Dynamically determine the region

Abstract

A computer-implemented method includes: monitoring sensor data by a computing device during a match of a sports event; determining, by the computing device, a predictor associated with a target based on the monitored sensor data; determining, by the computing device, a real-time effectiveness region for the target based on the predictor and training data identifying the historical effectiveness of the target; and outputting, by the computing device, the real-time effectiveness region for displaying the real-time effectiveness region around the target.

Description

Background Art

[0001] The present invention generally relates to dynamically determining regions.

[0002] During a match of some sports (e.g. tennis), a player attempts to score points from an opponent by hitting the ball within the boundaries of the court and at a position that minimizes the opponent's chance of returning the ball. In other words, a player attempts to shoot the ball in such a way as to minimize the effectiveness of the opponent's return. There is an area around each player where they are most active. This area is constantly changing as the athlete / player adapts to the environment on the field or court. Summary of the invention

[0003] In one aspect of the invention, a computer-implemented method includes: monitoring sensor data by a computing device during play of a sporting event; determining, by the computing device, a predictor associated with a target based on the monitoring of the sensor data; determining, by the computing device, a real-time validity zone for the target based on the predictor and training data identifying the historical validity of the target; and outputting, by the computing device, the real-time validity zone for displaying the real-time validity zone around the target. In another aspect of the invention, the method includes updating the real-time validity zone for the target based on continuous monitoring of the sensor data; and continuously outputting updates to the real-time validity zone to continuously display updates to the real-time validity zone. In another aspect of the invention, the training data includes training records that identify the validity of the game and a specific set of predictors associated with the validity of the game. Advantageously, aspects of the invention determine and present real-time validity zones to improve spectator experience and improve evaluation of athletes' play and technique.

[0004] In one aspect of the invention, there is a computer program product for training a machine learning system to determine and display a real-time volume of effectiveness of a target. The computer program product includes a computer-readable storage medium having program instructions embodied therein, the program instructions being executable by a computing device to cause the computing device to: monitor sensor data during the play of a sporting event; determine the effectiveness of the play performed by the target; determine a data set of predictors associated with the target based on the monitoring of the sensor data; generate and store a training data record, the training data record associating the effectiveness of the play with the data set of predictors; determine a data set of real-time predictors based on the monitoring of the sensor data; determine the real-time volume of effectiveness of the target based on the data set of real-time predictors and the generation of the training data record; and output a real-time volume of effectiveness for displaying the real-time volume of effectiveness around the target. In another aspect of the invention, the real-time volume of effectiveness is the volume of a cylinder, wherein the radius of the volume of the cylinder is determined based on a first regression equation, and the height of the cylinder is determined based on a second regression equation. Advantageously, aspects of the invention train a machine learning system for determining a personalized volume of effectiveness to improve the audience experience and improve the evaluation of athletes' play and technique.

[0005] In one aspect of the invention, a system includes: a processor associated with a computing device, a computer-readable memory, and a computer-readable storage medium; program instructions for monitoring sensor data during the play of a sporting event; program instructions for determining a volume of effectiveness of the primary goal based on the monitoring of the sensor data and a first set of predictors associated with a primary goal; program instructions for determining a volume of effectiveness of the secondary goal based on the monitoring of the sensor data and a second set of predictors associated with a secondary goal; program instructions for determining a third set of predictors associated with the secondary goal, the third set of predictors minimizing the volume of effectiveness of the secondary goal; program instructions for determining one or more recommended actions for the primary goal to introduce the third set of predictors and minimize the volume of effectiveness of the secondary goal; and program instructions for displaying the volume of effectiveness of the primary goal, the volume of effectiveness of the secondary goal, and the recommended actions. The program instructions are stored on a computer-readable storage medium for execution by the processor via the computer-readable memory. In another aspect of the invention, the system also includes program instructions for determining and displaying a narrative describing the volume of effectiveness of the primary goal, the volume of effectiveness of the secondary goal, or the recommended action generated using natural language. In another aspect of the invention, the primary target is a player of a sporting event, the secondary target is an opponent player, and the sporting event is tennis. Advantageously, aspects of the invention determine and present real-time effectiveness zones and corresponding automatically generated commentary to improve the spectator experience and improve the evaluation of the player's play and technique.

[0006] In one aspect of the invention, a computer-implemented method includes generating, by a computing device, a plurality of training data records of a target of a sporting event, wherein the training data records each identify a measure of effectiveness of a play conducted by the target, and a data set of historical predictors associated with each measure of effectiveness; monitoring sensor data of the sporting event in real time by the computing device; determining, by the computing device, a data set of real-time predictors of the target based on the monitoring of the sensor data; determining, by the computing device, a real-time effectiveness volume of the target based on the data set of real-time predictors and the generating of the plurality of training data records; and outputting, by the computing device, a real-time effectiveness volume for displaying the real-time effectiveness volume around the target. In another aspect of the invention, the real-time effectiveness volume is the volume of a cylinder, wherein the radius of the volume of the cylinder is determined based on a first regression equation, and the height of the cylinder is determined based on a second regression equation. Advantageously, aspects of the invention maintain training records for determining and presenting real-time effectiveness areas to improve spectator experience and improve evaluation of athletes' play and technique. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] The invention is described in the following detailed description, by way of non-limiting examples of exemplary embodiments of the invention, with reference to the several figures mentioned.

[0008] Figure 1 A computer infrastructure according to aspects of the invention is shown.

[0009] Figure 2 An overview of an example implementation according to aspects of the invention is shown.

[0010] Figure 3 An example environment according to aspects of the invention is shown.

[0011] Figure 4 An example flow chart for generating a training data record to be used to determine weighting factors and values ​​for unknown variables in an effectiveness volume equation is shown in accordance with aspects of the present invention.

[0012] Figure 5 An implementation according to aspects of the present invention is shown.

[0013] Figure 6 An example flow chart for determining a real-time effectiveness volume at a specific point in time based on training data, real-time predictors, and / or weighting factors according to aspects of the present invention is shown.

[0014] Figure 7 An example flow diagram for determining actions that minimize an adversary's effectiveness volume according to aspects of the invention is shown.

[0015] Figure 8-10 An exemplary graph showing rate of change analysis of various predictors according to aspects of the present invention is shown.

[0016] Fig.11 An example flow chart for determining a real-time effectiveness volume according to aspects of the present invention is shown. DETAILED DESCRIPTION

[0017] The present invention generally relates to dynamically determining the effectiveness area of ​​an athlete during a match, and more specifically, to dynamically determining the effectiveness area of ​​an athlete based on a predictor during a match. Aspects of the present invention dynamically determine the effectiveness area of ​​a target (e.g., an athlete) during a match of a sport (e.g., tennis). Aspects of the present invention display the effectiveness area (also referred to herein as "effectiveness area" or "effectiveness volume") in real time during a match. As described herein, in one aspect of the present invention, the effectiveness area represents an area or volume around a target (e.g., an athlete) in which the athlete is considered to be "effective" (e.g., conducting an effective "match" with a high probability of scoring against an opponent or defending against a player by an opponent). Using a tennis game as an illustrative example, a "match" is considered to be an event in which an athlete is assigned a task to return the ball to an opponent in an attempt to score against the opponent.

[0018] In an embodiment, the validity volume is the volume of a cylinder (or any other various shapes) with a specific radius around the athlete. As described herein and according to an embodiment of the present invention, the validity volume is determined based on the validity of various predictors, situation data, sequential data, biometric data related to the athlete and / or the previous game performed by the athlete. Using a tennis match as an illustrative example, the "validity" of the game can be related to whether the game causes the athlete to score, or causes the successful defense of the opponent to the athlete's score. As described herein, the validity volume is determined based on the validity and predictors of the previous game, the predictors such as the body position / towards of the athlete, the momentum and running direction of the athlete at a given time, the initial and end speed of the athlete during the game, the maximum and average acceleration of the athlete, the angle of the direction / track of the athlete and the change of the direction / track, the track of the ball, the forehand swing or backhand swing position of the athlete, the fatigue level of the athlete, the position of the athlete on the court, etc. As described herein, a group of sensor devices (including cameras, motion sensors, object sensors, etc.) are used to collect predictors, which are distributed in a sports environment (for example, around courts, venues, etc.) and / or worn by the athlete.

[0019] As described herein, the predictor is used to determine the unknown variable in the volume equation for a particular shape (e.g., V = πr for a cylinder). 2). In the case of a cylinder, the predictors are used to determine values ​​for the radius and height to derive the volume of effectiveness. As described herein, historical data and / or training data records are used to determine the predictors, which can then be used to determine the unknown variables in the volume equation to determine the volume of effectiveness. The training data can be periodically updated to more accurately determine the volume of effectiveness. That is, machine learning and cognitive computing techniques are used to train a machine learning system to accurately determine the volume of effectiveness of a target at any given time based on the predictors associated with the target.

[0020] In an embodiment, the training data includes data records that associate predictors with the effectiveness of the play. Thus, aspects of the invention obtain information about the predictors from one or more sensor devices to derive the effectiveness of the play from the historical training data and determine a volume of effectiveness. In an example use case according to an embodiment of the invention, the volume of effectiveness is viewable in real time to enhance the spectator viewing experience and can be replayed at a later time and used to allow athletes and coaches to evaluate, adjust and improve technique.

[0021] As described herein, the athlete's effectiveness volume is determined using a set of predictors. Likewise, aspects of the present invention determine the actions that athletes can take in order to create a situation where a predictor (e.g., minimizing the effectiveness of the opponent's "redirection step" when redirecting to play a game) is introduced during a match to minimize the effectiveness volume of the opponent. As described herein, a "redirection step" may refer to a movement or a series of movements that change the direction in which the player moves. Movement may be a shortening or extension of footsteps (e.g., short steps to long strides), lateral movement (e.g., sliding steps), slamming (e.g., when reaching a drop shot), stepping back (e.g., for the player in front of the net and the opponent in the situation of the player's overhead "high ball"). In other words, aspects of the present invention determine the actions that athletes can take in order to minimize the effectiveness volume of their opponents and minimize the chance of the opponent's scoring or the game performed by the antagonist.

[0022] As an illustrative example, aspects of the invention determine that at a given point in a tennis match, the player should aim to hit the ball to a particular location in the court, a backhand swing toward the opponent, etc., because these actions will result in the occurrence of predictors that minimize the opponent's effective volume. That is, aspects of the invention determine that the suggested actions will result in the opponent being in a "weak" position, the opponent needing to take a difficult trajectory to make the match, the opponent needing to take a difficult "redirecting step", the opponent needing to use a weaker type of swing (e.g., a backhand swing), the opponent needing to travel a relatively long distance to make the match, the opponent needing to have a particular momentum and direction to make the match, etc.

[0023] In an embodiment, the effectiveness volume is generated in any of a variety of shapes (e.g., cube, cylinder, rectangular prism, etc.). Different athletes, preferences, and goals use different shapes. In an embodiment, aspects of the invention determine effectiveness volumes for multiple different shapes, and the user can select which shape to display for the effectiveness volume.

[0024] In embodiments, aspects of the invention use an effectiveness volume to predict where a player is likely to be predicted to be during play based on predictors such as ball trajectory. For example, aspects of the invention predict that a player is within a volume of effectiveness. Additionally or alternatively, the effectiveness volume represents where the player should have the highest chance of success, and similarly, represents actions that the player can take to minimize the chance of success of his or her opponent.

[0025] As described herein, in an exemplary use case, aspects of the invention generate a narrative based on a determination of an effectiveness volume and / or a determination of actions that a player can take to minimize an opponent's effectiveness volume. For example, aspects of the invention use natural language generation (NLG) techniques to generate a narrative that describes a situation based on an effectiveness volume and corresponding predictors (e.g., to generate an automated play-by-play analysis). As an illustrative example, aspects of the invention generate a narrative "Player A is outstanding at returning the ball after 5 rounds of rallies and when hitting a forehand."

[0026] Although aspects of the present invention are described in terms of determining the effectiveness volume for a tennis match, aspects of the present invention are not limited thereto. For example, aspects of the present invention may be applied to other sports or recreational activities, such as baseball, basketball, boxing / taekwondo, golf, Frisbee, kite flying, billiards, table tennis, polo, soccer, rugby, etc. In addition, aspects of the present invention may be applied to singles or doubles tennis, so that an analysis may be performed to determine a situation in which one player is optimally positioned to play over another player. In addition, aspects of the present invention are used to determine any effectiveness area (e.g., an effectiveness area for a two-dimensional analysis rather than an effectiveness volume for a three-dimensional analysis). Thus, a similar process for determining an effectiveness volume may be used to determine an effectiveness area.

[0027] Aspects of the present invention provide a technical solution to the technical problem of determining an athlete's effectiveness volume by determining an unknown variable in a volume equation to determine a volume metric. As described herein, regression techniques are used to determine the unknown variables in the volume equation. In addition, technical solutions involving machine learning and cognitive computing techniques are used to solve the technical problem of accurately determining a predictor for an athlete, which in turn is used to determine the effectiveness volume. In an embodiment, aspects of the present invention generate a user interface or modify an existing user interface to display and illustrate the effective range / volume of an athlete's movement and effectiveness. Aspects of the present invention improve user interface technology by implementing a prediction system that displays effectiveness, predicted movement, and related simulations on a user interface.

[0028] Aspects of the present invention provide specific implementations that solve specific problems, namely, using machine learning and cognitive computing to solve the problem of determining the effective volume of a player and minimizing the effective volume of the player's opponents. In the professional sports environment, specific solutions of aspects of the present invention are used to solve real-world specific problems. In addition, aspects of the present invention improve the way data is processed to provide specific solutions to the specific problems described herein.

[0029] The present invention may be a system, method and / or computer program product at any possible level of technical detail integration. The computer program product may include a computer-readable storage medium (or multiple media) having computer-readable program instructions thereon, and the computer-readable program instructions are used to cause a processor to perform various aspects of the present invention.

[0030] A computer-readable storage medium may be a tangible device capable of retaining and storing instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of computer-readable storage media includes the following: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device such as a punch card or a raised structure in a groove on which instructions are recorded, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium should not be interpreted as a temporary signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated by a waveguide or other transmission medium (e.g., a light pulse by an optical fiber cable), or an electrical signal transmitted by a wire.

[0031] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to a corresponding computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical transmission fibers, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions to be stored in a computer-readable storage medium within the corresponding computing / processing device.

[0032] The computer-readable program instructions for performing the operation of the present invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, configuration data of an integrated circuit, or source code or object code written in any combination of one or more programming languages ​​(including object-oriented programming languages, such as Smalltalk, C++, etc.) and procedural programming languages ​​(such as "C" programming language or similar programming languages). The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or completely on a remote computer or server. In the latter case, the remote computer may be connected to the user's computer via any type of network connection, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider via the Internet). In some embodiments, in order to perform various aspects of the present invention, an electronic circuit including, for example, a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA) may execute computer-readable program instructions to personalize the electronic circuit by utilizing the state information of the computer-readable program instructions.

[0033] Various aspects of the present invention are described herein with reference to the flow chart and / or block diagram of the method, device (system) and computer program product according to embodiments of the present invention. It will be understood that each frame of the flow chart and / or block diagram and the combination of frames in the flow chart and / or block diagram can be implemented by computer-readable program instructions.

[0034] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device create a device for implementing the functions / actions specified in one or more boxes of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, which can guide the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable storage medium having the instructions stored therein includes an article of manufacture, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes of the flowchart and / or block diagram.

[0035] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable apparatus, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable apparatus, or other device implement the functions / actions specified in one or more boxes of the flowchart and / or block diagram.

[0036] Flowcharts and block diagrams in the accompanying drawings show possible architectures, functions and operations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each frame in a flow chart or a block diagram can represent a module, a segment or a part of an instruction, which includes one or more executable instructions for realizing a specified logical function. In some alternative embodiments, the function noted in the frame may not occur in the order noted in the figure. For example, two frames shown in succession can actually be performed substantially simultaneously, or these frames can sometimes be performed in reverse order, depending on the function involved. It will also be noted that each frame of a block diagram and / or a flow chart diagram and the combination of frames in a block diagram and / or a flow chart diagram can be realized by a dedicated hardware-based system that performs a specified function or action or performs a combination of special-purpose hardware and computer instructions.

[0037] Reference now Figure 1 , a schematic diagram of an example of a computer infrastructure is shown. Computer infrastructure 10 is only one example of a suitable computing node and is not intended to impose any limitations on the scope of use or functionality of the embodiments of the present invention described herein. Regardless, computer infrastructure 10 can be implemented and / or perform any of the functions described above.

[0038] In the computer infrastructure 10, there is a computer system / server 12, which can operate with many other general or special purpose computing system environments or configurations. Examples of well-known computing systems, environments and / or configurations suitable for use with the computer system / server 12 include, but are not limited to, personal computer systems, server computer systems, thin clients, fat clients, handheld or laptop devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputer systems, mainframe computer systems, and distributed cloud computing environments including any of the above systems or devices, etc.

[0039] Computer system / server 12 may be described in the general context of computer system executable instructions, such as program modules, executed by the computer system. Generally, program modules may include routines, programs, objects, components, logic, data structures, etc. that perform specific tasks or implement specific abstract data types. Computer system / server 12 may be practiced in a distributed cloud computing environment, where tasks are performed by remote processing devices that are linked through a communications network. In a distributed cloud computing environment, program modules may be located in local and remote computer system storage media including memory storage devices.

[0040] like Figure 1 As shown, the computer system / server 12 in the computer infrastructure 10 is shown in the form of a general-purpose computing device. The components of the computer system / server 12 may include, but are not limited to, one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 to the processor 16.

[0041] Bus 18 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. By way of example and not limitation, these architectures include an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MCA) bus, an Enhanced ISA (EISA) bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0042] Computer system / server 12 typically includes a variety of computer system readable media. Such media can be any available media that can be accessed by computer system / server 12, and it includes volatile and nonvolatile media, removable and non-removable media.

[0043] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The computer system / server 12 may also include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, a storage system 34 may be provided for reading from and writing to a non-removable, non-volatile magnetic medium (not shown, and commonly referred to as a "hard drive"). Although not shown, a disk drive for reading from and writing to a removable, non-volatile disk (e.g., a "floppy disk") may be provided, as well as an optical drive for reading from or writing to a removable, non-volatile optical disk such as a CD-ROM, DVD-ROM or other optical media. In this case, each may be connected to the bus 18 via one or more data media interfaces. As will be further depicted and described below, the memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of an embodiment of the present invention.

[0044] A program / utility 40 having a set (at least one) of program modules 42, as well as an operating system, one or more application programs, other program modules, and program data, may be stored in memory 28 as an example and not by way of limitation. Each of the operating system, one or more application programs, other program modules, and program data, or some combination thereof, may include an implementation of a networking environment. Program modules 42 generally perform the functions and / or methods of embodiments of the present invention described herein.

[0045] The computer system / server 12 may also communicate with one or more external devices 14, such as a keyboard, pointing device, display 24, etc.; one or more devices that enable a user to interact with the computer system / server 12; and / or any device that enables the computer system / server 12 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may occur via an input / output (I / O) interface 22, however, the computer system / server 12 may communicate with one or more networks, such as a local area network (LAN), a general purpose wide area network (WAN), and / or a public network (e.g., the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other components of the computer system / server 12 via a bus 18, and it should be understood that, although not shown, other hardware and / or software components may be used in conjunction with the computer system / server 12, examples of which include, but are not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archival storage systems, etc.

[0046] Figure 2An overview of an example implementation according to aspects of the present invention is shown. Figure 2 As shown, during a match of a sporting event (e.g., tennis), an effectiveness volume is determined for each player at a given time. For example, as the match progresses, the players move around, and the predictors continuously change based on the player's trajectory, the ball trajectory, the player's momentum, the player's acceleration, the player's speed, the player's, etc. Figure 2 As can be seen in Figure 2, as the game progresses, the effectiveness volume changes dynamically based on the changing predictors. Figure 2 In the example of , at one moment in time, a player has one effectiveness volume (e.g., effectiveness volume 201), and at another moment in time (e.g., after the player has moved), the same player has a different effectiveness volume (e.g., effectiveness volume 202). Similarly, at one moment in time, an opponent has one effectiveness volume (e.g., effectiveness volume 203), and at another moment in time (e.g., after the opponent has moved), the same opponent has a different effectiveness volume (e.g., effectiveness volume 204).

[0047] In an embodiment, the validity volume is included in a live broadcast of a sporting event. As an exemplary use case according to one aspect of the present invention, the validity volume is Figure 2 A similar manner as shown is superimposed on a live video broadcast of the athlete. Additionally or alternatively, in an exemplary embodiment, the user device runs an application that graphically represents the athlete and the effectiveness volume in real time. In this way, the audience experience is improved by providing the audience with greater insight into how the conduct of the game affects the effectiveness of the athlete. Furthermore, in an embodiment, the game video with the effectiveness volume is stored and replayed at a later time to allow athletes and coaches to evaluate, adjust and improve techniques. In addition, predictors related to the effectiveness volume may be stored to allow athletes and coaches to evaluate and gain insight into which predictors maximize the effectiveness volume of the athlete and which predictors minimize the effectiveness volume of their opponents. In an exemplary embodiment, Figure 2 The example shown may be a screenshot of a user interface displaying players and opponents and their respective effectiveness volumes in real time. Figure 2 These images / simulations shown in are presented and can be further manipulated while displayed in a user interface.

[0048] Figure 3 An example environment according to aspects of the present invention is shown. Figure 3 As shown, environment 300 includes user device 210, sensor device 215, athlete effectiveness volume determination system 220, and network 230. In an embodiment, one or more components in environment 300 correspond to Figure 2In one embodiment, one or more components in the cloud computing environment 300 include Figure 1 Components of computer system / server 12.

[0049] User device 210 comprises a computing device capable of communicating via a network, such as network 230. For example, user device 210 may correspond to a mobile communication device (e.g., a smart phone or personal digital assistant (PDA)), a portable computer device (e.g., a laptop or tablet computer), a desktop computer, and / or another type of computing device. In some embodiments, user device 210 hosts an application for displaying representations of athletes and their respective effectiveness volumes. Additionally or alternatively, user device 210 is used to view a live or recorded broadcast of a sporting event, wherein the effectiveness volume is superimposed on the live video of the athlete. Additionally or alternatively, user device 210 receives information identifying a predictor based on which the effectiveness volume is based at a particular point in time (e.g., to allow an athlete and / or coach to evaluate how different predictors and situations affect the effectiveness volume).

[0050] Sensor device 215 comprises one or more electronic sensors (for example, camera, motion sensor, object sensor, audio sensor, etc.) in order to collect sensor data relevant to predictor. In an embodiment, sensor device 215 is distributed on or around court, field, etc. In an embodiment, sensor device 215 is used to determine predictor and / or other data during the game, such as athlete track, ball track, athlete speed, athlete acceleration, change in athlete movement, towards / position, etc. In an embodiment, sensor device 215 comprises wearable device worn by athlete, wherein sensor device 215 collects biodata and / or one or more predictor, such as those described herein. In an embodiment, sensor device 215 collects data, such as X, Y, Z coordinates and / or speed unit vectors, ball and speed of each athlete / opponent's position, etc. of ball and each athlete / opponent. The data collected by sensor device 215 can be stored in a cloud-based database, and can comprise millions or potentially billions of data points. In an embodiment, storage data record is associated with the measure of the effectiveness of predictor and game.

[0051] The athlete effectiveness volume determination system 220 includes one or more computing devices (e.g., such as Figure 1Computer system / server 12 of the present invention) dynamically determines the effectiveness volume of the athlete during the game. As described herein, the athlete effectiveness volume determination system 220 tracks training data, which establishes the measure of the effectiveness of various games performed by the athlete (e.g., using the game effectiveness determination module 222), and the predictor related to the effectiveness (e.g., using the predictor determination module 221). From the training data (e.g., stored by the training database 223), the athlete effectiveness volume determination system 220 determines the weighting factor, which is incorporated into the determination of the unknown variable in the volume equation, as described in more detail herein. The athlete effectiveness volume determination system 220 monitors the sensor data collected by the sensor device 215, and stores information associating the sensor data (e.g., related to the predictor) with the measure of the effectiveness of the game. The athlete effectiveness volume determination system 220 uses the real-time sensor data to determine the real-time predictor (e.g., using the predictor determination module 221) and determine the real-time effectiveness volume of the athlete (e.g., using the effectiveness volume determination module 224). The athlete effectiveness volume determination system 220 uses machine learning / training and cognitive computing techniques to accurately determine the effectiveness volume of a goal at any given time based on predictors associated with the goal.

[0052] The network 230 includes network nodes and one or more wired and / or wireless networks. For example, the network 230 may include a cellular network (e.g., a second generation (2G) network, a third generation (3G) network, a fourth generation (4G) network, a fifth generation (5G) network, a long term evolution (LTE) network, a global system for mobile (GSM) network, a code division multiple access (CDMA) network, an evolution data optimized (EVDO) network, etc.), a public land mobile network (PLMN) and / or another network. In addition, or alternatively, the network 230 may include a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), a public switched telephone network (PSTN), an ad hoc network, a managed Internet protocol (IP) network, a virtual private network (VPN), an intranet, the Internet, a fiber-based network and / or a combination of these or other types of networks.

[0053] The number of devices and / or networks in environment 300 is not limited to Figure 3 The number shown, in reality, environment 300 may include additional devices and / or networks; fewer devices and / or networks; different devices and / or networks; or Figure 3 Furthermore, in some implementations, one or more devices of environment 300 may perform one or more functions described as being performed by another one or more devices of environment 300. The devices of environment 300 may be interconnected via wired connections, wireless connections, or a combination of wired and wireless connections.

[0054] Figure 4 An example flow chart of a process for generating a training data record that will be used to determine weighting factors and to determine values ​​of unknown variables in the effectiveness volume equation is shown. Figure 4 For example, in Figure 3 is implemented in an environment and uses Figure 3 As described above, the flowcharts illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. As described herein, Figure 4 A process is used to determine training data representing the effectiveness of matches, the effectiveness volumes of those matches, and the predictors of those matches. Once sufficient training data is generated, the training data is used to derive a real-time effectiveness volume at a given time based on a real-time set of predictors.

[0055] like Figure 4 As shown, as an illustrative example, process 400 includes monitoring sensor data during the play of a game (step 410). For example, the player effectiveness volume determination system 220 monitors sensor data from the sensor device 215 during the play of a sport (e.g., tennis). In an embodiment, the player effectiveness volume determination system 220 monitors sensor data related to predictors, such as player trajectory, ball trajectory, player speed, player acceleration, changes in player movement, orientation / position, etc.

[0056] Process 400 also includes determining the effectiveness of the game (step 420). For example, the athlete effectiveness volume determination system 220 determines the measure of the effectiveness of the game played by the athlete. Using a tennis match as an illustrative example, a "game" can be considered as such an event, wherein the athlete is assigned a task to return the ball to the opponent in an attempt to score against the opponent. In tennis, the effectiveness of the game can be measured based on the ball speed after playing the game (for example, when the ball returns), the result of the game (for example, whether the game leads to scoring, defensive opponent scoring, etc.) and / or the result of the subsequent game. In an embodiment, the effectiveness of the game is determined to be a numerical value representing the level that the game effectively reaches. For example, the game score of scoring immediately is relatively high, and the game score of losing the scoring point immediately is relatively low.

[0057] Process 400 also includes determining that the athlete travels to complete the distance of the game (step 430). For example, the athlete's effectiveness volume determination system 220 uses the sensor data monitored to determine that the athlete travels to complete the distance of the game. As described in more detail here, in an exemplary embodiment, the radius value of the distance representation effectiveness volume, and is a part for determining the training data record of the weighting factor to be used to determine the real-time effectiveness volume. In fact, the athlete travels to complete the distance representation radius of the game, and therefore represents volume (wherein in an exemplary embodiment, the height value is a fixed value based on the height of the athlete and the reach range). If the game is considered to be effective (for example, in step 420), the volume determined in step 430 is the effectiveness volume.

[0058] Process 400 also includes determining a predictor data set (step 440). For example, the player effectiveness volume determination system 220 determines a predictor data set that identifies predictors during play at a given point in time. The predictor data set includes information collected by the sensor device 215 while monitoring sensor data. For example, the predictor data set represents a player's position on the court, a player's trajectory, a player's momentum, a ball trajectory, a player's speed, a player's acceleration, a change in the player's motion, a direction / position, and / or other actions related to playing the game. Additionally or alternatively, the predictor data set identifies biometric data of the player.

[0059] Process 400 also includes storing training data records for completed matches (step 450). For example, the athlete effectiveness volume determination system 220 stores training data records, which associate the prediction data set with a measure of the effectiveness of the match and the distance traveled by the athlete (e.g., corresponding to the radius in the volume equation of a cylinder, or the length / width in the volume equation of a rectangular prism). That is, the training data record identifies the effectiveness level of the match, the distance traveled by the match, and the prediction data associated with the match. Like this, the training data record identifies the effectiveness volume of the match for a given set of prediction data. Repeat processing steps 410-450 to collect more training data, and generate more training data records for different prediction data sets, and average effectiveness scores for similar prediction factor sets. In an example implementation, the prediction factors are normalized to a value set using any suitable data normalization technique.

[0060] As described in more detail herein, the training data records are used to determine the real-time effectiveness volume based on comparing the real-time predictors to the historical predictors and the historical effectiveness volumes associated with those historical predictors. As described herein, when determining the real-time effectiveness volume, weighting factors are also considered.

[0061] Process 400 also includes determining weighting factors after collecting sufficient training data (step 460). For example, athlete effectiveness volume determination system 220 determines weighting factors for determining the values ​​of unknown variables in the effectiveness volume equation. Taking a cylinder as an example, the effectiveness volume equation is V = πr 2 h. Two regression equations are used for the radius and height in the volume efficiency equation of the cylinder.

[0062] r i =A1x i1 +A2x i2 +…+A p x ip +ε r (1)

[0063] h i =β1x i1 +β2x i2 +…+β p x ip +ε h (2)

[0064] In equations (1) and (2), x i is a set of predictors, A and β are weighting factors (e.g., weighting coefficients), ε r and ε h are configurable constants that adjust the radius and height as needed (e.g., ε can be adjusted higher or lower to show a larger or smaller radius and height for athlete training purposes). The weighting factor is the slope of the regression line and is based on the predictor. In Equation 1, since r for each training data record is known (e.g., from step 430), and the predictor x i is known (e.g., from step 440), so the athlete effectiveness volume determination system 220 calculates the athlete effectiveness volume by using r and x included in the training data record. i Each value of β in equation (1) is derived by solving for β inversely using the known value of h (e.g., based on the height of the athlete), the predictor x i (eg, from step 440), the athlete effectiveness volume determination system 220 derives each value of β in equation (2). As described later herein, two regression equations are used to determine the radius value and the height value, and in turn determine the effectiveness volume.

[0065] Process 400 also includes storing the weighting factors used to determine the real-time effectiveness volume (step 470). For example, the player effectiveness volume determination system 220 stores the weighting factors determined in step 460. As described herein, the player effectiveness volume determination system 220 subsequently uses the weighting factors to determine a radius given a set of predictors.

[0066] Figure 5 An example implementation according to aspects of the present invention is shown. Figure 5 As shown, sensor device 215 is used to determine the starting position of the athlete at the beginning of the game, the ending position of the athlete during the game, and the distance traveled during the game (e.g., the radius in the volume equation). Athlete effectiveness volume determination system 220 determines radius information from sensor device 215 (e.g., similar to process step 430), determines the effectiveness of the game (e.g., similar to process step 420), determines predictors (e.g., similar to process step 440), and stores training data records (e.g., similar to process step 450).

[0067] Figure 6 An example flow chart of a process for determining a real-time effectiveness volume at a specific time point based on training data, real-time predictors, and / or weighting factors is shown. In an example implementation, Figure 6 For example, in Figure 3 is implemented in an environment and uses Figure 3 400. As described above, the flowcharts illustrate possible implementations of the system, method, and computer program product according to various embodiments of the present invention. As described herein, data and / or training records from process 400 are used in process 600, as indicated in the various process steps of process 600.

[0068] like Figure 6 As shown, process 600 includes monitoring sensor data during the performance of a game (step 610). For example, the athlete effectiveness volume determination system 220 monitors sensor data from the sensor device 215 in a manner similar to that discussed above with respect to process step 410.

[0069] Process 600 also includes identifying a real-time predictor data set (step 620). For example, the player effectiveness volume determination system 220 identifies a predictor data set in real-time based on the monitored sensor data from step 610. As described herein, predictors include the position of a target (e.g., a player) on the field, player trajectory, player momentum, ball trajectory, player speed, player acceleration, changes in player movement, orientation / position, and / or other actions related to the conduct of the game.

[0070] Process 600 further includes determining a real-time effectiveness volume based on the real-time predictors, the previously determined weighting factors, and the training data record (step 630). In one example, the athlete effectiveness volume determination system 220 obtains the real-time effectiveness volume of the target (e.g., the athlete) by determining the unknown variables in the volume equation. Using a cylinder as an example, the athlete effectiveness volume determination system 220 uses two regression equations (1) and (2) to determine the radius and height, and then determines the effectiveness volume of the target (e.g., the athlete). As an example, the athlete effectiveness volume determination system 220 uses equations (1) and (2) and uses the training data record (e.g., in Figure 4 generated and stored at step 450 of process 400 and at Figure 5 ) to determine the radius and height in the volume equation of the cylinder, where xi is each set of predictors determined at step 620, and β is a previously determined weighting factor (e.g., Figure 4 460 in process 400). In an embodiment, the athlete effectiveness volume determination system 220 uses any number of shapes (e.g., rectangular prisms, trapezoidal prisms, pentagonal prisms, octagonal prisms, etc.) to determine the real-time effectiveness volume. In an exemplary implementation, the real-time effectiveness volume is the union or intersection of the volumes of multiple shapes. In an embodiment, the training data records are used to determine the real-time effectiveness volume based on comparing the real-time predictors to the historical predictors and the historical effectiveness volumes associated with those historical predictors, in combination with previously determined weighting factors.

[0071] Process 600 includes outputting the effectiveness volume and related information for display (step 640). For example, the player effectiveness volume determination system 220 outputs the effectiveness volume for display. As described herein, in an exemplary embodiment, the effectiveness volume is displayed as part of a live broadcast, where the effectiveness volume is superimposed on the player (e.g., as a Figure 2 Additionally or alternatively, in an exemplary embodiment, the user device 210 runs an application that graphically represents the athlete and effectiveness volume in real time.

[0072] In an embodiment, the player effectiveness volume determination system 220 also outputs relevant information associated with the effectiveness volume. For example, natural language generation techniques are implemented to generate a narrative describing a situation based on the effectiveness volume and corresponding predictors. As an illustrative example, one exemplary aspect of the invention generates a narrative "Player A is outstanding in returning the ball after 5 rounds of rallies and when hitting a forehand."

[0073] like Figure 6As further shown, process 600 returns to process step 420 to generate more training data records based on continuous games. In this way, the training data is continuously updated and refined to improve the calculation and accuracy of the effectiveness volume. In an exemplary embodiment, process 600 is continuously repeated so that during the game when the athletes move around the court and play the game, the real-time effectiveness volume is dynamically determined and displayed. In this way, the audience experience is improved by providing the audience with greater insight into how the game affects the effectiveness of the athletes. In addition, in an exemplary embodiment, the game video with the effectiveness volume is stored and replayed at a later time to allow athletes and coaches to evaluate, adjust and improve technology.

[0074] Figure 7 An example flow chart showing a process for determining actions that minimize an opponent's effectiveness volume. In an example implementation, Figure 7 For example, in Figure 3 is implemented in an environment and uses Figure 3 As described above, the flowcharts illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention.

[0075] like Figure 7 As shown, process 700 includes monitoring sensor data during the performance of a game (step 710). For example, the athlete effectiveness volume determination system 220 monitors sensor data from the sensor device 215 in a manner similar to that discussed above with respect to process step 410.

[0076] The process 700 includes identifying predictors that minimize the effectiveness volume of a secondary target (e.g., an opponent) prior to a play by a primary target or player (step 720). For example, based on previously obtained training data related to the opponent, the player effectiveness volume determination system 220 identifies a set of predictors that previously resulted in a minimum effectiveness volume for the opponent. More specifically, the player effectiveness volume determination system 220 identifies predictors of the opponent that minimize the opponent's effectiveness volume, such as opponent trajectory, momentum, position, orientation, etc.

[0077] Process 700 also includes outputting information identifying actions that introduce predictors that minimize the opponent's effectiveness volume (step 730). For example, the player effectiveness volume determination system 220 outputs information identifying possible actions that a primary target (e.g., a player) can take to minimize the effectiveness volume of its opponent. That is, the player effectiveness volume determination system 220 identifies a set of possible actions that the player can take based on the opponent's predictors and the effectiveness associated with those predictors, and identifies which action(s) the player should take in order to introduce a situation that reduces the opponent's effectiveness volume.

[0078] As an example, the player effectiveness volume determination system 220 provides suggested actions / shot selections that the player can take, introducing such predictors (determined in step 720) at specific moments during the course of the match, thereby minimizing the opponent's effectiveness volume. As an illustrative example, the player effectiveness size determination system 220 determines that at a given point in a tennis match, the player should aim to hit the ball to a specific location in the court, a backhand swing toward the opponent, etc., because these actions will result in predictors that minimize the opponent's effectiveness size. That is, the suggested actions will result in the opponent being in a "weak" position, the opponent needing to take a difficult trajectory to play, the opponent needing to use a weaker type of swing (e.g., a backhand swing), the opponent needing to travel a relatively long distance to play, the opponent needing to have a specific momentum and direction to play, and the like.

[0079] In an exemplary embodiment, the athlete effectiveness volume determination system 220 stores and / or presents the suggested action in a manner that allows the athlete and / or coach to review the suggested action at a later time during the game playback. That is, in an exemplary embodiment, the athlete effectiveness volume determination system 220 merges the suggestion into a part of the live broadcast of the game as a subtitle, which can be recorded so as to review at a later time. Additionally or alternatively, the athlete effectiveness volume determination system 220 stores the suggested action in a data structure or some other manner for later review and retrieval. Additionally or alternatively, the athlete effectiveness volume determination system 220 graphically presents the suggested action in the application so that the suggested action is visible at the corresponding time index during the game.

[0080] Figure 8-10An exemplary graph illustrating a rate of change analysis of various predictors according to aspects of the present invention is shown. As described herein, in an exemplary implementation, the rates of change of the predictors are predicted and these predicted rates of change are used as part of a regression model to determine the effectiveness volume. Additionally or alternatively, in an exemplary embodiment, the predicted rates of change are used as input to a support vector machine to select a shape for determining the effectiveness volume. Data related to the predicted rates of change can be displayed in a user interface, such as displaying Figure 2 The user interface of the content.

[0081] In an exemplary embodiment, athlete effectiveness volume determination system 220 tracks data associated with predictors and presents the rate of change of that data in a graphical form in a user interface (e.g., user interface 800). Figure 8 In the example shown, the athlete effectiveness volume determination system 220 presents the redirection speeds of two athletes or players according to a match (e.g., where the x-axis is the match number and the y-axis is a measure of the redirection speed). Figure 8 In the graph shown, the rate of change of the redirection speed is predicted.

[0082] refer to Fig. 9 , in an exemplary embodiment, a comparison of predictor data for two different players of a player is displayed (e.g., in user interface 900). The comparison shows the rate of change of the two different players based on the match. In an example implementation, the comparison or difference between the players will take into account the effectiveness volume factor of each player (e.g., a higher difference with the opponent results in a lower effectiveness volume of the opponent).

[0083] refer to Fig.10 In an exemplary embodiment, the differences in predictive factors for a particular athlete across several games are presented (e.g., in user interface 1000). Fig.10 As shown in the graph, an athlete's rate of change for a predictor can be predicted and used to determine an effectiveness volume as described herein.

[0084] Fig.11 An example flow chart for determining real-time effectiveness volume is shown. In an example implementation, Fig.11 For example, in Figure 3 is implemented in an environment and uses Figure 3 As described above, the flowcharts illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention.

[0085] like Fig.11As shown, process 1100 includes collecting sensor data in real time (step 1105). For example, athlete effectiveness volume determination system 220 collects sensor data from sensor device 215 (e.g., in the same manner as described above with respect to Figure 4 4, or in a similar manner as discussed above with respect to step 410 in FIG. 4 ).

[0086] Process 1100 also includes predicting a rate of change (step 1110). For example, athlete effectiveness volume determination system 220 predicts a rate of change of a predictor based on sensor data collected over a period of time (e.g., collected at step 1105). Examples of predicting a rate of change of a predictor are described above with reference to Figure 8-10 A discussion was held.

[0087] Process 1100 also includes applying Runge-Kutta to the rate of change (step 1115). For example, athlete effectiveness volume determination system 220 applies Runge-Kutta to the rate of change determined in step 1110. In an embodiment, the classic RK4 Runge-Kutta method can be applied, for example:

[0088]

[0089] For n = 0, 1, 2, 3, ..., use

[0090]

[0091] In the above Runge-Kutta method, y n+1 is y(t n+1 ), and the next value (y n+1 ) is calculated from the current value (y n ) plus a weighted average of four increments, where each increment is the product of the size of the interval h and the estimated slope specified by the function f on the right-hand side of the differential equation. k1 is an increment based on the slope at the beginning of the interval using y (Euler's method); k2 is an increment based on the slope at the midpoint of the interval using y and k1; k3 is again an increment based on the slope at the midpoint, but now using y and k2; and k4 is an increment based on the slope at the end of the interval using y and k3.

[0092] Process 1100 also includes selecting a shape using the results of the support vector machine and Runge-Kutta (step 1120). For example, the athlete effectiveness determination volume system 220 selects a shape (e.g., a cylinder, a rectangular prism, etc.) by inputting the results of the Runge-Kutta analysis (from step 1115) into a support vector machine (SVM). In an exemplary embodiment, the athlete effectiveness determination volume system 220 uses any suitable SVM technique to analyze the data for classification and regression analysis as part of the shape selection.

[0093] Process 1100 also includes applying a regression model to the selected shape using the historical and predicted data (step 1125). For example, the athlete effectiveness volume determination system 220 applies a regression model for the selected shape and uses the historical and predicted data (e.g., from steps 1105 and 1110). Using a cylinder as an example, the athlete effectiveness volume determination system 220 may apply a regression model, such as a regression model associated with equations (1) and (2).

[0094] Process 1100 also includes selecting position data and stratified rate of change (step 1130). For example, the player effectiveness volume determination system 220 selects position data (e.g., based on the player's current position on the court or field) and stratified rate of change (e.g., based on the rate of change data from step 1110). From step 1130, the player effectiveness volume determination system 220 determines the unknown variables in the volume regression equation (e.g., equations (1) and (2) using a cylinder as an example).

[0095] Process 1100 also includes determining an effectiveness volume (step 1135). For example, athlete effectiveness volume determination system 220 determines the effectiveness volume by inputting the unknown variables (derived from steps 1125 and 1130) into a regression equation of a selected shape.

[0096] Process 1100 also includes repeating the effectiveness volume determination for each spatial region (step 1140). For example, the player effectiveness volume determination system 220 repeats steps 1130 and 1135 as the player moves around the court or field to determine the player's effectiveness volume at various points in time.

[0097] Process 1100 also includes generating captions (step 1145). For example, the athlete effectiveness volume determination system 220 generates a narrative or description based on the athlete's effectiveness volume (e.g., using natural language generation (NLG) techniques to generate a narrative describing the situation based on the effectiveness volume and corresponding predictors).

[0098] Process 1100 also includes outputting actions to minimize the opponent's effective volume (step 1150). For example, the player effective volume determination system 220 can be used in the same manner as described above with respect to Figure 7 The actions used to minimize the opponent's effective volume are output in a similar manner as discussed in processing step 730 of .

[0099] Process 1100 also includes outputting an opponent effectiveness volume (step 1155). For example, player effectiveness volume determination system 220 determines and outputs an opponent's effectiveness volume based on process steps similar to those described in steps 1105-1135, but for the player's opponent.

[0100] As described herein, aspects of the present invention dynamically determine an effectiveness zone for a player during a match of a sport (e.g., tennis), and display the effectiveness zone (e.g., effectiveness volume) in real time during the match. As described herein, an effectiveness zone represents an area or volume around a player where the player is considered "effective" (e.g., making an effective "play" with a high probability of scoring against an opponent or defending against a player by an opponent). The effectiveness volume is used to predict where a player / opponent may be on the court at a given time, and is used for real-time and / or post-match analysis to improve spectator experience and coaching strategies.

[0101] In an embodiment, a service provider may provide for performing the processes described herein. In this case, the service provider may create, maintain, deploy, support, etc., a computer infrastructure that performs the process steps of the present invention for one or more customers. These customers may be, for example, any business that uses the technology. In return, the service provider may receive payment from the customer(s) under a subscription and / or fee agreement, and / or the service provider may receive payment from the sale of advertising content to one or more third parties.

[0102] In another embodiment, the present invention provides a computer-implemented method via a network. In this case, a computer system / server 12 ( Figure 1 ) and may acquire (e.g., create, purchase, use, modify, etc.) one or more systems for performing the processes of the present invention and deploy them to the computer infrastructure. In this sense, deployment of the systems may include one or more of the following: (1) downloading from a computer-readable medium to a computer system / server 12 (e.g., Figure 1 (a) installing program code on a computing device (as shown); (2) adding one or more computing devices to a computer infrastructure; and (3) incorporating and / or modifying one or more existing systems of the computer infrastructure to enable the computer infrastructure to perform the processes of the present invention.

[0103] The description of various embodiments of the present invention has been given for the purpose of illustration, but it is not intended to be exhaustive or limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terms used herein are selected to best explain the principles of the embodiments, practical applications, or technical improvements existing in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A computer-implemented method comprising: monitoring, by a computing device, real-time sensor data during play of a sporting event, the real-time sensor data providing information about participants in the sporting event; determining, by the computing device, a real-time predictor associated with the participant based on monitoring the real-time sensor data during play of the sporting event, the real-time predictor comprising a trajectory of a ball; using machine learning to train a machine learning system on data identifying the historical effectiveness of the contests of the participants; determining weighting factors based on training data identifying the historical effectiveness of the game for the participant, wherein the weighting factors include a first factor for adjusting a radius of an effectiveness volume for a player within the training data and a second factor for adjusting a height of the effectiveness volume for the player within the training data; determining, by the computing device, a size of a real-time effectiveness zone around the participant during play of the sporting event based on the predictor, the training data identifying the participant's historical effectiveness of the play, and the weighting factor, wherein the real-time effectiveness zone represents an area in which the participant is considered effective; the real-time effectiveness zone around the participant changes based on changes to the real-time predictor during play of the sporting event; identifying, by the computing device, a set of suggested moves for the participant prior to competition by the participant in the sporting event, wherein the set of suggested moves is predicted to minimize a real-time zone of effectiveness of a second participant prior to competition by the second participant in the sporting event, wherein the second participant is an opponent of the participant; predicting, by the computing device, a rate of change of the real-time prediction factor; determining, by the computing device, a volume of the real-time effectiveness zone for the participant based on the predicted rate of change of the real-time predictor; as well as The shape of the determined volume for the real-time validity region is selected by the computing device by utilizing a support vector machine that receives the predicted rate of change of the real-time predictor.

2. The computer-implemented method of claim 1 , further comprising: updating the real-time validity zone for the participant based on continuous monitoring of the sensor data; as well as outputting a visual display that continuously outputs updates to the real-time validity region to continuously display the updates to the real-time validity region; as well as An audio narration is generated that describes at least one condition based on the real-time validity zone and the real-time predictor corresponding to the real-time validity zone.

3. The computer-implemented method of claim 1 , further comprising determining a real-time predictor for the second participant that minimizes the real-time effectiveness region for the second participant, Wherein the training data includes training records identifying the effectiveness of a match and a specific set of predictors associated with the effectiveness of the match.

4. The computer-implemented method of claim 3, wherein: The real-time predictors for the second participant include a trajectory of the second participant, a momentum of the second participant, and an orientation of the second participant, and wherein the predictors include at least one selected from the group consisting of: a position or orientation of the participant's body; the position of said participants on the court; the momentum of said participants; the speed of said participant; the trajectory of said participants; the acceleration of the participant; The trajectory of the ball; and Biometric data of the participant.

5. The computer-implemented method of claim 1 , wherein: The real-time validity region is a validity volume in the form of a shape selected from the group consisting of: a cube, a cylinder, and a rectangular prism.

6. The computer-implemented method of claim 1, wherein the participant is a player of the sporting event, and the sporting event is tennis.

7. The computer-implemented method of claim 1 , wherein: The real-time validity region is in the form of a cylinder having a volume, wherein a radius of the cylinder is determined based on a first regression equation, and a height of the cylinder is determined based on a second regression equation.

8. The computer-implemented method of claim 7, wherein: The first regression equation is r i =A1x i1 +A2x i2 +…+A p x ip +ε r , the second regression equation is h i =β1x i1 +β2x i2 +…+β p x ip +ε h , where x i is a set of predictors, A and β are weighting factors, and ε r and ε h Is a configurable constant.

9. The computer-implemented method of claim 1, wherein the participant is a primary participant, the method further comprising determining an action for the primary participant based on predictors associated with secondary participants to minimize an effectiveness area for the secondary participants.

10. The computer-implemented method of claim 1, wherein a service provider at least one of creates, maintains, deploys, and supports the computing device.

11. The computer-implemented method of claim 1 , wherein said monitoring said determining said predictive factors and said determining said real-time effectiveness zones are provided by a service provider on a subscription, advertising, and / or fee basis.

12. The computer-implemented method of claim 1, wherein the computing device includes software provided as a service in a cloud environment.

13. The computer-implemented method of claim 1, further comprising deploying a system, including providing a computer infrastructure operable to perform said monitoring, said determining said predictive factors, and said determining said real-time effectiveness areas.

14. A computer program product for training a machine learning system to determine and display a real-time effectiveness volume around an athlete, the computer program product comprising a computer-readable storage medium having program instructions embodied therein, the program instructions executable by a computing device to cause the computing device to: Monitoring sensor data during play at a sporting event; determining the validity of a play performed by said athlete during the performance of said play at said athletic event; determining a data set of predictors associated with the athlete based on said monitoring of said sensor data during said play of said athletic event; training the machine learning system using the sensor data, the determined effectiveness of the match, and the dataset of predictors to generate and store a training data record that associates the effectiveness of the match with the dataset of predictors; determining a data set of real-time predictors based on said monitoring of said sensor data during play of said sporting event, said real-time predictors comprising a trajectory of a ball; using machine learning to train the machine learning system on data identifying the historical effectiveness of the contest for participants; determining weighting factors based on the training data identifying the historical effectiveness of the competition for the participant, wherein the weighting factors include a first factor for adjusting a radius of an effectiveness volume for a player within the training data and a second factor for adjusting a height of the effectiveness volume for the player within the training data; determining the real-time effectiveness volume around the athlete during the play of the sporting event based on the dataset of real-time predictors, the training data identifying the historical effectiveness of the play of the participant, and the weighting factors; as well as generating and outputting a visual display of the real-time effectiveness volume during the play of the athletic event, the visual display being superimposed over and around the video image of the athlete, wherein the real-time effectiveness volume changes dynamically during the play of the athletic event; predicting a rate of change of the real-time prediction factor; determining a volume of the real-time effectiveness volume for the participant based on the predicted rate of change of the real-time predictor; as well as The shape of the volume for determination of the real-time effectiveness volume is selected by utilizing a support vector machine that receives the predicted rate of change of the real-time predictor.

15. The computer program product of claim 14, further comprising: generating an audio narration describing at least one condition based on a real-time validity region and the real-time predictor corresponding to the real-time validity region, Wherein the real-time effectiveness volume is in the form of a cylinder having a volume, wherein the determined radius of the cylinder is determined based on a first regression equation, and the height of the cylinder is determined based on a second regression equation.

16. The computer program product of claim 15, further comprising: determining a real-time predictor for a second participant that minimizes the real-time effectiveness region of the second participant, Among them, the first regression equation is r i =A1x i1 +A2x i2 +…+A p x ip +ε r , the second regression equation is h i =β1x i1 +β2x i2 +…+β p x ip +ε h , where x i is a set of predictors, A and β are weighting factors, and ε r and ε h Is a configurable constant.

17. The computer program product of claim 16, wherein: The real-time prediction factors for the second participant include a trajectory of the second participant, a momentum of the second participant, and an orientation of the second participant, and wherein the weighting factor β is determined based on inversely solving the weighting factor β using a value of a radius included in the training data record.

18. The computer program product of claim 14, wherein the data set of predictors includes at least one item selected from the group consisting of: the position or orientation of the athlete’s body; the players’ positions on the field; the athlete’s momentum; The speed of the athlete; the athlete’s trajectory; The athlete’s acceleration; The trajectory of the ball; and Biometric data of athletes.

19. A system comprising: a processor, computer-readable memory, and computer-readable storage media associated with a computing device; program instructions for monitoring sensor data during play at a sporting event; program instructions for determining a volume of effectiveness for a primary participant in the sporting event based on said monitoring of said sensor data and a first set of predictors associated with said primary participant, wherein said volume of effectiveness for said primary participant represents a volume surrounding said primary participant in which said primary participant is considered effective, and wherein said first set of predictors includes a trajectory of a ball; program instructions for using machine learning to train a machine learning system on data identifying the historical effectiveness of the matches of said major players; program instructions for determining weighting factors based on training data identifying the historical effectiveness of the games of the primary participants, wherein the weighting factors include a first factor for adjusting a radius of a player effectiveness volume within the training data and a second factor for adjusting a height of the player effectiveness volume within the training data; program instructions for determining a volume for effectiveness of the secondary participant at the athletic event based on said monitoring of said sensor data and a second set of predictors associated with secondary participants, said training data identifying historical effectiveness of said primary participant at said athletic event, and said weighting factors, wherein said volume for effectiveness of said secondary participant represents a volume surrounding said secondary participant in which said secondary participant is considered effective; program instructions for predicting a rate of change of said first set of predictors; program instructions for determining said volume of said volume of said effectiveness for said primary participant based on said predicted rate of change of said first set of predictors; and program instructions for selecting a shape of the volume for determination of the volume of validity by utilizing a support vector machine receiving the predicted rate of change of the first set of predictors, The program instructions are stored on the computer-readable storage medium for execution by the processor via the computer-readable memory.

20. The system of claim 19, further comprising: program instructions for determining and displaying a narrative describing the effectiveness volume of the primary participant, the effectiveness volume of the secondary participant, or a suggested action generated using natural language; as well as Program instructions for generating an audio narration describing at least one condition based on a real-time validity zone and a real-time predictor corresponding to the real-time validity zone.

21. The system of claim 19, further comprising: determining a real-time predictor for the secondary participant that minimizes the real-time validity region of the secondary participant, The real-time predictive factors for the secondary participant include a trajectory of the secondary participant, a momentum of the secondary participant, and a heading of the secondary participant, and The primary participants are players of the sporting event, the secondary participants are opposing players, and the sporting event is tennis.

22. A computer-implemented method comprising: generating, by a computing device, a plurality of training data records of participants of an athletic event, wherein the training data records each identify a measure of effectiveness of play by the participants and a data set of historical predictors associated with each measure of effectiveness; The computing device monitors sensor data of the sports event in real time; determining, by the computing device, in real time from the sensor data, a data set of real-time predictors for the participant, the real-time predictors comprising a trajectory of a ball; using machine learning, by the computing device, to train a machine learning system on data identifying the historical effectiveness of the participant's matches; determining, by the computing device, a weighting factor based on training data identifying the historical effectiveness of the game for the participant, wherein the weighting factor includes a first factor for adjusting a radius of a player effectiveness volume within the training data and a second factor for adjusting a height of the player effectiveness volume within the training data; dynamically determining, by the computing device, a real-time effectiveness volume for the participant over a time period during the sporting event based on the dataset of real-time predictors, the training data identifying the historical effectiveness of the game for the participant, and the weighting factors; outputting, by the computing device, the real-time effectiveness volume for displaying the real-time effectiveness volume superimposed over and around the video image of the participant, wherein the real-time effectiveness volume changes based on changes to the real-time predictor during the athletic event; predicting, by the computing device, a rate of change of the real-time prediction factor; determining, by the computing device, a volume of the real-time effectiveness volume for the participant based on the predicted rate of change of the real-time predictor; as well as The shape of the volume for determination of the real-time effectiveness volume is selected by the computing device by utilizing a support vector machine that receives the predicted rate of change of the real-time predictor.

23. The computer-implemented method of claim 22, further comprising: generating an audio narration describing at least one condition based on a real-time validity region and the real-time predictor corresponding to the real-time validity region; Wherein, each of the real-time validity volumes is in the form of a cylinder having a specific volume, wherein a radius of the specific volume of the cylinder is determined based on a first regression equation, and a height of the cylinder is determined based on a second regression equation.

24. The computer-implemented method of claim 22, further comprising: determining a real-time predictor for a second participant that minimizes the real-time effectiveness region of the second participant, The real-time predictors for the second participant include a trajectory of the second participant, a momentum of the second participant, and a heading of the second participant, and The dataset of real-time predictors includes at least one item selected from the group consisting of: the position or orientation of the participant’s body; the participants’ positions on the field; the momentum of the participants; the speed of the participants; the participants’ trajectories; the acceleration of the participant; The trajectory of the ball; and Biometric data of participants.

Images