System and methods for conducting competitor-handicapped, skill-based competitions supported by artificial intelligence processes to verify integrity by detecting fraudulant activity of competitors and provide recommendations to participants of an activity

Abstract

A system and methods for conducting competitor-handicapped, skill-based competitions supported by artificial intelligence processes to verify integrity of competitors. The system and methods may utilize handicap data of the competitors and ensure integrity of that data utilizing a variety of different techniques, including, but not limited to artificial intelligence analytics. For example, activity data captured during a competition between competitors and analyzed to determine deviations from historical activities of the respective competitors, and enable the competitors to access the deviations and submit protests or challenges to an official. The use of the artificial intelligence may eliminate fraud, such as "sandbagging," such competitors may be more willing to participate and wager in competitions as the system supports auditing captured data such that integrity amongst competitors in different geographical locations and playing in asynchronous competitions. The competitions may be performed on simulators (e.g., golf simulators) or in real-world environments (e.g., golf courses).

Description

SYSTEM AND METHODS FOR CONDUCTING COMPETITOR-HANDICAPPED, SKILL-BASED COMPETITIONS SUPPORTED BY ARTIFICIAL INTELLIGENCE PROCESSES TO VERIFY INTEGRITY BY DETECTING FRAUDULANT ACTIVITY OF COMPETITORS AND PROVIDE RECOMMENDATIONS TO PARTICIPANTS OF AN ACTIVITYRELATED APPLICATIONS

[0001] This application claims priority to co-pending U.S. Provisional Patent Applications having Serial Nos. 63 / 623,749 filed on January 22, 2024, and 63 / 648,117 filed on May 15, 2024; the contents of which are hereby incorporated by reference in their entirety.BACKGROUND OF THE INVENTION

[0002] Current golf handicapping systems lacks integrity and are exclusive systems for a small group of elite players. The current handicapping system in golf, for example, is fundamentally flawed due to its reliance on self-reported scores without a robust mechanism for auditing and verification. This lack of integrity self-reporting scoring often leads to mistrust amongst players, especially when a player plays significantly better than what the handicap would suggest is possible. Another problem that exists is that for self-reporting handicap scoring is that there is a scarcity of handicapped golf tournaments of significance. Most significant golf tournaments are non-handicapped, which cater only to highly skilled players, who represent a very small percentage (e.g., 3%) of all golfers. Consequently, this exclusivity renders competitive golf non-inclusive, effectively marginalizing a large majority of golf enthusiasts who do not fall within this small percentage of elite players. Thus, there is a need for a more inclusive system that can accurately and fairly evaluate and accommodate the skills of a broader range of players.

[0003] Technology has advanced over the past few decades to the point that many real- world activities are able to be simulated using actual devices normally used to perform those real-world activities. For example, golf simulators allow for participants to swing actual golf clubs to hit actual golf balls. Such simulators include, but are not limited to SkyTrak®, Uneekor, and Bushnell, just to name a few. These simulators range in quality and price, but each senses different parameters to determine flight path of a golf ball, including speed, distance, direction (e.g., slice, straight, draw), ball rotation, club head speed and angle, and so on. Based on those parameters, the simulators estimate and / or determine golf ball flightpath and where a golf ball will land on a simulated golf course. Other parameters that may be collected include motion (e.g., speed, spin, and direction) of the golf club and so on. As users utilize the golf simulator, users may improve such that their real-world golfing skills improve.

[0004] Although handicapping is primarily thought of in terms of golf, there are many other competitive activities that have handicaps. Such competitive activities include, but are not limited to, bowling, darts, axe throwing, running, swimming, baseball, basketball, tennis, iron man competitions, weightlifting, rowing, race car driving, cycling, and many others. As with golf, there are elite competitors in each of the competitive activities, but handicapping is generally not utilized in the non-golf competitive activities either.SUMMARY OF THE INVENTION

[0005] To overcome the problems of self-reported handicapped skill-based competitive activities or competitions in which competitors self-report or even use other people to perform certain activities (e.g., tee shots, free throws, etc.), the principles provided herein support a data-driven handicapping system that utilizes data analysis processes, such as artificial intelligence (Al), to accurately measure and determine player handicaps along with performing verification of competitor or player identity before and / or throughout a competition, thereby providing for integrity of skill-based competitions. By providing for integrity of player handicaps, the ability to support handicapped competitions such that players at any level may play against players at the same or other handicapped levels in tournaments may be possible. As a result, the large majority of handicapped players, not just the elite players, may (i) be able to enter handicapped competitions and (ii) be confident that other players who also have trustworthy handicap scores and verifiable identities.

[0006] To support data-driven handicapping, the principles provided herein may include the use of sensors that capture performance of players practicing and / or playing in tournaments. The sensors may be part of a simulator or sensors positioned in the real-world (e.g., at locations at which people practice and / or play competitions) that capture historical skill-based activity data for use in determining a handicap of a user (i.e., player, competitor). The historical skill-based activity data may be used to determine and validate handicap of a user that is measured so that the ability for a user to self-report a handicap and the problems that result in such reporting may be eliminated. Data derived from player practice and / or tournament play may be considered to be audited data as the identity and biomechanics of theplayer may be considered to be audited historical skill-based activity data and handicap. Moreover, the historical skill -based activity data may be used to identify fraud during and / or after a skill-based activity competition, as further described herein.

[0007] Player Identity Verification: the system and processes provided herein may provide for player identity verification. A first step of an illustrative process may include verifying the identity of each player using one or more data-based processes, including, but not limited to, biometrics, activity “fingerprint,” digital . The process(es) may ensure that the individual submitting scores during a competition is indeed the one who played, thereby eliminating impersonation, identity fraud, and / or total fabrication of the results.

[0008] Authenticity of Performance Data: Following the confirmation of the player's identity, the system and process(es) may utilize an advanced verification process for ensuring accuracy of scores or results. Specifically in golf simulations, for example, an advanced verification process may entail a detailed analysis of various data types, including, but not limited to, video footage, golf ball data, club head data, and the player's biomechanical information. Additionally, system and processes may be designed to integrate data from an array of other potential sources, such as sensors, launch monitors, or any emerging technology that can capture relevant performance metrics. Utilizing a thorough and multi-faceted approach to data analysis helps ensure authenticity of the results, thereby significantly enhancing the reliability and integrity of a system that incorporates handicapping. It should be understood that non-golf systems and processes (e.g., bowling, darts, etc.) may utilize alternative sensors and data as a function of those activities. The processes may be in communication with simulations and / or sensors directly so that historical and competition data of a skill-based activity may be accessed for the data analysis. The analysis may utilize artificial intelligence (Al), machine learning (ML), or any other process(es) in accordance with the principles herein.

[0009] In addition to using the historical skill-based activity data for use in competition for handicap and fraud prevention, the skill-based activity data may be used for recommendations for both goods and services to users. The recommendations may identify skill-based activity data to determine skill-based activity equipment (e.g., golf clubs, golf balls, golf shoes, etc.) and / or services (e.g., instructor who specializes in correcting golf swings that slice, instructor who is good at correcting putting problems, instructor who is good with certain demographics, etc.).

[0010] One embodiment of a computer-implemented method for conducting a skill-based activity competition may include accessing handicap data of a first competitor, where the handicap data may be derived from historical physical activity performance of the first competitor during practice and / or competition play of the skill-based activity as captured by at least one sensor. During the skill-based activity competition, data captured of the physical activity performed by the first competitor using the at least one sensor and a score achieved by the first competitor in performing the physical activity during the skill-based activity competition may be received. A handicap-adjusted score of the first competitor by applying the handicap data to the score of the first competitor may be computed, and a winner of the skill-based activity may be determined by comparing the handicap-adjusted score of the first competitor with one or more handicap-adjusted scores of at least one respective other competitor.

[0011] One embodiment of a computer-implemented method of ensuring integrity of competitors participating in a skill-based activity competition may include accessing historical skill-based activity data sensed by at least one sensor of a competitor of the skillbased activity competition performing the skill-based activity prior to the skill-based activity competition. Skill-based activity data measured by the sensor(s) of the competitor performing the skill-based activity during the skill-based activity competition may be accessed. The historical skill-based activity data and measured skill-based activity data during the skillbased activity competition may be compared to validate (i) an identity of the competitor, and (ii) a difference of the historical skill-based activity data and measured skill-based activity data during the skill-based activity competition is within a statistical deviation range that is indicative of integrity of the competitor. In response to not validating identity of the competitor or that the difference of the historical skill-based activity data and measured skillbased activity data is outside of the statistical deviation range, a notification indicative of the competitor violating a role of the competition may be generated. The notification may be communicated to notify a second competitor and / or official of the skill-based activity competition to enable action against the violation of the rule to be performed.

[0012] One embodiment of a computer-implemented method for perform activity matching services may include capturing activity data of a participant of a skill-based activity while performing at least one skill of the skill-based activity. An artificial intelligence engine may process the activity data of the participant from the captured activity data to generate recommendations, the recommendations including at least one of equipment, trainer,instructor, and exercises. An application that enables the participant to receive the generated recommendations may be provided. The application may present the recommendations to the participant. Capturing activity data may include capturing golf activity data from a golf simulator.BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Illustrative embodiments of the present invention are described in detail below with reference to the attached drawing figures, which are incorporated by reference herein and wherein:

[0014] FIG. 1 is an illustration of an illustrative system environment in which a system is configured to support one or more skill-based activity, such as competitions, one-on-one wagering, sub -competitions (e.g., closest to the hold), and team and / or match play events;

[0015] FIG. 2 is a screen shot of an illustrative user interface that enables competitors to select a skill-based activity competition in which to participate;

[0016] FIG. 3 is a screen shot of an illustrative user interface that enables competitors to select a system or platform, such as a simulator on which the skill-based activity competition is played;

[0017] FIG. 4 is a network environment in which a system, such as a competition platform server in communication with one or more simulators that are used as part of a skillbased activity competition;

[0018] FIG. 5 is an image of a simulator in which a competitor may use to compete in a skill-based activity competition and to use for practice prior to the competition;

[0019] FIG. 6 is an illustration of an illustrative series of swings of a user or competitor during practice from which one or more sensors capture and an artificial intelligence (Al) platform may use to analyze the user’s golf biomechanics, for example;

[0020] FIG. 7 is an illustration of an illustrative wearable device, in this case a golf glove, that may include one or more sensor (e.g., motion, pressure, temperature, pulse, etc.);

[0021] FIGS. 8A-8I are screen shots of illustrative user interfaces for a user to participate in a skill-based activity competition in which Al fraud detection may be utilized for player integrity purposes;

[0022] FIG. 9 is an illustration of an illustrative environment in which a skill-based activity, in this case golf, being performed in the real-world, in this case a golf course, as opposed to a simulator;

[0023] FIG. 10 is a flow diagram of an illustrative process in which a skill-based activity competition may be performed and managed in a manner that supports integrity by reducing or eliminating fraud using player identification and using an Al model to detect fraudulent activity by competitors; and

[0024] FIG. 11 is an illustration of a network environment in which skill-based activities are performed and data of users performing the skill-based activities are captured by sensors so that Al activity matching may be made.DETAILED DESCRIPTION OF THE DRAWINGS

[0025] Skill-based activity competitions have been expanding in recent years. Such expansion has been a result of global interests in a variety of different skill-based activities, including golf, tennis, pickleball, bowling, darts, axe throwing, running, swimming, baseball, basketball, tennis, iron man competitions, weightlifting, rowing, race car driving, cycling, and many others. Many of these activities are enjoyed as leisure activities, while others who are more serious, participate in tournaments and other events. To support skill-based activity competitions in a manner in which competitors are ensured that the competition has integrity, anti-fraud systems and methodologies may be employed.

[0026] Because esports, such as golf simulator competitions are remote, generally not live, and asynchronous in nature, as opposed to being performed by players being in the same location, integrity for asynchronous, networked (platform) competition may be supported by utilizing an artificial intelligence (Al) platform that may access data captured by the gaming platform on which competitors are performing the skill-based activities. In operation, fraud in the form of identity fraud, skill-based activity fraud (e.g., “sandbagging”), equipment fraud, platform differences and / or tampering, etc., may be identified and notifications may be communicated to competitors and / or officials regulating the competition. Notifications may be in the form of providing information on an app, communicating messages, halting play on an app, preventing a fraudulent competitor from accessing the app or joining future competitions, or otherwise. Consequences in the form of financial or otherwise may be imposed on the fraudulent competitor and the non-fraudulent competitor may be compensated (e.g., return of wager). The wagering platform (e.g., gaming server, Al platform, etc.) maybe independent of gaming platforms, such as golf simulators may be in communication with a golf simulator server and the wagering platform may receive or access data from the gaming platform. In an embodiment, sensors may be fixed for indoor skill-based activity competitions and / or practice. If the skill-based activity is outdoors, then a robot (e.g., cart, bag, robot, drone) may capture data with sensors (e.g., camera, radar, etc.) and communicate the captured data to an Al or wagering platform.

[0027] Simulators have been used to help people improve their skills in different activities. The advancement of simulators of competitive activities have been able to improve skills. Simulators may also be used for competitions where many different competitors who use the simulators may compete. Because of advancement of communications, in addition to the advancement of the simulators themselves, simulators that are remote from one another are now able to enable competitors from around the globe to compete, often in real-time, with one another. Such competitions may involve one-on-one competitions (e.g., golf, tennis, etc.) or group competitions (e.g., golf, race car driving, cycling, etc.). Each of these types of competitions between competitors may be considered peer-to-peer, skill-based activity competitions.

[0028] Historically, golf handicaps are “suspect” because handicaps are handled by selfreporting of competitors. Other competitive activities have similar problems. The handicaps for these competitive activities are often suspect due to the self-reporting, and arguments due to integrity concerns of the competitors often result. If competitive leagues or tournaments are established for peer-to-peer competitions, especially those that use handicapping, support may be lost in the event if competitors are less than forthright in self-reporting their handicaps. Such competitions may have hundreds of thousands or millions of dollars as prize money, and integrity of the competitions are critical to avoid “scandals,” where competitors misrepresent their handicaps so as to “sandbag” other competitors so as to play better than their handicaps. In competitions that involve prize money or even in one-on-one competitions (e.g., golf round with wagering for each hole and / or round), dishonest players can corrupt the integrity of the competition.

[0029] With regard to FIG. 1, an illustration of an illustrative system environment 100 in which a system is configured to support one or more skill-based activity, such as competitions, one-on-one wagering, sub-competitions (e.g., closest to the hold), and team and / or match play events is shown. The system environment 100 may include an artificial intelligence (Al) platform 102 that may be in communication with one or moreplatforms 104a-104n (collectively 104) that access or receive data of users performing a skill-based activity using platform(s) 104 when practicing and / or competing in skillbased activities. The Al platform 102 may be formed of one or more computing systems (e.g., servers), and may be configured to specialize in analyzing one or more skill-based activities. The Al platform 102 may be configured to process and / or identify skill-based activity data, identification data, event data, lesson data, equipment data, wagering data, or any other data associated with a skill-based activity practice and / or competition. As further described herein, the Al platform 102 may support one or more mobile app(s) that enables the users (e.g., competitors) to submit various information that assists the Al platform 102 to determine whether improvements or changes to the player’s skill-based activity that would otherwise appear to be dramatic or deviate in such a manner as to cause an Al engine to identify the change to be outside of a statistical deviation range that would be determined to be potential fraud.

[0030] As shown, the platform 104a may be configured to enable a player to practice and / or compete in a shooting skill. The platform 104b may be configured to enable a player to practice and / or compete in a basketball skill. The platform 104c may be configured to enable a player to practice and / or compete in a golf skill on a golf simulator. The platform 104d may be configured to enable a player to practice and / or compete in a golf skill on an actual golf course. The platform 104e may be configured to enable a player to practice and / or compete in a baseball skill. The platform 104f may be configured to enable a player to practice and / or compete in a cricket skill. The platform 104g may be configured to enable a player to practice and / or compete in a darts skill. The platform 104h may be configured to enable a player to practice and / or compete in a driving skill on a driving simulator. The platform 104i may be configured to enable a player to practice and / or compete in an axe throwing skill. The platform 104n may be configured to enable a player to practice and / or compete in a Skee-Ball skill. The platforms 104 may also include arcade games, such as Pac-Man®.

[0031] Each of the platforms 104 may be configured with one or more sensors to capture data of users performing the respective skills. For platform 104a that supports a shooting skill, the platform 104a may be configured with sensors (not shown) that are specifically configured to capture data associated with shooting. For example, the sensors may include one or more camera (e.g., high-speed camera), motion sensor(s), timer (e.g., integrated into camera or post processing from image or other sensoranalysis), heart rate sensor, etc., for identifying location of bullet strike, sensing recoil amount, measuring time from start to trigger pull, measuring steadiness, measuring motion of muzzle, detecting motion of eye(s), measuring breathing of user, measuring heart rate of user, identifying stance or body in prone position, and so on. The sensors may include camera(s), such as stereographic cameras, three-dimensional (3D) cameras, radar, LIDAR, timer(s), or any other sensor. The sensors may be attached or mounted to equipment (e.g., mounted to or connected to a gun, target, glasses, strap, or otherwise), attached to or mounted to a user (e.g., arm, hand, head, torso, leg, foot, etc.), or remote from the equipment and user (e.g., mounted to or positioned on a wall, ceiling, floor, or otherwise). In an embodiment, the sensor(s) may execute software to measure or sense the various parameters of the user and / or equipment before, during, or after performing a skill-based activity during practice and / or competition.

[0032] Each of the platforms 104 may be in communication with a network 106 so as to, in one embodiment, communicate sensed or measured data 108a-108n (collectively 108) to one or more servers (not shown) configured to manage one or more common skill-based activity simulators (e.g., golf simulators) or other platforms (e.g., outdoor sensors at a golf course), and / or in another embodiment, communicate sensed or measured data from the sensors or local computing device directly to the Al platform 102 for processing thereat. In an embodiment, the Al platform 102 may be locally positioned or be centrally located to receive the data communications from one or more of the platforms 104. The platforms 104 may be trained for individual users so as to learn the users’ biometrics, biomechanics, and skill-based activity performance, thereby being capable of identifying identity and skill-based activity fraud, as further described herein.

[0033] With regard to FIG. 2, a screen shot of an illustrative user interface 200 of a mobile app or application executed on a stationary computing system (e.g., wall-mounted that enables competitors to select a skill-based activity competition in which to participate is shown. The user interface 200 may include selection elements 202a-202n (collectively 202) associated with skill-based activities in which the competitors may select. As shown, the selection elements 202 may include a cycling 202a, shooting 202b, basketball 202c, pickleball 202d, archery 202e, soccer 202f, darts 202g, and cricket 202n. It should be understood that golf and other skill-based activities, such as pool, may be included in the selection elements 202 for competitors to select on the same or different user interface. Once selected, a user interface specific to the selected selection element. To support integrity ofthe competitors, the Al platform 102 of FIG. 1 may be configured to be in communication with mobile device executing the user interface 200 and a platform, such as any of the platforms 104, to verify audited identity and skill-based activity of the competitor or user who selected the activity from the selection elements 202.

[0034] With regard to FIG. 3, a screen shot of an illustrative user interface 300 that enables competitors to select a system or platform, such as a golf simulator, on which the skill-based activity competition, is played. The user interface 300 include a list of selectable elements 302a-302n (collectively 302) associated with different golf simulators. As shown, selection element 302a may be associated with the Trugolf® golf simulator, selection element 302b may be associated with the Trackman® golf simulator, and selection element 302n may be associated with the aboutGOLF® golf simulator. Other golf simulators may be available for selection beyond those shown. As understood, although different golf simulators provide for many of the same features (e.g., swing speed, ball speed, club head angle, ball angle, ball spin, etc.), the different golf simulators may have different skill-based activity parameters.

[0035] Moreover, the different golf simulators may use different sensors that are more or less precise, have more or less gain, have more or less sensitivity, etc., so that the responses to identical swings of a golf driver with the same club may result in different simulation results. Such deviations may result from difference in calibration, differences in algorithms of ball trajectories, differences in physics modeling (e.g., grass resistances, wind forces, ball reactions, club head friction and coefficient of restitution, etc.), and so on such that a competitor playing on one simulator may have an advantage or disadvantage to a competitor playing on a different golf simulator. In an embodiment, the Al platform 102 may be configured to normalize data accessed from the different golf simulators so as to balance or eliminate differences between the golf simulators. It should be understood that the same make and model of golf simulators (e.g., Trugolf golf simulator) may have different responses, as well, such that normalization of all golf simulators that are to be used in a skill-based activity competition may be calibrated and normalized with respect to other golf simulators, whether or not the same make and model of golf simulators. In an embodiment, one or more calibration signals may be injected into different golf simulators to perform a calibration and normalization process. The calibration signal(s) may simulate one or more different skillbased activity, such as driver shot that slices, goes straight, has a draw, as high, medium, low, and no spin, goes fast, goes slow, has high loft, has no loft, and so on. From the calibration injections, outputs of the different golf simulators may be accessed by the Al platform toperform calibration and / or normalization. By calibrating and normalizing the data from each of the individual golf simulators, whether or not the same or different make and model, integrity and fraud may be reduced or eliminated such that competitors are confident that a skill-based activity competition is fair. It should be understood that the same or similar type of calibration and normalization process may be performed for one or more of the different skill-based activity platforms used for competition. Once calibrated and normalized, the Al platform may retain the calibration and normalization information so as to apply during future skill-based activities. If a new platform is used or an existing one is moved or repaired, then a recalibration and renormalization process may be selectably performed.

[0036] With regard to FIG. 4, a network environment 400 in which a system, such as a competition platform server or Al platform 402, in communication with one or more simulators or platforms 404a-404n (collectively 404) or one or more simulation platform servers 406 that are used as part of a skill-based activity competition is shown. The simulation platform server(s) 406 may include hardware consistent with other servers, as further described herein. In an embodiment, the platform 402 may be in direct communication with the simulators 404 or indirectly in communication via the simulator platform server(s) 406 via communications network 408. In operation, users 410a-410n (collectively 410) may practice and / or compete in a skill-based activity competition using the different simulators 404a and 404n. Each of the simulators 404a and 404n may have respective simulator sensors 412ai-412am(collectively 412) and 414ai-414ao(collectively 414). The simulators 404a and 404n may be different makes and models. Alternatively, the simulators 404a and 404n may be the same make and model. In either case, data 416a and 416n (collectively 416) captured by the simulators 404a and 404n from a simulator console or interface including one or more processors (not shown) and sensors 412 and 414 may be communicated to the platform server 406, which may be a cloud-based server, for collection and storage thereat in a data repository 418

[0037] The data 416 may include audited identity and skill-based activity data from the simulators 404. In being audited, the simulators 404 may verify identity or capture data or image(s) of the respective users prior to, during, and / or after practice and / or competition of a skill-based activity such that confirmation may be made to validate that the identify of the user if verified to avoid someone else playing or taking turns for the user or the user “sandbagging” during practice so as to have a higher handicap and playing better during a competition to have a competitive advantage. Moreover, the sensors 410 may be configuredto sense equipment (e.g., club brand, club weight, club head and club face dimensions, club length, golf ball weight, dimensions, dimple pattern, etc.) and biomechanics of the user, thereby being able to validate that the equipment is within regulation and biomechanics comply with regulations of a competition and that the user performs within a statistical deviation range during practice and / or previous competitions to confirm that the user is not “sandbagging” or committing fraud in some other manner.

[0038] The Al platform may include one or more processors 420 that executes software 422 configured manage a skill-based activity competition in which competitors are using simulators 404. The skill-based activity competition may be considered a peer-to-peer competition that includes match play, leagues, tournaments, and skill challenges. Non-peer- to-peer competitions are ones in which one or more competitors play against the “house” (competition operator) and the house sets odds for the competitor to beat, where the house may or may not adjust the odds for the skill-based activity over time. The software 422 may be configured to generate artificial intelligence (e.g., neural network 424) and / or machine learning software that is used to identify users or competitors along with biomechanics, equipment, etc. of the simulators 404, as previously described.

[0039] The processor(s) 420 may be in communication with memory 426, input / output (I / O) unit 428, and storage device 430 inclusive of one or more data repositories 432a-432n (collectively 432) that store data associated with users, simulators, and so on. In an embodiment, an official / event or competition moderator 434 may receive data 436 inclusive of protests from competitors, data that is determined to be outside of a statistical deviation range. A statistical deviation range may use any statistical analysis performed by Al model or non-AI (e.g., standard deviation equations) algorithms that identify performance, such as biomechanics of a competitor hitting a golf ball, walking technique (e.g., gate, arm swing, stride length, head motions, etc.), driving distance (e.g., 180 average yards to 285 yards), or otherwise that are indicative that the competitor may be cheating or has improved his or her biomechanics of performing the skill-based activity.

[0040] In an embodiment, the official 434 may be presented a user interface 438 in which the official 434 may adjudicate as to whether to accept or disqualify the competitor in the competition. In an embodiment, the official 434 may be provided with the ability to communicate with a competitor via a mobile app, telephone, email, text messages, and / or otherwise to assist in determining whether the competitor has improved his or her skill-based activity abilities, changed equipment, or changed something that resulted in the software 422or Al model 424 determining that potentially fraudulent behavior occurred (if non-real-time analysis is performed) or is occurring (if real-time analysis is being performed).

[0041] With regard to FIG. 5, an image of a simulator 500 in which a competitor 502 may use to compete in a skill -based activity competition and to use for practice prior to the competition is shown. The simulator 500 may include multiple sensors 504a-504n (collectively 504), including cameras (e.g., smart cameras), motion sensors, and other sensors, as previously described. The sensors 504 may also include sensors that are attached or mounted to the competitor 502 or equipment used by the competitor 502. The simulator 500 may include a local console (not shown) in which a user interacts via a user interface (not shown) or via a mobile app, for example. Alternatively, the simulator 500 may interact with one or more cloud-based computing devices via a user interface (not shown) that may be accessed via a mobile device (e.g., smart phone, tablet, etc.). As the competitor 502 uses the simulator 500, the user views a display 506 as the competitor uses real-world equipment, in this case swings a golf club 508 to hit a real-world golf ball 510, and the sensors 504 sense motion of the equipment (e.g., golf club 508 and golf ball 510) and the simulator 500 determines trajectory of the golf ball, such as distance, angle, height, loft, slice, draw, etc. to display a virtual representation of the golfball.

[0042] With regard to FIG. 6, an illustration of a simulator environment 600 in which a user 602 is performing an illustrative series of swings 604 during practice and / or during a skill-based activity competition from which one or more sensors (see FIG. 5) capture data and an artificial intelligence (Al) model may use to analyze the user’s golf biomechanics, for example is shown. The Al model may be trained to identify biomechanics of the user 602, equipment, and so on.

[0043] With regard to FIG. 7, an illustration of a user 700 wearing an illustrative wearable device 702, in this case a golf glove, that may include one or more sensor (e.g., motion, pressure, temperature, pulse, etc.) is shown. It should be understood that alternative wearable devices, such as hats, bands, etc., may be utilized to sense motions (e.g., X-axis, Y-axis, Z- axis motions), biomechanics, blood pressures, temperatures, eye movement, joint angles, velocity, acceleration, and / or other sensors may be utilized for collecting user and / or equipment data. The sensing may be performed during practice and / or competitions such that the collected data and analytics, such as Al analytics generated by an Al model, thereof may be used to ensure integrity of the competitor during a competition, such as during a peer-to- peer competition.

[0044] With regard to FIGS. 8A-8I, screen shots of illustrative user interfaces 800a- 800I_ for a user to participate in a skill-based activity competition in which Al fraud detection may be utilized for player integrity purposes are shown. As shown in FIG. 8A, a screen shot of the user interface 800a in which a user (competitor) may select a competition or game type to join by selecting one of multiple available options. As shown, multiple selection features 802a-802c (collectively 802) may be available for selection in which a first selection feature 802a may allow a user / competitor to use an Al matchmaker to be paired up against another user. The Al matchmaker may match the user with another user based on a number of different factors, such as by skill, geographies, demographics, handicap, speed of play, interests (if communications between the users / competitors is made available), and so on. A second selection feature 802b may allow for a user to manually select an opponent to play in a match. In response to the second selection feature 802b, a list of opponents may be presented to the user. The list may be presented in any number of ways, such as alphabetical, based on skill, based on geographies, based on demographics, based on handicap, based on speed of play, based on interests, and so on. The manual selection may also enable a user to search for an opponent using a simple search feature (e.g., handicap, average score, etc.) or detailed search (e.g., enter or select one or more searchable parameters, such as geographies, demographics, simulator type, etc.). A third selection feature 802c enables the user to select from a private group of users with which to compete. It should be understood that additional and / or alternative selection features may be provided to enable the user to select to be in one or more types of peer-to-peer competition types, including match play, leagues, tournaments, and skill challenges. In an embodiment, certain principles described herein may be applicable to play against the “house.”

[0045] The game type may be non-real-time (e.g., each user plays a complete game (e.g., 18 holes of golf, a full game of cricket in darts, a complete game (i.e., ten frames or multiples of ten frames) of bowling, etc.) or partial games (e.g., one or multiple holes of golf, one or more turns of darts, one or more frames of bowling, etc.) and then the platform may determine the winner from the complete game or enable the other user to perform a corresponding game or partial game. If played real-time, then the system may allow each of the users to perform a turn (e.g., two bowling frames, one golf shot, one turn in darts, etc.). In either case, the skill-based activity of a user, which may include motions performed by a user and / or equipment in the user performing the skill-based activity, may be captured by one or more sensors (e.g., camera, radar, LIDAR, etc.).

[0046] As shown in FIG. 8B, a user interface 800b displays a challenger 804 selected by or who selected the user to compete in a one-on-one competition. Information associated with the challenger 804 may include the challenger’s name (actual or non-actual) 806, location 808, golf course (simulated in this case) 810, bet or wager amount 812 (e.g., $100), and handicap 814 (e.g., 80). The wager amount may be a set amount of which the challenger 804 is always willing to accept or may be entered by the challenger or by the user to the challenger 804. The handicap 814 may change over time based on ongoing practice and competition play by the challenger 804. A selection element 816 may enable the user to view a full profile of the challenger 804. If the user agrees with the challenge, including the various terms, then the user may select a “confirm challenge” selection element 818 and if the challenger also confirms the challenge, then the two users may compete with one another to play on the golf course 800 for the bet amount 812.

[0047] User interface 800c may present a user 818 and competitor 804 with information 820 associated with the skill-based activity competition. The information may include a number of parameters of the skill-based activity performed by each of the competitors, including score, driver (currently selected), irons, short game, etc. The driver information may include distance of the current round and typical distance by the competitor 804. As shown, the max distance during the tournament is shown to be 250 yards while the typical max distance is 190 yards. The average distance is 247 yards while the average yards is 188. Club head speed, ball speed, and other parameters may be sensed by sensors and computed by one or more processors. Each of the users 818 and 804 may view respective information 820 to determine whether or not the other suspects fraud may be occurring. If fraud is suspected by either of the users 818 and 804, then the user may submit a formal protest (see, for example, FIGS. 8H and 81).

[0048] With regard to FIG. 8D, a screenshot 800d that provides for match details with an initial Al fraud alert sent to the players is shown. The user interface 800d may show each of the users 818 and 804 at the top of the user interface 800d with indicators 820a and 820b, such as circles around the users 818 and 804, having different colors (e.g., white, green, yellow, red, etc.). If an Al model detects that one of the users or competitors 804 has a score, for example, indicative of fraud being committed, then the Al model may look “behind the score” to determine how the user 804 was able to achieve such a good score as compared to historical scores and whether or not one or more parameters of the skill-based activity is outside of a statistical deviation range. Performance of a parameter of the skill-based activitythat is outside of a statistical deviation range may indicate that fraud is being committed during the skill-based competition. In such an event, a notification 822, such as “AIXT has flagged this match for fraud” or any other message along with information 824 for the competition, including “you already played. View your stats.,” “An opponent has accepted your challenge. View opponent profile.,” and “the other player already played and you have one this challenge! You final stats.,” etc. the fraud notification may be in the form of an SMS message, message on the user interface 800d, or any other technique to the users and / or official who was refereeing or otherwise overseeing the competition between the two users or competitors 818 and 804. It should be understood that additional and / or alternative information 824 may be presented to either or both of the users 818 and 804.

[0049] Wagering information 826, such as amount earned, may also be displayed. Moreover, information 828, such as points earned, may be displayed. By using an artificial intelligence model to alert one or both of the players of potential fraud, the users 818 and 804 may be more hesitant to commit fraud, such as “sandbagging” or swapping in a different player during the competition. As previously described, fraud may include identity fraud, skill-based activity fraud, equipment fraud, or otherwise, and the fraud may be identified by an Al model being executed to compare skills-based activity performance in the form of statistics captured by a simulator, identity from images captured by a camera, biomechanics from video captured by a camera, or otherwise.

[0050] With regard to FIG. 8E, a user interface 800e that includes skill-based activity performance parameters of today or the competition versus average performance parameters is shown. The user interface 800e is automatically highlighted by software operating the user interface 800e as a result of an Al model determining fraud detection results, which may be triggered based on overall score of the user 804. In an embodiment, the highlights may be text shown in red or otherwise to indicate fraud that manifests in particular performance parameters as provided in the information 820. For example, “gross score” today being at 65, where the average gross score is 71 may be indicative of fraud having been committed by the user 804. Moreover, world rankings of the user or competitor 804 being at 7, whereas the average of the user 804 is 81, may also be indicative of fraud having been committed. Such fraud may result by the handicap of the user 804 having been manipulated during practice (i.e., historical performance of the user 804), such that the performance during the competition of the user 804 far exceeding average performance of the skill-based activity by the user 804. In other words, an Al model may be configured to compare current score to ahandicap index of the user 804 to ensure that the current score falls within an acceptable variance of the handicap index. The user interface allows for the competitor 818 to be able to view and determine whether or not submit a protest. Additionally and / or alternatively, a user interface for an official of the competition may also enable the official to further investigate and submit an official protest to adjudicate whether or not fraud was committed.

[0051] With regard to FIG. 8F, a screenshot 800f may further present information 820 being highlighted to indicate specific performance parameters that may indicate that fraud has been committed. Again, an indication of fraud may be indicative of a skill-based activity being outside of a statistical deviation range or variance based on historical data of a user. In this case, an Al model may generate a report on ball and club data that indicates anomalies that activated a fraud alert of a scoring system, and a fraud alert or notification may be communicated to one or both of the users 818 and 804, and / or an official of the competition. By utilizing an Al model to detect and report fraud, integrity of the competition may be improved or insured such that competitors may feel confident that the platform that supports the competition is fair such that the players are willing to wager money in competitions that utilize the Al platform, as previously described.

[0052] With regard to FIG. 8G, a user interface 800g may include a video portion 830 in which video segments may be displayed, and portion of the skill-based activity, in this case 18 holes, during which the video segments are shown. The user interface 800g may also include a selectable list of portions 832 of the skill-based activity to select the video segments to view. In operation, the Al model may analyze swings of a user to (i) verify player identification (e.g., facial recognition, biomechanics recognition, physical movement of the player and / or equipment being used by the player, physical measurements, and so on) and (ii) compare biomechanics, physical movement of the player and / or equipment, both identity and fraud may be determined. By using an Al model to identify various sensed parameters, which may be automatically performed or performed in response to a user selecting a selectable user interface element 834, integrity may be provided. If the competitor were a different skillbased activity, then the user interface 800g and selectable list of portions 832 may be configured for the different skill-based activity (e.g., frames 1-10 of bowling, game number, etc.).

[0053] With regard to FIG. 8H, user interface 800h may enable a user to protest the competition by selecting a protest selection element 836 is shown. The user should be able to view a video segment to confirm identity of the competitor and / or any other activitiesperformed by the competitor in the video segment. By providing user interface 808 with the protest selection element 836, a protest and resolution process may be initiated. In response to protest, disqualification and / or penalties may be imposed on a fraudulent competitor and the competitor who was defrauded may receiving their entry fee or wager back possibly with additional compensation from the fraudulent competitor. The process may include both an Al-driven model analysis and human oversight to ensure fairness and accuracy of the skillbased activity competition.

[0054] With regard to FIG. 81, a screenshot of an illustrative user interface 800i that may be displayed in response selecting a protest selection element 836 is shown. Text entry field 838 may enable the user to enter a message for consideration by an official of the competition as part of the protest. As shown, the user 818 who is protesting may enter a message, such as “Hey! That’s Tony Finau!” The message may be stored as part of the competition and provided to the official and / or competitor 804 of the user 818. The protest may be communicated to the official and / or allow for the competitor 804 being accused of fraud to provide for a response to the protest. To enable the competitor 804 being accused of fraud, a user interface (not shown) that includes one or more text entry fields and / or selection elements to enable the user to respond to the fraud charge. For example, if the competitor, such as competitor 804, has recently taken lessons from an instructor or been practicing more than normal, the competitor may have actually improved significantly enough that the changes in score, difference in skill-based activity (e.g., golf swing changed) may be plausible. In an embodiment, the Al model may be trained to re-analyze the competitor’s performance and response (e.g., took 10 lessons recently) by the competitor to determine whether or not it is plausible that the competitor improved his or her skill-based activity such that fraud does not actually exist. If, alternatively, the player’s identity is challenged based on his or her facial features, for example, then justification for the change in facial features may be more limited.

[0055] With regard to FIG. 9, an illustration of an illustrative environment 900 in which a skill-based activity, in this case golf, being performed in the real-world, in this case a golf course 902, as opposed to a simulator is shown. A player 904 may utilize a robotic golf cart 906 and optionally one or more drones 908a and 908b (collectively 908) that include cameras and / or other sensors that capture images and / or sense other parameters associated with the skill-based activity of which the player 904 is performing. The drone(s) 908 may be configured to manually, semi-automatically, and / or automatically be positioned in a manner that the player 904 and equipment (e.g., golf club, golfball, etc.) may be sensed. It should beunderstood that rather than using a robot on which one or more sensors (e.g., camera, radar, etc.) may be positioned that one or more non-robotic systems or devices may be utilized to perform the same or similar function of capturing the player 904 performing the skill-based activity. It should further be understood that alternative skill-based activities may utilize different robotics, sensors, drones, etc., and provide for capturing a player performing the skill-based activity for use in identifying fraud during practice and / or competition.

[0056] The robotic golf cart 906 may be configured to carry a golf bag 910 and the player 904 or multiple players. The size and configuration of the robotic golf cart 906 may be different, but perform the same or similar functionality. In an embodiment, the drone(s) 908 may be configured to automatically land on the robotic golf cart 906 or a stand (not shown) that is positioned along the golf course 902. The drone(s) 908 may be configured to hover above, behind, on the side, in front, or any other position while the player 904 is hitting so as to capture video and other data (e.g., golf club make and model, golf club size, golfball brand, golf ball dimples, etc.) so as to be used by the competitor(s), official(s), and / or Al model to perform verification and analysis of the identity of the player and the player’s skill-based activity “DNA” that is indicative as to the biomechanics of the player 904 for identity and performance analyses as part of an anti-fraud methodology.

[0057] With regard to FIG. 10, a flow diagram of an illustrative process 1000 in which a skill-based activity competition may be performed and managed in a manner that supports integrity by reducing or eliminating fraud using player identification and using an Al model to detect fraudulent activity by competitors. The process 1000 may include a mobile device 1002 on which a mobile app is executed, one or more simulator or gaming device 1004, a simulator or gaming device storage (e.g., cloud-based server) 1006, competition server platform 1008. In operation, a competitor or user using the mobile device 1002 may register or otherwise check-in by submitting a unit identification code (UIC) in the form of a quick reference (QR) code or other identifier of the simulator or gaming device 1004 at step 1010.

[0058] In an embodiment, the mobile device 1002 may capture an image of the QR code representative of the UIC and submit an identifier of the simulator or gaming device, user identifier, and game data with the competition server platform 1008 at step 1012. As the competitor performs the skill-based activity during a skill-based activity competition or practice for a competition, game data captured by sensors of the simulator 1004 may be communicated to the simulator or gaming device storage 1006 at step 1014or, alternatively, the game data may be communicated directly to the competition server platform 1008 at step 1016. If the game data is communicated directly to the simulator or gaming device storage 1006, then the competition server platform 1008 may access the game data by polling or the storage device 1006 may be communicated to the competition server platform 1008 automatically at step 1018. The competition server platform 1008 may be used to generate results, including identifying competitor identification fraud, competitor skill-based activity fraud, update handicap and rankings of the competitor, and generate fraud alerts during or after a competition at step 1020. The fraud alerts may cause a change of features of a user interface, cause the competition to be halted by altering operation of the app or even the simulator, of controllable by the competition server platform 1008 or app being executed by the mobile device 1002. The competitor may review potential fraud via the mobile app and submit a formal protest to an official officiating the competition. Prize distribution, such as wager transaction, may be performed by the competition server platform 1008. Additionally, penalties may be issued by the platform 1008. In an embodiment, an official officiating a competition may receive the fraud notification to enable the official to view video segments, identity data, skill-based activity data, a protest submission explanation by the non-fraudulent competitor, a response to the fraud protest by the accused fraud competitor, or otherwise, and make a ruling as to whether there is fraud. The explanation may include freeform text and / or be selections from a user interface of possible defenses (e.g., recent lessons, more practice recently, new or better equipment, or otherwise).Al Activity Match Making

[0059] With regard to FIG. 11, an illustration of a network environment 1100 in which skill-based activities are performed and data of users performing the skill-based activities are captured by sensors so that Al activity matching may be made is shown. The sensors may be part of simulators 1102, such as a golf simulator, or may be independent and be independent of a simulator. For example, sensors that are independent of a simulator may be added to gaming devices, outdoor uses and mounted to stationary structures (natural and / or manmade), integrated into equipment of competitors, included on robots, drones, or otherwise. Data from sensors may be communicated to an Al server 1104 that performs Al functionality, as previously described, but may also execute an Al engine 1106 that is trained to identify player information, such as demographics, geographies, skill-based activity that is good and bad so as to recommend goods and services to the player, as further described herein.

[0060] To support the skill-based activity for a user, a mobile app that supports a user interface 1108 that executes on a mobile device 1110 may be utilized. The mobile app may present recommendations generated by the Al engine 1106 inclusive of goods and / or services to the user, as further described herein. Communications of data 1112 may be communicate via a network 1114.

[0061] In addition to the system being able to reduce or prevent fraud when players or participants are participating in activities and generating data-based handicapping, the collected data may additionally be used for activity match making purposes. For example, for a golf application, an Al system may be trained to identify a type of skills (e.g., swing type, ball accuracy, club head speed, ball speed, ball rotation, etc.) the players have in matching the players with particular club types, club brands, club materials, etc. More particularly, if the player has a fast swing, a shaft material that is more flexible may be recommended to the participant by the Al system. Still yet, the system may be configured to identify personality traits of the player, for example, by determining aggressiveness of a player in performing an activity, and automatically matching the player with a particular trainer or instructor who works well with that type of personality (e.g., the Al system may perform an analysis of the trainers and instructors to determine personalities and skills or the trainers may simply provide answers to questions or submit a profile).

[0062] In an embodiment, the Al system may determine intensity of a participant based on frequency of using a simulator or playing on a course, for example, improvement speed of the player for performing one or more types of skills within the activity, or otherwise, and use that learned information to match the player with a trainer, equipment, and / or otherwise. For example, if the Al engine determines that the player is improving his or her skills faster than other players or in a small percentage of players (e.g., improving skills in top 10% of players), then the Al system may recommend equipment (e.g., golf clubs) to the participant that will match the participant’s predicted improved skill set within a certain time period, such as six months or a year, thereby avoiding the player being limited by equipment as opposed to the participant’s ability to perform the activity. In essence, the principles described herein through the use of capturing player activities while practicing and / or while competing in an activity, an Al matching tool may be able to match the player ability with equipment, instructors, trainers, upcoming events, or any other commercial activity and / or products within the activity.

[0063] As shown in FIG. 11, a participant of an activity, such as golf, may utilize the golf simulator 1102 to practice and / or play in golf tournaments and competitions. The Al server 1104 may collect data 1112 from the simulator and perform analyses of the player, including identity, swing profile, consistency, and any other information that is collectible from the golf simulator, as previously described. The Al server 1112 may execute the Al engine 1106 to make skill-based activity recommendations that may be used to drive the mobile app for participants of the activity, in this case golf, that is capable of providing recommendations for clubs, lessons, caddies, courses to play, and any other recommendations of the activity, such as, but not limited to, apparel (e.g., clothing, shoes, hats, gloves, etc.) and accessories (e.g., rangefinders, ball monitors, etc.).

[0064] In an embodiment, the Al engine 1106 may be configured to capture data of other players, and, based on feedback and / or success of the other players who may be identified as having similar skills as the player at a certain point in time of the players learning, determine and recommend best equipment and / or other recommendations (e.g., instructors, apparel, etc.) for the player based on the speed of improvement, lack of improvement, success, and / or failure of other players. For example, if other players who had similar skills if the player started to use certain clubs, and then the players skills did not improve or worsened, then the Al engine 1106 may determine that the player would not benefit from those clubs, but possibly recommend other clubs depending on what players with similar clubhead speed, accuracy, etc. utilized and their improvement or lack of improvement. Still yet, the Al engine 1106 may determine and recommend certain activities, such as stretches, gyms, exercises, etc., to the player based on the player’s skills and shortcomings in performing the activity (e.g., exercises that may build strength or improve club head speed). It should be understood that the principles described herein may be utilized for any other activity, as previously described, and use the Al engine 1106 for matching participants of the activities with equipment, coaches, instructors, trips, and so on.

[0065] General Conclusion

[0066] In general, the principles provided herein may support trusted handicaps that are audited by verifying identity and historical skill-based activity (e.g., practice and competition play), including biometrics, biomechanics (e.g., movement), equipment, and / or platform (e.g., simulator). In an embodiment, the principles provided herein may provide for rankings, such as world rankings, as a platform that supports an application for one or more skill-based activities, may be regional, national, and / or global, and may be segmented based on variouscriteria, including simulator brand or platform, demographics, geographies, skill level, and other specific subsets.

[0067] Rankings may be established for any skill-based activity. As an example, for golf simulator skill-based activity competition, ranking may be based on points accumulated from participation in open tournaments. A number of points may be awarded contingent on the competitive level of each tournament. Because simulators are often remote from one another, verifying player identity and skill level is used to uphold the integrity of the competitions. Rankings that undergo verification and auditing may be considered reliable and integral, while non-verified and audited may be considered unreliable and non-integral. In tournaments with a competitive field of competitors, especially those including high-ranking players, the top 20%, for example, of participants may receive bonus points to reflect strength of the competition. The world rankings may have two primary functions, including (a) determining eligibility and qualification for exclusive invitational tournaments and match play events for the top-ranked players, and (b) providing players with opportunities for bragging rights and recognition.

[0068] Competitive benchmarking may provide for golfers with a clear benchmark of their skills compared to others globally, thereby encouraging the competitors to improve and develop their game. Simulation golf handicap system and world rankings may be provided a handicap system characterized by integrity and be designed to broaden tournament accessibility to players of all skill levels by using handicap scoring, thereby allowing for a beginner player to compete against and advanced player. The handicap system may further support wagering that is trusted by competitors as fraud may be reduced or completely eliminated by using Al models of competitors, equipment, etc.

[0069] More specifically, an Al-formulated handicap may utilize an advanced Al model to calculate player handicaps from audited scores and detailed performance metrics. Precise causation identification may determine the exact metrics responsible for variations in a player's performance relative to their established handicap, as described above by (i) determine that a player’s score is out of a typical variance and then look specifically at different skill-based activity parameters (e.g., golf swing, ball control, dart speed, bowling ball speed and spin, etc.). The Al model may perform automatic flagging of potential fraud to ensure integrity in response to the Al model detecting discrepancies. The flagging may cause information to be highlighted, message(s) to be sent, etc., in a real-time or non-real- time basis. If sensing is performed continuously throughout a competition when thecompetitors are performing skill-based activities (e.g., taking a golf shot), then the Al model may be continuously utilized throughout an entire competition to ensure integrity exists throughout the entire tournament.

[0070] In an embodiment, corrective action enforcement may be performed by performing a process that, in response to detection of irregularities, the system may implement corrective action(s) to maintain fairness and the integrity of the game. The corrective action(s) may include the use of a formal protest, manually or automatically, to be submitted such that enforcement of rules may be enforced. In an embodiment, player-enabled review and challenge may be enabled via a mobile app or other user interface. The platform described herein may be external from simulators so as to avoid concerns of competitors that the simulator manufacturer may have a vested interest in some manner. Players may have the option to review an opponent’s play. The review may be performed on an activity -byactivity basis (e.g., by hole and by shot for golf) and may request a manual or Al-supported challenge if discrepancies are suspected. For other skill-based activities, a user interface may be configured to enable the player to review a competitor’s play (e.g., by mile marker for a driving simulator, by inning for a baseball simulator, etc.).

[0071] Handicapping may be performed by using score and data analytics. For example, for golf, score, ball and club head data, swing data, equipment, equipment motion, biometrics, and demographics may be utilized. Additional and / or data analytics may be utilized, as well. For non-golf, the data may include score, equipment (e.g., basketball, darts and dartboard, arcade games (e.g., arcade basketball), actual basketball, etc.), motion data, biometrics, and demographics may be utilized to determine a handicap of a player. Utilizing the data analytics, not only can a data-driven handicap be determined, but also fraud detection may occur, as previously described.

[0072] To use in wagering to level the playing field, score adjustments or money odds may utilize handicap scores of competitors. Player profiling to avoid fraud may also use data analytics, including handicap, score, ball and club head data, swing data, biometrics, equipment, equipment motion, and demographic. Additional and / or alterative data analytics may be utilized, as well.

[0073] Match making for competitions of two or more competitors may be automated or searchable using player profiling, handicapping, score, ball and club head data, swing data, biometrics, demographics, or otherwise. The use of Al match making may support matching opponents against one another, matching a player with custom golf equipment, matching aplayer with training and instruction. As an example, if the Al platform detects a certain swing style, the Al platform may match a player with equipment specifically beneficial for a swing style or an instructor who is good at changing the swing style. The principles described herein may create a data-driven handicap system for sports simulators, arcade games, games of skill, etc., to be used for fair peer-to-peer competition with integrity, thereby eliminating selfreporting.

[0074] A data driven handicap system may include a player performing a minimum of 10 rounds of golf (or other skill-based activity), collecting scores, tracking ball data, collecting golf equipment (club) data (e.g., make and model), swing data, and player profile. A player profile may be used for (i) establishing a handicap, (ii) Al match making for finding an opponent based on handicap, ball data, golf equipment (club) data, (iii) scores, including (a) the last 10 rounds of simulation golf, and (b) ball data. Device used to capture ball (or other equipment) data may include different sensor types, including camera for capturing images and / or video, radar, sensors embedded or attached to equipment (e.g., golf club, ball, racket, etc.) so as to track the equipment (e.g., golf ball). Data may be collected for creating actual data captured or by algorithm or both. The data may include ball speed, ball spin, ball distance, launch angle, angle of decent, maximum height. Club data may be created by actual data capture or by algorithm or both, and include club head speed, club angles, club path, club face, etc., over a period of time, such as the last 10 rounds of simulation golf.

[0075] Scores may be saved and not self-reported, thereby avoiding any misdeeds by players. Data from sensors may saved to correspond to the score by per shot or stroke, per hole, per round and per average of all 10 rounds or more. Alternative skill-based activities may store data in association with activities for those skill-based activities for competitor review, official review, and / or Al analysis.

[0076] The system or platform described herein enables users to participate in worldwide tournaments or private group events, and enables matching players ranging from pros to high handicappers (i.e., excellent players to beginners) as a result of integrity and handicap scores being audited and validated. Competition and wagering may also be supported using the principles described herein by enabling players to challenge other players for real cash, points, and / or prizes, supported by analytics-based handicapping system and a player identity platform, thereby ensuring fairness and integrity on the platform. Because of the integrity, competitors are more confident that wagering using handicap scores is fair. It should beunderstood that non-handicap competitions may also be supported by the platform described herein.

[0077] The principles described herein may provide for a more competitive player vs. player gaming system by automatically adjusting for differences in skills of participants to produce balanced competitions. Digitally facilitated competitions in gaming are very common today. Esports games may link anywhere from two players to potentially hundreds of players in a video game competition. The winner of these competitions may be determined by a number of factors, such as total score, achievements in game, “last man standing”, and more.

[0078] Other digitally mediated games may involve players competing against each other on physical / digital hybrid apparatus. For example, two players might compete in a round of golf, each playing on a simulator (e.g., golf simulator). The simulator played by the competitors may be the same simulator or may be different simulators that are connected or not connected through a server. The player with the best score is declared the winner and any prizes and / or cash stakes put up for the game are released to the winner’s account. All competitive games require reasonable balance in skill-level between players in order to maintain a viable population of players. If there is too great an imbalance in skill between players, the less-skilled players may become demotivated at the inability to win and no longer play the game. Loss of player enthusiasm reduces overall participation in the gaming system, which can cost operators money and can potentially terminate the viability of the games (due to a severe lack of players).

[0079] To prevent this problem, most esports games track individual player performance over a series of games and assign a ranking to the player. Rankings may be determined by a number of factors, including an assessment of the player’s performance in gameplay (using data metrics, such as aim accuracy, actions per minute, average score, etc.). Player rankings may then be determined by comparing individual player metrics with the population of players and assigning players a skill score and / or assigning players into categories (such as beginner, intermediate, expert, elite).

[0080] There are some drawbacks to the traditional method of ranking and pairing players in video games and other digitally mediated competitions. A system that labels and groups competitive players within a range of skill does not completely account for gaps in skill. For example, the system may pair two players in a match who are close in skill, but are not equal. The player who is identified as less skilled is unknowingly in a match where they have adisadvantage. The is also a benefit for a large player pool. A system in which only players who are close in skill may compete against one another demands a larger pool of available players in order to ensure that there is an available match for players of different skill rankings. Having to support a large player pool can make it very difficult to create a viable competitive environment for new games that have few initial players or to keep games active during times when there are fewer players active. Dull competition is also a challenge for games in which competing players are generally evenly matched, which may ultimately become frustrating and even boring. With the right structure, gaming can be exciting to compete against players of different skill levels (greater than or less than), if there are adjustments made to the game to balance fairness. The principles provided herein overcomes the shortcomings of current handicapping systems that are handled by self-reporting without any auditing system for integrity and verification. At worst case scenario, a player does not even have to actually play and can submit a fictitious score and the handicap system does not verify the score.

[0081] Often, in competitive sports, such as golf, players with a significant skill gap compete against one another. A handicap is used to provide balance between the players. For example, in a matchup between two players where one golfer is substantially more skilled compared to the opponent, the players may agree to handicap the skilled player’s score by adding additional strokes to whatever the skilled player’s final score is. In order to win, the skilled player’s score must exceed the less-skilled player’s score and also overcome the handicap.

[0082] In golf matchups, handicaps are determined through an assessment and comparison of each player’s score from a previous number of games. Other examples may include racing and other point or goal gaming. In a race, the less-skilled racer may start the race closer to the finish line. In a game involving points or goals, the more skilled player may start the match with a point deduction that the more skilled play has to overcome in addition to beating the opponent(s)’ score. In a video game that involves completing certain objectives, such as eliminating players, collecting objects, etc., the more skilled player(s) may have a starting deficit on these objectives. Another form of handicapping in video games might include restricting the more skilled player’s access to resources (including time, ingame currency, or other elements that impact performance).

[0083] Example 1 : Handicapping in esports (video game) competition.

[0084] A system or platform may include each individual player having their own account that tracks and stores data of the history of their performance in past games. Data metrics may include win / loss stats, actions per minute, analysis of strategy, other game performance metrics (eliminations, score, combinations). A more advanced form of data collection and analysis might include comparing player performance when matched against different players with different playing styles and skill levels). Each player account may generate an active skill metric / score (using collected historical data that prioritizes more recent data when compiling the skill score.). The game system matches two or more players for a competition. The system may assess the skill ranking of all competitors and assign a handicap condition to the more skilled player(s). At the conclusion of the game, each player’s performance, including the handicap, may be evaluated. The winner(s) may be determined, and any prizes or awards are released to the winner(s) account.

[0085] Live vs Asynchronous.

[0086] In a live match where players are competing in real time, the competing players may be made aware of a handicap in advance. The game may be designed in such a way that players can decline to complete after the handicap is revealed. Alternatively, the game may be designed so that it is not possible to withdraw from the competition after the handicap is revealed.

[0087] Some competitive esports models employ an asynchronous matching system. In an asynchronous competition, the player completes their game tasks independent of the other player(s) in the match. Frequently, in asynchronous matches, the competitors are matched and complete their gameplay at different times. For example, Player A may enroll in the match and complete the challenge at 11 :00am on Wednesday. At 1 :00pm the next day, Player B may opt to enroll in the game and is matched against Player A’s already completed match. The skill levels of each player may be assessed and a handicap may be assigned. Player B may not be aware of the assigned handicap before beginning his or her turn. At the conclusion of the match, Player A and B’s scores are compared, with the assigned handicap to the more skilled player included in the assessment. Player A and B may be notified of the outcome through their accounts. This notification includes details about the handicap assigned to the more skilled player. The prize may be delivered to the winning player’s account.

[0088] Example 2: Golf Simulator.

[0089] The use of a handicapping system may also be applied in competitions for golf simulators (and other athletic simulators, such as are described in US patent 11 328 559). Such handicapping systems may include individual player accounts that identify players and track data on gameplay over time. One or more of the golf simulators may be in communication with a server.

[0090] Golf (and other athletic simulators) may use a variety of sensors to translate player athletic performance into data required to conduct a simulation. The sensed data may be quite precise and, in golf, include characteristics related to the players accuracy, force, stance, and adaptability to course conditions. The sensor data may be used (in addition to the history of the player’s score) to create an accurate record of player skill that can be used to create adaptive handicap conditions against a wide range of skilled competitors.

[0091] Features of Handicapping in competitive gaming.

[0092] Less restrictions on matches: A robust handicapping system as described above may enable more matches between players with significant skill differences (due to its ability to adapt to large skill gaps and create a more fair competition). The handicap system may allow for a more precise matchup between players of differing skill, thereby creating a matchup that is fairer. Players may be more willing to enter future matches when there is a feeling that the gameplay experience was fair and the odds of winning the match are fair. In traditional skill matching systems (both real time and asynchronous), players have limited knowledge about the skill level of their opponent(s) and are limited to playing against opponents that are only somewhat above or below their own skill level. The handicap system communicates each competitor’s skill more directly as one competitor may find themselves playing against a player who is far above or below them. The gap is compensated through a handicap. The ability to compete against players above or below (and know this fact) changes the experience of the game and may give players a sense of pride, accomplishment, or amusement to know, for example, that they performed well against a better player.

[0093] Additional Features

[0094] One embodiment of a computer-implemented method for conducting a skill-based activity competition may include accessing handicap data of a first competitor, where the handicap data may be derived from historical physical activity performance of the first competitor during practice and / or competition play of the skill-based activity as captured by at least one sensor. During the skill-based activity competition, data captured of the physicalactivity performed by the first competitor using the at least one sensor and a score achieved by the first competitor in performing the physical activity during the skill-based activity competition may be received. A handicap-adjusted score of the first competitor by applying the handicap data to the score of the first competitor may be computed, and a winner of the skill-based activity may be determined by comparing the handicap-adjusted score of the first competitor with one or more handicap-adjusted scores of at least one respective other competitor.

[0095] The process may further include verifying, may be based on at least one biometric parameter, an identity of the first competitor. Verifying an identify of the first competitor may further include verifying the identity of the first competitor based at least in part on physical activity of the first player measured by the sensor(s) during the skill-based activity competition relative to the historical physical activity of the at least one player measured by the sensor(s).

[0096] Receiving data may include receiving data captured using the sensor(s) may include receiving data that is the same sensor(s) used to capture of the physical activity during practice and / or competition play of the skill-based activity. In other words, the sensor(s) may be the same sensor(s) because a user may play on the same simulator during a competition as used during practice. The sensor(s) may be different if the user participates in a competition that is in a different simulator or location from that on which the user practices. Receiving data may include receiving data from a simulator used by the first competitor during the skillbased activity competition.

[0097] Second handicap data of a second competitor may be accessed, where the second handicap data may be derived from historical physical activity performance of the second competitor during practice and / or competition play of the skill-based activity as captured by at least one second sensor. The data derived from the historical physical activity performance of the second competitor may be data that is mathematically or statistically reduced from raw data generated by sensors (e.g., those of a simulator). During the skill-based activity competition, second activity data captured of the physical activity performed by the second competitor using the second sensor(s) and a second score achieved by the second competitor in performing the physical activity during the skill-based activity competition may be received. A second handicap-adjusted score of the second competitor may be computed by applying the second handicap data to the second score of the second competitor. A winner of the skill-based activity competition between the first and second competitors may bedetermined by comparing the handicap-adjusted score of the first competitor and second handicap-adjusted score of the second competitor.

[0098] Determining a winner of the skill -based activity may include determining a winner amongst the first competitor and the other competitor(s) that includes at least two other competitors in addition to the first competitor. Accessing handicap data may include accessing handicap data produced by a common skill-based simulator on which the first competitor used to generate the handicap data using the sensor(s). Accessing the handicap data may include determining that the handicap data is certified by the common skill-based simulator by verifying identity of the first competitor prior to and / or while the first competitor is generating the handicap data. Accessing the handicap data may include accessing the handicap data from a system in communication with sensors disposed at a physical location at which the skill-based activity is performed. Accessing the handicap data in communication from a system with sensors disposed at a physical location may include accessing the handicap data from a system with sensors disposed at a golf course.

[0099] The process may further include enabling the first competitor to submit a monetary wager directly against a second competitor of the other competitor(s), and enabling the second competitor to submit a second monetary wager. In response to determining the winner between the first and second competitors, the wager of a non-winning first or second competitor to the winning first or second competitor may be awarded. The first competitor may be enabled to submit an entry fee for entry into the skill-based competition with a plurality of other competitors, and the other competitors may be enabled to submit the entry fee.

[0100] Accessing the handicap data may include accessing statistical data representative of the first competitor. Verifying an identity of the first competitor may include using facial recognition of images captured of the first competitor while competing in the skill-based activity. Verifying identity of the first competitor may include using artificial intelligence to determine the identity of the first competitor. Verifying an activity of the first competitor may include using artificial intelligence to identify the first competitor based on “signature” motions of the first competitor.

[0101] A player profile of the first competitor and the other competitor(s) as determined by historical activity data of each of the respective first competitor and other competitor(s) may be accessed. The historical activity data may include data captured from at least ten practice sessions and / or competitions. Accessing skill level may include accessing historicaldata from at least ten practice sessions and / or competitions of rounds of golf. Variation of each of the first and other competitor(s) from historical data may be determined using artificial intelligence to analyze the received activity data from the skill-based activity competition from the first competitor and the other competitor(s). A notification in the event that the variation of one of the first competitor or the at least one other competitor is above fraud threshold may be generated. In response to determining that the variation is indicative of fraud, a mobile app being used by the first competitor and the other competitor(s) are using during the skill-based activity competition may be caused to be altered from normal operation. In response to determining that the variation is indicative of fraud, a wager may be caused to be invalidated and the first competitor or one of the second competitor(s) may be disqualified.

[0102] Variation data of each of the first and the other competitor(s) as produced by the artificial intelligence may be generated, the variation data may be communicated to each of the first competitor and the other competitor(s). The variation data may be communicated to each of the first competitor and the other competitor(s) to a mobile application being executed on mobile devices of each of the first competitor and the other competitor(s), thereby enabling the first competitor and the other competitor(s) to review the variation data. Each of the first competitor and the other competitor(s) may be enabled to submit a protest to an operator of the skill-based activity competition for adjudication as to whether the variation data is indicative of foul play via the mobile application.

[0103] Each of the first competitor and the at least one other competitor may be enabled to submit a protest to an operator of the skill-based activity competition for adjudication as to whether an identity of the first competitor or the at least one other competitor is indicative of someone other than the first competitor or the at least one other competitor performing the skill-based activity in place of either the first competitor or the at least one other competitor.

[0104] One embodiment of a system for conducting a skill-based activity competition may include an input / output (VO) unit in communication with a network, and a processor in communication with the I / O unit. The processor(s) may be configured to access handicap data of a first competitor, the handicap data being derived from historical physical activity performance of the first competitor during practice and / or competition play of the skill-based activity as captured by at least one sensor. Data captured of the physical activity performed by the first competitor may be received during the skill-based activity competition using the sensor(s) and a score achieved by the first competitor in performing the physical activity during the skill-based activity competition. A handicap-adjusted score of the first competitormay be computed by applying the handicap data to the score of the first competitor. A winner of the skill-based activity may be determined by comparing the handicap-adjusted score of the first competitor with one or more handicap-adjusted scores of at least one respective other competitor.

[0105] The processor(s) may further be configured to verify, based on at least one biometric parameter, an identity of the first competitor. Identity of the first competitor may be verified based at least in part on physical activity of the first competitor measured by the sensor(s) during the skill-based activity competition relative to the historical physical activity of the competitor measured by the sensor(s). Data captured using the sensor(s) may be received from the same sensor(s) used to capture of the physical activity during practice and / or competition play of the skill-based activity.

[0106] In receiving data, the processor(s) may further be configured to receive data from a simulator used by the first competitor during the skill-based activity competition. The processor(s) may further be configured to access second handicap data of a second competitor, the second handicap data being derived from historical physical activity performance of the second competitor during practice and / or competition play of the skillbased activity as captured by at least one second sensor. During the skill-based activity competition, second activity data captured of the physical activity performed by the second competitor may be received using the second sensor(s) and a second score achieved by the second competitor in performing the physical activity during the skill-based activity competition. A second handicap-adjusted score of the second competitor may be computed by applying the second handicap data to the second score of the second competitor. A winner of the skill-based activity competition may be determined between the first and second competitors by comparing the handicap-adjusted score of the first competitor and second handicap-adjusted score of the second competitor.

[0107] The at least one processor, in determining a winner of the skill-based activity, may further be configured to determine a winner amongst the first competitor and the at least one other competitor that includes at least two other competitors in addition to the first competitor. The processor(s), in accessing handicap data, may further be configured to access handicap data produced by a common skill-based simulator on which the first competitor used to generate the handicap data using the at least one sensor. In accessing the handicap data, the processor(s) may further be configured to determine that the handicap data is certified by thecommon skill-based simulator by verifying identity of the first competitor prior to and / or while the first competitor is generating the handicap data.

[0108] In accessing the handicap data, the processor(s) may further be configured to access the handicap data from a system in communication with sensors disposed at a physical location at which the skill-based activity is performed. In accessing the handicap data in communication from a system with sensors disposed at a physical location, the processor(s) may further be configured to include accessing the handicap data from a system with sensors disposed at a golf course. The first competitor may be enabled to submit a monetary wager directly against a second competitor of the at least one other competitors, and the second competitor may be enabled to submit a second monetary wager.

[0109] The processor(s) may further be configured to, in response to determining the winner between the first and second competitors, award the wager of a non-winning first or second competitor to the winning first or second competitor. The processor(s) may further be configured to enable the first competitor to submit an entry fee for entry into the skillbased competition with a plurality of other competitors, and enabling the plurality of other competitors to submit the entry fee. In accessing the handicap data, the processor(s) may further be configured to include accessing statistical data representative of the first competitor. In verifying an identity of the first competitor, the processor(s) may further be configured to include using facial recognition of images captured of the first competitor while competing in the skill-based activity. In verifying identity of the first competitor, the processor(s) may further be configured to use artificial intelligence to determine the identity of the first competitor.

[0110] In verifying an activity of the first competitor, the processor(s) may further be configured to include using artificial intelligence to identify the first competitor based on “signature” motions of the first competitor. The processor(s) may further be configured to access a player profile of the first competitor and the at least one other competitor as determined by historical activity data of each of the respective first competitor and at least one other competitor, where the historical activity data includes data captured from at least ten practice sessions and / or competitions.

[0111] The processor(s) may further be configured to access skill level includes accessing historical data from at least ten practice sessions and / or competitions of rounds of golf. The processor(s) may further be configured to determine variation of each of the first and at least one other competitors from historical data using artificial intelligence to analyze the receivedactivity data from the skill-based activity competition from the first competitor and the at least one other competitor, and generate a notification in the event that the variation of one of the first competitor or the at least one other competitor is above fraud threshold.

[0112] The processor(s) may further be configured to, in response to determining that the variation is indicative of fraud, cause a mobile app being used by the first competitor and the at least one other competitor are using during the skill-based activity competition to be altered from normal operation. The processor(s) may further configured to, in response to determining that the variation is indicative of fraud, cause a wager to be invalidated and the first competitor or one of the at least one second competitor being disqualified.

[0113] The processor(s) may further be configured to generate variation data of each of the first and the at least one other competitor as produced by the artificial intelligence, and communicate the variation data to each of the first competitor and the at least one other competitor. The processor(s), in communicating the variation data to each of the first competitor and the at least one other competitor, may further be configured to communicate the variation data to a mobile application being executed on mobile devices of each of the first competitor and the at least one other competitor, thereby enabling the first competitor and the at least one other competitor to review the variation data.

[0114] The processor(s) may further be configured to enable each of the first competitor and the competitor(s) to submit a protest to an operator of the skill-based activity competition for adjudication as to whether the variation data is indicative of foul play via the mobile application. The processor(s) may further be configured to enable each of the first competitor and the other competitor(s) to submit a protest to an operator of the skill-based activity competition for adjudication as to whether an identity of the first competitor or the other competitor(s) is indicative of someone other than the first competitor or the other competitor(s) performing the skill-based activity in place of either the first competitor or the other competitor(s).

[0115] One embodiment of a system for conducting a skill-based activity competition may include at least one sensor configured to capture at least one first biometric parameter of a first competitor and a second competitor. At least one processor may be in communication with the sensor(s), and be configured to verify an identity of the first and second competitors, access handicap data of the first and second competitors of the skill-based activity, receive, during a competition, activity data from each of the first and second competitors, the activity data including a score of each of the first and second competitors, generate an adjusted scoreof the first and second competitors by applying the handicap data of the first and second competitors to the respective scores thereof, and determine a winner between the first and second competitors based on the adjusted score of the first and second competitors.

[0116] The handicap data may be produced by a common skill-based platform on which each of the first and second competitors have used to generate the handicap data. The processor(s) may further be configured to determine that the handicap data is certified by the common skill-based platform by verifying identity of each of the first and second competitors prior to and / or while the first and second competitors are generating the handicap data. In accessing the handicap data, the handicap data may be accessed from a common skill-based platform that is a simulator. The processor(s) may further be configured to enable the first and second competitors to submit a monetary wager. In response to determining the winner between the first and second competitors, the wager of a non-winning competitor may be awarded to the winning competitor by the processor(s).

[0117] In accessing the handicap data, the processor(s) may further be configured to access statistical data representative of each of the first and second competitor. The processor(s), in verifying an identity of the first and second competitors, may further be configured to use facial recognition of images captured of the competitors while competing in the skill-based activity. In verifying identities of the first and second competitors, the processor(s) may further include using artificial intelligence. The processor(s), in verifying an activity of the first and second competitors, may further be configured to use artificial intelligence to identify the first and second competitors based on “signature” motions of each of the respective first and second competitors.

[0118] The processor(s) may further be configured to access skill level of each of the first and second competitors as determined by historical activity data of each of the respective first and second competitors. The processor(s) may further be configured to determine variation from historical based on using artificial intelligence to analyze the received activity data from each of the first and second competitors. The processor(s) may further be configured to generate variation data of each of the first and second competitors as produced by the artificial intelligence, and communicate the variation data to each of the first and second competitors. In communicating the variation data to each of the first and second competitors, the variation data may be communicated to a mobile application being executed on mobile devices of each of the first and second competitors, thereby enabling the first and second competitors to review the variation data.

[0119] The processor(s) may further be configured to enable each of the first and second competitors to submit a protest to an operator of the skill-based activity competition for adjudication as to whether the variation data is indicative of foul play via the mobile application. The skill-based activity competition may be a peer-to-peer skill-based activity competition.

[0120] The processor(s) may further be configured to enable each of the first and second competitors to submit a protest to an operator of the skill-based activity competition for adjudication as to whether an identity of the first or second competitor is indicative of someone other than the first or second competitor performing the skill-based activity in place of either the first or second competitor.

[0121] One embodiment of a computer-implemented method of ensuring integrity of competitors participating in a skill-based activity competition may include accessing historical skill-based activity data sensed by at least one sensor of a competitor of the skillbased activity competition performing the skill-based activity prior to the skill-based activity competition. Skill-based activity data measured by the sensor(s) of the competitor performing the skill-based activity during the skill-based activity competition may be accessed. The historical skill-based activity data and measured skill-based activity data during the skillbased activity competition may be compared to validate (i) an identity of the competitor, and (ii) a difference of the historical skill-based activity data and measured skill-based activity data during the skill-based activity competition is within a statistical deviation range that is indicative of integrity of the competitor. In response to not validating identity of the competitor or that the difference of the historical skill-based activity data and measured skillbased activity data is outside of the statistical deviation range, a notification indicative of the competitor violating a role of the competition may be generated. The notification may be communicated to notify a second competitor and / or official of the skill-based activity competition to enable action against the violation of the rule to be performed.

[0122] Communicating the notification may include causing a protest selection feature on a user interface to be activated to enable the second competitor to select to initiate a formal protest against the competitor of the skill-based activity competition with the official of the skill-based activity competition. Comparison data that resulted in the difference of the historical activity data and measured skill-based activity data to be outside the statistical deviation range may be generated. The comparison data may be displayed. The process may further include automatically highlighting and / or annotating the comparison data that resultedin the difference of the historical activity data and measured skill-based activity data to be outside the statistical deviation range.

[0123] In an embodiment, video content of the competitor performing the skill-based activity during the skill-based activity competition may be captured. At least one video segment corresponding to the comparison data that resulted in the difference of the historical activity data may be determined and skill-based activity to be outside the statistical deviation range may be measured. The at least one video segment may be displayed.

[0124] At least one second video segment of the competitor performing the same skillbased activity from historical video content may be identified. The video segment(s) and second video segment(s) may be displayed in a format that enables a user to identify differences in the same skill-based activity between the historical video content and the captured video content of the competitor during the skill-based activity. In an embodiment, the format may be side-by-side, overlayed, sequential, or otherwise.

[0125] Generating comparison data may include executing an artificial intelligence (Al) model to generate the comparison data and determine that either or both of the identity of the competitor is not validated, and that the measured skill-based activity data is outside the statistical deviation.

[0126] Skill-based activity equipment being used by the competitor to perform the skillbased activity during the skill-based activity competition may be sensed. The sensing of the equipment may be weighted by a scale, sized by a camera and software, identified by capturing a label or other identifier of the equipment, or otherwise. Automatic determination as to whether the sensed skill-based activity equipment complies with regulations of the skillbased activity competition may be performed. In response to determining that the sensed skill-based activity equipment does not comply with regulations of the skill-based activity competition, a second notification indicative of the sensed skill-based activity equipment not complying with the regulations may be generated. Otherwise, the sensed skill -based activity equipment complies with the regulations may be recorded (e.g., stored in a non-transitory memory).

[0127] In response to determining that the identity of the competitor is not validated or that the difference of the historical activity data and measured skill-based activity data is outside the statistical deviation range, a user interface associated with the skill-based activity competition being used by the competitor from a first mode to a second mode may beautomatically transitioned. Automatically transitioning the user interface from a standard skill-based activity competition mode to a second mode may include automatically transitioning the user interface from a first mode to a questionnaire mode that prompts the competitor with questions related to the identity of the competitor and / or possible reasons as to why the difference being outside a statistical deviation range was determined. As opposed to a questionnaire mode, a mode in which a text entry field may be displayed for the competitor to enter information.

[0128] Prompting the competitor may include prompting the competitor as to whether the competitor (i) is using different equipment than used in generating the historical skill-based activity data, and (ii) took lessons or practiced in a manner that caused the competitive to change how the competitor performs the skill-based activity. Receiving measured skill-based activity data may include receiving measured skill-based activity data of the competitor playing golf. A handicap of the competitor may be to a score of the competitor in the skillbased activity competition.

[0129] The competitor may be enabled to submit an entry fee to enter the skill-based activity competition. Accessing skill-based activity data may include accessing skill-based activity data of a one-on-one competition between the competitor and one other competitor. The skill -based activity data measured by the sensor(s) may include accessing the skill-based activity data measured by the sensor(s) positioned or controlled to be positioned by the competitor. Accessing the skill-based activity data may be measured by the sensor(s) positioned in a robot, drone, mobile device, or portable sensor. A system that performs the computer-implemented method of ensuring integrity of competitors participating in a skillbased activity competition may be utilized.

[0130] One embodiment of a computer-implemented method for perform activity matching services may include capturing activity data of a participant of a skill-based activity while performing at least one skill of the skill-based activity. An artificial intelligence engine may process the activity data of the participant from the captured activity data to generate recommendations, the recommendations including at least one of equipment, trainer, instructor, and exercises. An application that enables the participant to receive the generated recommendations may be provided. The application may present the recommendations to the participant. Capturing activity data may include capturing golf activity data from a golf simulator.

[0131] The foregoing method descriptions and the process flow diagrams are provided merely as illustrative examples and are not intended to require or imply that the steps of the various embodiments must be performed in the order presented. As will be appreciated by one of skill in the art, the steps in the foregoing embodiments may be performed in any order. Words such as “then,” “next,” etc. are not intended to limit the order of the steps; these words are simply used to guide the reader through the description of the methods. Although process flow diagrams may describe the operations as a sequential process, many of the operations may be performed in parallel or concurrently. In addition, the order of the operations may be re-arranged. A process may correspond to a method, a function, a procedure, a subroutine, a subprogram, etc. When a process corresponds to a function, its termination may correspond to a return of the function to the calling function or the main function.

[0132] The various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the embodiments disclosed here may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

[0133] Embodiments implemented in computer software may be implemented in software, firmware, middleware, microcode, hardware description languages, or any combination thereof. A code segment or machine-executable instructions may represent a procedure, a function, a subprogram, a program, a routine, a subroutine, a module, a software package, a class, or any combination of instructions, data structures, or program statements. A code segment may be coupled to and / or in communication with another code segment or a hardware circuit by passing and / or receiving information, data, arguments, parameters, or memory contents. Information, arguments, parameters, data, etc. may be passed, forwarded, or transmitted via any suitable means including memory sharing, message passing, token passing, network transmission, etc.

[0134] The actual software code or specialized control hardware used to implement these systems and methods is not limiting of the invention. Thus, the operation and behavior of thesystems and methods were described without reference to the specific software code being understood that software and control hardware can be designed to implement the systems and methods based on the description here.

[0135] When implemented in software, the functions may be stored as one or more instructions or code on a non-transitory computer-readable or processor-readable storage medium. The steps of a method or algorithm disclosed here may be embodied in a processorexecutable software module which may reside on a computer-readable or processor-readable storage medium. A non-transitory computer-readable or processor-readable media includes both computer storage media and tangible storage media that facilitate transfer of a computer program from one place to another. A non-transitory processor-readable storage media may be any available media that may be accessed by a computer. By way of example, and not limitation, such non-transitory processor-readable media may comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other tangible storage medium that may be used to store desired program code in the form of instructions or data structures and that may be accessed by a computer or processor. Disk and disc, as used here, include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk, and Blu-ray disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media. Additionally, the operations of a method or algorithm may reside as one or any combination or set of codes and / or instructions on a non-transitory processor-readable medium and / or computer-readable medium, which may be incorporated into a computer program product.

[0136] The previous description is of at least one embodiment for implementing the invention, and the scope of the invention should not necessarily be limited by this description. The scope of the present invention is instead defined by the following claims.

Claims

CLAIMSWhat is claimed is:

1. A computer-implemented method for conducting a skill -based activity competition, said method comprising: accessing handicap data of a first competitor, the handicap data being derived from historical physical activity performance of the first competitor during practice and / or competition play of the skill-based activity as captured by at least one sensor; receiving, during the skill-based activity competition, data captured of the physical activity performed by the first competitor using the at least one sensor and a score achieved by the first competitor in performing the physical activity during the skill-based activity competition; computing a handicap-adjusted score of the first competitor by applying the handicap data to the score of the first competitor; and determining a winner of the skill-based activity by comparing the handicap- adjusted score of the first competitor with one or more handicap-adjusted scores of at least one respective other competitor.

2. The method according to claim 1, further comprising verifying, based on at least one biometric parameter, an identity of the first competitor.

3. The method according to claim 2, wherein verifying an identify of the first competitor further includes verifying the identity of the first competitor based at least in part on physical activity of the first player measured by the at least one sensor during the skillbased activity competition relative to the historical physical activity of the at least one player measured by the at least one sensor.

4. The method according to claim 1, wherein receiving data includes receiving data captured using the at least one sensor includes receiving data is the same at least one sensor used to capture of the physical activity during practice and / or competition play of the skill-based activity.

5. The method according to claim 1 , wherein receiving data includes receiving data from a simulator used by the first competitor during the skill-based activity competition.

6. The method according to claim 1, further comprising:424898-7681 -9471.1accessing second handicap data of a second competitor, the second handicap data being derived from historical physical activity performance of the second competitor during practice and / or competition play of the skill-based activity as captured by at least one second sensor; receiving, during the skill-based activity competition, second activity data captured of the physical activity performed by the second competitor using the at least one second sensor and a second score achieved by the second competitor in performing the physical activity during the skill-based activity competition; computing a second handicap-adjusted score of the second competitor by applying the second handicap data to the second score of the second competitor; and determining a winner of the skill-based activity competition between the first and second competitors by comparing the handicap-adjusted score of the first competitor and second handicap-adjusted score of the second competitor.

7. The method according to claim 1, wherein determining a winner of the skill-based activity includes determining a winner amongst the first competitor and the at least one other competitor that includes at least two other competitors in addition to the first competitor.

8. The method according to claim 1, wherein accessing handicap data includes accessing handicap data produced by a common skill-based simulator on which the first competitor used to generate the handicap data using the at least one sensor.

9. The method according to claim 8, wherein accessing the handicap data includes determining that the handicap data is certified by the common skill-based simulator by verifying identity of the first competitor prior to and / or while the first competitor is generating the handicap data.

10. The method according to claim 8, wherein accessing the handicap data includes accessing the handicap data from a system in communication with sensors disposed at a physical location at which the skill-based activity is performed.

11. The method according to claim 10, wherein accessing the handicap data in communication from a system with sensors disposed at a physical location includes accessing the handicap data from a system with sensors disposed at a golf course.

12. The method according to claim 1, further comprising enabling the first competitor to submit a monetary wager directly against a second competitor of the at least one other competitors, and enabling the second competitor to submit a second monetary wager.

13. The method according to claim 12, further comprising, in response to determining the winner between the first and second competitors, awarding the wager of a nonwinning first or second competitor to the winning first or second competitor.

14. The method according to claim 1, further comprising enabling the first competitor to submit an entry fee for entry into the skill -based competition with a plurality of other competitors, and enabling the plurality of other competitors to submit the entry fee.

14. The method according to claim 1, wherein accessing the handicap data includes accessing statistical data representative of the first competitor.

15. The method according to claim 1, wherein verifying an identity of the first competitor includes using facial recognition of images captured of the first competitor while competing in the skill-based activity.

16. The method according to claim 15, wherein verifying identity of the first competitor includes using artificial intelligence to determine the identity of the first competitor.

17. The method according to claim 1, wherein verifying an activity of the first competitor includes using artificial intelligence to identify the first competitor based on “signature” motions of the first competitor.

18. The method according to claim 1, further comprising accessing a player profile of the first competitor and the at least one other competitor as determined by historical activity data of each of the respective first competitor and at least one other competitor, wherein the historical activity data includes data captured from at least ten practice sessions and / or competitions.

19. The method according to clam 18, wherein accessing skill level includes accessing historical data from at least ten practice sessions and / or competitions of rounds of golf.

20. The method according to claim 1, further comprising: determining variation of each of the first and at least one other competitors from historical data using artificial intelligence to analyze the received activity datafrom the skill-based activity competition from the first competitor and the at least one other competitor; and generating a notification in the event that the variation of one of the first competitor or the at least one other competitor is above fraud threshold.

21. The method according to claim 20, further comprising, in response to determining that the variation is indicative of fraud, causing a mobile app being used by the first competitor and the at least one other competitor are using during the skill-based activity competition to be altered from normal operation.

22. The method according to claim 20, further comprising, in response to determining that the variation is indicative of fraud, causing a wager to be invalidated and the first competitor or one of the at least one second competitor being disqualified.

23. The method according to claim 20, further comprising: generating variation data of each of the first and the at least one other competitor as produced by the artificial intelligence; and communicating the variation data to each of the first competitor and the at least one other competitor.

24. The method according to claim 20, wherein communicating the variation data to each of the first competitor and the at least one other competitor includes communicating the variation data to a mobile application being executed on mobile devices of each of the first competitor and the at least one other competitor, thereby enabling the first competitor and the at least one other competitor to review the variation data.

25. The method according to claim 24, further comprising enabling each of the first competitor and the at least one other competitor to submit a protest to an operator of the skill-based activity competition for adjudication as to whether the variation data is indicative of foul play via the mobile application.

26. The method according to claim 1, further comprising enabling each of the first competitor and the at least one other competitor to submit a protest to an operator of the skill-based activity competition for adjudication as to whether an identity of the first competitor or the at least one other competitor is indicative of someone other than the first competitor or the at least one other competitor performing the skill-based activity in place of either the first competitor or the at least one other competitor.

27. A system for conducting a skill-based activity competition, said system comprising:an input / output (I / O) unit in communication with a network; and at least one processor in communication with the I / O unit, and configured to: access handicap data of a first competitor, the handicap data being derived from historical physical activity performance of the first competitor during practice and / or competition play of the skill-based activity as captured by at least one sensor; receive, during the skill-based activity competition, data captured of the physical activity performed by the first competitor using the at least one sensor and a score achieved by the first competitor in performing the physical activity during the skill -based activity competition; compute a handicap-adjusted score of the first competitor by applying the handicap data to the score of the first competitor; and determine a winner of the skill-based activity by comparing the handicap- adjusted score of the first competitor with one or more handicap-adjusted scores of at least one respective other competitor.

28. The system according to claim 27, wherein the at least one processor is further configured to verify, based on at least one biometric parameter, an identity of the first competitor.

29. The system according to claim 28, wherein the at least one processor, in verifying an identify of the first competitor, is further configured to verify the identity of the first competitor based at least in part on physical activity of the first competitor measured by the at least one sensor during the skill-based activity competition relative to the historical physical activity of the competitor measured by the at least one sensor.

30. The system according to claim 27, wherein the at least one processor, in receiving data, is further configured to receive data captured using the at least one sensor includes receiving data is the same at least one sensor used to capture of the physical activity during practice and / or competition play of the skill-based activity.

31. The system according to claim 27, wherein the at least one processor, in receiving data, is further configured to receive data from a simulator used by the first competitor during the skill-based activity competition.

32. The system according to claim 27, wherein the processor is further configured to: access second handicap data of a second competitor, the second handicap data being derived from historical physical activity performance of the second competitor during practice and / or competition play of the skill-based activity as captured by at least one second sensor; receive, during the skill-based activity competition, second activity data captured of the physical activity performed by the second competitor using the at least one second sensor and a second score achieved by the second competitor in performing the physical activity during the skill-based activity competition; compute a second handicap-adjusted score of the second competitor by applying the second handicap data to the second score of the second competitor; and determine a winner of the skill-based activity competition between the first and second competitors by comparing the handicap-adjusted score of the first competitor and second handicap-adjusted score of the second competitor.

33. The system according to claim 27, wherein the processor, in determining a winner of the skill-based activity, is further configured to determine a winner amongst the first competitor and the at least one other competitor that includes at least two other competitors in addition to the first competitor.

34. The system according to claim 27, wherein the processor, in accessing handicap data, is further configured to access handicap data produced by a common skill-based simulator on which the first competitor used to generate the handicap data using the at least one sensor.

35. The system according to claim 34, wherein the processor, in accessing the handicap data, is further configured to determine that the handicap data is certified by the common skill-based simulator by verifying identity of the first competitor prior to and / or while the first competitor is generating the handicap data.

36. The system according to claim 34, wherein the processor, in accessing the handicap data, is further configured to access the handicap data from a system in communication with sensors disposed at a physical location at which the skill-based activity is performed.

37. The system according to claim 36, wherein the processor, in accessing the handicap data in communication from a system with sensors disposed at a physical location, isfurther configured to include accessing the handicap data from a system with sensors disposed at a golf course.

38. The system according to claim 27, wherein the at least one processor is further configured to enable the first competitor to submit a monetary wager directly against a second competitor of the at least one other competitors, and enabling the second competitor to submit a second monetary wager.

39. The system according to claim 38, wherein the at least one processor is further configured to, in response to determining the winner between the first and second competitors, award the wager of a non-winning first or second competitor to the winning first or second competitor.

40. The system according to claim 27, wherein the at least one processor is further configured to enable the first competitor to submit an entry fee for entry into the skillbased competition with a plurality of other competitors, and enabling the plurality of other competitors to submit the entry fee.

41. The system according to claim 27, wherein the at least one processor, in accessing the handicap data, is further configured to include accessing statistical data representative of the first competitor.

42. The system according to claim 27, wherein the at least one processor, in verifying an identity of the first competitor, is further configured to include using facial recognition of images captured of the first competitor while competing in the skill-based activity.

43. The system according to claim 42, wherein the at least one processor, in verifying identity of the first competitor, is further configured to use artificial intelligence to determine the identity of the first competitor.

44. The system according to claim 27, wherein the at least one processor, in verifying an activity of the first competitor, is further configured to include using artificial intelligence to identify the first competitor based on “signature” motions of the first competitor.

45. The system according to claim 27, wherein the at least one processor is further configured to access a player profile of the first competitor and the at least one other competitor as determined by historical activity data of each of the respective firstcompetitor and at least one other competitor, wherein the historical activity data includes data captured from at least ten practice sessions and / or competitions.

46. The system according to clam 45, wherein the at least one processor is further configured to access skill level includes accessing historical data from at least ten practice sessions and / or competitions of rounds of golf.

46. The system according to claim 27, wherein the at least one processor is further configured to: determine variation of each of the first and at least one other competitors from historical data using artificial intelligence to analyze the received activity data from the skill-based activity competition from the first competitor and the at least one other competitor; and generate a notification in the event that the variation of one of the first competitor or the at least one other competitor is above fraud threshold.

47. The system according to claim 46, wherein the at least one processor is further configured to, in response to determining that the variation is indicative of fraud, cause a mobile app being used by the first competitor and the at least one other competitor are using during the skill-based activity competition to be altered from normal operation.

48. The system according to claim 46, wherein the at least one processor is further configured to, in response to determining that the variation is indicative of fraud, cause a wager to be invalidated and the first competitor or one of the at least one second competitor being disqualified.

49. The system according to claim 46, wherein the at least one processor is further configured to: generate variation data of each of the first and the at least one other competitor as produced by the artificial intelligence; and communicate the variation data to each of the first competitor and the at least one other competitor.

50. The system according to claim 46, wherein the at least one processor, in communicating the variation data to each of the first competitor and the at least one other competitor, is further configured to communicate the variation data to a mobile application being executed on mobile devices of each of the first competitor and theat least one other competitor, thereby enabling the first competitor and the at least one other competitor to review the variation data.

51. The system according to claim 50, wherein the at least one processor is further configured to enable each of the first competitor and the at least one other competitor to submit a protest to an operator of the skill-based activity competition for adjudication as to whether the variation data is indicative of foul play via the mobile application.

52. The system according to claim 27, wherein the at least one processor is further configured to enable each of the first competitor and the at least one other competitor to submit a protest to an operator of the skill-based activity competition for adjudication as to whether an identity of the first competitor or the at least one other competitor is indicative of someone other than the first competitor or the at least one other competitor performing the skill-based activity in place of either the first competitor or the at least one other competitor.

53. A computer-implemented method of ensuring integrity of competitors participating in a skill-based activity competition, comprising: accessing historical skill-based activity data sensed by at least one sensor of a competitor of the skill-based activity competition performing the skill-based activity prior to the skill-based activity competition; accessing skill-based activity data measured by the at least one sensor of the competitor performing the skill-based activity during the skill-based activity competition; comparing the historical skill-based activity data and measured skill-based activity data during the skill-based activity competition to validate: an identity of the competitor; and a difference of the historical skill-based activity data and measured skillbased activity data during the skill-based activity competition is within a statistical deviation range that is indicative of integrity of the competitor; in response to not validating identity of the competitor or that the difference of the historical skill-based activity data and measured skill-based activity data is outside of the statistical deviation range, generating a notification indicative of the competitor violating a role of the competition; andcommunicating the notification to notify a second competitor and / or official of the skill-based activity competition to enable action against the violation of the rule to be performed.

54. The method according to claim 53, wherein communicating the notification includes causing a protest selection feature on a user interface to be activated to enable the second competitor to select to initiate a formal protest against the competitor of the skill-based activity competition with the official of the skill-based activity competition.

55. The method according to claim 53, further comprising: generating comparison data that resulted in the difference of the historical activity data and measured skill-based activity data to be outside the statistical deviation range; and displaying the comparison data.

56. The method according to claim 55, further comprising automatically highlighting and / or annotating the comparison data that resulted in the difference of the historical activity data and measured skill-based activity data to be outside the statistical deviation range.

57. The method according to claim 56, further comprising: capturing video content of the competitor performing the skill-based activity during the skill-based activity competition; determining at least one video segment corresponding to the comparison data that resulted in the difference of the historical activity data and measured skillbased activity to be outside the statistical deviation range; and displaying the at least one video segment.

58. The method according to claim 57, further comprising: identifying at least one second video segment of the competitor performing the same skill -based activity from historical video content; and displaying the at least one video segment and at least one second video segment in a format that enables a user to identify differences in the same skill-based activity between the historical video content and the captured video content of the competitor during the skill -based activity.

59. The method according to claim 58, wherein generating comparison data includes executing an artificial intelligence (Al) model to generate the comparison data and determine that either or both of the identity of the competitor is not validated, and that the measured skill-based activity data is outside the statistical deviation.

60. The method according to claim 53, further comprising: sensing skill-based activity equipment being used by the competitor to perform the skill-based activity during the skill-based activity competition; automatically determining whether the sensed skill-based activity equipment complies with regulations of the skill-based activity competition; and in response to determining that the sensed skill-based activity equipment does not comply with regulations of the skill-based activity competition, generating a second notification indicative of the sensed skill-based activity equipment not complying with the regulations, otherwise, recording that the sensed skillbased activity equipment complies with the regulations.

61. The method according to claim 53, further comprising, in response to determining that the identity of the competitor is not validated or that the difference of the historical activity data and measured skill-based activity data is outside the statistical deviation range, automatically transitioning a user interface associated with the skill-based activity competition being used by the competitor from a first mode to a second mode.

62. The method according to claim 61, wherein automatically transitioning the user interface from a standard skill-based activity competition mode to a second mode includes automatically transitioning the user interface from a first mode to a questionnaire mode that prompts the competitor with questions related to the identity of the competitor and / or possible reasons as to why the difference being outside a statistical deviation range was determined.

63. The method according to claim 62, wherein prompting the competitor includes prompting the competitor as to whether the competitor (i) is using different equipment than used in generating the historical skill-based activity data, and (ii) took lessons or practiced in a manner that caused the competitive to change how the competitor performs the skill-based activity.

64. The method according to claim 53, wherein receiving measured skill-based activity data includes receiving measured skill-based activity data of the competitor playing golf.

65. The method according to claim 53, further comprising applying a handicap of the competitor to a score of the competitor in the skill-based activity competition.

66. The method according to claim 53, further comprising enabling the competitor to submit an entry fee to enter the skill-based activity competition.

67. The method according to claim 53, wherein accessing skill-based activity data includes accessing skill -based activity data of a one-on-one competition between the competitor and one other competitor.

68. The method according to claim 53, wherein accessing the skill-based activity data measured by the at least one sensor includes accessing the skill-based activity data measured by the at least one sensor positioned or controlled to be positioned by the competitor.

69. The method according to claim 68, wherein accessing the skill-based activity data measured by the at least one sensor is positioned in a robot, drone, mobile device, or portable sensor.

70. A computer-implemented method for perform activity matching services, said method comprising: capturing activity data of a participant of a skill-based activity while performing at least one skill of the skill-based activity; processing, using an artificial intelligence engine, the activity data of the participant from the captured activity data to generate recommendations, the recommendations including at least one of equipment, trainer, instructor, and exercises; providing an application that enables the participant to receive the generated recommendations; and presenting, by the application, the recommendations to the participant.

71. The method according to claim 70, wherein capturing activity data includes capturing golf activity data from a golf simulator.

Images