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 Amendment
Claims 1-20 are pending.
As an initial matter, the objections to claims 5 and 14 are withdrawn in view of applicant’s amendments.
Response to Arguments
Applicant’s arguments with respect to claim(s) 1-20 have been considered but are moot because the arguments are directed towards the newly amended claims that change the scope of the claims as a whole and are open tot new grounds of rejection/interpretation.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1-5, 9-14, 18-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Terry et al. (US 20160027198) et. al. in view of Jiang et al. (“Text2Human: Text-Driven Controllable Human Image Generation”).
Re claim 1, Terry teaches a method for content generation, comprising:
displaying a generation component for generating synthetic reference media content related to a role for use in role design, the generation component comprising a plurality of generation portals ([0003] Stories in script form are typically written by scriptwriters in plain text, a script specifying the characters, dialog, backgrounds, props, director or stage directions, and scenes of a story. In order for a script to be performed or acted out, time, effort, and resources are required. Among other things, backgrounds and sets may need to be built, props and costumes acquired, actors are needed to play the characters, a director is required to coordinate the actors, stagehands, and other persons involved as specified by the script, and the like. Each change in the script, in turn, requires a corresponding change in the performance of the script), ([0004] In a computerized environment, characters may be represented as avatars and the avatars may be programmed to speak dialog, move a certain way, or otherwise serve as substitutes for human actors. Typically technical persons, such as computer programmers or coders, write program code to specify avatars and their performance actions. Such program code is in computer programming languages that are not familiar to non-technical writers, such as scriptwriters. Although scriptwriters are the experts in writing a story in script form, as opposed to computer programmers, scriptwriters likely lack the requisite computer programming knowledge to write a story in script form in computer programming languages capable of generating avatar performances), ([0098] Screen 610 includes a characters icon 612 to start specifying characteristics of a character or actor that will appear in chapter 1. Upon actuation of characters icon 612, a screen 620 of FIG. 6C is displayed. Screen 620 includes various UI elements to accept input of a character name in a character name input field 622, and to select an avatar to graphically represent the character via an avatar selection element 624 and/or 626. In screen 620, a character is named “Michelle Lee” and the “Charlotte” avatar is selected to represent the “Michelle Lee” character) and (see Fig. 6D, wherein synthetic reference media content of an avatar role includes a plurality of generation portals such as name, outfit, hair, eyes, etc.)
obtaining, via the generation component, natural language description information associated with the role, wherein the natural language description information corresponds to at least one of the plurality of generation portals (see Fig. 6D, wherein media content of a avatar role includes a plurality of generation portals with descriptive natural language information such as name, outfit, hair, eyes, etc. for each portal)
Terry does not explicitly teach providing the natural language description information to a first model to generate prompt input information for a second model, wherein the first model is a language model and the second model is a media generation model, and the second model generates synthetic media content from the prompt input information, and displaying via the generation component, a set of variant media contents generated by the second model based on the input information.
However, Jiang teaches providing the natural language description information to a first model to generate prompt input information for a second model, wherein the first model is a language model and the second model is a media generation model, and the second model generates synthetic media content from the prompt input information (see p. 2, in reference to Fig. 1, “…To bridge the gap, in this work, we propose the Text2Human framework for the text-driven controllable human image generation. As shown in Fig. 1, given a human pose, users can specify the clothes shapes and textures using solely natural language descriptions. Human images are then synthesized in accordance with the textual requests), and (See p. 6, in reference to Fig. 4, wherein a first model takes user input text prompt, and a second model uses the text prompt to generate synthesized human image.
and displaying via the generation component, a set of variant media contents generated by the second model based on the input information (see Fig. 1a wherein a synthesized human image is generated, and see Fig 1b wherein a set of variant media contents generated is shown, as different text prompts generate different synthesized images).
Terry and Jiang teaches claim 1. It would have been obvious to one of ordinary skill in the are before the effective filing date of the claimed invention to modify Terry’s content generation system including interpreting natural language to generate content to explicitly include providing natural language to a first model to generate prompt input information for a second model, wherein the first model is a language model and the second model is a media generation model, and the second model generates synthetic media content from the prompt input information, as taught by Jiang, as the references are in the analogous art of natural language interpretation for generation of visual content. An advantage of the modification is that it achieves the result of an interface for a user to provide text prompt into a first model for a second model to interpret the text prompt to generate synthetic character content, providing an improved content generation interface for the user.
Re claim 2, Terry and Jiang teaches claim 1. Furthermore, Terry teaches obtaining, via the generation component, a generating parameter associated with a generating process, and providing the generating parameter to the first model for use in the generating the prompt input information (see [0098] and Fig. 6C, selecting a starting actor such as “Charlotte”, which selects the first model avatar). Terry also teaches obtaining a generating parameter that is provided to the a first model for use in generating the prompt information (see Fig. 1 and 4, wherein inputted pose information is used for the generating of prompt input information). For motivation, see claim 1.
Re claim 3, Terry and Jiang teaches claim 1. Furthermore, Jiang teaches wherein the set of variant media contents is a first set of media contents ([see Fig. 1a, as a first set of human images generated)
The method further comprising:
Displaying, based on the request to regenerate the media content, a second set of media contents generated by the second model based on the input information (see Fig. 1b, showing at least a second set of media content generated by the second model based on input prompt information to generate variant media content). For motivation, see claim 1.
Re claim 4, Terry and Jiang teaches claim 3. Furthermore, Terry teaches wherein displaying a second set of media contents generated by the second model based on the prompt input information comprises: receiving a selection for a target media content in the first set of media content; and continuing displaying of the target media content of the first set of media contents with the second set of media contents displayed ([0100] The avatar's outfit can be specified by actuation of an outfits icon 614 in FIG. 6B. In response, a screen 640 in FIG. 6E is displayed. Screen 640 permits modifications to be made to the selected avatar's outfit. An avatar's outfit includes clothing, shoes, and accessories, such as eyeglasses, hair accessories, and bag. The avatar's default outfit items 642 are displayed along with outfit modification choices 644. Upon saving any changes, the author user is returned to screen 610 of FIG. 6B). Thus, target media content (such as different outfits worn by an avatar) can be selected and displayed with the second set of media contents displayed (the one or more avatars).
Re claim 5, Terry and Jiang teaches claim 1. Furthermore, Terry teaches wherein the plurality of generation portals comprise at least a first generation portal and a second generation portal (see Fig. 6D, comprising at least a first generation portal (such as name, hair) and a second generation portal (such as face and eyes).
and providing the description information to a first model comprises:
in response to a selection of the first generation portal, providing first description information corresponding to the first generation portal to the first model; or in response to a selection for the second generation portal, providing the first model with second description information corresponding to the second generation portal, wherein the first description information and the second description information comprise at least different information portions describing different aspects of the role (see Fig. 6D, wherein each generation portal provides description that describe different aspect of the character avatar role, such as name, eyes, etc.).
Re claim 9, Terry teaches claim 1. Furthermore, Terry teaches wherein the set of variant media contents comprises at least one of the following: text content, image content, audio content, or video content (see Fig. 6D, wherein variant media content is directed towards an image of an avatar of a role, consisting of different avatars and roles).
Claim 10-14 claims limitations in scope to claims 1-5, respectively, and is rejected for at least the reasons above.
Claim 18 claims limitations in scope to claim 9 and is rejected for at least the reasons above.
Claims 19-20 claim limitations in scope to claims 1-2, respectively, and are rejected for at least the reasons above.
Claims 6-7, 15-16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Terry et al. (US 20160027198) et. al. in view of Jiang et al. (“Text2Human: Text-Driven Controllable Human Image Generation”) and Smith et al. (US 20180025750).
Re claim 6, Terry and Jiang teaches claim 1. Terry and Jiang do not explicitly teach wherein the generation component further comprises a search portal, the method further comprising:
in response to a selection for the search portal, providing the description information to the first model for use in generating query information for a search tool; and
displaying a third set of media contents obtained by the search tool based on the query information.
However, Smith teaches wherein the generation component further comprises a search portal, the method further comprising:
in response to a selection for the search portal, providing the description information to the first model for use in generating query information for a search tool; and displaying a third set of media contents obtained by the search tool based on the query information ([0020] Featured person module 143 is a software module stored in memory 130 for execution by processor 120 to identify one or more people who may be featured in video content 131. In some implementations, featured person module 143 may receive a performance analysis from performance analysis module 141 including various elements of the role of the actor in video content 131. In one implementation, featured person module 143 may search performance data database 135 for one or more people who have all of the elements for the role of an actor in video content 131. In one implementation, featured person module 143 may search online for one or more people who have all of the elements for the role of an actor in video content 131. Featured person module 143 may identify one or more people who may be featured (e.g., inserted) in video content 131. In some implementations, a user may select one of the people to feature in video content 131), ([0048] In other implementations, featured person module 143 may search one or more remote resources to find performance data for people. For example, featured person module 143 may search the Internet for performance data of one or more people. In one implementation, featured person module 143 may search one or more websites for images, video clips, movies, or other previous performances by people that may be used as performance data for the people), and (see [0050-0053], search and inserting selected person into video content).
Terry, Jiang, and Smith teach claim 6. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Terry and Jiang’s content generation system to explicitly include a search portal to provide information to display content obtained by the search tool, as taught by Smith, as the references are in the analogous art of content generation using generation portals to provide information to a model. An advantage of the modification is that it achieves the result of allowing for a search portal that helps aid in finding description information to be applied to a model.
Re claim 7, Terry and Jiang teach claim 1. Terry and Jiang do not explicitly teach generating demand information associated with the role based on the description information and at least one selected media content of the set of media contents.
However, Smith teaches generating demand information associated with the role based on the description information and at least one selected media content of the set of media contents ([0038] FIG. 6 shows a diagram of another exemplary user interface for featuring a person in a video content using performance data associated with the person, according to one implementation of the present disclosure. User interface 685 includes performance tuner or filter 645, mood tuner 665, and table 605 including column 615 listing one or more characters to replace and column 625 including possible replacements for the characters in column 615. Performance tuner or filter 645 may be a tool that a user may use to more finely tune or filter the options related to creation of a personalized video content. As shown in FIG. 6, performance tuner 645 includes selectable options to tune or filter for a replacement actor's quality or popularity. In one implementation, the user may adjust performance tuner 645 to limit the options of replacement actors that are available to select. In FIG. 6, performance tuner 645 is set to limit selectable replacement actors to those having a quality rating of four (4) or higher. Accordingly, only Actor 1 and Actor 6 remain selectable, because each of Actors 2-5 have a quality rating of three (3) or lower. In some implementations, performance tuner may include two selectors allowing a user to set a range, such as actors having a quality or popularity between two and four). Smith teaches generating demand information associated with the role (popularity as a demand) based on the description information and at least one selected media content of the set of media contents (performance tuner including selectors for selecting range of popularity).
Terry, Jiang, and Smith teach claim 7. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Terry and Jiang’s content generation system to explicitly include generating demand information associated with a role, as taught by Smith, as the references are in the analogous art of content generation for roles. An advantage of the modification is that it achieves the result of using demand information to filter demand such as popularity level of an actor for a particular role.
Claims 15-16 claim limitations in scope to claim 6-7 and is rejected for at least the reasons above.
Claim(s) 8, 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Terry et al. (US 20160027198) in view of Jiang et al. (“Text2Human: Text-Driven Controllable Human Image Generation”) and Ume et al. (US 20240212249).
Re claim 8, Terry and Jiang teach claim 1. Terry and Jiang do not explicitly teach wherein the description information corresponds to a first language and the input information corresponds to a second language different from the first language, the second language being determined based on the second model.
However, Ume teaches wherein the description information corresponds to a first language and the input information corresponds to a second language different from the first language, the second language being determined based on the second model ([0014] Described herein are, among other things, techniques, devices, and systems for using latent space manipulation and neural animation to generate hyperreal synthetic faces. The disclosed techniques may include receiving input video data corresponding to unaltered video content. The unaltered video content may feature a subject (e.g., a person) with a face making a mouth-generated sound. For example, the unaltered video content may represent original footage of an actor saying something (e.g., a line from a movie). Audio data may also be received as input, wherein the audio data corresponds to a different mouth-generated sound. For example, a voice actor may be recorded while speaking a first language different than a second language spoken by the subject in the unaltered video content. Using the various techniques described herein, altered video content may be created, wherein the altered video content features the subject in the original footage with a hyperreal synthetic face making the different mouth-generated sound included in the input audio data. For example, the altered video content may feature an actor with a hyperreal synthetic face saying something that the actor did not actually say in the original footage. The synthetic face of the subject in the altered video content may be indiscernible from the actual, real life subject making the same mouth-generated sound. This makes the synthetic face in the altered video content hyperreal).
Terry, Jiang, and Ume teach claim 8. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Terry and Jiang’s content generation system to explicitly include description information in a first language and the input information corresponds to a second language different from the first language, as taught by Terry, as the references are in the analogous art of content generation of a role. An advantage of the modification is that it achieves the result of allowing for altering of video content of a role based on differences in languages, thus allow for content creation in a different language than an original language.
Claim 17 claims limitations in scope to claim 8 and is rejected for at least the reasons above.
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 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 Peter Hoang whose telephone number is (571)270-1346. The examiner can normally be reached Monday-Friday 8:00 am - 5:00 pm PST.
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, Hajnik F. Daniel can be reached at (571) 272-7642. 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.
/PETER HOANG/ Primary Examiner, Art Unit 2616
Prosecution Insights