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 .
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 as being directed to a judicial exception without significantly more.
Claims 1, 10, and 17 recite receiving player positional and team formation and role information, comparing the information to determine a correspondence, and identifying a player based on that correspondence. These limitations recite the abstract mental process of observing, comparing, and evaluating information to reach a conclusion regarding player identity.
Claims 2, 11, and 18 further recite assigning coordinates and timestamps; claims 3, 12, and 19 further recite identifying and comparing jersey numbers and evaluating a confidence threshold; claims 4, 13, and 20 further recite comparing facial information; claims 5 and 14 further define the formation information; claims 6 and 15 derive formation information from prior data; and claims 7, 8, and 16 update formation based on event data. These limitations merely further specify the information collected, analyzed, compared, or updated and do not alter the abstract nature of the claims.
Claim 9 further requires use of a graph recurrent neural network (GRNN). The GRNN itself is not characterized as a mental process. Rather, claim 9 recites the GRNN as the computer tool with a high level of generality used to perform the otherwise abstract comparison of positional and formation information.
The claims do not integrate the abstract idea into a practical application. The recited video feed, computing system, processor, memory, and computer readable medium merely collect and process information using generic computing components. The claims do not recite a specific improvement to video processing, player tracking, computer operation, or machine-learning technology, but instead recite the desired result of identifying players from analyzed information. Likewise, the additional elements do not amount to significantly more. The generic computer components perform their ordinary functions, and the dependent claim limitations merely further specify data collection, comparison, classification, or updating. Claim 9 similarly does not recite an improvement to GRNN technology, but merely uses a GRNN to perform the claimed analysis.
Accordingly, claims 1 20 are directed to an abstract idea without significantly more and are therefore ineligible under 35 U.S.C. § 101.
Claim Rejections - 35 USC § 102
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 (i.e., changing from AIA to pre-AIA ) 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.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 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.
Claim 1, 2, 5, 10, 11, 14, 17, and 18 rejected under 35 U.S.C. 102(a)(1) as being anticipated by Yun et al. (US 2023/0137915 A1; hereinafter “Yun”).
Regarding claim 1,
Yun teaches: a method for identifying a player in a sports event (¶¶494-500, 548-552; Fig. 37),
comprising receiving a video feed of a sporting event; capturing, by a computing system, positional data of a player in one or more video frames of the video feed (¶¶186, 298, 308; teaching player tracking data comprising player locations obtained through image analysis of sports video and receiving camera imagery to calculate player locations);
receiving, by the computing system, team formation data for at least one team in the sporting event, wherein the team formation data comprises a player role associated with each player (¶¶497, 539-542, 548-550; teaching formation data including formation positions, e.g., LW, CF, RW, LMF and CB, and participating player information identifying which player plays each position);
determining, by the computing system, a correspondence between the positional data of a player and the team formation data (¶¶543-546; determining a player position assignment by comparing location information of the tracked player with location characteristics of formation positions to determine which player corresponds to which position);
generating, by the computing system, a player identification for the player, wherein the player identification is based on the correspondence between the positional data for the player and a player role from the team formation data (¶¶548-552; using the player position assignment and participating player information associating formation positions with player identifiers to match each tracked player to a player identifier, such as the player's name or jersey number).
Regarding claim 2,
Yun further teaches: wherein capturing position data of a player in one or more video frames of the video feed includes: assigning an x, y coordinate values to the player relative to a field of the sporting event; and assigning a time stamp to the x, y coordinate values ((¶¶344, 347-349, 373, 378, 383-385; Figs. 18, 21, 23 25). In particular, Yun teaches representing player locations according to a two dimensional stadium coordinate system having an x-axis extending along the length of the stadium and a y-axis extending along the width of the stadium (¶349), acquiring player location data at a plurality of time points (¶¶344, 347, 373), and associating player locations/frames with corresponding timestamps, e.g., 0.1 sec, 123.4 sec, and 7,200.0 sec (¶¶378, 383-385)).
Regarding claim 5,
Yun further teaches: wherein the team formation data includes a positional setup of players on a field of the sporting event ((¶¶539 542; Fig. 37). In particular, Yun teaches formation data including information identifying a plurality of positions making up a formation and location characteristic values for those positions (¶540). Yun further teaches, for example, a 3-4-3 formation comprising left wing, center forward, right wing, midfield, and center back positions having corresponding location feature values (¶541), wherein the location characteristic value of each position may be based on a representative location or representative location distribution of that position (¶542)).
Regarding claims 10, 11, 14, 17, and 18: the functionals claims limitations are similar to those of claims 1, 2, 5, 1, and 2, respectively; therefore, rejected in the same manner as applied above. Yun further teaches the system of claim 10 and CRMof claim 17 in FIG. 9 and ¶¶337-338.
Claim Rejections - 35 USC § 103
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 (i.e., changing from AIA to pre-AIA ) 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.
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.
Claims 3, 12, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Yun et al. (US 2023/0137915 A1) in view of Liu et al., Automated player identification and indexing using two-stage deep learning network (2023).
Regarding claims 3, 12, and 19:
Yun further teaches receiving a set of jersey numbers for each player in the sporting event (¶¶548-550; acquiring player participation information including the name and/or uniform number (jersey number) of a player participating in each position).
Yun does not expressly teach identifying an associated number with the player from the video feed, the associated number having an assigned confidence value; determining that the associated number matches an assigned jersey number from the set of jersey numbers; and determining that the confidence value is above a threshold value.
However, in the same field of endeavor, Liu teaches receiving jersey number information in the form of a team roster (p. 6, Database subsystem)
identifying an associated number with the player from the video feed, the associated number having an assigned confidence value; determining that the associated number matches an assigned jersey number from the set of jersey numbers; and determining that the confidence value is above a threshold value ((pp. 4 5, player detection subsystems; and Jersey number recognition subsystem; Fig. 5), detecting and recognizing jersey numbers from detected players in sports video; (p. 6, Database subsystem), associating recognized jersey numbers with players using the team roster, and (p. 7, Implementation details; Fig. 8), applying a confidence threshold to jersey number recognition, specifically an optimal confidence threshold of 0.97).
Therefore, It would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate Liu's video-based jersey number recognition into Yun's player identification system to provide an additional visual identifier for confirming the identity of a tracked player and thereby improve the reliability of player identification when positional based identification is uncertain, with Liu's confidence threshold providing a known mechanism for accepting sufficiently reliable jersey-number detections.
Claims 4, 13, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Yun et al. (US 2023/0137915 A1) in view of Chandrasekhar et al. (US 2023/0082197 A1).
Regarding claims 4, 13, and 20:
Yun does not expressly teach receiving a set of facial construction data for each player in the sporting event; identifying data of a facial reconstruction of the player from the video feed; and determining that the facial reconstruction of the player matches facial construction data received for the player.
However, in the same field of endeavor, Chandrasekhar teaches receiving a set of facial construction data for each player in the sporting event (FIGS. 3 – 4C, 6A, and ¶¶ 11, 32-33. In particular, Chandrasekhar receives the live video broadcast stream of the sporting event from a video capturing device and detects faces of the persons to compare it with pre-existing data of all players including high resolution facial images)
identifying data of a facial reconstruction of the player from the video feed (¶33, detecting faces of the persons in the frame and creating bounding boxes around the detected faces such that the faces are tightly cropped by the bounding box as illustrated in FIG. 4C. ¶37, extracting embeddings from a detected face and comparing them to another array of embeddings obtained from a previously collected static set of high resolution images as illustrated in FIG. 6A);
determining that the facial reconstruction of the player matches facial construction data received for the player (¶37, extracting embeddings from a detected face and comparing them to another array of embeddings obtained from a previously collected static set of high resolution images as illustrated in FIG. 6A. The facial recognition is based on similarity between the embeddings)
Therefore, It would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate Chandrasekhar's facial recognition technique into Yun's player identification system to provide an additional visual identification cue for confirming the identity of a tracked player and reducing erroneous player identifications when positional or role based identification is uncertain, as Chandrasekhar teaches combining recognition cues to improve the final player identification inference.
Claim 6 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Yun et al. (US 2023/0137915 A1) in view of Austerlade et al. (US 2015/0148129 A1).
Regarding claims 6 and 15:
Yun does not expressly teach that wherein the team formation data is generated, by the computing system, based on exemplary data captured prior to a start of the sports event.
However, in the same field of endeavor, Austerlade teaches wherein the team formation data is generated, by the computing system, based on exemplary data captured prior to a start of the sports event (FIG. 4, and ¶167 teach a formation models database 316 that contains models of various formations (e.g., offensive formations, defensive formations, special teams formations, etc.) defined for the relevant sport or activity (e.g., football in the depicted embodiment). The models of various formations may be derived from multi-dimensional player location information collected during prior games, practices, etc., (e.g., learned by the system) or as input by one or more teams, such as by using model generation engine 338, historical data store 336, and/or team analytics engine 346. In ¶209 Austerlade further teaches that historical data store 336 provides historical data to model generation engine 338 for learning/developing new formation models for inclusion in the formation-model database).
Therefore, It would have been obvious to one of ordinary skill in the art before the effective filing date to generate Yun's team formation data using historical player location data collected during prior games or practices, as taught by Austerlade in order to automatically learn representative formation models from previously observed player arrangements for subsequent formation and player role analysis.
Claims 7-8 and 16-17 are rejected under 35 U.S.C. 103 as being unpatentable over Yun et al. (US 2023/0137915 A1) in view of Thormann et al. (US 2021/0402307 A1).
Regarding claims 7-8 and 16-17:
Yun does not expressly teach wherein the operations further comprise: retrieving event data related to the sporting event, and based upon the retrieved event data, updating the team formation data dynamically; wherein updating the team formation data includes: updating a formation for the at least one team or a listing of players in the sporting.
However, Thormann teaches wherein the operations further comprise: retrieving event data related to the sporting event, and based upon the retrieved event data, updating the team formation data dynamically; wherein updating the team formation data includes: updating a formation for the at least one team or a listing of players in the sporting (¶55 and FIG. 3C teach automatically updating the roaster by the system in response to a substitution even);
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Yun to update its team formation based on sporting event as taught by Thormann in order to maintain the play role information consistent with the players currently participating in the sporting event, thereby allowing subsequent player identification to be performed using current rather than outdated player role information.
Claims 9 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Yun et al. (US 2023/0137915 A1) in view of Kamikawa et al. (the machine English translation of JP2021081921A, “Kami”).
Regarding claims 9 and 18:
Yun further teaches: wherein correspondence between the positional data of the player and the team formation data (¶¶543-546 teaches acquiring player position assignments by comparing the tracked location characteristics of players with the location characteristics of the positions making up the formation, thereby determining which player corresponds to which formation position. Yun also teaches that a player’s position may be identified using deep learning algorithm receiving location information of the individual player and other players and outputting a position label. Yun also teaches using player adjacency matrices, including a sequence of adjacency matrices as ANN inputs for formation analysis)
Yun does not expressly disclose determined by a graph recurrent neural network.
However, in the same field of endeavor, Kami teaches determined by a graph recurrent neural network (Kami teaches processing player positional information using graph and recurrent neural network processing. In particular, Kami teaches player positional data comprising X-Y coordinates at multiple measurement time points (¶¶22-24, 32-34) and further teaches that feature data may include the team's formation (player placement) (¶29). Kami treats the arrangement of players as a graph in which the objects are nodes and their relative positional relationships are represented and processed using Dense Graph Attention or Graph Attention (¶¶52-56). Kami further expressly teaches that data transformed by the graph attention processing are input to RNN 3218, which recurrently processes the data over successive time points (¶¶69-71; Fig. 6)
PNG
media_image1.png
1108
912
media_image1.png
Greyscale
).
Therefore, It would have been obvious to one of ordinary skill in the art to employ Kami's graph-attention architecture in performing Yun's determination of correspondence between player positional information and team formation positions because Yun determines player positions based on spatial player information, while Kami teaches processing player positional information and player relationships using graph processing followed by recurrent processing over time. Such modification would predictably permit Yun's correspondence determination to account jointly for the spatial relationships among players and the temporal evolution of those relationships.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Lucey (US 20150142716 A1) teaches artificial intelligence systems used to analyze participants engaged in an activity and, in particular, to tracking player role using non-rigid formation priors.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to WASSIM MAHROUKA whose telephone number is (571)272-2945. The examiner can normally be reached Monday-Thursday 8:00-5:00 EST.
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, Stephen Koziol can be reached at (408) 918-7630. 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.
/WASSIM MAHROUKA/Primary Examiner, Art Unit 2665
