Patent Application
20250135282
Various embodiments of the present disclosure relate generally to methods and systems for rating abilities of players on a sports teams.
Assigning a measure of ability to a player on a sports teams, for example, players on soccer teams across the globe, is a vital ingredient for accurate predictions across the sport. From predicting a win probability of a match to predicting a number of shots that a player is expected to make, knowing the ability of the player on the teams involved in a game is helpful. To leverage these models over a large scale in the ever-growing landscape of the sport, it is helpful that these player ability ratings are rolled out at a huge scale across both the men's and the women's games.
Deploying ratings at scale can be a challenging task. For example, a majority of soccer matches are between teams within the same domestic league. This makes judging team and player quality within a league relatively simple. However, due to a lack of matches outside of domestic leagues, comparison of team and player quality from different leagues, countries and in particular continents, can be more challenging. This difficulty is exacerbated in women's soccer, where there is a wider range of team and player ability and even fewer matches between teams from different leagues, countries, and continents.
The present disclosure is directed to overcoming one or more of these above-referenced challenges. The introduction description provided herein is for the purpose of generally presenting the context of the disclosure.
In some embodiments, a method is disclosed herein. The method generates a dynamic rating for an entity and rearranging an icon associated with the entity on a graphical user interface (GUI) of a computer system. The computer system receives, via one or more data sources, a first set of data associated with one or more parameters for the entity. The computer system calculates, via a deterministic algorithm, a plurality of ability scores based on the first set of data associated with the one or more parameters. The computer system generates, via the deterministic algorithm, a first player rating based on each ability score of the plurality of ability scores. The computer system dynamically adjusts, via the deterministic algorithm, the plurality of ability scores based on receiving a second set of data associated with the one or more parameters for the entity. The computer system updates, via the deterministic algorithm, the first player rating based on the adjusted plurality of ability scores. The computer system automatically rearranges the icon to a position above or below a current position of the icon on the GUI based on the updated first player rating.
In some embodiments, a method is disclosed herein. The method generates an overall rating for an entity. A computer system receives, via one or more data sources, a first set of data associated with an entity. The computer system calculates, via a deterministic algorithm, a first plurality of ability scores based on the first set of data associated with one or more parameters. The computer system generates, via the deterministic algorithm, a first rating based on each ability score of the first plurality of ability scores. The computer system calculates, via the deterministic algorithm, a second plurality of ability scores based on the first set of data associated with the one or more parameters. The computer system generates, via the deterministic algorithm, a second rating based on each ability score of the second plurality of ability scores and the first rating. The computer system dynamically adjusts, via the deterministic algorithm, the first plurality of ability scores and the second plurality of ability scores based on receiving a second set of data associated with the one or more parameters for the entity. The computer system updates, via the deterministic algorithm, the first rating and the second rating based on the adjusted plurality of ability scores. The computer system automatically rearranges an icon to a position above or below a current position of the icon on a graphical user interface (GUI) based on the updated second rating.
In some embodiments, a system is disclosed herein. The system includes a processor and a memory. The memory has programming instructions stored thereon, which, when executed by the processor, performs operations. The operations include generating a dynamic rating for an entity and rearranging an icon associated with the entity on a graphical user interface (GUI). The operations further include receiving, via one or more data sources, a first set of data associated with one or more parameters for the entity. The operations further include calculating, via a deterministic algorithm, a plurality of ability scores based on the first set of data associated with the one or more parameters. The operations further include generating, via the deterministic algorithm, a first player rating based on each ability score of the plurality of ability scores. The operations further include dynamically adjusting, via the deterministic algorithm, the plurality of ability scores based on receiving a second set of data associated with the one or more parameters for the entity. The operations further include updating, via the deterministic algorithm, the first player rating based on the adjusted plurality of ability scores. The operations further include automatically rearranging the icon to a position above or below a current position of the icon on the GUI based on the updated first player rating.
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate various exemplary embodiments and together with the description, serve to explain the principles of the disclosed aspects.
Notably, for simplicity and clarity of illustration, certain aspects of the figures depict the general configuration of the various embodiments. Descriptions and details of well-known features and techniques may be omitted to avoid unnecessarily obscuring other features. Elements in the figures are not necessarily drawn to scale; the dimensions of some features may be exaggerated relative to other elements to improve understanding of the example embodiments.
The general discussion of this disclosure provides a brief, general description of a suitable computing environment in which the present disclosure may be implemented. In one embodiment, any of the disclosed systems, methods, and/or graphical user interfaces may be executed by or implemented by a computing system consistent with or similar to that depicted and/or explained in this disclosure. Although not required, aspects of the present disclosure are described in the context of computer-executable instructions, such as routines executed by a data processing device, e.g., a server computer, wireless device, and/or personal computer. Those skilled in the relevant art will appreciate that aspects of the present disclosure can be practiced with other communications, data processing, or computer system configurations, including: Internet appliances, hand-held devices (including personal digital assistants (“PDAs”)), wearable computers, all manner of cellular or mobile phones (including Voice over IP (“VoIP”) phones), dumb terminals, media players, gaming devices, virtual reality devices, multi-processor systems, microprocessor-based or programmable consumer electronics, set-top boxes, network PCs, mini-computers, mainframe computers, and the like. Indeed, the terms “computer,” “server,” and the like, are generally used interchangeably herein, and refer to any of the above devices and systems, as well as any data processor.
Aspects of the present disclosure may be embodied in a special purpose computer and/or data processor that is specifically programmed, configured, and/or constructed to perform one or more of the computer-executable instructions explained in detail herein. While aspects of the present disclosure, such as certain functions, are described as being performed exclusively on a single device, the present disclosure may also be practiced in distributed environments where functions or modules are shared among disparate processing devices, which are linked through a communications network, such as a Local Area Network (“LAN”), Wide Area Network (“WAN”), and/or the Internet. Similarly, techniques presented herein as involving multiple devices may be implemented in a single device. In a distributed computing environment, program modules may be located in both local and/or remote memory storage devices.
Aspects of the present disclosure may be stored and/or distributed on non-transitory computer-readable media, including magnetically or optically readable computer discs, hard-wired or preprogrammed chips (e.g., EEPROM semiconductor chips), nanotechnology memory, biological memory, or other data storage media. Alternatively, computer implemented instructions, data structures, screen displays, and other data under aspects of the present disclosure may be distributed over the Internet and/or over other networks (including wireless networks), on a propagated signal on a propagation medium (e.g., an electromagnetic wave(s), a sound wave, etc.) over a period of time, and/or they may be provided on any analog or digital network (packet switched, circuit switched, or other scheme).
Program aspects of the technology may be thought of as “products” or “articles of manufacture” typically in the form of executable code and/or associated data that is carried on or embodied in a type of machine-readable medium. “Storage” type media include any or all of the tangible memory of the computers, processors or the like, or associated modules thereof, such as various semiconductor memories, tape drives, disk drives and the like, which may provide non-transitory storage at any time for the software programming. All or portions of the software may at times be communicated through the Internet or various other telecommunication networks. Such communications, for example, may enable loading of the software from one computer or processor into another, for example, from a management server or host computer of the mobile communication network into the computer platform of a server and/or from a server to the mobile device. Thus, another type of media that may bear the software elements includes optical, electrical and electromagnetic waves, such as used across physical interfaces between local devices, through wired and optical landline networks and over various air-links. The physical elements that carry such waves, such as wired or wireless links, optical links, or the like, also may be considered as media bearing the software. As used herein, unless restricted to non-transitory, tangible “storage” media, terms such as computer or machine “readable medium” refer to any medium that participates in providing instructions to a processor for execution.
The terminology used above may be interpreted in its broadest reasonable manner, even though it is being used in conjunction with a detailed description of certain specific examples of the present disclosure. Indeed, certain terms may even be emphasized above; however, any terminology intended to be interpreted in any restricted manner will be overtly and specifically defined as such in this Detailed Description section. Both the foregoing general description and the detailed description are exemplary and explanatory only and are not restrictive of the features.
As used herein, the terms “comprises,” “comprising,” “having,” including,” or other variations thereof, are intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements, but may include other elements not expressly listed or inherent to such a process, method, article, or apparatus.
In this disclosure, relative terms, such as, for example, “about,” “substantially,” “generally,” and “approximately” are used to indicate a possible variation of ±10% in a stated value.
The term “exemplary” is used in the sense of “example” rather than “ideal.” As used herein, the singular forms “a,” “an,” and “the” include plural reference unless the context dictates otherwise.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. It is intended that the specification and examples be considered as exemplary only.
Various embodiments of the present disclosure relate generally to rating abilities of players and teams in sports. As discussed above, existing systems suffer from deficiencies. For example, none of the existing approaches apply the rating system at anywhere near the same scale as those described herein, or across men's and/or women's soccer, for example. In the context of soccer in particular, the rating system disclosed herein may be built worldwide across both men's (13,000+ teams across 183 different countries and 413 leagues) and women's (2,000+ teams across 68 different countries and 140 leagues).
While soccer is used as an example, disclosed techniques are equally applicable to other team sports such as football, basketball, cricket, rugby, baseball, and so forth.
Disclosed techniques can employ algorithmic and/or machine-learning approaches.
Technical advantages of the disclosed techniques include improvements to rating reports for sports matches. For instance, certain aspects relate to determining representative parameters and ratings from a multitude of data sources in order to improve the performance, accuracy, and results of information to be mapped to play graphics. In doing so, disclosed techniques provide improvements relative to existing solutions. The techniques disclosed herein improve rating reports for sports matches by, for example, generating as well as dynamically adjusting and refining ratings for a sports team based on one or more of player performance data, match reports, and/or designated parameters in a hierarchical structure. By employing such a process that dynamically adjust and refines ratings for a sports team in a hierarchical structure, the scope and breadth of the number of sports teams that can be rated is vastly improved and the data considered in generating and adjusting ratings for a sports team, thereby resulting in more accurate rating reports for sports matches as well as the ability to more accurately predict the result of a sports match. Accordingly, the techniques disclosed herein apply technological solutions for generating team ratings using a hierarchical structure in an efficient and scalable manner that would not otherwise be possible without such technical solutions.
As used herein, a “machine learning model” generally encompasses instructions, data, and/or a model configured to receive input, and apply one or more of a weight, bias, classification, or analysis on the input to generate an output. The output may include, for example, a classification of the input, an analysis based on the input, a design, process, prediction, or recommendation associated with the input, or any other suitable type of output. A machine learning model is generally trained using training data, e.g., experiential data and/or samples of input data, which are fed into the model in order to establish, tune, or modify one or more aspects of the model, e.g., the weights, biases, criteria for forming classifications or clusters, or the like. Aspects of a machine learning model may operate on an input linearly, in parallel, via a network (e.g., a neural network), or via any suitable configuration.
The execution of the machine learning model may include deployment of one or more machine learning techniques, such as generative learning, linear regression, logistic regression, random forest, gradient boosted machine (GBM), deep learning, graphical neural network (GNN), and/or a deep neural network. Supervised and/or unsupervised training may be employed. For example, supervised learning may include providing training data and labels corresponding to the training data, e.g., as ground truth. Unsupervised approaches may include clustering, classification or the like. K-means clustering or K-Nearest Neighbors may also be used, which may be supervised or unsupervised. Combinations of K-Nearest Neighbors and an unsupervised cluster technique may also be used. Any suitable type of training may be used, e.g., stochastic, gradient boosted, random seeded, recursive, epoch or batch-based, etc.
While several of the examples herein involve certain types of machine learning, it should be understood that techniques according to this disclosure may be adapted to any suitable type of machine learning. It should also be understood that the examples above are illustrative only. The techniques and technologies of this disclosure may be adapted to any suitable activity.
Compared to the prior art, disclosed techniques herein offer advantages such as (1) being able to analyze as many sports teams as possible and (2) being able to provide ratings for both men's and women's sports teams.
Disclosed systems rely on a team ability ratings system which is flexible enough to provide ratings to any sports team and enable comparison of sports teams within the same sport from any league in the world. For example, both men's soccer (13,000+ teams across 183 different countries and 413 leagues) and/or women's soccer (2,000+ teams across 68 different countries and 140 leagues) teams may be rated and although their rating systems are run separately, the same or similar algorithm may be used for both.
To cover as many teams as possible, an ability rating system is built using match final score data. Many leagues do not have detailed in-game information; hence the rating system may not rely upon detailed in-game match data needed to obtain the desired breadth of coverage in the rating system.
The rating system may ensure that the system is built in a way that there is no need to change the framework for men's and women's soccer. The ratings of men's teams may not be compared with those of women's teams, as the systems may be separate. However, the rating systems may use similar methods and/or may learn from each other.
Disclosed systems can adapt quickly across all teams worldwide. The rating system enables rating change to quickly propagate between leagues and across continents. Certain leagues have very little cross-pollination with other leagues, countries, and continents, and thus a need exists to be able to compare sports teams worldwide using a fair easily digestible system. Additionally, as teams move between leagues, the rating system may adjust their rating going into their new season accordingly.
As an example, an Elo rating system may be used. Elo ratings may be a rating system used, for example, in sports such as chess. This system updates ability ratings after each match by comparing a pre-game expected result based on the pre-game ratings of each player/team, and the actual result of that match. If a player/team performs worse than the expected result, then the player/team loses rating (e.g., is associated with a relatively worse rating).
The better a team is, the easier it is for them to lose rating through poor results, since their pre-game win expectancy will usually be high. Elo may be a zero-sum system. In other words, whichever one team in the match gain or lose in Elo rating, the other team may have an opposite change in Elo rating. For example, one team loses 20 rating points, then the other team will then gain 20 rating points.
Ensuring that the rating system is flexible across a huge pool of teams worldwide, in which very few teams from different leagues, countries and continents that will ever play each other to provide with reliable comparative information. To solve this issue, a hierarchical ability rating system may be used, which assign ability scores to each continent, country, league, and team. To obtain a final ability score, these four ratings are summed together. Although four ratings are provided as an example, it will be understood that any applicable number of ratings may be applied. For example, take Arsenal Football Club in the top tier of England (Premier League). Their ability rating will be a sum of four separate ability ratings for their continent, country, league, and within-league ability.
The within-league team level of the hierarchy has its Elo rating adjusted for every game. However, the league, country and continent levels may be adjusted when a game takes place between teams in different elements of that hierarchy. Only the highest level of the hierarchy may be affected. The following are examples of the Elo rating adjustment.
Example 1: Manchester United Women vs Manchester City Women in the English Women's Super League. In this case, both team's within-league ratings may be updated without updating any other hierarchy value as they are all the same (same league, country and continent for both teams).
Example 2: Manchester City (English Premier League) vs York City (English National League North) in the FA Cup. In this case, both team's within-league rating scores may be updated but along with adjusting their league ratings (Premier League and Nation League North).
Example 3: Manchester United vs Manchester City (both English Premier League teams) playing in the FA Cup. In this case, both team's within-league ratings may be updated but without updating any other hierarchy value since they are still from the same league even though they are playing in a different competition.
Example 4: Manchester City Women (English Women's Super League) vs FC Barcelona Femeni (Spanish Women's Primera Division) in the UEFA Women's Champions League. In this case, both team's within-league rating and both England's and Spain's ratings may be updated. The league rating may not be updated since only the highest level of the hierarchy affected may be altered (apart from within-league rating which is always updated).
Example 5: Manchester City (English Premier League) vs Vasco da Gama (Campeonato Brasileiro Série A) in the FIFA Club World Cup. We update both team's within-league rating along with the European and South American continent ratings. We do not alter the league or country ratings as we only adjust the highest level of the hierarchy affected (apart from within-league rating which is always updated).
When an update is applied to more than just the within-league team rating, a proportion of the rating change from the match to the higher-level hierarchy may be applied. In the final example above, say the Elo rating change from the final result is +50 for Manchester City, then a percentage of that 50 rating points may go to Manchester City's within-league team score, and the remaining to the European continent rating (and taken away from the South American continent rating). This percentage is a model parameter and can be changed for league, country, and continents. 100% of the rating change from a within-league match may go to the teams.
When teams move leagues, there is a need to ensure that their new pre-season rating makes sense within the context of their new league. Typically, when teams move league, their ability will change quite drastically due to either getting more money through promotion, or less money through relegation. In addition, some leagues can be easier to move between than others, so there needs a model that is general enough to provide a reasonable approximation to the initial performance of a team when moving leagues.
To do this, a league change adjustment calculation may be added to the method. An example is provided for exemplary purposes. For example, teams moving into and out of the English Championship—the 2nd tier of the English football system. The adjustment calculation is based on percentiles of the within-league ratings from the league that the team that is being adjusted is moving into. Recall that the final team rating includes the league rating which will consequently change for teams moving leagues. Therefore, what will need adjustment is the within-league ability score.
For example, three teams are promoted from the Championship (tier 2—England) into the Premier League (tier 1—England) for the 2021/2022 season. The newly promoted teams are assumed to be relatively weak in the new league. Hence, their within-league ratings is adjusted based on a low percentile of Premier League within-league team ratings from the 2020/2021 season. The percentile is a model parameter that can be adjusted for each league based on historical knowledge of how easy the transition has been for teams moving between these leagues in the past.
For promotion into the new league, all the newly promoted team's within-league ratings may be multiplied by a constant, which ensures that their new average within-league rating is equal to the low-percentile within-league rating of the league above (most commonly 25th percentile). For teams being relegated, it's the same approach except that the percentile value of previous season within-league rating is higher (most commonly 75th percentile). Hence, it may be ensured that the relegated teams new within-league ratings are on average a high percentile in the new league (e.g., will be on average a high ability team in the new league).
The advantage of this approach is that previous season performance in the newly adjusted ratings (e.g. champions of a league should have a better ratings than the other promoted teams) are accounted for, but also centering the ability of new teams on a likely performance level, which may be optimized in model training.
In some examples, not all games are of equal importance. For instance, playing in the Community Shield is less important than the Champions League final. Hence, there needs to be accounting for this in how certain games impact the potential change of ability rating for teams, leagues, countries, and continents.
To do this, a match importance factor may be included in the rating method, which adjusts the “importance value” within the Elo calculation. This value controls how much rating is available to trade in a match, with a higher importance meaning a team can gain or lose more rating, and a lower importance meaning you cannot gain or lose as much. For example, the importance may be adjusted in two ways:
Competition-based match importance. This is based on the type of competition that the match is being played in. For example, domestic leagues and between-country competitions are typically more important than domestic cup competitions.
Game week-based match importance. The game week is which game of the season that this is for each team. In this case, more importance is assigned to the first 9 game weeks within domestic leagues. Although these games might not be more important for the teams involved, they are more important for the method to learn changing team performance based on pre-season expectations. This could be due to new players and is particularly important for teams which have just moved league and have gone through the promotion/relegation rating adjustment.
Further, as team-level Elo models attempt to quantify team ability by modelling a team's results, a player-level Elo model attempts to quantify player ability based on the results of their team when that player features on the pitch. This can provide a universal player quality index which can rank all players in the world. These could also be used to improve the accuracy of Pre-Game/Live Win Probability predictions in games without full strength squad like, for example, cup games where team-based Elo is a poor representation (e.g., when Aston Villa beat Liverpool 5-0 in the Carabao Cup in 2019 after Liverpool fielded the youngest side in their history in response to their senior team having to play another game in Qatar<24 hours later), or games where an important player is unavailable.
For example, using only the 2013/14-2020/21 seasons of the English Premier League, initializing Player Elo with their club's Team Elo when they first appear in the dataset and updating Player Elo game-by-game based on: i) the number of minutes played by a player in the game, ii) the expected score line based upon the difference in Team Elo between the player's team and the opposition team, and iii) the observed goal difference of their team at full time. The target of observed goal difference could alternatively be expected goals (xG) instead of observed goals, and could alternatively account for the result when the player was on the pitch.
Disclosed techniques can scale the final rating scores of each team to make a digestible number for public use. For example, in the case of a Power Ranking system, the final rating score of each team may be taken and then both power and min/max scaler transformers may be utilized to create a 0-100 rating score for each team, where the best team in the world on any given day is scored 100 (and the worst 0).
As discussed herein, one or more machine learning models may be trained to understand a sports language. Accordingly, machine learning models disclosed herein are sports machine learning models. Such sports machine learning models may be trained using sports related data (e.g., tracking data, event data, etc., as discussed herein). A sports machine learning model trained to understand a sports language based on sports related data may be trained to adjust one or more weights, layers, nodes, biases, and/or synapses based on the sports related data. A sports machine learning model may include components (e.g., a weights, layers, nodes, biases, and/or synapses) that collectively associate one or more of: a player with a team or league; a team with a player or league; a score with a team; a scoring event with a player; a sports event with a player or team; a win with a player or team; a loss with a player or team; and/or the like. A sports machine learning model may correlate sports information and statistics in a competition landscape. A sports machine learning model may be trained to adjust one or more weights, layers, nodes, biases, and/or synapses to associate certain sports statistics in view of a competition landscape. For example, a win indicator for a given team may automatically correlated with a loss indicator for an opposing team. As another example, a score static may be considered a positive attribution for a scoring team and a negative attribution for a team being scored upon. As another example, a given score may be ranked against one or more scores based on a relative position of the score in comparison to the one or more other scores.
A sports machine learning model may be trained based on sports tracking and/or event data, as discussed herein. Such data may include player and/or object position information, movement information, trends, and changes. For example, a sports machine learning model may be trained by modifying one or more weights, layers, nodes, biases, and/or synapses to associate given positions in reference to the playing surface of venue and/or in reference to one or more agents. As another example, a sports machine learning model may be trained by modifying one or more weights, layers, nodes, biases, and/or synapses to associate given movement or trends in reference to the playing surface of venue and/or in reference to none or more agents. As another example, a sports machine learning model may be trained by modifying one or more weights, layers, nodes, biases, and/or synapses to associate sporting events with corresponding time boundaries, teams, players, coaches, officials, and environmental data associated with a location of corresponding sporting events.
A sports machine learning model may be trained by modifying one or more weights, layers, nodes, biases, and/or synapses to associate position, movement, and/or trend information in view of a sports target. A sports target may be a score related target (e.g., a score, a goal, a shot, a shot count, a point, etc.), a play outcome (e.g., a pass, a movement of an object such as a ball, player positions, etc.), a player position, and/or the like. A sports machine learning model may be trained in view sports targets, play outcomes, player positions, and/or the like associated with a given sport (e.g., soccer, American football, basketball, baseball, tennis, golf, rugby, hockey, a team sport, an individual sport, etc.). For example, a football based sports machine learning model may be trained to correlate or otherwise associate player position information in reference to a football field. The football based sports machine learning model may further be trained to correlate or otherwise associate sports data in reference to a number of players and sports targets specific to football.
According to aspects, one or more given sports machine learning model types (e.g., generative learning, linear regression, logistic regression, random forest, gradient boosted machine (GBM), deep learning, graph neural networks (GNN) and/or a deep neural network) may be determined based on attributes of a given sport for which the one or more machine learning models are applied. The attributes may include, for example, sport type (e.g., individual sport vs. team sport), sport boundaries (e.g., time factors, player number factors, object factors, possession periods (e.g., overlapping or distinct), playing surface type (e.g., restricted, unrestricted, virtual, real, etc.) player positions, etc.
According to aspects, a sports machine learning model may receive inputs including sports data for a given sport and may generate a matrix representation based on features of the given sport. The sports machine learning model may be trained to determine potential features for the given sport. For example, the matrix may include fields and/or sub-fields related to player information, team information, object information, sports boundary information, sporting surface information, etc. Attributes related to each field or sub-field may be populated within the matrix, based on received or extracted data. The sports machine learning model may perform operations based on the generated matrix. The features may be updated based on input data or updated training data based on, for example, sports data associated with features that the model is not previously trained to associate with the given sport. Accordingly, sports machine learning models may be iteratively trained based on sports data or simulated data.
The user device(s) 112 may be configured to enable a user to access and/or interact with other systems in the environment 100. For example, the user device(s) 112 may each be a computer system such as, for example, a desktop computer, a mobile device, a tablet, etc. In some embodiments, the user device(s) 112 may include one or more electronic application(s), e.g., a program, plugin, browser extension, etc., installed on a memory of the user device(s) 112. In some embodiments, the electronic application(s) may be associated with one or more of the other components in the environment 100. For example, the electronic application(s) may include one or more of system control software, system monitoring software, software development tools, etc.
In various embodiments, the environment 100 may include a data store 114 (e.g., database). The data store 114 may include a server system and/or a data storage system such as computer-readable memory such as a hard drive, flash drive, disk, etc. In some embodiments, the data store 114 includes and/or interacts with an application programming interface for exchanging data to other systems, e.g., one or more of the other components of the environment. The data store 114 may include and/or act as a repository or source for storing event data, user data, a generated display, output data, and the like (e.g., to be transmitted to user device(s) 112 or any of the other components of environment 100).
In some embodiments, the components of the environment 100 are associated with a common entity, e.g., a service provider, an account provider, or the like. For example, in some embodiments, computing system 102 and data store 114 may be associated with a common entity. In some embodiments, one or more of the components of the environment is associated with a different entity than another. For example, computing system 102 may be associated with a first entity (e.g., a service provider) while data store 114 may be associated with a second entity (e.g., a storage entity providing storage services to the first entity). The systems and devices of the environment 100 may communicate in any arrangement.
As depicted in
According to certain embodiments, data stream module 104 may receive in-venue or broadcast data associated with a sporting event. Such in-venue or broadcast data may be used to generate the event data discussed herein. For example, such in-venue or broadcast data may be provided to one or more event machine learning models. The one or more event machine learning models may be trained based on training data that includes historical or simulated in-venue or broadcast data, historical or simulated event data (e.g., tagged data), historical or simulated event actions, and/or the like. The training data may be used to train the event machine learning models by modifying one or more weighs, layers, synapses, biases, and/or the like of the event machine learning models, in accordance with a machine learning algorithm, as discussed herein. Alternatively, or in addition, such in-venue or broadcast data may supplement received event data for verification and/or use to generate an interactive display.
Computing system(s) 102 may also include display generation module 106. In various embodiments, display generation module 106 may be configured to generate an interactive display using the data received by data stream module 104. In various embodiments, display generation module 106 may be configured to generate an interactive display. The interactive display may include at least one of a graphical representation of one or more of the aspects described herein. In various embodiments, the interactive display is generated in real-time as the data is received (e.g., by data stream module 104). Computing system(s) 102 may also include transmission module 108. In various embodiments, transmission module 108 may be configured to transmit to a user interface the interactive display.
As depicted in
Although depicted as separate components in
The methods described herein may be performed on or between one or more computing devices.
The method 200 includes a first step 202 where a first set of data may be received from the data store 114 and/or one or more data sources separate from the data store 114. The first set of data may be associated with one or more parameters related to generating the rating for the sports team. For example, the first set of data may include one or more of: a first match report, a first set of player data, a geographical location, and/or a first score report. In some examples, the first set of data may be gathered manually by one or more users. One or more users may review score reports including games between multiple teams. The score reports may include a final match score (e.g., the match finished 2-0 or 1-1). For example, the geographical location of the sports team may be Germany, England, France, USA, Colombia, Argentina, etc. The one or more parameters may include, for example, competition-based match importance weighting and/or game week-based match importance weighting. The one or more parameters controls the value in which a certain match affects the dynamic rating of the sports team.
At a second step 204, a plurality of ability scores may be calculated for the sports team based on the first set of data. For example, a first ability score and a second ability score of the plurality of ability scores may be generated based on the geographical location of the sports team. This first ability score may be a country ability score. The second ability score of the plurality of ability scores may be a continent ability score. A third ability score of the plurality of ability scores may be generated for a league associated with the sports team. This third ability score may be a league ability score. A fourth ability score of the plurality of ability scores may be generated within the league associated with the sports team. This fourth ability score may be a within-league ability score. While four ability scores are described of the plurality of ability scores, any desired number of ability scores may be used to generate a first rating for the sports team.
At a third step 206, the first rating may be generated as a sum or other applicable relationship of the plurality of ability scores. For example, the first rating may be generated by adding the country ability score, the within continent ability score, league ability score, and the within-league ability score. In an example, the first rating may be an Elo rating for the sports team. The first rating may be incorporated into a hierarchical rating system (shown in
At a fourth step 208, the plurality of ability scores may be dynamically adjusted upon receipt of a second set of data. The second set of data may be associated with the one or more parameters related to generating the rating for the sports team. For example, the second set of data may include one or more of: a second match report, a second set of player data, and/or a second score report. The second set of data may be used to update one or more of: the country ability score, the continent ability score, league ability score, and the within-league ability score. For example, the second score report associated with the sports team is received and the within-league ability score may be updated based on the second score report. As another example, the second score report associated with the sports team is received and the second score report details a match between the sports team associated with the league and a different sports team associated with a different league. In such an example, the within-league ability score and the league ability score may be updated. As yet another example, the second score report details a match between the sports team associated with the league and a different sports team associated with the same league, but in a separate competition than the league. In such an example, only the within-league ability score may be updated.
At a fifth step 210, the first rating is updated based on the dynamically adjusted plurality of ability scores. This first rating is updated via a deterministic algorithm. The deterministic algorithm may adjust the ability score based on the first set of data and the second set of data such that the first rating is updated relative to the hierarchical rating system. For example, at a sixth step 212, the first rating for the sports team may be represented by an icon in a graphical user interface (GUI) (shown in
The method 300 includes a first step 302 where a first set of data may be received from the data store 114 and/or one or more data sources separate from the data store 114. The first set of data may be associated with one or more parameters related to generating the rating for the player. For example, the first set of data may include one or more of: a first match report, a first set of player data, a geographical location, event level data, and/or a first score report. In an example, the event level data may include tracking data, completed passes, distance covered, chances created, attempted passes, etc. One or more users may review match reports, including games between multiple teams, in order to determine and/or confirm the tracking data used in monitoring the player's on field time and off field time. In some examples, the first set of data may be gathered manually by one or more users. The one or more parameters may include, for example, an expected team rating, an actual team rating, an expected goal value, an expected possession value, a weighted goal value, and/or a defensive or attacking value. The one or more parameters may control the level in which a certain value affects the dynamic rating of the player.
At a second step 304, a plurality of ability scores may be calculated for the player based on the first set of data. For example, a first ability score and a second ability score of the plurality of ability scores may be generated based on the first set of data. In an example, the first ability score may be a first player attribute score. In an example, the second ability score of the plurality of ability scores may be a second player attribute score different from the first player attribute player score. Any number of ability scores may be generated, based on the first set of data, as desired to generate the dynamic player rating.
At a third step 306, a first player rating may be generated as a sum or other applicable relationship of the plurality of ability scores. For example, the first player rating may be generated by adding the first ability score and the second ability score. In an example, the first player rating may be an Elo rating for the player. The first player rating may be incorporated into a hierarchical rating system (shown in
At a fourth step 308, the plurality of ability scores may be dynamically adjusted upon receipt of a second set of data. The second set of data may be associated with the one or more parameters related to generating the rating for the player. For example, the second set of data may include one or more of: a second match report, a second set of player data, a second geographical location, second event level data, and/or a second score report. The second set of data may be used to update one or more of the first ability score and/or the second ability score. For example, the second event level data associated with the player is received and the first ability score may be updated based on the second event level data. In such an example, the second event level data may include tracking information for the player. The tracking information may indicate how much distance the player has traveled as well as identify when the player was on the field vs off the field.
At a fifth step 310, the first player rating may be updated based on the dynamically adjusted plurality of ability scores. This first player rating may be updated via a deterministic algorithm. The deterministic algorithm may adjust the ability score based on the first set of data and the second set of data such that the first player rating is updated relative to the hierarchical rating system. For example, at a sixth step 312, the first player rating for the player may be represented by an icon in a graphical user interface (GUI) (shown in
The method 400 includes a first step 402 where a first set of data may be received from the data store 114 and/or one or more data sources separate from the data store 114. The first set of data may be associated with one or more parameters related to generating the overall rating for the sports team. For example, the first set of data may include one or more of: a first match report, a first set of player data, a geographical location, and/or a first score report.
At a second step 404, a plurality of ability scores may be calculated for the sports team based on the first set of data. For example, a first ability score and a second ability score of the plurality of ability scores may be generated based on the geographical location of the sports team. This first ability score may be a country ability score. The second ability score of the plurality of ability scores may be a continent ability score. A third ability score of the plurality of ability scores may be generated for a league associated with the sports team. This third ability score may be a league ability score. A fourth ability score of the plurality of ability scores may be generated within the league associated with the sports team. This fourth ability score may be a within-league ability score. While four ability scores are described of the plurality of ability scores, any desired number of ability scores may be used to generate the overall rating for the sports team.
At a third step 406, the overall rating may be generated as a sum or other applicable relationship of the plurality of ability scores and the one or more player ratings. The one or more player ratings may be generated as described in the method 300. Each player rating of the one or more player ratings may be incorporated into the overall rating as an additional sum or other applicable relationship with the plurality of ability scores. For example, the overall rating may be generated by adding the country ability score, the within continent ability score, league ability score, the within-league ability score, and the one or more player ratings. At a fourth step 408, the plurality of ability scores and/or the one or more player ratings may be dynamically adjusted upon receipt of a second set of data. The second set of data may be associated with the one or more parameters related to generating the rating for the sports team. The second set of data may include one or more of: a second match report, a second set of player data, and/or a second score report.
The second set of data may be used to update one or more of: the country ability score, the continent ability score, league ability score, and the within-league ability score. For example, the second score report associated with the sports team is received and the within-league ability score may be updated based on the second score report. As another example, the second score report associated with the sports team is received and the second score report details a match between the sports team associated with the league and a different sports team associated with a different league. In such an example, the within-league ability score and the league ability score may be updated. As yet another example, the second score report details a match between the sports team associated with the league and a different sports team associated with the same league, but in a separate competition than the league. In such an example, only the within-league ability score may be updated.
At a fifth step 410, the overall rating is updated based on the dynamically adjusted plurality of ability scores as well as based on the one or more player ratings. This overall rating may be updated via a deterministic algorithm. The deterministic algorithm may adjust the ability score as well as the one or more player ratings based on the first set of data and the second set of data such that the overall rating is updated relative to the hierarchical rating system. For example, at a sixth step 412, the overall rating for the sports team may be represented by an icon in a graphical user interface (GUI) (shown in
In another example, the overall rating may be comprised solely of the one or more player ratings. For example, the one or more player ratings may include a starting 11 rating and a substitute rating. In such an example, the players in the starting 11 of the sports match each may have a player rating, the combination of which forms the starting 11 rating. The players not starting the match may each have a player rating, the combination of which forming the substitute rating. The starting 11 rating and the substitute rating may be summed or may have another relationship applied to form the overall rating of the sports team. When obtained in this manner, the overall rating may be statistical weighted differently from the overall rating calculated using the plurality of ability scores and the one or more player ratings.
In an example, the overall rating may be output by a machine learning model (e.g., an overall rating machine learning model). The machine learning model may be trained using a training data set that includes historical or simulated characteristics associated with the first data set and the second data set, based on historical, simulated, or actual match reports (e.g., using tracking data and/or event data), based on historical or simulated score reports, and/or the like. The machine learning model may receive, as inputs, the first data set and the second data set. The match report may be provided as inputs to the machine learning model or may be otherwise accessible by the machine learning model. The machine learning model learns associations between the first data set and the second data set. Based on such input data and/or access, the machine learning model may output an overall rating for the sports team. For example, the machine learning model may generate and output an overall rating that is based on one or more game reports of a sports match between the two sports teams in the match report. The machine learning model may update the output overall rating based on receiving a third set of data. The machine learning model may output an updated overall rating for each new set of data that is received.
The one or more player ratings allow for the user to discern various aspects of the players for a large pool of players. For example, the one or more player ratings may be able to take into account both defensive and offensive statistics. In an example, the one or more player ratings may be able to accurately weight goals for a player who is playing as a defender versus goals for a player who is playing as an attacker. The one or more player ratings may also provide an on-field player impact versus an off-field player impact. For example, if a player having a certain player rating is on the field, the player rating is able to provide an indication of the outcome of the match based on that player's rating in relationship to player ratings for other players on the field. Once that player leaves the field, the indication of the outcome of the match may be adjusted as certain players with varying player ratings replace that initial player.
Additionally, the dynamic rating for the sports team may be statistically anchored by the player rating in order provide more relevant data. For example, goals may be unfairly statistically weighted for the dynamic rating for the sports team, but identifying that goals may be associated with a specific player having a certain player rating within the sports team provides added statistical context for the dynamic rating for the sports team.
The training data 812 and a training algorithm 820 may be provided to a training component 830 that may apply the training data 812 to the training algorithm 820 to generate a trained machine learning model 850. According to an implementation, the training component 830 may be provided comparison results 816 that compare a previous output of the corresponding machine learning model to apply the previous result to re-train the machine learning model. The comparison results 816 may be used by the training component 830 to update the corresponding machine learning model. The training algorithm 820 may utilize machine learning networks and/or models including, but not limited to a deep learning network such as Deep Neural Networks (DNN), Convolutional Neural Networks (CNN), Fully Convolutional Networks (FCN) and Recurrent Neural Networks (RCN), probabilistic models such as Bayesian Networks and Graphical Models, and/or discriminative models such as Decision Forests and maximum margin methods, or the like. The output of the flow diagram 800 may be a trained machine learning model 850.
A machine learning model disclosed herein may be trained by adjusting one or more weights, layers, and/or biases during a training phase. During the training phase, historical or simulated data may be provided as inputs to the model. The model may adjust one or more of its weights, layers, and/or biases based on such historical or simulated information. The adjusted weights, layers, and/or biases may be configured in a production version of the machine learning model (e.g., a trained model) based on the training. Once trained, the machine learning model may output machine learning model outputs in accordance with the subject matter disclosed herein. According to an implementation, one or more machine learning models disclosed herein may continuously update based on feedback associated with use or implementation of the machine learning model outputs.
It should be understood that aspects in this disclosure are exemplary only, and that other aspects may include various combinations of features from other aspects, as well as additional or fewer features.
In general, any process or operation discussed in this disclosure that is understood to be computer-implementable, such as the processes illustrated in the flowcharts disclosed herein, may be performed by one or more processors of a computer system, such as any of the systems or devices in the exemplary environments disclosed herein, as described above. A process or process step performed by one or more processors may also be referred to as an operation. The one or more processors may be configured to perform such processes by having access to instructions (e.g., software or computer-readable code) that, when executed by the one or more processors, cause the one or more processors to perform the processes. The instructions may be stored in a memory of the computer system. A processor may be a central processing unit (CPU), a graphics processing unit (GPU), or any suitable types of processing unit.
A computer system, such as a system or device implementing a process or operation in the examples above, may include one or more computing devices, such as one or more of the systems or devices disclosed herein. One or more processors of a computer system may be included in a single computing device or distributed among a plurality of computing devices. A memory of the computer system may include the respective memory of each computing device of the plurality of computing devices.
The computer 900 may also have a memory 904 (such as RAM) storing instructions 924 for executing techniques presented herein, for example the methods described with respect to
Program aspects of the technology may be thought of as “products” or “articles of manufacture” typically in the form of executable code and/or associated data that is carried on or embodied in a type of machine-readable medium. “Storage” type media include any or all of the tangible memory of the computers, processors or the like, or associated modules thereof, such as various semiconductor memories, tape drives, disk drives and the like, which may provide non-transitory storage at any time for the software programming. All or portions of the software may at times be communicated through the Internet or various other telecommunication networks. Such communications, for example, may enable loading of the software from one computer or processor into another, for example, from a management server or host computer of the mobile communication network into the computer platform of a server and/or from a server to the mobile device. Thus, another type of media that may bear the software elements includes optical, electrical and electromagnetic waves, such as used across physical interfaces between local devices, through wired and optical landline networks and over various air-links. The physical elements that carry such waves, such as wired or wireless links, optical links, or the like, also may be considered as media bearing the software. As used herein, unless restricted to non-transitory, tangible “storage” media, terms such as computer or machine “readable medium” refer to any medium that participates in providing instructions to a processor for execution.
While the disclosed methods, devices, and systems are described with exemplary reference to transmitting data, it should be appreciated that the disclosed aspects may be applicable to any environment, such as a desktop or laptop computer, an automobile entertainment system, a home entertainment system, etc. Also, the disclosed aspects may be applicable to any type of Internet protocol.
It should be appreciated that in the above description of exemplary aspects of the invention, various features of the invention are sometimes grouped together in a single aspect, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed aspect. Thus, the claims following the Detailed Description are hereby expressly incorporated into this Detailed Description, with each claim standing on its own as a separate aspect of this invention.
Furthermore, while some aspects described herein include some but not other features included in other aspects, combinations of features of different aspects are meant to be within the scope of the invention, and form different aspects, as would be understood by those skilled in the art. For example, in the following claims, any of the claimed aspects can be used in any combination.
Thus, while certain aspects have been described, those skilled in the art will recognize that other and further modifications may be made thereto without departing from the spirit of the invention, and it is intended to claim all such changes and modifications as falling within the scope of the invention. For example, functionality may be added or deleted from the block diagrams and operations may be interchanged among functional blocks. Operations may be added or deleted to methods described within the scope of the present invention.
The above disclosed subject matter is to be considered illustrative, and not restrictive, and the appended claims are intended to cover all such modifications, enhancements, and other implementations, which fall within the true spirit and scope of the present disclosure. Thus, to the maximum extent allowed by law, the scope of the present disclosure is to be determined by the broadest permissible interpretation of the following claims and their equivalents, and shall not be restricted or limited by the foregoing detailed description. While various implementations of the disclosure have been described, it will be apparent to those of ordinary skill in the art that many more implementations are possible within the scope of the disclosure. Accordingly, the disclosure is not to be restricted except in light of the attached claims and their equivalents.
This application claims priority under 35 U.S.C. § 119 (e) to Provisional U.S. Patent Application No. 63/595,036, filed Nov. 1, 2023, the disclosure of which is hereby incorporated by reference in its entirety.
| Number | Date | Country | |
|---|---|---|---|
| 63595036 | Nov 2023 | US |
