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 § 112
The following is a quotation of 35 U.S.C. 112(d):
(d) REFERENCE IN DEPENDENT FORMS.—Subject to subsection (e), a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
The following is a quotation of pre-AIA 35 U.S.C. 112, fourth paragraph:
Subject to the following paragraph [i.e., the fifth paragraph of pre-AIA 35 U.S.C. 112], a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
Claim 15 is rejected under 35 U.S.C. 112(d) or pre-AIA 35 U.S.C. 112, 4th paragraph, as being of improper dependent form for failing to further limit the subject matter of the claim upon which it depends, or for failing to include all the limitations of the claim upon which it depends. Wherein claim 14 embodies all of the limitations of claim 15. Applicant may cancel the claim(s), amend the claim(s) to place the claim(s) in proper dependent form, rewrite the claim(s) in independent form, or present a sufficient showing that the dependent claim(s) complies with the statutory requirements.
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.
Claim(s) 1-8 and 14-18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Mahyar et al., US PGPUB No. 10999566 B1, hereinafter Mahyar, and further in view of Bai et al., US PGPUB No. 20260196033 A1, hereinafter Bai.
Regarding claim 1, Mahyar discloses a system (Mahyar; a system [Col. 18, lines 2-17 and Col. 23, line 27 to Col. 24, line 22], as illustrated within Fig. 6) comprising:
at least one processor (Mahyar; the system [as addressed above] comprises at least one processor [Col. 20, line 25-51]);
at least one memory component storing instructions that, when executed by the at least one processor, cause the at least one processor to perform operations (Mahyar; the system [as addressed above] comprises at least one memory component storing instructions [Col. 19, line 10 to Col. 20, line 6] that cause the at least one processor to perform operations [Col. 23, line 27 to Col. 24, line 45] when executed by the at least one processor [Col. 20, lines 25-51]) comprising:
accessing a sequence of events (Mahyar; the processor [as addressed above] comprises accessing a sequence of events [Col. 6, line 62 to Col. 7, line 18 and Col. 7, line 49 to Col. 8, line 2]; moreover, sequence of event [Col. 5, lines 1-40], as illustrated within Fig. 1), the sequence of events comprising time ranges for events of the sequence of events and text descriptions for the events (Mahyar; the sequence of events [as addressed above] comprising time ranges for events of the sequence of events and text descriptions for the events [Col. 6, line 64 to Col. 7, line 27]; wherein, segments are linked to time [Col. 13, lines 10-23]);
accessing a global caption (Mahyar; the processor [as addressed above] comprises accessing a global caption (i.e. (non-prompt) text description, aggregate text description) [Col. 3, lines 15-34 and Col. 4, lines 59-57]; additionally, content processing engine [Col. 9, line 55 to Col. 10, line 27]), the global caption comprising a text description for the sequence of events (Mahyar; the global caption (i.e. (non-prompt) text description, aggregate text description) comprising a text description for the sequence of events [Col. 2, line 15-58]; wherein, textual description generation engine [Col. 4, lines 48-67]; moreover, generating textual descriptions [Col. 3, line 65 to Col. 4, line 47]); and
inputting the sequence of events and the global caption into a trained neural network to generate a video or an audio sequence (Mahyar; the processor [as addressed above] comprises inputting the sequence of events and the global caption into a trained NN [Col. 2, line 33 to Col. 3, line 7, Col. 3, line 65 to Col. 4, line 21] to generate a video or an audio sequence [Col. 4, lines 36-67 and Col. 5, line 32-51]; moreover, one or more action detection and/or object detection algorithm to process video frames or set of frames in relation to outputting audio (as a form of textual description) [Col. 15, lines 21-52 and Col. 16, lines 12-25 17]).
Mahyar fails to disclose inputting the sequence of events and the global caption simultaneously into a trained neural network to generate a video or an audio sequence.
However, Bai teaches inputting the sequence of events and the global caption simultaneously into a trained neural network to generate a video or an audio sequence (Bai; inputting the sequence of events and the global caption simultaneously into a trained NN to generate a video or an audio sequence [¶ 0036-0038], as illustrated within Fig. 3; additional; video generation model [¶ 0028-0029, ¶ 0031, and ¶ 0034], as illustrated within Figs. 1 and 2).
Mahyar and Bai are considered to be analogous art because both pertain to generating and/or managing data in relation with providing media data to a user, wherein one or more computerized units are utilized in order to produce a mixed reality effect.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing of the claimed invention was made to modify Mahyar, to incorporate inputting the sequence of events and the global caption simultaneously into a trained neural network to generate a video or an audio sequence (as taught by Bai), in order to provide improved imaging using machine-learning models (Bai; [¶ 0002-0003]).
Regarding claim 2, Mahyar in view of Bai further disclose the system of claim 1, wherein content depicted within frames of the video or sounds of the audio sequence during a time range of the time ranges is in accordance with a corresponding text description of the text descriptions (Mahyar; content depicted within frames of the video or sounds of the audio sequence during a time range (i.e. start and stop time) of the time ranges (i.e. possible time pairs) is in accordance with a corresponding text description of the text descriptions [Col. 6, line 64 to Col. 7, line 27]; additionally, time segment in relation with audio [Col. 13, lines 10-23]).
Regarding claim 3, Mahyar in view of Bai further disclose the system of claim 1, wherein the operations (Mahyar; the operations [as addressed within the parent claim(s)]) further comprise:
generating an event for each of the plurality of portions to generate the sequence of events (Mahyar; generating an event/action for each of the plurality of portions to generate the sequence of events/actions [Col. 15, lines 21-52 and Col. 16, lines 12-30], as illustrated within Fig. 5; moreover, generation of textual descriptions of video content in relation with determining several actions [Col. 3, line 65 to Col. 4, line 35], as illustrated within Fig. 1);
determining the time ranges for the sequence of events (Mahyar; determining the time ranges for the sequence of events/actions [Col. 6, line 64 to Col. 7, line 27]; additionally, time segment in relation with audio [Col. 13, lines 10-23]); and
determining the global caption based on the sequence of events (Mahyar; determining the global caption (i.e. (non-prompt) text description, aggregate text description) based on the sequence of events/actions [Col. 4, lines 1-35 and lines 59-57]).
Bai further teaches accessing a text prompt (Bai; accessing a text prompt [¶ 0034 and ¶ 0038]; wherein, prompt is an input [¶ 0025-0026 and ¶ 0028] and/or a target [¶ 0057]; and wherein, a prompt is associated with action [¶ 0058 and ¶ 0068]), the text prompt comprising a plurality of portions (Bai; the text prompt comprising a plurality of portions [¶ 0028]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing of the claimed invention was made to modify Mahyar as modified by Bai, to incorporate accessing a text prompt, the text prompt comprising a plurality of portions (as taught by Bai), in order to provide improved imaging using machine-learning models (Bai; [¶ 0002-0003]).
Regarding claim 4, Mahyar in view of Bai further disclose the system of claim 3, wherein the trained neural network is a first trained neural network (Mahyar; the trained NN [as addressed within the parent claim(s)] is a 1st trained NN [Col. 7, line 49 to Col. 8, line 2]), and wherein the generating the event for each of the plurality of portions to generate the sequence of events (Mahyar; the generating the event/action for each of the plurality of portions to generate the sequence of events/actions [as addressed within the parent claim(s)]) further comprises:
invoking a second trained neural network with the text prompt as input (Mahyar; invoking a 2nd trained NN with the text/description as input [Col. 8, lines 30-59] and the 2nd trained NN is associated with an event for each of the plurality of portions (given the 1st NN) [Col. 7, line 49 to Col. 8, line 2]).
Bai further teaches invoking a trained neural network with the text prompt as input and a request indicating the trained neural network is to generate an event for each of the plurality of portions (Bai; invoking a trained NN with the text prompt as input and a request indicating the trained NN is to generate an event for each of the plurality of portions [¶ 0034 and ¶ 0057-0058]; moreover, a text prompt is integrated into a diffusion model [¶ 0038], as illustrated within Fig. 3).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing of the claimed invention was made to modify Mahyar as modified by Bai, to incorporate invoking a trained neural network with the text prompt as input and a request indicating the trained neural network is to generate an event for each of the plurality of portions (as taught by Bai), in order to provide improved imaging using machine-learning models (Bai; [¶ 0002-0003]).
Regarding claim 5, Mahyar in view of Bai further disclose the system of claim 1, wherein content depicted in frames of the video or sounds of the audio sequence are in accordance with the text description of the global caption (Mahyar; content depicted in frames of the video or sounds of the audio sequence are in accordance with the text description of the global caption (i.e. (non-prompt) text description, aggregate text description) [Col. 4, lines 1-35 and lines 48-67]).
Regarding claim 6, Mahyar in view of Bai further disclose the system of claim 1, the operations (Mahyar; the operations [as addressed within the parent claim(s)]).
Bai further teaches accessing a text prompt (Bai; accessing a text prompt [¶ 0034 and ¶ 0038]; wherein, prompt is an input [¶ 0025-0026 and ¶ 0028] and/or a target [¶ 0057]; and wherein, a prompt is associated with action [¶ 0058 and ¶ 0068]), the text prompt comprising a text description of an event (Bai; the text prompt comprising a text description of an event [¶ 0028 and ¶ 0057-0058]); and
generating the sequence of events from the text description (Bai; generating the sequence of events from the text description [¶ 0034 and ¶ 0057], as Illustrated within Figs. 7A-B).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing of the claimed invention was made to modify Mahyar as modified by Bai, to incorporate accessing a text prompt, the text prompt comprising a text description of an event; and generating the sequence of events from the text description (as taught by Bai), in order to provide improved imaging using machine-learning models (Bai; [¶ 0002-0003]).
Regarding claim 7, Mahyar in view of Bai further disclose the system of claim 6, wherein the trained neural network is a first trained neural network (Mahyar; the trained NN [as addressed within the parent claim(s)] is a 1st trained NN [Col. 7, line 49 to Col. 8, line 2]);
invoking a second trained neural network with the text description as input (Mahyar; invoking a 2nd trained NN with the text description as input [Col. 8, lines 30-59] and the 2nd trained NN is associated the sequence of events and the time ranges [Col. 7, lines 1-27 and Col. 7, line 49 to Col. 8, line 2]); and
to generate the sequence of events and the time ranges (Mahyar; to generate the sequence of events and the time ranges [Col. 7, lines 1-27 and Col. 7, line 49 to Col. 8, line 2]).
Bai further teaches wherein the generating the sequence of events from the text description (Bai; the generating the sequence of events from the text description [¶ 0037-0038 and ¶ 0057], as illustrated within Figs. 7A-B) further comprises:
invoking a trained neural network with the text description as input and a request indicating the trained neural network is to generate the sequence of events and the time ranges (Bai; invoking a trained NN with the text description as input and a request indicating the trained NN is to generate the sequence of events and the implicit time ranges (given temporal attention layers) [¶ 0037-0038 and ¶ 0057).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing of the claimed invention was made to modify Mahyar as modified by Bai, to incorporate wherein the generating the sequence of events from the text description further comprises: invoking a trained neural network with the text description as input and a request indicating the trained neural network is to generate the sequence of events and the time ranges (as taught by Bai), in order to provide improved imaging using machine-learning models (Bai; [¶ 0002-0003]).
Regarding claim 8, Mahyar in view of Bai further disclose the system of claim 1, wherein the sequence of events comprises a scene cut (Mahyar; the sequence of events comprises a scene cut (i.e. interrupt/pause or stop) [Col. 6, line 64 to Col. 7, line 27]), the scene cut comprising a scene cut time (Mahyar; the scene cut [as addressed above] comprising a scene cut time (i.e. interrupt, start and/or stop time) [Col. 6, line 64 to Col. 7, line 27]; additionally, a time segment (e.g. cut) in relation with audio [Col. 13, lines 10-23], as illustrated within Fig. 4), wherein content depicted in frames of the video or sounds of the audio sequence before the scene cut time are not continuous with content depicted in the frames of the video or the sounds of the audio sequence after the scene cut time (Mahyar; content depicted in frames of the video or sounds of the audio sequence [as addressed within the parent claim(s)] before the scene cut time (i.e. interrupt, start and/or stop time) are not continuous with content depicted in the frames of the video or the sounds of the audio sequence after the scene cut time (i.e. start and/or stop time) [Col. 6, line 64 to Col. 7, line 27]; additionally, an audio segment that involve a before and after [as addressed above]).
Regarding claim 14, the rejection of claim 14 is addressed within the rejection of claims 1 & 2, due to the similarities claim 14 and claims 1 & 2 share, therefore refer to the rejection of claims 1 & 2 regarding the rejection of claim 14. Although, claim 14 and claims 1 & 2 may not be identical, they are considerably comparable or substantially equivalent given their overlapping subject matter. Thus, it is reasonable to reject claim 14 based on the teachings and rational in relation with the prior art within the rejection of claims 1 & 2.
Regarding claim 15, the rejection of claim 15 is addressed within the rejection of claim 2, due to the similarities claim 15 and claim 2 share, therefore refer to the rejection of claim 2 regarding the rejection of claim 15.
Regarding claim 16, the rejection of claim 16 is addressed within the rejection of claim 1, due to the similarities claim 16 and claim 1 share, therefore refer to the rejection of claim 1 regarding the rejection of claim 16. Although, claim 16 and claim 1 may not be identical, they are considerably comparable or substantially equivalent given their overlapping subject matter. However, the subject matter/limitations not addressed by claim 1 is/are addressed below.
Mahyar discloses a non-transitory computer-readable storage medium storing instructions (Mahyar; a non-transitory computer-readable storage medium storing instructions executed by the at least one processor [Col. 19, line 10 to Col. 20, line 6 and Col. 20, lines 25-51]; moreover, performed operations [Col. 23, line 27 to Col. 24, line 45]).
(further refer to the rejection of claim 1)
Regarding claim 17, the rejection of claim 17 is addressed within the rejection of claim 2, due to the similarities claim 17 and claim 2 share, therefore refer to the rejection of claim 2 regarding the rejection of claim 17.
Regarding claim 18, the rejection of claim 18 is addressed within the rejection of claim 5, due to the similarities claim 18 and claim 5 share, therefore refer to the rejection of claim 5 regarding the rejection of claim 18.
Regarding claim 19, the rejection of claim 19 is addressed within the rejection of claim 3, due to the similarities claim 19 and claim 3 share, therefore refer to the rejection of claim 3 regarding the rejection of claim 19.
Allowable Subject Matter
Claims 9-13 and 20 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
(regarding action models)
Wang et al. (US PGPUB 20250166377 A1); and
Mittal et al. (US Patent No. 12386890 B1).
(regarding prompt-based video generation and UI for video editing)
Koch et al. (US PGPUB No. 20260105660 A1); and
Brooks et al. (US PGPUB No. 20250259362 A1).
(regarding prompt-based video generation involving descriptions)
Zhang et al. (US PGPUB No. 20250175679 A1); and
Hu et al. (US Patent No. 12664710 B1).
(regarding video generation associated with a timeline, timestamps, and/or temporal coherence)
Gu et al. (US PGPUB No. 20260212673 A1); and
Babaeizadeh et al. (US Patent No. 12750565 B2).
(regarding media generation associated with diffusion time steps and cross-attention)
Cohen et al. (US PGPUB No. 20260094327 A1); and
Yang et al. (US PGPUB No. 20260195587 A1).
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Refer to PTO-892, Notice of Reference Cited for a listing of analogous art.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Charles Lloyd Beard whose telephone number is (571)272-5735. The examiner can normally be reached Monday - Friday, 8:00 AM - 5:00 PM, alternate Fridays 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, Tammy Goddard can be reached at (571) 272-7773. 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.
CHARLES LLOYD. BEARD
Primary Examiner
Art Unit 2611
/CHARLES L BEARD/Primary Examiner, Art Unit 2611
Prosecution Insights