阅读说明：本技术 用数据和身体姿态分析运动表现以对表现进行个性化预测 (Analyzing athletic performance with data and body posture to personalize predictions of performance ) 是由 保罗·大卫·鲍尔 阿迪亚·切鲁库穆迪 S·甘古利 魏新宇 沙龙 詹尼弗·霍布斯 赫克托· 于 2020-02-28 设计创作，主要内容包括：本文公开了一种生成运动员预测的方法。计算系统从数据存储中检索数据。计算系统使用人工神经网络生成预测模型。该人工神经网络生成一个或更多个个性化嵌入,一个或更多个个性化嵌入包括基于历史表现的运动员特定信息。计算系统从数据中选择与在数据中捕获的每次射击尝试相关的一个或多个特征。人工神经网络至少基于一个或多个个性化嵌入以及与每次射击尝试相关的一个或多个特征,来学习每次射击尝试的结果。(A method of generating an athlete prediction is disclosed herein. The computing system retrieves data from the data store. A computing system generates a predictive model using an artificial neural network. The artificial neural network generates one or more personalized inlays that include athlete-specific information based on historical performance. The computing system selects one or more features from the data that are associated with each firing attempt captured in the data. The artificial neural network learns the results of each shooting attempt based on at least one or more personalized inlays and one or more features associated with each shooting attempt.)

1. A method of generating an athlete prediction, comprising:

retrieving, by a computing system, data from a data store, the data comprising information for a plurality of events across a plurality of season;

generating, by the computing system, a predictive model using an artificial neural network by:

generating, by the artificial neural network, one or more personalized inlays comprising athlete-specific information based on historical performance;

selecting one or more features from the data that are relevant to each scored event attempt captured in the data; and

learning, by the artificial neural network, a result of each scored event attempt based at least on the one or more personalized inlays and the one or more features related to each scored event attempt;

receiving, by the computing system, a data set for a target scoring event attempt, the data set including at least the athlete involved in the target scoring event attempt and one or more characteristics related to the target scoring event attempt; and

generating, by the computing system via the predictive model, a likely outcome of the scored event attempt based on the personalized insert of the athlete involved in the targeted scored event attempt and the one or more features related to the targeted scored event attempt.

2. The method of claim 1, wherein selecting the one or more features from the data that are relevant to each scored event attempt captured in the data comprises:

for each scored event attempt, at least one or more of scored event start location information, player location, and one or more geometric features of the scored event attempt are identified.

3. The method of claim 2, wherein the one or more geometric features of the scored event attempt include at least one or more of an angle between a front and a goalie, a first distance from the front to a goal center, and a second distance from the goalie to the goal center.

4. The method of claim 2, further comprising:

for each shot attempt, body posture information associated with a front of the shot attempt is identified.

5. The method of claim 1, further comprising:

identifying, by the computing system, a set of scored event attempts over a first duration;

simulating, by the computing system, a number of scoring event attempts that an average player will lose a ball based on one or more parameters associated with the set of scoring event attempts;

identifying, by the computing system, a set of athletes, each athlete including one or more personalized inlays;

for each player in the goalkeeper set, simulating a number of scoring event attempts that the player will miss based on the one or more parameters associated with the set of scoring event attempts and the respective set of one or more personalized inlays; and

generating, by the computing system, a graphical representation ranking each player in the set of players based on an expected scoring event that misses as compared to the average player.

6. The method of claim 1, further comprising:

identifying, by the computing system, a first athlete and one or more scoring event attempts defended by the first athlete for a first duration;

generating, by the computing system, a data set corresponding to one or more parameters associated with the one or more scored event attempts defended by the first athlete for the first duration of time;

identifying, by the computing system, a second athlete, wherein the second athlete is associated with one or more personalized inlays;

simulating, by the computing system, a number of goals that the second player will lose based on the one or more parameters associated with the one or more scored event attempts defended by the first player and the one or more personalized inlays; and

generating, by the computing system, a graphical representation comparing the number of balls lost by the second player to the number of balls lost by the first player.

7. The method of claim 1, further comprising:

identifying, by the computing system, an athlete and one or more scoring event attempts defended by the athlete for a first duration;

generating, by the computing system, a data set corresponding to one or more parameters associated with the one or more scored event attempts defended by the athlete for the first duration;

identifying, by the computing system, one or more inlays associated with the athlete, wherein the one or more personalized inlays correspond to attributes of the athlete over a second duration;

simulating, by the computing system, a number of balls the athlete will lose based on the one or more parameters associated with the one or more scored event attempts defended by the athlete and the one or more personalized inlays corresponding to the attributes of the athlete within the second duration; and

generating, by the computing system, a graphical representation comparing the number of balls lost by the player in the second duration based on the attribute to the number of balls lost by the player in the first duration.

8. A system for generating an athlete prediction, comprising:

a processor; and

a memory having stored thereon programming instructions that, when executed by the processor, perform one or more operations comprising:

retrieving data from a data store, the data comprising information for a plurality of events across a plurality of season;

generating a predictive model using an artificial neural network by:

generating, by the artificial neural network, one or more personalized inlays comprising goalkeeper-specific information based on historical performance;

selecting from the data one or more characteristics relating to each shot attempt captured in the data; and

learning, by the artificial neural network, a result of each shot attempt based at least on the one or more personalized inlays and the one or more features associated with each shot attempt;

receiving a data set for a target shooting attempt, the data set including at least the goalkeeper involved in the target shooting attempt and one or more characteristics related to the target shooting attempt; and

generating, via the predictive model, a likely outcome of the goal shooting attempt based on the personalized embedding of the goalkeeper involved in the goal shooting attempt and the one or more features related to the goal shooting attempt.

9. The system of claim 8, wherein selecting the one or more characteristics from the data that are relevant to each shot attempt captured in the data comprises:

for each shot attempt, at least one or more of shot start location information, a goalkeeper location, and one or more geometric features of the shot attempt are identified.

10. The system of claim 9, wherein the one or more geometric features of the shot attempt include at least one or more of an angle between a front and the goalie, a first distance from the front to a goal center, and a second distance from the goalie to the goal center.

11. The system of claim 9, further comprising:

for each shot attempt, body posture information associated with a front of the shot attempt is identified.

12. The system of claim 8, wherein the one or more operations further comprise:

identifying a set of shooting attempts within a first duration;

simulating the number of balls that a common goalkeeper will lose based on one or more parameters associated with the goal set;

identifying a set of goalkeepers, each goalkeeper comprising one or more personalized inlays;

for each goalkeeper in the set of goalkeepers, simulating a number of goals that the goalkeeper will miss based on the one or more parameters associated with the goal set and the respective set of one or more personalized inlays; and

generating a graphical representation ranking each goalkeeper in the set based on expected assaults compared to the ordinary goalkeeper.

13. The system of claim 8, wherein the one or more operations further comprise:

identifying a first goalkeeper and one or more shots defended by the first goalkeeper for a first duration;

generating a data set corresponding to one or more parameters associated with the one or more shots defended by the first goalkeeper for the first duration;

identifying a second goalkeeper, wherein the second goalkeeper is associated with one or more personalized inlays;

simulating an amount that the second goalie will lose balls based on the one or more parameters associated with the one or more shots defended by the first goalie and the one or more personalized inlays; and

generating a graphical representation comparing the number of balls the second goalkeeper will lose to the number of balls the first goalkeeper will lose.

14. The system of claim 8, wherein the one or more operations further comprise:

identifying a goalkeeper and one or more shots defended by the goalkeeper for a first duration;

generating a data set corresponding to one or more parameters associated with one or more shots defended by the goalkeeper for the first duration;

identifying one or more insertions associated with the goalkeeper, wherein the one or more personalized insertions correspond to attributes of the goalkeeper over a second duration;

simulating an amount that the goalkeeper will lose balls based on one or more parameters associated with the one or more shots defended by the goalkeeper and the one or more personalized inlays corresponding to the goalkeeper's attributes over the second duration; and

generating a graphical representation comparing the number of balls lost by the goalkeeper based on the attribute over the second duration to the number of balls lost by the goalkeeper over the first duration.

15. A non-transitory computer-readable medium comprising one or more sequences of instructions which, when executed by one or more processors, cause:

retrieving, by a computing system, data from a data store, the data comprising information for a plurality of events across a plurality of season;

generating, by the computing system, a predictive model using an artificial neural network by:

generating, by the artificial neural network, one or more personalized inlays comprising goalkeeper-specific information based on historical performance;

selecting from the data one or more characteristics associated with each shot attempt captured in the data; and

learning, by the artificial neural network, a result of each shot attempt based at least on the one or more personalized inlays and the one or more features associated with each shot attempt;

receiving, by the computing system, a data set for a target shooting attempt, the data set including at least the goalkeeper involved in the target shooting attempt and one or more features related to the target shooting attempt; and

generating, by the computing system via the predictive model, a likely outcome of the goal shooting attempt based on the personalized embedding of the goalkeeper involved in the goal shooting attempt and the one or more features related to the goal shooting attempt.

16. The non-transitory computer-readable medium of claim 15, wherein selecting the one or more features from the data that are relevant to each shot attempt captured in the data comprises:

for each shot attempt, at least one or more of shot start location information, a goalkeeper location, and one or more geometric features of the shot attempt are identified.

17. The non-transitory computer-readable medium of claim 16, wherein the one or more geometric features of the shot attempt include at least one or more of an angle between a front and the goalkeeper, a first distance from the front to a goal center, and a second distance from the goalkeeper to the goal center.

18. The non-transitory computer-readable medium of claim 15, further comprising:

identifying, by the computing system, a set of shooting attempts within a first duration;

simulating, by the computing system, a number of balls that an ordinary goalkeeper will lose based on one or more parameters associated with the goal set;

identifying, by the computing system, a set of goalkeepers, each goalkeeper comprising one or more personalized inlays;

for each goalkeeper in the set of goalkeepers, simulating a number of goals that the goalkeeper will miss based on the one or more parameters associated with the goal set and the respective set of one or more personalized inlays; and

generating, by the computing system, a graphical representation ranking each goalkeeper in the set of goalkeepers based on an expected putting compared to the ordinary goalkeeper.

19. The non-transitory computer-readable medium of claim 15, further comprising:

identifying, by the computing system, a first goalkeeper and one or more shots defended by the first goalkeeper for a first duration;

generating, by the computing system, a data set corresponding to one or more parameters associated with the one or more shots defended by the first goalkeeper for the first duration;

identifying, by the computing system, a second goalkeeper, wherein the second goalkeeper is associated with one or more personalized inlays;

simulating, by the computing system, an amount that the second goalie will lose balls based on the one or more parameters associated with the one or more shots defended by the first goalie and the one or more personalized inlays; and

generating, by the computing system, a graphical representation comparing the number of balls lost by the second goalkeeper to the number of balls lost by the first goalkeeper.

20. The non-transitory computer-readable medium of claim 15, further comprising:

identifying, by the computing system, a goalkeeper and one or more shots defended by the goalkeeper for a first duration;

generating, by the computing system, a data set corresponding to one or more parameters associated with one or more shots defended by the goalkeeper for the first duration;

identifying, by the computing system, one or more insertions associated with the goalkeeper, wherein the one or more personalized insertions correspond to attributes of the goalkeeper over a second duration;

simulating, by the computing system, an amount that the goalkeeper will lose balls based on one or more parameters associated with the one or more shots defended by the goalkeeper and the one or more personalized inlays corresponding to the goalkeeper's attributes over the second duration; and

generating, by the computing system, a graphical representation comparing the number of balls lost by the goalkeeper based on the attribute over the second duration to the number of balls lost by the goalkeeper over the first duration.

Technical Field

The present disclosure relates generally to systems and methods for generating personalized predictions of athletic performance based on, for example, data

Background

Sports fans and data analysts are increasingly engaged in sports analysis, particularly in attempting to determine whether the outcome of a race or game instance will change based on changes in the players in the race. For example, a typical "quarterback on the morning of monday" commentator may argue how the outcome of the competition may change if, for example, the coach makes one or more roster adjustments. Thus, there is a continuing competition for developing systems that can more accurately predict the outcome of a game instance.

Disclosure of Invention

Embodiments disclosed herein relate generally to systems and methods for generating a shot prediction. In another embodiment, a method of generating an athlete prediction is disclosed herein. The computing system retrieves data from the data store. The data includes information for a plurality of events across a plurality of season. A computing system generates a predictive model using an artificial neural network. The artificial neural network generates one or more personalized inlays that include athlete-specific information based on the historical performance. The computing system selects one or more features from the data that are associated with each shot attempt captured in the data. The artificial neural network learns the results of each shot attempt based on at least one or more personalized embeddings and one or more features associated with each shot attempt. A computing system receives a data set for a target shot attempt. The data set includes at least an athlete involved in the target shot attempt and one or more characteristics associated with the target shot attempt. The computing system generates, via the predictive model, a likely outcome of the goal shooting attempt based on the personalized insert of the athlete involved in the goal shooting attempt and the one or more characteristics associated with the goal shooting attempt.

In some embodiments, a system for generating an athlete prediction is disclosed herein. The system includes a processor and a memory. The memory has stored thereon programming instructions that, when executed by the processor, perform one or more operations. The one or more operations include retrieving data from a data store. The data includes information for a plurality of events across a plurality of season. The one or more operations further comprise generating a predictive model using the artificial neural network by: generated by an artificial neural network; selecting from the data one or more characteristics associated with each shot attempt captured in the data; and learning, by the artificial neural network, a result of each shot attempt based at least on the one or more personalized inlays and the one or more features associated with each shot attempt. The one or more personalized inserts include player specific information based on historical performance. The one or more operations further include receiving a data set for the target shot attempt. The data set includes at least an athlete involved in the target shot attempt and one or more characteristics associated with the target shot attempt. The one or more operations further include generating, via the predictive model, a likely outcome of the goal shooting attempt based on the personalized insert of the athlete involved in the goal shooting attempt and the one or more characteristics associated with the goal shooting attempt.

In another embodiment, a non-transitory computer-readable medium is disclosed herein. The non-transitory computer-readable medium includes one or more sequences of instructions which, when executed by one or more processors, cause a computing system to perform one or more operations. The computing system retrieves data from the data store. The data includes information for a plurality of events across a plurality of season. A computing system generates a predictive model using an artificial neural network. The artificial neural network generates one or more personalized inlays that include athlete-specific information based on the historical performance. The computing system selects one or more characteristics from the data that are associated with each shot attempt captured in the data. The artificial neural network learns the results of each shot attempt based on at least one or more personalized embeddings and one or more features associated with each shot attempt. A computing system receives a data set for a target shot attempt. The data set includes at least an athlete involved in the target shot attempt and one or more characteristics associated with the target shot attempt. The computing system generates, via the predictive model, a likely outcome of the goal shooting attempt based on the personalized insert of the athlete involved in the goal shooting attempt and the one or more characteristics associated with the goal shooting attempt.

Drawings

So that the manner in which the above recited features of the present disclosure can be understood in detail, a more particular description of the disclosure, briefly summarized above, may be had by reference to embodiments, some of which are illustrated in the appended drawings. It is to be noted, however, that the appended drawings illustrate only typical embodiments of this disclosure and are therefore not to be considered limiting of its scope, for the disclosure may admit to other equally effective embodiments.

FIG. 1 is a block diagram illustrating a computing environment, according to an example embodiment.

Fig. 2 is a block diagram illustrating a structure of an artificial neural network according to an example embodiment.

FIG. 3 is a flow diagram illustrating a method of generating a fully trained predictive model according to an example embodiment.

FIG. 4 is a flowchart illustrating a method of generating a shot prediction using a fully trained predictive model according to an example embodiment.

FIG. 5A is a flow diagram illustrating a method of generating a player ranking based on a number of simulated losses, according to an example embodiment.

FIG. 5B is a block diagram of a graphical user interface illustrating player ranking according to an example embodiment.

Fig. 6A is a flow chart illustrating a method of comparing athletes using a simulation process according to an example embodiment.

FIG. 6B is a block diagram illustrating a graphical user interface of a simulated goal map according to an example embodiment.

FIG. 7A is a flow chart illustrating a method for comparing an athlete's season using a simulation process according to an example embodiment.

FIG. 7B is a block diagram illustrating a graphical user interface of a simulated goal map according to an example embodiment.

FIG. 8A is a block diagram illustrating a computing device, according to an example embodiment.

FIG. 8B is a block diagram illustrating a computing device, according to an example embodiment.

To facilitate understanding, identical reference numerals have been used, where possible, to designate identical elements that are common to the figures. It is contemplated that elements disclosed in one embodiment may be beneficially utilized on other embodiments without specific recitation.

Detailed Description

One or more techniques disclosed herein relate generally to systems and methods for generating gatekeeper predictions. In other words, one or more techniques disclosed herein relate to systems and methods for predicting the likelihood that a goalkeeper will lose the ball or block a shot attempt based on, for example, one or more shooting parameters and personalized information about the goalkeeper.

In the lower half of the year 2018, the championship (Real Madrid) and the liverpole (Liverpool), which leads with a score of 2-1, between the royal Madrid, whose player Gareth Bale (gares bell) aims at the strong and straight goal of the liverpole goalkeeper lores (lores Karius) from 35 yards. The ball eventually slides through Karius' hands, effectively getting a third sequential champion title to the royal horse delhi team. The sharp purchasers immediately responded to the disfavor, and the club purchased the brazilian, Alisson (alison) from AS Roma (roman football club) at a price of 67 million pounds, breaking the gatekeeper's world record.

Although this transition may trigger a further high-priced concatemer transition between the european top-level league, keeping the cost of the concatemer at the highest historical record, it raises the following problems: 1) how to compare the performance of different goalkeepers in teams and leagues? And 2) how can a goalkeeper be evaluated for success in a particular team?

Conventional methods use a coarse metric to evaluate goalkeepers, such as "no-ball," "total-ball-loss," or "number-of-fire-for-rescue-to-number-of-balls" ratio. More recently, conventional systems have implemented "prospective metrics," such as prospective suppression (xS), to compare goalkeeper performance to tournament averages. However, these methods are problematic in that goalkeepers may perform different types of putting depending on the style of the team and the opponent they are facing.

Instead of using a metric that may not capture all of the different situations and contexts, one or more techniques disclosed herein transcend the metric by simulating each goalkeeper for each shot and comparing who will lose the ball the most. For example, one or more of the techniques disclosed herein may provide answers to the following questions: how much will he put out/lose goal based on the goal that the risson faced during the season if he was in effect for the risson last year?

Although this concept appears simple to its surface, the process of accurately simulating the exchange of different gatekeepers for a particular situation is challenging due to several factors, such as but not limited to:

lacking a specific example for each goalkeeper: such a task would be easier if a goalkeeper were to face one million shots per season, for example. However, given that each goalkeeper faces an average of 2 to 5 goals per game (about 70-150 goals per season for a 38 game), goalkeepers may face only a few goals per position/context, or may not be based at all on the power of who they are. For example, a goalkeeper who is a team power that is typically tight in defense may not face many kickback goals, or another goalkeeper who is a team power where the location ball is very strong may not actually face many goals from the location ball.

Change in goalkeeper form: the form of the goalkeeper may change throughout the season and/or the course of the profession due to injury, fatigue, age, confidence, improvement in skills, education, etc. Such changes may cause the previous examples of goalkeeper saving to no longer be relevant (i.e., the examples may not be able to predict current or future performance).

Data are not refined enough: the view of each shot may be limited to only the x, y position of the host location, the x, y goalkeeper position at the time of the shot, the x, y final ball position (and associated player identity). To more accurately predict the likelihood of a goalkeeper fighting a shot, the body position location (i.e., whether they are crouching down, standing straight/unbalanced, wide arms, frontal body position, etc.) is useful for such analysis.

To address such challenges, one or more techniques described herein utilize personalized prediction methods that use dynamic spatial features within a deep learning framework. In particular, the techniques described herein may employ a feed-forward neural network with a combination of fixed (e.g., shot position and goalkeeper position) and dynamically updated (e.g., player patterns, game times, point bars, etc.) embeddings and features to predict the chance that a shot will be suppressed (e.g., expected to be suppressed), where the shot location is, and strictly allow the interface between goalkeepers to compare performance under the same circumstances.

FIG. 1 is a block diagram illustrating a computing environment 100, according to an example embodiment. The computing environment 100 may include a tracking system 102, an organization computing system 104, and one or more client devices 108 that communicate via a network 105.

The network 105 may be of any suitable type, including a separate connection via the internet, such as a cellular or Wi-Fi network. In some embodiments, the network 105 may connect terminals, services, and mobile devices using direct connections, such as Radio Frequency Identification (RFID), Near Field Communication (NFC), bluetooth^TMBluetooth with low power consumption^TM(BLE)、Wi-Fi^TM、ZigBee^TMEnvironmental backscatter communications (ABC) protocol, USB, WAN or LAN. Since the transmitted information may be personal or confidential, security considerations may dictate that one or more of these types of connections be encrypted or otherwise protected. However, in some embodiments, the information being transmitted may not be too personal, and thus, for convenience, rather than security, a network connection may be chosen.

The network 105 may include any type of computer network arrangement for exchanging data or information. For example, the network 105 may be the Internet, a private data network, a virtual private network using a public network and/or other suitable connection(s) that enable components in the computing environment 100 to send and receive information between components of the environment 100.

The tracking system 102 may be located in a site 106. For example, venue 106 may be configured to host an athletic event that includes one or more agents 112. The tracking system 102 may be configured to record the movements of all agents (i.e., players) on the playing surface, as well as one or more other related objects (e.g., a ball, a referee, etc.). In some embodiments, the tracking system 102 may be an optical-based system using, for example, multiple fixed cameras. For example, a system of six fixed, calibrated cameras may be used which project the three-dimensional positions of the players and ball onto a two-dimensional top view of the pitch. In some embodiments, the tracking system 102 may be a radio-based system using, for example, Radio Frequency Identification (RFID) tags worn by athletes or embedded in objects to be tracked. In general, the tracking system 102 may be configured to sample and record at a high frame rate (e.g., 25 Hz). The tracking system 102 may be configured to store player identity and location information (e.g., (x, y) locations) for all agents and objects on the playing surface at least for each frame in the game file 110.

The game file 110 may be augmented with other event information corresponding to event data such as, but not limited to, game event information (pass, shot, miss, etc.) and background information (current score, time remaining, etc.).

The tracking system 102 may be configured to communicate with the organization computing system 104 via a network 105. The organization computing system 104 may be configured to manage and analyze data captured by the tracking system 102. The organization computing system 104 may include at least a web client application server 114, a pre-processing engine 116, a data store 118, and a score prediction agent 120. Each of the pre-processing engine 116 and the goal prediction engine 120 may include one or more software modules. The one or more software modules may be code or an assemblage of instructions stored on a medium (e.g., a memory of the organization computing system 104) that represents a sequence of machine instructions (e.g., program code) that implement one or more algorithm steps. Such machine instructions may be the actual computer code that the processor of the organization computing system 104 interprets to implement the instructions, or alternatively, may be higher-level code that is interpreted to obtain the instructions of the actual computer code. The one or more software modules may also include one or more hardware components. One or more aspects of the example algorithm may be performed by a hardware component (e.g., a circuit) itself, rather than as a result of instructions.

The data store 118 may be configured to store one or more game files 124. Each game file 124 may include spatial event data and non-spatial event data. For example, spatial event data may correspond to raw data captured by the tracking system 102 from a particular game or event. The non-spatial event data may correspond to one or more variables describing an event that occurred in a particular contest without associated spatial information. For example, the non-spatial event data may include each shot attempt in a particular competition. In some embodiments, the non-spatial event data may be derived from spatial event data. For example, the pre-processing engine 116 may be configured to parse the spatial event data to derive the shot attempt information. In some embodiments, the non-spatial event data may be derived independently of the spatial event data. For example, an administrator or entity associated with an organization computing system may analyze each contest to generate such non-spatial event data. Thus, for purposes of this application, event data may correspond to spatial event data and non-spatial event data.

In some embodiments, each game file 124 may further include a current score for each time t during the game, where the game is played, a roster for each team, a time of presence for each team, and statistics associated with each team and each player.

The preprocessing agent 116 can be configured to process data retrieved from the data store 118. For example, the preprocessing agent 116 may be configured to generate one or more sets of information that may be used to train one or more neural networks associated with the score prediction agent 120. The preprocessing agent 116 can scan each of the one or more game files stored in the data store 118 to identify one or more statistics corresponding to each specified data set and generate each data set accordingly. For example, the preprocessing agent 116 may scan each of one or more game files in the data store 118 to identify one or more shots attempted in each game and identify one or more coordinates associated with the shots (e.g., a shot start coordinate, an end position coordinate, a goalkeeper start position coordinate, etc.).

The score prediction agent 120 may be configured to generate a "personalized prediction" of the outcome of a particular scored event. In some embodiments, an athletic event may be defined as a scoring attempt during the course of the athletic event. Exemplary scoring events may include, but are not limited to, a basketball shot attempt, a penalty attempt, a dartboard pass attempt, a dartboard shoot attempt, a shot attempt, a hockey penalty shot attempt, a baseball shot, a football shot attempt, a football penalty attempt, a golf putting attempt, a golf swing attempt, and the like. Although the following discussion focuses on a particular example related to soccer, one skilled in the art may readily appreciate that such operations may be extended to one or more scoring events in any type of athletic event. In some embodiments, the scoring prediction agent 120 may be configured to generate a predicted outcome of a shot based on at least one or more of a shot start position (x, y), a shot end position (x, y, z), a goalie start position (x, y), a game time, a half-field, a score, a location, a player identity (e.g., a goalie identity), one or more manual geometric features, and body pose information. Accordingly, the score prediction agent 120 may generate a predicted outcome of the shot based on the one or more fixed variables and the one or more dynamically updated embeddings and features to predict the chance that the shot will be suppressed, where the shot is, and the like. In some embodiments, if given the same circumstances (i.e., the same shooting attempts), score prediction agent 120 may be configured to strictly allow the exchange of goalies to compare performance. Still further, in some embodiments, score prediction agent 120 may be configured to allow a given goalkeeper to be analyzed on the job of that goalkeeper.

The score prediction agent 120 may include an artificial neural network 126 and a body posture agent 128. The artificial neural network 126 may be configured to predict whether a given shot will be successfully defended (i.e., no goal) or unsuccessfully defended (i.e., goal), which agents are in the event (e.g., on the course) at a given time. For example, the neural network module 220 may be configured to learn how to predict the outcome of a given shot based on, for example, one or more of a shot start location (x, y), a shot end location (x, y, z), a goalkeeper start location (x, y), a game time, a half-field, a score, a place, a player identity (e.g., a goalkeeper identity), one or more manual geometric features, and body pose information.

The body pose agent 128 may be configured to generate one or more metrics related to the body pose of at least one or more of a goalkeeper and a shooter for a given shot. In some embodiments, the body pose agent 128 may generate body pose information based on event data captured by the tracking system 102. In some embodiments, the body pose agent 128 may generate body pose information from a broadcast stream provided by a broadcast provider. The body posture agent 128 can identify, for example, a shooter starting position and angle, a running type (e.g., pause and speed), a shooting start (e.g., body tilt angle, upper body angle, hip orientation, kicking arm position, shoulder alignment, etc.), and the like. In addition, the original position of the body position in 2D or 3D, displayed as a skeleton, can be used to detect and associate certain key actions in sports.

The client device 108 may communicate with the organization computing system 104 via the network 105. The client device 108 may be operated by a user. For example, the client device 108 may be a mobile device, a tablet, a desktop computer, or any computing system having the capabilities described herein. The user may include, but is not limited to, an individual, such as a subscriber, client, prospective client, or customer of an entity associated with the organization computing system 104, such as an individual who has obtained from an entity associated with the organization computing system 104, will obtain from an entity associated with the organization computing system 104, or may obtain a product, service, or consultation from an entity associated with the organization computing system 104.

Client device 108 may include at least application 126. Application 126 may represent a web browser or a standalone application that allows access to a website. Client device 108 may access application 126 to access one or more functions of organization computing system 104. The client devices 108 may communicate over the network 105 to request web pages, for example, from a web client application server 114 of the organization computing system 104. For example, the client device 108 may be configured to execute an application 126 to access content managed by the web client application server 114. Content displayed to the client device 108 may be transmitted from the web client application server 114 to the client device 108 and subsequently processed by the application 126 for display via a Graphical User Interface (GUI) of the client device 108.

Fig. 2 is a block diagram illustrating an Artificial Neural Network (ANN) architecture 200, according to an example embodiment. The ANN structure 200 may represent the artificial neural network 126.

The ANN structure 200 may represent a four-layer feed-forward neural network. As shown, the ANN structure 200 may include an input layer 202, a first hidden layer 206, a second hidden layer 208, and an output layer 210.

The input layer 202 may represent one or more inputs 204 provided to the artificial neural network 126₁-204₅(generally "input 204"). For example, input 204₁Can point to the shooting start position, input 204₂Input 204, which may correspond to a goalkeeper position₃Inputs 204, which may correspond to points, times, and shot end positions₄May correspond to a dynamic goalkeeper embedding, and input 204₅May correspond to body posture information.

In some embodiments, to train and test the artificial network 126, one or more inputs 204 in the input layer 202 may be selected from data from three seasons (e.g., 2016-. The information may be divided into training and test sets (e.g., 80%/20%, respectively).

The size of the first hidden layer 206 may be 12. For example, the first hidden layerThe first hidden layer 206 may use a linear rectifying unit (ReLu) activation function. The size of the second hidden layer 208 may be 8. For example, a second hidden layerThe second hidden layer 208 may be implemented with a ReLu activation function.

The output layer 208 may be configured to generate an output prediction. For example, the output layer 208 may be configured to output "goals" or "puffs" as possible options for each respective shot. The output layer 208 may be implemented with a sigmoid activation function.

FIG. 3 is a flow diagram illustrating a method 300 of generating a fully trained predictive model according to an example embodiment. The method 300 may begin at step 302.

At step 302, the score prediction agent 120 may retrieve event data for a plurality of scoring attempts across a multi-match (e.g., a shoot attempt in soccer). For example, the score prediction agent 120 may retrieve spatial event data from the data store 118. The spatial event data may capture, in x, y coordinates and time stamps, each touch of the ball as well as non-spatial event data, i.e., one or more variables describing one or more events without associated spatial information. In some embodiments, the preprocessing agent 112 may be configured to parse the retrieved event data to identify one or more portions of the event data that include a shot attempt. For example, the preprocessing agent 112 may extract one or more portions from the event data such that only the event data corresponding to the shot attempt is included therein.

At step 304, the score prediction agent 120 may generate a first data set corresponding to the score attempt start location. For example, the score prediction agent 120 may parse one or more event data sets retrieved from the data store 118 to identify a shot start location for each shot identified therein. In some embodiments, the shot start position information may include x, y data coordinates. In some embodiments, the shot start position information may include x, y, z data coordinates. For example, additional contextual features such as, but not limited to, a head heading, or left or right foot in the ground or in the clear (e.g., a cut).

At step 306, the score prediction agent 120 may generate a second data set corresponding to the athlete's position. For example, the score prediction agent 120 may parse one or more event data sets retrieved from the data store 118 to identify a goalie location corresponding to each shot identified therein. In some embodiments, the score prediction agent 120 may associate the identified goalkeeper position with a corresponding start shot position.

At step 308, the score prediction agent 120 may generate a third data set corresponding to the score, time, and goal information. For example, the score prediction agent 120 may parse one or more sets of event data retrieved from the data store 118 to identify, for each shot, a time at which the shot occurred, a fraction of the shot occurred, a half-field at which the shot occurred, a location at which the shot occurred, and one or more geometric features. Such geometric features may include, but are not limited to, the front and goalkeeper angles and the distance to the center of the goal and each other.

At step 310, the score prediction agent 120 may generate a fourth data set corresponding to one or more player insertions. For example, one or more goalkeeper embeddings can transform the learning process from learning the habits of a general, ordinary goalkeeper to learning the habits of each specific goalkeeper. In other words, to make the prediction more personalized, the score prediction agent 120 may capture the identity of the goalkeeper for each shot. For each goalkeeper, score prediction agent 120 may be configured to generate a spatial descriptor for the goalkeeper, thereby capturing the goalkeeper's impact on the goal result. Such spatial descriptors may contain a large amount of information about the strength and vulnerability of the goalkeeper. For example, the one or more spatial descriptors may include, but are not limited to: a percentage of zero goals lost, a percentage of wins, a percentage of puffs of shots ending in the middle, left and right third of the goal, a percentage of puffs of shots directly to the goalkeeper or to the right or left of the goalkeeper, etc. These spatial descriptors may be dynamic in nature. In this way, spatial descriptors can be generated at the season level and on the x-match rolling window average (e.g., 10 matches) to capture the goalkeeper's cold-hot win.

In some embodiments, the method 300 may further include step 312. At step 312, the score prediction agent 120 may generate a fifth data set corresponding to the athlete's body position information. For example, body pose agent 128 may be configured to generate body pose information for each pair of front and goalkeeper in the event data.

Generally, in the european football game, the penalty is considered to be the most controlled scoring situation. Penalty balls are usually good for the front, and only 30% of penalty balls are saved by goalkeepers. In some embodiments, to be able to determine the goalkeepers' distinctions from each other, the score prediction agent 120 may override the event data to use more refined body pose data. Such body pose data may include, but is not limited to, shooter starting position and angle, running type (e.g., pause and speed), shooting start (e.g., body tilt angle, upper body angle, hip orientation, kicking arm position, shoulder alignment, etc.), and the like.

At step 314, the score prediction agent 120 may be configured to learn whether each score attempt was successful based on the data set. For example, the score prediction agent 120 may be configured to train the artificial neural network 126 using the first through fifth data sets to predict whether a goalkeeper will block or allow a goal. Because the scoring prediction agent 120 considers one or more gatekeeper embeddings, the scoring prediction agent 120 may be configured to train the artificial neural network 126 on a more granular basis. For example, rather than providing a determination based on an ordinary goalkeeper, the artificial neural network 126 may be trained to output different predictions based on one or more spatial descriptors of a given goalkeeper.

At step 316, the score prediction agent 120 may output the fully trained model. For example, the score prediction agent 120 may output a fully trained model configured to receive shot attempt information and determine whether a particular goalkeeper will miss or block a shot attempt.

FIG. 4 is a flow diagram illustrating a method 400 of generating a shot prediction using a fully trained predictive model according to an example embodiment. The method 400 may begin at step 402.

At step 402, the score prediction agent 120 may receive contest data for a given contest. For example, the score prediction agent 120 may receive pre-shot information for a shot attempt by a particular goalkeeper. In some embodiments, the score prediction agent 120 may receive contest data from the tracking system 102. In some embodiments, the score prediction agent 120 may receive the contest data from the client device 108. For example, a user may request, via the application 132, a prediction for a given goal in a given contest.

At step 404, the score prediction agent 120 may extract one or more parameters associated with the goal from the contest data. For example, the score prediction agent 120 may be configured to generate one or more input values for the artificial neural network 126 by selectively extracting one or more parameters associated with the goal. In some embodiments, the one or more parameters may include, but are not limited to, one or more of the following: shooting position (x, y) coordinates, goalkeeper position (x, y, z) coordinates, current time of the game, current score of the game, location, one or more manual geometric features, shooter start position and angle, type of running (e.g., pause and speed), and the like.

At step 406, the score prediction agent 120 may identify a goalkeeper who guards the goal. For example, the score prediction agent 120 may parse the contest data for a given contest and identify a particular goalkeeper defending a goal received from the front.

At step 408, the score forecasting agent 120 may generate an identity value for the gatekeeper. In some embodiments, the score prediction agent 120 may generate the identity value of the gatekeeper based on one or more embeddings generated during a training/testing phase of the artificial neural network 126. For example, the score prediction agent 120 may utilize the same or similar spatial descriptors of goalies used during the training/testing phase. This may allow the artificial neural network to identify a particular goalkeeper.

At step 410, the score prediction agent 120 may predict whether the goal attempt will be successful or unsuccessful. In other words, the score prediction agent 120 may predict whether a goalkeeper will lose the ball or block a shot attempt. The score prediction agent 120 may use the artificial neural network 126 to predict the outcome of the goal attempt. For example, the score prediction agent 120 may provide the extracted one or more parameters associated with the goal attempt and the identity information of the goalkeeper as input to the artificial neural network 126. The score prediction agent 120 may generate as output a predicted result of the shot attempt (i.e., goal or no goal).

Fig. 5A is a flow diagram illustrating a method 500 of generating a goalkeeper rank based on the number of simulated goals lost, according to an example embodiment. The method 500 may begin at step 502.

At step 502, the score prediction agent 120 may identify a goal set over a period of time t, e.g., the score prediction agent 120 may receive a request from the client device 108 via the application 132 to generate a gatekeeper ranking across the period of time t. In some embodiments, t may represent a number of contests, a full season, multiple seasons, etc. In some embodiments, the user may limit the request to a particular tournament (e.g., england super League, MLS, federal League, etc.).

At step 504, the score prediction agent 120 may simulate the number of goals that a common goalkeeper will want to lose/block during time t based on the identified set of goals. For example, the score prediction agent 120 may identify one or more parameters associated with each shot. Such parameters may include, but are not limited to, shot starting position information (e.g., x, y data coordinates), goalkeeper position (e.g., x, y, z data coordinates), time of shot occurrence, fraction of shot occurrence, half-time of shot occurrence, location of shot occurrence, front and goalkeeper angles, distance to goal center, and distance from each other, and body pose data may include, but is not limited to, shot starting position and angle, type of running (e.g., pause and speed), shot initiation (e.g., body tilt angle, upper body angle, hip direction, kickarm position, shoulder alignment, etc.), and the like.

At step 506, the score prediction agent 120 may identify a target gatekeeper. In some embodiments, the score prediction agent 120 may cycle through all available gatekeepers in all tournaments. In some embodiments, the score prediction agent 120 may cycle through all available gatekeepers defended against a threshold number of goals (e.g., at least 60 times). In some embodiments, the user may specify a gatekeeper set for ranking via the application 132.

At step 508, the score prediction agent 120 may generate one or more embeddings of the target gatekeeper. For example, the score prediction agent 120 may inject a gatekeeper's personalization descriptor into the extracted parameters. In some embodiments, score prediction agent 120 may iteratively inject one or more embeddings of each gatekeeper used for analysis into the extracted parameters. By injecting one or more personalized inserts into the data set used to simulate the amount of goals of an ordinary goalkeeper, the score prediction agent 120 may generate a data set that may be used to analyze the performance of each goalkeeper relative to an ordinary goalkeeper.

At step 510, the score prediction agent 120 may simulate the number of goals that the target goalie will miss/block based on the set of goals identified during time t and one or more embeddings of the target goalie. For example, the scoring prediction agent 120 may simulate the number of goals based on the goalie's personalized descriptor, the shot start location information (e.g., x, y data coordinates), the goalie's location (e.g., x, y, z data coordinates), the time the shot occurred, the fraction of the shot occurred, the half-field of the shot occurred, the place where the shot occurred, the front and goalie angles, the distance to the center of the goal and the distance between each other, and the body pose data may include, but is not limited to, the goalie start location and angle, the type of running (e.g., pause and speed), the shot launch (e.g., body tilt angle, upper body angle, hip direction, kicking arm position, shoulder alignment, etc.), and the like. In other words, the score prediction agent 120 may utilize the same parameters and one or more embeddings as used in step 506 above.

At step 512, the score prediction agent 120 may output a graphical representation of the gatekeeper ranking. One or more goalkeepers may be ranked based on the number of goals/goals blocked relative to a common goalkeeper. In some embodiments, this may be determined by subtracting the output generated in step 508 from the output generated in step 504. For example, for each goalkeeper, score prediction agent 120 may process the output generated in step 512 (i.e., the goalkeeper-specific output) based on the output generated in step 506 (i.e., the normal goalkeeper output) to generate a goal +/-value. In some embodiments, the graphical representation may be a list that ranks each goalkeeper. In some embodiments, the graphical representation may be a chart that ranks each goalkeeper. An exemplary graphical representation is discussed below in conjunction with fig. 5B.

Fig. 5B is a block diagram illustrating an exemplary graphical user interface 550, according to an example embodiment. GUI 550 may include a graphical representation of a goalkeeper dynamically embedded cluster. For example, as previously described, because the dynamic embedded features capture differences between gatekeepers, it should be possible to see significant separation in the data sets, and more particularly, should see elite shoot terminators in one cluster 552 and poor shoot terminators in another cluster 554. In some embodiments, due to the high dimensionality of the embedding, score prediction agent 120 may apply a t-distribution random neighborhood embedding (t-SNE) multidimensional descent technique to identify one or more clusters (e.g., cluster 552 and cluster 554). As shown, the highest scoring goalkeeper is included in the top cluster (i.e., cluster 552), while the lowest scoring goalkeeper is included in the bottom cluster (i.e., cluster 554).

FIG. 6A is a flow diagram illustrating a method 600 of comparing goalkeepers using a simulation process, according to an example embodiment. The method 600 may begin at step 602.

At step 602, the score prediction agent 120 may identify a first goalkeeper and a second goalkeeper. In some embodiments, the score prediction agent 120 may receive a request from the client device 108 via the application 132 to compare the second goalkeeper with the first goalkeeper. For example, the score prediction agent 120 may receive a request to generate a more personalized goal admission prediction by looking at how the second goalkeeper will replace the first goalkeeper.

At step 604, the score prediction agent 120 may retrieve data corresponding to one or more goals guarded by the first goalkeeper. For example, the score-predicting agent 120 may retrieve one or more parameters associated with one or more goals defended by the first goalie within a selected time period t, where t may represent a single shooting attempt, a single game, a set of games, a single season, multiple seasons, a profession, or the like. Such parameters may include, but are not limited to, shot starting position information (e.g., x, y data coordinates), goalkeeper position (e.g., x, y, z data coordinates), time of shot occurrence, fraction of shot occurrence, half-time of shot occurrence, location of shot occurrence, front and goalkeeper angles, distance to goal center, and distance from each other, and body pose data may include, but is not limited to, shot starting position and angle, type of running (e.g., pause and speed), shot initiation (e.g., body tilt angle, upper body angle, hip direction, kickarm position, shoulder alignment, etc.), and the like.

At step 606, the score prediction agent 120 may generate one or more embeddings of a second gatekeeper. For example, the score prediction agent 120 may inject a personalization descriptor for the second goalkeeper into the extracted parameters. By injecting one or more personalized inserts into the data sets corresponding to one or more goals guarded by a first goalkeeper, the score prediction agent 120 effectively exchanges goalkeeper identities to simulate how a second goalkeeper will deal with the one or more goals that the first goalkeeper is facing.

At step 608, the score prediction agent 120 may simulate the amount of time the second goalkeeper will lose/block goals based on the goal sets identified during time t and one or more embeddings of the second goalkeeper. For example, the scoring prediction agent 120 may simulate the number of goals based on the second goalie's personalized descriptor, the shot start location information (e.g., x, y data coordinates), the goalie's location (e.g., x, y, z data coordinates), the time the shot occurred, the fraction of the shot occurred, the half-field of the shot occurred, the place where the shot occurred, the front and goalie angles, the distance to the center of the goal, and the distance between each other, and the body pose data may include, but is not limited to, the goalie start location and angle, the type of running (e.g., pause and speed), the start of the shot (e.g., body tilt angle, upper body angle, hip direction, kick arm position, shoulder alignment, etc.), and so forth.

At step 610, the score prediction agent 120 may output a graphical representation that compares the second goalkeeper with the first goalkeeper. In some embodiments, the score prediction agent 120 may output a graphical representation on a goal-by-goal basis. For example, the score prediction agent 120 may generate a shoot simulation chart showing the number of goals missed by the second goalkeeper relative to the first goalkeeper. An exemplary graphical representation is discussed below in conjunction with fig. 6B.

Examples of the invention

To demonstrate the ability of the score prediction agent 120 to simulate goalkeeper skills, each goalkeeper confronted with over 60 goals from the european "quintet" at the season of 2017/2018 was simulated by exchanging the dynamic embedding of goalkeepers. The results are as follows.

First 10 goalkeeper

TABLE 1

Last 10 goalkeeper

TABLE 2

Fig. 6B is a block diagram of a graphical user interface 650 showing a simulated goal map 652, according to an example embodiment. As shown, the simulated goal map 652 may show an analysis of goals defended by the goalies of the liriops, lores Karius and Simon Mignolet, and how aisson would behave for the same goal. Such analysis may be performed, for example, by exchanging identities (i.e., spatial descriptors), using one or more of the operations discussed above in connection with fig. 6A. In some embodiments, the simulated goal map 652 may be a weighted two-dimensional gaussian distribution for whether the 2017/2018 season sports-card team lost the ball. Each shot may be weighted by the difference in expected saving between goalies. The first color shows where Alisson increases the chance of a fire for a fire, and shows where Karius/Mignolet increases the chance of a fire for a fire. As shown, no portion of the simulated goal map 652 is in the second color. Thus, given each shot, if Alisson is a Li-Pushing team at 2017/2018 season, they may expect fewer seven shots to miss.

FIG. 7A is a flowchart illustrating a method 700 of comparing gatekeeper seasons using a simulation process in accordance with exemplary embodiments. The method 700 may begin at step 702.

At step 702, the score prediction agent 120 may identify a target goalkeeper. In some embodiments, the score prediction agent 120 may receive a request from the client device 108 via the application 132 to compare the target goalkeeper in his or her current form with the goalkeeper's previous form. In other words, the score prediction agent 120 may receive a request to analyze goalkeeper behavior to determine whether the goalkeeper has improved during a profession, season, race span, etc.

At step 704, the score prediction agent 120 retrieves data corresponding to one or more goals guarded by a goalkeeper at a first stride. For example, the score prediction agent 120 may retrieve one or more parameters associated with one or more goals defended by the target goalie within a first time span t, where t may represent a single shot attempt, a single game, a set of games, a single season, multiple seasons, or the like. Such parameters may include, but are not limited to, shot starting position information (e.g., x, y data coordinates), goalkeeper position (e.g., x, y, z data coordinates), time of shot occurrence, fraction of shot occurrence, half-time of shot occurrence, location of shot occurrence, front and goalkeeper angles, distance to goal center, and distance from each other, and body pose data may include, but is not limited to, shot starting position and angle, type of running (e.g., pause and speed), shot initiation (e.g., body tilt angle, upper body angle, hip direction, kickarm position, shoulder alignment, etc.), and the like.

At step 706, the score prediction agent 120 may generate one or more inlays corresponding to the target goalkeeper based on a second time span, wherein the second time span is different from the first time span. For example, the score prediction agent 120 may inject a personalization descriptor of a second goalkeeper into the extracted parameters based on a second time space. By injecting one or more personalized inlays into the data set corresponding to one or more goals guarded by the first goalie, the score prediction agent 120 effectively exchanges goalie identities to simulate how the target goalie will cope with the one or more goals that the target goalie is facing in the form represented during the first timeframe in the form represented during the second timespan. This operation is possible because the dynamics of goalkeeper embedding can change from season to season, to match, etc.

At step 708, the score prediction agent 120 may simulate the number of goals that the target goalkeeper will lose/the number of blocked goals in the form represented in the second time span based on the set of goals identified during the first time span and one or more embeddings of the target goalkeeper generated using the goalkeeper data in the second time span. For example, the scoring prediction agent 120 may simulate the number of goals based on the second goalkeeper's personalized descriptor, the shot starting location information (e.g., x, y data coordinates), the goalkeeper's location (e.g., x, y, z data coordinates), the time the shot occurred, the fraction of the shot occurred, the half-field of the shot occurred, the place where the shot occurred, the front and goalkeeper angles, the distance to the goal center, and the distance between each other in a second time span, and the body pose data may include, but is not limited to, the shooter starting location and angle, the type of running (e.g., pause and speed), the shot launch (e.g., body tilt angle, upper body angle, hip direction, kick arm position, shoulder alignment, etc.), and the like.

At step 710, the score prediction agent 120 may output a graphical representation comparing the performance of the target goalkeeper. In some embodiments, the score prediction agent 120 may output a graphical representation on a goal-by-goal basis. For example, the score prediction agent 120 may generate a shoot simulation chart showing the number of goals that the second goalie loses in the case where the goalie is in the form represented in the second time span. An exemplary graphical representation is discussed below in conjunction with fig. 7B.

Fig. 7B is a block diagram of a graphical user interface 750 showing a simulated goal map 752, according to an example embodiment. As described above in Table 2, Joe Hart (Joe, hatt) is one of the worst performing goalkeepers in the 2017-18 season quinqueous tournament. Using one or more of the operations discussed above in connection with fig. 7A, score prediction agent 120 may determine whether the ranking is permanent or time varying. As previously described, because the embedding may be dynamic in nature, the score prediction agent 120 is able to measure how the gatekeeper changes, for example, between seasons. The simulated goal map 150 shows how Joe Hart performs in 2018-19 season compared to the goal attempts defended by Joe Hart in 2017-18 season. In some embodiments, the simulated shoot map 752 may be a weighted two-dimensional gaussian distribution. Each shot may be weighted by the difference in expected puffs between the 2018-19 season Joe Hart and the 2017-18 season Joe Hart. The first color (e.g., gray) shows that the 2018-19 season Joe Hart increases the chance of a fire for a rescue, while the second color shows, for example, that the 2017 season Joe Hart increases the chance of a fire for a rescue. As shown, no portion of the simulated goal map 652 is the second color. Thus, considering each goal shot, if the Western Hamming Union (West Ham) was validated at 2017/2018 for Joe Hart at the 2018-19 season instead of Joe Hart at the 2017-18 season, they could expect eight balls to be missed less.

FIG. 8A illustrates a system bus computing system architecture 800, according to an example embodiment. The system 800 may represent at least a portion of the organization computing system 104. One or more components of system 800 may be in electrical communication with each other using bus 805. The system 800 may include a processing unit (CPU or processor) 810 and a system bus 805 that couples various system components including the system memory 815, such as a Read Only Memory (ROM)820 and a Random Access Memory (RAM)825 to the processor 810. System 800 may include a cache of high-speed memory directly connected to processor 810, in close proximity to processor 810, or integrated as part of processor 810. The system 800 may copy data from the memory 815 and/or the storage device 830 to the cache 812 for quick access by the processor 810. In this way, cache 812 may provide a performance boost that avoids delays while processor 810 is waiting for data. These and other modules may control or be configured to control processor 810 to perform various actions. Other system memories 815 may also be used. The memory 815 may include a number of different types of memory having different performance characteristics. Processor 810 may include any general purpose processor and hardware or software modules configured to control processor 810 as well as special purpose processors, such as services 1832, services 2834, and services 3836 stored in storage device 830, where the software instructions are incorporated into the actual processor design. The processor 810 may be an entirely separate computing system containing multiple cores or processors, buses, memory controllers, caches, and the like. The multi-core processor may be symmetric or asymmetric.

To enable a user to interact with computing device 800, input device 845 may represent any number of input mechanisms, such as a microphone for speech, a touch-sensitive screen for gesture or graphical input, a keyboard, a mouse, motion input, speech, or the like. The output device 835 may also be one or more of a variety of output mechanisms known to those skilled in the art. In some instances, the multimodal system may enable a user to provide multiple types of input to communicate with the computing device 800. Communication interface 840 may generally govern and manage user input and system output. There is no limitation to the operation on any particular hardware arrangement, and thus the basic features herein may be readily replaced with developed modified hardware or firmware arrangements.

The storage device 830 may be a non-volatile memory and may be a hard disk or other type of computer-readable medium that can store data that is accessible by a computer, such as magnetic cassettes, flash memory cards, solid state memory devices, digital versatile disks, magnetic cassettes, Random Access Memories (RAMs) 825, Read Only Memories (ROMs) 820, and mixtures thereof.

Storage device 830 may include services 832, 834, and 836 for controlling processor 810. Other hardware or software modules are contemplated. A storage device 830 may be connected to the system bus 805. In one aspect, a hardware module that performs a particular function may include software components stored in a computer-readable medium that interface with the necessary hardware components to perform that function, such as processor 810, bus 805, display 835, and the like.

Fig. 8B illustrates a computer system 850 having a chipset architecture, which may represent at least a portion of the organization computing system 104. Computer system 850 may be an example of computer hardware, software, and firmware that may be used to implement the disclosed technology. System 850 may include a processor 855 that represents any number of physically and/or logically distinct resources capable of executing software, firmware, and hardware configured to execute the identified computing instructions. The processor 855 may be in communication with a chipset 860, which chipset 860 may control inputs to the processor 855 and outputs from the processor 855. In this example, chipset 860 outputs information to an output 865, such as a display, and may read and write information to a storage device 870, which may include, for example, magnetic media and solid state media. The chipset 860 may also read data from RAM 875 and write data to RAM 875. A bridge 880 may be provided for interfacing with various user interface components 885 for interfacing with chipset 860. Such user interface components 885 may include a keyboard, a microphone, touch detection and processing circuitry, a pointing device such as a mouse, and the like. In general, the inputs to system 850 can come from any of a variety of sources, machine-generated and/or human-generated.

Chipset 860 may also interface with one or more communication interfaces 890, which may have different physical interfaces. Such communication interfaces may include interfaces for wired and wireless local area networks, for broadband wireless networks, and personal area networks. Some applications of the methods for generating, displaying, and using the GUIs disclosed herein may include receiving ordered data sets through a physical interface, or generated by the machine itself through the processor 855 analyzing data stored in the storage 870 or 875. Further, the machine may receive inputs from the user through the user interface component 885 and perform appropriate functions, such as browsing functions, by interpreting the inputs using the processor 855.

It is to be appreciated that the example systems 800 and 850 can have more than one processor 810, or can be part of a group or cluster of computing devices networked together to provide greater processing power.

While the foregoing is directed to the embodiments described herein, other and further embodiments may be devised without departing from the basic scope thereof. For example, aspects of the present disclosure may be implemented in hardware or software or a combination of hardware and software. One embodiment described herein may be implemented as a program product for use with a computer system. The program(s) of the program product define functions of the embodiments (including the methods described herein) and can be contained on a variety of computer-readable storage media. Exemplary computer readable storage media include, but are not limited to: (i) non-writable storage media (e.g., read-only memory (ROM) devices within a computer such as CD-ROM disks readable by a CD-ROM drive, flash memory, ROM chips or any type of solid-state non-volatile memory) on which information is permanently stored; and (ii) writable storage media (e.g., floppy disks within a diskette drive or hard-disk drive or any type of solid-state random-access memory) on which alterable information is stored. Such computer-readable storage media, when carrying computer-readable instructions that direct the functions of the disclosed embodiments, are embodiments of the present disclosure.

Those skilled in the art will appreciate that the foregoing examples are illustrative and not limiting. All substitutions, enhancements, equivalents, and modifications which are intended to be obvious to one skilled in the art after having read the specification and studied the drawings are intended to be included within the true spirit and scope of the present disclosure. It is therefore intended that the following appended claims include all such modifications, permutations and equivalents as fall within the true spirit and scope of these teachings.