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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 04/25/2025 has been considered by the examiner.
Status of Claims
Claims 1-20 are pending in this application.
Positive Statement regarding 35 U.S.C. 101: Claims 1-19 are determined to be eligible under 35 U.S.C. 101. The claim 1, for example, at lines 2-4 recites "performing optical character recognition on a document to define spatial locations of bounding boxes for characters, wherein each bounding box includes at least one character.". It is given the weight of the description in the specification paragraph [0075] that performing optical character recognition on a document is not simply recognizing characters on a document but is directed to a specific image processing technique, including preforming OCR on a document. Paragraph [0075] "one or more computer vision driven techniques to extract information on a relatively complex layout scanned document in a non-searchable format such as, for example, a non-searchable Portable Document Format (PDF) (e.g., standardized as ISO 32000). In such an example, the PDF document can include raster graphics. For example, consider raster graphics represented as a two-dimensional picture in a rectangular matrix or grid of square pixels. A raster graphic may be characterized by width and height of an image in pixels and by number of bits per pixel. A raster graphic may be referred to as a raster image or a bitmap graphic or a bitmap image. As mentioned, such an image within a document may include text within the image where such text is not present in a searchable form. For example, to make the text searchable, an optical character recognition (OCR) technique may be applied that can recognize characters in an image and covert those characters to text, which may be stored to memory.". Therefore, it seems that the "performing optical character recognition on a document to define spatial locations of bounding boxes for characters, wherein each bounding box includes at least one character." in combination with other limitation/features in the claim, claim as a whole, makes it eligible under 35 USC 101.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claim 20 is rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. The claim(s) does/do not fall within at least one of the four categories of patent eligible subject matter because they cover both statutory and non-statutory embodiments (under the broadest reasonable interpretation of the claim when read in light of the specification and in view of one skilled in the art) and embraces subject matter that is not eligible for patent protection and therefore is directed to non-statutory subject matter.
Claim 20 line 1 recites “One or more computer-readable storage media…”. The claim does not fall within at least one of the four categories of patent eligible subject matter because the claim is directed to a signal per se. Although the specification states “As an example, a computer-readable medium (CRM) may be a computer-readable storage medium that is non-transitory and that is not a carrier wave.” (Paragraph [0122]) the language is non-assertive. Therefore, the claim language needs to be modified to state that the storage media is non-transitory.
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, 3-6, 8-13, 14-15, and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Davis et al. (US 2018/0276462 A1) (hereinafter; “Davis”) in view of Bellert (US 2019/0102619 A1).
Regarding claim 1, Davis discloses a method comprising: performing optical character recognition on a document (electronic document in Paragraph [0060] equates to a document) to define spatial locations of bounding boxes for characters, wherein each bounding box includes at least one character (text item in Paragraph [0060] equates to at least one character) (Paragraph [0060] “Method 200 may continue at step 204, which includes OCR'ing the electronic document (which may or may not be preprocessed as described). For example, in some aspects, the Tesseract OCR may be used to produce a hypertext markup language (html) representation of the page text (e.g., from the image in FIG. 3). From the html data, information about every text item's bounding rectangle may be parsed/saved in a JSON format (e.g., similar to the output of Google Vision).”);
identifying a spatial location of keyword characters via a corresponding one of the bounding boxes (Paragraph [0060] “From the html data, information about every text item's bounding rectangle may be parsed/saved in a JSON format (e.g., similar to the output of Google Vision).”; Paragraph [0071] “With the text value bins identified for every row, the result is a set of bounding rectangles for every text value on the page image. These text bounding rectangles are organized by row, and assigned a logical identification (ID) that is a concatenation of row index (starting with 0 at the top) and value index (starting at 0 from left to right).”; The examiner interprets the concatenated row index and value to be the spatial location of keyword characters via a bounding box);
[applying an edge detection technique to generate a skeletonized version of the document;
determining borders within the skeletonized version of the document to define regions]; and
extracting the characters within one of the regions that includes the keyword characters (Paragraph [0081] “Method 200 may continue at step 212, which includes extracting data from the detected one or more tables”; Paragraph [0083] “a cell value parser iterates through the table cells, checking the OCR output for text bounding boxes that fall inside the cell region. When an OCR text value is found to lie inside the table cell region, the text value is added to the table cell dictionary and removed from the OCR dictionary.”; Paragraph [0087] “The text for the column label rows may then be extracted using a similar methodology to the table extraction; bounding whitespace regions are identified as the text column boundaries, and the OCR text is then sorted by column. The sorted text is then associated with the table columns based on the amount of overlap in the horizontal extents of the table column region and the column label region. Once the column label text is associated with the data columns, the text is added to the table object (which stores the relative position information of all the parsed OCR text).”).
However, Davis fails to teach applying an edge detection technique to generate a skeletonized version of the document; and determining borders within the skeletonized version of the document to define regions.
Bellert teaches applying an edge detection technique to generate a skeletonized version of the document (image including a table in Paragraph [0052] equates to the document) (Paragraph [0031] “the skeleton engine (108) generates a skeleton graph for all identified connected components. Alternatively, the skeleton engine (108) generates the skeleton graph only for the largest connected component (i.e., the connected component with the largest number of pixels)”; Paragraph [0033] “a skeleton graph includes a series of edges and vertices. Each edge may correspond to a stroke, or a portion of a stroke, of the table. Each vertex may correspond to an intersection of two or more edges. Further, an edge may contain a path of pixels from one end of the stroke to the other end of the stroke, located approximately at the center of the stroke. The width of a path is one or more pixels.”; Paragraph [0052] “Initially, an image including a table is obtained (STEP 205). The image may be obtained (e.g., downloaded, scanned, etc.) from any source and may be of any size or format.”); and determining borders (edges that make up the cell in Paragraph [0041] equate to the boarders) within the skeletonized version of the document to define regions (cells in Paragraph [0041] equate to regions) (Paragraph [0041] “the table engine (110) executes a table cell detection method to identify one or more cells that make up the table. Initially candidate cells are identified from the skeleton graph. The candidate cells are composed of edges and vertices. Then one or more validation processes are executed on each candidate cell to confirm the candidate cell is actually a cell of the table. In one or more embodiments, the table engine (110) stores the validated cells in a validated cells data structure (e.g., array, list).”).
Therefore, it would have been obvious to one of ordinary skill of the art before the effective filing date to modify Davis’s reference to include applying an edge detection technique to generate a skeletonized version of the document; and determining borders within the skeletonized version of the document to define regions taught by Bellert’s reference. The motivation for doing so would have been to generate a high-level representation of the table for inclusion in the electronic document as suggested by Bellert (see Bellert, Paragraph [0039]).
Further, one skilled in the art could have combined the elements described above by known methods with no change to the respective functions, and the combination would have yielded nothing more than predictable results. Therefore, it would have been obvious to combine Bellert with Davis to obtain the invention specified in claim 1.
Regarding claim 3, which claim 1 is incorporated, Davis discloses wherein the characters within the one of the regions comprise characters of a table (Paragraph [0081] “Method 200 may continue at step 212, which includes extracting data from the detected one or more tables.”; Paragraph [0087] “The text for the column label rows may then be extracted using a similar methodology to the table extraction; bounding whitespace regions are identified as the text column boundaries, and the OCR text is then sorted by column. The sorted text is then associated with the table columns based on the amount of overlap in the horizontal extents of the table column region and the column label region. Once the column label text is associated with the data columns, the text is added to the table object (which stores the relative position information of all the parsed OCR text).”; Examiner interprets the extracted text from the table to be the characters of a table).
Regarding claim 4, which claim 1 is incorporated, Davis discloses wherein the keyword characters comprise characters of a table heading (Paragraph [0086] “For electronic documents that are directional surveys, for example, there may be a small number of keywords used to label the columns. Starting at the top of the table region, fuzzy matching (e.g., the Monge-Elkan algorithm for comparing lists of words to one another) may identify the text rows above the table region that represent the table columns. The fuzzy matching process may be used to score rows around the top of the data table region; the high-scoring row is used as the primary column label row. The text rows starting at the high-scoring text row to the text row directly above the table region may be assumed to be the table column labels.”; Figure 5).
Regarding claim 5, which claim 1 is incorporated, Davis discloses wherein the regions comprise at least two table regions (Paragraph [0072] “Method 200 may continue at step 210, which includes detecting one or more tables within the electronic document.”).
Regarding claim 6, which claim 1 is incorporated, Davis discloses generating a data structure for the spatial locations of the bounding boxes for the characters (Paragraph [0060] “From the html data, information about every text item's bounding rectangle may be parsed/saved in a JSON format (e.g., similar to the output of Google Vision).”; Paragraph [0071] “With the text value bins identified for every row, the result is a set of bounding rectangles for every text value on the page image. These text bounding rectangles are organized by row, and assigned a logical identification (ID) that is a concatenation of row index (starting with 0 at the top) and value index (starting at 0 from left to right).”).
Regarding claim 8, which claim 1 is incorporated, Davis fails to teach wherein determining borders comprises implementing an edge enhancement technique.
Bellert teaches wherein determining borders comprises implementing an edge enhancement technique (Paragraph [0039] “The table engine (110) determines portions of the table that can be repaired through the addition of artificial edges based on the edges and vertices of the skeleton graph. For example, an artificial edge can be built between two positions (e.g., pixels) on the skeleton graph to establish a near linear connection, a near perpendicular connection, or a corner connection.”).
Therefore, it would have been obvious to one of ordinary skill of the art before the effective filing date to modify Davis’s reference to include wherein determining borders comprises implementing an edge enhancement technique taught by Bellert’s reference. The motivation for doing so would have been to generate a high-level representation of the table for inclusion in the electronic document as suggested by Bellert (see Bellert, Paragraph [0039]).
Further, one skilled in the art could have combined the elements described above by known methods with no change to the respective functions, and the combination would have yielded nothing more than predictable results. Therefore, it would have been obvious to combine Bellert with Davis to obtain the invention specified in claim 8.
Regarding claim 9, which claim 8 is incorporated, Davis discloses implementing a connected component function to identify a connected region as the one of the regions (Paragraph [0079] “Using the seventy percent agreement rule for vertical associations, the vertical associations for each row value are adjusted. Once all the vertical and horizontal associations are identified, connected component logic is used to find the extent of the table region of the image. Using connected graph logic, any set of connected values that span multiple rows is flagged as a table.”).
Regarding claim 10, which claim 9 is incorporated, Davis discloses identifying the bounding boxes within the connected region as the one of the regions (Paragraph [0080] “FIG. 5 illustrates the result 500 of the table detection step as applied to the example electronic document 300 page of FIG. 3. The light gray boxes are for all text items identified by the layout analysis, the dark gray boxes represent possible table candidates based on their vertical alignment with other values, and the box that encloses the tabular data represents the connected table region.”).
Regarding claim 11, which claim 10 is incorporated, Davis discloses wherein the extracting the characters within the one of the regions that includes the keyword characters comprises accessing characters within the identified bounding boxes (Paragraph [0081] “Method 200 may continue at step 212, which includes extracting data from the detected one or more tables. For example, once the bounding rectangle information for the table region is identified, the table region is cropped out of the image. With all vertical and horizontal lines removed from the image, the bounding area for columns may be identified by looking for vertical whitespace boundaries in the new table region image. This is done by calculating the pixel column means and subsequently binning the means using the same methodology used for finding vertical boundaries in text rows.”).
Regarding claim 12, which claim 1 is incorporated, Davis discloses comprising storing the extracted characters within the one of the regions to a data storage device (Paragraph [0097] “Method 200 may continue at step 218, which includes exporting the extracted data into an electronic file for presentation to a user, storage, conversion to hardcopy (e.g., printing) or otherwise). For example, once text has been identified for every cell value region, the cell boundary dictionary may be converted to a Pandas dataframe, and exported as a CSV file.”).
Regarding claim 13, which claim 1 is incorporated, Davis discloses wherein the document is a single page document (Paragraph [0088] “Method 200 may be executed to extract such data for each page individually.”; Examiner interprets that if one page is individually processed at a time then the document can be a single page).
Regarding claim 14, which claim 1 is incorporated, Davis discloses wherein the document comprises multiple pages (Paragraph [0088] “In some aspects, electronic documents span multiple pages.”).
Regarding claim 15, which claim 1 is incorporated, Davis discloses wherein the document comprises geologic information (Paragraph [0053] “Each of the electronic documents 140 may comprise or be a digital image of a paper document, such as, for example, a directional survey for a petroleum or water well.”).
Regarding claim 19, Davis discloses a system comprising: one or more processors (Paragraph [0099] “The computing system 600 includes a processor 610, a memory 620, a storage device 630, and an input/output device 640.”);
memory accessible to at least one of the one or more processors (Paragraph [0099] “The computing system 600 includes a processor 610, a memory 620, a storage device 630, and an input/output device 640.”);
processor-executable instructions stored in the memory and executable to instruct the system to (Paragraph [0099] “he processor 610 is capable of processing instructions for execution within the computing system 600. The processor may be designed using any of a number of architectures.”):
perform optical character recognition on a document (electronic document in Paragraph [0060] equates to a document) to define spatial locations of bounding boxes for characters, wherein each bounding box includes at least one character (text item in Paragraph [0060] equates to at least one character) (Paragraph [0060] “Method 200 may continue at step 204, which includes OCR'ing the electronic document (which may or may not be preprocessed as described). For example, in some aspects, the Tesseract OCR may be used to produce a hypertext markup language (html) representation of the page text (e.g., from the image in FIG. 3). From the html data, information about every text item's bounding rectangle may be parsed/saved in a JSON format (e.g., similar to the output of Google Vision).”);
identify a spatial location of keyword characters via a corresponding one of the bounding boxes (Paragraph [0060] “From the html data, information about every text item's bounding rectangle may be parsed/saved in a JSON format (e.g., similar to the output of Google Vision).”; Paragraph [0071] “With the text value bins identified for every row, the result is a set of bounding rectangles for every text value on the page image. These text bounding rectangles are organized by row, and assigned a logical identification (ID) that is a concatenation of row index (starting with 0 at the top) and value index (starting at 0 from left to right).”; The examiner interprets the concatenated row index and value to be the spatial location of keyword characters via a bounding box);
[apply an edge detection technique to generate a skeletonized version of the document;
determine borders within the skeletonized version of the document to define regions]; and
extract the characters within one of the regions that includes the keyword characters (Paragraph [0081] “Method 200 may continue at step 212, which includes extracting data from the detected one or more tables”; Paragraph [0083] “a cell value parser iterates through the table cells, checking the OCR output for text bounding boxes that fall inside the cell region. When an OCR text value is found to lie inside the table cell region, the text value is added to the table cell dictionary and removed from the OCR dictionary.”; Paragraph [0087] “The text for the column label rows may then be extracted using a similar methodology to the table extraction; bounding whitespace regions are identified as the text column boundaries, and the OCR text is then sorted by column. The sorted text is then associated with the table columns based on the amount of overlap in the horizontal extents of the table column region and the column label region. Once the column label text is associated with the data columns, the text is added to the table object (which stores the relative position information of all the parsed OCR text).”).
However, Davis fails to teach apply an edge detection technique to generate a skeletonized version of the document; and determine borders within the skeletonized version of the document to define regions.
Bellert teaches apply an edge detection technique to generate a skeletonized version of the document (image including a table in Paragraph [0052] equates to the document) (Paragraph [0031] “the skeleton engine (108) generates a skeleton graph for all identified connected components. Alternatively, the skeleton engine (108) generates the skeleton graph only for the largest connected component (i.e., the connected component with the largest number of pixels)”; Paragraph [0033] “a skeleton graph includes a series of edges and vertices. Each edge may correspond to a stroke, or a portion of a stroke, of the table. Each vertex may correspond to an intersection of two or more edges. Further, an edge may contain a path of pixels from one end of the stroke to the other end of the stroke, located approximately at the center of the stroke. The width of a path is one or more pixels.”; Paragraph [0052] “Initially, an image including a table is obtained (STEP 205). The image may be obtained (e.g., downloaded, scanned, etc.) from any source and may be of any size or format.”); and
determine borders (edges that make up the cell in Paragraph [0041] equate to the boarders) within the skeletonized version of the document to define regions (cells in Paragraph [0041] equate to regions) (Paragraph [0041] “the table engine (110) executes a table cell detection method to identify one or more cells that make up the table. Initially candidate cells are identified from the skeleton graph. The candidate cells are composed of edges and vertices. Then one or more validation processes are executed on each candidate cell to confirm the candidate cell is actually a cell of the table. In one or more embodiments, the table engine (110) stores the validated cells in a validated cells data structure (e.g., array, list).”).
Therefore, it would have been obvious to one of ordinary skill of the art before the effective filing date to modify Davis’s reference to include apply an edge detection technique to generate a skeletonized version of the document; and determine borders within the skeletonized version of the document to define regions taught by Bellert’s reference. The motivation for doing so would have been to generate a high-level representation of the table for inclusion in the electronic document as suggested by Bellert (see Bellert, Paragraph [0039]).
Further, one skilled in the art could have combined the elements described above by known methods with no change to the respective functions, and the combination would have yielded nothing more than predictable results. Therefore, it would have been obvious to combine Bellert with Davis to obtain the invention specified in claim 19.
Regarding claim 20, Davis discloses one or more computer-readable storage media comprising processor-executable instructions to instruct a computing system to (Paragraph [0102] “The storage device 630 is capable of providing mass storage for the computing system 600. In one implementation, the storage device 630 is a computer-readable medium.”):
perform optical character recognition on a document (electronic document in Paragraph [0060] equates to a document) to define spatial locations of bounding boxes for characters, wherein each bounding box includes at least one character (text item in Paragraph [0060] equates to at least one character) (Paragraph [0060] “Method 200 may continue at step 204, which includes OCR'ing the electronic document (which may or may not be preprocessed as described). For example, in some aspects, the Tesseract OCR may be used to produce a hypertext markup language (html) representation of the page text (e.g., from the image in FIG. 3). From the html data, information about every text item's bounding rectangle may be parsed/saved in a JSON format (e.g., similar to the output of Google Vision).”);
identify a spatial location of keyword characters via a corresponding one of the bounding boxes (Paragraph [0060] “From the html data, information about every text item's bounding rectangle may be parsed/saved in a JSON format (e.g., similar to the output of Google Vision).”; Paragraph [0071] “With the text value bins identified for every row, the result is a set of bounding rectangles for every text value on the page image. These text bounding rectangles are organized by row, and assigned a logical identification (ID) that is a concatenation of row index (starting with 0 at the top) and value index (starting at 0 from left to right).”; The examiner interprets the concatenated row index and value to be the spatial location of keyword characters via a bounding box);
[apply an edge detection technique to generate a skeletonized version of the document;
determine borders within the skeletonized version of the document to define regions]; and
extract the characters within one of the regions that includes the keyword characters (Paragraph [0081] “Method 200 may continue at step 212, which includes extracting data from the detected one or more tables”; Paragraph [0083] “a cell value parser iterates through the table cells, checking the OCR output for text bounding boxes that fall inside the cell region. When an OCR text value is found to lie inside the table cell region, the text value is added to the table cell dictionary and removed from the OCR dictionary.”; Paragraph [0087] “The text for the column label rows may then be extracted using a similar methodology to the table extraction; bounding whitespace regions are identified as the text column boundaries, and the OCR text is then sorted by column. The sorted text is then associated with the table columns based on the amount of overlap in the horizontal extents of the table column region and the column label region. Once the column label text is associated with the data columns, the text is added to the table object (which stores the relative position information of all the parsed OCR text).”).
However, Davis fails to teach apply an edge detection technique to generate a skeletonized version of the document; and determine borders within the skeletonized version of the document to define regions.
Bellert teaches apply an edge detection technique to generate a skeletonized version of the document (image including a table in Paragraph [0052] equates to the document) (Paragraph [0031] “the skeleton engine (108) generates a skeleton graph for all identified connected components. Alternatively, the skeleton engine (108) generates the skeleton graph only for the largest connected component (i.e., the connected component with the largest number of pixels)”; Paragraph [0033] “a skeleton graph includes a series of edges and vertices. Each edge may correspond to a stroke, or a portion of a stroke, of the table. Each vertex may correspond to an intersection of two or more edges. Further, an edge may contain a path of pixels from one end of the stroke to the other end of the stroke, located approximately at the center of the stroke. The width of a path is one or more pixels.”; Paragraph [0052] “Initially, an image including a table is obtained (STEP 205). The image may be obtained (e.g., downloaded, scanned, etc.) from any source and may be of any size or format.”); and
determine borders (edges that make up the cell in Paragraph [0041] equate to the boarders) within the skeletonized version of the document to define regions (cells in Paragraph [0041] equate to regions) (Paragraph [0041] “the table engine (110) executes a table cell detection method to identify one or more cells that make up the table. Initially candidate cells are identified from the skeleton graph. The candidate cells are composed of edges and vertices. Then one or more validation processes are executed on each candidate cell to confirm the candidate cell is actually a cell of the table. In one or more embodiments, the table engine (110) stores the validated cells in a validated cells data structure (e.g., array, list).”).
Therefore, it would have been obvious to one of ordinary skill of the art before the effective filing date to modify Davis’s reference to include apply an edge detection technique to generate a skeletonized version of the document; and determine borders within the skeletonized version of the document to define regions taught by Bellert’s reference. The motivation for doing so would have been to generate a high-level representation of the table for inclusion in the electronic document as suggested by Bellert (see Bellert, Paragraph [0039]).
Further, one skilled in the art could have combined the elements described above by known methods with no change to the respective functions, and the combination would have yielded nothing more than predictable results. Therefore, it would have been obvious to combine Bellert with Davis to obtain the invention specified in claim 20.
Claims 2 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Davis et al. (US 2018/0276462 A1) (hereinafter; “Davis”) in view of Bellert (US 2019/0102619 A1) as applied to claim 1 above; and further in view of Prebble (US 2023/0094651 A1).
Regarding claim 2, which claim 1 is incorporated, Davis and Bellert fail to teach setting areas within the bounding boxes to a pixel value to reduce risk of character edge bleed over to one or more region edges.
Prebble teaches setting areas within the bounding boxes to a pixel value to reduce risk of character edge bleed over to one or more region edges (Paragraph [0034] “given a character bounding box with an inclusive upper left corner at coordinates (x, y) and an exclusive lower right corner at coordinates (x+w, y+h), the new value for pixel (x+j, y+i), where 0 ≤ j < w and 0 ≤ i < h, is set to the value of an interpolation function based on the values of the pixels just outside the four corners of the bounding box. In this way, the image characters are removed from the original input image while preserving the look of the background underlying the characters.”).
Therefore, it would have been obvious to one of ordinary skill of the art before the effective filing date to modify Davis in view of Bellert to include setting areas within the bounding boxes to a pixel value to reduce risk of character edge bleed over to one or more region edges taught by Prebble’s reference. The motivation for doing so would have been to remove the image characters while preserving the look of the background as suggested by Prebble (see Prebble, Paragraph [0034]).
Further, one skilled in the art could have combined the elements described above by known methods with no change to the respective functions, and the combination would have yielded nothing more than predictable results. Therefore, it would have been obvious to combine Prebble with Davis and Bellert to obtain the invention specified in claim 2.
Regarding claim 18, Davis and Bellert both fail to teach wherein the one of the regions comprises a polygonal border that comprises more than four sides.
PNG
media_image1.png
440
796
media_image1.png
Greyscale
Prebble teaches wherein the one of the regions comprises a polygonal border that comprises more than four sides (See Figure 7).
Therefore, it would have been obvious to one of ordinary skill of the art before the effective filing date to modify Davis in view of Bellert to include wherein the one of the regions comprises a polygonal border that comprises more than four sides taught by Prebble’s reference. The motivation for doing so would have been to remove the image characters while preserving the look of the background as suggested by Prebble (see Prebble, Paragraph [0034]).
Further, one skilled in the art could have combined the elements described above by known methods with no change to the respective functions, and the combination would have yielded nothing more than predictable results. Therefore, it would have been obvious to combine Prebble with Davis and Bellert to obtain the invention specified in claim 18.
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Davis et al. (US 2018/0276462 A1) (hereinafter; “Davis”) in view of Bellert (US 2019/0102619 A1) as applied to claim 6 above; and further in view of Vincent et al. (US 2010/0232719 A1) (hereinafter; “Vincent”).
Regarding claim 7, which claim 6 is incorporated, Davis and Bellert both fail to teach wherein the data structure comprises confidence indicators as to confidence of the optical character recognition for one or more strings of characters.
Vincent teaches wherein the data structure comprises confidence indicators as to confidence of the optical character recognition for one or more strings of characters (Paragraph [0022] “This method further includes applying shape clustering to the first OCR output to produce first clusters with first clip images and a respective confidence score for each assignment of one or more characters to a first clip image; applying shape clustering to the second OCR output to produce second clusters with second clip images and a respective confidence score for each assignment of one or more characters to a second clip image; and generating a final OCR output from the first OCR output and the second OCR output.”).
Therefore, it would have been obvious to one of ordinary skill of the art before the effective filing date to modify Davis in view of Bellert to include wherein the data structure comprises confidence indicators as to confidence of the optical character recognition for one or more strings of characters taught by Vincent’s reference. The motivation for doing so would have been to improve the OCR quality in the post-OCR processing as suggested by Vincent (see Vincent, Paragraph [0057]).
Further, one skilled in the art could have combined the elements described above by known methods with no change to the respective functions, and the combination would have yielded nothing more than predictable results. Therefore, it would have been obvious to combine Vincent with Davis and Bellert to obtain the invention specified in claim 7.
Claims 16 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Davis et al. (US 2018/0276462 A1) (hereinafter; “Davis”) in view of Bellert (US 2019/0102619 A1) as applied to claim 15 above; and further in view of Lai (US 2019/0332885 A1).
Regarding claim 16, which claim 15 is incorporated, Davis and Bellert both fail to teach wherein the geologic information comprises at least one log.
Lai teaches wherein the geologic information comprises at least one log (Paragraph [0004] “The execution environment includes a well log data solver configured to perform operations including: cropping one or more portions of a particular page of the well log file image that includes solid color space…executing an optical character recognition (OCR) technique on the cropped one or more portions of the particular page that includes well log file data to generate an OCR'd image”; Paragraph [0043] “Typically, a well log (or “log” for short) is a record of several criteria of a well versus depth or time, or both. The record can be of one or more physical properties in or around the well. Well logs can be generated a number of different ways.”).
Therefore, it would have been obvious to one of ordinary skill of the art before the effective filing date to modify Davis in view of Bellert to include wherein the geologic information comprises at least one log taught by Lai’s reference. The motivation for doing so would have been to identify, from a remote computing system, an identification of the user-specified well log file data as suggested by Lai (see Lai, Paragraph [0006]).
Further, one skilled in the art could have combined the elements described above by known methods with no change to the respective functions, and the combination would have yielded nothing more than predictable results. Therefore, it would have been obvious to combine Lai with Davis and Bellert to obtain the invention specified in claim 16.
Regarding claim 17, which claim 16 is incorporated, Davis and Bellert both fail to teach wherein the at least one log is oriented vertically.
Lai teaches wherein the at least one log is oriented vertically (Paragraph [0004] “The execution environment includes a well log data solver configured to perform operations including: cropping one or more portions of a particular page of the well log file image that includes solid color space…executing an optical character recognition (OCR) technique on the cropped one or more portions of the particular page that includes well log file data to generate an OCR'd image”; Paragraph [0050] “as shown in FIG. 4A, the page 401 of the well log file 400 is shown vertically oriented. If the determination in step 304 is yes, then step 204 may continue at step 308 (described below).”)
Therefore, it would have been obvious to one of ordinary skill of the art before the effective filing date to modify Davis in view of Bellert to include wherein the at least one log is oriented vertically taught by Lai’s reference. The motivation for doing so would have been to identify, from a remote computing system, an identification of the user-specified well log file data as suggested by Lai (see Lai, Paragraph [0006]).
Further, one skilled in the art could have combined the elements described above by known methods with no change to the respective functions, and the combination would have yielded nothing more than predictable results. Therefore, it would have been obvious to combine Lai with Davis and Bellert to obtain the invention specified in claim 17.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Shacham et al. (US 2013/0135689 A1) discloses a method for obtaining an image of a document by obtaining a bounding box that bounds the region of the image and determining coordinates of points within the region.
Slattery (US 2021/0326629 A1) discloses a method of capturing printed text and identifying shapes using edge detection and contouring document image text.
Xu et al. (US 2022/0309549 A1) discloses a method for processing documents by using a data processing hardware of a computer for converting unstructured documents to structured key-value pairs.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to UROOJ FATIMA whose telephone number is (571)272-2096. The examiner can normally be reached M-F 8:00-5:00.
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, Henok Shiferaw can be reached at (571) 272-4637. 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.
/UROOJ FATIMA/Examiner, Art Unit 2676
/Henok Shiferaw/Supervisory Patent Examiner, Art Unit 2676
Prosecution Insights