DETAILED ACTION
Summary and Status of Claims
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
This Office Action is in response to Applicant’s reply filed 11/12/2025.
Claims 1-20 are rejected under 35 U.S.C. 112(a).
Claims 1-20 are rejected under 35 U.S.C. 112(b).
Claims 1-20 are rejected under 35 U.S.C. 101.
Claims 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Ruiz et al. (US Patent Pub 2019/0228290) in view of Bloodworth (US Patent Pub 2013/0045806), further in view of Avruskin et al. (CA 3067562 A1).
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
Claim Objections
Claims 1, 7, 8, 14, 15, and 16 are objected to because of the following informalities:
In claim 1, in the “determining” limitation “… that the at least one of” should be “that at least one of”.
In claim 1, in the “generating, by the raw feature module” limitation, “raw feature module of computing” should be “raw feature module of the computing”.
In claim 7, “the current league” should be “the current professional league”.
Claims 8 and 15 recite similar limitations as claim 1 and have the same informalities.
Claims 14 and 16 recite the same limitations as claim 7 and have the same informalities.
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
Claims 1-20 rejected under 35 U.S.C. 112(a) as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor had possession of the claimed invention.
It is noted that Applicant has not provided citations to the specification or drawings for the amendments to the claims. The following issues are raised as best understood by the Examiner after reviewing the specification and drawings.
Claim 1 recites “based on the determining, generating, by a raw feature module of the computing system, updated player-position features corresponding to the first player, wherein the updated player-position features are generated by the raw feature module by classifying a position of the first player based on event-data stored at an updated game file” in the eighth limitation. The limitation references a “raw feature module” that generates “updated player-position features … by classifying a position of the first player”. There does not seem to be any description of these limitations in the specification. The disclosure describes the “raw feature module” at Fig. 3 and corresponding paragraphs 0043-50. No where in these areas is a “raw feature module” described to perform “classifying a position of the first player.” Instead, these paragraphs describe the “raw feature module” performing aggregation of feature data at a player level, a team level (with or without a particular player), or a team level by position. Aggregation of feature data is not the same as the claimed “classifying a position of the first player.” Moreover, “class” or “classifying” is not mentioned anywhere in the disclosure. Accordingly, the limitation does not comply with the written description requirement.
Continuing to the next two limitations, which recite “identifying, by the raw feature module of the computing system, a subset of times when the first player is active during a match based on the event-data stored in the updated game file” and “generating, by the raw feature module of the computing system, updated team features corresponding to the first player, wherein the updated team features are generated based on the subset of times when the first player is in the match.” In particular, these limitations recite “subset of times when the first player is active during” or “is in” a match (for the purposes of this rejection and interpretations below, being “active during” a match is interpreted as being the same as a player “is in” a match). This feature does not seem to be described in the specification or shown in the drawings. While the “raw feature module” can aggregate team features when a particular player is in the game, it does not seem to identify a “subset of times when the first player is active during a match.” This would mean, for example, if a player is in 10 matches, identifying a subset of times, would result in identifying 9 or less matches that the player was in. Such a feature does not seem to be described in the specification. At best, the specification at the previously cited paragraphs, describes identifying which games/matches where a particular player is active/is in and aggregating team features for those games while the player is in the game. While this timeframe may be a subset of the entire game time, the limitation is requiring a “subset” of the time when a player is active during a match, which is not described by the specification. For at least these reasons, these limitations do not comply with the written description requirement.
Claims 8 and 15 recite the same limitations as claim 1. Therefore, they are rejected for at least the same reasons.
The remaining claims are rejected because they depend on a rejected claim.
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
Claims 1-20 are rejected under 35 U.S.C. 112(b) as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor regards as the invention.
In claim 1, the limitation “the current professional league” in the “generating baseline priors” limitation. There is lack of antecedent basis for this limitation in the claim.
In claim 1, the limitation “the destination professional league” in the “predicting” limitations. It is unclear whether this limitation should be referring to the “destination professional league team”, which seems more consistent with what’s described in the specification. Clarification is required.
Claim 4 recites “the determining” in the third limitation. It is unclear which “determining” is being referenced because it could be referencing “determining, by the adjustment module” recited in claim 1 or the “determining that the destination professional league team …” in claim 4. Clarification is required.
Claim 4 also recites limitations for “generating … the updated team features corresponding to the first player.” These limitations reference “raw team data for the destination professional league team”. However, the “updated team features” are generated “based on the subset of times when the first player is in the match.” Ignoring the issue raised in the rejection under 112(a) above, the “updated team features” seem to be generated based on when the first player is in a match. It’s unclear “raw data for the destination professional league team” is utilized to generate the “updated team features” because the player would never be in a match for a “destination professional league team.” Clarification is required.
Claim 5 recites “the determining” in the third limitation. It is unclear which “determining” is being referenced because it could be referencing “determining, by the adjustment module” recited in claim 1 or the “determining that the first player has not played …” in claim 5. Clarification is required.
Claims 8 and 15 recite the same limitations as claim 1 and are rejected for the same reasons.
Claims 11 and 18 recite the same limitations as claim 4 and are rejected for the same reasons.
Claims 12 and 19 recite the same limitations as claim 5 and are rejected for the same reasons.
The remaining claims are rejected because they depend on a rejected claim.
Claim Rejections - 35 USC § 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 therefor, 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 a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more. Determining whether claims are statutory under 35 U.S.C. 101 involves a two-step analysis. Step 1 requires a determination of whether the claims are directed to the statutory categories of invention. Step 2 requires a determination of whether the claims are directed to a judicial exception without significantly more. Step 2 is divided into two prongs, with the first prong having a part 1 and part 2. See MPEP 2106.
Claim 1
Pursuant to Step 2A, part 1, claims are analyzed to determine whether they are directed to an abstract idea. Pursuant to MPEP 2106, claims are deemed to be directed to an abstract idea if, under their broadest reasonable interpretation, they fall within one of the enumerated categories of (a) mathematical concepts, (b) certain methods of organizing human activity, and (c) mental processes. Under the broadest reasonable interpretation, the terms of the claim are presumed to have their plain meaning consistent with the specification as it would be interpreted by one of ordinary skill in the art. See MPEP 2111.
Claim 1 recites the limitations of: (1) receiving, by a computing system, a request to project a performance of a first player from a current professional league team on a destination professional league team of a destination team-league, (2) generating, by a rating module of the computing system and in response to the request, current professional league team rating features and destination team-league rating features, (3) activating an adjustment module to perform an initialization process based on player-position features for the first player and team features associated with the current professional league team being below a low data quantity threshold identified based on an initial game file, (4) wherein the initialization process comprises: generating baseline priors for initial player-position features and initial team features based on average values of other players from the current professional league mapping to the first player's position and based on other teams in the current professional league, respectively, (5) predicting, by the multi-head neural network model, a first performance of the first player on the destination professional league using target features, the current professional league team rating features, the destination team-league rating features, the initial player-position features, and the initial team features, wherein the target features are a subset of input features identified by the multi-head neural network model to meet performance prediction thresholds, (6) determining, by the adjustment module, that the at least one of player-position features or team features exceeds the low data quantity threshold, (7) based on the determining, generating, by a raw feature module of the computing system, updated player-position features corresponding to the first player, wherein the updated player-position features are generated by the raw feature module by classifying a position of the first player based on event-data stored at an updated game file, (8) identifying, by the raw feature module of the computing system, a subset of times when the first player is active during a match based on the event-data stored in the updated game file, (9) generating, by the raw feature module of computing system, updated team features corresponding to the first player, wherein the updated team features are generated based on the subset of times when the first player is in the match, and (10) predicting, by the multi-head neural network model, an updated performance of the first player on the destination professional league using the target features, the current professional league team rating features, the destination team-league rating features, updated player-position features, and updated team features.
Courts consider a mental process if it “can be performed in the human mind, or by a human using a pen and paper.” The mental process grouping covers concepts performed in the human mind, including observation, evaluation, judgment, and opinion. MPEP 2016(a)(2)(III). The mathematical concepts grouping is defined as mathematical relationships, mathematical formulas or equations, and mathematical calculations. The Supreme Court has identified a number of concepts falling within this grouping as abstract ideas including: a procedure for converting binary-coded decimal numerals into pure binary form, Gottschalk v. Benson, 409 U.S. 63, 65, 175 USPQ2d 673, 674 (1972); a mathematical formula for calculating an alarm limit, Parker v. Flook, 437 U.S. 584, 588-89, 198 USPQ2d 193, 195 (1978); the Arrhenius equation, Diamond v. Diehr, 450 U.S. 175, 191, 209 USPQ 1, 15 (1981); and a mathematical formula for hedging, Bilski v. Kappos, 561 U.S. 593, 611, 95 USPQ 2d 1001, 1004 (2010).
Limitations can also be deemed insignificant extra-solution activity (IESA). The term "extra-solution activity" can be understood as activities incidental to the primary process or product that are merely a nominal or tangential addition to the claim. Extra-solution activity includes both pre-solution and post-solution activity. An example of pre-solution activity is a step of gathering data for use in a claimed process, e.g., a step of obtaining information about credit card transactions, which is recited as part of a claimed process of analyzing and manipulating the gathered information by a series of steps in order to detect whether the transactions were fraudulent. An example of post-solution activity is an element that is not integrated into the claim as a whole, e.g., a printer that is used to output a report of fraudulent transactions, which is recited in a claim to a computer programmed to analyze and manipulate information about credit card transactions in order to detect whether the transactions were fraudulent. MPEP 2106.05(g). Examiner is also required to give claim limitations their broadest reasonable interpretation in light of the specification. MPEP 2106.II.
Limitation (1) is directed to receiving a request to project a performance of a player. It is essentially IESA in the form of necessary data gathering for use in the claimed process. Limitation (2) is directed to a step of generating “current professional league team rating features and destination team-league rating features,” which comprise rolling averages. Rolling average is are mathematical calculation that can be performed by a person in the mind or with the aid of pen and paper. Limitation (3) is directed to a mental step of determination involving evaluation and judgment, which concludes that “player-position features for the first player and team features associated with the current professional league team” are “below a low data quantity threshold.” The limitation further recites “activating an adjustment module to perform an initialization process,” which involves mathematical calculations, as recited in limitation (4). Therefore, the limitation of “activating” is merely interpreted as deciding to perform the calculations. Limitation (4) is directed to generating baseline priors, which are based on averages for other players and teams in the current professional league. Baseline priors are average values and are directed to a mathematical calculation that can be performed by a person. Limitation (5) is directed to a step of predicting a performance of a player on the destination professional league (team) utilizing the various calculated features from prior limitations for target features. Target features are essentially what performance stats to predict for. Accordingly, the step of predicting is directed to a mental step involving evaluation and judgment to evaluate the feature data and make a judgment as to the predicted performance of a player. Limitation (6) is directed to a step of determination, which is a mental step involving evaluation and judgment, to recognize that player-position features or team features exceeds a low data quantity threshold. In other words, recognizing that there is sufficient data above a quantity threshold. Limitation (7) is directed to a step of generating updated player-position features based on an updated game file. As explained above, generating player-position features is a mathematical calculation that can be performed by a person. Limitation (8) is directed to a mental step of identifying when a first player is active during matches in an updated game file. The step involves evaluation and judgment to make the identification, which can easily be performed by a person. Limitation (9) is directed to generating updated team features, which are mathematical calculations as explained above, based on when the player is active during matches, which can be performed by a person in the mind or with the aid of pen and paper. Limitation (10) is directed to a prediction step using the features calculated in prior limitations. As discussed above, predicting a performance of a player is a mental step requiring evaluation and judgment.
The recited “computing system”, its module components, and the multi-head neural network model are recited at a high level of generality, i.e., as a generic components performing generic computer functions and merely utilized to perform the abstract idea.
As discussed above, the limitations are categorized as mental processes or mathematical concepts/calculations. The Supreme Court has treated claims that include multiple exceptions in the same manner as claims reciting a single judicial exception. Id. (discussing Bilski v. Kappos, 561 U.S. 593 (2010)). As there are no bright lines between the types of judicial exceptions, and many of the concepts identified by the courts as exceptions can fall under several exceptions, MPEP 2106.04, subsection I instructs examiners to “identify . . . the claimed concept (the specific claim limitation(s) that the examiner believes may recite an exception) [that] aligns with at least one judicial exception.”
For at least these reasons, claim 1 is directed to an abstract idea categorized as mental processes.
Pursuant to Step 2A, part 2, claims are analyzed to determine whether the claim as a whole integrates the recited judicial exception into a practical application of the exception. This evaluation is performed by (1) identifying whether there are any additional elements recited in the claim beyond the judicial exception, and (2) evaluating those additional elements individually and in combination to determine whether the claim as a whole integrates the exception into a practical application. See MPEP 2106.04(d). One way to determine integration into a practical application is when the claimed invention improves the functioning of a computer or improves another technology or technical field. To evaluate an improvement to a computer or technical field, the specification must set forth an improvement in technology and the claim itself must reflect the disclosed improvement. See MPEP 2106.04(d)(1).
In this case, as explained above, claim 1 merely recites an abstract idea categorized under mental processes. As discussed above, Limitation (1) is directed to IESA and the remaining limitations (2) through (10) are directed to mental steps or mental performance of mathematical calculations that can be performed by a person in the mind or with the aid of pen and paper or with the aid of a computer as a tool. None of limitations (2) through (10) recite specific steps that would adequately demonstrate some type of improvement sufficient to integrate the abstract idea into a practical application. Limitations (5) and (10) are directed to a mental step of predicting a performance of a player using a multi-head neural network model. As recited, the multi-head neural network model is a generic model, which can be trained to make desired predictions based on input data. As described by the specification at para. 0024, predicting a performance for a player is a conventional process that is performed by team owners, managers, or transfer committees and can involve substantial time investment. In other words, the asserted improvement is to be able to predict a player performance more efficiently. However, the limitations, as recited, do not recite steps that would adequately demonstrate an improvement to the technology. At best, as recited, the limitations merely utilize a computer to perform the abstract idea. Improved speed or efficiency inherent with applying the abstract idea on a computer does not integrate the abstract idea into a practical application or provide an inventive concept. MPEP 2106.05(f)(2). Further, as discussed above, the limitation does not require that the multi-head neural network model perform any specific steps other than using calculated data to make a prediction (i.e., output data). While claim 1 recite additional components in the form of a computer system, adjustment module, raw feature module, and multi-head neural network model, they are recited at a high level of generality, which do not add meaningful limits on the recited abstract idea to integrate it into a practical application by providing an improvement to the functioning of a computer or technology, implementing the abstract idea with a particular machine or manufacture that is integral to the claim, effecting a transformation or reduction of a particular article to a different state or thing, nor applying the abstract idea in some meaningful way beyond linking its use to computer technology. See MPEP 2106.04(d).
For at least these reasons, claim 1 does not integrate the judicial exception into a practical application.
Pursuant to Step 2B, claims are analyzed to determine whether the claim as a whole amounts to significantly more than the recited exception i.e., whether any additional element, or combination of additional elements, adds an inventive concept to the claim. See MPEP 2106.05. In this case, claim 1 does not recite limitations that amount to significantly more than the abstract idea. For the same reasons as discussed above, the limitations do not amount to significantly more than the abstract idea. At Step 2B, the evaluation of the insignificant extra-solution activity consideration takes into account whether or not the extra-solution activity is well understood, routine, and conventional in the field. See MPEP 2106.05(g). Limitation(1) discussed above is directed to IESA of receiving or transmitting data over a network, e.g., using the Internet to gather data, which is well understood, routine, and conventional. See MPEP 2106.05(d), subsection II. Even when considered in combination, these additional elements represent mere instructions to implement an abstract idea or other exception on a computer and insignificant extra-solution activity, which do not provide an inventive concept. For at least these reasons, claim 1 is nonstatutory because they are directed to a judicial exception without significantly more.
Claim 2
Pursuant to step 2A, part 1, claim 2 depends on claim 1 and therefore recites the same abstract idea. Pursuant to step 2A, part 2, claim 2 recites the additional limitations of the updated performance of the first player comprises a player box score prediction. The limitation is essentially describing what the predicted performance of a player is, which is IESA. Therefore, these additional limitations do not integrate the abstract idea into a practical application. Pursuant to step 2B, for essentially the same reasons as discussed for step 2A, part 2, these additional limitations do not provide an inventive concept. For at least these reasons, claim 2 is directed to a judicial exception without significantly more.
Claim 3
Pursuant to step 2A, part 1, claim 3 depends on claim 2 and therefore recites the same abstract idea. Pursuant to step 2A, part 2, claim 3 recites the additional limitations of (1) comparing, by the computing system, the player box score predictionimprovement to the technology. Therefore, these additional limitations do not integrate the abstract idea into a practical application. Pursuant to step 2B, for essentially the same reasons as discussed for step 2A, part 2, these additional limitations do not provide an inventive concept. For at least these reasons, claim 3 is directed to a judicial exception without significantly more.
Claim 4
Pursuant to step 2A, part 1, claim 4 depends on claim 1 and therefore recites the same abstract idea. Pursuant to step 2A, part 2, claim 4 recites the additional limitations of (1) accessing raw team data for the destination professional league team, (2) determining that the destination professional league team has not played at least a threshold amount of minutes in the destination professional league, (3) based on the determining, adjusting the raw team data based on an average performance of teams in the destination professional league, and (4) using the adjusted raw team data in the generation of the updated team features associated with the first player. Limitation (1) is directed to IESA in the form of data gathering. Limitations (2) through (4) are directed to mental steps utilizing the gathered data (i.e., raw team data). Limitation (2) involves a step of determination, which is observation and evaluation that can be performed in the mind of a person. Limitations (3) and (4) are also mental steps of adjusting data and generating team features as a person can utilize their evaluations in limitation (2) to adjust the raw team data and use the adjusted data to generate other metrics (i.e., team features) as desired. None of limitations (2) through (4) recite specific requirements as to how the “determining,” “adjusting,” and “generating” are performed. As discussed above, in regards to claim 1, the “generating” is a mathematical calculation performed in the mind or with the aid of pen and paper. Therefore, these additional limitations do not integrate the abstract idea into a practical application. Pursuant to step 2B, for essentially the same reasons as discussed for step 2A, part 2, these additional limitations do not provide an inventive concept. For at least these reasons, claim 4 is directed to a judicial exception without significantly more.
Claim 5
Pursuant to step 2A, part 1, claim 5 depends on claim 1 and therefore recites the same abstract idea. Pursuant to step 2A, part 2, claim 5 recites the additional limitations of (1) accessing raw player data for the first player in the destination professional league, (2) determining that the first player has not played at least a threshold amount of minutes in the destination professional league, (3) based on the determining, adjusting the raw player data based on other player data on the destination professional league team that play a same position as the first player, and (4) using the adjusted raw player data in generation of the updated player-position features. Limitation (1) is directed to IESA in the form of data gathering. Limitations (2) through (4) are directed to mental steps utilizing the gathered data (i.e., raw team data). Limitation (2) involves a step of determination, which is observation and evaluation that can be performed in the mind of a person. Limitations (3) and (4) are also mental steps of adjusting data and generating team features as a person can utilize their evaluations in limitation (2) to adjust the raw team data and use the adjusted data to generate other metrics (i.e., team features) as desired. None of limitations (2) through (4) recite specific requirements as to how the “determining,” “adjusting,” and “generating” are performed. As discussed above, in regards to claim 1, the “generating” is a mathematical calculation performed in the mind or with the aid of pen and paper. Therefore, these additional limitations do not integrate the abstract idea into a practical application. Pursuant to step 2B, for essentially the same reasons as discussed for step 2A, part 2, these additional limitations do not provide an inventive concept. For at least these reasons, claim 5 is directed to a judicial exception without significantly more.
Claim 6
Pursuant to step 2A, part 1, claim 6 depends on claim 1 and therefore recites the same abstract idea. Pursuant to step 2A, part 2, claim 6 recites the additional limitations of storing, by the computing system, the baseline prior for the player-position features as a player initial value and the baseline prior for the team features as a team initial value. The limitation is directed to IESA because it is merely updating data, which is a form of mere data gathering. MPEP 2106.05(g). Therefore, these additional limitations do not integrate the abstract idea into a practical application. Pursuant to step 2B, for essentially the same reasons as discussed for step 2A, part 2, these additional limitations do not provide an inventive concept. For at least these reasons, claim 6 is directed to a judicial exception without significantly more.
Claim 7
Pursuant to step 2A, part 1, claim 7 depends on claim 1 and therefore recites the same abstract idea. Pursuant to step 2A, part 2, claim 7 recites the additional limitations of (1) receiving an indication of an amount of time played by the current professional league team in the current professional league, and (2) based on the amount of time, using a baseline set of features associated with the current professional league to predict the destination team-league rating features for the first player. Limitation (1) is directed to IESA of receiving data or mere data gathering. Limitation (2) is directed to a mental step of generate the team league rating features, which is a mathematical calculation that uses a set of default (baseline) data. As discussed above, the mathematical calculation is merely a “rolling average,” which can be easily calculated by a person in the mind or with the aid of pen and paper. Therefore, these additional limitations do not integrate the abstract idea into a practical application. Pursuant to step 2B, for essentially the same reasons as discussed for step 2A, part 2, these additional limitations do not provide an inventive concept. For at least these reasons, claim 7 is directed to a judicial exception without significantly more.
Claims 8-14 are essentially the same as claims 1-7, respectively, in the form of a non-transitory computer readable medium. Therefore, they are rejected for the same reasons. These claims recite the additional computer components of “a non-transitory computer readable medium” and “a processor”. However, they are recited at a high level of generality and do not put meaningful limits on the abstract idea to integrate it into a practical application nor do they amount to significantly more than the abstract idea.
Claims 15-20 recite essentially the same subject matter as claims 1, 7, 2 and 3, and 4-6, respectively, in the form of a system. Therefore, they are rejected for the same reasons. These claims recite the additional computer components of “a processor” and “a memory”. However, they are recited at a high level of generality and do not put meaningful limits on the abstract idea to integrate it into a practical application nor do they amount to significantly more than the abstract idea.
Claims 1-20 are therefore not drawn to eligible subject matter as they are directed to an abstract idea without significantly more.
To expedite a complete examination of the instant application, the claims rejected under 35 U.S.C. 101 (nonstatutory) above are further rejected as set forth below in anticipation of applicant amending these claims to overcome the rejection.
Note on Prior Art Rejections
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
Claims 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Ruiz et al. (US Patent Pub 2019/0228290) (Ruiz) in view of Bloodworth (US Patent Pub 2013/0045806), further in view of Avruskin et al. (CA 3067562 A1) (Avruskin).
In regards to claim 1, Ruiz discloses a method for predicting performance using a multi-head neural network model, comprising:
receiving, by a computing system, a request to project a performance of a first player from a current professional league team (Ruiz at para. 0128)1;
generating, by a rating module of the computing system and in response to the request, current professional league team rating features (Ruiz at paras. 0046-55)2;
predicting, by the multi-head neural network model, an outcome of a match using target features, the current professional league team rating features, the destination team-league rating features, the initial player-position features, and the initial team features, wherein the target features are a subset of input features identified by the multi-head neural network model to meet performance prediction thresholds (Ruiz at paras. 0111, 0119-120, 0141)3;
generating, by a raw feature module of the computing system, updated player-position features corresponding to the first player, wherein the updated player-position features are generated by the raw feature module by classifying a position of the first player based on event-data stored at an updated game file (Ruiz at paras. 0046-55)4;
identifying, by the raw feature module of the computing system, a subset of times when the first player is active during a match based on the event-data stored in the updated game file (Ruiz at paras. 0160-164);
generating, by the raw feature module of the computing system, updated team features corresponding to the first player, wherein the updated team features are generated based on the subset of times when the first player is in the match (Ruiz at paras. 160-164)5; and
predicting, by the multi-head neural network model, an updated outcome of a match using the target features, the current professional league team rating features, destination team-league rating features, updated player-position features, and updated team features. Ruiz at paras. 0054-55, 0082, 0111, 0119-120.6
Ruiz does not expressly disclose the request is to project a performance of a first player from a current professional league team on a destination professional league team of a destination team-league, predicting a first performance of a first player on a destination professional league team of a destination team-league using target features, generating destination team-league rating features, predicting an updated performance of the first player on the destination professional league using the target features.
Bloodworth discloses predicting future performances of sports players for a destination professional league team in order to determine which players to include on the team (i.e., request to project a performance …). Bloodworth at para. 0023. The method of predicting future performances includes using historical statistical data of teams and players (i.e., team-league rating features … destination professional league team). Bloodworth at paras. 0027-29, 0077. The method further includes generating ratings for players, such as skills ratings or effectiveness ratings, and ratings for teams, such as effectiveness ratings, which are used to predict the performance of a team and player (i.e., team-league rating features…). Bloodworth at paras. 0030, 0085, 0095. This data is used to generate player predictions of how the player will perform if added to the team (i.e., predicting a first performance … on the destination professional league team). Bloodworth further discloses updating stored data with more recent up to date data, which can be used to generate predictions. Bloodworth at para. 0028.
Ruiz and Bloodworth are analogous art because they are both directed to the same field of endeavor of sports performance predictions.
At the time before the effective filing date of the instant application, it would have been obvious to one of ordinary skill in the art to modify Ruiz by adding the features of the request is to project a performance of a first player from a current professional league team on a destination professional league team of a destination team-league, predicting a first performance of a first player on a destination professional league team of a destination team-league using target features, generating destination team-league rating features, predicting an updated performance of the first player on the destination professional league using the target features, as disclosed by Bloodworth.
The motivation for doing so would have been to improve methods of predicting player performance based on more than player statistics. Bloodworth at para. 0003.
Ruiz in view of Bloodworth does not expressly disclose activating an adjustment module to perform an initialization process based on player-position features for the first player and team features associated with the current professional league team being below a data quantity threshold identified based on an initial game file, wherein the initialization process comprises: generating baseline priors for initial player-position features and initial team features based on average values of other players from the current professional league mapping to the first player’s position and based on other teams in the current professional league, respectively; determining, by the adjustment module, that at least one of player-position features or team features exceeds the low data quantity threshold, and generating updated player-position features based on the determining.
Avruskin discloses a system and method for statistically predicting the expected performance of a sporting entity (e.g., a player or a team). Avruskin at abstract. The method includes generating predictions and taking into consideration historical performance data and recent performance data of a sporting entity (i.e., a player or a team). Avruskin at paras. 0080, 0084. The system further includes data filters that can be based on time, which allows the system to make predictions based on past performance data, such as average performance (i.e., generating baseline priors …), in instances where recent performance data is not available or when a sport’s entity has not had the required number of minutes or played in a game (i.e., below a data quantity threshold …). Once the sufficient requirements are met, the recent performance data can be utilized (i.e., determining … exceeds the low data quantity threshold; generating updated player-position features based on the determining). Avruskin at paras. 0086-87.
Ruiz, Bloodworth, and Avruskin are analogous art because they are all directed to the same field of endeavor of sports performance predictions.
At the time before the effective filing date of the instant application, it would have been obvious to one of ordinary skill in the art to modify Ruiz in view of Bloodworth by adding the features of activating an adjustment module to perform an initialization process based on player-position features for the first player and team features associated with the current professional league team being below a data quantity threshold identified based on an initial game file, wherein the initialization process comprises: generating baseline priors for initial player-position features and initial team features based on average values of other players from the current professional league mapping to the first player’s position and based on other teams in the current professional league, respectively; determining, by the adjustment module, that at least one of player-position features or team features exceeds the low data quantity threshold, and generating updated player-position features based on the determining, as disclosed by Avruskin.
The motivation for doing so would have been to provide appropriate conditions under which the data should be analyzed and can be customized based on different athletes and sports. Avrushkin at para. 0087.
In regards to claim 2, Ruiz in view of Bloodworth and Avruskin discloses the method of claim 1, the updated performance of the first player comprises a player box score prediction. (Ruiz at paras. 0040, 0047, 0054)7
In regards to claim 3, Ruiz in view of Bloodworth and Avruskin discloses the method of claim 2, further comprising:
a. comparing, by the computing system, the player box score prediction to actual box score data associated with the first player(Ruiz at Fig. 4-416; para. 0124)8; and
b. based on the comparing, adjusting, by the computing system, one or more parameters of the multi-head neural network model. Ruiz at para. 0101.9
In regards to claim 4, Ruiz in view of Bloodworth discloses the method of claim 1, wherein generating, by the raw feature module of the computing system, the updated team features corresponding to the first player comprises:
a. accessing raw team data for the destination professional league team (Ruiz at paras. 0041-42);
b. adjusting the raw team data based on an average performance of teams in the destination professional league. Ruiz at paras. 0083-87.10
d. using adjusted raw team data in the generation of the updated team features associated with the first player. Bloodworth at paras. 0028, 0049, 0086.11
Ruiz in view of Bloodworth does not expressly disclose determining that the destination professional league team has not played at least a threshold amount of minutes in the destination professional league and based on the determining, adjusting the raw team data based on an average performance of teams in the destination professional league.
Avruskin discloses a system and method for statistically predicting the expected performance of a sporting entity (e.g., a player or a team). Avruskin at abstract. The method includes generating predictions and taking into consideration historical performance data and recent performance data of a sporting entity (i.e., a player or a team). Avruskin at paras. 0080, 0084. The system further includes data filters that can be based on time, which allows the system to make predictions based on past performance data, such as average performance, in instances where recent performance data is not available. Avruskin at paras. 0086-87.
At the time before the effective filing date of the instant application, it would have been obvious to one of ordinary skill in the art to modify Ruiz in view of Bloodworth by adding the features of determining that the destination professional league team has not played at least a threshold amount of minutes in the destination professional league and based on the determining, adjusting the raw team data based on an average performance of teams in the destination professional league, as disclosed by Avruskin.
The motivation for doing so would have been to provide appropriate conditions under which the data should be analyzed and can be customized based on different athletes and sports. Avrushkin at para. 0087.
In regards to claim 5, Ruiz in view of Bloodworth discloses the method of claim 1, wherein generating, by the computing system, the updated player position features corresponding to the first player comprises:
a. accessing raw player data for the first player in the destination professional league (Ruiz at paras. 0041-42); and
c. adjusting the raw player data based on other player data on the destination professional league team that play a same position as the first player. Ruiz at paras. 0083-87.12
d. using the adjusted raw player data in the generation of the updated player-position features. Bloodworth at paras. 0028, 0049, 0086.13
Ruiz in view of Bloodworth does not expressly disclose determining that the first player has not played at least a threshold amount of minutes in the destination professional league and based on the determining, adjusting the raw player data based on other player data on the destination professional league team that play a same position as the first player.
Avruskin discloses a system and method for statistically predicting the expected performance of a sporting entity (e.g., a player or a team). Avruskin at abstract. The method includes generating predictions and taking into consideration historical performance data and recent performance data of a sporting entity (i.e., a player or a team). Avruskin at paras. 0080, 0084. The system further includes data filters that can be based on time, which allows the system to make predictions based on past performance data, such as average performance, in instances where recent performance data is not available. Avruskin at paras. 0086-87.
At the time before the effective filing date of the instant application, it would have been obvious to one of ordinary skill in the art to modify Ruiz in view of Bloodworth by adding the features of determining that the first player has not played at least a threshold amount of minutes in the destination professional league and based on the determining, adjusting the raw player data based on other player data on the destination professional league team that play a same position as the first player, as disclosed by Avruskin.
The motivation for doing so would have been to provide appropriate conditions under which the data should be analyzed and can be customized based on different athletes and sports. Avrushkin at para. 0087.
In regards to claim 6, Ruiz in view of Bloodworth and Avruskin discloses the system of claim 1, further comprising:
storing, by the computing system, the baseline prior for the player-position features as a player initial value and the baseline prior for the team features as a team initial value. (Avruskin at para. 0084, 0087)14
In regards to claim 7, Ruiz in view of Bloodworth discloses the method of claim 1, but does not expressly disclose wherein generating the destination team-league rating features comprises:
a. receiving an indication of an amount of time played by the current professional league team in the current professional league; and
b. based on the amount of time, using a baseline set of features associated with the current professional league to predict the destination team-league rating feature for the first player.
Avruskin discloses a system and method for statistically predicting the expected performance of a sporting entity (e.g., a player or a team). Avruskin at abstract. The method includes generating predictions and taking into consideration historical performance data and recent performance data of a sporting entity (i.e., a player or a team). Avruskin at paras. 0080, 0084. The system further includes data filters that can be based on time, which allows the system to make predictions based on past performance data, such as average performance, in instances where recent performance data is not available. Avruskin at paras. 0086-87. In other words, if a team has not played a sufficient amount of time, average performance (i.e., baseline) can be used for generating the team-league rating features.
At the time before the effective filing date of the instant application, it would have been obvious to one of ordinary skill in the art to modify Ruiz in view of Bloodworth by adding the features of receiving an indication of an amount of time played by the current professional league team in the current professional league and based on the amount of time, using a baseline set of features associated with the current professional league to predict the destination team-league rating feature for the first player, as disclosed by Avruskin.
The motivation for doing so would have been to provide appropriate conditions under which the data should be analyzed and can be customized based on different athletes and sports. Avrushkin at para. 0087.
Claims 8-14 are essentially the same as claims 1-7, respectively, in the form of a non-transitory computer readable medium (Ruiz at para. 0172). Therefore, they are rejected for the same reasons.
In regards to claim 15, Ruiz discloses a computing system comprising:
a processor implemented in hardware (Ruiz at para. 0168);
a multi-head neural network model (Ruiz at paras. 0004, 0027, 0043)15; and
a memory having programming instructions stored therein, which, when executed by the processor, causes the system to perform operations (Ruiz at para. 0168) comprising:
receiving, by a computing system, a request to project a performance of a first player from a current professional league team (Ruiz at para. 0128)16;
generating, by a rating module of the computing system and in response to the request, current professional league team rating features (Ruiz at paras. 0046-55)17;
predicting, by the multi-head neural network model, an outcome of a match using target features, the current professional league team rating features, the destination team-league rating features, the initial player-position features, and the initial team features, wherein the target features are a subset of input features identified by the multi-head neural network model to meet performance prediction thresholds (Ruiz at paras. 0111, 0119-120, 0141)18;
generating, by a raw feature module of the computing system, updated player-position features corresponding to the first player, wherein the updated player-position features are generated by the raw feature module by classifying a position of the first player based on event-data stored at an updated game file (Ruiz at paras. 0046-55)19;
identifying, by the raw feature module of the computing system, a subset of times when the first player is active during a match based on the event-data stored in the updated game file (Ruiz at paras. 0160-164);
generating, by the raw feature module of the computing system, updated team features corresponding to the first player, wherein the updated team features are generated based on the subset of times when the first player is in the match (Ruiz at paras. 160-164)20; and
predicting, by the multi-head neural network model, an updated outcome of a match using the target features, the current professional league team rating features, destination team-league rating features, updated player-position features, and updated team features. Ruiz at paras. 0054-55, 0082, 0111, 0119-120.21
Ruiz does not expressly disclose the request is to project a performance of a first player from a current professional league team on a destination professional league team of a destination team-league, predicting a first performance of a first player on a destination professional league team of a destination team-league using target features, generating destination team-league rating features, predicting an updated performance of the first player on the destination professional league using the target features.
Bloodworth discloses predicting future performances of sports players for a destination professional league team in order to determine which players to include on the team (i.e., request to project a performance …). Bloodworth at para. 0023. The method of predicting future performances includes using historical statistical data of teams and players (i.e., team-league rating features … destination professional league team). Bloodworth at paras. 0027-29, 0077. The method further includes generating ratings for players, such as skills ratings or effectiveness ratings, and ratings for teams, such as effectiveness ratings, which are used to predict the performance of a team and player (i.e., team-league rating features…). Bloodworth at paras. 0030, 0085, 0095. This data is used to generate player predictions of how the player will perform if added to the team (i.e., predicting a first performance … on the destination professional league team). Bloodworth further discloses updating stored data with more recent up to date data, which can be used to generate predictions. Bloodworth at para. 0028.
Ruiz and Bloodworth are analogous art because they are both directed to the same field of endeavor of sports performance predictions.
At the time before the effective filing date of the instant application, it would have been obvious to one of ordinary skill in the art to modify Ruiz by adding the features of the request is to project a performance of a first player from a current professional league team on a destination professional league team of a destination team-league, predicting a first performance of a first player on a destination professional league team of a destination team-league using target features, generating destination team-league rating features, predicting an updated performance of the first player on the destination professional league using the target features, as disclosed by Bloodworth.
The motivation for doing so would have been to improve methods of predicting player performance based on more than player statistics. Bloodworth at para. 0003.
Ruiz in view of Bloodworth does not expressly disclose activating an adjustment module to perform an initialization process based on player-position features for the first player and team features associated with the current professional league team being below a data quantity threshold identified based on an initial game file, wherein the initialization process comprises: generating baseline priors for initial player-position features and initial team features based on average values of other players from the current professional league mapping to the first player’s position and based on other teams in the current professional league, respectively; determining, by the adjustment module, that at least one of player-position features or team features exceeds the low data quantity threshold, and generating updated player-position features based on the determining.
Avruskin discloses a system and method for statistically predicting the expected performance of a sporting entity (e.g., a player or a team). Avruskin at abstract. The method includes generating predictions and taking into consideration historical performance data and recent performance data of a sporting entity (i.e., a player or a team). Avruskin at paras. 0080, 0084. The system further includes data filters that can be based on time, which allows the system to make predictions based on past performance data, such as average performance (i.e., generating baseline priors …), in instances where recent performance data is not available or when a sport’s entity has not had the required number of minutes or played in a game (i.e., below a data quantity threshold …). Once the sufficient requirements are met, the recent performance data can be utilized (i.e., determining … exceeds the low data quantity threshold; generating updated player-position features based on the determining). Avruskin at paras. 0086-87.
Ruiz, Bloodworth, and Avruskin are analogous art because they are all directed to the same field of endeavor of sports performance predictions.
At the time before the effective filing date of the instant application, it would have been obvious to one of ordinary skill in the art to modify Ruiz in view of Bloodworth by adding the features of activating an adjustment module to perform an initialization process based on player-position features for the first player and team features associated with the current professional league team being below a data quantity threshold identified based on an initial game file, wherein the initialization process comprises: generating baseline priors for initial player-position features and initial team features based on average values of other players from the current professional league mapping to the first player’s position and based on other teams in the current professional league, respectively; determining, by the adjustment module, that at least one of player-position features or team features exceeds the low data quantity threshold, and generating updated player-position features based on the determining, as disclosed by Avruskin.
The motivation for doing so would have been to provide appropriate conditions under which the data should be analyzed and can be customized based on different athletes and sports. Avrushkin at para. 0087.
Claims 16, 18, 19 are essentially the same as claims 7, 4, and 5, respectively, in the form of a system. Therefore, they are rejected for the same reasons.
In regards to claim 17, Ruiz in view of Bloodworth and Avruskin discloses the system of claim 16, wherein the operations further comprise, training the multi-head neural network model to generate a player box score prediction (Ruiz at paras. 0040, 0047, 0054)22, the training comprising:
a. comparing the player box score prediction to actual box score data associated with the first player (Ruiz at Fig. 4-416; para. 0124)23; and
b. based on the comparing, adjusting one or more parameters of the multi-head neural network model. Ruiz at para. 0101.24
Claim 20 is essentially the same as claim 6 in the form of a system. Therefore, it is rejected for the same reasons.
Response to Arguments
Rejection of claims 1-20 under 35 U.S.C. 101
Applicant’s arguments in regards to the rejection of claims 1-20 under 35 U.S.C. 101, have been fully considered and they are not persuasive.
Applicant argues the claims are analogous to those in the Desjardins decision of the Appeals Review Panel (ARP) because the claims recite a method for predicting performance using an improved multi-head neural network model that utilizes an adaptive feature of dynamically adjusting the predictions based on updates of each player, the team, and the league. Applicant argues this adaptive feature enables the computing system to deliver more relevant and accurate predictions to end users, thereby improving accuracy and efficiency in generating player performance predictions. Remarks at 22. Examiner respectfully disagrees. The ARP recognized in Desjardins that there was an improvement to how a machine learning model itself operates, including training a machine learning model to learn new tasks while protecting knowledge about previous tasks to overcome the problem of “catastrophic forgetting” encountered in continual learning systems. In particular, the ARP discerned the limitation “adjust the first values of the plurality of parameters to optimize performance of the machine learning model on the second machine learning task while protecting performance of the machine learning model on the first machine learning task” reflected the improvement disclosed in the specification. On the contrary, Applicant’s claims merely recite steps that perform simple mathematical calculations based on gathered data and performs prediction steps using the neural network model using calculated input data, without reciting particular steps with regards to how the prediction is performed, how the model was trained to perform the prediction, or any steps that would demonstrate an improvement like the claim in Desjardins. Moreover, updating calculated data with new information (i.e., updating averages based on new values) and feeding the updated data to the neural network model is not an improvement to how the neural network model operates but is simply inputting different data into the same neural network model to receive a prediction output. For at least these reasons, Examiner asserts the claims are not analogous to Desjardins and accordingly do not integrate the abstract idea into a practical application.
Applicant further argues the claimed neural network model generates “rating features” and “baseline priors” in an environment with a “low data quantity threshold” and is able to “predict a first performance of the first player” with minimal data usage, which can be updated as data “exceeds the low data quantity threshold.” Applicant argues these features do not recite a mental processed based on the August 2025 Memo on “Reminders on evaluating subject matter eligibility of claims under 35 U.S.C. 101”, which provides that “[c]laim limitations that encompass AI in a way that cannot be practically performed in the human mind do not fall within this grouping.” Remarks at 23. Examiner respectfully disagrees. As discussed in the rejection above, the “rating features” and “baseline priors” are mathematical calculations, such as averages. This is a mathematical calculation that is easily performed by a person with the aid of pen and paper or with a computer as a tool. A “low data quantity threshold” relates to having sufficient data, such as having a threshold amount of minutes where a player is active in a league or team. Spec at paras. 0051, 0053. This is a simple comparison based on gathered data to determine whether a player has been active for a required amount of minutes. As explained in the rejection above, none of the limitations recite steps that would be impractical or impossible for a person to perform with the aid of pen and paper or with the aid of a generic computer as a tool. In regards to steps involving the neural network model, the model is recited at a high level of generality and merely produces an output (i.e., the prediction) based on input (i.e., feature data). As discussed further below, the claims do not recite how the model is trained to make the prediction or how it uses the input to make the prediction. For at least these reasons, Examiner asserts the claims are directed to mental processes.
Applicant alleges the claims are eligible for the same reasons as claim 3 of example 47 in the July 2024 Subject Matter Eligibility Examples. Remarks at 23. Applicant further asserts that the claims improves the technological field and cites to paras. 0025-26 and 0087 of the specification. Remarks at 23-25. Examiner respectfully disagrees.
As discussed in the 101 rejection above, the claims are directed to steps of insignificant extra solution activity, mental steps of observation and evaluation, or a mental process of mathematical calculations. None of the recited limitations recite specific steps that would be sufficient to demonstrate the asserted improvement to integrate the abstract idea into a practical application. The limitations also do not recite features that would amount to significantly more than the abstract idea, as discussed in the rejection above.
Unlike claim 3 of example 47, the claims do not recite specifics features that taken as a whole, includes an improvement to the computer or technological field. Claim 3 of example 47 recites features, such as detecting network intrusions, taking real time remedial actions of dropping suspicious packets, and blocking traffic from suspicious source addresses. Unlike claim 3, the claims of the invention do not recite features that demonstrate the asserted improvements described in the specification. In regards to the whether the claims adequately improve the technological field, as explained in the rejection above, Applicant describes the process of predicting performance as a manual process, which requires time. The cited paragraphs discuss, in general, how a model is trained to make predictions about player performance based on learned feature interactions. However, none of the claims recite how the model is trained, how the model learns how input features interact, nor how it utilizes such learned interactions to make performance predictions. The claims, as currently presented, merely recite steps of requiring mathematical calculations and making predictions, which can all be practically performed by a person, as is conventionally done. Spec at para. 0024. In other words, none of the claims recite limitations that sufficiently demonstrate the asserted improvement.
For at least these reasons, claims 1-20 are rejected under 35 U.S.C. 101.
Rejection of claims 1-20 under 35 U.S.C. 103
Applicant’s arguments in regards to the rejections to claims 1-20 under 35 U.S.C. 103, have been fully considered but they are not persuasive. In regards to claim 1, Applicant alleges that cited prior art fails to disclose the limitations of claim 1, as amended. Remarks at 26-27. Applicant's arguments fail to comply with 37 CFR 1.111(b) because they amount to a general allegation that the claims define a patentable invention without specifically pointing out how the language of the claims patentably distinguishes them from the references.
As set forth in the rejections above, the combination of Ruiz, Bloodworth and Avruskin discloses all the limitations of claim 1.
Applicant does not present additional arguments with regards to the remaining limitations. Therefore, Examiner asserts the cited prior art discloses all the limitations of claim 1 for the reasons explained above. In regards to the remaining claims, Applicant refers to the arguments presented in regards to claim 1, which are addressed above. Consequently, the rejection to claims 1-20 under 35 U.S.C. 103 is maintained under the new grounds of rejection as necessitated by Applicant’s amendments.
Additional Prior Art
Additional relevant prior art are listed on the attached PTO-892 form. Some examples are:
Fenyvesi et al. (US Patent Pub 2019/0318651) discloses a system and method for analyzing sports performance data using a machine algorithm.
Martin (US Patent Pub 2018/0280811) discloses a system and method for managing fantasy sports teams and leagues, such as player trades and projecting performance of athletes.
Krasadakis (US Patent Pub 2017/0109015) discloses a system and method for athlete performance assessment using selected variables and weights.
Thompson et al. (US Patent 9,463,388) discloses a system and method for fantasy sports score estimates with performance estimations.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Examiner Michael Le whose telephone number is 571-272-7970 and fax number is 571-273-7970. The examiner can normally be reached Mon-Fri 9:30 AM – 6 PM.
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, Tony Mahmoudi can be reached on 571-272-4078. 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.
/MICHAEL LE/Examiner, Art Unit 2163
/TONY MAHMOUDI/Supervisory Patent Examiner, Art Unit 2163
1 User replaces an agent with a new agent, new predictions are requested (i.e., request to project a performance…)
2 Historical performance for teams is analyzed to generate feature data for the trained models to process and make predictions.
3 Box scores and match outcomes are predicted based on the generated feature information, including historical and generated information. The predictions are performed using a neural network.
4 Historical player performance is analyzed to generate feature data of a player for trained models to process. The data is updated in real time or periodically (i.e., event data stored at an updated game file).
5 The system identifies that a match is in progress and the player’s statistics are received to generate vectors for the teams (i.e., updated team features).
6 The outcome of a match is predicted based on updated information during a match that is received in real time or periodically. This includes information about both teams (current and destination), both historical and updated, and player statistics during the match (i.e., updated player-position features).
7 Neural networks (i.e., neural network model) will learn information to enable it to predict outcomes (i.e., player box score). The information including historical feature data and real-time data (i.e. updated performance…).
8 Comparison of a predicted outcome with the actual outcome is performed.
9 The neural network (i.e., neural network model) has its parameters iteratively adjusted to generate the best predictions.
10 Game performance for a team/player is given context (i.e., raw team data is adjusted) based on average performance data.
11 Most recent data is used (i.e., adjusting raw team data). For example, on a week to week basis.
12 Game performance for a team/player is given context (i.e., raw team data is adjusted) based on average performance data.
13 Most recent data is used (i.e., adjusting raw team data). For example, on a week to week basis.
14 Historical data for sporting entities (i.e., player or team) can be used to refine a specific athlete’s or team’s performance (i.e., storing baselines as initial values for a player and team)..
15 One or more deep neural networks are utilized.
16 User replaces an agent with a new agent, new predictions are requested (i.e., request to project a performance…)
17 Historical performance for teams is analyzed to generate feature data for the trained models to process and make predictions.
18 Box scores and match outcomes are predicted based on the generated feature information, including historical and generated information. The predictions are performed using a neural network.
19 Historical player performance is analyzed to generate feature data of a player for trained models to process. The data is updated in real time or periodically (i.e., event data stored at an updated game file).
20 The system identifies that a match is in progress and the player’s statistics are received to generate vectors for the teams (i.e., updated team features).
21 The outcome of a match is predicted based on updated information during a match that is received in real time or periodically. This includes information about both teams (current and destination), both historical and updated, and player statistics during the match (i.e., updated player-position features).
22 Neural networks (i.e., neural network model) will learn information to enable it to predict outcomes (i.e., player box score). The information including historical feature data.
23 Comparison of a predicted outcome with the actual outcome.
24 The neural network (i.e., neural network model) has its parameters iteratively adjusted to generate the best predictions.