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 .
Response to Arguments
Applicant's arguments filed 10/27/25 have been fully considered but they are not persuasive.
Applicant argues that the prior art does not teach creating, by a processor, a prompt for a large language model, the prompt comprising: the at least one statistic and a set of constraints configured to produce as output from the LLM a fantasy team recap; the fantasy team recap output being an electronic file created by the LLM (Amendment, pages 9, 10).
The examiner disagrees, since Miller et al. disclose “in accordance with a user instruction as to voice style, a prompt may instruct the LLM to generate a script in the form of a radio or television sports broadcast reporting scores for a fantasy sporting “event.”… a schedule may be specified at which a content generation process will request the latest data points with respect to a user's fantasy sport team/players/league… By way of illustration, the data may be requested every 15 minutes, every hour, every three hours, or other time period. The data points may then be used to generate a prompt for the LLM (or other such AI engine), which in turn may generate a script which may be textually, audibly, and/or via video (e.g., comprising an animated or deepfake talking head and comprising an audio track) presented to a user via a user device… a prompt may instruct the LLM to generate a script in the speech style of a film critic or a cartoon character.” (paragraphs 30 – 35).
Applicant’s arguments, see pages 7, 8, filed 10/27/25, with respect to claims 1 - 20 have been fully considered and are persuasive. The rejection of claims 1 – 20 under 35 U.S.C 101 has been withdrawn.
Claim Rejections - 35 USC § 102
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)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1 – 8, 11, 12, 14 – 20 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Miller et al. (US PAP 2025/0139160).
As per claims 1, 14, and 20, Miller et al. teach a method comprising:
obtaining, by a processor, at least one statistic related to a recent history of a fantasy athletic team managed by a user within a fantasy athletic league (“Fantasy managers may rely on real-time updates and statistics from sports news outlets or league-provided platforms to track their team's performance and to make strategic decisions. Such updates and statistics may be included in the LLM-generated script.”; paragraphs 87, 95);
creating, by the processor, a prompt for a large language model (LLM), the prompt comprising (“The prompt may optionally be submitted to the LLM in real time”; paragraph 98):
the at least one statistic; and a set of constraints configured to produce as output from the LLM a fantasy team recap that conforms to at least one predetermined guideline, the fantasy team recap output being an electronic file created by the LLM (“in accordance with a user instruction as to voice style, a prompt may instruct the LLM to generate a script in the form of a radio or television sports broadcast reporting scores for a fantasy sporting “event.”… a schedule may be specified at which a content generation process will request the latest data points with respect to a user's fantasy sport team/players/league… By way of illustration, the data may be requested every 15 minutes, every hour, every three hours, or other time period. The data points may then be used to generate a prompt for the LLM (or other such AI engine), which in turn may generate a script which may be textually, audibly, and/or via video (e.g., comprising an animated or deepfake talking head and comprising an audio track) presented to a user via a user device… a prompt may instruct the LLM to generate a script in the speech style of a film critic or a cartoon character.”; paragraphs 30 - 35, 98);
providing, by the processor, the prompt to the LLM as input (“The prompt may optionally be submitted to the LLM in real time”; paragraph 98); and
causing display, by the processor, of the fantasy team recap output by the LLM in response to processing the prompt by the LLM (“The prompt may be configured to cause the LLM to generate a recap providing the desired data in a fluid, natural language manner…the query/request may be transmitted to the AI engine (e.g., LLM) without performing a cache lookup. At block 506, the query/request response from the AI engine may be received and transmitted to the user device for display and playback”; paragraphs 30 – 35, 98, 101, 156).
As per claims 2, 15, Miller et al. further disclose the recent history of the fantasy athletic team comprises a drafting of players of the fantasy athletic team and the fantasy team recap comprises a draft recap (“the results of a league draft may be retrieved from a draft data resource (e.g., a database, feed, a source specified via a URL, or other data source). Optionally, a draft label may be specified to retrieve results for a specific draft. The resource may include a list of draft picks including the overall number of the picks, the round number, the number of the pick in the round, the player picked, and the team that picked the player. In the instance where there is a salary cap draft, the resource may also include a record of the bids in the salary cap. The draft results may also contain a status element that indicates if the draft is in progress or is complete.”; paragraphs 99, 126).
As per claims 3, 16, Miller et al. further disclose the recent history of the fantasy athletic team comprises a performance of the fantasy athletic team over a predetermined window of time and the fantasy team recap comprises a recap for the predetermined window of time (“the reporting period may be from the last time reporting content has been provided to the user, the previous 24 hours, the previous day, the previous week, from the beginning of the season to the current time, when scores become official, and/or other period… statistics for a league for a specified timeframe paragraphs 124, 128 - 136).
As per claims 4, 17, Miller et al. further disclose the recent history of the fantasy athletic team comprises a matchup against an additional fantasy athletic team within the fantasy athletic league and the fantasy team recap comprises a matchup recap (“breakdown standings against opponents for a fantasy league (e.g., in the instances where leagues use a head-to-head scoring system as matchups and opponents only exist for head-to-head league) where the data may be broken down by actual standings against each opponent and by standings against each team if each team played every team each period”; paragraphs 88, 92, 133).
As per claims 5, 18, Miller et al. further disclose obtaining, by the processor, the at least one statistic comprises calculating an expected performance of the fantasy athletic team over a duration of a season of the fantasy athletic league based at least in part on a plurality of expected performances of a plurality of players on the fantasy athletic team (“Fantasy managers may rely on real-time updates and statistics from sports news outlets or league-provided platforms to track their team's performance and to make strategic decisions. Such updates and statistics may be included in the LLM-generated script.”; paragraphs 87, 95, 96).
As per claims 6, 19, Miller et al. further disclose obtaining, by the processor, the at least one statistic comprises: calculating an expected performance of at least one additional fantasy athletic team within the fantasy athletic league over the duration of the season of the fantasy athletic league; and comparing the expected performance of the fantasy athletic team over the duration of the season of the fantasy athletic league to the expected performance of the at least one additional fantasy athletic team (“In head-to-head leagues, fantasy teams compete against one another each week, with the team scoring the most points winning that week's matchup. In rotisserie-style leagues, teams accumulate points over the course of a season, and rankings are based on cumulative statistics. The results of team scoring for each league a user is participating in (e.g., as a manager) may be included in the LLM-generated script.”; paragraphs 87 – 98).
As per claim 7, Miller et al. further disclose obtaining, by the processor, the at least one statistic comprises: calculating an expected performance of at least one hypothetical fantasy athletic team selected by an algorithm over the duration of the season of the fantasy athletic league; and comparing the expected performance of the fantasy athletic team over the duration of the season of the fantasy athletic league to the expected performance of at least one hypothetical fantasy athletic team selected by the algorithm (“Many fantasy leagues have playoff rounds toward the end of the sports season, mimicking the real-world playoffs. Teams that perform sufficiently well during the regular season may advance to compete for the league championship. The results of advancement to the playoffs and the results of the playoff games and championship may be included in the LLM-generated script.”: paragraphs 87 – 98).
As per claim 8, Miller et al. further disclose calculating the expected performance of the fantasy athletic team based at least in part on a plurality of the expected performances of the plurality of players on the fantasy athletic team comprises calculating, for each player in the plurality of the players, a numerical value of the player compared to a numerical value of a lowest-performing available player of a same position within the fantasy athletic league (allowing managers to strengthen their teams by acquiring high-performing players. Such trades may be included in the LLM-generated script. …the LLM may be used to generate content scripts using league specific data for a given league including results of competitions, recent transactions in the league, best available free agent players, player injury reports, recent news updates on players for the user's rostered players, an identification of players performing very well or very poorly”; paragraphs 87 – 99).
As per claim 11, Miller et al. further disclose the set of constraints configured to produce as the output from the LLM the fantasy team recap that conforms to the at least one predetermined guideline comprises instructions specifying a conversational tone for the fantasy team recap (“the script text generated by the LLM may be converted to speech using a text-to-speech (TTS) service… perform text preprocessing to improve pronunciation and prosody (the rhythm, stress, and intonation of speech)”; paragraphs 76 – 78).
As per claim 12, Miller et al. further disclose the set of constraints configured to produce as the output from the LLM the fantasy team recap that conforms to the at least one predetermined guideline comprises instructions specifying a data format for the fantasy team recap (“The prompt template/format may optionally be specified by the user in whole or in part (e.g., to further customize the generated content)… Fantasy leagues can operate in different formats. In head-to-head leagues, fantasy teams compete against one another each week, with the team scoring the most points winning that week's matchup.” paragraphs 77, 88).
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 9, 10 are rejected under 35 U.S.C. 103 as being unpatentable over Miller et al. (US PAP 2025/0139160) in view of Frazier (US PAP 2018/0318720).
As per claim 9, Miller et al. do not specifically teach creating, by the processor, the prompt for the LLM comprises replacing a name of a player on the fantasy athletic team with a placeholder identifier for the player; and causing display, by the processor, of the fantasy team recap comprises replacing the placeholder identifier for the player in the fantasy team recap with the name of the player.
Frazier discloses Drafting quivers are ranked lists comprising placeholders for up to 20 players, used as a draft organizer for a weekly head-to-head drafts… a player is removed from its drafting quiver and returned to the player pool by clicking on a green arrow found to the right of the player's name (paragraphs 35 – 37).
Therefore, it would have been obvious to one of ordinary skill in the art before the filing date of the claimed invention to use placeholder identifier as taught by Frazier in Miller et al., because that would help automatically remove player from the fantasy team (paragraph 41).
As per claim 10, Miller et al. do not specifically teach creating, by the processor, the prompt for the LLM comprises replacing a user-supplied name of the fantasy athletic team with a placeholder identifier for the fantasy athletic team; causing display, by the processor, of the fantasy team recap comprises replacing the placeholder identifier for the fantasy athletic team in the fantasy team recap with the user-supplied name of the fantasy athletic team.
Frazier discloses Drafting quivers are ranked lists comprising placeholders for up to 20 players, used as a draft organizer for a weekly head-to-head drafts… a player is removed from its drafting quiver and returned to the player pool by clicking on a green arrow found to the right of the player's name (paragraphs 35 – 37).
Therefore, it would have been obvious to one of ordinary skill in the art before the filing date of the claimed invention to use placeholder identifier as taught by Frazier in Miller et al., because that would help automatically remove player from the fantasy team (paragraph 41).
Claim 13 is rejected under 35 U.S.C. 103 as being unpatentable over Miller et al. (US PAP 2025/0139160) in view of Jones (US PAP 2017/0188097).
As per claim 13, Miller et al. do not specifically teach providing as input to the LLM the fantasy team recap and a prompt instructing the LLM to output an evaluation of the fantasy team recap for offensiveness; and performing a moderation action on the fantasy team recap based on the evaluation output by the LLM.
Jones teach that the content event related to a fantasy reception or rushing touchdown can be assigned a higher magnitude of fantasy weight than an accumulation of yards irrespective of the number of fantasy points or magnitude of offensive rating associated thereto as the content event type might be more prone to be reviewed, summarized, compiled or excluded along with other content events, etc.(paragraph 100)… The content rating component defining a potentially offensive content event can define extraction, redaction, overlay of advertising or other media so as to make imperceptible the content event during playback (paragraph 107).
Therefore, it would have been obvious to one of ordinary skill in the art before the filing date of the claimed invention to determine the content offensiveness as taught by Jones in Miller et al., because that would help delete the offensive content from the recap (paragraph 108).
Conclusion
THIS ACTION IS MADE FINAL. 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 nonprovisional extension fee (37 CFR 1.17(a)) 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 mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to LEONARD SAINT-CYR whose telephone number is (571)272-4247. The examiner can normally be reached Monday- Friday.
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, Richemond Dorvil can be reached at (571)272-7602. 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.
/LEONARD SAINT-CYR/ Primary Examiner, Art Unit 2658