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 .
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.
Claims 1 - 20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception without significantly more.
Regarding Claim 1:
Step 1 – Is the claim to a process, machine, manufacture, or composition of matter?
Yes
Step 2A – Prong 1 – Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Yes, the claim recites the abstract ideas of:
gathering a training dataset comprising digital designs for a plurality of orthodontic aligners, wherein each digital design is associated with a respective orthodontic aligner of the plurality of orthodontic aligners, and wherein each digital design comprises metadata indicating whether the associated respective orthodontic aligner was damaged during manufacturing of the associated respective orthodontic aligner; This limitation is directed to the abstract idea of a mental process as gathering data is analogous to evaluation and judgment, which can be performed by the human mind, or by a human using pen and paper (see MPEP 2106.04(a)(2) III. C.).
Step 2A – Prong 2 – Does the claim recite additional elements that integrate the judicial exception into a practical application? – No, there are no additional elements that integrate the judicial exception into a practical application.
training the machine learning model using the training dataset, wherein the machine learning model is trained to process data from a digital design for an orthodontic aligner and to output a probability that the orthodontic aligner associated with the digital design will be damaged during manufacturing of the orthodontic aligner. The claim further recites using a machine learning model and training data. However, using machine learning merely provides instructions to apply the mathematical concept and therefore does not integrate the judicial exception into a practical application. The claim does not improve the functioning of a computer or another technology (MPEP 2106.05(f)).
Step 2B – Does the claim recite any additional elements that amount to significantly more than the judicial exception? – No, there are no additional elements that amount to significantly more than the judicial exception.
training the machine learning model using the training dataset, wherein the machine learning model is trained to process data from a digital design for an orthodontic aligner and to output a probability that the orthodontic aligner associated with the digital design will be damaged during manufacturing of the orthodontic aligner. The additional elements, machine learning model and training data, do not amount to significantly more than the abstract idea. A machine learning model merely provides instructions to apply the mathematical concept. The claim does not improve the functioning of a computer or another technology (MPEP 2016.04(d)(1)).
Step 2A Prong Two and Step 2B:
Thus, the judicial exception is not integrated into a practical application (see MPEP 2106.04(d) I.), failing step 2A prong 2. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception under step 2B. The claim is ineligible.
Regarding Claim 2:
Step 1 – Is the claim to a process, machine, manufacture, or composition of matter?
Yes
Step 2A – Prong 1 – Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Claim 2 does not recite abstract ideas other than the ones recited at claim 1.
Step 2A – Prong 2 – Does the claim recite additional elements that integrate the judicial exception into a practical application? – No, there are no additional elements that integrate the judicial exception into a practical application.
one or more of the digital designs comprises metadata indicating a location of damage that occurred for the associated respective orthodontic aligner. The limitation that the digital designs comprising the metadata, which used in performing the abstract idea constitutes insignificant extra-solution activity and therefore does not integrate the judicial exception into a practical application (MPEP 2106.05(g)).
Step 2B – Does the claim recite any additional elements that amount to significantly more than the judicial exception? – No, there are no additional elements that amount to significantly more than the judicial exception.
one or more of the digital designs comprises metadata indicating a location of damage that occurred for the associated respective orthodontic aligner. This limitation specifying the digital designs comprising the metadata does not amount to significantly more than the abstract idea. The limitation merely describes the type of data obtained and/or represents well-understand, routine, and conventional activity in the field of data processing (MPEP 2106.05(d))
Step 2A Prong Two and Step 2B:
Thus, the judicial exception is not integrated into a practical application (see MPEP 2106.04(d) I.), failing step 2A prong 2. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception under step 2B. The claim is ineligible.
Regarding Claim 3:
Step 1 – Is the claim to a process, machine, manufacture, or composition of matter?
Yes
Step 2A – Prong 1 – Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Claim 3 does not recite abstract ideas other than the ones recited at claim 1.
Step 2A – Prong 2 – Does the claim recite additional elements that integrate the judicial exception into a practical application? – No, there are no additional elements that integrate the judicial exception into a practical application.
receiving the digital designs for the plurality of orthodontic aligners, wherein the digital designs for the plurality of orthodontic aligners comprise at least one of digital models of the plurality of orthodontic aligners or digital models of molds used to manufacture the plurality of orthodontic aligners; This limitation recites as an insignificant extra solution activity, as receiving the digital designs, under BRI, is mere data gathering per MPEP 2106.05(g)(3).
receiving information indicating one or more of the plurality of orthodontic aligners that were damaged during manufacturing; This limitation recites as an insignificant extra solution activity, as receiving information, under BRI, is mere data gathering per MPEP 2106.05(g)(3).
for each digital design associated with an orthodontic aligner that was damaged during manufacturing, adding the metadata to the digital design indicating that the orthodontic aligner was damaged during manufacturing. This limitation recites as an insignificant extra solution activity, as adding data into the digital designs, under BRI, is mere data gathering per MPEP 2106.05(g)(3).
Step 2B – Does the claim recite any additional elements that amount to significantly more than the judicial exception? – No, there are no additional elements that amount to significantly more than the judicial exception.
receiving the digital designs for the plurality of orthodontic aligners, wherein the digital designs for the plurality of orthodontic aligners comprise at least one of digital models of the plurality of orthodontic aligners or digital models of molds used to manufacture the plurality of orthodontic aligners; This limitation is directed to receiving data, which the courts have recognized as well-understood, routine, conventional activity when they are claimed at a high level of generality or as insignificant extra-solution activity [see MPEP 2106.05(d) II. i] and therefore fails to amount to significantly more than the judicial exception.
receiving information indicating one or more of the plurality of orthodontic aligners that were damaged during manufacturing; This limitation is directed to receiving data, which the courts have recognized as well-understood, routine, conventional activity when they are claimed at a high level of generality or as insignificant extra-solution activity [see MPEP 2106.05(d) II. i] and therefore fails to amount to significantly more than the judicial exception.
for each digital design associated with an orthodontic aligner that was damaged during manufacturing, adding the metadata to the digital design indicating that the orthodontic aligner was damaged during manufacturing. This limitation is directed to receiving data, which the courts have recognized as well-understood, routine, conventional activity when they are claimed at a high level of generality or as insignificant extra-solution activity [see MPEP 2106.05(d) II. i] and therefore fails to amount to significantly more than the judicial exception.
Step 2A Prong Two and Step 2B:
Thus, the judicial exception is not integrated into a practical application (see MPEP 2106.04(d) I.), failing step 2A prong 2. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception under step 2B. The claim is ineligible.
Regarding Claim 4:
Step 1 – Is the claim to a process, machine, manufacture, or composition of matter?
Yes
Step 2A – Prong 1 – Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Yes, the claim recites the abstract ideas of:
extracting a plurality of characteristics of the associated respective orthodontic aligner from the digital design, the plurality of characteristics comprising at least one of geometrical characteristics, clinical characteristics or treatment related characteristics that are represented as structured or tabular data; This limitation is directed to the abstract idea of a mental process as extracting characteristics is analogous to evaluation and judgment, which can be performed by the human mind, or by a human using pen and paper (see MPEP 2106.04(a)(2) III. C.).
selecting a subset of the plurality of characteristics; This limitation is directed to the abstract idea of a mental process as selecting a subset of plurality of characteristics is analogous to evaluation and judgment, which can be performed by the human mind, or by a human using pen and paper (see MPEP 2106.04(a)(2) III. C.).
generating an embedding for the digital design based on the subset of the plurality of characteristics, wherein the training dataset comprises embeddings for the digital designs for the plurality of orthodontic aligners. This limitation is directed to the abstract idea of a mental process as generating an embedding is analogous to evaluation and judgment, which can be performed by the human mind, or by a human using pen and paper (see MPEP 2106.04(a)(2) III. C.). Also, this limitation is directed to the abstract idea of a mathematical concepts, as generating an embedding is analogous to a mathematical calculation (see MPEP 2106.04(a)(2) I. C.)
Step 2A – Prong 2 – Does the claim recite additional elements that integrate the judicial exception into a practical application? – No, there are no additional elements that integrate the judicial exception into a practical application.
the digital designs for the plurality of orthodontic aligners comprise at least one of digital models of the plurality of orthodontic aligners or digital models of molds used to manufacture the plurality of orthodontic aligners, the method further comprising performing the following for each digital design of the digital designs. The limitation that the digital designs comprising a model or a method, which used in performing the abstract idea constitutes insignificant extra-solution activity and therefore does not integrate the judicial exception into a practical application (MPEP 2106.05(g))
Step 2B – Does the claim recite any additional elements that amount to significantly more than the judicial exception? – No, there are no additional elements that amount to significantly more than the judicial exception.
the digital designs for the plurality of orthodontic aligners comprise at least one of digital models of the plurality of orthodontic aligners or digital models of molds used to manufacture the plurality of orthodontic aligners, the method further comprising performing the following for each digital design of the digital designs. This limitation specifying the digital designs comprising a model or a method does not amount to significantly more than the abstract idea. The limitation merely describes the type of data obtained and/or represents well-understand, routine, and conventional activity in the field of data processing (MPEP 2106.05(d))
Step 2A Prong Two and Step 2B:
Thus, the judicial exception is not integrated into a practical application (see MPEP 2106.04(d) I.), failing step 2A prong 2. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception under step 2B. The claim is ineligible.
Regarding Claim 5:
Step 1 – Is the claim to a process, machine, manufacture, or composition of matter?
Yes
Step 2A – Prong 1 – Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Claim 5 does not recite abstract ideas other than the ones recited at claim 1.
Step 2A – Prong 2 – Does the claim recite additional elements that integrate the judicial exception into a practical application? – No, there are no additional elements that integrate the judicial exception into a practical application.
periodically repeating the gathering and the training using digital designs for recently manufactured orthodontic aligners. This limitation is directed to merely manipulating data in an iterative manner. Such activity constitutes insignificant extra-solution activity and therefore, it does not impose meaningful limits on the claim, considered an insignificant extra solution activity. (MPEP 2105(g)(2))
Step 2B – Does the claim recite any additional elements that amount to significantly more than the judicial exception? – No, there are no additional elements that amount to significantly more than the judicial exception.
periodically repeating the gathering and the training using digital designs for recently manufactured orthodontic aligners. This limitation is proper to state it as well-understood, routine and conventional (WURC) since repeating the operations such as gathering and training… as being a clear court example of “Performing repetitive calculations” for being WURC per (MPEP 2106.05 (d) II ii).
Step 2A Prong Two and Step 2B:
Thus, the judicial exception is not integrated into a practical application (see MPEP 2106.04(d) I.), failing step 2A prong 2. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception under step 2B. The claim is ineligible.
Regarding Claim 6:
Step 1 – Is the claim to a process, machine, manufacture, or composition of matter?
Yes
Step 2A – Prong 1 – Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Claim 6 does not recite abstract ideas other than the ones recited at claim 1.
Step 2A – Prong 2 – Does the claim recite additional elements that integrate the judicial exception into a practical application? – No, there are no additional elements that integrate the judicial exception into a practical application.
the machine learning model is a random forest classifier or a gradient boosted decision tree classifier. This limitation recites description that the machine learning model is a random forest classifier or a gradient boosted decision tree. Therefore, this limitation amounts to merely indicating a field of use or technological environment [see MPEP 2106.05(h)] and fails to integrate the judicial exception into a practical application.
Step 2B – Does the claim recite any additional elements that amount to significantly more than the judicial exception? – No, there are no additional elements that amount to significantly more than the judicial exception.
the machine learning model is a random forest classifier or a gradient boosted decision tree classifier. This limitation recites description that the machine learning model is a random forest classifier or a gradient boosted decision tree. Therefore, this limitation amounts to merely indicating a field of use or technological environment [see MPEP 2106.05(h)] and therefore fails to amount to significantly more than the judicial exception.
Step 2A Prong Two and Step 2B:
Thus, the judicial exception is not integrated into a practical application (see MPEP 2106.04(d) I.), failing step 2A prong 2. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception under step 2B. The claim is ineligible.
Regarding Claim 7:
Step 1 – Is the claim to a process, machine, manufacture, or composition of matter?
Yes
Step 2A – Prong 1 – Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Yes, the claim recites the abstract ideas of:
determining whether any probable points of damage for the orthodontic aligner are predicted based on a result of the processing; This limitation is directed to the abstract idea of a mental process as determining whether any probable point of the damage is analogous to evaluation and judgment, which can be performed by the human mind, or by a human using pen and paper (see MPEP 2106.04(a)(2) III. C.).
Step 2A – Prong 2 – Does the claim recite additional elements that integrate the judicial exception into a practical application? – No, there are no additional elements that integrate the judicial exception into a practical application.
processing additional digital designs for a plurality of additional orthodontic aligners using a first numerical simulation that simulates removal of an orthodontic aligner from a mold of a dental arch of a patient or a second numerical simulation that simulates loading around weak spots in the orthodontic aligner; The claim further recites processing digital designs and using simulations. However, processing digital designs and using simulations merely provides instructions to apply the mathematical concept and therefore does not integrate the judicial exception into a practical application. The claim does not improve the functioning of a computer or another technology (MPEP 2106.05(f)).
adding information about the probable points of damage as metadata to the digital design; This limitation recites as an insignificant extra solution activity, as adding information, under BRI, is mere data gathering per MPEP 2106.05(g)(3).
adding the additional digital designs for the plurality of additional orthodontic aligners to the training dataset. This limitation recites as an insignificant extra solution activity, as adding digital designs to the dataset, under BRI, is mere data gathering per MPEP 2106.05(g)(3).
Step 2B – Does the claim recite any additional elements that amount to significantly more than the judicial exception? – No, there are no additional elements that amount to significantly more than the judicial exception.
processing additional digital designs for a plurality of additional orthodontic aligners using a first numerical simulation that simulates removal of an orthodontic aligner from a mold of a dental arch of a patient or a second numerical simulation that simulates loading around weak spots in the orthodontic aligner; The additional elements, digital designs and simulations, do not amount to significantly more than the abstract idea. Digital designs and simulations, merely provides instructions to apply the mathematical concept. The claim does not improve the functioning of a computer or another technology (MPEP 2016.04(d)(1)).
adding information about the probable points of damage as metadata to the digital design; This limitation is directed to receiving data, which the courts have recognized as well-understood, routine, conventional activity when they are claimed at a high level of generality or as insignificant extra-solution activity [see MPEP 2106.05(d) II. i] and therefore fails to amount to significantly more than the judicial exception.
adding the additional digital designs for the plurality of additional orthodontic aligners to the training dataset. This limitation is directed to receiving data, which the courts have recognized as well-understood, routine, conventional activity when they are claimed at a high level of generality or as insignificant extra-solution activity [see MPEP 2106.05(d) II. i] and therefore fails to amount to significantly more than the judicial exception.
Step 2A Prong Two and Step 2B:
Thus, the judicial exception is not integrated into a practical application (see MPEP 2106.04(d) I.), failing step 2A prong 2. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception under step 2B. The claim is ineligible.
Regarding claims 8 - 14
Claims 8 - 14 recites analogous limitations to claims 1 - 7 (respectively) and therefore they are rejected on the same grounds as claims 1 - 7.
Regarding claims 15 - 19
Claims 15 - 19 recites analogous limitations to claims 1-5 (respectively) and therefore they are rejected on the same grounds as claims 1-5.
Regarding claim 20
Claim 20 recites analogous limitations to claim 7 (respectively) and therefore they are rejected on the same grounds as claim 7.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or non-obviousness.
Claim(s) 1 ,3 ,5, 8, 10, 12, 15, 17 and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kuo (US20140142897A1 Pub. Date 05/22/2014, by Kuo et al - hereinafter Kuo) in view of Su (WO2017194281A1, Pub. Date 11/16/2017, by Su et al - hereinafter Su).
Referring to Claim 1, Kuo teaches:
gathering a training dataset comprising digital designs for a plurality of orthodontic aligners, wherein each digital design is associated with a respective orthodontic aligner of the plurality of orthodontic aligners, and wherein each digital design comprises metadata indicating whether the associated respective orthodontic aligner was damaged during manufacturing of the associated respective orthodontic aligner; See Kuo at [0003]:” Such appliances may utilize a shell of material having resilient properties, referred to as an ‘aligner’ that generally conforms to a patients teeth but is slightly out of alignment with the then current tooth configuration.” And see Kuo at [0035]:” For example, a treatment plan can include the use of a set of appliances, created according to models described herein.” Examiner interprets a set of appliances as equivalent as a plurality of orthodontic aligners. Then, see Kuo at [0059]:” The physical dental mold can be manufactured by downloading a Computer-aided Design (CAD) digital dental model to a rapid prototyping process. Such as, for example, a Computer-aided manufacturing (CAM) milling, Stereolithography, and/or photolithography.” Examiner interprets the CAD digital dental model as equivalent to the digital design as claimed, and manufacturing a physical dental mold by downloading a CAD digital dental model as equivalent as a digital design is associated with an orthodontic aligner. Also, see Kuo at [0020]:” Reduced stress on the semi-rigid dental appliance can result in less breakage and/or tears of the dental appliance during its use and/or during its manufacture when the appliance is being inserted and removed from the reference model of the teeth.” Kuo discloses the breakage and tears of dental appliance during the manufacture.
However, Kuo fails to teach: gathering a training dataset, and each digital design comprises metadata indicating the damage.
Su teaches gathering a training dataset, and each digital design comprises metadata indicating the damage. See Su at [0059]:” Determinations 730A, 730B, ... are made based on the characteristics 710A, 710B, ... , as to whether the hot spots 700A, 700B are defective, respectively, under the process conditions 720A, 720B, ... , respectively. … … The characteristics 750A, 750B, ... may be obtained by 20 simulation, e.g., directly or measured from a simulated image of the hot spots 700A, 700B, ……The characteristics 740A, 740B, ... , the determinations 730A, 730B, ... , and the characteristics 750A, 750B, ... are included in a training set 770 as samples 760A, 760B, ... , respectively. In procedure 780, a machine learning model 790 is trained using the training set 770.” Examiner interprets determination based on the characteristics as to whether the hot spots are defective as equivalent as the metadata indicating the damage; Determinations and characteristics are included in a training set as equivalent as the training dataset comprising the metadata; Obtaining the characteristics by simulation as equivalent as gathering the training dataset. It would have been obvious to apply Su’s training dataset organization to Kuo’s aligner-manufacturing information. Kuo teaches a set of appliances created through a CAD-digital-model-to-mold procesIs, while Su teaches gathering corresponding item-specific information as samples in a training set. Applying Su’s organization would have gathered Kuo’s CAD digital models into a training dataset while maintaining the association between each model and the respective aligner manufactured from it. Accordingly, Kuo as modified by Su would have resulted in the recited training dataset.
training the machine learning model using the training dataset, wherein the machine learning model is trained to process data from a digital design for an orthodontic aligner and to output a probability that the orthodontic aligner associated with the digital design will be damaged during manufacturing of the orthodontic aligner.
As discussed above, Kuo teaches the digital design for the orthodontic aligner and the orthodontic aligner associated with the digital design was damaged during manufacturing of the orthodontic aligner. However, Kuo fails to teach training the machine learning model using the training dataset, wherein the machine learning model is trained to process data from a digital design and to output a probability of damage.
Su teaches training the machine learning model using the training dataset, wherein the machine learning model is trained to process data from a digital design and to output a probability of damage. See Su at [0059]:” In procedure 780, a machine learning model 790 is trained using the training set 770.” Examiner interprets using training set to train the model as equivalent as training the machine learning model using the training dataset as claimed; And see Su at [0067 - 0068]: “In an embodiment, the machine learning input has three parts: design data extracted from the hot spot patterns, simulation data for the hot spot patterns, and process condition variables. … Adding design data and/or simulation data has two functions: differentiating those hot spot patterns used in the training stage and predicting those “unseen” hot spot patterns in the test stage. … Any machine learning algorithm (SVM, logistic regression, KNN, AdaBoost, etc.) that gives good prediction result can be used. The output of the machine learning can be Y/N, defect probability, and/or defect size.” Examiner interprets design data extracted from the hot spot patterns, simulation data and process condition variables as equivalent to the data from a digital design; the output of the machine learning can be the defect probability as equivalent as outputting a probability of damage. It would have been obvious to apply Su’s machine-learning technique to the training data set discussed above. Kuo teaches CAD digital models used to manufacture aligners and possible breakage or tearing during manufacture, while Su teaches that training a machine-learning model to process design data and output a defect probability. Applying Su’s technique would have trained the model to process data from each Kuo CAD digital model and output the probability that the corresponding aligner would be damaged during manufacture, thereby allowing damage-prone designs to be identified before manufacture. Accordingly, Kuo as modified by Su would have resulted in the recited trained machine-learning model.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Kuo with the above teachings of Su by the digital design for the orthodontic aligner and the orthodontic aligner associated with the digital design damaged during manufacturing, as taught by Kuo; gathering data, training the model and outputting a probability of the damage, as taught by Su. The modification would have been obvious because one of ordinary skill in art would be motivated to use machine learning to determine the defective under the process condition, as suggested by Su. See Su at [0012]: “…obtaining characteristics of each of the process conditions; obtaining characteristics of each of the hot spots; and training, by a hardware computer system, a machine learning model using a training set comprising a plurality of samples, wherein each of the sample has a feature vector comprising the characteristics of one of the process conditions and the characteristics of one of the hot spots, the feature vector further comprising a label comprising whether that hot spot is defective under that process condition.”
Referring to Claim 3, Kuo- Su teaches the method of claim 1. Kuo further teaches:
receiving the digital designs for the plurality of orthodontic aligners, wherein the digital designs for the plurality of orthodontic aligners comprise at least one of digital models of the plurality of orthodontic aligners or digital models of molds used to manufacture the plurality of orthodontic aligners; See Kuo at [0083]: “The input/output interfaces 470 can receive executable instructions and/or data, storable in the data storage device (e.g., memory), representing a digital dental model of a patient’s dentition.” And see Kuo at [0059]:” The dental appliance 206 can be made, for example, by thermal-forming a piece of plastic over a physical dental mold. The physical dental mold, for instance, can represent an incremental position to which a patient’s teeth are to be moved. The physical dental mold can be manufactured by downloading a Computer-aided Design (CAD) digital dental model to a rapid prototyping process. Such as, for example, a Computer-aided manufacturing (CAM) milling, Stere olithography, and/or photolithography.” Kuo expressly teaches receiving data representing a digital dental model. Kuo also discloses using a digital dental model to manufacture a physical dental mold, and further to make a dental appliance. The limitation states the model alternatives disjunctively (“or”); Kuo’s receiving digital model used to manufacture the physical mold satisfies the digital-model-of-the-mold alternative.
However, Kuo fails to teach:
receiving information indicating one or more of the plurality of orthodontic aligners that were damaged during manufacturing; for each digital design associated with an orthodontic aligner that was damaged during manufacturing, adding the metadata to the digital design indicating that the orthodontic aligner was damaged during manufacturing.
Su teaches:
receiving information indicating one or more of the plurality of orthodontic aligners that were damaged during manufacturing; As discussed in claim 1, Su teaches gathering a training dataset comprising the digit designs, and further comprising the metadata, which is as equivalent as receiving information as claimed. It would have been obvious to apply Su’s training dataset organization to Kuo’s aligner-manufacturing information as discussed in claim 1. Thus, Kuo – Su teaches the limitation.
for each digital design associated with an orthodontic aligner that was damaged during manufacturing, adding the metadata to the digital design indicating that the orthodontic aligner was damaged during manufacturing. As discussed in claim 1, Su teaches gathering a training dataset comprising the digit designs, and further comprising the metadata, which is as equivalent as adding the metadata to the digital design as claimed. It would have been obvious to apply Su’s training dataset organization to Kuo’s aligner-manufacturing information as discussed in claim 1. Thus, Kuo – Su teaches the limitation.
The same motivation that was utilized for combining Kuo with Su as set forth in claim 1 is equally applicable to claim 3.
Referring to Claim 5, Kuo- Su teaches the method of claim 1. Su also teaches:
periodically repeating the gathering and the training using digital designs for recently manufactured orthodontic aligners. See Su at [0066]: “In an embodiment, such a method can be extended to a realtime mode, which means verification data is continuously collected and 20 the model is updated in time by using an online learning technique).” Su teaches the real time mode continuously gathering data and updating the model, which is as equivalent as repeating the gathering and training as claimed.
The same motivation that was utilized for combining Kuo with Su as set forth in claim 1 is equally applicable to claim 5.
Referring to Claims 8 and Claim 15, these claims are rejected on the same basis as claim 1, mutatis mutandis, since they are analogous claims.
Referring to Claims 10 and Claim 17, these claims are rejected on the same basis as claim 3, mutatis mutandis, since they are analogous claims.
Referring to Claims 12 and Claim 19, these claims are rejected on the same basis as claim 5, mutatis mutandis, since they are analogous claims.
Claim(s) 2, 9 and 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kuo -Su in view of Newcomer (US20080307327A1, Pub. Date 12/11/2008, by Newcomer et al - hereinafter Newcomer).
Referring to Claims 2, Kuo – Su teaches the method of claim 1.
However, Kuo – Su fails to teach: one or more of the digital designs comprises metadata indicating a location of damage that occurred for the associated respective orthodontic aligner.
Newcomer teaches:
one or more of the digital designs comprises metadata indicating a location of damage that occurred for the associated respective orthodontic aligner. See Newcomer at [0039 -0040]: “These defects may be stored for later review using defect entry process 302. … In these illustrative examples, defect information 304 contains an identification of the defect, as well as the location of the defect. The identification of the defect may include a unique identifier as well as information described in the defect that has occurred.” Newcomer teaches storing information describing an identified defect and its location. Combined with “wherein each digital design comprises metadata indicating whether the associated respective orthodontic aligner was damaged”, as taught by Kuo -Su in claim 1, the limitation is taught.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Kuo - Su with the above teachings of Newcomer by applying machine learning model to digital aligner, as taught by Kuo -Su; recording an actual physical defect and its location as information associated with corresponding model, as taught by Newcomer. The modification would have been obvious because one of ordinary skill in the art would be motivated to present a set of defects using a three-dimensional presentation, as suggested by Newcomer. See Newcomer at [0009]:” In response to a request to present a set of defects using a three dimensional presentation, information is retrieved for the set of defects from a database, wherein the information includes an identification of a defect and a location of the defect in the system.”
Referring to Claims 9 and Claim 16, these claims are rejected on the same basis as claim 2, mutatis mutandis, since they are analogous claims.
Claim(s) 4, 6, 11, 13 and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kuo -Su in view of Coffman (US10061300B1, Pub. Date 08/28/2018, by Coffman et al - hereinafter Coffman).
Referring to Claims 4, Kuo – Su teaches the method of claim 1.
However Kuo – Su fails to teach: extracting a plurality of characteristics of the associated respective orthodontic aligner from the digital design, the plurality of characteristics comprising at least one of geometrical characteristics, clinical characteristics or treatment related characteristics that are represented as structured or tabular data; selecting a subset of the plurality of characteristics; generating an embedding for the digital design based on the subset of the plurality of characteristics, wherein the training dataset comprises embeddings for the digital designs for the plurality of orthodontic aligners.
Coffman teaches:
extracting a plurality of characteristics of the associated respective orthodontic aligner from the digital design, the plurality of characteristics comprising at least one of geometrical characteristics, clinical characteristics or treatment related characteristics that are represented as structured or tabular data; See Coffman at [Column 8, line 66]: “A PSMP server (e.g., PSMP server 109 shown in FIG. 1 and FIG. 2) can receive a CAD file or other suitable electronic file with a design of a physical model at 301. In some instances, a CAD file or other suitable electronic file can include data points corresponding to a mesh scheme of the digital model.” Also see Coffman at [Column 9, line 59]: “An instance of a mesh is analyzed at 305 to determine physical and/or geometric attributes of the physical model represented in an electronic file. Example of attributes calculated from a mesh scheme include a data value corresponding to a volume of the physical object, data values corresponding to a surface areas of the physical object, 3-tuple data structures including a length value, a width value, and a height value associated with a prism or bounding box enclosing the digital model, ...” Coffman discloses receiving a CAD file containing a digital model, extracting mesh data from that file, and calculating geometric attributes as numerical values and 3-tuple data structures, including volume, surface area, length, width, and height. It would have been obvious to apply that known CAD preprocessing to each Kuo’s mold model incorporated from claim 3. Because the aligner is formed over the mold, the extracted mold-model geometry describes geometrical characteristics of the associated aligner; Coffman’s numerical and 3-tuple structures satisfy the claimed structured-or-tabular-data requirement.
selecting a subset of the plurality of characteristics; See Coffman at [Column 16, line 36]: “PSMP server 109 generates, at 603, a training set by executing one or more operations over the corpus received at 601. The operations, executed at 603, include the selection of a minimum set of shape attributes that can be used by, for example, a classifier to differentiate among different shapes. In some instances, such a minimum set of shape attributes can be determined by eliminating shape attributes that are highly correlated and thus, redundant.” Coffman expressly teaches selecting a minimum set of shape attributes and obtaining that set by eliminating highly correlated and redundant attributes, which is as equivalent as selecting a subset of the plurality of characteristics as claimed.
generating an embedding for the digital design based on the subset of the plurality of characteristics, wherein the training dataset comprises embeddings for the digital designs for the plurality of orthodontic aligners. See Coffman at [Column 16, line 19]:” A PSMP server (e.g., PSMP server 109 shown in FIG. 1) can implement supervised, unsupervised, and /or reinforcement based machine learning models…” and Coffman at [Column 16, line 29]:”PSMP server 109 receives, at 601, a corpus of raw datasets. Each dataset in the corpus includes a labeled shape associated with an array data structure: the shapes can be 2D, 3D shapes or any other shape defined in other suitable dimension space. The array data structure stores a set of data values corresponding to geometric and / or physical attributes of such a shape …” Also, see Coffman at [Column 16, line 43]: “Accordingly, a dimensionality reduction process can be applied to compress the attributes onto a lower dimensionality subspace and advantageously, storage space can be minimized, resulting in the improvement or optimization of computation load used by the method. In some further instances, the attributes associated with a shape are scaled, for example, each selected attribute is expressed as a value ranging from [0 . . . 1] and/or a standard normal distribution with zero mean and unit variance.” Examiner interprets the dataset storing a set of data values corresponding to geometric attributes as equivalent the training dataset comprising embeddings. And the server 109 generating a training set by the operation of dimensionality reduction process and compressing the attributes onto a lower dimensionality subspace, which is as equivalent as generating an embedding based on the subset of the plurality of characteristics as is well known that in the art, a machine learning model is configured to receive an input embedding and process the same to output a resultant embedding.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Kuo - Su with the above teachings of Coffman by applying machine learning model to digital aligner, as taught by Kuo -Su; extracting characteristics and generating embeddings, as taught by Coffman. The modification would have been obvious because one of ordinary skill in the art would be motivated to provide objective, accurate, and consistent classifications and predictions regarding manufacturing processes, as suggested by Coffman. See Coffman at [Column 3, line 29]:” The subject technology provides objective, accurate, and consistent classifications and/or predictions regarding manufacturing processes, including estimated times, optimal costs, comparisons of fabrication materials, and other suitable information. The classifications and/or predictions are reliable; that is, assessments for the manufacture of similar products result in similar or equivalent outcomes. The subject technology operates in near real-time and thus, optimizes manufacturing process by decreasing overhead associated with human-based estimations.”
Referring to Claims 6, Kuo – Su teaches the method of claim 1.
However, it fails to teach:
the machine learning model is a random forest classifier or a gradient boosted decision tree classifier.
Coffman teaches:
the machine learning model is a random forest classifier or a gradient boosted decision tree classifier. See Coffman at [Column 2, line 17]:” FIG. 10 is a flowchart illustrating a method to build a random forest classifier machine learning model, according to an embodiment.” Coffman discloses a method to build a random forest classifier machine learning model, which satisfies the model is random forest classifier or decision tree classifier as claimed.
The same motivation that was utilized for combining Kuo - Su with Coffman as set forth in claim 4 is equally applicable to claim 6.
Referring to Claims 11 and Claim 18, these claims are rejected on the same basis as claim 4, mutatis mutandis, since they are analogous claims.
Referring to Claims 13, these claims are rejected on the same basis as claim 6, mutatis mutandis, since they are analogous claims.
Claim(s) 7, 14 and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kuo -Su in view of Chan - Park (NPL, “Simulation and Investigation of Factors Affecting High Aspect Ratio UV Embossing” Pub. Date 03/01/2005, by Chan - Park et al - hereinafter Chan).
Referring to Claims 7, Kuo – Su teaches method of claim 1.
Kuo – Su also teaches:
adding information about the probable points of damage as metadata to the digital design; As Examiner interprets in claim 1, Kuo-Su teaches “gathering a training dataset comprising digital designs for a plurality of orthodontic aligners… wherein each digital design comprises metadata indicating whether the associated respective orthodontic aligner was damaged” which is as equivalent as adding information as metadata to the digital design. Thus, Kuo – Su teaches the limitation.
and adding the additional digital designs for the plurality of additional orthodontic aligners to the training dataset. As discussed in the claim 1, Kuo - Su teaches “gathering a training dataset comprising digital designs for a plurality of orthodontic aligners” which is as equivalent as adding digital designs to the training dataset as claimed. Thus, Kuo - Su also teaches the limitation
However, it fails to teach:
processing additional digital designs for a plurality of additional orthodontic aligners using a first numerical simulation that simulates removal of an orthodontic aligner from a mold of a dental arch of a patient or a second numerical simulation that simulates loading around weak spots in the orthodontic aligner; for each digital design of the additional digital designs for the plurality of additional orthodontic aligners, performing the following comprising: determining whether any probable points of damage for the orthodontic aligner are predicted based on a result of the processing;
Chan teaches:
processing additional digital designs for a plurality of additional orthodontic aligners using a first numerical simulation that simulates removal of an orthodontic aligner from a mold of a dental arch of a patient or a second numerical simulation that simulates loading around weak spots in the orthodontic aligner; See Chan at [Page 2, mid - right]:” Finite element simulation was used to estimate the spatial distribution of stress experienced by the polymer, interface, and mold during demolding. The finite element software used was LUSAS 13.0 PC version.19 A model was built to represent the mold-polymer assembly to simulate the shrinkage effect and mold/polymer interaction. For ease of simulation, but without loss of generality, a plane strain assumption was employed.” Chan discloses the finite-element demolding technique: numerically modeling a polymer-and-mold assembly to determine the spatial distribution of stress in the polymer, interface, and mold during demolding. Also, as Examiner interprets in claim 1, Kuo teaches a plurality of stage-specific digital aligner designs and corresponding reference models representing a patient’s teeth, and further teaches that stress generated when an aligner is removed from the reference model during manufacture may cause breakage or tearing. Kuo expressly identifies removal-induced stress as a cause of manufacturing breakage or tearing, while Chan provides a known numerical technique for evaluating that same polymer-demolding problem. Although Chan is not directed to dentistry, it is reasonably pertinent to Kuo’s identified problem of avoiding polymer damage during removal from a mold. Applying the same analysis to each of Kuo’s additional stage-specific aligner designs would have predictably produced design-specific demolding-stress results. The rejection relies on the first recited alternative. Accordingly, the second alternative concerning loading around weak spots need not be reached.
for each digital design of the additional digital designs for the plurality of additional orthodontic aligners, performing the following comprising: determining whether any probable points of damage for the orthodontic aligner are predicted based on a result of the processing; As discussed above, Chan teaches generating a spatially resolved distribution of stress during polymer demolding and evaluating the simulated stress under a polymer-failure criterion. As Examiner interprets in claim 1, Kuo - Su identifies removal-induced stress as a cause of breakage or tearing of a dental appliance during manufacture; teaches obtaining simulation-derived characteristics for respective hot spots and making respective defect determinations based on those characteristics; also teaches obtaining simulation-derived characteristics for respective hot spots and making respective defect determinations based on those characteristics. Thus, the combination of Kuo–Su and Chan teach the limitation.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Kuo - Su with the above teachings of Chan by applying machine learning model to digital aligner, as taught by Kuo-Su; using numerical simulation that simulates removal of an orthodontic aligner from a mold and determining probable points of damage, as taught by Chan. The modification would have been obvious because one of ordinary skill in the art would be motivated to be commercially viable, fast, reproducible and simple for the microstructure products, and significant cost savings for macroscopic applications, as suggested by Chan. See Chan at [Page 1, mid - left]:” For microstructured products to be commercially viable, the patterning technique must be fast, reproducible, and simple. For macroscopic applications, plastic molding or replication techniques such as compression or injection molding offer significant cost savings over metal forming technologies.”
Referring to Claims 14 and 20, these claims are rejected on the same basis as claim 7, mutatis mutandis, since they are analogous claims.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JIAYUE MA whose telephone number is (571)272-9658. The examiner can normally be reached between 9 am to 5 pm.
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, David Yi can be reached at (571) 270-7519. 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.
/Jiayue Ma/
Examiner, Art Unit 2126
/DAVID YI/Supervisory Patent Examiner, Art Unit 2126
Prosecution Insights