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 .
DETAILED ACTION
This office action is in response to the claims filed on 04/29/2022.
Claims 1-14 are presented for examination.
Priority
The following claimed benefit is acknowledged: the instant application, filed 04/29/2022 claims priority from foreign application KR10-2021-0056211, filed 04/30/2021.
Information Disclosure Statement
The information disclosure statements (IDS) filed 00/00/0000 is in compliance with the provisions of 37 CFR 1.97 and 1.98. Accordingly, the information disclosure statement is being considered by the examiner.
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 1-14 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1 analysis:
In the instant case, the claims are directed to a method (claims 1-6), apparatus (claims 7-12) and computer-readable (claims 13-14). Thus, each of the claims falls within one of the four statutory categories (i.e., process, machine, manufacture, or composition of matter).
Step 2A analysis:
Based on the claims being determined to be within of the four categories (Step 1), it must be determined if the claims are directed to a judicial exception (i.e., law of nature, natural phenomenon, and abstract idea), in this case the claims fall within the judicial exception of an abstract idea. Specifically the abstract idea of “Mental Processes/Concepts performed in the human mind (including an observation, evaluation, judgment, opinion)” and mathematical concept.
The claim 1 recites:
Step 2A: prong 1 analysis:
-“ predicting properties of feed and products in a reformer” this is a mental process, the human mind can predict the properties of the fee and production in reformer, for example, the human can tell what are chemical included in the mixed oil, (Observation/Evaluation).
-“ predicting the properties of feed in the reformer” this is a mental process, as the human mind can predict what are the properties compounds needs to make the gas/fuel(observation/Evaluation).
-“ predicting the properties of products in the reformer” this is a mental process, as the human mind can predict what are the properties compounds in the gas (product), (observation/Evaluation).
-“ predicting the properties of feed being currently supplied to the reactor in real time” this is a mental process, the human mind can predict what are the properties compounds are supplied to the reactor (mixing product) in the real time, (Observation/Evaluation).
-“ predicting the properties of products being produced in the reactor in real time” this is a mental process, the human mind can predict what are the properties compounds are supplied to the reactor (gas product) in the real time, (Observation/Evaluation).
a) Step 2A: Prong 2 analysis:
-“ predicting the properties of feed being currently supplied to the reactor in real time by allowing a first prediction unit including the trained first prediction model to receive a current operating condition of the reactor in the reformer;” “ and predicting the properties of products being produced in the reactor in real time by allowing a second prediction unit including the trained second prediction model to receive the current operating condition and the predicted properties of feed.” This/these limitations is/are recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component (See MPEP 2106.05(f)).
b) Step 2B analysis:
- -“ predicting the properties of feed being currently supplied to the reactor in real time by allowing a first prediction unit including the trained first prediction model to receive a current operating condition of the reactor in the reformer;” “ and predicting the properties of products being produced in the reactor in real time by allowing a second prediction unit including the trained second prediction model to receive the current operating condition and the predicted properties of feed.” This/these limitations is/are recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component (See MPEP 2106.05(f)).
The claim 2 recites:
a) Step 2A: Prong 2 analysis:
-“ wherein the first prediction model is trained by using, as training data, experimental values for the properties of feed supplied to the reactor, a past operating condition of the reactor, and a difference in temperature between front and rear ends of the reactor.” This/these limitations is/are recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component (See MPEP 2106.05(f)).
b) Step 2B analysis:
- -“ wherein the first prediction model is trained by using, as training data, experimental values for the properties of feed supplied to the reactor, a past operating condition of the reactor, and a difference in temperature between front and rear ends of the reactor.” This/these limitations is/are recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component (See MPEP 2106.05(f)).
The claim 3 recites:
a) Step 2A: Prong 2 analysis:
-“ wherein the second prediction model is trained by using, as training data, experimental values for the properties of feed supplied to the reactor, a past operating condition of the reactor, a difference in temperature between front and rear ends of the reactor, and experimental values for the properties of products produced in the reactor.” This/these limitations is/are recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component (See MPEP 2106.05(f)).
b) Step 2B analysis:
-“ wherein the second prediction model is trained by using, as training data, experimental values for the properties of feed supplied to the reactor, a past operating condition of the reactor, a difference in temperature between front and rear ends of the reactor, and experimental values for the properties of products produced in the reactor.” This/these limitations is/are recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component (See MPEP 2106.05(f)).
The claim 4 recites:
a) Step 2A: Prong 2 analysis:
-“wherein the first prediction unit predicts a content of napthene and a content of paraffin contained in the feed being currently supplied to the reactor, respectively.” This/these limitations is/are recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component (See MPEP 2106.05(f)).
b) Step 2B analysis:
-“wherein the first prediction unit predicts a content of napthene and a content of paraffin contained in the feed being currently supplied to the reactor, respectively.” This/these limitations is/are recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component (See MPEP 2106.05(f)).
The claim 5 recites:
a) Step 2A: Prong 2 analysis:
-“ wherein the second prediction unit predicts a content of aromatics and a content of paraffin included in the product being produced in the reactor, respectively.” This/these limitations is/are recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component (See MPEP 2106.05(f)).
b) Step 2B analysis:
-“ wherein the second prediction unit predicts a content of aromatics and a content of paraffin included in the product being produced in the reactor, respectively.” This/these limitations is/are recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component (See MPEP 2106.05(f)).
The claim 6 recites:
a) Step 2A: Prong 2 analysis:
-“ wherein the current operating condition includes one or more of an operating temperature, an operating pressure, a feed flow rate, a circulating gas flow rate, and hydrogen purity of the reactor.” This/these limitation(s) is/are amount to no more than generally linking the use of a judicial exception to a particular technological environment or field of use (See MPEP 2106.05(h)). As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception and that it does not integrate the judicial exception into a practical application.
b) Step 2B analysis:
-“ wherein the current operating condition includes one or more of an operating temperature, an operating pressure, a feed flow rate, a circulating gas flow rate, and hydrogen purity of the reactor.” This/these limitation(s) is/are amount to no more than generally linking the use of a judicial exception to a particular technological environment or field of use. As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not amount to significantly more than the exception itself.
The claim 7 recites:
Step 2A: prong 1 analysis:
-“predicting properties of feed and products in a reformer” this is a mental process, the human mind can predict the properties of the fee and production in reformer, for example, the human can tell what are chemical included in the mixed oil, (Observation/Evaluation).
-“ to predict the properties of feed being currently supplied to a reactor in the reformer in real time” this is a mental process, the human mind can predict what are the properties compounds are supplied to the reactor (mixing product) in the real time, (Observation/Evaluation).
-“to predict the properties of products being produced in the reactor in real time” this is a mental process, the human mind can predict what are the properties compounds are supplied to the reactor (gas product) in the real time, (Observation/Evaluation).
a) Step 2A: Prong 2 analysis:
- “comprising: a first prediction unit configured”, “ by using a pre-trained first prediction model when a current operating condition of the reactor in the reformer is input”, “a second prediction unit configured”, “by using a pre-trained second prediction model when the current operating condition and the predicted properties of feed are input.” This/these limitations is/are recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component (See MPEP 2106.05(f)).
b) Step 2B analysis:
- “comprising: a first prediction unit configured”, “ by using a pre-trained first prediction model when a current operating condition of the reactor in the reformer is input”, “a second prediction unit configured”, “by using a pre-trained second prediction model when the current operating condition and the predicted properties of feed are input.” This/these limitations is/are recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component (See MPEP 2106.05(f)).
The claim 8 recites:
a) Step 2A: Prong 2 analysis:
-“ wherein the first prediction model is trained by using, as training data, experimental values for the properties of feed supplied to the reactor, past operating conditions of the reactor, and a difference in temperature between front and rear ends of the reactor.” This/these limitations is/are recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component (See MPEP 2106.05(f)).
b) Step 2B analysis:
-“ wherein the first prediction model is trained by using, as training data, experimental values for the properties of feed supplied to the reactor, past operating conditions of the reactor, and a difference in temperature between front and rear ends of the reactor.” This/these limitations is/are recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component (See MPEP 2106.05(f)).
The claim 9 recites:
a) Step 2A: Prong 2 analysis:
-“ wherein the second prediction model is trained by using, as training data, experimental values for the properties of feed supplied to the reactor, past operating conditions of the reactor, a difference in temperature between front and rear ends of the reactor, and experimental values for the properties of products produced in the reactor.” This/these limitations is/are recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component (See MPEP 2106.05(f)).
b) Step 2B analysis:
-“ wherein the second prediction model is trained by using, as training data, experimental values for the properties of feed supplied to the reactor, past operating conditions of the reactor, a difference in temperature between front and rear ends of the reactor, and experimental values for the properties of products produced in the reactor.” This/these limitations is/are recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component (See MPEP 2106.05(f)).
The claim 10 recites:
a) Step 2A: Prong 2 analysis:
-“ wherein the first prediction unit predict a content of napthene and a content of paraffin contained in the feed being currently supplied to the reactor, respectively.” This/these limitations is/are recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component (See MPEP 2106.05(f)).
b) Step 2B analysis:
-“ wherein the first prediction unit predict a content of napthene and a content of paraffin contained in the feed being currently supplied to the reactor, respectively.” This/these limitations is/are recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component (See MPEP 2106.05(f)).
The claim 11 recites:
a) Step 2A: Prong 2 analysis:
-“wherein the second prediction unit predicts a content of aromatics and a content of paraffin included in the product being produced in the reactor, respectively.” This/these limitations is/are recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component (See MPEP 2106.05(f)).
b) Step 2B analysis:
-“wherein the second prediction unit predicts a content of aromatics and a content of paraffin included in the product being produced in the reactor, respectively.” This/these limitations is/are recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component (See MPEP 2106.05(f)).
The claim 12 recites:
-“ wherein the current operating condition includes one or more of an operating temperature, an operating pressure, a feed flow rate, a circulating gas flow rate, and hydrogen purity of the reactor.” This/these limitation(s) is/are amount to no more than generally linking the use of a judicial exception to a particular technological environment or field of use (See MPEP 2106.05(h)). As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception and that it does not integrate the judicial exception into a practical application.
b) Step 2B analysis:
-“ wherein the current operating condition includes one or more of an operating temperature, an operating pressure, a feed flow rate, a circulating gas flow rate, and hydrogen purity of the reactor.” This/these limitation(s) is/are amount to no more than generally linking the use of a judicial exception to a particular technological environment or field of use. As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not amount to significantly more than the exception itself.
The claim 13 recites “A computer-readable recording medium in which a program for executing the method of predicting properties of feed and products in a reformer”. The claim13 is rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. Specifically, claim 13 recites toward "a computer-readable recording medium”. The broadest reasonable interpretation of “a computer-readable recording medium” covers transitory propagating signals, which are non-statutory. The disclosure in [0013] discloses that “computer-readable media, i.e., not storage media, may additionally include communication media such as transmission media for wireless signals and the like.” Although this disclosure may exclude “transmission media such as wireless signals and the like” from “a storage media,” it does not make it clear that “a storage device” is a “storage media,” and thus “a storage device” may exclude “transmission media such as wireless signals and the like.” Further, even if “a storage device” were considered as a “storage media,” the statement only explicitly excludes “wireless signals and the like.” It is unclear whether other types of signal, e.g., signal in wired transmission, is excluded from a storage media.
Therefore, a broadest reasonable interpretation of claim 13 covers a transitory signal. When the broadest reasonable interpretation of a claim covers a signal per se, the claim must be rejected under 35 U.S.C. 101 as covering non-statutory subject matter. See In re Nuijten, 500 F.3d 1346, 1356-57 (Fed. Cir. 2007) (transitory
embodiments are not directed to statutory subject matter); MPEP 9th Ed., § 2106.I. To overcome this rejection, applicant should insert –- non-transitory — before “computer-readable recording medium”. Such an amendment is not considered new matter. See the “Subject Matter Eligibility of Computer Readable Media” memo dated January 26, 2010 (OG Cite: 1351 OG 212; OG Date: 23 Feb 2010).
The claim 14 is rejected for the same reason as the claim 13, since the claim 14 recites “a computer-readable transitory recording medium”.
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 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 nonobviousness.
Claims 1, 2, 15, 16, 18 are rejected under 35 U.S.C. 103 as being unpatentable over of Kumar et al. (PUB. No. US 20170322131-hereinafter, Kumar) and further in view of Shao et al. (Patent. No. US 12153037 -hereinafter, Shao).
Regarding claim 1, Kumar teaches a method of predicting properties of feed and products in a reformer, comprising the steps of: training a first predictive model for predicting the properties of feed in the reformer (Kumar, [Par.0075], “In one implementation, a first correlation model is developed by the model generator module 110 based on the coefficients of regression calculated. The first correlation model predicts the kinematic viscosity of vacuum residue of a crude oil at a predetermined temperature from the physical parameters of the crude oil. Theoretically, the first correlation model may be written as, [0076] KV-VR @ 50, 100, or 135 degree Celsius=f (at least one of Vacuum Residue yield and Conradson Carbon Residue (CCR) content)” and [Par.0099], “The output generated is a predicted value of kinematic viscosity of vacuum residue of crude oil. In one implementation, the predicted value of kinematic viscosity may be used for determining production requirements of Fuel oil, Low Sulphur Heavy Stock, Low Sulphur Fuel Oil, and bitumen, and estimating amount of cutter stock required in vacuum residue evacuation process.” Examiner’s note, the first correlation model to predict the kinematic viscosity of vacuum residue of the crude oil at the predetermined temperature, therefore, the kinematic viscosity/physical properties of the crude oil at the predetermined temperature that is considered as the properties of feed in the reformer.).
and a second predictive model for predicting the properties of products in the reformer (Kumar, [[Par,.0056], “In one implementation, a second correlation model and third correlation model may be developed based on coefficients obtained by experimental analyses. For example, the second correlation model may be used to predict kinematic viscosity of a blended petroleum product including a heavy product, from the kinematic viscosities of individual products in the blended petroleum product” Examiner’s note, the second machine learning model to predict the kinematic viscosity/properties of the blended product from the individual products in the blended petroleum product );
predicting the properties of feed being currently supplied to the reactor in real time by allowing a first prediction unit including the trained first prediction model to receive a current operating condition of the reactor in the reformer (Kumar, [Par.0068], “. The first prediction module 114 predicts kinematic viscosity of vacuum residue at a predetermined temperature of given crude oil.” And [Par.0097-0098], “At block 302, values of physical parameters, including at least one of Vacuum Residue yield and Conradson Carbon Residue (CCR) content of crude oil are received as inputs to the first correlation model from the data. The data may include values of physical parameters of crude oils whose kinematic viscosity of vacuum residue is unknown. In one implementation, the values of physical parameters may be provided by a user through one or more interfaces. The interfaces may include peripheral devices, such as mouse, keyboard, external memory, etc. The first prediction module may access the data for receiving values of physical parameters as input. The physical parameters of the selected crude oil may also include one or more of API gravity, Sulphur content, Hydrogen content, Nitrogen content, Pour point, Saturates, Aromatics, Resins, Asphaltenes, etc. For example, the physical parameters include Vacuum Residue yield, Conradson Carbon Residue (CCR) content, and API gravity…[0098] At block 304, the kinematic viscosity of vacuum residue of crude oil at a predetermined temperature is determined. The correlation model on receiving the values of physical parameters, calculates an estimated value of kinematic viscosity of vacuum residue of crude oil.” Examiner’s note, the first prediction model to predict the properties of the given crude oil at a particular predetermined temperature based on a training output of the first prediction model is trained at the first prediction module (first training unit), therefore, the predicting properties of the given crude oil at particular predetermined temperature, that corresponds to the predicting the properties of feed being currently supplied to the reactor in real time.)
and predicting the properties of products being produced in the reactor in real time by allowing a second prediction unit including the trained second prediction model to receive the current operating condition and the predicted properties of feed (Kumar, [Par.0056], “In one implementation, a second correlation model and third correlation model may be developed based on coefficients obtained by experimental analyses. For example, the second correlation model may be used to predict kinematic viscosity of a blended petroleum product including a heavy product, from the kinematic viscosities of individual products in the blended petroleum product.” And [Par.0068], “] Further, the plurality of prediction modules includes a first prediction module 114 and a second prediction module 116. The first prediction module 114 and the second prediction module 116 can predict kinematic viscosity based on the correlation models generated by the model generator module 110. The first prediction module 114 predicts kinematic viscosity of vacuum residue at a predetermined temperature of given crude oil. Similarly, the second prediction module 116 predicts the kinematic viscosity of refinery heavy product blends.” Examiner’s note, the second model (second prediction model) predicts the properties of the refinery heavy product blends from the kinematic viscosities of individual products in the blended petroleum product, therefore, the predicting from the kinematic viscosities of individual products in the blended petroleum product by using the second prediction model is trained by the second prediction module corresponds to the predicting the properties of products being produced in the reactor in real time by allowing a second prediction unit.)
However, Kumar does not teach the first prediction unit including the trained first prediction model, the second prediction unit including the trained second prediction model.
On the other hand, Shao teaches the first prediction unit including the trained first prediction model (Col. 15, lines 10-41], “For example, the first prediction model may be trained by a computing device (e.g., the processing device 140) …The training of the first prediction model may include one or more first iterations, and each first iteration may include updating model parameters of the first prediction model based on the first training samples.” Examiner’s note, the first prediction model is iteratively trained by the computing device, therefore, the computing device is considered as the first predicting unit includes the first trained prediction model.
the second prediction unit including the trained second prediction model (Shao [Col.18, lines 13-25], “ In some embodiments, the processing device may train the second prediction model based on one or more second training samples to acquire a second prediction model after training. The training of the second prediction model may include one or more second iterations, and each of the second iterations may include updating model parameters of the second prediction model based on the second training sample. In some embodiments, the optimization target of the second prediction model may include adjusting the model parameters such that the value of the second loss function becomes smaller (e.g., minimizing the value of the second loss function).” Examiner’s note, the processing device is iteratively trained the second prediction model by iteratively update the parameter of the second prediction model, therefore, the processing device is considered as the second prediction unit includes the trained second prediction model.
Kumar and Shao are analogous in arts because they have the same field of endeavor of generating the machine learning model based on the industrial data.
Accordingly, it would have been obvious to one of the ordinary skills in the art before the effective filing date of the claimed invention to modify the predicting the properties of feed being currently supplied to the reactor in real time by allowing a first prediction unit including the first prediction model to receive a current operating condition of the reactor in the reformer, and predicting the properties of products being produced in the reactor in real time by allowing a second prediction unit including the second prediction model to receive the current operating condition and the predicted properties of feed, as taught by Kumar to include the first prediction unit including the trained first prediction model, the second prediction unit including the trained second prediction model, as taught by Shao. The modification would have been obvious because one of the ordinary skills in art would be motivated to optimize the loss value (Shao, [Col.15, lines 40-45], “In some embodiments, the optimization target of the first prediction model training may include adjusting the model parameters such that the value of the first loss function becomes smaller (e.g., minimizing the value of the first loss function).” And [Col18, lines 13-24], “In some embodiments, the processing device may train the second prediction model based on one or more second training samples to acquire a second prediction model after training. The training of the second prediction model may include one or more second iterations, and each of the second iterations may include updating model parameters of the second prediction model based on the second training sample. In some embodiments, the optimization target of the second prediction model may include adjusting the model parameters such that the value of the second loss function becomes smaller (e.g., minimizing the value of the second loss function).”).
Regarding claim 2, Kumar teaches the method of claim 1, wherein the first prediction model is trained by using as experimental values for the properties of feed supplied to the reactor (Kumar, [Par.0097], “The first prediction module may access the data for receiving values of physical parameters as input. The physical parameters of the selected crude oil may also include one or more of API gravity, Sulphur content, Hydrogen content, Nitrogen content, Pour point, Saturates, Aromatics, Resins, Asphaltenes, etc. For example, the physical parameters include Vacuum Residue yield, Conradson Carbon Residue (CCR) content, and API gravity.”).
and a difference in temperature between front and rear ends of the reactor (Kumar, [Par.0015], “the predetermined temperature may be in a range of 50 degree Celsius to 135 degree Celsius.” And [Par.0110], “The graphs illustrated in the FIG. 5-FIG. 12 are generated by studying the relationship of physical parameters of crude oil and kinematic viscosity of vacuum residue at 100 degree Celsius. The temperature must not be construed as a limitation as a person skilled in the art would understand that similar influence of physical parameters on kinematic viscosity of vacuum residue may be observed in a temperature range of 50 to 135 degree Celsius.” ).
However, Kumar does not teach the first prediction model is trained by using training data, a past operating condition of the reactor Shao, [Col.2, lines 1-10], “In some embodiments, wherein the first prediction model is obtained by a training process, the training process comprising: obtaining at least one training sample, wherein each of the at least one training sample includes a sample carbon content of a sample natural gas, a sample ambient temperature and a sample air oxygen content when the sample natural gas was provided in use, a sample transmission rate when the sample natural gas is provided and a sample energy per unit volume value of the sample natural gas, wherein the sample energy per unit volume value is determined by the actual combustion of the sample natural gas; and obtaining the first prediction model based on the at least one training sample.”). and [Col. 3, lines 55-66], “In some embodiment, wherein the first prediction model is obtained by a training process, the training process comprising: obtaining at least one training sample, wherein each of the at least one training sample includes a sample carbon content of a sample natural gas, a sample ambient temperature and a sample air oxygen content when the sample natural gas was provided in use, a sample transmission rate when the sample natural gas is provided and a sample energy per unit volume value of the samples”.).
Kumar and Shao are analogous in arts because they have the same field of endeavor of generating the machine learning model based on the industrial data.
Accordingly, it would have been obvious to one of the ordinary skills in the art before the effective filing date of the claimed invention to modify the wherein the first prediction model is trained by using as experimental values for the properties of feed supplied to the reactor and a difference in temperature between front and rear ends of the reactor, as taught by Kumar to include the first prediction model is trained by using training data, a past operating condition of the reactor, as taught by Shao. The modification would have been obvious because one of the ordinary skills in art would be motivated to optimize the loss value (Shao, [Col.15, lines 40-45], “In some embodiments, the optimization target of the first prediction model training may include adjusting the model parameters such that the value of the first loss function becomes smaller (e.g., minimizing the value of the first loss function).” And [Col18, lines 13-24], “In some embodiments, the processing device may train the second prediction model based on one or more second training samples to acquire a second prediction model after training. The training of the second prediction model may include one or more second iterations, and each of the second iterations may include updating model parameters of the second prediction model based on the second training sample. In some embodiments, the optimization target of the second prediction model may include adjusting the model parameters such that the value of the second loss function becomes smaller (e.g., minimizing the value of the second loss function).”).
Regarding claim 3, Kumar teaches the method of claim 1, wherein the second prediction model is trained by using, as, experimental values for the properties of feed supplied to the reactor, and experimental values for the properties of products produced in the reactor (Kumar, [Par.0056], “In one implementation, a second correlation model and third correlation model may be developed based on coefficients obtained by experimental analyses. For example, the second correlation model may be used to predict kinematic viscosity of a blended petroleum product including a heavy product, from the kinematic viscosities of individual products in the blended petroleum product.”
using, a difference in temperature between front and rear ends of the reactor (Kumar, [Par.0015], “the predetermined temperature may be in a range of 50 degree Celsius to 135 degree Celsius.” And [Par.0110], “The graphs illustrated in the FIG. 5-FIG. 12 are generated by studying the relationship of physical parameters of crude oil and kinematic viscosity of vacuum residue at 100 degree Celsius. The temperature must not be construed as a limitation as a person skilled in the art would understand that similar influence of physical parameters on kinematic viscosity of vacuum residue may be observed in a temperature range of 50 to 135 degree Celsius.”).
However, Kumar does not teach wherein the second prediction model is trained by using, as training data, a past operating condition of the reactor,
On the other hand, Shao teaches wherein the second prediction model is trained by using, as training data, a past operating condition of the reactor, [Col.4, lines 11-24], “In some embodiment, wherein the training process of the second prediction model comprises: obtaining at least one training sample, wherein each of the at least one training sample includes a sample combustible composition information of sample natural gas, the sample ambient temperature and the sample air oxygen content when the sample natural gas was provided in use, the sample transmission rate when the sample natural gas is provided and the sample energy per unit volume value of the sample natural gas, wherein the sample energy per unit volume value is determined by the actual combustion of the sample natural gas; and obtaining the second prediction model based on the at least one training sample.” And (Col. 16, liens 1-19], “As shown in FIG. 5, for any subarea in a plurality of subareas, a second prediction model 503 corresponding to the each subarea may be determined based on the decontamination manner 501 of the natural gas corresponding to the each subarea, and the calorific value distribution function of the natural gas 504 corresponding to the each subarea after performing the decontamination manner may be obtained based on the second prediction model that is configured to process the calorific value distribution function of the natural gas 502 corresponding to the each subarea. The second prediction model may be a machine learning model for predicting the calorific value distribution function of the natural gas after performing the decontamination manner. In some embodiments, the second prediction model may be a convolutional neural network (CNN), the like, or other neural network models.”).
Kumar and Shao are analogous in arts because they have the same field of endeavor of generating the machine learning model based on the industrial data.
Accordingly, it would have been obvious to one of the ordinary skills in the art before the effective filing date of the claimed invention to modify the the second prediction model is trained by using, as, experimental values for the properties of feed supplied to the reactor, and experimental values for the properties of products produced in the reactor, a difference in temperature between front and rear ends of the reactor, as taught by Kumar to include the second prediction model is trained by using, as training data, a past operating condition of the reactor, as taught by Shao. The modification would have been obvious because one of the ordinary skills in art would be motivated to optimize the loss value (Shao, [Col.15, lines 40-45], “In some embodiments, the optimization target of the first prediction model training may include adjusting the model parameters such that the value of the first loss function becomes smaller (e.g., minimizing the value of the first loss function).” And [Col18, lines 13-24], “In some embodiments, the processing device may train the second prediction model based on one or more second training samples to acquire a second prediction model after training. The training of the second prediction model may include one or more second iterations, and each of the second iterations may include updating model parameters of the second prediction model based on the second training sample. In some embodiments, the optimization target of the second prediction model may include adjusting the model parameters such that the value of the second loss function becomes smaller (e.g., minimizing the value of the second loss function).”).
Regarding claim 5, Kumar teaches the method of claim 1, wherein the second prediction unit predicts a content of aromatics and a content of paraffin included in the product being produced in the reactor, respectively, (Kumar, [Par.0007], “n embodiments of the method, the method can further include determining the kinematic viscosity of a heavy product blend from the kinematic viscosity of fraction of the heavy product blend based on a second correlation model. In such embodiments, the heavy product blend may correspond to a blend of different fractions of the crude oil derived from different or same crude oils.” Examiner’s note, the second correlation model predicts/determines the faction of the heavy product blend, wherein, the faction of the product includes the content of aromatics and a content of paraffin, as it can be seen at [Par.0120-0121], “ FIG. 10, FIG. 11, and FIG. 12, illustrate the impact on kinematic viscosity of vacuum residue of crude oil due to change in saturates content, aromatics content, and asphaltene content in crude oil. Saturates, Aromatics, and Asphaltenes are three groups into which the components of heavy fraction of a petroleum fluid can be separated into. The chemical constitution of these contents is complex and the physical measurement and separation is difficult, in comparison to estimation of other physical parameters of crude oil…[0121] Saturates content and Aromatics content may be determined by adsorption chromatography, typically from silica or silica/alumina. Saturates may be eluted with a paraffinic solvent, such as pentane or heptane, while Aromatics may be eluted either with paraffinic or moderately polar solvents, such as toluene. On elution of the contents, different measurement techniques can be used as known from the state of the art technology.”).
Regarding claim 6, Kumar teaches the method of claim 1, wherein the current operating condition includes one or more of an operating temperature, an operating pressure, a feed flow rate, a circulating gas flow rate, and hydrogen purity of the reactor (Kumar, [Par.0006], “In one aspect, embodiments of a method for predicting kinematic viscosity of a fraction of a crude oil to optimize selection of crude oils is provided. The method includes the step of receiving, by a processor, physical parameters of the crude oil as an input, wherein the physical parameters comprise at least one of Vacuum Residue yield and Conradson Carbon Residue (CCR) content. The method also includes the step of determining, by the processor, kinematic viscosity of the fraction of the crude oil at a first predetermined temperature, wherein the kinematic viscosity is determined based on a first correlation model between the physical parameters of the crude oil and the kinematic viscosity at the first predetermined temperature.”).
Regarding claim 7, Kumar teaches an apparatus for predicting properties of feed and products in a reformer (Kumar, [Par.0075], “In one implementation, a first correlation model is developed by the model generator module 110 based on the coefficients of regression calculated. The first correlation model predicts the kinematic viscosity of vacuum residue of a crude oil at a predetermined temperature from the physical parameters of the crude oil. Theoretically, the first correlation model may be written as, [0076] KV-VR @ 50, 100, or 135 degree Celsius=f (at least one of Vacuum Residue yield and Conradson Carbon Residue (CCR) content)” and [Par.0099], “The output generated is a predicted value of kinematic viscosity of vacuum residue of crude oil. In one implementation, the predicted value of kinematic viscosity may be used for determining production requirements of Fuel oil, Low Sulphur Heavy Stock, Low Sulphur Fuel Oil, and bitumen, and estimating amount of cutter stock required in vacuum residue evacuation process.” Examiner’s note, the first correlation model to predict the kinematic viscosity of vacuum residue of the crude oil at the predetermined temperature, therefore, the kinematic viscosity/physical properties of the crude oil at the predetermined temperature that is considered as the properties of feed in the reformer.). and [Par,.0056], “In one implementation, a second correlation model and third correlation model may be developed based on coefficients obtained by experimental analyses. For example, the second correlation model may be used to predict kinematic viscosity of a blended petroleum product including a heavy product, from the kinematic viscosities of individual products in the blended petroleum product” Examiner’s note, the second machine learning model to predict the kinematic viscosity/properties of the blended product from the individual products in the blended petroleum product );
comprising: a first prediction unit configured to predict the properties of feed being currently supplied to a reactor in the reformer in real time by using a pre-trained first prediction model when a current operating condition of the reactor in the reformer is input (Kumar, [Par.0068], “. The first prediction module 114 predicts kinematic viscosity of vacuum residue at a predetermined temperature of given crude oil.” And [Par.0097-0098], “At block 302, values of physical parameters, including at least one of Vacuum Residue yield and Conradson Carbon Residue (CCR) content of crude oil are received as inputs to the first correlation model from the data. The data may include values of physical parameters of crude oils whose kinematic viscosity of vacuum residue is unknown. In one implementation, the values of physical parameters may be provided by a user through one or more interfaces. The interfaces may include peripheral devices, such as mouse, keyboard, external memory, etc. The first prediction module may access the data for receiving values of physical parameters as input. The physical parameters of the selected crude oil may also include one or more of API gravity, Sulphur content, Hydrogen content, Nitrogen content, Pour point, Saturates, Aromatics, Resins, Asphaltenes, etc. For example, the physical parameters include Vacuum Residue yield, Conradson Carbon Residue (CCR) content, and API gravity…[0098] At block 304, the kinematic viscosity of vacuum residue of crude oil at a predetermined temperature is determined. The correlation model on receiving the values of physical parameters, calculates an estimated value of kinematic viscosity of vacuum residue of crude oil.” Examiner’s note, the first prediction model to predict the properties of the given crude oil at a particular predetermined temperature based on a training output of the first prediction model is trained at the first prediction module (first training unit), therefore, the predicting properties of the given crude oil at particular predetermined temperature, that corresponds to the predicting the properties of feed being currently supplied to the reactor in real time.).
and a second prediction unit configured to predict the properties of products being produced in the reactor in real time by using a pre-trained second prediction model when the current operating condition and the predicted properties of feed are input (Kumar, [Par.0056], “In one implementation, a second correlation model and third correlation model may be developed based on coefficients obtained by experimental analyses. For example, the second correlation model may be used to predict kinematic viscosity of a blended petroleum product including a heavy product, from the kinematic viscosities of individual products in the blended petroleum product.” And [Par.0068], “] Further, the plurality of prediction modules includes a first prediction module 114 and a second prediction module 116. The first prediction module 114 and the second prediction module 116 can predict kinematic viscosity based on the correlation models generated by the model generator module 110. The first prediction module 114 predicts kinematic viscosity of vacuum residue at a predetermined temperature of given crude oil. Similarly, the second prediction module 116 predicts the kinematic viscosity of refinery heavy product blends.” Examiner’s note, the second model (second prediction model) predicts the properties of the refinery heavy product blends from the kinematic viscosities of individual products in the blended petroleum product, therefore, the predicting from the kinematic viscosities of individual products in the blended petroleum product by using the second prediction model is trained by the second prediction module corresponds to the predicting the properties of products being produced in the reactor in real time by allowing a second prediction unit.)
However, Kumar does not teach pre-trained first prediction model, pre-trained second prediction model.
On the other hand, Zhao teaches pre-trained first prediction model, (Zhao, [Col. 15, lines 10-41], “For example, the first prediction model may be trained by a computing device (e.g., the processing device 140) …The training of the first prediction model may include one or more first iterations, and each first iteration may include updating model parameters of the first prediction model based on the first training samples.” Examiner’s note, the first prediction model is iteratively trained by the computing device, therefore, the computing device is considered as the first predicting unit includes the first trained prediction model.
pre-trained second prediction model (Shao [Col.18, lines 13-25], “ In some embodiments, the processing device may train the second prediction model based on one or more second training samples to acquire a second prediction model after training. The training of the second prediction model may include one or more second iterations, and each of the second iterations may include updating model parameters of the second prediction model based on the second training sample. In some embodiments, the optimization target of the second prediction model may include adjusting the model parameters such that the value of the second loss function becomes smaller (e.g., minimizing the value of the second loss function).” Examiner’s note, the processing device is iteratively trained the second prediction model by iteratively update the parameter of the second prediction model, therefore, the processing device is considered as the second prediction unit includes the trained second prediction model.
Kumar and Shao are analogous in arts because they have the same field of endeavor of generating the machine learning model based on the industrial data.
Accordingly, it would have been obvious to one of the ordinary skills in the art before the effective filing date of the claimed invention to modify the first prediction unit configured to predict the properties of feed being currently supplied to a reactor in the reformer in real time by using a first prediction model when a current operating condition of the reactor in the reformer is input and a second prediction unit configured to predict the properties of products being produced in the reactor in real time by using a second prediction model when the current operating condition and the predicted properties of feed are input, as taught by Kumar to include the pre-trained first prediction model, pre-trained second prediction model., as taught by Shao. The modification would have been obvious because one of the ordinary skills in art would be motivated to optimize the loss value (Shao, [Col.15, lines 40-45], “In some embodiments, the optimization target of the first prediction model training may include adjusting the model parameters such that the value of the first loss function becomes smaller (e.g., minimizing the value of the first loss function).” And [Col18, lines 13-24], “In some embodiments, the processing device may train the second prediction model based on one or more second training samples to acquire a second prediction model after training. The training of the second prediction model may include one or more second iterations, and each of the second iterations may include updating model parameters of the second prediction model based on the second training sample. In some embodiments, the optimization target of the second prediction model may include adjusting the model parameters such that the value of the second loss function becomes smaller (e.g., minimizing the value of the second loss function).”)..
Regarding claim 8 is rejected for the same reason as the claim 2, since these claims recite the same limitations.
Regarding claim 9 is rejected for the same reason as the claim 3, since these claims recite the same limitations.
Regarding claim 11 is rejected for the same reason as the claim 5, since these claims recite the same limitations.
Regarding claim 12 is rejected for the same reason as the claim 6, since these claims recite the same limitations.
Regarding claim 13 is rejected for the same reason as the claim 1, since these claims recite the same limitations.
Regarding claim 14 is rejected for the same reason as the claim 2, since these claims recite the same limitations.
Claims 4, 10 are rejected under 35 U.S.C. 103 as being unpatentable over of Kumar et al. (PUB. No. US 20170322131-hereinafter, Kumar) and further in view of Shao et al. (Patent. No. US 12153037 -hereinafter, Shao) and further in view of Brown et al . (PUB. No. US 20030195708 -hereinafter, Brown).
Regarding claim 4, Kumar teaches the method of the claim 1, the first prediction unit but it does not teach wherein the first prediction unit predicts a content of napthene and a content of paraffin contained in the feed being currently supplied to the reactor, respectively.
On the other hand, Brown teaches wherein the first prediction unit predicts a content of napthene and a content of paraffin contained in the feed being currently supplied to the reactor, respectively (Brown, [par.0133], “An additional example demonstrates that the method of the current invention can be applied for the detailed analysis of materials other than crude oil. The method can be used to predict molecular distribution and Structure-Oriented Lumping (SOL) information for feeds to catalytic cracking units. The molecular distribution information predicted is dependent on the specific reference analysis employed and includes information such as paraffin, naphthene and aromatic molecular types as a function of boiling range. Structured-Oriented Lumping is described by Quann and Jaffe (Ind. Eng. Chem. Res. 1992, 31, 2483-2497), as is its use in process modeling (Chemical Engineering Science, 1996, 51, 1615-1635). For this example, the references consist of 49 virgin gas oils and process streams that are components typically used as feeds to a fluid catalytic cracking process.”).
Kumar and Brown are analogous in arts because they have the same field of endeavor of generating the machine learning model based on the industrial data.
Accordingly, it would have been obvious to one of the ordinary skills in the art before the effective filing date of the claimed invention to modify the first prediction unit, as taught by Kumar to include the first prediction unit predicts a content of napthene and a content of paraffin contained in the feed being currently supplied to the reactor, respectively, as taught by Brown. The modification would have been obvious because one of the ordinary skills in art would be motivated to cause the significant changes in the value of the crude oil and the product can be made from it. (Brown, [Par.0009], “A detailed crude assay can take several weeks to months to complete. As a result, the assay data used for making business decisions, and for planning, controlling and optimizing operations is seldom from the cargoes currently being bought, sold or processed, but rather historical data for "representative" past cargoes. The assays do not account for variations between cargoes that can have a significant effect on operations. K. G. Waguespack (Hydrocarbon Processing, 77 (9), 1998 Feature Article) discusses the sources of oil quality variation, their effect on refinery operations, and the need for improved analytical technology for use in crude oil quality monitoring. Wagusepack lists sources of crude oil variability, both over time and during its transport life as: aging production reservoirs; changes in relative field production rates; mixing of crude in the gathering system; pipeline degradation vis--vis batch interfaces; contamination; and injection of significantly different quality streams into common specification crude streams. Such variations can cause significant changes in the value of the crude oil, and in the products that can be made from it.”).
Regarding claim 10 is rejected for the same reason as the claim 4, since these claims recite the same limitations.
Conclusion
. Any inquiry concerning this communication or earlier communications from the examiner should be directed to EM N TRIEU whose telephone number is (571)272-5747. The examiner can normally be reached on Mon-Fri from 9:00-5:00.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Omar Fernandez Rivas can be reached on (571) 272-2589. 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.
/E.T./Examiner, Art Unit 2128
/OMAR F FERNANDEZ RIVAS/Supervisory Patent Examiner, Art Unit 2128
Prosecution Insights