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 .
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Regarding claim 1, an input to the claimed model, such as an image as shown in figure 2, is not defined. It is unclear what the raster segmentation model is being executed on. Similarly, the term “header mask” is ambiguous as it is undefined whether the “header” is, for example, a region of pixels or a row in a table. This leaves the difference between the “raster segmentation model” and the “header mask segmentation model” unclear. It is also unclear how exactly the “segment comparison model” uses the first header mask with the second header mask to generate a comparison score.
Regarding claim 2, it is not clear how the recited raster segmentation model operates. Claim 1 recites “executing a raster segmentation model… to generate a plurality of masks”, however claim 2 recites that “executing the raster segmentation model… comprises: tiling an image into a set of image tiles”, with no stated relationship between the tiling and mask generation. It is unclear whether the model operates per-tile, on the whole image, on a different input, or if the tiling has any influence on the masks at all.
Regarding claim 3, it is not clear whether the recited image tile is the same as the image tile recited in claim 2 or a separate one. It is also unclear how a plurality of mask tiles is generated from the single recited image tile.
Regarding claim 4, it is not clear how the plurality of mask tiles is generated. It is also unclear whether the recited plurality of header mask tiles, track mask tiles, and depth track mask tiles include the header mask tile, track mask tile, and depth mask tile generated in claim 3.
Regarding claim 5, it is not clear how a header is identified.
Claims 11-15 and 20 correspond to claims 1-5 respectively and are similarly rejected.
Regarding claims 2-10, an incorrect dependency on claim 21 is recited. It appears to be directed towards claim 1.
Regarding claims 12-19, an incorrect dependency on claim 31 is recited. It appears to be directed towards claim 11.
All dependent claims inherit the deficiencies of their parent claim and are similarly rejected.
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 1, 7, 10-11, 17, and 20 as best understood are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1, 7-10, 15-16, and 18 of U.S. Patent No. 12,488,610 to Gune (present inventor) et al. in view of Nasim et al. (NPL, “VeerNet: Using Deep Neural Networks for Curve Classification and Digitization of Raster Well-Log Images”, pdf attached).
The conflicting claims are:
Claims 1, 7, 10-11, 17, and 20 in present application 18/919,811.
Claims 1, 7-10, 15-16, and 18 in US Patent No. 12,488,610.
Table 1 provided below is the comparative mapping of the limitations of the independent claims 1, 11, and 20 of the present application when compared against the limitations of claims 1 of Patent No. 12,488,610. Although limitations involving using operation values in the comparison model as well as a threshold are not explicitly recited in the claims of US 12,488,610, they are addressed separately below in view of Nasim.
Present Application 18/919,811
US Patent No. 12,488,610
1. A method comprising: executing a raster segmentation model for a first stage to generate a plurality of masks comprising a first header mask; executing a header mask segmentation model for a second stage to generate a second header mask; executing a segment comparison model using the first header mask with the second header mask to generate a comparison score; generating a raster retraining score from the comparison score for the raster segmentation model of a raster digitization engine; and retraining the raster segmentation model using the raster retraining score.
1. A method comprising: receiving raster images of downhole assembly logs comprising well information, wherein the downhole assembly logs comprise plots, tracks and headers and wherein, compared to the plots and the tracks, the headers are underrepresented; processing the raster images using a trained machine learning model to generate segmentation masks for the downhole assembly logs for identification of the plots, the tracks and the headers; adjusting the trained machine learning model using labeled synthetic data, wherein the labeled synthetic data comprises synthetic downhole assembly logs, and the labeled synthetic data is generated by grouping headers to generate groups, labeling at least one header from at least one of the groups, and replicating the at least one header; and generating digitized versions of the downhole assembly logs, wherein each of the digitized versions of the downhole assembly logs comprises a digitized plot with an associated digitized header and an associated digitized track.
7. The method of claim 21, wherein executing the segment comparison model comprises: processing the first header mask with a set of second mask tiles to generate a set of operation values, wherein a second mask tile of the set of second mask tiles corresponds to the second header mask, and wherein an operation value of the set of operation values is one of an intersection over union value, an F1 score value, and a DICE score value.
7. The method of claim 2, comprising performing a quality control process on the numerical values to identify one or more erroneous numerical values.
10. The method of claim 21, wherein retraining the raster segmentation model comprises: retraining the raster segmentation model when the raster retraining score satisfies a raster retraining threshold, wherein the raster retraining threshold is 0.9 and the raster segmentation model is retrained when the raster retraining score is below the raster retraining threshold.
8. The method of claim 7, wherein the quality control process utilizes multiple outlier detection techniques.
Claims 11, 17, and 20 correspond to claims 1 and 7 and are similarly rejected.
9. The method of claim 1, wherein processing the raster images comprises a first stage and a second stage.
10. The method of claim 9, wherein the first stage utilizes a single classification process for plots, tracks and headers and wherein the second stage utilizes a single classification process for plots and another single classification process for headers.
15. The method of claim 1, comprising testing the trained machine learning model for making a decision as to acceptable performance or unacceptable performance.
16. The method of claim 15, wherein the labeled synthetic data is generated in response to the decision as to unacceptable performance.
18. The method of claim 1, wherein adjusting the trained machine learning model comprises retraining or fine tuning the trained machine learning model based on the labeled synthetic data.
In the combination of claims above, US Patent No. 12,488,610 teaches a two-stage classification process for header segmentation masks, performing a quality control process that identifies erroneous values, testing a trained model to determine whether performance is acceptable or unacceptable, and responsive to a determination of unacceptable performance, generating synthetic data and retraining the model.
Nasim discloses a similar Raster well-log digitization method where they compare predicted segmentation masks against a reference mask using metrics such as IoU and F1 scores (Table 4). One of ordinary skill in the art would have recognized that implementing the already claimed acceptable/unacceptable performance test by comparing the claimed first and second stage header outputs using IoU, F1, or DICE metrics to quantify the determination is a routine variation using known techniques, as disclosed by Nasim. One of ordinary skill in the art would have also understood that specifying a threshold to determine when to retrain the raster segmentation model is a predictable modification using well-known techniques in view of the already disclosed retraining and acceptable/unacceptable process.
Allowable Subject Matter
Claims 1, 11, 20, and their dependents would be allowable if rewritten or amended to overcome the rejection(s) under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), 2nd paragraph, set forth in this Office action as well as upon resolution of the double patenting rejection set forth above.
Conclusion
Pertinent Prior Art: Nasim, M. Q., Patwardhan, N., Maiti, T., & Tarry, S. (2022). Digitization of raster logs: A deep learning approach. arXiv.Org. https://arxiv.org/abs/2210.05597 Earlier version of the VeerNet architecture. Similar Raster digitization but does not perform multi-stage segmentation masking or retraining based on a comparison score.
Valluru et al., US 20250013916 A1, “SYSTEMS AND METHODS FOR IDENTIFYING MODEL DEGRADATION AND PERFORMING MODEL RETRAINING”, filed 2023, Similar retraining method which uses a threshold to evaluate the model performance and determine if retraining is necessary. Does not perform multi-stage segmentation masking.
Juillard, US 11270438 B2, “System And Method For Triggering Machine Learning (ML) Annotation Model Retraining”, filed 2021, Similar retraining method that works on segmentation masks. Includes input from a human operator and comparison is not between masks generated from a two-stage process.
Kim et al., US 11961281 B1, “Training And Using Computer Vision Model For Item Segmentations In Images”, filed 2021, Similar method of optimizing training for a segmentation model. Performs an IoU to compare two masks for filtering. Does not retrain based on a comparison score
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DAVID A WAMBST whose telephone number is (703)756-1750. The examiner can normally be reached M-F 9-6:30 EST.
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 (571)272-3838. 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.
/DAVID ALEXANDER WAMBST/Examiner, Art Unit 2663
/GREGORY A MORSE/Supervisory Patent Examiner, Art Unit 2698
Prosecution Insights