DETAILED ACTION
Claims 1-6 are presented for examination.
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Drawings
The drawings received on 10 June 2022 are accepted.
Claim Interpretation
Claim 1 recites “burning rising point (BRP).” This claim term does not appear to have any special definition within the art of sintering. This phrase is interpreted in light of Specification figure 3 which shows the BRP as an inflection point or critical point of the curve. However, the broadest reasonable interpretation of a rising point is any point on the curve with a positive slope/gradient/first derivative. See MPEP §2111.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-6 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor, or for pre-AIA the applicant regards as the invention.
Claim 1 twice recites “segmenting the data.” In each instance it is unclear which data “the data” is referring to. There are multiple different data recited in the claim.
Dependent claims 2-6 are rejected for depending from a rejected claim.
Claim 5 recites “and feature data are input in time series to obtain an output, namely an advanced feature.” There are two issues with this. First, a broad range or limitation together with a narrow range or limitation that falls within the broad range or limitation (in the same claim) may be considered indefinite if the resulting claim does not clearly set forth the metes and bounds of the patent protection desired. See MPEP § 2173.05(c). In the present instance, claim 5 recites the broad recitation “feature data,” and the claim also recites “namely advanced feature” which is the narrower statement of the range/limitation. The claim(s) are considered indefinite because there is a question or doubt as to whether the feature introduced by such narrower language is (a) merely exemplary of the remainder of the claim, and therefore not required, or (b) a required feature of the claims. Second, the term “advanced” in the phrase “advanced feature” is a relative term which renders the claim indefinite. The term “advanced” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention. Specification [0016] and [0063] mention “advanced feature” but neither section clarifies what features are, or are not, “advanced.”
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 1-6 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
To determine if a claim is directed to patent ineligible subject matter, the Court has guided the Office to apply the Alice/Mayo test, which requires:
1. Determining if the claim falls within a statutory category;
2A. Determining if the claim is directed to a patent ineligible judicial exception consisting of a law of nature, a natural phenomenon, or abstract idea; and
2B. If the claim is directed to a judicial exception, determining if the claim recites limitations or elements that amount to significantly more than the judicial exception.
See MPEP §2106.
Step 2A is a two prong inquiry. MPEP §2106.04(II)(A). Under 2A(i), the first prong, examiners evaluate whether a law of nature, natural phenomenon, or abstract idea is set forth or described in the claim. Abstract ideas include mathematical concepts, certain methods of organizing human activity, and mental processes. MPEP §2106.04(a)(2). Under 2A(ii), the second prong, examiners determine whether any additional limitations integrates the judicial exception into a practical application. MPEP §2106.04(d).
In particular, the Court has found a mathematical formula for calculating an alarm limit is an ineligible mathematical concept. See Parker v. Flook, 437 U.S. 584, 588-89, 198 USPQ2d 193, 195 (1978).
Claim 1 step 2A(i):
The claim(s) recite:
1. A method for predicting burning through point (BTP) based on an encoder-decoder network, comprising:
…, and calculating BTP and burning rising point (BRP) with a polynomial fitting method;
a second step segmenting the data with a sliding window method based on the input features to construct training samples, verification samples, and test samples;
a third step establishing a BTP prediction model based on the encoder-decoder network, and training the model by means of the training samples; and
…, calculating BTP and BRP with a least square method; segmenting the data with the sliding window method to obtain data segments and establish a many-to-many sequence data set from the time
k
-
t
h
to time
k
; and inputting the many-to-many sequence data set into the trained BTP prediction model to obtain a BTP prediction result within a next prediction time length
t
f
from the time
k
.
Calculating a predicted BTP corresponds with respective mathematical calculations.
Calculating a BTP and BRP using a polynomial fitting is mathematical calculation.
Segmenting the data into time windows and constructing training, verification, and test designated samples are mathematical operations.
Establishing the BTP prediction model by performing respective mathematical calculations of the training using the data is performing those respective mathematical calculations. See further Specification ¶63 regarding calculating “weight coefficient” correlation using a temporal attention mechanism.
Calculating a BTP and BRP using least squares is further mathematical calculation.
Segmenting the data with sliding window is mathematical operation.
Inputting the sequence data into the prediction model to obtain a prediction corresponds with performing the respective mathematical calculations of the model.
This falls within the mathematical concepts grouping of abstract ideas. See MPEP §2106.04(a)(2).
Claim 1 step 2A(ii):
This judicial exception is not integrated into a practical application because:
The claim(s) recite:
a first step determining auxiliary variables related to BTP as input features, reading and preprocessing data of a sintering process from a database; reading data of exhaust-gas temperatures in bellows from the database, …
…
a fourth step reading, at current time
k
, on-line historical data from time
k
-
t
h
to time
k
in real time from a sensor and the database, collecting and preprocessing the auxiliary variables; reading the data of the exhaust-gas temperatures in the bellows from the time
k
-
t
h
to time
k
, ….
Determining variables and reading data from a database are generic recitations of data gathering. Mere data gathering is insignificant extra solution activity. See MPEP §2106.05(g).
Reading historical data from a sensor and database and reading temperatures is further recitation of data gathering. Mere data gathering is insignificant extra solution activity. See MPEP §2106.05(g).
Claim 1 step 2B:
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception, when considered individually and in combination, because:
The claim(s) recite:
a first step determining auxiliary variables related to BTP as input features, reading and preprocessing data of a sintering process from a database; reading data of exhaust-gas temperatures in bellows from the database, …
…
a fourth step reading, at current time
k
, on-line historical data from time
k
-
t
h
to time
k
in real time from a sensor and the database, collecting and preprocessing the auxiliary variables; reading the data of the exhaust-gas temperatures in the bellows from the time
k
-
t
h
to time
k
, ….
MPEP §2106.05(d) provides examples of insignificant extra-solution activity:
i. Receiving or transmitting data over a network
…
iv. Storing and retrieving information in memory
This is sufficient Berkheimer evidence for the non-specific claim recitations of data gathering.
When further considering the claims as a whole and as an ordered combination the claims fail to amount to significantly more than the judicially excepted abstract idea.
Claim 2 step 2A(i):
Dependent claims recite at least the identified judicially excepted subject matter of their parent claim(s).
This falls within the mathematical concepts grouping of abstract ideas. See MPEP §2106.04(a)(2).
Claim 2 step 2A(ii):
This judicial exception is not integrated into a practical application because:
The claim(s) recite:
2. The method for predicting BTP based on the encoder-decoder network according to claim 1, wherein in the first step, the auxiliary variables are selected as: a solid fuel ratio, a quicklime ratio, a limestone ratio, a dolomite-water ratio, a water content after a second mixing, a material thickness, an ignition temperature, air permeability, a negative pressure of a main fan, a pallet velocity, an exhaust-gas temperature of a large flue, and BRP,
wherein all the auxiliary variables except BRP are obtained from the data of the sintering process stored in the database; the auxiliary variables are taken as the input features, and calculated BTP is taken as an output label.
The respective auxiliary variables used correspond with generally linking the mathematical concept to a particular field of use. Merely indicating a field of use fails to integrate an abstract idea into a practical application. See MPEP §2106.05(h).
Obtaining the auxiliary variable data from a database is a generic recitation of data gathering. Designating a calculated result as an output is merely outputting the result of the abstract idea. The data gathering and insignificant outputting are insignificant extra solution activity. See MPEP §2106.05(g).
Claim 2 step 2B:
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception, when considered individually and in combination, because:
Limitations analyzed under MPEP §2106.05(h) in step 2A(ii) above are analyzed the same here under step 2B.
The claim(s) recite:
wherein all the auxiliary variables except BRP are obtained from the data of the sintering process stored in the database; the auxiliary variables are taken as the input features, and calculated BTP is taken as an output label.
MPEP §2106.05(d) provides examples of insignificant extra-solution activity:
i. Receiving or transmitting data over a network
…
iv. Storing and retrieving information in memory
This is sufficient Berkheimer evidence for the non-specific claim recitations of data gathering and a generic outputting data, i.e. over a network.
When further considering the claims as a whole and as an ordered combination the claims fail to amount to significantly more than the judicially excepted abstract idea.
Claim 3 step 2A(i):
Dependent claims recite at least the identified judicially excepted subject matter of their parent claim(s).
The claim(s) recite:
3. The method for predicting BTP based on the encoder-decoder network according to claim 1, wherein, in the first step, reading the data of the exhaust-gas temperatures in the bellows from the database and calculating BTP and BRP with the polynomial fitting method comprises: regarding the exhaust-gas temperature
T
i
and a position
x
i
of the bellows at a vicinity of BTP as a quadratic relation which satisfies a first formula:
T
i
=
a
x
i
2
+
b
x
i
+
c
i
=
1,2
,
…
,
m
substituting the positions and the exhaust-gas temperatures,
x
i
,
T
i
, of last three bellows into the first formula to obtain a linear equation set of the exhaust-gas temperatures and the positions of the bellows, wherein a subscript i represents an ith bellows to a last bellows; and solving the linear equation set to obtain a:
a
=
T
1
-
T
2
x
1
-
x
2
-
T
2
-
T
3
x
2
-
x
3
x
1
-
x
3
then solving the linear equation set to obtain b:
b
=
T
1
-
T
2
x
1
-
x
2
-
a
x
1
+
x
2
then:
c
=
T
i
-
a
x
i
2
-
b
x
i
obtaining BTP by means of the equations as follows:
x
m
a
x
=
-
b
2
a
wherein, BRP refers to a position where the exhaust-gas temperature rise in a length direction of a sintering machine, and the position
x
k
corresponding to the exhaust-gas temperature
T
k
of 1800ºC is solved based on a following formula:
T
k
=
a
x
k
2
+
b
x
k
+
c
.
The quadratic relation and formula for a parabola are explicit recitations of mathematical concepts. The further recitation of substituting, solving, and obtaining by respective calculations corresponds with a mathematical algorithm for performing the fitting calculations of the polynomial fitting for this quadratic relation.
This falls within the mathematical concepts grouping of abstract ideas. See MPEP §2106.04(a)(2).
Claim 3 step 2A(ii):
This judicial exception is not integrated into a practical application because:
Claim(s) do not recite any “additional” limitations.
Claim 3 step 2B:
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception, when considered individually and in combination, because:
Claim(s) do not recite any “additional” limitations.
When further considering the claims as a whole and as an ordered combination the claims fail to amount to significantly more than the judicially excepted abstract idea.
Claim 4 step 2A(i):
Dependent claims recite at least the identified judicially excepted subject matter of their parent claim(s).
The claim(s) recite:
4. The method for predicting BTP based on the encoder-decoder network according to claim 1, wherein, in the second step, sampling is performed with a sliding time window segment method, and each input segment sample is expressed as a matrix:
X
∈
R
T
h
×
f
wherein,
T
h
represents a number of frames of an observation segment,
f
represents a number of features of the segment; and an output sample Y is set to correspond to each input sample X:
Y
∈
R
T
f
×
f
.
Discretizing the measurements using a sliding time window is a mathematical operation. The resulting sample expressed as the matrix X and Y are explicit recitation of the mathematical structure.
This falls within the mathematical concepts grouping of abstract ideas. See MPEP §2106.04(a)(2).
Claim 4 step 2A(ii):
This judicial exception is not integrated into a practical application because:
Claim(s) do not recite any “additional” limitations.
Claim 4 step 2B:
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception, when considered individually and in combination, because:
Claim(s) do not recite any “additional” limitations.
When further considering the claims as a whole and as an ordered combination the claims fail to amount to significantly more than the judicially excepted abstract idea.
Claim 5 step 2A(i):
Dependent claims recite at least the identified judicially excepted subject matter of their parent claim(s).
The claim(s) recite:
5. The method for predicting BTP based on the encoder-decoder network according to claim 1, wherein, in the third step, establishing the BTP prediction model based on the encoder-decoder network comprises:
establishing the model by means of a encoder-decoder framework, wherein an encoder is established by means of a gated recurrent unit (GRU), and feature data are input in time series to obtain an output, namely an advanced feature, of the encoder; then calculating a correlation between a hidden state vector and an advanced feature vector of a decoder by means of a temporal attention mechanism to obtain a weight coefficient between them; and calculating a correlation between an output label and the advanced feature by means of a spatial attention mechanism to establish a potential correlation between an object variable and the advanced feature.
Calculating a correlation between hidden state vectors and feature vectors according to a temporal attention mechanism is a recitation of mathematical operations to obtain respective numerical weight coefficient(s). The calculation of the correlation and established potential correlation is mathematical calculation.
This falls within the mathematical concepts grouping of abstract ideas. See MPEP §2106.04(a)(2).
Claim 5 step 2A(ii):
This judicial exception is not integrated into a practical application because:
Claim(s) do not recite any “additional” limitations.
Claim 5 step 2B:
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception, when considered individually and in combination, because:
Claim(s) do not recite any “additional” limitations.
When further considering the claims as a whole and as an ordered combination the claims fail to amount to significantly more than the judicially excepted abstract idea.
Claim 6 step 2A(i):
Dependent claims recite at least the identified judicially excepted subject matter of their parent claim(s).
The claim(s) recite:
6. The method for predicting BTP based on the encoder-decoder network according to claim 1, wherein parameters of the BTP prediction model are adjusted in real time according to real-time data of the sintering process for continuous iteration and optimization, so that the model has high robustness.
Adjusting the parameters of the BTP prediction model with continuous iteration and optimization calculations is additional mathematical calculations of the mathematical modeling.
This falls within the mathematical concepts grouping of abstract ideas. See MPEP §2106.04(a)(2).
Claim 6 step 2A(ii):
This judicial exception is not integrated into a practical application because:
Claim(s) do not recite any “additional” limitations.
Claim 6 step 2B:
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception, when considered individually and in combination, because:
Claim(s) do not recite any “additional” limitations.
When further considering the claims as a whole and as an ordered combination the claims fail to amount to significantly more than the judicially excepted abstract idea.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
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 and 3-6 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang, X., et al. “Multivariate Time-Series Modeling for Forecasting Sintering Temperature in Rotary Kilns Using DCGNet” IEEE Transactions on Industrial Informatics, vol. 17, no. 7 (July 2021) [herein “Zhang”] in view of Li, M.H. & Wang, J. “The Research for Soft Measuring Technique of Sintering Burning Through Point” IEEE 1st Conf. on Industrial Electronics & Applications (2006) [herein “Li”].
Claim 1 recites “1. A method for predicting burning through point (BTP) based on an encoder-decoder network.” Zhang title discloses “Multivariate Time-Series Modeling for Forecasting Sintering Temperature in Rotary Kilns Using DCGNet” The sintering temperature (ST) corresponds with a burning through point. The DCGNet corresponds with an encoder-decoder network.
Claim 1 further recites “comprising: a first step determining auxiliary variables related to BTP as input features, reading and preprocessing data of a sintering process from a database; reading data of exhaust-gas temperatures in bellows from the database.” Zhang page 4639 right column last paragraph discloses “seven auxiliary variables closely related to the ST were collected.” Zhang page 4640 right column first paragraph discloses “selected as the best features in the component matrix. That is, the kiln head temperature, airflow rotation speed, and coal feeding value are the optimal input variates.” The selected input variates corresponds to determining respective auxiliary variables as input features. The kiln head temperature corresponds with an exhaust gas temperature of the bellows. Zhang page 4636 right column third paragraph section II discloses “the coal powder is blown into the kiln by a blower from the kiln head.” The blower corresponds with the bellows. Accordingly, the temperature at the kiln head corresponds with an exhaust gas temperature of the bellows.
Zhang page 4639 right column last paragraph discloses “For standardization, all the data were scaled into the range of 0–1, according to (11).” Scaling the data into a range 0-1 is a normalization corresponding with preprocessing the data.
Furthermore, Zhang page 4637 left column first paragraph disclose “An infrared thermometer can measure the [Sintering Temperature (ST)] by a temperature-sensing element installed in the burning zone.”
Zhang abstract discloses “DCGNet uses convolutional neural networks and gated recurrent unit (GRU) to extract the local spatial-temporal dependence patterns among the multivariates, and another parallel GRU using the historical ST data as input.” Historical data corresponds with data from a database.
Furthermore, Zhang page 4637 left column sixth paragraph disclose:
In this article, time-series forecasting is focused on multiple input variates and a singular prediction output. More formally, a series of process variates
X
=
x
1
,
…
,
x
i
and
y
as the variate to be estimated [Sintering Temperature (ST)] are given, where
X
∈
R
N
×
i
,
y
∈
R
,
i
is the variable dimension, and
N
is the number of samples collected by the DCS.
Samples collected from a DCS correspond with collecting data from at least one kind of a database.
Claim 1 further recites “and calculating BTP and burning rising point (BRP) with a polynomial fitting method.” Zhang does not explicitly disclose calculating a BTP and BRP with a polynomial fitting; however, in analogous art of predicting sintering endpoint, Li abstract teaches “The math model will be built based on the relation of measurable variables with BTP to judge the BTP online. Quadratic curve is fitted according to three measured points including the highest waste gas in five windboxes at discharge end.”
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to combine Zhang and Li. One having ordinary skill in the art would have found motivation to use quadratic curve fitting into the system of multivariate modeling for forecasting sintering temperature using DCGNet for the advantageous purpose of “to measure BTP online,” also known as in real-time. See Li abstract.
Claim 1 further recites “a second step segmenting the data with a sliding window method based on the input features to construct training samples, verification samples, and test samples.” Zhang page 4637 left column sixth paragraph discloses “where τ is the correlative time interval of the thermal process data.” The time interval for the process variables and estimated state corresponds with a time window of a sliding window method.
Zhang page 4639 Algorithm 1 shows “Input: The training set Z.” The training set are training samples. Zhang page 4639 last paragraph section IV(A) discloses “All samples were divided into 75%, 5%, and 20% proportions for training, validation, and testing.” The training, validation, and testing samples correspond with training samples, verification samples, and test samples, respectively.
Claim 1 further recites “a third step establishing a BTP prediction model based on the encoder-decoder network, and training the model by means of the training samples.” The encoder-decoder network is interpreted in light of Specification paragraph 18.
Zhang page 4639 right column first paragraph discloses “once the training work is performed by using the training set.” See also Zhang Algorithm 1. Performing the training corresponds to establishing the BTP prediction model by means of the training samples.
Zhang abstract discloses “DCGNet uses convolutional neural networks and gated recurrent unit (GRU) to extract the local spatial-temporal dependence patterns among the multivariates, and another parallel GRU using the historical ST data as input.” The DCGNet using CNN and GRUs corresponds with the encoder-decoder network.
Claim 1 further recites “and a fourth step reading, at current time
k
, on-line historical data from time
k
-
t
h
to time
k
in real time from a sensor and the database, collecting and preprocessing the auxiliary variables; reading the data of the exhaust-gas temperatures in the bellows from the time
k
-
t
h
to time
k
, calculating BTP and BRP with a least square method.” Zhang page 4637 left column sixth paragraph disclose “We aim to predict the next signals in a rolling forecasting fashion. Assuming that [..] are available, we estimate the ST at the next moment, thus predicting y(t+1).” Prediction in a rolling fashion of a next moment correspond with a online/real-time measurement and prediction.
Zhang page 4639 section III(C) disclose “the mean squared error loss function is used for optimization in model training.” A mean squared error loss function corresponds with a least square method.
Claim 1 further recites “segmenting the data with the sliding window method to obtain data segments and establish a many-to-many sequence data set from the time
k
-
t
h
to time
k
.” Zhang page 4637 left column sixth paragraph discloses “where τ is the correlative time interval of the thermal process data.” The time interval for the process variables and estimated state corresponds with a time window of a sliding window method. The data sets X and y correspond with an established many-to-many sequence of data. See also Zhang algorithm 1 input.
Claim 1 further recites “and inputting the many-to-many sequence data set into the trained BTP prediction model to obtain a BTP prediction result within a next prediction time length
t
f
from the time
k
.” Zhang page 4639 right column last line discloses “the predicted results.” The predicted results of the DCGNet correspond with inputting respective data into the model and obtaining the respective prediction results.
Claim 3 further recites “3. The method for predicting BTP based on the encoder-decoder network according to claim 1, wherein, in the first step, reading the data of the exhaust-gas temperatures in the bellows from the database and calculating BTP and BRP with the polynomial fitting method comprises: regarding the exhaust-gas temperature
T
i
and a position
x
i
of the bellows at a vicinity of BTP as a quadratic relation which satisfies a first formula:
T
i
=
a
x
i
2
+
b
x
i
+
c
i
=
1,2
,
…
,
m
substituting the positions and the exhaust-gas temperatures,
x
i
,
T
i
, of last three bellows into the first formula to obtain a linear equation set of the exhaust-gas temperatures and the positions of the bellows, wherein a subscript i represents an ith bellows to a last bellows; and solving the linear equation set to obtain a:
a
=
T
1
-
T
2
x
1
-
x
2
-
T
2
-
T
3
x
2
-
x
3
x
1
-
x
3
then solving the linear equation set to obtain b:
b
=
T
1
-
T
2
x
1
-
x
2
-
a
x
1
+
x
2
then:
c
=
T
i
-
a
x
i
2
-
b
x
i
obtaining BTP by means of the equations as follows:
x
m
a
x
=
-
b
2
a
wherein, BRP refers to a position where the exhaust-gas temperature rise in a length direction of a sintering machine, and the position
x
k
corresponding to the exhaust-gas temperature
T
k
of 1800ºC is solved based on a following formula:
T
k
=
a
x
k
2
+
b
x
k
+
c
.
Zhang does not explicitly disclose calculating a BTP and BRP with a polynomial fitting; however, in analogous art of predicting sintering endpoint, Li abstract teaches “The math model will be built based on the relation of measurable variables with BTP to judge the BTP online. Quadratic curve is fitted according to three measured points including the highest waste gas in five windboxes at discharge end.”
Li discloses the respective claimed equations with Li page 2. In particular Li equations (1)-(3).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to combine Zhang and Li. One having ordinary skill in the art would have found motivation to use quadratic curve fitting into the system of multivariate modeling for forecasting sintering temperature using DCGNet for the advantageous purpose of “to measure BTP online,” also known as in real-time. See Li abstract.
Claim 4 further recites “4. The method for predicting BTP based on the encoder-decoder network according to claim 1, wherein, in the second step, sampling is performed with a sliding time window segment method, and each input segment sample is expressed as a matrix:
X
∈
R
T
h
×
f
wherein,
T
h
represents a number of frames of an observation segment,
f
represents a number of features of the segment; and an output sample Y is set to correspond to each input sample X:
Y
∈
R
T
f
×
f
.
Zhang page 4637 left column sixth paragraph disclose:
In this article, time-series forecasting is focused on multiple input variates and a singular prediction output. More formally, a series of process variates
X
=
x
1
,
…
,
x
i
and
y
as the variate to be estimated [Sintering Temperature (ST)] are given, where
X
∈
R
N
×
i
,
y
∈
R
,
i
is the variable dimension, and
N
is the number of samples collected by the DCS. …., where
τ
is the correlative t time interval of the thermal process data.
Here, Zhang’s X and y correspond with claimed X and Y. The number of samples N corresponds with a number of frames. The variable dimension index
i
corresponds with a number of features.
Claim 5 further recites “5. The method for predicting BTP based on the encoder-decoder network according to claim 1, wherein, in the third step, establishing the BTP prediction model based on the encoder-decoder network comprises: establishing the model by means of a encoder-decoder framework, wherein an encoder is established by means of a gated recurrent unit (GRU).” Zhang abstract discloses “DCGNet uses convolutional neural networks and gated recurrent unit (GRU) to extract the local spatial-temporal dependence patterns among the multivariates, and another parallel GRU using the historical ST data as input.”
Claim 5 further recites “and feature data are input in time series to obtain an output, namely an advanced feature, of the encoder.” Zhang page 4637 left column sixth paragraph disclose:
In this article, time-series forecasting is focused on multiple input variates and a singular prediction output. More formally, a series of process variates
X
=
x
1
,
…
,
x
i
and
y
as the variate to be estimated [Sintering Temperature (ST)] are given, where
X
∈
R
N
×
i
,
y
∈
R
,
i
is the variable dimension, and
N
is the number of samples collected by the DCS.
Time-series forecasting is with time series as an input.
Claim 5 further recites “then calculating a correlation between a hidden state vector and an advanced feature vector of a decoder by means of a temporal attention mechanism to obtain a weight coefficient between them; and calculating a correlation between an output label and the advanced feature by means of a spatial attention mechanism to establish a potential correlation between an object variable and the advanced feature.” Zhang page 4639 section III(C) disclose “the mean squared error loss function is used for optimization in model training.” Zhang page 4639 Algorithm 1 step 6 discloses “Calculate the loss introduced in Eq. (1) between the prediction and targets” and “Backward Propagation: Compute the gradient by using Adam, and update the weight matrix and bias vector.” The loss function between prediction and target is a calculated correlation. Updating the weight matrix corresponds to obtaining respective weight coefficients. Training the DCGNet model corresponds with establishing correlation between the input object variables and the predicted targets.
Zhang page 4638 right column discloses “the space-time coupling features” and third paragraph discloses “After the feature extraction of two convolutional layers, a GRU layer is added to store time information about the important characteristics of multivariate variates.” Zhang page 4638 further discloses equations (6)-(7). A space-time coupling corresponds with a temporal and spatial coupling. The respective calculations of h correspond with an attention mechanism of the GRU.
Claim 6 further recites “6. The method for predicting BTP based on the encoder-decoder network according to claim 1, wherein parameters of the BTP prediction model are adjusted in real time according to real-time data of the sintering process for continuous iteration and optimization, so that the model has high robustness.” Zhang page 4639 left column last paragraph disclose “the new weight is obtained through the parameter update process. The model weights are calculated iteratively until a predetermined small loss is reached, and the optimal predicted value is obtained.” Zhang page 4640 middle discloses “All methods use a backpropagation algorithm to continuously adjust the weight matrix and bias between the hidden and output layers.” Continuously adjusting and iteratively updating model weights corresponds with adjusting the model in real-time with a continuous iteration and optimization. Zhang page 4643 section IV(D) discloses “to verify the robustness of our proposed DCGNetmodel.”
Allowable Subject Matter
Claim 2 would be allowable if rewritten to overcome the rejection(s) under 35 U.S.C. §101 and under 35 U.S.C. §112(b) or 35 U.S.C. §112 (pre-AIA ), 2nd paragraph, set forth in this Office action and to include all of the limitations of the base claim and any intervening claims.
The following is a statement of reasons for the indication of allowable subject matter:
Zhang, X., et al. “Multivariate Time-Series Modeling for Forecasting Sintering Temperature in Rotary Kilns Using DCGNet” IEEE Transactions on Industrial Informatics, vol. 17, no. 7 (July 2021) [herein “Zhang”] page 4640 table I teaches various thermal variables for a rotary kiln. Zhang page 4636 right column section II teach “High silica bauxite, soda ash, lime, etc., are mixed and grounded into a raw material slurry in a certain proportion.” A proportion is a ratio. But Zhang fails to teach a quicklime ratio, limestone ratio, or a dolomite-water ratio.
Li, M.H. & Wang, J. “The Research for Soft Measuring Technique of Sintering Burning Through Point” IEEE 1st Conf. on Industrial Electronics & Applications (2006) [herein “Li”] abstract teaches measuring BTP using a quadratic curve fitting on exhaust gas. But Li fails to teach a quicklime ratio, limestone ratio, or a dolomite-water ratio.
Wang, J., et al. “BTP Prediction of Sintering Process by Using Multiple Models” IEEE 26th Chinese Control & Decision Conf., pp. 4008-4012 (2014) [herein “Wang”] abstract teaches a fuzzy neural network for predicting burning through point BTP. Wang page 4010 section 3.2 teaches using sintering trolley velocity along with exhaust gas temperatures as variables to predict BTP. But Wang fails to teach a quicklime ratio, limestone ratio, or a dolomite-water ratio..
CN 113111571 A Chang, et al. [herein “Chang”] [Citations to Chang herein refer to the attached English machine translation thereof] page 5 [n0012] teaches “Based on the quadratic relationship between the sintering endpoint and the exhaust gas temperature of the front and rear air boxes, and since the sintering endpoint is the highest point of the curve, the temperature of each air box is fitted to the curve and the temperature curve is plotted.” But Chang fails to teach a quicklime ratio, limestone ratio, or a dolomite-water ratio.
Wu, X., et al. “Prediction of Sinter Burn-Through Point Based on Support Vector Machines” Intelligent Control & Automation, Int’l Conf. on Intelligent Computing, ICIC (2006) [herein “Wu”] teaches predicting sinter burn-through point using SVM. Wu section 1 first paragraph teaches “The raw mix in the form of small pellets composed essentially of ore, coke and water.” But Wu fails to teach a quicklime ratio, limestone ratio, or a dolomite-water ratio.
Wu, Z. & Zhou, P. “Feature selection of Wrapper based on GA and prediction of Burning Through Point of integrated multi-kernel support vector machine” IEEE 33rd Chinese Control & Decision Conf., pp.618-623 (May 2021) [herein “Wu 2021”] section I Introduction first paragraph teaches “In the sintering process, iron ore powder, coke powder, flux (limestone, dolomite) and returned ore are mixed in a certain proportion, and then granulated by mixing and adding water for the first time and then mixing and adding water for the second time.” While Wu teaches limestone and dolomite in the alternative, Wu fails to teach using quicklime, limestone, and dolomite together. Furthermore, while Wu does teach mixing with water, Wu fails to teach a dolomite-water ratio used as an auxiliary variable.
Cao, W., et al. “A dynamic subspace model for predicting burn-through point in iron sintering process” Information Sciences, vol. 466, pp. 1-12 (2018) page 3 section 2.3 teaches “It is clear from Sections 2.2 and 2.3 that the BTP is not only based on sintering process parameters (process parameters hereafter), such as the pallet velocity, thickness of the material layer, and negative pressure of bellows; but it is also related to the EGTs at previous bellows, which are process conditions parameters.” Cao page 2 section 2.1 teaches “The raw material, which contains limestone, ore, coke.” But Cao fails to teach a quicklime ratio, limestone ratio, or a dolomite-water ratio.
US patent 7,968,044 B2 Rocha, et al. [herein “Rocha”] teaches technology background on a sintering process line. See Rocha figure 3 and Rocha column 3 lines 51-64. Rocha column 3 lines 42-45 teach “The input materials 19-22 typically comprise an oxide source such as raw ore 19 and iron waste products 20. In addition, a flux material such as limestone as well as a fuel material such as coke 22.” While Rocha teaches a limestone flux, Rocha fails to teach dolomite and fails to teach quicklime (in addition to the limestone). Furthermore, Rocha fails to teach a variable of a dolomite to water ratio.
None of the references taken either alone or in combination with the prior art of record disclose “a quicklime ratio, a limestone ratio, a dolomite-water ratio, …, and BRP” in combination with the remaining elements and features of the claimed invention.
Note, the auxiliary variables of claim 2 are not written in the alternative (i.e., there is no “or,” instead the listing ends “and BRP”). Accordingly, claim 2 currently requires each auxiliary variable recited in the claim.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Jay B Hann whose telephone number is (571)272-3330. The examiner can normally be reached M-F 10am-7pm EDT.
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, Renee Chavez can be reached at (571) 270-1104. 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.
/Jay Hann/Primary Examiner, Art Unit 2186 12 December 2025