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 .
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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 11 February 2026 has been entered.
Claims 1, 11 and 19 (all of the independent claims) have been amended.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1-20 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
In each of the independent claims, the numeric representation is now required to comprise an “embedding vector generated by inputting the spatial position of the [document features to an ML model]”. This is not apparent from the specification. The concept of an embedding vector shows up in [0063] and [0073], (also noted by Applicant at Remarks p. 7) but that largely relates to an embedding vector of a [corporate] logo and the vector appears to be an output of feeding the image of the logo to an ML model and not inputting the averaged spatial positions from e.g. [0012-0013]. Therefore, it does not appear that the embeddings are later averaged (“average numeric representation”). Where does the specification as filed show that the embeddings of [0063] and [0073] are processed in the manner required by the “generating” step of claim 1?
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.
Claims 1, 4-5, 8-9, 11, 14, and 17-19 as best understood are rejected under 35 U.S.C. 103 as being unpatentable over Sampson et al. (US Pat. No. 8,595,235, hereinafter “Sampson”) in view of Tata et al. (US PG Pub 20210374395, hereinafter “Tata”).
Regarding claim 1, Sampson discloses a system comprising at least one data processor (Col. 3 lines 4-12 and lines 53-55), and at least one memory (Col. 3 lines 10-30, 47, and 54-55) storing instructions which, when executed by the at least one data processor, result in operations comprising determining, based on a received document, a plurality of layout characteristics including a spatial position of one or more document features included in the received document and a numeric representation of the one or more document features included in the received document (Col. 5, lines 21-43, col. 6 lines 21-36, and col. 12, lines 26-52, wherein the location comparison engine contains spatial positions of document features within the received document, and stores spatial positions, which can also be represented numerically by splitting the document image up and obtaining coordinates); generating an aggregated similarity score by at least comparing the plurality of layout characteristics to a first plurality of predefined layout characteristics of a first predefined layout of a plurality of predefined layouts, wherein the first plurality of predefined layout characteristics includes an average spatial position of the one or more document features included in a plurality of sample documents having the first predefined layout and/or an average numeric representation of the one or more document features included in the plurality of sample documents having the first predefined layout (Col. 5, lines 21-43, col. 6 lines 21-36, and col. 12 lines 26-52 regarding the spatial positions and numerical representations; and Col. 8 lines 1-21, wherein step 920 performs a clustering algorithm comparing pluralities of layout characteristics to obtain a “distance”, which is a measure of similarity); identifying a layout of the received document as the first predefined layout of the plurality of predefined layouts based on the aggregated similarity score meeting a threshold score (Col. 8, lines 22-35, wherein the similarity score exceeding a threshold indicates the two document images (and thus, the two documents) belong to the same class); and performing a document processing operation based on the identified layout(Col. 20, lines 23-42, wherein the processing includes classification within different categories and potential template generation).
Specifically, Sampson discloses a method and system of document layout identification and classification using OCR and spatial relations between common document features.
Sampson does not disclose wherein the numeric representation of the one or more document features comprises an image embedding vector generated by inputting the spatial position of the one or more document features to a machine learning model trained to output a numeric representation in a latent space.
However, Tata discloses a method and system of machine learning-based document image analysis wherein a numeric representation of the one or more document features comprises an image embedding vector generated by inputting the spatial position of the one or more document features to a machine learning model trained to output a numeric representation in a latent space (paras. 0021-0022 for extraction of different document features (significant text portions or strings), and determination of features to generate scores for format; and paras. 0109-0115 for the generation of an input feature vector based on spatial positions and distances of the candidate text features within the paper, and the use of a machine learning model to generate scores for the candidate text features for application of a similarity metric to the document). Specifically, Tata discloses a method and system of form text extraction using a machine learning model to determine feature text from different portions of similar documents. Therefore, both Sampson and Tata disclose methods of analyzing documents based on common feature determination and spatial distance and similarity metrics. Thus, it would have been obvious to one having ordinary skill in the art prior to the effective filing date of the claimed invention to have utilized Tata’s disclosure of an image embedding feature vector encoding spatial positions within a machine learning framework within the training and classification modules of the method of Sampson as the application of a known technique to a known device in a similar field of endeavor to yield the predictable result of an improved method of layout determination; specifically, the spatial position embedding and learning method of Tata would enable improved accuracy within calculating similarity scores of the documents of Sampson by evaluating similarity further than simply through word-based clustering.
Claims 11 and 19 are rejected, mutatis mutandis, for reasons similar to claim 1. Sampson further discloses the non-transitory computer-readable medium of claim 19 (Col. 3 lines 10-30, 47, and 54-55) storing instructions which, when executed by the at least one data processor, result in operations comprising the method of claim 11 within the system of claim 1.
Regarding claim 4, Sampson in view of Tata discloses all limitations of claim 1. Sampson further discloses wherein the spatial position includes spatial coordinates (Col. 1, description of fig. 14 for spatial relations; Col. 14 lines 29-42 for determination of spatial coordinates in 2D space, and col. 16 lines 11-38 for measuring bounding boxed area with respect to coordinates for calculating similarity scores within distance values).
Regarding claim 5, Sampson in view of Tata discloses all limitations of claim 1. Sampson further discloses wherein the first plurality of predefined layout characteristics further includes a spatial spread associated with the average spatial position (Col 19 line 9-Col 20 line 10, wherein a matching word finder scorer is used to generate a grid according to a predefined threshold, and wherein the spatial spread applied as a tolerance for detected and compared defined layout characteristics is a distance deviation vector of less than 15 pixels @ 300 dpi).
Regarding claim 8, Sampson in view of Tata discloses all limitations of claim 1. Sampson further discloses wherein the average spatial position of the first plurality of predefined layout characteristics is generated by at least extracting, from the plurality of sample documents, the one or more document features (Col. 5, lines 21-43, col. 6 lines 21-36, and col. 12, lines 26-52, wherein the location comparison engine contains spatial positions of document features within the received document, and stores spatial positions, which can also be represented numerically by splitting the document image up and obtaining coordinates, both of which are identified as predefined layout characteristics); determining a spatial position of the one or more extracted document features in each of the plurality of sample documents (Col. 8 lines 1-21, col. 12 lines 26-52); and averaging the spatial position of the one or more extracted document features in each of the plurality of sample documents (Col. 21 lines 30-41, wherein the bounding box around the word (the feature, which returns the centroid or coordinates as the spatial position) is the result of an averaging of spatial positions depending on the word’s determined bounds).
Regarding claim 9, Sampson in view of Tata discloses all limitations of claim 1. Sampson further discloses wherein the aggregated similarity score is further generated by at least comparing, prior to comparing the plurality of layout characteristics to the first plurality of predefined layout characteristics, the plurality of layout characteristics to a second plurality of predefined layout characteristics of a second predefined layout of the plurality of predefined layouts, wherein the second plurality of predefined layout characteristics includes an average spatial position of the one or more document features included in a plurality of
Regarding claim 14, Sampson in view of Tata discloses all limitations of claim 11. Sampson further discloses wherein the first plurality of predefined layout characteristics further includes a spatial spread associated with the average spatial position (Col 19 line 9-Col 20 line 10, wherein a matching word finder scorer is used to generate a grid according to a predefined threshold, and wherein the spatial spread applied as a tolerance for detected and compared defined layout characteristics is a distance deviation vector of less than 15 pixels @ 300 dpi).
Regarding claim 17, Sampson in view of Tata discloses all limitations of claim 11. Sampson further discloses wherein the average spatial position of the first plurality of predefined layout characteristics is generated by at least extracting, from the plurality of sample documents, the one or more document features (Col. 5, lines 21-43, col. 6 lines 21-36, and col. 12, lines 26-52, wherein the location comparison engine contains spatial positions of document features within the received document, and stores spatial positions, which can also be represented numerically by splitting the document image up and obtaining coordinates, both of which are identified as predefined layout characteristics); determining a spatial position of the one or more extracted document features in each of the plurality of sample documents (Col. 8 lines 1-21, col. 12 lines 26-52); and averaging the spatial position of the one or more extracted document features in each of the plurality of sample documents (Col. 21 lines 30-41, wherein the bounding box around the word (the feature, which returns the centroid or coordinates as the spatial position) is the result of an averaging of spatial positions depending on the word’s determined bounds).
Regarding claim 18, Sampson in view of Tata discloses all limitations of claim 11. Sampson further discloses wherein the aggregated similarity score is further generated by at least comparing, prior to comparing the plurality of layout characteristics to the first plurality of predefined layout characteristics, the plurality of layout characteristics to a second plurality of predefined layout characteristics of a second predefined layout of the plurality of predefined layouts, wherein the second plurality of predefined layout characteristics includes an average spatial position of the one or more document features included in a plurality of sample documents having the second predefined layout and/or an average numeric representation of the one or more document features included in the plurality of sample documents having the second predefined layout, and wherein the second predefined layout has a lower execution priority than the first predefined layout (Col. 8 line 36 – Col 10 line 54, and figs. 9 and 10, wherein the comparison between layout characteristics of a subject document and at least a first and a second predefined set of layout characteristics consists of a combined similarity score distance comparison between document classes using a clustering algorithm. Within this algorithm, the first class generated (cluster) has a higher priority, with each subsequently added class decreasing in priority, with the comparison process being described in steps 920, 1010, 1015, 1020, 1025, 1030, 1035, 1040, 1045, 1050, 1055, 1060, 1065, and 1070).
Claims 2-3, 12-13, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Sampson in view of Tata and in further view of Singh Bawa et al. (US PG Pub 20220237373, hereinafter “Singh Bawa”).
Regarding claim 2, Sampson in view of Tata discloses all limitations of claim 1. The combination of Sampson and Tata does not disclose wherein the one or more document features includes a spatial position of the document header field and a spatial position of the table header field, and wherein the numeric representation includes a numeric representation of the logo.
However, Singh Bawa discloses wherein the one or more document features includes a spatial position of the document header field (para. 0079, specifically where the pixel layout features determined for the document include the location of the centroid of the document header) and a spatial position of the table header field (para. 0079 discloses obtaining centroid positions of headers, and para. 0087 discloses calculating positions of table elements), and wherein the numeric representation includes a numeric representation of the logo (paras. 0038-0039, wherein the logos are non-word elements whose locations are stored numerical pixel features, as specified in 0038, and whose centroids are also used as numerical features according to 0039). Specifically, Singh Bawa discloses a method of automated document summarization and categorization based on machine learning processing of input documents into predetermined categories based on observed document content. As a result, Sampson in view of Tata and Singh Bawa disclose methods for extracting document features, specifically tending towards automated categorization of document features. Thus, it would have been obvious for one having ordinary skill in the art prior to the effective filing date of the claimed invention to combine the specific document features and feature identification methods of Singh Bawa within the general document similarity and categorization method of Sampson in view of Tata as a simple substitution of the specific header, table header, and logo locations as specific spatial characteristics disclosed by Singh Bawa in the place of the general word-position-based spatial characteristic identification disclosed by Sampson in view of Tata.
Regarding claim 3, Sampson in view of Tata in further view of Singh Bawa discloses all limitations of claim 2. Sampson further discloses wherein the one or more document features further includes vendor information, and wherein the plurality of layout characteristics further includes an identifier associated with the vendor information (Col. 6 lines 21-36). Specifically, Sampson in view of Tata discloses extraction of words and numerical information, of which vendor information is a particular type or set of words and/or numbers.
Regarding claim 12, Sampson in view of Tata discloses all limitations of claim 11. The combination of Sampson and Tata does not disclose wherein the one or more document features includes a spatial position of the document header field and a spatial position of the table header field, and wherein the numeric representation includes a numeric representation of the logo.
However, Singh Bawa discloses wherein the one or more document features includes a spatial position of the document header field (para. 0079, specifically where the pixel layout features determined for the document include the location of the centroid of the document header) and a spatial position of the table header field (para. 0079 discloses obtaining centroid positions of headers, and para. 0087 discloses calculating positions of table elements), and wherein the numeric representation includes a numeric representation of the logo (paras. 0038-0039, wherein the logos are non-word elements whose locations are stored numerical pixel features, as specified in 0038, and whose centroids are also used as numerical features according to 0039). Thus, it would have been obvious for one having ordinary skill in the art prior to the effective filing date of the claimed invention to combine the disclosures of Sampson in view of Tata and Singh Bawa according to the rationale of claim 2.
Regarding claim 13, Sampson in view of Tata and in further view of Singh Bawa disclose all limitations of claim 12. Sampson further discloses wherein the one or more document features further includes vendor information, and wherein the plurality of layout characteristics further includes an identifier associated with the vendor information (Col. 6 lines 21-36). Specifically, Sampson discloses extraction of words and numerical information, of which vendor information is a particular type or set of words and/or numbers.
Regarding claim 20, Sampson in view of Tata discloses all limitations of claim 19. The combination of Sampson and Tata does not disclose wherein the one or more document features includes a spatial position of the document header field and a spatial position of the table header field, and wherein the numeric representation includes a numeric representation of the logo.
However, Singh Bawa discloses wherein the one or more document features includes a spatial position of the document header field (para. 0079, specifically where the pixel layout features determined for the document include the location of the centroid of the document header) and a spatial position of the table header field (para. 0079 discloses obtaining centroid positions of headers, and para. 0087 discloses calculating positions of table elements), and wherein the numeric representation includes a numeric representation of the logo (paras. 0038-0039, wherein the logos are non-word elements whose locations are stored numerical pixel features, as specified in 0038, and whose centroids are also used as numerical features according to 0039). Thus, it would have been obvious for one having ordinary skill in the art prior to the effective filing date of the claimed invention to combine the disclosures of Sampson in view of Tata and Singh Bawa according to the rationale of claim 1.
Claims 6-7 and 15-16 are rejected under 35 U.S.C. 103 as being unpatentable over Sampson in view of Tata and in further view of Downs et al. (US PG Pub 20210256216, hereinafter “Downs”).
Regarding claim 6, Sampson in view of Tata discloses all limitations of claim 1. The combination of Sampson and Tata does not disclose wherein the aggregated similarity score meets the threshold score when the aggregated similarity score is less than the threshold score.
However, Downs discloses wherein the aggregated similarity score meets the threshold score when the aggregated similarity score is less than the threshold score (para. 0075, wherein the semantic match step 1012 and the threshold value step 1014 are considered to be met, and the document in question is similar, if the combined/aggregate similarity score calculated between two documents is equal to or less than a predetermined threshold value). Specifically, Downs discloses a method of creating electronic document templates given a plurality of instances of common document content (wherein multiple similar elements necessitate creation of a common form). Therefore, Sampson and Tata and Downs disclose methods of document feature extraction and comparison for calculation of a similarity score and subsequent form categorization. Thus, it would have been obvious to one having ordinary skill in the art prior to the effective filing date of the claimed invention to utilize the combination of similarity scores and the distance and thresholding metric of Downs within the similarity score comparison calculation of Sampson in view of Tata as a simple substitution of Sampson’s known method of exceeding a similarity threshold for Downs’ known vector distance minimization method between form elements which would yield the predictable result of an intuitive optimization method for form comparison and classification.
Regarding claim 7, Sampson in view of Tata discloses all limitations of claim 1 The combination of Sampson and Tata does not disclose wherein the aggregated similarity score is further generated by at least: generating a similarity score for each of the plurality of layout characteristics; and aggregating the similarity score generated for each of the plurality of layout characteristics.
However, Downs discloses wherein the aggregated similarity score is further generated by at least: generating a similarity score for each of the plurality of layout characteristics (para. 0074, specifically “individual similarity scores” being the scores for each of the plurality of layout characteristics); and aggregating the similarity score generated for each of the plurality of layout characteristics (para. 0074-0075, wherein the combined score is any one of the sums of the individual scores, the square root of the sums of the squares of individual scores, or other embodiments of combination). Thus, it would have been obvious to one having ordinary skill in the art prior to the effective filing date of the claimed invention to combine the disclosures of Sampson in view of Tata and Downs according to the rationale of claim 6.
Regarding claim 15, Sampson in view of Tata discloses all limitations of claim 11. The combination of Sampson and Tata does not disclose wherein the aggregated similarity score meets the threshold score when the aggregated similarity score is less than the threshold score.
However, Downs discloses wherein the aggregated similarity score meets the threshold score when the aggregated similarity score is less than the threshold score (para. 0075, wherein the semantic match step 1012 and the threshold value step 1014 are considered to be met, and the document in question is similar, if the combined/aggregate similarity score calculated between two documents is equal to or less than a predetermined threshold value). Thus, it would have been obvious to one having ordinary skill in the art prior to the effective filing date of the claimed invention to combine the disclosures of Sampson in view of Tata and Downs according to the rationale of claim 6.
Regarding claim 16, Sampson in view of Tata discloses all limitations of claim 1. The combination of Sampson and Tata does not disclose wherein the aggregated similarity score is further generated by at least: generating a similarity score for each of the plurality of layout characteristics; and aggregating the similarity score generated for each of the plurality of layout characteristics.
However, Downs discloses wherein the aggregated similarity score is further generated by at least: generating a similarity score for each of the plurality of layout characteristics (para. 0074, specifically “individual similarity scores” being the scores for each of the plurality of layout characteristics); and aggregating the similarity score generated for each of the plurality of layout characteristics (para. 0074-0075, wherein the combined score is any one of the sums of the individual scores, the square root of the sums of the squares of individual scores, or other embodiments of combination). Thus, it would have been obvious to one having ordinary skill in the art prior to the effective filing date of the claimed invention to combine the disclosures of Sampson in view of Tata and Downs according to the rationale of claim 6.
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Sampson in view of Tata and in further view of Torres et al. (US PG Pub 20210073532, hereinafter “Torres”).
Regarding claim 10, Sampson in view of Tata discloses all limitations of claim 1. The combination of Sampson and Tata does not disclose wherein the document processing operation includes at least one of applying a dedicated extraction model to the received document based on the identified layout, applying correction logic to the received document based on the identified layout to correct a value extracted from the received document, and applying a custom extraction model based on the identified layout.
However, Torres discloses wherein the document processing operation includes applying a dedicated extraction model to the received document based on the identified layout (paras. 0022-0025, wherein the extraction model itself may be used for extracting particular class attributes, learning class attributes based on extracted features for classification or data entry purposes, or generate confidence features). Specifically, Torres discloses a document extraction system executed by a processor which uses automated routing if a high likelihood of accurate automated extraction and feature processing is possible. Therefore, both Sampson in view of Tata and Torres disclose automated methods of document feature extraction and processing. Thus, it would have been obvious to one having ordinary skill in the art prior to the effective filing date of the claimed invention to have applied the dedicated extraction model of Torres to the system and method of Sampson as modified by Tata as the application of the known model of Sampson to the known system and method of Sampson in view of Tata in order to obtain the predictable result of easier automated document classification and increasingly efficient data and feature extraction from similar forms for storage and processing.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ROHAN TEJAS MUKUNDHAN whose telephone number is (571)272-2368. The examiner can normally be reached Monday - Friday 9AM - 6PM.
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, Gregory Morse can be reached at 5712723838. 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.
/ROHAN TEJAS MUKUNDHAN/Examiner, Art Unit 2663
/GREGORY A MORSE/Supervisory Patent Examiner, Art Unit 2698