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 10/02/2025 was filed and is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
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.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1, 4-7, 13, 16, 17 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Coffman (US 11,698,623 B2, 2022).
Regarding claim 1, Coffman teaches A method for predicting product manufacturing index (Coffman, column 4, lines 51-65, reproduced below:
PNG
media_image1.png
680
1056
media_image1.png
Greyscale
. “Predictive system for Manufacture Processes” is being interpreted as involving “predicting product manufacturing index”), comprising:
Step P1) performing an image preprocessing (Coffman, see nearest image above, predictive system for manufacture processes using a scanned copy of a model drafted by hand is being interpreted as involving image preprocessing) on a flat development drawing of a product (Coffman, see nearest image above, “CAD file, a scanned copy of a model drafted by hand” is being interpreted as involving “a flat development drawing of a product”) to convert the flat development drawing into input data (Coffman, column 5, lines 31-10, reproduced below:
PNG
media_image2.png
302
708
media_image2.png
Greyscale
. “Data processing” is being interpreted as involving converting the flat development drawing into input data);
Step P2) performing a principal component analysis (PCA) (Coffman, see nearest image below, “Dimensionality reduction process engines” are being interpreted to involve PCA) on the input data to convert the input data into a principal component data (Coffman, column 22, lines 18-30, reproduced below:
PNG
media_image3.png
594
1062
media_image3.png
Greyscale
.”Machine learning models” and “properties of a physical object represented in the CAD model” are being interpreted to involve converted input data); and
Step P3) using a first artificial intelligence (AI) model (Coffman, see column 22 image above, “one or more machine learning models” is being interpreted to involve “a first artificial intelligence model”) to predict a manufacturing index of the product (Coffman, see column 4 image above, “A Predictive System for Manufacture Processes”) according to the principal component data (Coffman, see column 22 image above, “dimensionality reduction”).
Regarding claim 4, Coffman teaches The method of claim 1, wherein the method comprises performing a model training process before executing the step P1), and the model training process comprises:
Step T1) performing the image preprocessing (Coffman, see column 4 image, predictive system for manufacture processes using a scanned copy of a model drafted by hand is being interpreted as involving image preprocessing) on each of a plurality of flat development drawings (Coffman, column 4, lines 59-60: “a scanned copy of a model drafted by hand”) to convert the plurality of flat development drawings into a plurality of input data (Coffman, column 17, lines 28-44, reproduced below:
PNG
media_image4.png
782
1074
media_image4.png
Greyscale
. “generates a training set” over the corpus [of raw datasets; as cited in col 17, lines 21-22] is being interpreted as an example of converting the plurality of flat development drawings into a plurality of input data);
Step T2) performing the principal component analysis (Coffman, see nearest image above, “a dimensionality reduction process”) on each of the plurality of input data (Coffman, see nearest image above, “Accordingly, a dimensionality reduction process can be applied to compress the attributes onto a lower dimensionality subspace”. Which is being interpreted to be done on the input data as the PSMP server generates a training set) to convert the plurality of input data into a plurality of principal component data (Coffman, see nearest image above, “Accordingly, a dimensionality reduction process can be applied to compress the attributes onto a lower dimensionality subspace and advantageously, storage space can be minimized”. “Storage space” is being interpreted as involving the result of the dimensionality reduction of converting the plurality of input data into a plurality of principal component data);
Step T3) determining a training dataset (Coffman, see nearest image above, “PSMP server 109 generates, at 603, a training set”) and a testing dataset from the plurality of principal component data (Coffman, column 17, lines 57-67, reproduced below:
PNG
media_image5.png
508
1064
media_image5.png
Greyscale
. “test dataset” is being interpreted as testing dataset from the plurality of principal component data);
Step T4) training a second initial model corresponding to a second AI model (Coffman, see nearest image below, “a subset of the training machine learning models” is being interpreted as involving “a second AI model”) according to the training dataset (Coffman, see nearest image below, “training” shows a training dataset was used) and the testing dataset (Coffman, column 17, lines 45-56, reproduced below:
PNG
media_image6.png
544
1064
media_image6.png
Greyscale
. “Classification accuracy” is being interpreted as involving “testing dataset”); and
Step T5) training a first initial model (Coffman, see nearest image above, “one or more machine learning models are trained”, which is being interpreted to involve “a first initial model”) corresponding to the first AI model (Coffman, see nearest image above, “one or more machine learning models are trained”, which is being interpreted to involve “first AI model”) according to the training dataset (Coffman, see nearest image above, “one or more machine learning models are trained” is being interpreted as using a “training dataset”) and the testing dataset (Coffman, see nearest image above, “classification accuracy” is being interpreted as involving a testing dataset to obtain classification accuracy, as one with ordinary skill in the art would know).
Regarding claim 5, Coffman teaches The method of claim 4, wherein the step T4) comprises:
training the second initial model according to the training dataset and a training manufacturing index set (Coffman, see nearest image below, “specific parameters…for the operation of predictive machine learnings” are being interpreted as involving “manufacturing index set”. A non-exhaustive example of a manufacturing index set would be “performing descriptive or inferential statistical analysis over datasets”) corresponding to the training dataset (Coffman, column 13, lines 1-13, reproduced below:
PNG
media_image7.png
652
1068
media_image7.png
Greyscale
”inputs for predictive machine learning models” is being interpreted as involving “training dataset”); and
testing the second initial model (Coffman, see nearest image below, “a subset of the trained machine learning models can be selected” is being interpreted as involving “testing the second initial model”, the test involving checking classification accuracy) according to the testing dataset and a testing (Coffman, see nearest image below, “classification accuracy” is being interpreted as involving “testing” dataset) manufacturing index set (Coffman, see nearest image above, “specific parameters” used for prediction are being interpreted as involving “manufacturing index set” when combined with the below image) corresponding to the testing dataset (Coffman, column 17, lines 45-56, reproduced below:
PNG
media_image6.png
544
1064
media_image6.png
Greyscale
. “Classification accuracy” is being interpreted as involving “testing dataset”).
Regarding claim 6, Coffman teaches The method of claim 5, wherein the step T5) comprises:
training the first initial model according to the training dataset (Coffman, column 17, lines 45-56, reproduced below:
PNG
media_image6.png
544
1064
media_image6.png
Greyscale
. “more than one machine learning model can be trained” is being interpreted to involve “training the first initial model according to the training dataset”) and the training manufacturing index set (Coffman, see nearest image below, “specific parameters” used for prediction are being interpreted as involving “manufacturing index set”) corresponding to the training dataset (Coffman, column 13, lines 1-13, reproduced below:
PNG
media_image7.png
652
1068
media_image7.png
Greyscale
”inputs for predictive machine learning models” is being interpreted as involving “training dataset”); and
testing the first initial model (Coffman, see nearest column 17 image above, “more than one machine learning model can be trained” is being interpreted to involve “first initial model”; “classification accuracy” is being interpreted as involving testing) according to the testing dataset (Coffman, see nearest column 17 image above, “classification accuracy” is being interpreted as involving using the testing dataset, as one with ordinary skill in the art would know) and the testing manufacturing index set (Coffman, see nearest image above, “specific parameters” used for prediction are being interpreted as involving “manufacturing index set”) corresponding to the testing dataset (Coffman, see nearest column 17 image above, “classification accuracy” is being interpreted as involving using the testing dataset, as one with ordinary skill in the art would know).
Regarding claim 7, Coffman teaches The method of claim 6, wherein the model training process further comprises:
Step T6) when the first initial model and the second initial model (Coffman, column 17, lines 45-46, “one or more machine learning models are trained”, which includes first and second initial models) do not pass the test (Coffman, see nearest image below, “when the desired accuracy level is not reached” is being interpreted as involving “do not pass the test”), increasing sample completeness of the training dataset (Coffman, column 17, lines 57-67, reproduced below:
PNG
media_image5.png
508
1064
media_image5.png
Greyscale
. “considering a larger collection of raw data” is being interpreted as “increasing sample completeness of the training dataset”); and
returning to the step T4) (Coffman, Figure 6, which shows at 615 if accuracy levels are not reached, the flowchart repeats the process that involves training and testing machine learning models; column 17, lines 45-46, “one or more machine learning models are trained”, which includes first and second initial models).
Regarding claim 13, Coffman teaches The method of claim 1, wherein the product is a mechanical component (Coffman, column 4, lines 51-65, reproduced below:
PNG
media_image8.png
454
710
media_image8.png
Greyscale
. “Mechanical part” is being interpreted as “mechanical component”. Examiner notes this limitation is being interpreted as part of an “or” statement, and only one portion of the or statement will be addressed), a printed circuit board, an interior space or a building, and the flat development drawing (Coffman, see nearest image above, “a scanned copy of a model drafted by hand”) is a mechanical drawing (Coffman, see nearest image above, “mechanical part…conveyed in an electronic file such as a CAD file, a scanned copy of a model drafted by hand” is being interpreted as involving “a mechanical drawing”. Examiner notes this part of the limitation is being interpreted as part of an “or” statement, and will only consider a portion of the “or” statement), a printed circuit board layout, a panorama of interior design drawing or an architectural drawing.
Regarding claim 16, Coffman teaches A first device for predicting product manufacturing index, comprising:
a first processing unit (Coffman, column 5, lines 31-40, reproduced below:
PNG
media_image9.png
462
1056
media_image9.png
Greyscale
. “One or more computer processors” are being interpreted to involve “a first processing unit”); and
a storing unit (Coffman, see nearest image above, “PSMP server” is being interpreted as involving a storing unit), coupled to the first processing unit (Coffman, see nearest image above, “PSMP server can include one or more computer processors”), configured to store a program code (Coffman, see nearest image above, “computer memories” is being interpreted as involving storing program code), wherein the program code instructs the first processing unit to perform the method of claim 1 (Coffman, see nearest image above, PSMP server is being interpreted as performing the method of claim 1, as seen in example Figure 11).
Regarding claim 17, Coffman teaches A second device (Coffman, see nearest image below and Figure 11, “PSMP Server” is being interpreted as involving “a second device”), comprising:
an image capturing unit configured to capture a flat development drawing of a product (Coffman, column 4, lines 59-60, “a scanned copy of a model drafted by hand” is being interpreted as involving an image capturing unit to cause the scanning. “Scanned copy” is being interpreted as involving “a flat development drawing”); and
a communication unit coupled to the image capturing unit (Coffman, column 5, lines 31-40, reproduced below:
PNG
media_image9.png
462
1056
media_image9.png
Greyscale
. “Communication operations” is being interpreted as involving “a communication unit”), configured to transmit the flat development drawing to the first device of claim 16 (Coffman, see nearest image above, “PSMP server receives…electronic files”; column 4, lines 59-60, “a scanned copy of a model drafted by hand” is being interpreted as “flat development drawing”), and receive a manufacturing index of the product from the first device (Coffman, see nearest image above, “PSMP server…processes prediction requests”, which is being interpreted as involving predicting “a manufacturing index of the product from the first device”).
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.
Claim(s) 2 is/are rejected under 35 U.S.C. 103 as being unpatentable over Coffman, in view of Joshua M (“Advanced Knowledge Extraction of Physical Design Drawings, Translation and conversion to CAD formats using Deep Learning”, 2023).
Regarding claim 2, Coffman teaches The method of claim 1, wherein the step P1) comprises:
However, Coffman does not appear to explicitly teach converting the flat development drawing into a binary image.
Pertaining to the same field of endeavor, Joshua M teaches
Step P11) converting the flat development drawing (Joshua M, title, “Physical Design Drawings”) into a binary image (Joshua M, pg 5, Section 3.1.3, “edge detection”. One with ordinary skill in the art would know that edge detection results in a binary image. See informative footnote: https://docs.opencv.org/4.13.0/da/d22/tutorial_py_canny.html);
Step P12) cropping the binary image to retain a region of interest (ROI) (Joshua M, pg 7, section 3.21, “Primarily, the text objects are identified and bounding boxes over the objects are drawn to facilitate cropping and further the text is extracted from the cropped image using the Optical Character Recognition (OCR)”. The text ROI, or bounding boxes, are an example of cropping. As this step happens after edge detection, this occurs on the binary image.);
Step P13) normalizing a size of the ROI (Joshua M, pg 5, yolo_lights key function: “YOLO model trained specifically for decor”. PHOSITA would know YOLO outputs normalized bounding boxes, or ROI. See the following footnote for more information: https://medium.com/@miramnair/yolov7-calculating-the-bounding-box-coordinates-8bab54b97924); and
Step P14) converting the normalized ROI into the input data represented as a one-dimensional array (Joshua M, pg 8, Section 3.2.2, “From the above models, the various shapes detected are extracted, consolidated and converted to csv file format for each line, circle, lights etc., with coordinates of individual items saved”. “Converted to csv file format” is being interpreted as converting the normalized ROI into the input data, as seen in the example table “Converted csv file”. Each row of the CSV file is being interpreted as a vector, or a one-dimensional array, as PHOSITA would know, of the various shapes).
Coffman and Joshua M are considered to be analogous art because they are directed to image processing related to CAD models. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method and system for predicting manufacturing index (as taught by Coffman) to include image conversion into binary image (as taught by Joshua M) because the combination provides an improvement to advanced knowledge extraction (Joshua M, Abstract). Further, binary image conversion is common practice in the field of image processing, as PHOSITA would know.
Claim(s) 3 is/are rejected under 35 U.S.C. 103 as being unpatentable over Coffman, as modified by Joshua M, in view of Pythongeeks (“Color, Grayscale and Binary Image Conversion in OpenCV”, 2022).
Regarding claim 3, Coffman teaches The method of claim 2, wherein the step P11) comprises:
… the flat development drawing… (Coffman, column 4, lines 59-60: “a scanned copy of a model drafted by hand”)
However, Coffman and Joshua M does not appear to explicitly teach converting into a grayscale image, and then into a binary image.
Pertaining to the same field of endeavor, Pythongeeks teaches
converting…into a grayscale image (Pythongeeks, pg 1, last paragraph: “Grayscaling is the process of converting an image from any color space to grayscale”. Which shows image conversion to grayscale); and
performing binary conversion on the grayscale image to convert the grayscale image into the binary image (Pythongeeks, pg 10, Section Thresholding in OpenCV, reproduced below:
PNG
media_image10.png
268
796
media_image10.png
Greyscale
. “Converted from…grayscale into a binary image”).
Coffman, Joshua M, and Pythongeeks are considered to be analogous art because they are directed to image processing. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method and system for predicting manufacturing index modified to include image conversion into binary image (as taught by Coffman, modified by Joshua M) to include image conversion into grayscale, and then into binary image (as taught by Pythongeeks) because the combination provides an improvement to advanced knowledge extraction (Joshua M, Abstract). Further, grayscale and binary image conversion is common practice in the field of image processing, as PHOSITA would know. It would obvious to try, as Pythongeeks states on pg 2, the importance of gray scaling includes an example of reducing model complexity, and binary conversion is important for image processing (pg 10).
Claim(s) 8-10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Coffman, in view of Bogorad (US 2024/0378484 A1).
Regarding claim 8, Coffman teaches The method of claim 6, wherein the model training process further comprises:
Step T7) when the second initial model passes the test, storing the second initial model as the second AI model (Coffman, column 17, lines 52-56: “Thus, a subset of the trained machine learning models can be selected to build predictive engine 611 according to, for example, classification accuracy, defined as the proportion of correctly classified 55 instances.” “Subset” is being interpreted as involving the second initial model. “selected” is being interpreted as involving storing the second initial model as the second AI model as part of the subset. “proportion of correctly classified instances” is being interpreted as involving “passes the test”); and
adjusting at least one hyperparameter of the first initial model and returning to the step T5) (Coffman, column 8, lines 24-27: “execute one or more processes to retrain evolutionary computation models such that the matching error rate is decreased to an acceptable level”. Coffman already teaches multiple machine learning models. PHOSITA would know retraining of machine learning models, such as the evolutionary computation model, requires adjusting at least one hyperparameter. The evolutionary computation model is being interpreted as involving “first initial model”.).
However, Coffman does not appear to explicitly teach first initial model not passing the test and second initial model passing the test.
Pertaining to the same field of endeavor, Bogorad teaches
Step T8) when the first initial model does not pass the test (Bogorad, [0054]: “The overlay model can be not significantly contributing when the overlay model contributes below a threshold amount”. “below a threshold amount” is being interpreted as “does not pass the test”. “Overlay model” is being interpreted as first initial model) and the second initial model passes the test (Bogorad, [0055]: “The base model can be not significantly contributing when the base model contributes below a threshold amount”. Which shows the base model, interpreted as the second model, can be above a threshold, or passing the test), …
Coffman and Bogorad are considered to be analogous art because they are directed to multiple machine learning models management. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method and system for predicting manufacturing index (as taught by Coffman) to include first initial model not passing the test and second initial model passing the test (as taught by Bogorad) because the combination provides an improvement to machine learning models accuracy (Bogorad, [0025]).
Regarding claim 9, Coffman teaches The method of claim 8, wherein the model training process further comprises:
Step T9) when the first initial model passes the test, storing the first initial model as the first AI model (Coffman, column 17, lines 52-56: “Thus, a subset of the trained machine learning models can be selected to build predictive engine 611 according to, for example, classification accuracy, defined as the proportion of correctly classified instances”. Which shows when the first initial model passes the test of classification accuracy, the model will be selected, or stored); and
However, Coffman does not appear to explicitly teach when the first initial model passes the test and no matter the second initial model passes the test or not, verifying a first accuracy of the first AI model and a second accuracy of the second AI model according to a verification testing set.
Pertaining to the same field of endeavor, Bogorad teaches
Step T10) when the first initial model passes the test (Bogorad, [0054]: “The overlay model can be not significantly contributing when the overlay model contributes below a threshold amount”. “Below a threshold” shows that “above a threshold” is included in passing the test. “Overlay model” is being interpreted as the first initial model) and no matter the second initial model passes the test or not (Bogorad, [0013]: “The operations further include determining, based on the plurality of metrics, an amount of bias to provide to the base model compared to the overlay model when performing predictions using the ensemble model”. “Plurality of metrics” includes classification performance, as stated in [0015]. The classification performance is calculated for both first [interpreted from overlay model] and second [interpreted from base model], no matter if the second passes the test or not), verifying a first accuracy of the first AI model (Bogorad, [0027]: “Classification performance of the overlay model should be on par with the base model”. “Classification performance” is being interpreted as involving verifying accuracy. “Overlay model” is being interpreted as “first AI model” and the classification performance on the overlay model being interpreted as first accuracy) and a second accuracy of the second AI model according to a verification testing set (Bogorad, [0027]: “Classification performance of the overlay model should be on par with the base model”. “Classification performance” is being interpreted as involving verifying accuracy. “Base model” is being interpreted as “second AI model” and the classification performance on the overlay model being interpreted as second accuracy).
Coffman and Bogorad are considered to be analogous art because they are directed to multiple machine learning models management. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method and system for predicting manufacturing index (as taught by Coffman) to include when the first initial model passes the test and no matter the second initial model passes the test or not, verifying a first accuracy of the first AI model and a second accuracy of the second AI model according to a verification testing set (as taught by Bogorad) because the combination provides an improvement to machine learning models accuracy (Bogorad, [0025]). Additionally, Coffman already teaches classification accuracy, as PHOSITA would know, classification accuracy is a common concern for training machine learning models.
Regarding claim 10, Coffman teaches The method of claim 9, wherein the model training process further comprises:
Step T11) when the first accuracy is not lower than the second accuracy, finishing the model training process (Coffman, column 18, lines 36-38, reproduced below: “A termination condition is then evaluated at 705. A termination condition can based on any of: 1) a known optimal fitness level…”. Which shows when a termination condition of met, the training completes)
However, Coffman does not appear to explicitly teach when the first accuracy is lower than the second accuracy, retraining the first model.
Pertaining to the same field of endeavor, Bogorad teaches
Step T11) when the first accuracy is lower than the second accuracy (Bogorad, [0027]: “Classification performance of the overlay model should be on par with the base model”. Which shows Bogorad does find out if the first accuracy from the overlay model is lower than the second accuracy of the base model), returning to the step T8) (Bogorad, [0006]: “where the overlay model contributes below a threshold amount to the ensemble model predictions; and retraining, with the one or more processors, the overlay model with the second dataset”. Which shows retraining the overlay model is below a threshold amount); or
Coffman and Bogorad are considered to be analogous art because they are directed to multiple machine learning models management. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method and system for predicting manufacturing index with classification accuracy (as taught by Coffman) to include when the first accuracy is lower than the second accuracy, retraining the first model (as taught by Bogorad) because the combination provides an improvement to machine learning models accuracy (Bogorad, [0025]). Additionally, Coffman already teaches classification accuracy, as PHOSITA would know, classification accuracy is a common concern for training machine learning models.
Claim(s) 11, 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Coffman, in view of Lillestolen (US 2021/0181694 A1, 2019).
Regarding claim 11, Coffman teaches The method of claim 4,
However, Coffman does not appear to explicitly teach second AI model is a linear regression model; though Coffman does teach logistic regression.
Pertaining to the same field of endeavor, Lillestolen teaches
wherein the second AI model is a linear regression model (Lillestolen, [0052]: “the third machine learning model is a linear regression machine learning model”).
Coffman and Lillestolen are considered to be analogous art because they are directed to multiple machine learning models. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method and system for predicting manufacturing index (as taught by Coffman) to include second AI model is a linear regression model (as taught by Lillestolen) because the combination provides an improvement machine learning models management (Lillestolen, [0003]). Further, PHOSITA would know it is common practice to compare various machine learning model performances.
Regarding claim 12, Coffman teaches The method of claim 1, wherein the first AI model is a support vector regression (SVR) model (Lillestolen, [0052]: “the second machine learning model is a support vector regression (SVR) machine learning model”).
However, Coffman does not appear to explicitly teach first AI model is a support vector regression; though Coffman does teach logistic regression.
Pertaining to the same field of endeavor, Lillestolen teaches
wherein the second AI model is a linear regression model (Lillestolen, [0052]: “the third machine learning model is a linear regression machine learning model”).
Coffman and Lillestolen are considered to be analogous art because they are directed to multiple machine learning models. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method and system for predicting manufacturing index (as taught by Coffman) to include first AI model is a support vector regression (as taught by Lillestolen) because the combination provides an improvement machine learning models management (Lillestolen, [0003]). Further, PHOSITA would know it is common practice to compare various machine learning model performances.
Claim(s) 14, 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Coffman, in view of Armstrong (“Tech Tip: Inserting Flat Patterns into Drawings”, 2018).
Regarding claim 14, Coffman teaches The method of claim 1,
However, Coffman does not appear to explicitly teach stitching multiple perspective views. One with ordinary skill in the art would know it is a common feature of CAD software to convert the creating 3D object into a flat development drawing.
Pertaining to the same field of endeavor, Armstrong teaches
further comprising stitching multiple perspective views (Armstrong, pg 3, “Clicking this option adds the flat patterns to the list of insertable selections for your drawing view”. “Insertable selections for your drawing view” is being interpreted as having multiple perspective views”. Inserting the selections into the flat development drawing on pg 4 is being interpreted as “stitching”) of the product into the flat development drawing (Armstrong, pg 4, “flat pattern views”, and the image showing the flat development drawing, is being interpreted as involving “flat development drawing) before the step P1).
Coffman and Armstrong are considered to be analogous art because they are directed to image processing for CAD models. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method and system for predicting manufacturing index (as taught by Coffman) to include stitching multiple perspectives into a flat development drawing (as taught by Armstrong) because the combination provides an improvement to the production of CAD products (Coffman, column 1, lines 52-55). Further, converting CAD drawings into flat development drawings is a common feature in CAD software, as one with ordinary skill in the art would know.
Regarding claim 18, Coffman teaches The second device of claim 17, further comprising:
However, Coffman does not appear to explicitly teach stitching multiple perspective views. One with ordinary skill in the art would know it is a common feature of CAD software to convert the creating 3D object into a flat development drawing.
Pertaining to the same field of endeavor, Armstrong teaches
a second processing unit (Armstrong, pg 1, “Onshape”, one with ordinary skill in the art would know Onshape is a cloud CAD software service. Cloud service is being interpreted as involving at least a second processing unit) coupled to the image capturing unit and the communication unit (Armstrong, pg 1, “Onshape”, one with ordinary skill in the art would know Onshape is a cloud CAD software service, which requires a communication unit to communicate with the cloud service; along with the image capturing unit, otherwise, no image could be seen), and configured to stitch (Armstrong, pg 3, “flat pattern views” and the image shown, which shows the user can stitch together multiple views onto the drawing) multiple perspective views (Armstrong, pg 2 image, which shows “Sheet Metal Flat Patterns”, the plurality of perspective views shows are being interpreted as “multiple perspective views”) of the product into the flat development drawing (Armstrong, pg 3, “flat pattern views” is being interpreted as involving “flat development drawing”, also viewable in the image);
wherein the image capturing unit is configured to obtain the multiple perspective views of the product (Armstrong, pg 4, “Creating views of your sheet metal parts in Onshape is easy”, which is being interpreted as “multiple perspective views of the product”. Further, one with ordinary skill in the art would know that flat pattern drawing would be output, which involves the image capturing unit).
Coffman and Armstrong are considered to be analogous art because they are directed to image processing for CAD models. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method and system for predicting manufacturing index (as taught by Coffman) to include stitching multiple perspectives into a flat development drawing (as taught by Armstrong) because the combination provides an improvement to the production of CAD products (Coffman, column 1, lines 52-55). Further, converting CAD drawings into flat development drawings is a common feature in CAD software, as one with ordinary skill in the art would know.
Claim(s) 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Coffman, in view of Borzel (“Case Study on Model-based Application of Machine Learning using Small CAD Databases for Cost Estimation”, 2019).
Regarding claim 15, Coffman teaches The method of claim 1,
However, Coffman does not appear to explicitly total number of molds.
Pertaining to the same field of endeavor, Borzel teaches
wherein the manufacturing index is a total number of processes or a total number of molds (Borzel, pg 263, Section 5, ¶1, reproduced below:
PNG
media_image11.png
482
580
media_image11.png
Greyscale
. “Predicted number of mould nests” is being interpreted as “total number of molds”. Examiner notes this limitation is part of an “or” statement, thus only one possibility will be considered.).
Coffman and Borzel are considered to be analogous art because they are directed to predicting manufacturing index for CAD models. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method and system for predicting manufacturing index (as taught by Coffman) to total number of molds (as taught by Borzel) because the combination provides an improvement price quotation speeds on CAD products (Borzel, Abstract).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Serrat et al ("Cost estimation of custom hoses from STL files and CAD drawings", 2013) discloses machine learning models to predict manufacturing processes for cost estimation of STL files (which may include flat development drawings), and CAD drawings (with multiple perspectives).
Brede et al ("Part Based Mold Quotation With Methods Of Machine Learning", 2020) discloses machine learning model for predicting manufacturing index (interpreted from part based mold quotation)
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JOHNNY B DUONG whose telephone number is (571)272-1358. The examiner can normally be reached Monday - Thursday 10a-9p (ET).
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, Matthew Bella can be reached at (571)272-7778. 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.
/J.B.D./Examiner, Art Unit 2667
/Soo Shin/Primary Examiner, Art Unit 2667
Prosecution Insights