a stats evaluation unit 57, a stats analysis unit 58, and a stats support unit 59. After each game, staff members acquire data on predetermined stats items (illustrated in FIG. 3 ) for each player and input the data into the system 1 from the user terminal 2.

[0112] The stats input unit 56 receives the input stats data for each player, organizes it by player and by stats item, and stores it in the stats data unit 34 .

[0113] The stats evaluation unit 57 evaluates the stats data for each stats item of each player in the stats data unit 34 in light of evaluation criteria preset for each stats item. The stats evaluation unit 57 also compares the data for each stats item of each player with target values ​​preset for each stats item and determines the degree to which the target values ​​have been reached. The evaluation results for each item are associated with the data for each item and stored in the stats data unit 34.

[0114] The stats analysis unit 58 analyzes the data for each item in the stats data unit 34, and compiles the analysis results, such as daily trends, comparisons between players, the above-mentioned evaluation results, and the degree of balance of evaluation results among multiple stats items, into analytical data that can be displayed in a visual format such as a line graph, radar chart, or list, and stores the analytical data in the analytical data unit 30. The analytical data is displayed on the user terminals 2 of the staff and players by the dashboard control unit 20 (FIG. 2).

[0115] The stats support unit 59 enables each staff member and each player to communicate, via their respective user terminals, messages such as guidance and assistance from the staff member according to the player's stats data, and messages such as consultations and questions from the player.

[0116] 13 is a block diagram showing the functional configuration of the injury management unit. As shown in FIG. 13, the injury management unit 25 includes, as processing functions according to one embodiment of the present invention, an injury input unit 60, an injury prevention unit 61, a rehabilitation planning unit 62, an injury analysis unit 63, and an injury support unit 64. When a player or staff member suffers an injury or illness, they input data (injury data) for specified injury items (examples of which are shown in FIG. 3) into the system 1 from the user terminal 2.

[0117] The injury input unit 60 receives the input injury data of each player, organizes it by player and injury item, and stores it in the injury data unit 35 .

[0118] The injury prevention unit 61 presents the injury data accumulated in the injury data unit 35 to the staff terminal 2, allowing the staff to create a plan (injury prevention plan) to prevent the occurrence of one or more injuries or illnesses. The injury prevention unit 61 stores the created injury prevention plan in the injury data unit 35 in association with data on related injuries or illnesses and players, and also displays it on the user terminal 2 of the staff and players.

[0119] The rehabilitation planning unit 62 presents the current injury / illness data of each player accumulated in the injury data unit 35 to the staff member's terminal 2, enabling the staff member to create a rehabilitation activity plan (rehabilitation plan) for recovery from the injury / illness. The rehabilitation planning unit 62 associates the created rehabilitation plan with the related player and injury / illness data, stores it in the injury data unit 35, and also displays it on the staff member's and the user terminal 2 of the relevant player.

[0120] The injury analysis unit 63 analyzes the injury data in the injury data unit 35, generates analysis results such as the injury history, the number of injuries and illnesses within a specified period, the type of injury and the number of injuries and illnesses by body part, and the number of injuries and illnesses by player, and compiles these analysis results into analysis data that can be displayed in a visual format such as a graph, and stores this analysis data in the analysis data unit 30. The analysis data is displayed on the user terminals 2 of the staff and players by the dashboard control unit 20 (FIG. 2).

[0121] The injury support unit 64 enables each staff member and each player to communicate, via their respective user terminals 2, messages such as guidance and assistance from the staff member regarding the player's injury or illness, and messages such as consultations and questions from the player.

[0122] Fig. 14 is a block diagram showing the functional configuration of the treatment management unit. As shown in Fig. 14, the treatment management unit 26 includes, as processing functions according to one embodiment of the present invention, a treatment input unit 65, a treatment analysis unit 66, and a treatment support unit 67. When medical staff performs medical treatment on an injured or ill player, data (treatment data) of predetermined treatment items (examples of which are shown in Fig. 3) are input to the system 1 from the user terminal 2.

[0123] The treatment input unit 65 receives the input treatment data, organizes it by player, staff member, injury, and treatment content, and stores it in the treatment data unit 36 ​​.

[0124] The treatment analysis unit 66 analyzes the treatment data in the treatment data unit 36, generates analysis results such as the number of treatments within a specified period, the number of treatments by treatment site, the number of treatments by player, and the number or amount of treatments performed by each staff member (e.g., the number of treatments), compiles these analysis results into analysis data that can be displayed in a visual format such as a graph, and stores this analysis data in the analysis data unit 30. The analysis data is displayed on the user terminals 2 of the staff and players by the dashboard control unit 20 (FIG. 2).

[0125] The treatment support unit 67 enables each medical staff member and each player to communicate, via their respective user terminals 2, messages such as guidance and assistance from the medical staff member regarding the player's medical treatment, and messages such as consultations and questions from the player.

[0126] 15 is a block diagram showing the functional configuration of the physical growth management unit. As shown in FIG. 15, the physical growth management unit 27 includes, as processing functions according to one embodiment of the present invention, a physical growth input unit 68, a physical growth prediction unit 69, a physical growth analysis unit 70, and a physical growth support unit 71. Each player inputs their own age, sex, and physique data of their parents into the system 1 in advance from the user terminal 2. Furthermore, when each player undergoes physical measurements, they input various types of physical measurement data, such as height, weight, and sitting height, into the system 1 from the user terminal 2.

[0127] The physical growth input unit 68 receives the input data (physical growth data), organizes it by player and measurement date, and stores it in the physical growth data unit 37 .

[0128] The physical growth prediction unit 69 predicts the future physical growth of each player (especially young players in their growth period, such as children or students) based on the physical growth data stored in the physical growth data unit 37. The physical growth prediction unit 69 predicts the peak height velocity age (PHVa) of the growth rate, future height, growth rate, etc., using a prediction method such as the Maturity Offset method based on, for example, the age of each player, changes in height, sitting height, and weight over time, and the physiques of the parents, and stores the prediction results in the physical growth data unit 37.

[0129] The physical growth analysis unit 70 analyzes the PHVa, predicted height, and growth rate in the physical growth data unit 37, generates analysis results such as a physical growth curve and a growth rate curve, compiles these analysis results into analysis data that can be displayed in a visual format such as a graph, and stores this analysis data in the analysis data unit 30. The analysis data is displayed by the dashboard control unit 20 (FIG. 2) on the user terminal 2 of the staff and the relevant player.

[0130] The physical growth support unit 71 enables each staff member and each player to communicate, via their respective user terminals 2, messages such as guidance and assistance from the staff member regarding the player's physical growth, and messages such as consultations and questions from the player.

[0131] FIG. 16 is a block diagram showing an example of the functional configuration of a player model included in the sports support system 1 according to an embodiment. In one aspect, the player model 77 shown in FIG. 16 may be each of the player models 50A, 50B, 50C, ... operating within the training simulator 50 as shown in FIG. 10 . In another aspect, the player model 77 may be a player model operating independently of the training simulator 50, and has a function of imitating the physical and / or mental characteristics of an individual player within a team, a group of players, the entire team, or a fictitious player (this also applies to various configuration examples of the player model 77 described later with reference to FIGS. 17 to 32 ). The player model 77 receives a training menu 72 and predicts what ACWR the target player will have if the target player performs the menu 77. The player model 77 also evaluates the predicted ACWR (e.g., whether it is in the danger zone (alert) of 1.5 or higher, in the appropriate zone of 0.8 to 1.3, or below 0.8, which is too low, etc.). As mentioned above, the target player may be a specific individual player, an average or representative of multiple players belonging to a team, or an average or representative of one or more players belonging to a specific category.

[0132] The training menu 72 includes menu items such as one or more exercise types 73, and load amounts 74 and / or training time 75 for each exercise type 73. The exercise types 73 may include, for example, various types of running, various types of weight training, and various types of skill practice. The load amounts 74 may include, for example, the distance run, number of runs, and total distance run in the case of running, or the weight, number of sets, and number of repetitions per set in the case of weight training. The training time 75 may include, for example, a time period such as a start and end time, a duration such as hours, and the like.

[0133] Many variations can be adopted for the control process of the athlete model 77. An example of the control process shown in FIG. 16 is as follows. The athlete model 77 inputs a training menu and calculates the objective exercise intensity (X) of the input training menu (S1). For example, in the case of running, the objective exercise intensity may be a value obtained by multiplying a coefficient value corresponding to the type of running by the distance run and the number of runs. Alternatively, in the case of a certain type of weight training, the objective exercise intensity may be a value obtained by multiplying a coefficient value corresponding to the type of weight training by the weight of the weights, the number of sets, and the number of repetitions per set.

[0134] The player model 77 inputs the target player's actual ACWR history (e.g., ACWR daily transition data) and calculates a representative value (Y) of past ACWR from that history (S2). This representative value may be, for example, a moving average of ACWR over a recent fixed period (e.g., one week or two weeks) or an exponentially weighted moving average of ACWR. The player model 77 calculates a predicted ACWR by substituting the objective exercise intensity (X) of the training menu and the representative value (Y) of past ACWR into a predetermined function F(X, Y) (S3). The player model 77 evaluates the calculated predicted ACWR against predetermined evaluation criteria (e.g., a threshold of 1.5 for determining a danger zone (alert), and thresholds of 0.8 and 1.3 for determining a suitable zone) (S4).

[0135] Here, the function F(X, Y) that predicts ACWR, which is the core part of the player model 77, can take various forms, such as a relatively simple arithmetic formula generated by linear regression, a model created by a random forest method, a model created by a gradient boosting machine, or a trained neural network model created by machine learning using a neural network. Each of these models creates a player model that reflects the individuality of the target player by learning the target player's past training history and ACWR history using a respective method. Each time the target player performs training and inputs the training results and RPE into the support system 1, the player model 77 may learn the player's individuality in substantially real time, using not only the target player's past training history, but also the ACWR calculated from the input training results and RPE, and the player model 77 may be updated.

[0136] 17 is a block diagram showing another example of the functional configuration of a player model 77. This player model 77 inputs a training menu 80 and predicts the target player's future ACWR, condition data, physical data, injury data, and stats data, as well as (if the target player is a young player still developing) physical growth data, if the target player were to implement the menu (i.e., the effect of the training menu on these data). The player model 77 also evaluates the predicted ACWR, condition data, physical data, injury data, stats data, and physical growth data (e.g., determining the level by comparing them with the predetermined reference values ​​or thresholds, as described above). To make these predictions, the player model 77 also inputs the target player's condition data, physical data, injury data, and stats data histories 81-85 (if the target player is a young player still developing, it also inputs physical growth data history 110). As mentioned above, the target player may be a specific individual player, an average or representative of multiple players belonging to a team, or an average or representative of one or more players belonging to a specific category. The training menu 80 includes data on the items shown in the previous figure.

[0137] The player model 77 has, as processing functions related to one embodiment of the present invention, an ACWR prediction & evaluation unit 86, a condition prediction & evaluation unit 87, a physical prediction & evaluation unit 88, an injury prediction & evaluation unit 89, a physical growth prediction & evaluation unit 111, and a stats prediction & evaluation unit 90.

[0138] The ACWR prediction and evaluation unit 86 may be the one described with reference to the previous figure.

[0139] The condition prediction and evaluation unit 87 inputs the training menu 80, the predicted ACWR from the ACWR prediction and evaluation unit 86, and the target player's condition data history 81, and predicts how the target player's condition will change as a result of the target player performing the training menu. The condition data handled here does not need to be data for all condition items, and may only be data for pre-selected condition items. The prediction model used to predict the condition can be, for example, a neural network model that has been machine-learned to determine the relationship between the target player's training results and condition from the target player's training data history (e.g., a history of past training menus and the resulting training results, such as session RPE and ACWR) and condition data history.

[0140] The physical prediction and evaluation unit 88 inputs the training menu 80, the predicted ACWR, and the target athlete's physical data history 83, and predicts how the target athlete's physical data (i.e., athletic abilities such as muscle strength, running ability, and competitive skills) will change as a result of the target athlete performing the training menu. The physical data handled here does not need to be data for all physical items, and may only be data for pre-selected physical items. The prediction model used to predict the physical data can be, for example, a neural network model that uses machine learning to determine the relationship between the target athlete's training results and physical data (athletic ability) based on the target athlete's training data history (e.g., past training results) and physical data (athletic ability) history.

[0141] The injury prediction and evaluation unit 89 inputs the training menu 80, the predicted ACWR, and the target player's injury data history 84, and predicts how the target player's injury data will change after the target player performs the training menu (i.e., for example, the probability of the target player suffering from a certain type of injury or illness). The injury data handled here does not need to be data on all injury items, but may be data on pre-selected injury items only. The prediction model used to predict injury data can be, for example, a neural network model that uses machine learning to determine the relationship between the target player's training results and injury data (injuries or illnesses) from the target player's training data history (e.g., past training results) and injury data (injuries or illnesses suffered).

[0142] The physical growth prediction and evaluation unit 111 inputs the training menu 80, the predicted ACWR, and the target player's physical growth data history 110, and predicts how the target player's physical growth data will change if the target player implements the training menu. The physical growth data handled here does not need to be data on all physical growth items, and may only be data on pre-selected physical growth items (e.g., the target player's height and weight). The prediction model used to predict the physical growth data can be, for example, a neural network model that uses machine learning to determine the relationship between the target player's training results and physical growth data from the target player's training data history (e.g., past training results) and physical growth data history.

[0143] The stats prediction & evaluation unit 90 inputs the training menu 80, the predicted ACWR, predicted condition data from the condition prediction & evaluation unit 87, predicted physical data from the physical prediction & evaluation unit 88, predicted injury data from the injury prediction & evaluation unit 89, predicted physical growth data from the physical growth prediction & evaluation unit 111, and the target player's condition data, physical data, injury data, physical growth data, and stats data history, and predicts how the target player's stats data (performance in a game) will change as a result if the target player performs the training menu, that is, for example, what the probability is of what kind of performance the player will demonstrate in a game scheduled for a specific time in the future. The various data handled here do not need to be data for all items, and only data for pre-selected items will be sufficient. The predictive model used to predict stats data can be, for example, a neural network model that uses machine learning to determine the relationship between the target player's training results, condition, athletic ability, injuries, and physical growth and the stats data, based on the target player's training data history (e.g., past training results), condition data, physical data, injury data, and stats data history.

[0144] Note that the various prediction models described above, which are the core parts of the player model, may use models that learn the above relationships using, for example, linear regression, random forests, gradient boosting machines, etc., instead of or in combination with neural network models. The player model may also have a simpler configuration, including only some of the various prediction and evaluation units shown in the figure and not others. Each prediction model within the player model may also have a simpler configuration, inputting only some of the various input data described above and not the rest. The player model may also be more complex than the configuration shown in the figure, or may be configured to input other types of data not shown in the figure and use them for prediction or evaluation.

[0145] Furthermore, each predictive model may be updated substantially in real time using machine learning based on not only the target player's past data history, but also the target player's training results, condition data, physical data, injury data, and / or stats data each time the input data is entered into system 1.

[0146] 18 is a block diagram showing an example of the functional configuration of a training proposer. The training proposer 51 designs and proposes a training plan (training menu) for achieving goals set by a user. The goals may include goals 97-101 for the target player's ACWR, condition data, physical data, injury data, and / or stats data at a specific time in the future. Examples of goals may include a target value for tomorrow's ACWR, a target status for one or more specific condition items on a specific game date, a target value for a specific physical item on a specific athletic ability test date, a target status for a specific injury item for a specific future period, or a target value for one or more specific stats items on a specific game date.

[0147] As shown in FIG. 18, the training proposer 51 has a simulation execution unit 102, a plan evaluation unit 103, a plan recording unit 104, a plan modification unit 105, and a plan proposal unit 106 as processing functions according to one embodiment of the present invention.

[0148] The simulation execution unit 102 inputs a specific training plan 96 (for example, a training menu for one day tomorrow, or a set of daily training menus for the coming week or several weeks) into the player model 77 described above, and receives predicted results of ACWR, condition data, physical data, injury data, and / or stats data for that training plan 80.

[0149] The plan evaluation unit 103 compares the received prediction result with the goal set by the user and evaluates the prediction result. The plan recording unit 104 records the plan 80, the prediction result, and the evaluation result.

[0150] The plan modification unit 105 modifies the contents of the plan 96 (for example, the type and quantity of training in the training menu), provides the modified plan 109 to the simulation execution unit 102, and causes the simulation execution unit 102 to repeat simulation and evaluation of the modified plan 109. While repeating the plan modification, the plan modification unit 105 refers to the evaluation results of various different plans recorded in the plan recording unit 104 and controls whether to further repeat or terminate the plan modification.

[0151] After the plan change is complete, the plan suggestion unit 106 selects one or more plans with relatively good evaluations from the various training plans that have been simulated and evaluated up to that point as a proposed training plan and presents it to the user. The plan suggestion unit 106 also presents the user with the predicted results of the simulation for the proposed training plan and the evaluation results in light of the goal. Such training run suggestions help the user plan the optimal training in line with their intentions.

[0152] FIG. 19 is a block diagram showing another example of the functional configuration of the player model of the sports support system 1 according to an embodiment. This player model 77 inputs training data accumulated in the training data unit 32, generates training advice that the player should be aware of, and presents it to the player. As described above, the target player may be a specific individual player, an average or representative of multiple players belonging to a team, or an average or representative of one or more players belonging to a specific category. A more specific example of this function is providing the player with advice to reduce the risk of adverse consequences, such as injury or illness, that may be caused by the training, based on the training load of the player.

[0153] An example of the control process shown in Figure 19 is as follows. The player model 77 extracts data (e.g., RPE and training time) necessary to evaluate, for example, the exercise load (or exercise intensity) of the training performed by the player from the training data unit 32 (S1). The player model 77 multiplies the RPE by the training time to calculate sRPE (sRPE (subjective exercise intensity)) (S2). Based on the sRPE, the player model 77 calculates the amount of exercise the player has performed over the past seven days (acute load) and the average weekly exercise load performed over the past 28 days (chronic load) (S3). Based on the acute load and chronic load, the player model 77 calculates ACWR (an index indicating the likelihood of injury due to exercise load) (S4). The player model 77 evaluates the calculated ACWR in light of predetermined evaluation criteria (for example, thresholds of 1.5 and 0.7 for determining a dangerous zone (alert), thresholds of 0.8 and 1.3 for determining a suitable zone, etc.) (S5).

[0154] Depending on the results of the training evaluation, the player model 77 generates specific advice for each of the following cases: when the calculated ACWR exceeds a threshold of 1.5; when the calculated ACWR is below a threshold of 0.7; and when the calculated ACWR is in an appropriate range (threshold of 0.8 to 1.3), and displays the advice on the display unit of the user terminal 2 (S6). When the calculated ACWR exceeds the threshold of 1.5, the player model 77 generates advice such as, "The load of your recent training is too high. Reduce the intensity of your next training by 10 to 20%," "To reduce the risk of injury, we recommend switching to lighter training or recovery sessions for the next few days and taking sufficient rest," or "Perform stretching and massage after training to promote muscle recovery."

[0155] Furthermore, if the calculated ACWR is below the threshold value of 0.7, the player model 77 generates advice such as, "Your recent training volume has been insufficient. Try increasing the exercise time and intensity a little in your next training session," "Consider incorporating weight training or interval training to improve your muscle strength," or "Increase the variety of your training and incorporate fun exercises to maintain your motivation."

[0156] Furthermore, if the calculated ACWR is in an appropriate range (threshold 0.8 to 1.3), the player model 77 will generate advice such as, "Your current training balance is good. Continue training at this pace and make minor adjustments as necessary.", "Your recent performance has improved. Use self-evaluation and feedback to set further goals," or "Ensure sufficient recovery and strive to prevent injuries. It is especially important to replenish nutrition and rest after training."

[0157] Here, to generate advice, which is the core part of the player model 77, for example, a neural network model or a decision tree model can be used that uses machine learning to determine the relationship between the target player's training results and injury risk from the target player's training data history (e.g., RPE, training time, and / or training menu, etc.) and injury data history (injury facts, cause of occurrence, and / or injury location, etc.).

[0158] 20 is a block diagram showing another example of the functional configuration of the player model of the sports support system 1 according to an embodiment. The player model 77 receives the physical data stored in the physical data unit 33 and / or the stats data stored in the stats data unit 34, generates training advice that the player should be aware of, and presents this advice to the player. A more specific example of this function is to provide the player with advice that helps improve the effectiveness of training, such as advice on setting goals or improving training methods, based on performance or self-evaluation as the results of training that appear in the physical data or stats data.

[0159] An example of the control process shown in FIG. 20 is as follows. The player model 77 compares the physical or stats data of one or more physical or stats items related to the player's performance in an athletic test or game stored in the physical data section 33 or the stats data section 34 with predetermined target values ​​for each item to evaluate the degree to which the target values ​​are reached (S1). Specifically, in the case of a weightlifting athlete, the degree to which the athlete's weightlifting performance has reached the predetermined target values, such as the weight of the weights and number of repetitions, is evaluated. For example, in the case of a sprinter in track and field, the degree to which the athlete's performance has reached a target time for the 100-meter sprint is evaluated. For example, in the case of a baseball player, the degree to which the athlete's performance has reached a target batting average is evaluated. The evaluation results for each stats item are associated with the data for each item and stored in the physical data section 33 or the stats data section 34.

[0160] The player model 77 analyzes the evaluation results of each stats item over a certain period of time (e.g., several weeks) (S2). Based on the analysis results, the player model 77 generates specific advice (e.g., advice on setting a target value and / or how to implement training) that is useful for improving performance, and displays it on the display unit of the user terminal 2 (S3). For example, in the case of a weightlifting athlete, if the degree of achievement of the target value has been low for several weeks consecutively, the player model 77 generates advice such as, "To achieve your goal of 100 kg, try setting a small goal of 95 kg first," or advice such as, "Review your form and increase training with lighter weights to strengthen your basic muscle strength."

[0161] For example, if a sprinter has not been able to achieve his target time for several weeks, the athlete model 77 may generate advice such as, "In your next training session, try to aim for a time of under 12 seconds for 100 meters. Pay attention to your pace and practice to improve your time," or, "Your self-evaluation has been low recently, so I recommend reducing the intensity of your training and focusing on recovery."

[0162] For example, if a baseball player has not been able to achieve their target batting average for several weeks, the player model 77 might generate advice such as, "If your batting average in recent games has not reached your target, set a specific goal for the next game. For example, we recommend that you aim to get three or more hits in your next game." It might also generate mental advice such as, "Try to relax before the game. Incorporating deep breathing and imagery training can help ease the pressure of the game."

[0163] Here, the generation of advice, which is the core part of the player model 77, can use, for example, a neural network model or decision tree model that learns the relationship between the results of the target player's training and their performance or self-assessment from the target player's training data history (e.g., RPE, training time, training menu, target values, etc.), physical data and / or stats data history (performance and results in athletic ability tests or matches for the team and each player, self-assessment, etc.), and data showing advice provided in the past and its effects, and that has learned how to generate advice for improving training based on the player's performance or self-assessment in matches or tests.

[0164] 21 is a block diagram showing another example of the functional configuration of an athlete model included in the sports support system 1 according to an embodiment. This athlete model 77 receives condition data stored in the condition data unit 31, generates advice that the athlete should be aware of, and presents it to the athlete. A more specific example of this function is to provide advice for improving the effectiveness of training or for reducing stress and increasing motivation, based on mental condition data such as the athlete's motivation for training or self-evaluation.

[0165] An example of the control process shown in Figure 21 is as follows: The player model 77 receives input data on mental condition for training (for example, training motivation or self-assessment score), organizes it for each player, and stores it in the condition data section 31 (S1). Motivation scores for training can be divided into 10 levels from 1 to 10, with 1 being "very low" and 10 being "very high," for example.

[0166] The player model 77 analyzes the motivation score for practice over a certain period (e.g., several weeks) (S2). If the motivation score for practice remains low over that period (e.g., if the motivation score for practice is 5 or less), the player model 77 determines that stress is likely to be present and extracts the player's physiological data (e.g., sleep heart rate, sleep pattern, etc.) from the condition data unit 31 (S3).

[0167] The player model 77 analyzes the correlation between the motivation score for practice and the physiological data, and identifies the cause of stress (S4). For example, the player model 77 groups the motivation score for practice and the physiological data using a clustering method (e.g., K-means method) to identify the cause of stress.

[0168] The player model 77 generates specific advice for the player based on the identified stress factor and displays it on the display unit of the user terminal 2 (S5). For example, if a high training load is the cause of stress, the player model 77 generates advice such as "reduce the load in the next training session and focus on recovery."

[0169] Here, the core part of the player model 77, that is, the identification of stress factors and the generation of advice, can employ a neural network model or decision tree model that uses, as training data, the history of the target player's condition data (e.g., motivation score for training and physiological data, etc.), labels of stress factors identified during past periods of low motivation of the target player (e.g., excessive training, lack of sleep, poor nutrition, mental pressure, external factors (e.g., match results), etc.), and data showing advice provided in the past and its effects, to learn what patterns of physiological data appear during times of low motivation, learn how to identify stress factors based on that physiological data, and then generate advice based on the identified stress factors.

[0170] 22 is a block diagram showing another example of the functional configuration of an athlete model included in the sports support system 1 according to an embodiment. This athlete model 77 inputs condition data relating to the food consumed, which is stored in the condition data unit 31, and generates and presents advice to the athlete that the athlete should be aware of. A more specific example of this function is to identify the athlete's eating patterns based on the number of meals and snacks consumed by the athlete, and provide the athlete with advice regarding their eating habits.

[0171] An example of the control process shown in Fig. 22 is as follows: The player model 77 extracts dietary data relating to the meals the player has eaten in the past (such as the number of meals and snacks the player has had, the time of each meal, and the types and nutrients of foods ingested at each meal) from the condition data section 31 (S1).

[0172] The player model 77 identifies and analyzes the player's eating pattern based on the dietary data (S2). Methods for analyzing eating patterns include evaluating the total number of meals per day (total of staple foods and supplementary foods), determining whether there is a deficiency in necessary nutrients, and checking whether meals are biased towards certain times of the day.

[0173] The player model 77 generates specific advice regarding eating habits based on the analyzed eating patterns and displays it on the display unit of the user terminal 2 (S3). For example, the player model 77 generates advice such as "Aim to eat three meals a day" to suggest dietary improvements to a player who is not eating enough. Also, for example, the player model 77 generates advice such as "Add a protein bar to your next snack" to suggest specific foods to a player who is lacking in a specific nutrient. Also, for example, the player model 77 generates advice such as "We recommend changing your snacks to fruits or nuts" to a player who is eating inappropriate snacks.

[0174] Here, the identification and analysis of dietary patterns and generation of advice, which are the core parts of the player model 77, require, for example, a history of the target player's daily dietary data (e.g., the number and time of meals and snacks, food types, intake amounts, nutrient information, etc.), the target player's physical data (e.g., gender, age, height, weight, etc.), the target player's training and condition data (e.g., training load, physical condition, fatigue level, etc.), and labels related to dietary quality (e.g., good nutritional balance and bad nutritional balance, good meal timing and bad meal timing, overintake, nutritional deficiency, risk foods, food diversity, etc.). A neural network model or decision tree model can be used that learns how to identify an athlete's actual eating patterns using training data such as criteria for the athlete's diet, the desired eating pattern to aim for (for example, target patterns for the number of meals, time of day, amount of intake, nutritional balance, etc.), and advice provided in the past and data showing its effectiveness, and then learns how to identify the characteristics of the eating pattern and areas for improvement by comparing the identified eating pattern with the athlete's training situation, condition, and good eating habits, and then learns how to generate advice from these characteristics and areas for improvement.

[0175] 23 is a block diagram showing yet another example of the functional configuration of an athlete model included in the sports support system 1 according to an embodiment. This athlete model 77 receives sleep-related condition data stored in the condition data unit 31, generates advice that the athlete should be aware of, and presents it to the athlete. A more specific example of this function is to identify the athlete's sleep pattern based on the amount of sleep the athlete has had and their sense of restfulness, and provide the athlete with advice on their sleep habits.

[0176] An example of the control process shown in Figure 23 is as follows: The player model 77 extracts sleep data related to the player's past sleep (sleep duration, heart rate during sleep, pulse movement, feeling of deep sleep, feeling of restful sleep, etc.) from the condition data unit 31 (S1). The sleep duration, heart rate, and pulse movement can be obtained using a wearable device such as an Ora Ring, and the feeling of deep sleep and feeling of restful sleep can be obtained by performing a simple cognitive test (e.g., a reaction time test or a memory test) after waking up.

[0177] The player model 77 identifies and analyzes the player's sleep pattern based on the sleep data (S2). For example, the player model 77 identifies and analyzes the temporal patterns (sleep patterns) of the various stages of deep sleep, light sleep, and REM sleep that appear in the sleep data to evaluate the degree to which quality sleep is ensured, or analyzes fluctuations in heart rate during sleep to evaluate the player's degree of relaxation and stress level. Furthermore, for example, the player model 77 groups the player's sleep patterns using a clustering method (e.g., K-means) to identify players with similar sleep patterns (e.g., players with little deep sleep or players with low sleep efficiency).

[0178] The player model 77 generates specific advice for the player based on the sleep pattern and displays it on the display unit of the user terminal 2 (S3). For example, if the player's sleep time is short or the quality is poor, the player model 77 generates advice such as "You've been sleeping less recently, so I recommend going to bed 30 minutes earlier" or "You're not getting enough deep sleep, so I recommend limiting your caffeine intake before bed and taking time to relax" as specific measures for improvement.

[0179] Here, the identification, analysis, and advice generation of sleep patterns, which are the core parts of the player model 77, can employ a neural network model or decision tree model that uses, as training data, the player's daily sleep history (e.g., objective data such as sleep duration, time spent in deep sleep, light sleep, and REM sleep, heart rate, pulse, and sleep efficiency, as well as subjective data such as a sense of deep sleep and a sense of restfulness), the player's stress and relaxation indicators (e.g., heart rate variability (HRV), heart rate variability during sleep, daytime stress level, etc.), and advice previously provided and data showing its effectiveness, to learn how to grasp sleep characteristics (e.g., consistency of sleep duration, ratio of deep sleep to light sleep, sleep efficiency, etc.) based primarily on the objective data of the sleep data, learn how to classify this and identify sleep patterns, learn the relationship between these sleep patterns and subjective data such as a sense of deep sleep and a sense of restfulness, as well as stress and relaxation indicators, and then use this relationship to generate advice to improve sleep effects such as a sense of deep sleep, a sense of restfulness, and stress and relaxation indicators.

[0180] 24 is a block diagram showing another example of the functional configuration of the player model of the sports support system 1 according to an embodiment. This player model 77 inputs the physical data stored in the physical data unit 33, generates advice that the player should be aware of, and presents it to the player. A more specific example of this function is to provide the player with advice that the player should be aware of regarding changes in, for example, weight gain.

[0181] An example of the control process of the player model 77 shown in Figure 24 is as follows: The player model 77 extracts weight data (weight, body fat percentage, lean body mass, etc.) related to the player's weight from the physical data section 33 (S1). The weight data here includes past weight data and current weight data.

[0182] The player model 77 compares past weight data with current weight data, and if weight has increased, evaluates whether the increase is due to an increase in lean body mass or an increase in body fat (S2). For example, if the weight increase is due to an increase in lean body mass, the player model 77 determines that the weight increase is appropriate because muscle mass has increased. Also, for example, if the weight increase is due to an increase in body fat, the player model 77 determines that the weight increase is inappropriate because fat has increased.

[0183] The athlete model 77 generates specific advice based on the evaluation results and displays it on the display unit of the user terminal 2 (S3). For example, if the athlete model 77 determines that the weight gain is appropriate, it generates advice such as, "Your current weight gain is due to an increase in lean body mass, and you are making good progress. Keep it up." Alternatively, if the athlete model 77 determines that the weight gain is inappropriate, it generates advice such as, "Your weight is increasing, but your body fat percentage is also increasing. You need to review your diet and adjust your training program." The advice may be selected from advice prepared in advance for each evaluation result, or may be generated using a neural network model or a decision tree model that has learned the correlation between the cause of weight gain (e.g., an increase in lean body mass, an increase in body fat, etc.) and the amount of weight gain and areas for improvement in diet and training.

[0184] 25 is a block diagram showing another example of the functional configuration of the athlete model included in the sports support system 1 according to an embodiment. This athlete model 77 receives the physical data stored in the physical data section 33, the condition data stored in the condition data section 31, and the training data stored in the training data section 32, generates advice that the athlete should be aware of, and presents it to the athlete. A more specific example of this function is providing the athlete with advice regarding changes in the athlete's weight, such as weight loss, to improve their eating habits in accordance with the amount of exercise the athlete performs.

[0185] An example of the control process shown in Figure 25 is as follows: The player model 77 extracts the player's weight data (weight, body fat percentage, lean body mass, etc.) from the physical data section 33 (S1). The weight data here includes past weight data and current weight data.

[0186] The player model 77 extracts dietary data of the player's past meals (number of meals, number of snacks, meal contents, calorie intake, etc.) from the condition data section 31 (S2). The player model 77 extracts data on the amount of exercise of the player's past training (training menu, training time, calorie consumption, etc.) from the training data section 32 (S3).

[0187] The player model 77 compares past weight data with current weight data to evaluate whether the player has lost weight (S4). If the player has lost weight, the player model 77 analyzes the dietary data and training data to identify the cause of the weight loss (S5). For example, the player model 77 compares the amount of calories ingested through diet with the amount of calories burned through training to identify the cause of the weight loss.

[0188] The player model 77 generates specific advice for the player based on the identified cause and displays it on the display unit of the user terminal 2 (S6). For example, if the player's weight is decreasing but the training time is increasing, the player model 77 generates advice such as "Since the training time is increasing, we recommend that you increase the number of supplementary meals to replenish your energy." Also, for example, if the number of meals is less than the recommended number, the player model 77 generates advice such as "We recommend that you increase the number of meals and take in a balanced diet."

[0189] Here, to identify the cause of weight loss and generate advice, which is the core part of the athlete model 77, a neural network model or decision tree model can be used that uses, for example, the target athlete's past weight data, dietary data, training data, labels of the cause of weight loss (for example, imbalance between calorie intake and expenditure, imbalance in nutrient balance, changes in training frequency or intensity, etc.), and data showing advice provided in the past and its effects as training data, to learn how to identify the cause of weight loss from the dietary data and training data at the time of weight loss, and then learn how to generate advice to improve eating habits and training from the factors behind weight loss.

[0190] 26 is a block diagram showing yet another example of the functional configuration of the athlete model of the sports support system 1 according to an embodiment. This athlete model 77 receives injury data stored in the injury data unit 35 and training data stored in the training data unit 32, generates advice that the athlete should be aware of, and presents it to the athlete. A more specific example of this function is to provide the athlete with advice regarding treatments and training improvements to alleviate physical pain in the athlete.

[0191] An example of the control process shown in Fig. 26 is as follows: The player model 77 extracts pain data (such as the location, degree, type, time of occurrence, and circumstances of occurrence) of physical pain or discomfort (hereinafter referred to as pain) that the player is experiencing from the injury data section 35 (S1).

[0192] The player model 77 identifies and analyzes pain patterns based on the pain data (S2). Methods for analyzing pain patterns include quantitatively evaluating the degree of pain and calculating average and median values ​​to understand the overall trend of pain, or classifying the type of pain into dull pain, sharp pain, numbness, etc. and analyzing the circumstances under which each type of pain occurs.

[0193] Based on the identified pain pattern and past training data, the player model 77 generates specific advice regarding treatments or training improvements to alleviate the pain, and displays the advice on the display unit of the user terminal 2 (S3). For example, for sharp pain or sudden onset pain, the player model 77 generates advice such as, "Cool the area of ​​pain and rest. Apply ice as needed." For dull pain that lasts for a long time, the player model 77 generates advice such as, "If the pain persists, we recommend that you review the intensity of your training and incorporate stretching and rehabilitation." For example, for muscle pain after training, the player model 77 generates advice such as, "Perform light stretching and massage, and try heat therapy as needed."

[0194] Here, for the identification and analysis of pain patterns and generation of advice, which are the core parts of the player model 77, a neural network model or decision tree model can be used that uses, for example, the target player's past pain data, training data (e.g., type of training, amount of load, etc.), treatment data (e.g., body parts treated, type and effect of that treatment, etc.), and data indicating advice provided in the past and its effects as training data, to learn how to identify pain patterns from pain data, how to identify effective treatments or training improvements from those pain patterns, and how to generate advice informing the player of those treatments or training improvements.

[0195] 27 is a block diagram showing yet another example of the functional configuration of the player model of the sports support system 1 according to an embodiment. This player model 77 receives the training data stored in the training data unit 32 and the stats data stored in the stats data unit 34, generates advice that the player should be aware of, and presents it to the player. A more specific example of this function is to provide the player with advice on the training that the player should undertake, based on the sport that the player is engaged in, the task that the player is working on, and / or various score results (performance) for each sport.

[0196] An example of the control process shown in Figure 27 is as follows. The player model 77 extracts training data specific to one or more sports in which the player is engaged (e.g., competition data related to one or more sports in which the player participates, data on challenges the player needs to overcome in each sport, etc.) from the training data unit 32 (S1). The competition data includes the type of sport (including roles or positions within a sport, such as pitcher, batter, or shortstop in baseball), sport characteristics, and sport rules. The data on challenges may include physical challenges, such as lack of endurance or speed, and / or technical challenges, such as mastering a specific technique.

[0197] The athlete model 77 extracts the athlete's stats data (for example, scores for each event, such as the times for the 400m, 800m, and 1500m of a middle-distance runner) from the stats data section 34 (S2). The scores for each event may include time, points, ranking, etc.

[0198] The player model 77 analyzes the correlation between the training data and the stats data for each sport to evaluate which factors are affecting performance (S3). For example, the player model 77 analyzes the correlation between the tasks being worked on and the scores to identify which tasks are affecting the player's performance.

[0199] Based on the evaluation results, the athlete model 77 generates specific advice for improving performance in each sport and displays it on the display unit of the user terminal 2 (S4). For example, if the athlete's lack of endurance is affecting their athletic performance, the athlete model 77 generates advice such as, "To improve your endurance, incorporate long runs three times a week. Gradually increase the distance, aiming for 5 km the first week, 7 km the next week, and 10 km the following week. In addition, do pace runs once a week to develop endurance at race pace." Alternatively, if the athlete's lack of speed is affecting their athletic performance, the athlete model 77 generates advice such as, "To improve your speed, do interval training twice a week. Specifically, run 400 m at full speed, followed by a 200 m jog to recover, and repeat this set six times. This will have the effect of training both your speed and endurance."

[0200] Here, the analysis of the relationship between training data and stats data and the generation of advice, which is the core part of the athlete model 77, can use, for example, the athlete's past competition data for each sport, data on tasks to be worked on, training data, and stats data, as well as labels of performance factors for each sport (for example, speed, starting sprint, power, etc. in the case of sprinting), as training data to learn the relationship between the sport and the abilities required for it, the relationship between tasks to be worked on and stats data (for example, how tasks affect athletic performance), and the relationship between training data and stats data (for example, how frequency, intensity, and type of training affect athletic performance), and can then use a neural network model or decision tree model that has learned how to generate advice to improve stats data (performance) based on the tasks and training data.

[0201] 28 is a block diagram showing yet another example of the functional configuration of the athlete model of the sports support system 1 according to an embodiment. This athlete model 77 inputs physical growth data accumulated in the physical growth data unit 37, generates advice that the athlete should be aware of, and presents it to the athlete. A more specific example of this function is to predict the athlete's growth stage and / or the time when the athlete's physical growth rate, such as height growth rate, will peak based on the athlete's past physical growth data, such as height, and provide the athlete with dietary advice according to the athlete's growth stage or peak growth period.

[0202] An example of the control process shown in Figure 28 is as follows: The player model 77 extracts physical growth data (such as changes in age, height, sitting height, and weight over time, and the physiques of the parents) of a young player in the growth stage, such as a child or student, from the physical growth data unit 37 (S1). Based on the physical growth data, the player model 77 predicts each growth stage (early growth stage, peak growth stage, late growth stage) of the player using a prediction method such as the Maturity Offset method (S2). The player model 77 calculates the required amount of nutrients (protein, vitamins, minerals, etc.) for each growth stage (S3).

[0203] The player model 77 generates specific advice based on the calculation results and displays it on the display unit of the user terminal 2 (S4). For example, for an athlete in the peak growth period, the player model 77 may give advice such as "Try to eat a diet rich in calcium and protein," and generate a specific menu such as "Breakfast: Greek yogurt topped with fruit and oatmeal; Lunch: grilled chicken breast, spinach salad (dressed with olive oil and lemon), whole grain bread; Dinner: grilled fish (salmon or mackerel), steamed broccoli, brown rice; Snack: almonds or walnuts, cheese sticks." For example, Player Model 77 may provide advice to a player in the early stages of growth, such as "Try to eat a well-balanced diet to ensure adequate energy replenishment," and generate specific menus, such as "Breakfast: whole wheat bread topped with avocado and egg, garnished with tomato; Lunch: stir-fried beef or chicken, sautéed vegetables (bell peppers, cabbage, etc.), white rice; Dinner: pork with ginger, blanched spinach, miso soup, brown rice; Snack: banana, yogurt, energy bar." For example, Player Model 77 might provide advice to a player in the later stages of growth, such as, "Take care of your weight while also taking in the nutrients necessary to maintain muscle." It might also generate and present specific menus to the player, such as, "Breakfast: Smoothie (banana, spinach, protein powder, almond milk); Lunch: Salad bowl (chicken breast, quinoa, avocado, vegetables, lemon dressing); Dinner: Oven-baked turkey or chicken, steamed vegetables (carrot, broccoli), sweet potato; Snack: Greek yogurt and berries, protein shake."

[0204] Here, the core parts of the player model 77, namely, predicting the growth stage, calculating the amount of nutrients needed, and generating advice, can be achieved by using, for example, the player's past physical growth data, labels for each growth stage (e.g., early growth stage, peak growth stage, late growth stage, etc.), nutritional requirements for each growth stage (e.g., the amount of various nutrients needed at each stage and / or important nutrients (e.g., peak growth stage: high protein and high calcium recommended; early growth stage: emphasis on energy intake; late growth stage: emphasis on muscle maintenance, etc.)), example meal menus that satisfy the nutritional requirements for each stage, and data identifying the peak growth period based on past physical growth data as training data. The training data can then be used to learn how to predict the growth stage and peak growth period from physical growth data, how to calculate the nutrients needed at each growth stage, how to generate specific meal menus based on the growth stage and nutritional requirements, and how to generate advice according to the growth stage, nutritional requirements, and / or meal menus.

[0205] 29 is a block diagram showing yet another example of the functional configuration of the player model of the sports support system 1 according to an embodiment. This player model 77 receives training data accumulated in the training data unit 32, generates advice that the player should keep in mind, and presents it to the player. A more specific example of this function is to notify the player of the accumulated experience of past training conducted by the player by expressing it as a score that "increases with training and decreases with rest," in order to increase the player's motivation to train.

[0206] An example of the control process shown in Figure 29 is as follows: The player model 77 extracts training data (e.g., perceived exertion intensity such as RPE, training time) related to the exercise stress of training performed by the player over a predetermined period (e.g., the current day) from the training data unit 32 (S1). The player model 77 calculates the exercise stress of the training for that day from the extracted data (e.g., multiplying the RPE by the training time to calculate the sRPE) (S2).

[0207] The athlete model 77 assigns a weight to the exercise load, e.g., sRPE, based on the athlete's training review (e.g., training impressions, evaluations, results, etc.) (e.g., multiplying by a coefficient based on the content of the review) to calculate the athlete's exercise experience value for that day (S3). The weight or coefficient based on the review is set, for example, based on the quantity and quality of the athlete's review. For example, the weight or coefficient based on quantity is determined based on the length and detail of the review written by the athlete. For example, the weight or coefficient based on quality is adjusted depending on whether the review contains positive or negative meanings. For example, the weight or coefficient is set high if there are many positive reviews and low if there are many negative reviews.

[0208] The player model 77 calculates a decay total value by decaying the total value of the exercise experience points up to the previous day at a predetermined decay rate (S4). The decay rate can be changed depending on the number of days the player has missed training. For example, if the total value of the exercise experience points up to the previous day is to decay by 10% for each day the player has missed training, the decay rate is set to 0.1. If the total value of the exercise experience points up to the previous day is to decay by 20% for each day the player has missed training, the decay rate is set to 0.2.

[0209] The player model 77 calculates a total exercise experience value, which is the sum of the exercise experience value for that day and the total decay value (S5). The total exercise experience value has the characteristic that it increases the more the player trains and decreases the more the player takes a break from training. The player model 77 quantifies this total exercise experience value as a score and displays it on the display unit of the user terminal 2 (S6). Displaying the total exercise experience value as a score in this way makes it easier for the player to set specific goals. For example, a player can increase their motivation for daily training by setting a specific goal such as "increasing my total exercise experience value by 500 points this week." Furthermore, being able to track changes in exercise experience value makes it easier for the player to realize their own growth, which helps maintain motivation for daily training.

[0210] 30 is a block diagram showing yet another example of the functional configuration of the athlete model of the sports support system 1 according to an embodiment. The athlete model 77 receives training data stored in the training data unit 32 and condition data stored in the condition data unit 31, generates advice that the athlete should be aware of, and presents it to the athlete. A more specific example of this function is to express the athlete's overall experience, including the accumulation of past training, eating habits, and sleeping habits, as a score with characteristics similar to physical and mental health or fatigue, in which "training increases, taking a break from training decreases, and further decreases if the athlete does not maintain appropriate lifestyle habits," in order to increase the athlete's motivation to train and maintain appropriate lifestyle habits.

[0211] An example of the control process shown in Figure 30 is as follows: The player model 77 extracts the player's training data (e.g., perceived exertion intensity such as RPE, training time) for a predetermined period of time in the past (e.g., the current day) from the training data unit 32 (S1). The player model 77 calculates the exercise stress of the training for that day from the extracted data (e.g., multiplying the RPE by the training time to calculate the sRPE) (S2).

[0212] The athlete model 77 calculates the energy expenditure for that day by weighting (e.g., multiplying by a coefficient corresponding to the lifestyle for that day) the exercise stress for that day, e.g., sRPE, based on the lifestyle for that day (e.g., number of meals, intake of snacks, sleep duration, feeling of deep sleep, etc.) included in the condition data (S3). The coefficient corresponding to the lifestyle is set as follows: for example, the coefficient is set to 1.05 for each increase in the number of meals, 1.1 for each increase in the number of snacks, 0.9 for sleep duration less than 7 hours, 1.1 for sleep duration 8 hours or more, 1.1 for a feeling of deep sleep, and 0.9 for a feeling of not deep sleep.

[0213] The player model 77 calculates a decay total value by decaying the total value of energy consumption over a certain period of the most recent past (e.g., the seven days before yesterday) at a predetermined decay rate (S4). The decay rate can be changed depending on the number of days the player has missed training. For example, if the total value of exercise experience points up to the previous day is to decay by 10% for each day the player misses training, the decay rate is set to 0.1. If the total value of exercise experience points up to the previous day is to decay by 20% for each day the player misses training, the decay rate is set to 0.2.

[0214] The player model 77 calculates the total energy consumption, which is the sum of the energy consumption for that day and the total decay value (S5). The total energy consumption has the characteristic that it increases the more the player trains, decreases the more the player takes a break from training, and increases the more the player practices appropriate lifestyle habits. The player model 77 quantifies this total energy consumption as a score and displays it on the display unit of the user terminal 2 (S6). Displaying the total energy consumption as a score in this way makes it easier for the player to set specific goals.

[0215] 31 is a block diagram showing yet another example of the functional configuration of an athlete model included in the sports support system 1 according to an embodiment. This athlete model 77 inputs condition data stored in the condition data unit 31, generates advice that the athlete should be aware of, and presents it to the athlete. A more specific example of this function is to suggest to the athlete items such as food and equipment to improve their nutritional and fatigue states, depending on the athlete's condition.

[0216] An example of the control process shown in Figure 31 is as follows: The player model 77 extracts condition data relating to the player's nutritional state and fatigue state (e.g., physical pain, physical fatigue, mental fatigue, dietary details, etc.) from the condition data section 31 (S1).

[0217] The player model 77 evaluates the player's nutritional state and fatigue level based on the condition data (S2). The player model 77 suggests foods containing necessary nutrients based on the player's nutritional state, and suggests necessary conditioning goods based on the player's fatigue level (S3). For example, the player model 77 suggests chicken, fish, beans, protein shakes, etc. for a player who is deficient in protein, and spinach and oranges for a player who is deficient in vitamins. For example, the player model 77 also suggests massage balls, stretch bands, heating pads, etc. for a player who has muscle pain.

[0218] Here, to generate food and conditioning goods suggestions, which are the core part of the player model 77, for example, data on the player's past nutritional status and fatigue state, nutritional data indicating the nutrients contained in various foods, conditioning goods data indicating the uses and effects of various conditioning goods, labels of nutritional status and fatigue level (for example, labels of nutritional status such as "good," "deficient," and "excessive" and their classification criteria, labels of fatigue levels such as "mild," "moderate," and "severe" and their classification criteria), and data indicating past suggestions and their effects can be used as training data to learn how to predict growth stages and peak growth periods from physical growth data, how to calculate the nutrients needed at each growth stage, how to generate specific meal menus based on the growth stage and nutritional requirements, and how to generate advice according to the growth stage, nutritional requirements, and / or meal menus.

[0219] 32 is a block diagram showing another example of the functional configuration of an athlete model included in the sports support system 1 according to an embodiment. This athlete model 77 inputs condition data accumulated in the condition data unit 31, generates advice that the athlete should be aware of, and presents it to the athlete. A more specific example of this function is determining which phase of a female athlete's menstrual cycle she is currently in based on her menstrual data, and providing the athlete with advice on adjusting her training and managing her physical condition according to the phase.

[0220] An example of the control process shown in Figure 32 is as follows: The player model 77 extracts the player's menstrual data (e.g., information related to the menstrual cycle, such as the start and end dates of menstruation, whether the player is menstruating, and if so, the number of days since the start of menstruation, and the average number of days the menstrual period lasts) from the condition data unit 31 (S1).

[0221] The player model 77 analyzes the menstrual data and estimates the current phase from among multiple menstrual cycle phases (menstrual period, follicular phase, ovulation period, luteal phase) (S2). In this case, the player model 77 determines the characteristics of the player's menstrual cycle (e.g., normal, degree of cycle variability, frequent menstruation, oligomenorrhea, amenorrhea, etc.) based on the past menstrual data, and estimates the current phase according to the menstrual characteristics.

[0222] The player model 77 inputs data indicating the player's physical and mental condition from the condition data section 31 and data regarding the content of the training performed by the player (e.g., menu, type, time, subjective exercise intensity, etc.) from the training data section 32 (S3).

[0223] The player model 77 generates advice based on the current phase, condition, and training content, and displays it on the display unit of the user terminal 2 (S3). For example, for a female player who is menstruating, the player model 77 generates advice such as, "Light aerobic exercise and stretching are recommended. Relaxing exercises such as yoga and walking are effective," or advice such as, "Avoid strenuous training and competitions, and adjust your training while listening to your body." For example, for a female player who is in the follicular phase, the player model 77 generates advice such as, "Since your energy level is increasing, this is a good time to incorporate endurance training and high-intensity training," or advice such as, "Improve your physical strength by increasing your strength training." For example, for a female player who is in the ovulation phase, the player model 77 generates advice such as, "Since your performance is at its peak, this is the best time to compete or engage in high-intensity training," or advice such as, "To maximize your sports performance, you may want to schedule your games and competitions around this period." For example, for a female athlete in the luteal phase, the athlete model 77 may generate advice such as, "Because your energy is likely to decrease, conduct training that emphasizes recovery and avoid excessive strain," or, "Incorporate exercises that will refresh your body, such as light aerobic exercise, stretching, and yoga." For athletes with irregular menstrual cycles, the athlete model 77 may also provide advice on how to restore a normal menstrual cycle. These pieces of advice enable female athletes to perform optimally in each phase of their menstrual cycle and provide optimal support for maintaining their health.

[0224] Here, the core part of the player model 77, that is, the estimation of the menstrual phase and the generation of advice, can use, for example, the player's menstrual data, physical condition data, mental condition data, training data, example advice according to the menstrual phase (for example, recommended training content and precautions for each phase (menstrual period, follicular phase, ovulation phase, luteal phase), countermeasures in case of menstrual abnormalities, etc.), and menstrual cycle health indicators (for example, reference data for classifying menstrual cycles as normal or abnormal) as training data, to learn how to grasp the characteristics of the player's menstrual cycle based on past menstrual data, learn how to estimate the player's current phase based on past menstrual data taking these characteristics into account, learn how to evaluate the player's physical and mental condition, and then use a neural network model or decision tree model that has learned how to generate advice according to the menstrual phase and condition evaluation results and training content.

[0225] The present invention is not limited to the above-described embodiments and includes various modifications. For example, the above-described embodiments have been described in detail to clearly explain the present invention, and are not necessarily limited to those including all of the described configurations. Furthermore, it is possible to replace part of the configuration of one embodiment with the configuration of another embodiment, and it is also possible to add the configuration of another embodiment to the configuration of one embodiment. Furthermore, it is possible to add, delete, or replace part of the configuration of each embodiment with other configurations.

[0226] DESCRIPTION OF SYMBOLS 1: Sports support system 2: User terminal 3: Measuring device 10: Communication I / F 11: CPU 12: Memory 13: Storage 15: Program 20: Dashboard control unit 21: Condition management unit 22: Training management unit 23: Physical management unit 24: Stats management unit 25: Injury management unit 26: Treatment management unit 27: Physical growth management unit 28: User I / F 30: Analysis data unit 31: Condition data unit 32: Training data unit 33: Physical data unit 34: Stats data unit 35: Injury data unit 36: Treatment data unit 37: Physical growth data unit 40: Team dashboard control unit 41: Player list dashboard control unit 42: Player dashboard control unit 43: Condition input unit 44: Alert determination unit 45: Condition analysis section 46: Condition support section 47: Training planning section 48: Training result section 49: Training analysis section 50: Training simulator 50A: Player model 50B: Player model 50C: Player model 51: Training proposer 52: Physical input section 53: Physical evaluation section 54: Physical analysis section 55: Physical support section 56: Stats input section 57: Stats evaluation section 58: Stats analysis section 59: Stats support section 60: Injury input section 61: Injury prevention section 62: Rehabilitation planning section 63: Injury analysis section 64: Injury support section 65: Treatment input section 66: Treatment analysis section 67: Treatment support section 68: Physical growth input section 69 : Physical growth prediction section 70: Physical growth analysis section 71: Physical growth support section

Claims

A sports support system capable of communicating with one or more athlete terminals used by one or more athletes constituting a team playing a sport, and one or more staff terminals used by one or more staff members supporting the athletes, a database storing condition data including one or more condition items related to the physical and / or mental condition of the athlete, and training data including one or more training items related to training performed by the athlete; a dashboard control unit that uses the data stored in the database to create a first dashboard that displays team condition information related to the team's condition status and team training information related to the team's training status, and a second dashboard that displays player condition information related to the condition status of each player and player training information related to the training status of each player, and provides the first and second dashboards to each staff terminal and the second dashboard corresponding to each user to each player terminal; Equipped with the training data includes, as the training items, items related to the exercise load of the training performed by the athlete; the first dashboard, a time series transition of a first index relating to the exercise load of the team based on the training data of the players, a time series transition of a second index relating to the physical and / or mental condition of the team based on the condition data of the players, and a time series transition of a third index relating to the risk of injury occurring according to the exercise load of the team are displayed on the same time axis so as to be comparable; The second dashboard corresponding to each player includes: The time series transition of a fourth index related to the exercise load of each of the players, the time series transition of a fifth index related to the physical and / or mental condition of each of the players, and the time series transition of a sixth index related to the risk of injury occurring according to the exercise load of each of the players are displayed in a comparative manner. Sports support system. 　 The sports support system according to claim 1, The training data includes, as the training item, an RPE (Rating of Perceived Exertion) input regarding the training performed by the athlete, the first index has a team RPE value related to the team's RPE based on the RPE input by the athlete; the third indicator has a team ACWR value related to the ACWR (Acute: Chronic Workload Ratio) of the team based on the RPE input by the player; the fourth index includes an athlete RPE value related to the RPE input by each athlete; The sixth indicator has an athlete ACWR value related to the ACWR (Acute: Chronic Workload Ratio) of each athlete based on the RPE input by each athlete. Sports support system. 　 The sports support system according to claim 1, the second index has a team condition value that quantifies the physical and mental condition of the team based on the condition data of the players; The fifth index has a player condition value that quantifies the physical and mental condition of each player based on the condition data of each player. Sports support system. 　 A sports support system capable of communicating with one or more athlete terminals used by one or more athletes constituting a team playing a sport, and one or more staff terminals used by one or more staff members supporting the athletes, a database storing condition data including one or more condition items related to the physical and / or mental condition of the athlete, and training data including one or more training items related to training performed by the athlete; a training planning unit that enables the staff member to plan a training menu, stores the planned training menu as the training item in the database, and provides the planned training menu to the staff terminal and the player terminal; a training simulator that inputs the planned training menu and estimates an implementation effect of the planned training menu that may appear in the training data or the condition data of the team or each player if the planned training menu is implemented for the team or each player; Equipped with Sports support system. 　 The sports support system according to claim 4, The implementation effect includes ACWR of the team or each player that may be generated by implementing the planned training menu. Sports support system. 　 A sports support system capable of communicating with one or more athlete terminals used by one or more athletes constituting a team playing a sport, and one or more staff terminals used by one or more staff members supporting the athletes, a database storing condition data including one or more condition items related to the physical and / or mental condition of the player, training data including one or more training items related to the training the player performs, injury data related to injuries or illnesses the player has sustained, physical data related to the player's physical performance, stats data related to the stats of the team and the player, and / or physical growth data related to the player's physical growth; a training planning unit that enables the staff member to plan a training menu, stores the planned training menu as the training item in the database, and provides the planned training menu to the staff terminal and the player terminal; a training simulator that inputs the planned training menu and estimates the implementation effect of the planned training menu that may appear in the training data, the condition data, the injury data, the physical data, the stats data, and / or the physical growth data of the team or each player if the planned training menu is implemented by the team or each player; A sports support system equipped with: 　 The sports support system according to claim 4 or 6, The training simulator has a player model that has learned the relationship between the training menu that the team or each player actually performed and the actual implementation effect thereof, and estimates the implementation effect of the planned training menu using the player model. Sports support system. A sports support system capable of communicating with one or more athlete terminals used by one or more athletes constituting a team playing a sport, and one or more staff terminals used by one or more staff members supporting the athletes, a database storing condition data including one or more condition items related to the physical and / or mental condition of the athlete, and training data including one or more training items related to training performed by the athlete; a training proposer that sets a goal related to the condition data or the training data of the team or each of the players, automatically creates a training menu according to the goal, and proposes it to the staff terminal or the player terminal; A sports support system equipped with: 　 A sports support system capable of communicating with one or more athlete terminals used by one or more athletes constituting a team playing a sport, and one or more staff terminals used by one or more staff members supporting the athletes, a database storing condition data including one or more condition items related to the physical and / or mental condition of the player, training data including one or more training items related to the training the player performs, injury data related to injuries or illnesses the player has sustained, physical data related to the player's physical performance, stats data related to the stats of the team and the player, and / or physical growth data related to the player's physical growth; a training proposer that sets goals for the condition data, the training data, the injury data, the physical data, the stats data, and / or the physical growth data of the team or each player, automatically creates a training menu according to the goals, and proposes the menu to the staff terminal or the player terminal; A sports support system equipped with: 　 An athlete support system capable of communicating with one or more athlete terminals used by one or more athletes, a database storing condition data including one or more condition items related to the physical and / or mental condition of the athlete, and training data including one or more training items related to training performed by the athlete; a generation unit that generates advice that the athlete should be aware of based on the condition data and / or the training data; a feedback unit that feeds back the advice to the athlete; An athlete support system comprising:

11. The athlete support system of claim 10, the training data includes, as the training items, data on the exercise load of the training performed by the athlete; the generating unit evaluates a risk of injury associated with the training performed by the athlete based on the data regarding the exercise load, and generates the advice regarding training according to the results of the evaluation. Athlete support system.

11. The athlete support system of claim 10, the database further stores data regarding the athlete's performance; the generating unit evaluates the data related to the performance, and generates the advice related to training in accordance with a result of the evaluation. Athlete support system.

11. The athlete support system of claim 10, the condition data includes data regarding the athlete's mental condition for training; the generating unit generates the advice regarding the athlete's stress based on the data regarding the mental condition. Athlete support system.

11. The athlete support system of claim 10, the condition data includes data on the athlete's dietary intake, the generating unit generates the advice for improving the athlete's eating habits based on the dietary data. Athlete support system.

11. The athlete support system of claim 10, the condition data includes data on the athlete's sleeping time and data on the athlete's feeling of deep sleep or sleep rest, the generating unit generates the advice for improving the athlete's sleeping habits based on the data regarding the sleeping time and the data regarding the feeling of deep sleep or restful sleep. Athlete support system.

11. The athlete support system of claim 10, the database stores data relating to body weight, including data relating to lean body mass and / or body fat of the athlete; the generation unit determines whether the increase in the athlete's weight is due to an increase in the lean body mass or an increase in the body fat based on the data related to the weight, and generates the advice related to the weight gain based on the result of the determination. Athlete support system.

11. The athlete support system of claim 10, the database stores data relating to the athlete's weight, data relating to the athlete's diet, and data relating to the athlete's training volume; the generation unit generates the advice to improve the athlete's eating habits in accordance with the amount of exercise, if the athlete is losing weight, based on the data related to the weight, the data related to the diet, and the data related to the amount of exercise. Athlete support system.

11. The athlete support system of claim 10, the database stores data regarding the location and type of carburization pain of the athlete; the generating unit generates the advice regarding treatment for the pain based on data regarding the location and type of the pain. Athlete support system.

11. The athlete support system of claim 10, the database stores data relating to a sport in which the athlete participates and data relating to the athlete's performance in the sport; the generation unit generates the advice regarding training to improve the performance based on data regarding the sport and data regarding the performance in the sport. Athlete support system.

11. The athlete support system of claim 10, the database further stores physical growth data relating to the athlete's physical growth; the generation unit predicts a growth stage of the athlete based on the physical growth data, and generates the advice regarding dietary content according to the growth stage. Athlete support system.

11. The athlete support system of claim 10, The database stores data on the exercise intensity of the training performed by the athlete and data on the athlete's review of the training performed by the athlete; the generation unit generates the advice including a score that increases when the athlete trains and decreases when the athlete takes a break from training, based on the data related to the exercise intensity and the review data. Athlete support system.

11. The athlete support system of claim 10, the database stores data on the exercise intensity of the training performed by the athlete, data on the food consumed by the athlete, and data on the sleep taken by the athlete; the generation unit generates the advice including a score that increases when the athlete trains and decreases when the athlete rests and neglects appropriate lifestyle habits, based on the data related to the exercise intensity, the data related to the diet, and the data related to the sleep. Athlete support system.

11. The athlete support system of claim 10, the database stores menstrual data relating to the menstruation of female athletes; the generation unit identifies a current menstrual phase of the female athlete from among a plurality of menstrual phases of a menstrual cycle based on the menstrual data, and generates the advice regarding training or physical condition in accordance with the current menstrual phase. Athlete support system.

11. The athlete support system of claim 10, the database stores menstrual data relating to the menstruation of female athletes; the generation unit estimates an abnormality in the female athlete's menstrual cycle based on the menstrual data, and generates the advice for improving the abnormality. Athlete support system.

Images