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 Interpretation
During patent examination, pending claims must be “given their broadest reasonable interpretation consistent with the specification.” MPEP 2111; See also, MPEP 2173.02. Limitations appearing in the specification but not recited in the claim are not read into the claim. In re Prater, 415 F.2d 1393, 1404-05, 162 USPQ 541, 550-551 (CCPA 1969). See also, In re Zletz, 893 F.2d 319, 321-22, 13 USPQ2d 1320, 1322 (Fed. Cir. 1989) (“During patent examination the pending claims must be interpreted as broadly as their terms reasonably allow”). The reason is simply that during patent prosecution when claims can be amended, ambiguities should be recognized, scope and breadth of language explored, and clarification imposed. An essential purpose of patent examination is to fashion claims that are precise, clear, correct, and unambiguous. Only in this way can uncertainties of claim scope be removed, as much as possible, during the administrative process.
The Examiner respectfully requests of the Applicant in preparing responses, to consider fully the entirety of the reference(s) as potentially teaching all or part of the claimed invention. It is noted, REFERENCES ARE RELEVANT AS PRIOR ART FOR ALL THEY CONTAIN.
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)(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(s) 1-20 are rejected under 35 U.S.C. 102 (a)(1) as being anticipated by U.S. Patent Application Publication No. 2024/0221242 A1 to Greenen et al. (hereinafter Greenen).
With regard to claim 1, Greenen discloses:
1. A method comprising:
obtaining a design prompt that describes a document type (see, detailed description, including, Sets of content tiles can then be generated that satisfy these boundary conditions, allowing for a random, semi-random, or selected layout of those content tiles in a region as long as the layout of tiles satisfies the boundary conditions. Para. 0022);
selecting a design template for the document type based on the design prompt (see, Fig. 1, and detailed description, including, Such an image tile 100 can be selected or generated manually, or may be synthesized based on text or selection input, among other such options, para. 0026);
generating, using an image generation model, an image for the design template based on the design prompt (see, detailed description, including, a trained, stable diffusion model can be used that does not need to undergo any specialized training, and boundary-compliant tiles can be iteratively generated over repeated inference loops, para. 0022); and
generating a design document based on the design template, wherein the design document has the document type and includes the image at a location indicated by the design template (see, detailed description, including, Using a naive tiling approach to fill a first region 120, such as approaches utilized in prior systems, such a single image tile can be placed repeatedly, edge-to-edge, across the region in order to cause the region to be filled with the target texture. Such an approach has advantages as it only requires creation and storage of a single, small image file or texture that can be reused multiple times, rather than one or more large texture images that require significant resource to create, store, transmit, and use, para. 0026).
With regard to claim 2, Greenen discloses:
2. The method of claim 1, further comprising:
generating, using a text generation model, text for the design template based on the design prompt, wherein the design document includes the text at a location determined according to the design template (see, detailed description, including, Such an image tile 100 can be selected or generated manually, or may be synthesized based on text or selection input, among other such options. Using a naive tiling approach to fill a first region 120, such as approaches utilized in prior systems, such a single image tile can be placed repeatedly, edge-to-edge, across the region in order to cause the region to be filled with the target texture, para. 0026).
With regard to claim 3, Greenen discloses
3. The method of claim 1, wherein selecting the design template comprises:
encoding the design prompt to obtain an intent embedding (see, detailed description, including, The diffusion network can be given an encoding or latent embedding as input, as well as a set of noisy prior images, para. 0023);
encoding the design template to obtain a template embedding (see, detailed description, including, encoding or latent embedding can be generated from input/output specifying a type of content to be synthesized for the set of content tiles, where the input can come in any of a number of different forms, such as a sample image or text. Para. 0023); and
comparing the template embedding to the intent embedding to obtain a similarity score, wherein the design template is selected from the plurality of design templates based on the similarity score (see, Fig. 13, and detailed description, including, training pipeline 1404 similar to a first example described with respect to FIG. 13 may be used for a first machine learning model, training pipeline 1404 similar to a second example described with respect to FIG. 13, para. 0125).
With regard to claim 4, Greenen discloses
4. The method of claim 1, wherein generating the image comprises:
generating an image generation prompt based on the design prompt and the image field of the design template, wherein the image is generated based on the image generation prompt (see, detailed description, including, one or more pre-trained models can be used at inference time. In at least one embodiment, a trained, stable diffusion model can be used that does not need to undergo any specialized training, and boundary-compliant tiles can be iteratively generated over repeated inference loops. Such an approach can enable many different types of pre-trained networks, para. 0022).
With regard to claim 5, Greenen discloses
5. The method of claim 1, further comprising:
identifying a style embedding of the design template, wherein the style embedding comprises image style features and text features, and wherein the design template is selected based on the style embedding (see, detailed description, including, boundary-compliant tiles can be iteratively generated over repeated inference loops. Such an approach can enable many different types of pre-trained networks (e.g., stable diffusion, Dalle, or mid-journey networks) to be used, where the quality of those models can be leveraged to generate tiles, para. 0022).
With regard to claim 6, Greenen discloses
6. The method of claim 5, further comprising:
concatenating the image style features and the text features to obtain the style embedding 9swee, detailed description, including, A content image can be provided to serve as an example of the texture, but other inputs can be used as well, such as texture inputs, feature vectors, latent encodings, textual terms or descriptions, and the like, where the input can be converted to a form such as an encoding or latent embedding as needed, para. 0034).
With regard to claim 7, Greenen discloses
7. The method of claim 1, wherein selecting the design template comprises:
obtaining a user preference embedding, wherein the design template is selected based on the user preference embedding (see, detailed description, including, In some embodiments a user may also have an option to specify a ruleset to be used, para. 0037).
With regard to claim 8, Greenen discloses
8. The method of claim 1, wherein selecting the design template comprises:
encoding an image of the design template to obtain a mood embedding, wherein the design template is selected based at least in part on the embedding (see, detailed description, including, A content image can be provided to serve as an example of the texture, but other inputs can be used as well, such as texture inputs, feature vectors, latent encodings, textual terms or descriptions, and the like, where the input can be converted to a form such as an encoding or latent embedding as needed, para. 0034).
With regard to claim 9, claim 9 (a non-transitory computer readable medium claim) recites substantially similar limitations to claim 1 and claim 2 (both method claims) and is therefore rejected using the same art and rationale set forth above.
With regard to claim 10, claim 10 (a non-transitory computer readable medium claim) recites substantially similar limitations to claim 3 (a method claim) and is therefore rejected using the same art and rationale set forth above.
With regard to claim 11, claim 11 (a non-transitory computer readable medium claim) recites substantially similar limitations to claim 5 (a method claim) and is therefore rejected using the same art and rationale set forth above.
With regard to claim 12, claim 12 (a non-transitory computer readable medium claim) recites substantially similar limitations to claim 7 (a method claim) and is therefore rejected using the same art and rationale set forth above.
With regard to claim 13, claim 13 (a non-transitory computer readable medium claim) recites substantially similar limitations to claim 8 (a method claim) and is therefore rejected using the same art and rationale set forth above.
With regard to claim 14, claim 14 (a system claim) recites substantially similar limitations to claim 1 (a method claim) (with the addition of a processing device coupled to a memory component, see, detailed description, including, A video game application can cause the relevant diffusion tiles to be loaded into memory, such as into GPU memory, and the GPU can perform random selection and placement that complies with the relevant boundary conditions. A table of indices can be used along with the textures and shaders to place and render the appropriate textures, para. 0043) and is therefore rejected using the same art and rationale set forth above.
With regard to claim 15, claim 15 (a system claim) recites substantially similar limitations to claim 2 (a method claim) and is therefore rejected using the same art and rationale set forth above.
With regard to claim 16, claim 16 (a system claim) recites substantially similar limitations to claim 4 (a method claim) and is therefore rejected using the same art and rationale set forth above.
17. The system of claim 14, further comprising:
the image generation model comprises a diffusion model (see, Fig. 1, and detailed description, including, such a tiling approach, a small number (e.g., 8 or 12) of image tiles or textures can be generated using, for example, a trained diffusion model. These diffusion-based (or diffusion-generated) para. 0027).
With regard to claim 18, claim 18 (a system claim) recites substantially similar limitations to claim 5 (a method claim) and is therefore rejected using the same art and rationale set forth above.
With regard to claim 19, Greenen discloses
19. The system of claim 18, further comprising:
a style decoder configured to decode the image style features and the text features to obtain a style category (see, detailed description, including, In this example, input indicating a type of content to be represented in a set of content tiles is received 552. This input can be received in or as a number of different forms, such as text, speech, a sample image, or a feature vector, among other such options, para. 0046).
With regard to claim 20, Greenen discloses
20. The system of claim 19, wherein:
the search component selects the design template based on the style category (see, detailed description, including, In this example, input indicating a type of content to be represented in a set of content tiles is received 552. This input can be received in or as a number of different forms, such as text, speech, a sample image, or a feature vector, among other such options, para. 0046).
A sampling of the prior art made of record and not relied upon and considered
pertinent to Applicants’ disclosure includes: U.S. Patent Application No. 20250371762 A1 to Rai et al. that discusses: A method, apparatus, non-transitory computer readable medium, apparatus, and system for generating pattern data include obtaining an input image including a pattern element. Then, embodiments generate a pattern image including the pattern element based on the input image. The pattern image includes a plurality of versions of the pattern element. Subsequently, embodiments generate a pattern caption based on the pattern image. Embodiments then utilize the pattern image and the pattern caption for training an image generation model to generate pattern images based on a text prompt.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to WILLIAM D. TITCOMB whose telephone number is (571)270-5190. The examiner can normally be reached 9:30 AM - 6:30 PM (M-F).
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 C. Hong can be reached at 571-272-4124. 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.
WILLIAM D. TITCOMB
Primary Examiner
Art Unit 2178
/WILLIAM D TITCOMB/Primary Examiner, Art Unit 2178 8-31-2026
Prosecution Insights