DETAILED ACTION
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 7 July 2026 has been entered. Claims 1-20 have been examined and are pending.
Pertinent Prior Art
Prior art that is considered pertinent to applicant's disclosure but not currently relied upon:
20210294851
Pars. 42-48
Document segmentation using machine learning
20190087444
Pars. 35-39
Feature based document page image comparisons to determine similarities
20240289356
Pars. 59, 75-86, 89
Detecting scanned document subsections using feature extraction and object detection
20220237230
Pars.51, 110
Similarity based sub-document determination
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.
Claims 1, 2, 5, 8, 9, 12, 15, 16 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Uppal et al., Pub. No.: US 20210019512 A1, hereinafter Uppal in view of V. Balannik, Pub. No.: US 20230260284 A1, hereinafter Balannik.
As per claim 1, Uppal discloses a computer-based method of decomposing composite scanned documents, the method comprising:
detecting a target composite scanned document, wherein the target composite scanned document is a single digital file comprising sequential pages produced by scanning and digitally merging multiple documents (pars. 3, 4, 18 disclose a composite file with a stream of pages produced by scanning and storing different documents and par. 42 discloses receiving the composite file);
extracting, from the sequential pages of the target composite scanned document, a series of document features (pars. 24, 25, 43, 44 disclose using image processing, text processing, OCR techniques to extract image and text features from each page of the composite file as it is split into individual sequential pages);
iteratively generating a series of sub-documents, wherein each sub-document is generated by iteratively adding a next page from the sequential pages of the target composite scanned document to a series of the sequential pages preceding the added next page (par. 26 discloses iteratively feeding consecutive pages in to the DNN across all pages of the composite file, progressively identifying page groupings such that pages 1-3 belong to a first document, pages 4-5 belong to a second one and so on; par. 47 discloses that steps 314-320 are repeated for all individual pages of the compositive file);
generating a vector representation for each sub-document of the iteratively generated series of sub-documents based on a set of the extracted series of document features corresponding to the respective sub-document (see rejection above including pars. 39-40);
calculating similarity scores for the sub-documents by comparing the generated vector representations with a knowledgebase of document vectors (pars. 23, 32 disclose document repo 202 has labeled training documents of different types constituting a knowledgebase of document vectors; par. 32 discloses that the DNN learns the best feature representations from the training data which are then compared with consecutive pages to identify whether they belong to the same document (i.e. calculating similarity score); pars. 40, 47 disclose studying the continuity pattern across the document vector to determine whether pages belong to the same or different documents) corresponding to historical documents from an associated domain (pars. 23, 32 disclose past or stored (i.e. historical) document types stored in document repo 202, wherein types and subtypes correspond to domains) ;
clustering the sequential pages of the target composite scanned document based on the calculated similarity scores (pars. 47-48 disclose identifying pages belonging to the same documents based on the continuity pattern determination and merging the pages belonging to the same documents to form grouped page clusters). Uppal does not disclose however Balannik, in the related field of endeavor of data analysis, discloses wherein the clustering comprises generating a new cluster in response to identifying a page from the sequential pages corresponding to a local maximum in a plot of the calculated similarity scores (Balannik claim 4, pars. 91, 92, 96 disclose computing similarity scores sequential portions of ordered content and clustering the sequential content based on the scores, a dataset is defined in which sequential positions are mapped to the similarity scores, identifying local maximum values in the dataset and clustering the sequential content according to each local maximum value. Note that Balannik par. 96 makes it clear that the clustering is based on points in a space with distances (i.e. plot)). Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of the cited references because Balannik would have allowed Uppal to provide a way to efficiently convert sequential similarity scores into clusters of related sequential content; and
outputting separate files, respectively including a set of the clustered sequential pages (Uppal pars. 27, 48-49 disclose merging clustered pages to form separate individual documents for output (specific sequential pages for invoices, receipts, etc.)).
As per claim 2, Uppal as modified discloses The computer-based method of claim 1, wherein the extracted series of document features comprises one or more of page structure features, page textual features, and page layout features (pars. 25, 37, 38, 44).
As per claim 5, Uppal as modified discloses the computer-based method of claim 2, wherein the target composite scanned document has been scanned using optical character recognition, and the page textual features are extracted using natural language processing techniques (pars. 25, 37, 38, 44).
As per claims 8, 9, 12, 15, 16 and 19, they are analogous to claims above and therefore likewise rejected.
Claims 3, 4, 10, 11, 17 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Uppal as modified and further in view of Foster et al., Pub. No.: US 20060155725 A1, hereinafter Foster.
As per claim 3, Uppal as modified discloses The computer-based method of claim 1. Uppal as modified does not expressly disclose however Foster in the related field of endeavor of document analysis discloses the clustering further comprising: identifying a plurality of anchor pages corresponding to local maxima in the plot of the calculated similarity scores (Foster fig.’s 44-46, pars. 422, 475-476). Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of the cited references because Foster would have allowed Uppal as modified to generate a plot of similarity scores in a multidimensional similarity space because this helps explain how closely documents match one another (Foster, par. 364).
As per claim 4, Uppal as modified discloses the computer-based method of claim 3, wherein the clustering further comprises: generating an additional cluster following each respective one of the identified anchor pages (see Uppal as cite din the rejection of claim 1 including pars. 47-48 and Foster as cited in the rejection of claim 3).
As per claims 10, 11, 17 and 18, they are analogous to claims above and therefore likewise rejected.
Claims 6, 13 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Uppal as modified and further in view of Zeng et al., Pub. No.: US 20210374397, hereinafter Zeng.
As per claim 6, Uppal as modified discloses the computer-based method of claim 2. Uppal as modified does not expressly disclose however Zeng in the related field of endeavor of document analysis discloses wherein the page layout features are encoded into concatenated vectors using text-to-vector models (Zeng pars. 46-59, 145). Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of the cited references because Zeng would have allowed the combination to improve the accuracy of document layout analysis based on the character information, semantic information, and spatial location information (Zeng, par. 51 and see Uppal, pars. 38-39).
Analogous claims 13 and 20 are likewise rejected.
Claims 7 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Uppal as modified and further in view of Sato, Pub. No.: US 20160366299 A1, hereinafter Sato.
As per claim 7, Uppal as modified discloses the computer-based method of claim 2. Uppal as modified does not expressly disclose however Sato in the related field of endeavor of document analysis discloses wherein the extracted series of document features further include fonts used (Sato par. 25). Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of the cited references because Sato would have allowed Uppal as modified to “OCR server 104 may be configured or programmed to receive documents and perform OCR functions on the documents to create OCR text data. For example, a matrix matching algorithm may be used to compare pixels in the image data with pixels of letters in various fonts stored in a data structure on OCR server 104. Alternatively, or additionally, a feature extraction algorithm may be used to compare features in the image data with features of characters in various fonts stored in the data structure on OCR server 104” (Sato par. 25). Claim 14 is likewise rejected.
Response to Arguments
Applicant's arguments filed 3/13/2026 have been considered. With respect to the prior art rejection, Balannik, Pub. No.: US 20230260284, has been applied in response to claim amendments.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SYED HASAN whose telephone number is (571)270-5008. The examiner can normally be reached M-F 8am - 5 pm.
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, Boris Gorney can be reached at (571)270-5626. 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.
/SYED H HASAN/Primary Examiner, Art Unit 2154
Prosecution Insights