DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Objection to Drawings
The drawings are objected to because figure 5B describes [0161] a method of predicting
player performance in a second league for a player from a first league, but the figure in block 560 reads “Project Player Performance in a Second Game,” a potential typographical error. As currently written, it appears that the output of the method of predicting player performance in a second league is next game performance which clashes with the stated intent of the process of figure 5B. Of note, [0170] discusses the application of the padding module to predict next game performance and that approach may be applied to the performance in the next league as well, but that is not overtly stated in [0170]. In any event, either correction is required to figure 5B or clarification to [0170], to ensure proper understanding of next game or next league predictions made by the invention. Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Claim Rejections – 35 U.S.C. § 101
35 U.S.C. § 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefore, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. § 101 because the claimed invention is directed
to non-statutory subject matter. The claims, 1-20, are directed to a judicial exception (i.e., law of nature, natural phenomenon, abstract idea) without providing significantly more.
Step 1
Step 1 of the subject matter eligibility analysis per MPEP § 2106.03, required the claims to be a process, machine, manufacture or a composition of matter. Claims 1-20 are directed to a process (method), and machine (system), which are statutory categories of invention.
Step 2A
Claims 1-20 are directed to abstract ideas, as explained below.
Prong one of the Step 2A analysis requires identifying the specific limitation(s) in the claim under examination that the examiner believes recites an abstract idea and determining whether the identified limitation(s) falls within at least one of the groupings of abstract ideas of mathematical concepts, mental processes, and certain methods of organizing human activity.
Step 2A-Prong 1
The claims recite the following limitations that are directed to abstract ideas, which can be summarized as being directed to a method, the abstract idea, of analyzing the performance of a player playing a sport in a first league and predicting the player’s predicted level of performance in a second league.
Claim 1 discloses a method, comprising: A method for utilizing tracking data to predict a player rating, the method comprising:
receiving broadcast data for a plurality of games in a first league, the plurality of games including a first player;
generating tracking data for each of the plurality of games, the tracking data
comprising coordinates of player positions and ball positions for each frame of the broadcast data, (following rules or instructions, observation, evaluation, judgment, performance);
receiving play-by-play data for each of the plurality of games, the play-by-play
data describing events that occur within the plurality of games;
merging the tracking data and play-by-play data to generate a set of input
features; (following rules or instructions, observation, evaluation, judgment, performance), and
predicting, based on the set of input features, a player rating for the first player, (following rules or instructions, observation, evaluation, judgment, performance),
the player rating being indicative of a predicted level of performance in a second league.
Additional limitations disclose more of the method, including, receiving box score data and merging with tracking data and play-by-play data to generate inputs features, (following rules or instructions, observation, evaluation, judgment, opinion - claim 2), applying a multiplier to the box score based on first league and year of the player playing, (following rules or instructions, observation, evaluation, judgment, opinion - claim 3), incorporating biographical data for the player, (following rules or instructions, observation, evaluation, judgment, opinion - claim 4), where merging data employs a fuzzy logic algorithm, (following rules or instructions, observation, evaluation, judgment, opinion - claim 5), reducing random noise in the inputs using mean-regression, (following rules or instructions, observation, evaluation, judgment, opinion - claim 6), predicting using a random forest classification algorithm a classification of whether the player is drafted in the second league and incorporating that with the input features, (following rules or instructions, observation, evaluation, judgment, opinion - claim 7), predicting by applying the artificial neural network, which bin of draft picks the player will be in and adding that to the input features, (following rules or instructions, observation, evaluation, judgment, opinion - claim 8), where the artificial neural network comprises a Relu and softmax actuation function, an Adam optimizer, and categorical cross entropy loss to the set of input features to predict the bin for the player, (following rules or instructions, observation, evaluation, judgment, opinion - claim 9), where predicting based on input features comprises player ratings for a separate year of the first player in the second league, (following rules or instructions, observation, evaluation, judgment, opinion - claim 10), and where predicting based on input features includes a second random forest algorithm, (following rules or instructions, observation, evaluation, judgment, opinion - claim 11), (claims 11-15 recite similar abstract ideas as those identified with respect to claims 1-4); providing inputs to a first and second player prediction model trained to find links between first game data of other players and time series data of target players and output a next game prediction of the target player, and generating the next game prediction for the target player, generating an adjustment weighting for the target player, providing those as training data, and training the first and second player prediction models using the training data, (following rules or instructions, observation, evaluation, judgment, opinion - claim 16), comparing the next game projection to the actual statistics of the target player, determining differences between the next game statistics and the actual statistics and adjusting the next game projection, (following rules or instructions, observation, evaluation, judgment, opinion - claim 17), where generating the first game data comprises generating an adjusted game one metric based on attributes that include weight, age, and draft pick number, (following rules or instructions, observation, evaluation, judgment, opinion - claim 18), where generating time-series data points for the player comprises padding the first game data with league average data, (following rules or instructions, observation, evaluation, judgment, opinion - claim 19), and generating a baseline value for each statistic using a Bayes filter based on padded first game data, (following rules or instructions, observation, evaluation, judgment, opinion - claim 20).
Each of these claimed limitations involve the application of abstract ideas to include organizing human activity by following rules or instructions, and/or employ mental processes involving observation, evaluation, judgment, and opinion.
Thus, the concepts set forth in claims 1-20 recite abstract ideas.
Step 2A-Prong 2
As per MPEP § 2106.04, while the claims 1-20 recite additional limitations which are hardware or software elements such as a system comprising a memory configured to store processor-readable instructions and a processor operatively connected to the memory, and configured to execute the instructions, a computing system, these limitations are not sufficient to qualify as a practical application being recited in the claims along with the abstract ideas since these elements are invoked as tools to apply the instructions of the abstract ideas in a specific technological environment. The mere application of an abstract idea in a particular technological environment and merely limiting the use of an abstract idea to a particular technological field do not integrate an abstract idea into a practical application (MPEP § 2106.05 (f) & (h)).
Evaluated individually, the additional elements do not integrate the identified abstract ideas into a practical application. Evaluating the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually.
The claims do not amount to a “practical application” of the abstract idea because they neither (1) recite any improvements to another technology or technical field; (2) recite any improvements to the functioning of the computer itself; (3) apply the judicial exception with, or by use of, a particular machine; (4) effect a transformation or reduction of a particular article to a different state or thing; (5) provide other meaningful limitations beyond generally linking the use of the judicial exception to a particular technological environment.
Accordingly, claims 1-20 are directed to abstract ideas.
Step 2B
Claims 1-20 do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements, when considered both individually and as an ordered combination, do not amount to significantly more than the abstract idea.
The analysis above describes how the claims recite the additional elements beyond those identified above as being directed to an abstract idea, as well as why identified judicial exception(s) are not integrated into a practical application. These findings are hereby incorporated into the analysis of the additional elements when considered both individually and in combination.
For the reasons provided in the analysis in Step 2A, Prong 1, evaluated individually, the additional elements do not amount to significantly more than a judicial exception. Thus, taken alone, the additional elements do not amount to significantly more than a judicial exception.
Evaluating the claim limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually. In addition to the factors discussed regarding Step 2A, prong two, there is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely amount to instructions to implement the identified abstract ideas on a computer.
Therefore, since there are no limitations in the claims 1-20 that transform the exception into a patent eligible application such that the claims amount to significantly more than the exception itself, the claims are directed to non-statutory subject matter and are rejected under 35 U.S.C. § 101.
Claim Rejections 35 U.S.C. §102
6. The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102(a)(1) that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on
sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-2, 5-8, 11-13, are rejected under 35 U.S.C. § 102(a)(1) as being taught by
Patton (US 11682209 B2), “Prediction of NBA Talent And Quality from Non-professional Tracking Data”.
Regarding Claim 1, Patton teaches, A method for utilizing tracking data to predict a player rating, the method comprising: (The computing system generates tracking data for each game from the broadcast video of a corresponding game, [1:31-33], implements a trained prediction model configured to predict the talent of future NBA players based, in part, on the generated tracking data [3:40-43], the computing system projects player performance, [Abstract]),
receiving broadcast data for a plurality of games in a first league, the plurality of
games including a first player; (A computing system identifies broadcast video for a plurality
of games in a first league, [1:37-38], an artificial intelligence and computer vision system configured to derive player-tracking data from broadcast video feeds, [5:16-22]).
generating tracking data for each of the plurality of games, (Tracking data system 116 may be configured to receive broadcast data from tracking system 102 and generate tracking data from the broadcast data, [5:16-18]), the tracking data comprising coordinates of player positions and ball positions for each frame of the broadcast data; (tracking data system 116 may map pixels corresponding to each player and ball to dots and may transform the dots to a semantically meaningful event layer, which may be used to describe player attributes, [5:25-28]),
receiving play-by-play data for each of the plurality of games, the play-by-play
data describing events that occur within the plurality of games; (play-by-play module 120 may receive a play-by-play feed corresponding to the broadcast video data. In some embodiments, the play-by-play data may be representative of human generated data based on events occurring within the game, [5:63-67]),
merging the tracking data and play-by-play data (to help identify events within the generated tracking data, tracking data system 116 may merge or align the play-by-play data with the raw generated tracking data, [6:11-13]), to generate a set of input features; (organization computing system 104 may go beyond the generation of tracking data
from broadcast video data. Instead, to provide descriptive analytics, as well as a useful feature
representation for prediction system 124, [5:54-58]), and
predicting, based on the set of input features, a player rating for the first player,
the player rating being indicative of a predicted level of performance in a second league, (a method of predicting player performance in a second league for a player from a first league, according to example embodiments, [2:43-46]).
Claim 12 recites substantially similar limitations as claim 1; therefore claim 12 is rejected with same rationale, reasoning and motivation as claim 1. In this claim, the addition of a system comprising a memory configured to store processor-readable instructions and a processor operatively connected to the memory, and configured to execute the instructions, [1:64-2:1], does not change the rationale for rejections under 35 U.S.C. § 103 or the referenced prior art.
Regarding Claim 2, Patton teaches the method of claim 1, further comprising:
receiving box score data for the plurality of games in the first league; and merging the box
score data with the tracking data and play-by-play data to generate the set of input features. (organization computing system 104 may enrich the tracking data. In some embodiments, enriching the tracking data may include tracking data system 116 merging play-by-play
data for an event with the generated tracking data. For example, play-by-play module 120 may receive a play-by-play feed corresponding to the broadcast video data. In some embodiments, the play-by-play data may be representative of human generated data based on events occurring within the game. Tracking data system 116 may merge or align the play-by-play data with the raw generated tracking data (which may include the game and shot clock), [10:56-67]), organization computing system 104 may pad the tracking data. For example, padding module 122 may create new player representations using mean-regression to reduce random noise in the features, [7:4-6], Because this approach can be applied to any game level statistic, padding
module 122 may be configured to apply such technique to every feature in both box-score and
AutoSTATS data, [7:18-21], configured to derive player-tracking data from broadcast video feeds, [5:21-22]).
Claim 13 recites substantially similar limitations as claim 2; therefore claim 13 is rejected with same rationale, reasoning and motivation as claim 2. In this claim, the addition of a system comprising a memory configured to store processor-readable instructions and a processor operatively connected to the memory, and configured to execute the instructions, [1:64-2:1], does not change the rationale for rejections under 35 U.S.C. § 103 or the referenced prior art.
Regarding claim 5, Patton teaches the method of claim 1, wherein merging the play-by-play data for each of the plurality of games with the tracking data of the plurality of games to generate the set of input features comprises:
combining the play-by-play data with optical character recognition data, the coordinates of player positions and ball positions using a fuzzy matching algorithm, (in some embodiments, tracking data system 116 may utilize a fuzzy matching algorithm, which may combine play-by-play data, optical character recognition data (e.g., shot clock, score, time remaining, etc.), and play/ball positions (e.g., raw tracking data) to generate the aligned tracking data, [13:15-20]).
Regarding claim 6, Patton teaches the method of claim 1, reducing random noise in the set of input features by creating new player representations using mean-regression, (organization computing system 104 may pad the tracking data. For example, padding module
122 may create new player representations using mean-regression to reduce random noise in the features, [7:4-6]).
Regarding claim 7, Patton teaches, the method of claim 1, further comprising:
predicting, by applying a first random forest classification algorithm, a classification for the
the classification being a prediction of whether the first player will be drafted in the second league; and incorporating the classification for the first player into the set of input features.
(raw data model 202 and padded data model 204 may be used to identify those players with greater than an x % (e.g., 40%) chance to make the NBA, [8:61-63], both the decorrelated raw and decorrelated padded data may be used in separate models and then ensembled to create three sets of predictions that may be carried forward. In some embodiments, each of raw data model 212 and padded data model 214 may be random forest regressors using a VORP (value over replacement player) pick values at each draft pick target, [9:4-10]).
Regarding claim 8, Patton teaches, the method of claim 1, further comprising:
predicting, a bin from a plurality of bins, (projecting, by the computing system, a
range of draft positions for each player of the subset of players based on the tracking data and the padded tracking data, [1:60-63]),
wherein the plurality of bins represent sets of draft picks in the second league; (FIG. 4 illustrates an exemplary chart corresponding to a draft talent bin prediction for Player B,
according to example embodiments, [2:37-39]), and
incorporating the predicted bin into the set of input features. (ensemble model 220 may be used to classify the player into one of several bins, with each bin representing a range of draft picks, [8:7-9]),
by applying an artificial neural network, (In some embodiments, each of the specialist event
detectors may be representative of a neural network, specially trained to identify a specific event type, [11:24-27]).
Regarding claim 11, Patton teaches, the method of claim 1, wherein predicting, based on the set of input features, the player rating for the first player, includes:
applying a second random forest algorithm to the set of input features, (Second set of models 203 may be used in conjunction with first set of models 201 for projecting a range of draft picks in which a player may fall, [8:64-66], both the decorrelated raw and decorrelated padded data may be used in separate models and then ensembled to create three sets of predictions that may be carried forward. In some embodiments, each of raw data model 212 and padded data model 214 may be random forest regressors using a VORP (value over replacement player) pick values at each draft pick target, [9:4-11]).
Claim Rejections 35 U.S.C. §103
The following is a quotation of 35 U.S.C. § 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 3, 14 are rejected under 35 U.S.C. § 103 as being taught by Patton (US 11682209
B2), “Prediction of NBA Talent And Quality From Non-professional Tracking Data,” in view of Avruskin, (CA 3067562 A1), System and Method for Statistically Predicting the Expected Performance of a Sporting Entity.”
Regarding claim 3, Patton teaches, the method of claim 2,
Patton does not teach, Avruskin teaches, further comprising: applying a multiplier to the box score data based on the first league, wherein the multiplier is based on the first league and particular year of the first player playing in the first league (statistically predicting the expected performance of a sporting entity, [abstract], receiving an actual performance outcome for the target performance metric; based on the actual performance outcome, determining the accuracy of the combined statistical data set; and based on the determined accuracy of the combined statistical data set, modifying the bias weightings assigned to each of the plurality of data categories, [0010], Data aggregator and processor may request data on past sporting events, scores and player statistics, [ ] In various cases, the data categories may include: (a) a sporting entity's "historical performance data", and (b) the sporting entity's "recent performance data," [ ] and In cases where the target performance metric relates to a particular athlete's performance, data categories can also include historical performance data, [0084]. A time interval filter limits data analyzed to data generated in a most recent three games played by the target athlete. The KPI filters applied in Table 2 are similar to those applied in Table 1. [0094] Table 3 shows data filters applied to global athlete historical data. The time interval filter is selected to include data within a seven-year time frame, [0094]).
It would have been obvious before the earliest effective filing date of this application to modify Patton’s player prediction method with the teachings of Avruskin in the use of bias weightings and based on actual outcomes, modifying the bias weightings to improve the predictive output and previous performance with the motivation to provide greater accuracy to the statistical data generator, [00104]. The claimed invention is a combination of existing elements and those elements, one of ordinary skill in the art recognizing the anticipated results and resulting benefit of modifying bias weightings to enhance modeling prediction.
Claim 14 recites substantially similar limitations as claim 3; therefore claim 14 is rejected with same rationale, reasoning and motivation as claim 3. In this claim, the addition of a system comprising a memory configured to store processor-readable instructions and a processor operatively connected to the memory, and configured to execute the instructions, [1:64-2:1], does not change the rationale for rejections under 35 U.S.C. § 103 or the referenced prior art.
Claims 4, 15 are rejected under 35 U.S.C. § 103 as being taught by Patton (US 11682209
B2), “Prediction of NBA Talent And Quality from Non-professional Tracking Data,” in view of Walker, (US-20230116986-A1), “Method for Generating Daily-updated Rating Of individual Player Performance in Sports.”
Regarding claim 4, Patton teaches the method of claim 1, but Patton does not teach, Walker teaches, incorporating biographical data for the first player into the set of input features, wherein the biographical data includes age, height, and weight of the first player, at step 206, organization computing system 104 may generate an adjusted game one metric for the player. For example, rookie module 120 may utilize attributes, such as but not limited to height, weight, age, and/or draft pick number, to predict metrics corresponding to a first game of the player's career. To generate the adjusted game one metric, rookie module 120 may utilize a rookie model, generated using previous rookie data from data store 118. Using the rookie model, rookie module 120may generate an adjusted game one estimate for each statistical category, [0039]).
It would have been obvious before the earliest effective filing date of this application to modify Patton’s player prediction method with the teachings of Walker in the use of multiple prediction models and adjustments to the model with the motivation to provide results more aligned with real world results or actual statistics [0033]. The claimed invention is a combination of existing elements and those elements, one of ordinary skill in the art recognizing the anticipated results and benefit of increased accuracy in prediction.
Claim 15 recites substantially similar limitations as claim 4; therefore claim 15 is rejected with same rationale, reasoning and motivation as claim 4. In this claim, the addition of a system comprising a memory configured to store processor-readable instructions and a processor operatively connected to the memory, and configured to execute the instructions, [1:64-2:1], does not change the rationale for rejections under 35 U.S.C. § 103 or the referenced prior art.
Claim 9 is rejected under 35 U.S.C. § 103 as being taught by Patton (US 11682209 B2),
“Prediction of NBA Talent And Quality From Non-professional Tracking Data,” in view of Ganguly, (US 11554292 B2), System and Method for Content and Style Predictions in Sports.”
Regarding claim 9, Patton teaches, method of claim 8,
But Patton does not teach, Ganguly teaches, wherein applying the artificial neural network comprises: applying a Relu and softmax activation function; applying an Adam optimizer; and
applying categorical cross entropy loss to the set of input features to predict the bin of the first player, (As illustrated, neural network structure 300 may include a team classifier 302. Team classifier 302may be a fully-connected feed forward network that may receive as input and may predict the team identity of the first team listed in the input data set. In some embodiments, team classifier 302 may include one or more layers (e.g., four) with rectified linear unit (“relu”) activation and an output layer with activations. In some embodiments, the input layer may use a tan h activation. In some embodiments, team prediction agent 120 may train the prediction model using an Adam optimizer to reduce (e.g., minimize) the cross-entropy loss between a predicted team identity, and the actual team identity, [7:50-64].
It would have been obvious before the earliest effective filing date of this application to modify Patton’s player prediction method with the teachings of Ganguly in the use of artificial neural network activation functions with the motivation to provide variants in the style of play and learning team style to further support predictions in the models. [Abstract]. The claimed invention is a combination of existing elements and those elements, one of ordinary skill in the art recognizing the anticipated results and resulting benefit of play prediction in modeling.
Claim 10 is rejected under 35 U.S.C. § 103 as being taught by Patton (US 11682209 B2),
“Prediction of NBA Talent And Quality From Non-professional Tracking Data,” in view of Dinsdale, (US 20220374475 A1), “System and Method for Predicting Future Player Performance in Sport.”
Regarding claim 10, Patton teaches the method of claim 1, wherein predicting, based on the set of input features, the player rating for the first player comprises:
predicting a collection of player ratings for the first player, (The computing system generates tracking data for each game from the broadcast video of a corresponding game, [1:31-33], implements a trained prediction model configured to predict the talent of future NBA players based, in part, on the generated tracking data [3:40-43], the computing system projects player performance, [1:36-40],
Patton does not teach, Dinsdale teaches, each of the collection of player rating being for a separate year of the first player in the second league, (project a performance of a first player from a current team on a destination team; based on the request, generating, by the computing system, player-position features corresponding to the first player, wherein the player-position features comprise a rolling average of historical player performance data of the first player while playing a first position; generating, by the computing system, team features corresponding to the first player, [ ], and generating, by the computing system via a prediction model, a player box score prediction based on the player-position features, the team features, and the rating features, wherein the player box score prediction comprises a plurality of per game metrics of the first player, [Claim 1].
It would have been obvious before the earliest effective filing date of this application to modify Patton’s player prediction method with the teachings of Dinsdale in the use of training player prediction models with training data, with the motivation to provide accurate predictions to help improve the understanding of how a player’s profile would fit within a new team [0087]. The claimed invention is a combination of existing elements and those elements, one of ordinary skill in the art recognizing the anticipated results and resulting benefit predicting the performance of a player as they join a new team.
Claims 16-20 are rejected under 35 U.S.C. § 103 as being taught by Patton (US
11682209 B2), “Prediction of NBA Talent And Quality From Non-professional Tracking Data,” in view of Walker, (US-20230116986-A1), “Method for Generating Daily-updated Rating Of individual Player Performance in Sports,” and in further view of Dinsdale, (US 20220374475 A1), “System and Method for Predicting Future Player Performance in Sport.”
Regarding claim 16, Patton teaches, a method for determining a performance rating of a target player, (present techniques are able to obtain or generate more accurate forecasts of draft-eligible player performance, [3:46-48]), the method comprising:
identifying, by a computing system, the target player; (an artificial intelligence and computer vision system configured to derive player-tracking data from broadcast video feeds [5:16-22]),
receiving broadcast data for a plurality of game, the plurality of games including
the target player; (A computing system identifies broadcast video for a plurality of games in a first league, [1:37-38], an artificial intelligence and computer vision system configured to derive player-tracking data from broadcast video feeds, [5:16-22]).
generating tracking data for each of the plurality of games, the tracking data comprising coordinates of a position of the target player and ball positions for each frame of the broadcast data; (Tracking data system 116 may be configured to receive broadcast data from tracking system 102 and generate tracking data from the broadcast data, [5:16-18], tracking data system 116 may map pixels corresponding to each player and ball to dots and may transform the dots to a semantically meaningful event layer, which may be used to describe player attributes, [5:25-28]),
receiving play-by-play data for each of the plurality of games, the play-by-play
data describing events related to the target player that occur within the plurality of
games; (play-by-play module 120 may receive a play-by-play feed corresponding to the broadcast video data. In some embodiments, the play-by-play data may be representative of human generated data based on events occurring within the game, [5:63-67]),
Patton does not teach, but Walker teaches, generating, by the computing system, time series data points for the target player, based on the tracking data and play-by-play data of the target player; (time series module 122 may be configured to create time series data points for each player, [0030], pre-processing agent 116 may be configured to generate a game file 125 based on data captured by tracking system 102. In some embodiments, pre-processing agent 116 may further be configured to store tracking data associated with each game in a respective game file 125. Tracking data may refer to the (x, y) coordinates of all players and balls on the playing surface during the game. In some embodiments, pre-processing agent 116 may receive tracking data directly from tracking system 102. In some embodiments, pre-processing agent 116 may derive tracking data from the broadcast feed of the game. [0027] In some embodiments, pre-processing agent 116 may be configured to receive play-by-play data from one or more third party systems. For example, pre-processing agent 116 may receive a play-by-play feed corresponding to the broadcast video data. In some embodiments, the play-by-play data may be representative of human generated data based on events occurring within the game. Such play-by-play data may be stored in a corresponding game file 125, [0028]).
providing, by the computing system, an input including the time series data points
to a first player prediction model and a second player prediction model, wherein the first
and the second player prediction models are trained to find associations between the
first game data of a plurality of other players and the time series data points of the target
player and output a next game projection for the target player; (rookie module 120 may include a prediction model generated using previous rookie data in data store 118. Using this data, rookie module 120 may generate an adjusted game one estimate for each statistical category. Because such data is typically needed for the rookie's initial game, careful work was done to ensure that such projections are not used to develop the models for the rest of the player's career, [0029]. In some embodiments, prediction module 126 may include a separate prediction model tuned for each player. Given that all players are very different from each other, there are times that a prediction model may have trouble projecting their abilities. In such scenarios, projections from prediction module 126 may be compared with real-world or actual statistics, [0033]. Prediction module 126 may be configured to generate next game predictions for each player. For example, prediction module 126 may be configured to receive the foregoing features (e.g., rookie priors, time series data points, player position data, box score data, play-by-play data, and the like) as inputs and run the inputs through gradient-boosted decision trees to generate next-game projections for each player, [0032]).
generating, by the first and second player prediction models, the next game
projection for the target player; (Prediction module 126 may be configured to generate next game predictions for each player, [0032]),
generating, by the computing system, an adjustment weighting, wherein the
adjustment weighting is based on a comparison of the next game projection for the
target player with an average statistic for the target player; (if prediction module 126 generates a three-point percentage for Curry that is below Curry's average three-point percentage, an operator may adjust the weights of Curry's individualized prediction model, [0033]),
providing, by the computing system, the adjustment weighting to the first and the
second player prediction models as training data; (Using the next-game predictions, prediction module 126 may take each statistical output and project player contribution to a team's plus/minus per 100 possessions on both offense and defense. In some embodiments, adjusted plus/minus may be used as the target, [0032]), and
It would have been obvious before the earliest effective filing date of this application to modify Patton’s player prediction method with the teachings of Walker in the use of multiple prediction models and adjustments to the model with the motivation to provide results more aligned with real world results or actual statistics [0033]. The claimed invention is a combination of existing elements and those elements, one of ordinary skill in the art recognizing the anticipated results and benefit of increased accuracy in prediction.
Patton does not teach, but Dinsdale teaches, training, by the computing system, the first and the second player prediction models using the training data, (in FIG. 2, training module 206 may be configured to train machine learning model 212 to generate a player prediction for a new team. In some embodiments, machine learning model 212 may be representative of a neural network model for generating prediction. Training module 206 may train machine learning model 212 to use game-level adjusted features to predict player performance based on the target team. Once trained, training module 206 may output a fully trained prediction model 214 for deployment, [0078], model architecture 700 may include a first neural network model 702 corresponding to group 1 and a second neural network model 704 corresponding to group 2, [0082]).
It would have been obvious before the earliest effective filing date of this application to modify Patton’s player prediction method with the teachings of Dinsdale in the use of training player prediction models with training data, with the motivation to provide accurate predictions to help improve the understanding of how a player’s profile would fit within a new team [0087]. The claimed invention is a combination of existing elements and those elements, one of ordinary skill in the art recognizing the anticipated results and resulting benefit predicting the performance of a player as they join a new team.
Regarding claim 17, Patton, Walker and Dinsdale teach the method of claim 16, but Walker teaches wherein the method further comprises:
comparing, by the computing system, the next game projection for the target
player to actual statistics of the target player; (Prediction module 126 may be configured to generate next game predictions for each player, [0032], there are times that a prediction model may have trouble projecting their abilities. In such scenarios, projections from prediction module 126 may be compared with real-world or actual statistics [0033].
determining, by the computing system, that the next game projection for the
target player differs from the actual statistics by at least a threshold amount in one
category of statistics; and
based on the determining, adjusting, by the computing system, the next game
projection. (Using Steph Curry, for example, if prediction module 126 generates a three-point percentage for Curry that is below Curry's average three-point percentage, an operator may adjust the weights of Curry's individualized prediction model, [0033], For example, prediction module 126 may be configured to receive the foregoing features as inputs and run the inputs through gradient-boosted decision trees to generate next-game projections for each player. Using the next-game predictions, prediction module 126 may take each statistical output and project player contribution to a team's plus/minus per 100 possessions on both offense and defense, [0032]).
It would have been obvious before the earliest effective filing date of this application to modify Patton’s player prediction method with the teachings of Walker in the use of multiple prediction models and adjustments to the model with the motivation to provide results more aligned with real world results or actual statistics [0033]. The claimed invention is a combination of existing elements and those elements, one of ordinary skill in the art recognizing the anticipated results and benefit of increased accuracy in prediction.
Regarding claim 18, Patton, Walker and Dinsdale teach the method of claim 16, but Walker teaches, wherein the generating, by the computing system, the first game data for the target player based on characteristics of the target player comprises:
generating an adjusted game one metric for each statistical category based at
least in part on attributes of the target player, the attributes comprising one or more of a
height, a weight, an age, and a draft pick number, (At step 206, organization computing system 104 may generate an adjusted game one metric for the player. For example, rookie module 120 may utilize attributes, such as but not limited to height, weight, age, and/or draft pick number, to predict metrics corresponding to a first game of the player's career. To generate the adjusted game one metric, rookie module 120 may utilize a rookie model, generated using previous rookie data from data store 118. Using the rookie model, rookie module 120may generate an adjusted game one estimate for each statistical category, [0039]).
It would have been obvious before the earliest effective filing date of this application to modify Patton’s player prediction method with the teachings of Walker in the use of adjusted game one metrics with the motivation to provide results supporting the Daily Rating of Individual Performance and enable more consistent DRIP ratings based on a first game in a league [0033]. The claimed invention is a combination of existing elements and those elements, one of ordinary skill in the art recognizing the anticipated results and benefit of increased accuracy in rookie performance prediction.
Regarding claim 19, Patton, Walker and Dinsdale teach the method of claim 16, but Walker teaches, wherein generating, by the computing system, the time series data points for the target player based on at least one of the first game data of the target player comprises:
padding the at least one of the first game data of the target player with league
average data, (At step 208, organization computing system 104 may generate time series data points for the player. For example, time series module 122 may generate time series data points for the player using one or more of a padding technique or bayes filters to achieve a baseline “now-cast” for each statistic a player accumulates. To generate the time series data points for the player, time series module 122 may use all available data on the player, starting with the rookie priors generated by rookie module 120. [0041]. In some embodiments, a padding technique may refer to a padding of player performance with league average data, [0030]).
It would have been obvious before the earliest effective filing date of this application to modify Patton’s player prediction method with the teachings of Walker in the use of time series data with the motivation to have time series module 122 use all available data on a player, starting with the rookie priors generated by rookie module [0030]. The claimed invention is a combination of existing elements and those elements, one of ordinary skill in the art recognizing the anticipated results and benefit of increased accuracy in rookie performance prediction.
Regarding claim 20, Patton, Walker and Dinsdale teach the method of claim 19, but Walker teaches, wherein the method further comprises:
generating a baseline value for each statistic using a bayes filter based on the
padded first game data, (time series module 122 may generate time series data points for the player using one or more of a padding technique or bayes filters to achieve a baseline “now-cast” for each statistic a player accumulates, [0030]).
It would have been obvious before the earliest effective filing date of this application to modify Patton’s player prediction method with the teachings of Walker in the use of a bayes filter with the motivation to support a “now-cast” (or rapid) prediction [0030]. The claimed invention is a combination of existing elements and those elements, one of ordinary skill in the art recognizing the anticipated results and benefit of increased accuracy in rookie performance prediction.
Conclusion
The prior art made of record and not relied upon is considered pertinent to
applicant's disclosure or directed to the state of the art is listed on the enclosed PTO-892.
Any inquiry concerning this communication or earlier communications from the
examiner should be directed to MICHAEL BOROWSKI whose telephone number is (703) 756-1822, (michael.borowski@uspto.gov). The examiner can normally be reached M-F 8-4:30.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Jerry O’Connor, can be reached on (571) 272-6787. The fax phone number for the organization where this application or proceeding is assigned is (571) 273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at (866) 217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call (800) 786-9199 (IN USA OR CANADA) or (571) 272-1000.
/MB/
Patent Examiner, Art Unit 3624
/MEHMET YESILDAG/Primary Examiner, Art Unit 3624
Prosecution Insights