DETAILED ACTION
This action is responsive to the filing of 3/4/25. Claims 1-12 are pending and have been considered below.
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 .
Allowable Subject Matter
Claims 5-6 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.
The following is an examiner's statement of reasons for allowance. The prior art of record fails to disclose selecting candidate paragraphs adjacent to a target paragraph, and pairing candidate paragraph with a target paragraph and choosing the best fit, in combination with other limitations recited within the claimed context. The claims present a combination of limitations that differ from the cited art, and there is no reasonable combination of references that would teach it.
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) 1-3, 7-12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Maderlechner (DE 102006025928A1) in view of Landes (2021/0263971) and in further view of Flake (9,430,583.)
Claim 1, 11-12: Maderlechner discloses a computer-implemented method for converting PDF documents into human readable and machine parsable HTML code comprising the steps of:
extracting texts (par. 41, related text blocks are extracted from the document);
extracting formatting styles (par. 48, the font size, font style (i.e. normal, bold or italic) and font type (i.e. the typeface used) are taken into account);
extracting background graphs (par. 33, all images extracted from the PDF document are stored);
extracting positional info (par. 34, not only the image itself but also the sizes and positions of the images);
extracting font family information (par. 48, During the text attribute evaluation in step S5, the font size, font style (i.e. normal, bold or italic) and font type (i.e. the typeface used) are taken into account);
annotating of html code (par. 36, positions are specified by the code "left:89;top:71"; par. 50, image dimensions);
organizing reading order (par. 29, any PDF document is processed and converted into an HTML document, which essentially has the same layout as the original PDF document); and
including metadata (par. 36, positions are specified by the code "left:89;top:71"; par. 50, image dimensions);
organizing of the reading order is determined based on a combination of:
innate reading order (par. 41, the size of the individual text blocks is specified by the longest line extending from left to right in the text block of the original PDF document);
region delineation by a segmentation algorithm (par. 40, reference is made to publications [1], [2] and [3], which describe the layout segmentation of documents in detail; par. 41, related text blocks are extracted from the document.); and
paragraph sequencing (Fig. 4, large number of text blocks T1, T2, T3, T4, T5, T6, T7 and T8);
However, Maderlechner does not explicitly disclose:
characterized in that, a machine learning algorithm is used to automatically annotate HTML code, which machine learning algorithm is trained with a set of manually annotated HTML code examples, the extracted font family information is True Type Fonts compatible;
text within a paragraph is annotated with <span></span> tags.
Landes discloses a similar method for a machine learning model, including:
characterized in that, a machine learning algorithm is used to automatically annotate HTML code, which machine learning algorithm is trained with a set of manually annotated HTML code examples, the extracted font family information is True Type Fonts compatible (par. 79, the annotated dataset may then be used to train a machine learning model, where the result of the training is a machine learned model. In one example, the machine learning model is a machine learning network and the machine learned model is a machine learned network; par. 77, In computer text processing examples, the annotator 168 may use a markup language to perform the annotating. Markup languages, like XML and HTML, annotate text in a way that is syntactically distinguishable from that text. Markup languages can be used to add information about the desired visual presentation, or machine-readable semantic information, as in the semantic web.)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to combine the teachings of Maderlechner with that of Landes so as to automate a potentially complex, and time consuming task by using AI to save time.
Flake discloses a similar method for stylizing text within a paragraph, including:
text within a paragraph is annotated with <span></span> tags (Fig. 4: 422; Table A, 5:40-6:25.)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to combine the teachings of Maderlechner with that of Flake based on a suggestion for stylizing text in par. 18 and 48 of Maderlechner.
Claim 2: Maderlechner Landes and Flake disclose the method according to claim 1, characterized in that, each paragraph is annotated such that it is contained between <div></div> tags (Flake Fig. 10: 1000 div.)
Claim 3: Maderlechner Landes and Flake disclose the method according to claim 1 to claim 2, characterized in that, tables are annotated with <tr></tr> only for rows and <td></td> only for table cells (Flake, Table B1, using <tr> and <td>.)
Claim 7: Maderlechner Landes and Flake disclose the method according to claim 1, characterized in that, the metadata included in a converted file includes tables, graphs, headings, page headers and footers (Maderlechner HTML markup itself functions as metadata as it tells the browser about the data and how to display it, such as locations, style and font, par. 48.)
Claim 8: Maderlechner Landes and Flake disclose the method according to claim 1, characterized in that, tables and graphs are detected by means of an object recognition algorithm (Maderlechner par. 31, identifying objects, such as images in the pdf format.)
Claim 9: Maderlechner Landes and Flake disclose the method according to claim 1, characterized in that, headings are identified based of differences in font styles between headings and regular text (Flake par. 49, the font distribution shows that the font of block T14 is significantly smaller than the other fonts on this page. From this, it is inferred that T14 is the image caption.)
Claim 10: Maderlechner Landes and Flake disclose the method according to claim 1, characterized in that, page headers and footers are identified based on text and text location similarity (Flake par. 49, the font distribution shows that the font of block T14 is significantly smaller than the other fonts on this page. From this, it is inferred that T14 is the image caption; par. 13, a caption for an image by the geometric arrangement of the text blocks to the images, in particular by the overlap of the text blocks with the images.)
Claim(s) 4 is/are rejected under 35 U.S.C. 103 as being unpatentable over
Maderlechner (DE 102006025928A1) in view of Landes (2021/0263971) in view of Flake (9,430,583) and in further view of Xu (2023/0222631.)
Claim 4: Maderlechner Landes and Flake disclose the method according to claim 1. However, Maderlechner does not disclose the segmentation algorithm is a U-Net algorithm.
Xu discloses a similar method for text and image processing, including: the segmentation algorithm is a U-Net algorithm (par. 67, Claim 10, wherein the image segmentation model is a pre-trained U-Net model for segmenting the input image.)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to combine the teachings of Maderlechner with that of Xu because the U-Net network model is a model with better performance for image segmentation (Xu par. 67.)
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ANDREY BELOUSOV whose telephone number is (571) 270-1695 and Andrew.belousov@uspto.gov email. The examiner can normally be reached Mon-Friday EST.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Adam Queler, can be reached at telephone number 571-272-4140. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from Patent Center and the Private Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from Patent Center or Private PAIR. Status information for unpublished applications is available through Patent Center and Private PAIR for authorized users only. Should you have questions about access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
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) Form at https://www.uspto.gov/patents/uspto-automated- interview-request-air-form.
/Andrey Belousov/
Primary Examiner
Art Unit 2172
6/22/26
Prosecution Insights