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 .
This Office Action is responsive to: Remarks filed 23 Feb. 2026
Claims 1-22 are pending in this case. Claims 1, 13 and 20 are independent claims
Applicant’s Response
In Applicant’s Response dated 23 Feb. 2026, Applicant amended claims 2, 8, 9, 13 and 16; added new claims 21-22. Applicant argued against all rejections previously set forth in the Office Action dated 08 Sep. 2006.
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.
Claims 1, 8, 9, 11-13 and 20 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Muthu et al. (Pub. No.: US 2023/0196813 A1; Filed: Dec. 16, 2021) (hereinafter “Muthu”).
Regarding independent claims 1, 13 and 20, Muthu disclose a method comprising:
identifying one or more portions of a data object that include a table by providing the data object to a table detection model (0050-0051; 0055);
determining a structure of the table by providing the one or more portions of the data object to a table structure recognition model (0050-0051; 0055);
generating a virtual table based on the determined structure of the table, the virtual table including an indication of at least one of one or more rows, one or more columns, or one or more cells corresponding to the table (0006; 0051-0051; 0055; 0064-0071; 0081);
mapping text from the one or more portions of the data object to corresponding cells of the virtual table (0051; 0055; 0069); and
performing a process with the virtual table (0051; 0071; 0081).
Regarding dependent claim 8, Muthu disclose the method of claim 1, wherein providing the one or more portions of the data object to the table structure recognition model comprises:
extracting the one or more portions of the data object from the data object (0050-0051; 0055); and
normalizing the extracted one or more portions of the data object prior to providing the one or more portions to the table structure recognition model (0050-0051; 0055).
Regarding dependent claim 9, Muthu disclose the method of claim 1, wherein determining the structure of the table comprises identifying one or more of a number of rows, a number of columns, a row height, a column width, or indications of merged cells (0066; 0070-0071).
Regarding dependent claim 11, Muthu disclose the method of claim 1, wherein mapping text from the one or more portions of the data object to corresponding cells of the virtual table comprises:
providing the virtual table on the one or more portions of the data object (0051; 0071; 0081); and
mapping text in each cell of the table in the one or more portions of the data object to the corresponding cell of the virtual table (0069; 0071; 0081).
Regarding dependent claim 12, Muthu disclose the method of claim 1, wherein performing a process with the virtual table comprises: providing the virtual table to the process for generating a visual representation of the table (0051; 0071; 0081).
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.
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
Claims 3 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Muthu in view of Xu et al. (Pub. No.: US 2022/0309549 A1; Filed: Feb. 27, 2019) (hereinafter “Xu”).
Regarding dependent claims 3 and 15, Muthu does not expressly disclose the method of claims 2 and 14 respectively, further comprising, before providing the data object to the table detection model:
modifying one or more parameters of the backbone network and the text detection head; and
modifying one or more parameters of the table detection head without modifying the one or more parameters of the backbone network and the text detection head.
Xu teach modifying one or more parameters of the backbone network and the text detection head (0053-0055; 0065-0067; 0076); and
modifying one or more parameters of the table detection head without modifying the one or more parameters of the backbone network and the text detection head (0053-0055; 0065-0067; 0076).
Therefore before the effective filing date of the claim invention, it would have been obvious to one of ordinary skill in the art to combine Xu with Muthu for the benefit of efficiently extracting structured data from documents that are less expensive, less time-consuming, and less error-prone (0003).
Claims 4-7, 10 and 16-19 are rejected under 35 U.S.C. 103 as being unpatentable over Muthu in view of Xu further in view of Carroll (Pub. No.: US 2017/0147552 A1; Filed: Nov. 19, 2015) (hereinafter “Xu”).
Regarding dependent claims 4 and 16, Muthu disclose the method of claims 2 and 14 respectively, wherein identifying the one or more portions of the data object comprises:
generating one or more bounding boxes around text included in the one or more portions of the data object (0011; 0022; 0046-0050); and
Muthu in view of Xu does not expressly disclose providing the one or more bounding boxes to the table structure recognition model.
Carroll teach providing the one or more bounding boxes to the table structure recognition model (0043-0044; 0075-0077; 0080-0081).
Therefore before the effective filing date of the claim invention, it would have been obvious to one of ordinary skill in the art to combine Carroll with Muthu in view of Xu for the benefit predicts the locations of fields of the table, as well as field identities/names/labels for the fields.
Regarding dependent claims 5 and 17, Muthu in view of Xu does not expressly disclose the method of claims 1 and 13 respectively, wherein identifying the one or more portions of the data object comprises:
generating, for one or more pixels of the data object, a likelihood that each pixel of the one or more pixels is part of a table; and
identifying one or more candidate table regions of the data object based on the generated likelihoods.
Carroll teach generating, for one or more pixels of the data object, a likelihood that each pixel of the one or more pixels is part of a table (0108-0111); and
identifying one or more candidate table regions of the data object based on the generated likelihoods (0121-0123).
Therefore before the effective filing date of the claim invention, it would have been obvious to one of ordinary skill in the art to combine Carroll with Muthu in view of Xu for the benefit predicts the locations of fields of the table, as well as field identities/names/labels for the fields.
Regarding dependent claims 6 and 18, Muthu in view of Xu, further in view of Carroll disclose the method of claims 5 and 17 respectively, wherein identifying the one or more portions of the data object comprises:
determining an orientation of one or more lines of text in a respective candidate table region of the one or more candidate table regions (0076; 0081; 0099; 0107);
determining an orientation of the respective candidate table region based on the orientation of one or more lines of text(0076; 0081; 0099; 0107); and
generating a bounding box based on the respective candidate table region and the determined orientation, the bounding box representing an identified portion of the data object (0076; 0081; 0099; 0107).
Regarding dependent claims 7 and 19, Muthu in view of Xu, further in view of Carroll disclose the method of claims 6 and 18 respectively, further comprising:
rejecting the respective candidate table region, in response to a determination that an amount of text in the identified portion of the data object is below a threshold amount of text (0080-0081); and
rejecting the respective candidate table region, in response to a determination that the determined orientation deviates more than a threshold amount from an average orientation of the one or more portions of the data object (0080-0081).
Regarding dependent claim 10, Muthu in view of Xu does not expressly disclose the method of claim 9, wherein the row height and the column width are a percentage of a height and width, respectively, of the one or more portions of the data object.
Carroll teach wherein the row height and the column width are a percentage of a height and width, respectively, of the one or more portions of the data object (0081).
Therefore before the effective filing date of the claim invention, it would have been obvious to one of ordinary skill in the art to combine Carroll with Muthu in view of Xu for the benefit predicts the locations of fields of the table, as well as field identities/names/labels for the fields.
Claims 2, 14, 21 and 22 are rejected under 35 U.S.C. 103 as being unpatentable over Muthu in view of Liao et al. (Pub. No.: US 2021/0366099 A1; Filed: Au. 9, 2021) (hereinafter “Liao”).
Regarding dependent claims 2 and 14, Muthu does not expressly disclose the method of claims 1 and 13 respectively, wherein the table detection model comprises a convolutional neural network comprising a backbone network and multiple network heads including a text detection head and a table detection head.
Liao teach wherein the table detection model comprises a convolutional neural network comprising a backbone network and multiple network heads including a text detection head and a table detection head (0009; 0243; 0390-0391).
Therefore before the effective filing date of the claim invention, it would have been obvious to one of ordinary skill in the art to combine Liao with Muthu for the benefit of generating and utilizing a document template database for automatically extracting document image contents into a contextually structured format.
Regarding dependent claim 21, Muthu does not expressly disclose the method of claim 1, wherein the one or more portions of the data object are preprocessed prior to input to the table structure recognition model.
Liao teach wherein the one or more portions of the data object are preprocessed prior to input to the table structure recognition model (0142; 0318-0319).
Therefore before the effective filing date of the claim invention, it would have been obvious to one of ordinary skill in the art to combine Liao with Muthu for the benefit of generating and utilizing a document template database for automatically extracting document image contents into a contextually structured format.
Regarding dependent claim 22, Muthu does not expressly disclose the method of claim 1, wherein mapping text from the one or more portions of the data object to corresponding cells of the virtual table comprises recreating the virtual table on the one or more portions of the data object and mapping the text in each cell to the corresponding cell of the recreated virtual table (0051; 0055; 0069).
Muthu does not expressly disclose wherein if a bounding box of text overlaps multiple cells of the recreated virtual table, the text is mapped to the cell with which it overlaps the most
Liao teach wherein if a bounding box of text overlaps multiple cells of the recreated virtual table, the text is mapped to the cell with which it overlaps the most (0004; 0007; 0013; 0019; 0286).
Therefore before the effective filing date of the claim invention, it would have been obvious to one of ordinary skill in the art to combine Liao with Muthu for the benefit of generating and utilizing a document template database for automatically extracting document image contents into a contextually structured format.
NOTE
It is noted that any citations to specific, pages, columns, lines, or figures in the prior art references and any interpretation of the reference should not be considered to be limiting in any way. A reference is relevant for all it contains and may be relied upon for all that it would have reasonably suggested to one having ordinary skill in the art. See MPEP 2123.
Response to Arguments
Applicant's arguments filed have been fully considered but they are not persuasive.
Applicant argues none of the cited passages of Muthu discloses “providing the data object to a table detection model nor providing the one or more portions of the data object to a table structure recognition model.
The Examiner disagree.
Muthu disclose (0051) an intelligent model for unstructured nested tabular data extraction. A second component receives output from the first component and an intelligent tabular data extraction (ITDE) algorithm is used to detect and extract tabular data. In addition, the algorithm constructs a virtual table object after locating the table headers, column headers and row headers and uses the same to extract tabular data efficiently (0051). Thus providing the data object to a table detection model providing the one or more portions of the data object to a table structure recognition model. Muthu also disclose an ITDE algorithm incorporates the HIKS technique to identify nested table, row, and column header (as well as sub-header) structures and transform them into ‘flat’ format before extracting the table (0061).
Applicant argues Muthu fails to disclose mapping text from the one or more portions of the data object to corresponding cells of the virtual table (0051; 0055; 0069).
The Examiner disagree.
Muthu disclose the ITDE algorithm generates a virtual table map (a virtual in-memory table object) when locating the headers, row headers, and column headers of the table to be extracted (a virtual table object). The virtual table map is then used during extraction to loop through the columns and rows in the table and extract the values (mapping text from the one or more portions of the data object to corresponding cells of the virtual table) (0069).
Conclusion
THIS ACTION IS MADE FINAL. 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 extension fee 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 JAMES J DEBROW whose telephone number is (571)272-5768. The examiner can normally be reached on 09:00 - 06:00.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, William Bashore can be reached on 571-272-4088. 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 or Private PAIR to authorized users only. Should you have questions about access to Patent Center or 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.
/James J Debrow/
Primary Patent Examiner
Art Unit 2174
571-272-5768
Prosecution Insights