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 .
Priority
The present application claims priority based on Patent Application No. 63/383,176, filed on 11/10/2022
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1 – 20 are rejected under 35 U.S.C. 101 because the claimed invention is directed
to an abstract idea without significantly more. The following sections follow the 2019 PEG
guidelines for analyzing subject matter eligibility.
The analysis below of the claims’ subject matter eligibility follows the 2019 Revised
Patent Subject Matter Eligibility Guidance, 84 Fed. Reg. 50-57 (January 7, 2019) (“2019 PEG”)
and the 2024 Guidance Update on Patent Subject Matter Eligibility, Including on Artificial
Intelligence, 89 Fed. Reg. 58128-58138 (July 17, 2024) (“2024 AI SME Update”).
When considering subject matter eligibility under 35 U.S.C. 101, it must be determined
whether the claim is directed to one of the four statutory categories of invention, i.e., process,
machine, manufacture, or composition of matter (Step 1). If the claim does fall within one of the
statutory categories, the second step in the analysis is to determine whether the claim is directed
to a judicial exception (Step 2A). The Step 2A analysis is broken into two prongs. In the first
prong (Step 2A, Prong 1), it is determined whether or not the claims recite a judicial exception
(e.g., mathematical concepts, mental processes, certain methods of organizing human activity). If
it is determined in Step 2A, Prong 1 that the claims recite a judicial exception, the analysis proceeds to the second prong (Step 2A, Prong 2), where it is determined whether or not the
claims integrate the judicial exception into a practical application. If it is determined at step 2A,
Prong 2 that the claims do not integrate the judicial exception into a practical application, the
analysis proceeds to determining whether the claim is a patent-eligible application of the
exception (Step 2B). If an abstract idea is present in the claim, any element or combination of
elements in the claim must be sufficient to ensure that the claim integrates the judicial exception
into a practical application, or else amounts to significantly more than the abstract idea itself.
Claim 1
Step 1: The claim recites a non-transitory computer readable medium, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1:
generating second subsets of training data at least by: (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
selecting the second subsets of training data from among the first subsets of training data; (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
applying noise to the second subsets of training data; and (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
for each subset of the second subsets of training data, applying a label identifying the subset as false operating data; (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
generate predicted target operating data; and (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
comparing a first value of a first data point of the received particular time series operating data with a second value corresponding to a predicted target operating data value associated with the first data point; and (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
based on determining a difference between the first value and the second value exceeds a threshold, identifying the first value as anomalous. (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
Step 2A Prong 2: The judicial exceptions are not integrated into a practical application. In particular, the claim recites these additional elements:
training a machine learning model to predict target operating values for monitored devices, the training comprising: (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
obtaining first subsets of training data comprising historical operating data for one or more monitored devices, each first subset of training data comprising: time-series operating values for the one or more monitored devices; and for each subset of the first subset of training data, a label identifying the subset as real operating data; (Mere data gathering, Insignificant extra solution activity in MPEP § 2106.05(g))
training the machine learning model based on the first subsets of training data and the second subsets of training data; (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
receiving particular time series operating data associated with a first monitored device; (Mere data gathering, Insignificant extra solution activity in MPEP § 2106.05(g))
applying the machine learning model to the particular time series operating data to (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
Step 2B: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
training a machine learning model to predict target operating values for monitored devices, the training comprising: (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
obtaining first subsets of training data comprising historical operating data for one or more monitored devices, each first subset of training data comprising: time-series operating values for the one or more monitored devices; and for each subset of the first subset of training data, a label identifying the subset as real operating data; (receiving or transmitting data, using components and functions claimed at a high level of generality have been determined by the courts as being well-understood, routine, and conventional activities in the field of computer functions (See MPEP § 2106.05(d)(II)(i))
training the machine learning model based on the first subsets of training data and the second subsets of training data; (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
receiving particular time series operating data associated with a first monitored device; (receiving or transmitting data, using components and functions claimed at a high level of generality have been determined by the courts as being well-understood, routine, and conventional activities in the field of computer functions (See MPEP § 2106.05(d)(II)(i))
applying the machine learning model to the particular time series operating data to (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
The courts have found that adding the words "apply it" (or an equivalent) with the
judicial exception, or mere instructions to implement an abstract idea on a computer does not
qualify as “significantly more”. (See MPEP § 2106.05(I)(A))
The courts have found that generally linking the use of the judicial exceptions to a
particular technological environment or field of use does not qualify as “significantly more”. (See MPEP § 2106.05(I)(A))
As an ordered whole, the claim is directed to method of predictive modeling, this is
nothing more than using machine learning models to classify the provided data. Nothing in the
claim provides significantly more than this. As such, the claim is not patent eligible.
Claim 2 incorporates the rejections of claim 1.
Step 1: The claim recites a non-transitory computer readable medium, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1: The judicial exceptions of claim 1 are incorporated.
comparing a third value of a second data point of the received particular time series operating data with a fourth value corresponding to a predicted target operating data value associated with the second data point; (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
based on determining a difference between the third value and the fourth value exceeds the threshold, identifying the third value as anomalous; (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
responsive to determining the difference between the first value and the second value exceeds the threshold by a first amount, assigning a first weight to the first value; (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
responsive to determining the difference between the third value and the fourth value exceeds the threshold by a second amount, assigning a second weight to the third value; (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
performing a remediation operation associated with the first value based on determining the first weight meets a remediation criteria; and (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
refraining from performing any remediation operation associated with the third value based on determining the second weight does not meet the remediation criteria. (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
Step 2A Prong 2: The judicial exceptions are not integrated into a practical application. In
particular, the claim recites these additional elements:
The claim does not recite any additional limitations. Therefore, there are no additional elements to integrate the abstract ideas into a practical applications. (Merely asserting that a judicial exception is to be carried out on a generic computer (i.e., “determine actions based on criteria” of base claim 1) cannot meaningfully integrate the judicial exceptions into a practical application. See MPEP § 2106.05(f))
Step 2B: The claim does not include additional elements that are sufficient to amount to
significantly more than the judicial exception.
The claim does not include additional elements that are sufficient to amount to
significantly more than the judicial exception. Mere instructions to apply an exception (i.e.,
“determine actions based on criteria” of base claim 1) cannot provide
an inventive concept. The claim is not patent eligible.
Claim 3 incorporates the rejections of claim 1.
Step 1: The claim recites a non-transitory computer readable medium, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1: The judicial exceptions of claim 1 are incorporated. Please see the analysis of
claim 1 above. Regarding the method steps recited in claim 1, these steps cover mental
processes based on comparing data.
Therefore, claim 3 is directed to an abstract idea – Mental Processes (i.e., can be performed in
the human mind, or by a human using a pen and paper, making observations, evaluations and
judgments as claimed)
Step 2A Prong 2: The judicial exceptions are not integrated into a practical application. In
particular, the claim recites these additional elements
wherein each first subset of training data further comprises attributes associated with the one or more monitored devices, the attributes including at least weather conditions in a vicinity of the one or more monitored devices. (Field of use and technological environment, it does no more than generally link a judicial exception to a particular technological environment. MPEP § 2106.05(h))
Step 2B: The claim does not include additional elements that are sufficient to amount to
significantly more than the judicial exception.
wherein each first subset of training data further comprises attributes associated with the one or more monitored devices, the attributes including at least weather conditions in a vicinity of the one or more monitored devices. (Field of use and technological environment, it does no more than generally link a judicial exception to a particular technological environment. MPEP § 2106.05(h))
The courts have found that generally linking the use of the judicial exceptions to a
particular technological environment or field of use does not qualify as “significantly more”. (See MPEP § 2106.05(I)(A))
Claim 4 incorporates the rejections of claim 3.
Step 1: The claim recites a non-transitory computer readable medium, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1: The judicial exceptions of claim 3 are incorporated. Please see the analysis of
claim 3 above. Regarding the method steps recited in claim 3, these steps cover mental
processes based on comparing data.
Therefore, claim 4 is directed to an abstract idea – Mental Processes (i.e., can be performed in
the human mind, or by a human using a pen and paper, making observations, evaluations and
judgments as claimed)
Step 2A Prong 2: The judicial exceptions are not integrated into a practical application. In
particular, the claim recites these additional elements
wherein the attributes associated with the one or more monitored devices further include at least one of: temperature data, dewpoint data, dwelling type data, and demographic data. (Field of use and technological environment, it does no more than generally link a judicial exception to a particular technological environment. MPEP § 2106.05(h))
Step 2B: The claim does not include additional elements that are sufficient to amount to
significantly more than the judicial exception.
wherein the attributes associated with the one or more monitored devices further include at least one of: temperature data, dewpoint data, dwelling type data, and demographic data. (Field of use and technological environment, it does no more than generally link a judicial exception to a particular technological environment. MPEP § 2106.05(h))
The courts have found that generally linking the use of the judicial exceptions to a
particular technological environment or field of use does not qualify as “significantly more”. (See MPEP § 2106.05(I)(A))
Claim 5 incorporates the rejections of claim 1.
Step 1: The claim recites a non-transitory computer readable medium, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1: The judicial exceptions of claim 1 are incorporated.
selecting a set of data points from among the first subsets of training data; (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
randomly selecting an addition operation or a subtraction operation to be performed; and (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
based on the randomly selected addition or subtraction operation, applying a random positive variation or a random negative variation, within a threshold level of variation, to a value of each data points in the selected set of data points. (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
Step 2A Prong 2: The judicial exceptions are not integrated into a practical application. In
particular, the claim recites these additional elements
The claim does not recite any additional limitations. Therefore, there are no additional elements to integrate the abstract ideas into a practical applications. (Merely asserting that a judicial exception is to be carried out on a generic computer (i.e., “randomly applying a positive or negative operation to a set of data” of base claim 1) cannot meaningfully integrate the judicial exceptions into a practical application. See MPEP § 2106.05(f))
Step 2B: The claim does not include additional elements that are sufficient to amount to
significantly more than the judicial exception.
The claim does not include additional elements that are sufficient to amount to
significantly more than the judicial exception. Mere instructions to apply an exception (i.e.,
“randomly applying a positive or negative operation to a set of data” of base claim 1) cannot provide an inventive concept. The claim is not patent eligible.
Claim 6 incorporates the rejections of claim 1.
Step 1: The claim recites a non-transitory computer readable medium, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1: The judicial exceptions of claim 1 are incorporated.
based on the location data, identifying a weather sensor within a threshold distance of the first monitored device; (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
Step 2A Prong 2: The judicial exceptions are not integrated into a practical application. In
particular, the claim recites these additional elements
receiving time series operation values and location data associated with the first monitored device; (Mere data gathering, Insignificant extra solution activity in MPEP § 2106.05(g))
obtaining weather data generated by the weather sensor associated with the received time series operation values; and (Mere data gathering, Insignificant extra solution activity in MPEP § 2106.05(g))
generating vectors including the time series operation values and the weather data, (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
wherein the machine learning model is applied to the vectors. (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
Step 2B: The claim does not include additional elements that are sufficient to amount to
significantly more than the judicial exception.
receiving time series operation values and location data associated with the first monitored device; (receiving or transmitting data, using components and functions claimed at a high level of generality have been determined by the courts as being well-understood, routine, and conventional activities in the field of computer functions (See MPEP § 2106.05(d)(II)(i))
obtaining weather data generated by the weather sensor associated with the received time series operation values; and (receiving or transmitting data, using components and functions claimed at a high level of generality have been determined by the courts as being well-understood, routine, and conventional activities in the field of computer functions (See MPEP § 2106.05(d)(II)(i))
generating vectors including the time series operation values and the weather data, (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
wherein the machine learning model is applied to the vectors. (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
The courts have found that adding the words "apply it" (or an equivalent) with the
judicial exception, or mere instructions to implement an abstract idea on a computer does not
qualify as “significantly more”. (See MPEP § 2106.05(I)(A))
Claim 7 incorporates the rejections of claim 1.
Step 1: The claim recites a non-transitory computer readable medium, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1: The judicial exceptions of claim 1 are incorporated. Please see the analysis of
claim 1 above. Regarding the method steps recited in claim 1, these steps cover mental
processes based on comparing data.
Therefore, claim 7 is directed to an abstract idea – Mental Processes (i.e., can be performed in
the human mind, or by a human using a pen and paper, making observations, evaluations and
judgments as claimed)
Step 2A Prong 2: The judicial exceptions are not integrated into a practical application. In
particular, the claim recites these additional elements
wherein the machine learning model is based on a deep learning long short-term memory (LSTM) type model. (Field of use and technological environment, it does no more than generally link a judicial exception to a particular technological environment. MPEP § 2106.05(h))
Step 2B: The claim does not include additional elements that are sufficient to amount to
significantly more than the judicial exception.
wherein the machine learning model is based on a deep learning long short-term memory (LSTM) type model. (Field of use and technological environment, it does no more than generally link a judicial exception to a particular technological environment. MPEP § 2106.05(h))
The courts have found that generally linking the use of the judicial exceptions to a
particular technological environment or field of use does not qualify as “significantly more”. (See MPEP § 2106.05(I)(A))
Claim 8 incorporates the rejections of claim 1.
Step 1: The claim recites a non-transitory computer readable medium, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1: The judicial exceptions of claim 1 are incorporated.
comparing a third value of a second data point of the received particular time series operating data with a fourth value corresponding to a predicted target operating data value associated with the second data point; and (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
based on determining a difference between the third value and the fourth value does not exceed the threshold, identifying the third value as non-anomalous. (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
Step 2A Prong 2: The judicial exceptions are not integrated into a practical application. In
particular, the claim recites these additional elements
The claim does not recite any additional limitations. Therefore, there are no additional elements to integrate the abstract ideas into a practical applications. (Merely asserting that a judicial exception is to be carried out on a generic computer (i.e., “classifying values based on a threshold” of base claim 1) cannot meaningfully integrate the judicial exceptions into a practical application. See MPEP § 2106.05(f))
Step 2B: The claim does not include additional elements that are sufficient to amount to
significantly more than the judicial exception.
The claim does not include additional elements that are sufficient to amount to
significantly more than the judicial exception. Mere instructions to apply an exception (i.e.,
“classifying values based on a threshold” of base claim 1) cannot provide
an inventive concept. The claim is not patent eligible.
Claim 9 incorporates the rejections of claim 1.
Step 1: The claim recites a non-transitory computer readable medium, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1: The judicial exceptions of claim 1 are incorporated.
associating a monetary value with a particular user account corresponding to the first monitored device; and (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
based on determining the first value of the first data point is anomalous: omitting from the monetary value associated with the particular user account a first monetary value associated with the first value of the first data point. (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
Step 2A Prong 2: The judicial exceptions are not integrated into a practical application. In
particular, the claim recites these additional elements
based on operating values of the first monitored device over a defined period of time (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
Step 2B: The claim does not include additional elements that are sufficient to amount to
significantly more than the judicial exception.
based on operating values of the first monitored device over a defined period of time (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
The courts have found that adding the words "apply it" (or an equivalent) with the
judicial exception, or mere instructions to implement an abstract idea on a computer does not
qualify as “significantly more”. (See MPEP § 2106.05(I)(A))
Claim 10 incorporates the rejections of claim 1.
Step 1: The claim recites a non-transitory computer readable medium, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1: The judicial exceptions of claim 1 are incorporated. Please see the analysis of
claim 1 above. Regarding the method steps recited in claim 1, these steps cover mental
processes based on comparing data.
Therefore, claim 10 is directed to an abstract idea – Mental Processes (i.e., can be performed in
the human mind, or by a human using a pen and paper, making observations, evaluations and
judgments as claimed)
Step 2A Prong 2: The judicial exceptions are not integrated into a practical application. In
particular, the claim recites these additional elements
wherein the time series operating data comprises power data measured by a power utility meter at a particular location. (Field of use and technological environment, it does no more than generally link a judicial exception to a particular technological environment. MPEP § 2106.05(h))
Step 2B: The claim does not include additional elements that are sufficient to amount to
significantly more than the judicial exception.
wherein the time series operating data comprises power data measured by a power utility meter at a particular location. (Field of use and technological environment, it does no more than generally link a judicial exception to a particular technological environment. MPEP § 2106.05(h))
The courts have found that generally linking the use of the judicial exceptions to a
particular technological environment or field of use does not qualify as “significantly more”. (See MPEP § 2106.05(I)(A))
Claim 11
Step 1: The claim recites a method, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1:
generating second subsets of training data at least by: (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
selecting the second subsets of training data from among the first subsets of training data; (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
applying noise to the second subsets of training data; and (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
for each subset of the second subsets of training data, applying a label identifying the subset as false operating data; (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
generate predicted target operating data; and (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
comparing a first value of a first data point of the received particular time series operating data with a second value corresponding to a predicted target operating data value associated with the first data point; and (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
based on determining a difference between the first value and the second value exceeds a threshold, identifying the first value as anomalous. (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
Step 2A Prong 2: The judicial exceptions are not integrated into a practical application. In particular, the claim recites these additional elements:
training a machine learning model to predict target operating values for monitored devices, the training comprising: (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
obtaining first subsets of training data comprising historical operating data for one or more monitored devices, each first subset of training data comprising: time-series operating values for the one or more monitored devices; and for each subset of the first subset of training data, a label identifying the subset as real operating data; (Mere data gathering, Insignificant extra solution activity in MPEP § 2106.05(g))
training the machine learning model based on the first subsets of training data and the second subsets of training data; (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
receiving particular time series operating data associated with a first monitored device; (Mere data gathering, Insignificant extra solution activity in MPEP § 2106.05(g))
applying the machine learning model to the particular time series operating data to (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
Step 2B: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
training a machine learning model to predict target operating values for monitored devices, the training comprising: (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
obtaining first subsets of training data comprising historical operating data for one or more monitored devices, each first subset of training data comprising: time-series operating values for the one or more monitored devices; and for each subset of the first subset of training data, a label identifying the subset as real operating data; (receiving or transmitting data, using components and functions claimed at a high level of generality have been determined by the courts as being well-understood, routine, and conventional activities in the field of computer functions (See MPEP § 2106.05(d)(II)(i))
training the machine learning model based on the first subsets of training data and the second subsets of training data; (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
receiving particular time series operating data associated with a first monitored device; (receiving or transmitting data, using components and functions claimed at a high level of generality have been determined by the courts as being well-understood, routine, and conventional activities in the field of computer functions (See MPEP § 2106.05(d)(II)(i))
applying the machine learning model to the particular time series operating data to (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
The courts have found that adding the words "apply it" (or an equivalent) with the
judicial exception, or mere instructions to implement an abstract idea on a computer does not
qualify as “significantly more”. (See MPEP § 2106.05(I)(A))
The courts have found that generally linking the use of the judicial exceptions to a
particular technological environment or field of use does not qualify as “significantly more”. (See MPEP § 2106.05(I)(A))
As an ordered whole, the claim is directed to method of predictive modeling, this is
nothing more than using machine learning models to classify the provided data. Nothing in the
claim provides significantly more than this. As such, the claim is not patent eligible.
Claim 12 incorporates the rejections of claim 11.
Step 1: The claim recites a method, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1: The judicial exceptions of claim 11 are incorporated.
comparing a third value of a second data point of the received particular time series operating data with a fourth value corresponding to a predicted target operating data value associated with the second data point; (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
based on determining a difference between the third value and the fourth value exceeds the threshold, identifying the third value as anomalous; (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
responsive to determining the difference between the first value and the second value exceeds the threshold by a first amount, assigning a first weight to the first value; (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
responsive to determining the difference between the third value and the fourth value exceeds the threshold by a second amount, assigning a second weight to the third value; (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
performing a remediation operation associated with the first value based on determining the first weight meets a remediation criteria; and (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
refraining from performing any remediation operation associated with the third value based on determining the second weight does not meet the remediation criteria. (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
Step 2A Prong 2: The judicial exceptions are not integrated into a practical application. In
particular, the claim recites these additional elements:
The claim does not recite any additional limitations. Therefore, there are no additional elements to integrate the abstract ideas into a practical applications. (Merely asserting that a judicial exception is to be carried out on a generic computer (i.e., “determine actions based on criteria” of base claim 11) cannot meaningfully integrate the judicial exceptions into a practical application. See MPEP § 2106.05(f))
Step 2B: The claim does not include additional elements that are sufficient to amount to
significantly more than the judicial exception.
The claim does not include additional elements that are sufficient to amount to
significantly more than the judicial exception. Mere instructions to apply an exception (i.e.,
“determine actions based on criteria” of base claim 11) cannot provide
an inventive concept. The claim is not patent eligible.
Claim 13 incorporates the rejections of claim 11.
Step 1: The claim recites a method, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1: The judicial exceptions of claim 11 are incorporated. Please see the analysis of
claim 11 above. Regarding the method steps recited in claim 11, these steps cover mental
processes based on comparing data.
Therefore, claim 13 is directed to an abstract idea – Mental Processes (i.e., can be performed in
the human mind, or by a human using a pen and paper, making observations, evaluations and
judgments as claimed)
Step 2A Prong 2: The judicial exceptions are not integrated into a practical application. In
particular, the claim recites these additional elements
wherein each first subset of training data further comprises attributes associated with the one or more monitored devices, the attributes including at least weather conditions in a vicinity of the one or more monitored devices. (Field of use and technological environment, it does no more than generally link a judicial exception to a particular technological environment. MPEP § 2106.05(h))
Step 2B: The claim does not include additional elements that are sufficient to amount to
significantly more than the judicial exception.
wherein each first subset of training data further comprises attributes associated with the one or more monitored devices, the attributes including at least weather conditions in a vicinity of the one or more monitored devices. (Field of use and technological environment, it does no more than generally link a judicial exception to a particular technological environment. MPEP § 2106.05(h))
The courts have found that generally linking the use of the judicial exceptions to a
particular technological environment or field of use does not qualify as “significantly more”. (See MPEP § 2106.05(I)(A))
Claim 14 incorporates the rejections of claim 13.
Step 1: The claim recites a non-transitory computer readable medium, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1: The judicial exceptions of claim 13 are incorporated. Please see the analysis of
claim 13 above. Regarding the method steps recited in claim 13, these steps cover mental
processes based on comparing data.
Therefore, claim 14 is directed to an abstract idea – Mental Processes (i.e., can be performed in
the human mind, or by a human using a pen and paper, making observations, evaluations and
judgments as claimed)
Step 2A Prong 2: The judicial exceptions are not integrated into a practical application. In
particular, the claim recites these additional elements
wherein the attributes associated with the one or more monitored devices further include at least one of: temperature data, dewpoint data, dwelling type data, and demographic data. (Field of use and technological environment, it does no more than generally link a judicial exception to a particular technological environment. MPEP § 2106.05(h))
Step 2B: The claim does not include additional elements that are sufficient to amount to
significantly more than the judicial exception.
wherein the attributes associated with the one or more monitored devices further include at least one of: temperature data, dewpoint data, dwelling type data, and demographic data. (Field of use and technological environment, it does no more than generally link a judicial exception to a particular technological environment. MPEP § 2106.05(h))
The courts have found that generally linking the use of the judicial exceptions to a
particular technological environment or field of use does not qualify as “significantly more”. (See MPEP § 2106.05(I)(A))
Claim 15 incorporates the rejections of claim 11.
Step 1: The claim recites a method, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1: The judicial exceptions of claim 1 are incorporated.
selecting a set of data points from among the first subsets of training data; (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
randomly selecting an addition operation or a subtraction operation to be performed; and (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
based on the randomly selected addition or subtraction operation, applying a random positive variation or a random negative variation, within a threshold level of variation, to a value of each data points in the selected set of data points. (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
Step 2A Prong 2: The judicial exceptions are not integrated into a practical application. In
particular, the claim recites these additional elements
The claim does not recite any additional limitations. Therefore, there are no additional elements to integrate the abstract ideas into a practical applications. (Merely asserting that a judicial exception is to be carried out on a generic computer (i.e., “randomly applying a positive or negative operation to a set of data” of base claim 11) cannot meaningfully integrate the judicial exceptions into a practical application. See MPEP § 2106.05(f))
Step 2B: The claim does not include additional elements that are sufficient to amount to
significantly more than the judicial exception.
The claim does not include additional elements that are sufficient to amount to
significantly more than the judicial exception. Mere instructions to apply an exception (i.e.,
“randomly applying a positive or negative operation to a set of data” of base claim 11) cannot provide an inventive concept. The claim is not patent eligible.
Claim 16 incorporates the rejections of claim 11.
Step 1: The claim recites a method, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1: The judicial exceptions of claim 11 are incorporated.
based on the location data, identifying a weather sensor within a threshold distance of the first monitored device; (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
Step 2A Prong 2: The judicial exceptions are not integrated into a practical application. In
particular, the claim recites these additional elements
receiving time series operation values and location data associated with the first monitored device; (Mere data gathering, Insignificant extra solution activity in MPEP § 2106.05(g))
obtaining weather data generated by the weather sensor associated with the received time series operation values; and (Mere data gathering, Insignificant extra solution activity in MPEP § 2106.05(g))
generating vectors including the time series operation values and the weather data, (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
wherein the machine learning model is applied to the vectors. (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
Step 2B: The claim does not include additional elements that are sufficient to amount to
significantly more than the judicial exception.
receiving time series operation values and location data associated with the first monitored device; (receiving or transmitting data, using components and functions claimed at a high level of generality have been determined by the courts as being well-understood, routine, and conventional activities in the field of computer functions (See MPEP § 2106.05(d)(II)(i))
obtaining weather data generated by the weather sensor associated with the received time series operation values; and (receiving or transmitting data, using components and functions claimed at a high level of generality have been determined by the courts as being well-understood, routine, and conventional activities in the field of computer functions (See MPEP § 2106.05(d)(II)(i))
generating vectors including the time series operation values and the weather data, (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
wherein the machine learning model is applied to the vectors. (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
The courts have found that adding the words "apply it" (or an equivalent) with the
judicial exception, or mere instructions to implement an abstract idea on a computer does not
qualify as “significantly more”. (See MPEP § 2106.05(I)(A))
Claim 17 incorporates the rejections of claim 11.
Step 1: The claim recites a method, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1: The judicial exceptions of claim 11 are incorporated. Please see the analysis of
claim 11 above. Regarding the method steps recited in claim 11, these steps cover mental
processes based on comparing data.
Therefore, claim 17 is directed to an abstract idea – Mental Processes (i.e., can be performed in
the human mind, or by a human using a pen and paper, making observations, evaluations and
judgments as claimed)
Step 2A Prong 2: The judicial exceptions are not integrated into a practical application. In
particular, the claim recites these additional elements
wherein the machine learning model is based on a deep learning long short-term memory (LSTM) type model. (Field of use and technological environment, it does no more than generally link a judicial exception to a particular technological environment. MPEP § 2106.05(h))
Step 2B: The claim does not include additional elements that are sufficient to amount to
significantly more than the judicial exception.
wherein the machine learning model is based on a deep learning long short-term memory (LSTM) type model. (Field of use and technological environment, it does no more than generally link a judicial exception to a particular technological environment. MPEP § 2106.05(h))
The courts have found that generally linking the use of the judicial exceptions to a
particular technological environment or field of use does not qualify as “significantly more”. (See MPEP § 2106.05(I)(A))
Claim 18 incorporates the rejections of claim 11.
Step 1: The claim recites a method, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1: The judicial exceptions of claim 11 are incorporated.
comparing a third value of a second data point of the received particular time series operating data with a fourth value corresponding to a predicted target operating data value associated with the second data point; and (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
based on determining a difference between the third value and the fourth value does not exceed the threshold, identifying the third value as non-anomalous. (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
Step 2A Prong 2: The judicial exceptions are not integrated into a practical application. In
particular, the claim recites these additional elements
The claim does not recite any additional limitations. Therefore, there are no additional elements to integrate the abstract ideas into a practical applications. (Merely asserting that a judicial exception is to be carried out on a generic computer (i.e., “classifying values based on a threshold” of base claim 11) cannot meaningfully integrate the judicial exceptions into a practical application. See MPEP § 2106.05(f))
Step 2B: The claim does not include additional elements that are sufficient to amount to
significantly more than the judicial exception.
The claim does not include additional elements that are sufficient to amount to
significantly more than the judicial exception. Mere instructions to apply an exception (i.e.,
“classifying values based on a threshold” of base claim 11) cannot provide
an inventive concept. The claim is not patent eligible.
Claim 19 incorporates the rejections of claim 11.
Step 1: The claim recites a method, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1: The judicial exceptions of claim 11 are incorporated.
associating a monetary value with a particular user account corresponding to the first monitored device; and (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
based on determining the first value of the first data point is anomalous: omitting from the monetary value associated with the particular user account a first monetary value associated with the first value of the first data point. (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
Step 2A Prong 2: The judicial exceptions are not integrated into a practical application. In
particular, the claim recites these additional elements
based on operating values of the first monitored device over a defined period of time (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
Step 2B: The claim does not include additional elements that are sufficient to amount to
significantly more than the judicial exception.
based on operating values of the first monitored device over a defined period of time (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
The courts have found that adding the words "apply it" (or an equivalent) with the
judicial exception, or mere instructions to implement an abstract idea on a computer does not
qualify as “significantly more”. (See MPEP § 2106.05(I)(A))
Claim 20
Step 1: The claim recites a system, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1:
generating second subsets of training data at least by: (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
selecting the second subsets of training data from among the first subsets of training data; (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
applying noise to the second subsets of training data; and (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
for each subset of the second subsets of training data, applying a label identifying the subset as false operating data; (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
generate predicted target operating data; and (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
comparing a first value of a first data point of the received particular time series operating data with a second value corresponding to a predicted target operating data value associated with the first data point; and (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
based on determining a difference between the first value and the second value exceeds a threshold, identifying the first value as anomalous. (Mental Processes: Can be performed in the human mind, or by a human using a pen and paper, making observations, evaluations and judgments as claimed)
Step 2A Prong 2: The judicial exceptions are not integrated into a practical application. In particular, the claim recites these additional elements:
training a machine learning model to predict target operating values for monitored devices, the training comprising: (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
obtaining first subsets of training data comprising historical operating data for one or more monitored devices, each first subset of training data comprising: time-series operating values for the one or more monitored devices; and for each subset of the first subset of training data, a label identifying the subset as real operating data; (Mere data gathering, Insignificant extra solution activity in MPEP § 2106.05(g))
training the machine learning model based on the first subsets of training data and the second subsets of training data; (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
receiving particular time series operating data associated with a first monitored device; (Mere data gathering, Insignificant extra solution activity in MPEP § 2106.05(g))
applying the machine learning model to the particular time series operating data to (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
Step 2B: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
training a machine learning model to predict target operating values for monitored devices, the training comprising: (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
obtaining first subsets of training data comprising historical operating data for one or more monitored devices, each first subset of training data comprising: time-series operating values for the one or more monitored devices; and for each subset of the first subset of training data, a label identifying the subset as real operating data; (receiving or transmitting data, using components and functions claimed at a high level of generality have been determined by the courts as being well-understood, routine, and conventional activities in the field of computer functions (See MPEP § 2106.05(d)(II)(i))
training the machine learning model based on the first subsets of training data and the second subsets of training data; (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
receiving particular time series operating data associated with a first monitored device; (receiving or transmitting data, using components and functions claimed at a high level of generality have been determined by the courts as being well-understood, routine, and conventional activities in the field of computer functions (See MPEP § 2106.05(d)(II)(i))
applying the machine learning model to the particular time series operating data to (Mere instructions to apply an exception as it recites only the idea of a solution or outcome as discussed in MPEP § 2106.05(f))
The courts have found that adding the words "apply it" (or an equivalent) with the
judicial exception, or mere instructions to implement an abstract idea on a computer does not
qualify as “significantly more”. (See MPEP § 2106.05(I)(A))
The courts have found that generally linking the use of the judicial exceptions to a
particular technological environment or field of use does not qualify as “significantly more”. (See MPEP § 2106.05(I)(A))
As an ordered whole, the claim is directed to method of predictive modeling, this is
nothing more than using machine learning models to classify the provided data. Nothing in the
claim provides significantly more than this. As such, the claim is not patent eligible.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1, 7, 8, 11, 17, 18 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Rashid (NPL: Times-series data augmentation and deep learning for construction equipment activity recognition) in view of McDonnell (US 20230071667 A1)
Regarding claim 1, Rashid teaches training a machine learning model to predict target operating values for monitored devices, the training comprising: (See e.g. [P2:S1:C1], In this paper, the problem of identifying construction activities is tackled using long-short time memory (LSTM) network trained [training a machine learning model] with data captured by IMUs monitored devices from articulated elements of the equipment.) (See e.g. [P10:Fig. 11 & 12], predictions using the LSTM [predict target operating values])
obtaining first subsets of training data comprising historical operating data for one or more monitored devices, each first subset of training data comprising: (See e.g. [P4:S4:C1], First, raw sensor data are collected from IMUs [one or more monitored devices] mounted on different articulated elements of construction equipment. Then, test data are separated from the raw data [obtaining first subsets of training data comprising historical operating data] to check unbiased performance of the LSTM network with augmented training data. The remaining data, (Raw Training Data in Fig. 1) are used for the data augmentation step.)
time-series operating values for the one or more monitored devices; and (See e.g. [P2:S1:C1], In this paper, the problem of identifying construction activities is tackled using long-short time memory (LSTM) network trained with data captured by IMUs [one or more monitored devices] from articulated elements of the equipment. To train the LSTM network with sufficient training data, time-series data time-series operating values augmentation techniques are developed and implemented to generate a synthetic training dataset.)
for each subset of the first subset of training data, a label identifying the subset as real operating data; (See e.g. [P4:S4:C1], First, raw sensor data are collected from IMUs mounted on different articulated elements of construction equipment. Then, test data are
separated from the raw data to check unbiased performance of the LSTM network with augmented training data. The remaining data, (Raw Training Data [first subset of training data] in Fig. 1) are used for the data augmentation step.) (See e.g. [P2:S2.1:C1], investigated the use of long-sequence videos to automatically detect, track, and identify activities [a label identifying the subset as real operating data] of an excavator and a dump truck.)(See e.g. [P7:Table 2], Activity name [a label identifying the subset as real operating data])
generating second subsets of training data at least by: selecting the second subsets of training data from among the first subsets of training data; (See e.g. [P4:S4:C1]: The remaining data [selecting the second subsets of training data], (Raw Training Data [from among the first subsets of training data] in Fig. 1) are used for the data augmentation step [generating second subsets]… The augmented training data [second subsets of training data] and raw training data [first subset of training data] are then combined together and used to train the LSTM network.)
applying noise to the second subsets of training data; and (See e.g. [P3:S2.3:C2], Most advanced object recognition algorithms utilize various image augmentation techniques, such as flipping, rotating, scaling, cropping, translating, and adding Gaussian noise [applying noise to the second subsets of training data] to generate synthetic data for training and testing machine/deep learning algorithms)
for each subset of the second subsets of training data, applying a label identifying the subset as false operating data; (See e.g. [P3:S2.3:C2] & [P5:Fig. 2], Most advanced object recognition algorithms utilize various image augmentation techniques, such as flipping, rotating, scaling, cropping, translating, and adding Gaussian noise to generate synthetic data [the subset as false operating data] for training and testing machine/deep learning algorithms) (See e.g. [P4:S4.1:C2], Rotation: Rotation can be accounted for introducing label-invariant [applying a label] variability of IMU sensor data when sensors are placed in the equipment with different orientations.)
training the machine learning model based on the first subsets of training data and the second subsets of training data; (See e.g. [P4:Fig 1.], Raw Training data [the first subsets] is combined with the Augmented Training Data [the second subsets] to train an LSTM Network.)
receiving particular time series operating data associated with a first monitored device; (See e.g. [P5:S5.1:C2], The three IMU [a first monitored device] sensors used in this study collected 18 channel of time-series data [receiving particular time series operating data] (i.e. three IMU multiplied by six channel) each equipment.)
Rashid does not teach A non-transitory computer readable medium comprising instructions which, when executed by one or more hardware processors, causes performance of operations comprising: applying the machine learning model to the particular time series operating data to generate predicted target operating data; and comparing a first value of a first data point of the received particular time series operating data with a second value corresponding to a predicted target operating data value associated with the first data point; and based on determining a difference between the first value and the second value exceeds a threshold, identifying the first value as anomalous.
McDonnell teaches A non-transitory computer readable medium comprising instructions which, when executed by one or more hardware processors, causes performance of operations comprising: (See e.g. [0006], In some aspects, a non-transitory computer-readable medium stores instructions. The instructions, when executed by one or more processors)
applying the machine learning model to the particular time series operating data to generate predicted target operating data; and (See e.g. [0022], a change in operating mode can be detected when the predicted time-series data [generate predicted target operating data] does not match actual time-series input data the particular time series operating data for the same time range.)
comparing a first value of a first data point of the received particular time series operating data with a second value corresponding to a predicted target operating data value associated with the first data point; and (See e.g. [0055], As another example, reference numbers with “N” (e.g., 109N and 153N), “O” (e.g., 109O and 153O), and “P” (e.g., 153P) are associated with the Nth time range, an Oth time range, and a Pth time range, respectively.) (See e.g. [0058], the time-series data predictor 140 receives the input time-series data 109N [a first value of a first data point] associated with the Nth time range [associated with the first data point], and determines whether a change in operating mode is detected based on a comparison of the predicted time-series data 153N [a second value corresponding to a predicted target operating data] (e.g., predicted sensor value(s)) and the input time-series data 109N (e.g., actual sensor value(s)))
based on determining a difference between the first value and the second value exceeds a threshold, identifying the first value as anomalous. (See e.g. [0157], that is based on a comparison of (e.g., difference between) the predicted time-series data 153N and the input time-series data [based on determining a difference between the first value and the second value] 109N.) (See e.g. [0022], For example, when second time-series input data for the second time range (e.g., the Nth time range) is received, the predicted second time-series data is compared to the second time-series input data to determine a risk score. In some examples, a change in operating mode is detected if the risk score is higher than a threshold risk score. [exceeds a threshold]) (See e.g. [0204], in response to determining that the change of operating mode corresponds to an anomaly, [identifying the first value as anomalous] generating the output to indicate one or more features of the first input time-series data that have the greatest impact in determining the second predicted time-series data.)
Accordingly, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention, having the teaching of Rashid and McDonnell before them, to include McDonnell’s time series predictor and anomalous detection which would allow Rashid’s model to check for anomalous values from historic data. One would have been motivated to make such a combination in order to prevent or reduce the impact that anomalous data might have on the operating state, as suggested by McDonnell (US 20230071667 A1) (0022)
Regarding claim 7, Rashid teaches the non-transitory computer readable medium of claim 1. Rashid further teaches wherein the machine learning model is based on a deep learning long short-term memory (LSTM) type model. (See e.g. [P2:S2:C1], The framework presented in this paper consists of a deep learning based activity recognition framework for construction equipment using multiple IMUs;) (See e.g. [P2:S1:C1], In this paper, the problem of identifying construction activities is tackled using long-short time memory (LSTM) network trained with data captured by IMUs from articulated elements of the equipment.)
Regarding claim 8, Rashid teaches the non-transitory computer readable medium of claim 1.
McDonnell teaches comparing a third value of a second data point of the received particular time series operating data with a fourth value corresponding to a predicted target operating data value associated with the second data point; (See e.g. [0022], when second time-series input data for the second time range [a second data point] (e.g., the Nth time range) is received, the predicted second time-series data [a fourth value corresponding to a predicted target operating data value associated with the second data point] is compared to the second time-series input data [comparing a third value] to determine a risk score.)
based on determining a difference between the third value and the fourth value does not exceed the threshold, identifying the third value as non-anomalous. (See e.g. [0022], when second time-series input data for the second time range (e.g., the Nth time range) is received, the predicted second time-series data [a fourth] is compared to the second time-series input data [comparing a third value] to determine a risk score. In some examples, a change in operating mode is detected if the risk score is higher than a threshold risk score. [exceeds the threshold]) (See e.g. [0152], In other implementations, the mode change detector 990 determines that the change in operating mode corresponds to an anomaly in response to determining that the risk score 981N is greater than an anomaly threshold. (Examiner’s notes: since this limitation is directed to checking if a threshold is exceeded to determine if the value is anomalous and it being a binary test, we can assume if the threshold is not exceeded, the value is non-anomalous.))
Accordingly, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention, having the teaching of Rashid and McDonnell before them, to include McDonnell’s time series predictor and anomalous detection which would allow Rashid’s model to check for anomalous values from historic data. One would have been motivated to make such a combination in order to prevent or reduce the impact that anomalous data might have on the operating state, as suggested by McDonnell (US 20230071667 A1) (0022)
Regarding claim 11, Rashid teaches training a machine learning model to predict target operating values for monitored devices, the training comprising: (See e.g. [P2:S1:C1], In this paper, the problem of identifying construction activities is tackled using long-short time memory (LSTM) network trained [training a machine learning model] with data captured by IMUs [monitored devices] from articulated elements of the equipment.) (See e.g. [P10:Fig. 11 & 12], predictions using the LSTM [predict target operating values])
obtaining first subsets of training data comprising historical operating data for one or more monitored devices, each first subset of training data comprising: (See e.g. [P4:S4:C1], First, raw sensor data are collected from IMUs [one or more monitored devices] mounted on different articulated elements of construction equipment. Then, test data are separated from the raw data [obtaining first subsets of training data comprising historical operating data] to check unbiased performance of the LSTM network with augmented training data. The remaining data, (Raw Training Data in Fig. 1) are used for the data augmentation step.)
time-series operating values for the one or more monitored devices; and (See e.g. [P2:S1:C1], In this paper, the problem of identifying construction activities is tackled using long-short time memory (LSTM) network trained with data captured by IMUs [one or more monitored devices] from articulated elements of the equipment. To train the LSTM network with sufficient training data, time-series data [time-series operating values] augmentation techniques are developed and implemented to generate a synthetic training dataset.)
for each subset of the first subset of training data, a label identifying the subset as real operating data; (See e.g. [P4:S4:C1], First, raw sensor data are collected from IMUs mounted on different articulated elements of construction equipment. Then, test data are
separated from the raw data to check unbiased performance of the LSTM network with augmented training data. The remaining data, (Raw Training Data [first subset of training data] in Fig. 1) are used for the data augmentation step.) (See e.g. [P2:S2.1:C1], investigated the use of long-sequence videos to automatically detect, track, and identify activities [a label identifying the subset as real operating data] of an excavator and a dump truck.)(See e.g. [P7:Table 2], Activity name [a label identifying the subset as real operating data])
generating second subsets of training data at least by: selecting the second subsets of training data from among the first subsets of training data; (See e.g. [P4:S4:C1]: The remaining data [selecting the second subsets of training data], (Raw Training Data [from among the first subsets of training data] in Fig. 1) are used for the data augmentation step [generating second subsets]… The augmented training data [second subsets of training data] and raw training data [first subset of training data] are then combined together and used to train the LSTM network.)
applying noise to the second subsets of training data; and (See e.g. [P3:S2.3:C2], Most advanced object recognition algorithms utilize various image augmentation techniques, such as flipping, rotating, scaling, cropping, translating, and adding Gaussian noise [applying noise to the second subsets of training data] to generate synthetic data for training and testing machine/deep learning algorithms)
for each subset of the second subsets of training data, applying a label identifying the subset as false operating data; (See e.g. [P3:S2.3:C2] & [P5:Fig. 2], Most advanced object recognition algorithms utilize various image augmentation techniques, such as flipping, rotating, scaling, cropping, translating, and adding Gaussian noise to generate synthetic data [the subset as false operating data] for training and testing machine/deep learning algorithms) (See e.g. [P4:S4.1:C2], Rotation: Rotation can be accounted for introducing label-invariant [applying a label] variability of IMU sensor data when sensors are placed in the equipment with different orientations.)
training the machine learning model based on the first subsets of training data and the second subsets of training data; (See e.g. [P4:Fig 1.], Raw Training data the first subsets is combined with the Augmented Training Data [the second subsets] to train an LSTM Network.)
receiving particular time series operating data associated with a first monitored device; (See e.g. [P5:S5.1:C2], The three IMU [a first monitored device] sensors used in this study collected 18 channel of time-series data [receiving particular time series operating data] (i.e. three IMU multiplied by six channel) each equipment.)
Rashid does not teach applying the machine learning model to the particular time series operating data to generate predicted target operating data; and comparing a first value of a first data point of the received particular time series operating data with a second value corresponding to a predicted target operating data value associated with the first data point; and based on determining a difference between the first value and the second value exceeds a threshold, identifying the first value as anomalous.
McDonnell teaches applying the machine learning model to the particular time series operating data to generate predicted target operating data; and (See e.g. [0022], a change in operating mode can be detected when the predicted time-series data [generate predicted target operating data] does not match actual time-series input data [the particular time series operating data] for the same time range.)
comparing a first value of a first data point of the received particular time series operating data with a second value corresponding to a predicted target operating data value associated with the first data point; and (See e.g. [0055], As another example, reference numbers with “N” (e.g., 109N and 153N), “O” (e.g., 109O and 153O), and “P” (e.g., 153P) are associated with the Nth time range, an Oth time range, and a Pth time range, respectively.) (See e.g. [0058], the time-series data predictor 140 receives the input time-series data 109N [a first value of a first data point] associated with the Nth time range [associated with the first data point], and determines whether a change in operating mode is detected based on a comparison of the predicted time-series data 153N [a second value corresponding to a predicted target operating data] (e.g., predicted sensor value(s)) and the input time-series data 109N (e.g., actual sensor value(s)))
based on determining a difference between the first value and the second value exceeds a threshold, identifying the first value as anomalous. (See e.g. [0157], that is based on a comparison of (e.g., difference between) the predicted time-series data 153N and the input time-series data [based on determining a difference between the first value and the second value] 109N.) (See e.g. [0022], For example, when second time-series input data for the second time range (e.g., the Nth time range) is received, the predicted second time-series data is compared to the second time-series input data to determine a risk score. In some examples, a change in operating mode is detected if the risk score is higher than a threshold risk score. [exceeds a threshold]) (See e.g. [0204], in response to determining that the change of operating mode corresponds to an anomaly, [identifying the first value as anomalous] generating the output to indicate one or more features of the first input time-series data that have the greatest impact in determining the second predicted time-series data.)
Accordingly, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention, having the teaching of Rashid and McDonnell before them, to include McDonnell’s time series predictor and anomalous detection which would allow Rashid’s model to check for anomalous values from historic data. One would have been motivated to make such a combination in order to prevent or reduce the impact that anomalous data might have on the operating state, as suggested by McDonnell (US 20230071667 A1) (0022)
Regarding claim 17, Rashid teaches the method of claim 1. Rashid further teaches wherein the machine learning model is based on a deep learning long short-term memory (LSTM) type model. (See e.g. [P2:S2:C1], The framework presented in this paper consists of a deep learning based activity recognition framework for construction equipment using multiple IMUs;) (See e.g. [P2:S1:C1], In this paper, the problem of identifying construction activities is tackled using long-short time memory (LSTM) network trained with data captured by IMUs from articulated elements of the equipment.)
Regarding claim 18, Rashid teaches the method of claim 11.
McDonnell teaches comparing a third value of a second data point of the received particular time series operating data with a fourth value corresponding to a predicted target operating data value associated with the second data point; (See e.g. [0022], when second time-series input data for the second time range [a second data point] (e.g., the Nth time range) is received, the predicted second time-series data [a fourth value corresponding to a predicted target operating data value associated with the second data point] is compared to the second time-series input data [comparing a third value] to determine a risk score.)
based on determining a difference between the third value and the fourth value does not exceed the threshold, identifying the third value as non-anomalous. (See e.g. [0022], when second time-series input data for the second time range (e.g., the Nth time range) is received, the predicted second time-series data [a fourth] is compared to the second time-series input data [comparing a third value] to determine a risk score. In some examples, a change in operating mode is detected if the risk score is higher than a threshold risk score. [exceeds the threshold]) (See e.g. [0152], In other implementations, the mode change detector 990 determines that the change in operating mode corresponds to an anomaly in response to determining that the risk score 981N is greater than an anomaly threshold. (Examiner’s notes: since this limitation is directed to checking if a threshold is exceeded to determine if the value is anomalous and it being a binary test, we can assume if the threshold is not exceeded, the value is non-anomalous.))
Accordingly, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention, having the teaching of Rashid and McDonnell before them, to include McDonnell’s time series predictor and anomalous detection which would allow Rashid’s model to check for anomalous values from historic data. One would have been motivated to make such a combination in order to prevent or reduce the impact that anomalous data might have on the operating state, as suggested by McDonnell (US 20230071667 A1) (0022)
Regarding claim 20, Rashid teaches training a machine learning model to predict target operating values for monitored devices, the training comprising: (See e.g. [P2:S1:C1], In this paper, the problem of identifying construction activities is tackled using long-short time memory (LSTM) network trained [training a machine learning model] with data captured by IMUs [monitored devices] from articulated elements of the equipment.) (See e.g. [P10:Fig. 11 & 12], predictions using the LSTM predict target operating values)
obtaining first subsets of training data comprising historical operating data for one or more monitored devices, each first subset of training data comprising: (See e.g. [P4:S4:C1], First, raw sensor data are collected from IMUs [one or more monitored devices] mounted on different articulated elements of construction equipment. Then, test data are separated from the raw data [obtaining first subsets of training data comprising historical operating data] to check unbiased performance of the LSTM network with augmented training data. The remaining data, (Raw Training Data in Fig. 1) are used for the data augmentation step.)
time-series operating values for the one or more monitored devices; and (See e.g. [P2:S1:C1], In this paper, the problem of identifying construction activities is tackled using long-short time memory (LSTM) network trained with data captured by IMUs [one or more monitored devices] from articulated elements of the equipment. To train the LSTM network with sufficient training data, time-series data [time-series operating values] augmentation techniques are developed and implemented to generate a synthetic training dataset.)
for each subset of the first subset of training data, a label identifying the subset as real operating data; (See e.g. [P4:S4:C1], First, raw sensor data are collected from IMUs mounted on different articulated elements of construction equipment. Then, test data are
separated from the raw data to check unbiased performance of the LSTM network with augmented training data. The remaining data, (Raw Training Data [first subset of training data] in Fig. 1) are used for the data augmentation step.) (See e.g. [P2:S2.1:C1], investigated the use of long-sequence videos to automatically detect, track, and identify activities [a label identifying the subset as real operating data] of an excavator and a dump truck.)(See e.g. [P7:Table 2], Activity name [a label identifying the subset as real operating data])
generating second subsets of training data at least by: selecting the second subsets of training data from among the first subsets of training data; (See e.g. [P4:S4:C1]: The remaining data [selecting the second subsets of training data], (Raw Training Data [from among the first subsets of training data] in Fig. 1) are used for the data augmentation step [generating second subsets]… The augmented training data [second subsets of training data] and raw training data [first subset of training data] are then combined together and used to train the LSTM network.)
applying noise to the second subsets of training data; and (See e.g. [P3:S2.3:C2], Most advanced object recognition algorithms utilize various image augmentation techniques, such as flipping, rotating, scaling, cropping, translating, and adding Gaussian noise [applying noise to the second subsets of training data] to generate synthetic data for training and testing machine/deep learning algorithms)
for each subset of the second subsets of training data, applying a label identifying the subset as false operating data; (See e.g. [P3:S2.3:C2] & [P5:Fig. 2], Most advanced object recognition algorithms utilize various image augmentation techniques, such as flipping, rotating, scaling, cropping, translating, and adding Gaussian noise to generate synthetic data [the subset as false operating data] for training and testing machine/deep learning algorithms) (See e.g. [P4:S4.1:C2], Rotation: Rotation can be accounted for introducing label-invariant [applying a label] variability of IMU sensor data when sensors are placed in the equipment with different orientations.)
training the machine learning model based on the first subsets of training data and the second subsets of training data; (See e.g. [P4:Fig 1.], Raw Training data [the first subsets] is combined with the Augmented Training Data the second subsets to train an LSTM Network.)
receiving particular time series operating data associated with a first monitored device; (See e.g. [P5:S5.1:C2], The three IMU [a first monitored device] sensors used in this study collected 18 channel of time-series data [receiving particular time series operating data] (i.e. three IMU multiplied by six channel) each equipment.)
Rashid does not teach applying the machine learning model to the particular time series operating data to generate predicted target operating data; and comparing a first value of a first data point of the received particular time series operating data with a second value corresponding to a predicted target operating data value associated with the first data point; and based on determining a difference between the first value and the second value exceeds a threshold, identifying the first value as anomalous.
McDonnell teaches applying the machine learning model to the particular time series operating data to generate predicted target operating data; and (See e.g. [0022], a change in operating mode can be detected when the predicted time-series data [generate predicted target operating data] does not match actual time-series input data [the particular time series operating data] for the same time range.)
comparing a first value of a first data point of the received particular time series operating data with a second value corresponding to a predicted target operating data value associated with the first data point; and (See e.g. [0055], As another example, reference numbers with “N” (e.g., 109N and 153N), “O” (e.g., 109O and 153O), and “P” (e.g., 153P) are associated with the Nth time range, an Oth time range, and a Pth time range, respectively.) (See e.g. [0058], the time-series data predictor 140 receives the input time-series data 109N [a first value of a first data point] associated with the Nth time range [associated with the first data point], and determines whether a change in operating mode is detected based on a comparison of the predicted time-series data 153N [a second value corresponding to a predicted target operating data] (e.g., predicted sensor value(s)) and the input time-series data 109N (e.g., actual sensor value(s)))
based on determining a difference between the first value and the second value exceeds a threshold, identifying the first value as anomalous. (See e.g. [0157], that is based on a comparison of (e.g., difference between) the predicted time-series data 153N and the input time-series data [based on determining a difference between the first value and the second value] 109N.) (See e.g. [0022], For example, when second time-series input data for the second time range (e.g., the Nth time range) is received, the predicted second time-series data is compared to the second time-series input data to determine a risk score. In some examples, a change in operating mode is detected if the risk score is higher than a threshold risk score. [exceeds a threshold]) (See e.g. [0204], in response to determining that the change of operating mode corresponds to an anomaly, [identifying the first value as anomalous] generating the output to indicate one or more features of the first input time-series data that have the greatest impact in determining the second predicted time-series data.)
Accordingly, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention, having the teaching of Rashid and McDonnell before them, to include McDonnell’s time series predictor and anomalous detection which would allow Rashid’s model to check for anomalous values from historic data. One would have been motivated to make such a combination in order to prevent or reduce the impact that anomalous data might have on the operating state, as suggested by McDonnell (US 20230071667 A1) (0022)
Claims 2 and 12, are rejected under 35 U.S.C. 103 as being unpatentable over Rashid (NPL: Times-series data augmentation and deep learning for construction equipment activity recognition) in view of McDonnell (US 20230071667 A1) further in view of GENEROSO (US 20200020447 A1)
Regarding claim 2, Rashid teaches the non-transitory computer readable medium of claim 1.
McDonnell teaches comparing a third value of a second data point of the received particular time series operating data with a fourth value corresponding to a predicted target operating data value associated with the second data point; (See e.g. [0022], when second time-series input data for the second time range a second data point (e.g., the Nth time range) is received, the predicted second time-series data [a fourth value corresponding to a predicted target operating data value associated with the second data point] is compared to the second time-series input data [comparing a third value] to determine a risk score.)
based on determining a difference between the third value and the fourth value exceeds the threshold, identifying the third value as anomalous; (See e.g. [0022], when second time-series input data for the second time range [a second data point] (e.g., the Nth time range) is received, the predicted second time-series data [a fourth value corresponding to a predicted target operating data value associated with the second data point] is compared to the second time-series input data [comparing a third value] to determine a risk score. In some examples, a change in operating mode is detected if the risk score is higher than a threshold risk score. [exceeds the threshold]) (See e.g. [0171], the line 1302 corresponds to the input time-series data 109, a line 1304B corresponds to the predicted time-series data 153 generated at a second time (e.g., corresponding to Epoch 3) that is subsequent to the first time, and the line 1306 corresponds to the anomaly. [identifying the third value as anomalous])
responsive to determining the difference between the first value and the second value exceeds the threshold by a first amount, assigning a first weight to the first value; (See e.g. [0157], that is based on a comparison of (e.g., difference between) the predicted time-series data 153N and the input time-series data [determining a difference between the first value and the second value] 109N.) (See e.g. [0022], For example, when second time-series input data for the second time range (e.g., the Nth time range) is received, the predicted second time-series data is compared to the second time-series input data to determine a risk score. In some examples, a change in operating mode is detected if the risk score is higher than a threshold risk score. [exceeds a threshold]) (See e.g. [0087], the spatial attention layer 230 accounts for spatial dependencies. “Spatial dependencies” as used herein refers to dependencies between the one or more sensors 104. For example, the spatial attention layer 230 generates the weighted sensor values 409 by applying a higher weight to normalized sensor values [assigning a first weight to the first value]; 327 of a first sensor that has a greater impact (e.g., greater importance) on predicted sensor values [the second value] of the predicted time-series data 153.)
responsive to determining the difference between the third value and the fourth value exceeds the threshold by a second amount, assigning a second weight to the third value; (See e.g. [0022], when second time-series input data for the second time range [a second data point] (e.g., the Nth time range) is received, the predicted second time-series data [a fourth value] is compared to the second time-series input data [the third value] to determine a risk score. In some examples, a change in operating mode is detected if the risk score is higher than a threshold risk score. [exceeds the threshold]) (See e.g. [0086], As another example, the spatial attention layer 230 applies a second weight of the spatial weights 432 to the normalized sensor value [assigning a second weight to the third value] 327RM to generate a weighted sensor value 409RM. The second weight may be the same as or different from the first weight.)
Accordingly, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention, having the teaching of Rashid and McDonnell before them, to include McDonnell’s time series predictor and anomalous detection which would allow Rashid’s model to check for anomalous values from historic data. One would have been motivated to make such a combination in order to prevent or reduce the impact that anomalous data might have on the operating state, as suggested by McDonnell (US 20230071667 A1) (0022)
GENEROSO teaches performing a remediation operation associated with the first value based on determining the first weight meets a remediation criteria; and (See e.g. [0055], At block 414, the system (e.g., the action module 240) determines whether possible health anomalies with a sufficient weight to raise a concern have been identified. This can be done, for example, by comparing the classified weight with a pre-determined threshold [the first value based on determining the first weight meets a remediation criteria]…. In an embodiment, a recommendation as to the nature of the possible health concern and potential further remedial actions can be provided. [performing a remediation operation])
refraining from performing any remediation operation associated with the third value based on determining the second weight does not meet the remediation criteria. (See e.g. [0055], At block 414, the system (e.g., the action module 240) determines whether possible health anomalies with a sufficient weight to raise a concern have been identified. This can be done, for example, by comparing the classified weight with a pre-determined threshold [determining the second weight does not meet the remediation criteria]. If not, the flow returns to block 404. [refraining from performing any remediation operation associated with the third value])
Accordingly, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention, having the teaching of Rashid, McDonnell and GENEROSO before them, to include GENEROSO’s remediation operation which would allow Rashid and McDonnell’s model to take actions if a remediation criteria is met. One would have been motivated to make such a combination in order to improve the efficiency and/or accuracy of the model, as suggested by GENEROSO (US 20200020447 A1) (0044)
Regarding claim 12, Rashid teaches the method of claim 11.
McDonnell teaches comparing a third value of a second data point of the received particular time series operating data with a fourth value corresponding to a predicted target operating data value associated with the second data point; (See e.g. [0022], when second time-series input data for the second time range [a second data point] (e.g., the Nth time range) is received, the predicted second time-series data [a fourth value corresponding to a predicted target operating data value associated with the second data point] is compared to the second time-series input data [comparing a third value] to determine a risk score.)
based on determining a difference between the third value and the fourth value exceeds the threshold, identifying the third value as anomalous; (See e.g. [0022], when second time-series input data for the second time range [a second data point] (e.g., the Nth time range) is received, the predicted second time-series data [a fourth value corresponding to a predicted target operating data value associated with the second data point] is compared to the second time-series input data [comparing a third value] to determine a risk score. In some examples, a change in operating mode is detected if the risk score is higher than a threshold risk score. [exceeds the threshold]) (See e.g. [0171], the line 1302 corresponds to the input time-series data 109, a line 1304B corresponds to the predicted time-series data 153 generated at a second time (e.g., corresponding to Epoch 3) that is subsequent to the first time, and the line 1306 corresponds to the anomaly. [identifying the third value as anomalous])
responsive to determining the difference between the first value and the second value exceeds the threshold by a first amount, assigning a first weight to the first value; (See e.g. [0157], that is based on a comparison of (e.g., difference between) the predicted time-series data 153N and the input time-series data [determining a difference between the first value and the second value] 109N.) (See e.g. [0022], For example, when second time-series input data for the second time range (e.g., the Nth time range) is received, the predicted second time-series data is compared to the second time-series input data to determine a risk score. In some examples, a change in operating mode is detected if the risk score is higher than a threshold risk score. [exceeds a threshold]) (See e.g. [0087], the spatial attention layer 230 accounts for spatial dependencies. “Spatial dependencies” as used herein refers to dependencies between the one or more sensors 104. For example, the spatial attention layer 230 generates the weighted sensor values 409 by applying a higher weight to normalized sensor values [assigning a first weight to the first value]; 327 of a first sensor that has a greater impact (e.g., greater importance) on predicted sensor values [the second value] of the predicted time-series data 153.)
responsive to determining the difference between the third value and the fourth value exceeds the threshold by a second amount, assigning a second weight to the third value; (See e.g. [0022], when second time-series input data for the second time range [a second data point] (e.g., the Nth time range) is received, the predicted second time-series data [a fourth value] is compared to the second time-series input data [the third value] to determine a risk score. In some examples, a change in operating mode is detected if the risk score is higher than a threshold risk score. [exceeds the threshold]) (See e.g. [0086], As another example, the spatial attention layer 230 applies a second weight of the spatial weights 432 to the normalized sensor value [assigning a second weight to the third value] 327RM to generate a weighted sensor value 409RM. The second weight may be the same as or different from the first weight.)
Accordingly, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention, having the teaching of Rashid and McDonnell before them, to include McDonnell’s time series predictor and anomalous detection which would allow Rashid’s model to check for anomalous values from historic data. One would have been motivated to make such a combination in order to prevent or reduce the impact that anomalous data might have on the operating state, as suggested by McDonnell (US 20230071667 A1) (0022)
GENEROSO teaches performing a remediation operation associated with the first value based on determining the first weight meets a remediation criteria; and (See e.g. [0055], At block 414, the system (e.g., the action module 240) determines whether possible health anomalies with a sufficient weight to raise a concern have been identified. This can be done, for example, by comparing the classified weight with a pre-determined threshold [the first value based on determining the first weight meets a remediation criteria]…. In an embodiment, a recommendation as to the nature of the possible health concern and potential further remedial actions can be provided. [performing a remediation operation])
refraining from performing any remediation operation associated with the third value based on determining the second weight does not meet the remediation criteria. (See e.g. [0055], At block 414, the system (e.g., the action module 240) determines whether possible health anomalies with a sufficient weight to raise a concern have been identified. This can be done, for example, by comparing the classified weight with a pre-determined threshold [determining the second weight does not meet the remediation criteria]. If not, the flow returns to block 404. [refraining from performing any remediation operation associated with the third value])
Accordingly, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention, having the teaching of Rashid, McDonnell and GENEROSO before them, to include GENEROSO’s remediation operation which would allow Rashid and McDonnell’s model to take actions if a remediation criteria is met. One would have been motivated to make such a combination in order to improve the efficiency and/or accuracy of the model, as suggested by GENEROSO (US 20200020447 A1) (0044)
Claims 3, 4, 13 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Rashid (NPL: Times-series data augmentation and deep learning for construction equipment activity recognition) in view of McDonnell (US 20230071667 A1) further in view of Soon-Shiong (US 20190356539 A1)
Regarding claim 3, Rashid teaches the non-transitory computer readable medium of claim 1. Rashid further teaches wherein each first subset of training data further comprises attributes associated with the one or more monitored devices (See e.g. [P4:S4:C1], First, raw sensor data are collected from IMUs [one or more monitored devices] mounted on different articulated elements of construction equipment. Then, test data are separated from the raw data [obtaining first subsets of training data] to check unbiased performance of the LSTM network with augmented training data. The remaining data, (Raw Training Data in Fig. 1) are used for the data augmentation step.)
Rashid and McDonnell do not teach the attributes including at least weather conditions in a vicinity of the one or more monitored devices.
Soon-Shiong teaches wherein each first subset of training data further comprises attributes associated with the one or more monitored devices, the attributes including at least weather conditions in a vicinity of the one or more monitored devices. (See e.g. [0074], For example, monitoring devices could be used to detect a weather or environmental occurrence such as a tree falling due to a storm or wind storm. In addition to monitoring in connection with the tree (or other object or environmental or structural feature, whether or not associated with a living or biological entity), various parameters could be sensed and utilized, such as, in this example, storm parameters such as wind, rain, lightning, temperature, humidity, barometric pressure, etc.)
Accordingly, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention, having the teaching of Rashid, McDonnell and Soon-Shiong before them, to include Soon-Shiong’s monitoring of temperature data which would allow Rashid and McDonnell’s model to monitor and add weather condition data to the model. One would have been motivated to make such a combination in order to monitor and change operating conditions in light of the weather conditions being monitored, as suggested by Soon-Shiong (US 20190356539 A1) (0062)
Regarding claim 4, Rashid teaches the non-transitory computer readable medium of claim 3.
Rashid and McDonnell do not teach wherein the attributes associated with the one or more monitored devices further include at least one of: temperature data, dewpoint data, dwelling type data, and demographic data.
Soon-Shiong teaches wherein the attributes associated with the one or more monitored devices further include at least one of: temperature data, dewpoint data, dwelling type data, and demographic data. (See e.g. [0074], For example, monitoring devices could be used to detect a weather or environmental occurrence such as a tree falling due to a storm or wind storm. In addition to monitoring in connection with the tree (or other object or environmental or structural feature, whether or not associated with a living or biological entity), various parameters could be sensed and utilized, such as, in this example, storm parameters such as wind, rain, lightning, temperature, humidity, barometric pressure, etc.)
Accordingly, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention, having the teaching of Rashid, McDonnell and Soon-Shiong before them, to include Soon-Shiong’s monitoring of temperature data which would allow Rashid and McDonnell’s model to monitor and add temperature data to the model. One would have been motivated to make such a combination in order to monitor and change operating conditions in light of the temperature being monitored, as suggested by Soon-Shiong (US 20190356539 A1) (0062)
Regarding claim 13, Rashid teaches the method of claim 11. Rashid further teaches wherein each first subset of training data further comprises attributes associated with the one or more monitored devices (See e.g. [P4:S4:C1], First, raw sensor data are collected from IMUs [one or more monitored devices] mounted on different articulated elements of construction equipment. Then, test data are separated from the raw data [obtaining first subsets of training data] to check unbiased performance of the LSTM network with augmented training data. The remaining data, (Raw Training Data in Fig. 1) are used for the data augmentation step.)
Rashid and McDonnell do not teach the attributes including at least weather conditions in a vicinity of the one or more monitored devices.
Soon-Shiong teaches wherein each first subset of training data further comprises attributes associated with the one or more monitored devices, the attributes including at least weather conditions in a vicinity of the one or more monitored devices. (See e.g. [0074], For example, monitoring devices could be used to detect a weather or environmental occurrence such as a tree falling due to a storm or wind storm. In addition to monitoring in connection with the tree (or other object or environmental or structural feature, whether or not associated with a living or biological entity), various parameters could be sensed and utilized, such as, in this example, storm parameters such as wind, rain, lightning, temperature, humidity, barometric pressure, etc.)
Accordingly, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention, having the teaching of Rashid, McDonnell and Soon-Shiong before them, to include Soon-Shiong’s monitoring of temperature data which would allow Rashid and McDonnell’s model to monitor and add weather condition data to the model. One would have been motivated to make such a combination in order to monitor and change operating conditions in light of the weather conditions being monitored, as suggested by Soon-Shiong (US 20190356539 A1) (0062)
Regarding claim 14, Rashid teaches method of claim 13.
Rashid and McDonnell do not teach wherein the attributes associated with the one or more monitored devices further include at least one of: temperature data, dewpoint data, dwelling type data, and demographic data.
Soon-Shiong teaches wherein the attributes associated with the one or more monitored devices further include at least one of: temperature data, dewpoint data, dwelling type data, and demographic data. (See e.g. [0074], For example, monitoring devices could be used to detect a weather or environmental occurrence such as a tree falling due to a storm or wind storm. In addition to monitoring in connection with the tree (or other object or environmental or structural feature, whether or not associated with a living or biological entity), various parameters could be sensed and utilized, such as, in this example, storm parameters such as wind, rain, lightning, temperature, humidity, barometric pressure, etc.)
Accordingly, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention, having the teaching of Rashid, McDonnell and Soon-Shiong before them, to include Soon-Shiong’s monitoring of temperature data which would allow Rashid and McDonnell’s model to monitor and add temperature data to the model. One would have been motivated to make such a combination in order to monitor and change operating conditions in light of the temperature being monitored, as suggested by Soon-Shiong (US 20190356539 A1) (0062)
Claims 5 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Rashid (NPL: Times-series data augmentation and deep learning for construction equipment activity recognition) in view of McDonnell (US 20230071667 A1) further in view of Trimble (US 20230316063 A1)
Regarding claim 5, Rashid teaches the non-transitory computer readable medium of claim 1. Rashid further teaches selecting a set of data points from among the first subsets of training data; (See e.g. [P4:S4:C1], First, raw sensor data are collected from IMUs one or more monitored devices mounted on different articulated elements of construction equipment. Then, test data are separated from the raw data to check unbiased performance of the LSTM network with augmented training data. The remaining data, (Raw Training Data in Fig. 1) are used for the data augmentation step…Each augmentation technique generated 4-fold increase in augmented
training data [among the first subsets of training data]; resulting in a 16-fold increase in the number of the training datapoints. [selecting a set of data points])
Rashid and McDonnell do not teach randomly selecting an addition operation or a subtraction operation to be performed; and based on the randomly selected addition or subtraction operation, applying a random positive variation or a random negative variation, within a threshold level of variation, to a value of each data points in the selected set of data points.
Trimble teaches randomly selecting an addition operation or a subtraction operation to be performed; (See e.g. [0063], However the perturbation could, instead, comprise modifying different data elements of the subset differently (e.g. by setting their data values to different values, or by adding or subtracting a different value, etc.). For example, the perturbation could include adding or subtracting a different randomly [randomly selecting an addition operation or a subtraction operation to be performed] generated value to different data elements of the input data array, thereby adding “noise” to the data.)
based on the randomly selected addition or subtraction operation, applying a random positive variation or a random negative variation, within a threshold level of variation, to a value of each data points in the selected set of data points. (See e.g. [0063], However the perturbation could, instead, comprise modifying different data elements of the subset differently [to a value of each data points in the selected set of data points] (e.g. by setting their data values to different values, or by adding or subtracting a different value, etc.). For example, the perturbation could include adding or subtracting a different randomly generated value to different data [based on the randomly selected addition or subtraction operation, applying a random positive variation or a random negative variation, within a threshold level of variation] elements of the input data array, thereby adding “noise” to the data.)
Accordingly, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention, having the teaching of Rashid, McDonnell and Trimble before them, to include Trimble’s random modification of the values which would allow Rashid and McDonnell’s model to handle a variation in data and input. One would have been motivated to make such a combination in order to reduce the amount processing that needs to be done to input data to generate an “explainable” operations of the neural network , as suggested by Trimble (US 20230316063 A1) (0043)
Regarding claim 15, Rashid teaches method of claim 11. Rashid further teaches selecting a set of data points from among the first subsets of training data; (See e.g. [P4:S4:C1], First, raw sensor data are collected from IMUs [one or more monitored devices] mounted on different articulated elements of construction equipment. Then, test data are separated from the raw data to check unbiased performance of the LSTM network with augmented training data. The remaining data, (Raw Training Data in Fig. 1) are used for the data augmentation step…Each augmentation technique generated 4-fold increase in augmented training data [among the first subsets of training data]; resulting in a 16-fold increase in the number of the training datapoints. [selecting a set of data points])
Rashid and McDonnell do not teach randomly selecting an addition operation or a subtraction operation to be performed; and based on the randomly selected addition or subtraction operation, applying a random positive variation or a random negative variation, within a threshold level of variation, to a value of each data points in the selected set of data points.
Trimble teaches randomly selecting an addition operation or a subtraction operation to be performed; (See e.g. [0063], However the perturbation could, instead, comprise modifying different data elements of the subset differently (e.g. by setting their data values to different values, or by adding or subtracting a different value, etc.). For example, the perturbation could include adding or subtracting a different randomly [randomly selecting an addition operation or a subtraction operation to be performed] generated value to different data elements of the input data array, thereby adding “noise” to the data.)
based on the randomly selected addition or subtraction operation, applying a random positive variation or a random negative variation, within a threshold level of variation, to a value of each data points in the selected set of data points. (See e.g. [0063], However the perturbation could, instead, comprise modifying different data elements of the subset differently [to a value of each data points in the selected set of data points] (e.g. by setting their data values to different values, or by adding or subtracting a different value, etc.). For example, the perturbation could include adding or subtracting a different randomly generated value to different data [based on the randomly selected addition or subtraction operation, applying a random positive variation or a random negative variation, within a threshold level of variation] elements of the input data array, thereby adding “noise” to the data.)
Accordingly, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention, having the teaching of Rashid, McDonnell and Trimble before them, to include Trimble’s random modification of the values which would allow Rashid and McDonnell’s model to handle a variation in data and input. One would have been motivated to make such a combination in order to reduce the amount processing that needs to be done to input data to generate an “explainable” operations of the neural network , as suggested by Trimble (US 20230316063 A1) (0043)
Claims 6, 10 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Rashid (NPL: Times-series data augmentation and deep learning for construction equipment activity recognition) in view of McDonnell (US 20230071667 A1) further in view of Brown (US 20210302621 A1)
Regarding claim 6, Rashid teaches the non-transitory computer readable medium of claim 1. Rashid further teaches receiving time series operation values and location data associated with the first monitored device; (See e.g. [P1:S1:C2], To develop an effective activity recognition framework for construction equipment, several previous studies have explored the feasibility of using location data and/or time-series vibration data from inertial measurement units (IMU) [receiving time series operation values and location data associated with the first monitored device])
generating vectors including the time series operation values and [the weather data,] (See e.g. [P3:S2.2:C1], These de-facto standard approaches of activity recognition treat individual dimensions of the sensor data statistically independently. Thus, each dimension of the data is converted into feature vectors without due consideration of their broader temporal context… explicitly models the temporal dynamics of the feature vectors. [generating vectors including the time series operation values])
wherein the machine learning model is applied to the vectors. (See e.g. [P1:S1:C2], traditional machine learning approaches require manual segmentation of timeseries data after collecting the training data, and further extraction of statistically significant feature vectors.)
Rashid and McDonnell do not teach based on the location data, identifying a weather sensor within a threshold distance of the first monitored device; obtaining weather data generated by the weather sensor associated with the received time series operation values; and generating vectors including the time series operation values and the weather data,
Brown teaches based on the location data, identifying a weather sensor within a threshold distance of the first monitored device; (See e.g. [0236], The power meter may measure a power usage of the base station and any attached modules…514 [weather sensor within a threshold distance of the first monitored device]) (See e.g. [0120], A precise location identifier 418 of the base station (or of a portion of the base station) may be stored in the data store [based on the location data])
obtaining weather data generated by the weather sensor associated with the received time series operation values; and (See e.g. [0454], the weather analysis device may comprise a plurality of sensors [obtaining weather data generated by the weather sensor] to gather other local weather-related data, such as temperature, barometric pressure, relative humidity, wind speed, and wind direction, among others…This transmission of the information can be highly cost effective, which makes massive, wide-spread deployments of multiple weather analysis devices on multiple streetlights feasible over a specified region or area, thereby allowing the central processing unit to aggregate and incorporate the real-time information into real-time weather reporting [the weather sensor associated with the received time series operation values], weather prediction, and climate assessment models.)
Accordingly, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention, having the teaching of Rashid, McDonnell and Brown before them, to include Brown’s weather sensor which would allow Rashid and McDonnell’s model to add weather data in proximity of the monitoring device. One would have been motivated to make such a combination in order enable real-time information into the model to make predictions on future weather events, as suggested by Brown (US 20210302621 A1) (0454)
Regarding claim 10, Rashid teaches the non-transitory computer readable medium of claim 1.
Rashid and McDonnell do not teach wherein the time series operating data comprises power data measured by a power utility meter at a particular location.
Brown teaches wherein the time series operating data comprises power data measured by a power utility meter at a particular location. (See e.g. [0342], a power meter that tracks an amount of power used [power data measured by a power utility meter] by the communications station (for instance, over a predetermined period of time [wherein the time series operating data]). The power meter may be included with the communications station [power utility meter at a particular location] (not shown in FIG. 36).)
Accordingly, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention, having the teaching of Rashid, McDonnell and Brown before them, to include Brown’s weather sensor which would allow Rashid and McDonnell’s model to add weather data in proximity of the monitoring device. One would have been motivated to make such a combination in order enable real-time information into the model to make predictions on future weather events, as suggested by Brown (US 20210302621 A1) (0454)
Regarding claim 16, Rashid teaches the method of claim 11. Rashid further teaches receiving time series operation values and location data associated with the first monitored device; (See e.g. [P1:S1:C2], To develop an effective activity recognition framework for construction equipment, several previous studies have explored the feasibility of using location data and/or time-series vibration data from inertial measurement units (IMU) [receiving time series operation values and location data associated with the first monitored device])
generating vectors including the time series operation values and [the weather data,] (See e.g. [P3:S2.2:C1], These de-facto standard approaches of activity recognition treat individual dimensions of the sensor data statistically independently. Thus, each dimension of the data is converted into feature vectors without due consideration of their broader temporal context… explicitly models the temporal dynamics of the feature vectors. [generating vectors including the time series operation values])
wherein the machine learning model is applied to the vectors. (See e.g. [P1:S1:C2], traditional machine learning approaches require manual segmentation of timeseries data after collecting the training data, and further extraction of statistically significant feature vectors.)
Rashid and McDonnell do not teach based on the location data, identifying a weather sensor within a threshold distance of the first monitored device; obtaining weather data generated by the weather sensor associated with the received time series operation values; and generating vectors including the time series operation values and the weather data,
Brown teaches based on the location data, identifying a weather sensor within a threshold distance of the first monitored device; (See e.g. [0236], The power meter may measure a power usage of the base station and any attached modules…514 [weather sensor within a threshold distance of the first monitored device]) (See e.g. [0120], A precise location identifier 418 of the base station (or of a portion of the base station) may be stored in the data store [based on the location data])
obtaining weather data generated by the weather sensor associated with the received time series operation values; and (See e.g. [0454], the weather analysis device may comprise a plurality of sensors [obtaining weather data generated by the weather sensor] to gather other local weather-related data, such as temperature, barometric pressure, relative humidity, wind speed, and wind direction, among others…This transmission of the information can be highly cost effective, which makes massive, wide-spread deployments of multiple weather analysis devices on multiple streetlights feasible over a specified region or area, thereby allowing the central processing unit to aggregate and incorporate the real-time information into real-time weather reporting [the weather sensor associated with the received time series operation values], weather prediction, and climate assessment models.)
Accordingly, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention, having the teaching of Rashid, McDonnell and Brown before them, to include Brown’s weather sensor which would allow Rashid and McDonnell’s model to add weather data in proximity of the monitoring device. One would have been motivated to make such a combination in order enable real-time information into the model to make predictions on future weather events, as suggested by Brown (US 20210302621 A1) (0454)
Claims 9 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Rashid (NPL: Times-series data augmentation and deep learning for construction equipment activity recognition) in view of McDonnell (US 20230071667 A1) further in view of CHIN (NPL: ANOMALY DETECTION FRAMEWORKS FOR IDENTIFYING ENERGY THEFT AND METER IRREGULARITIES IN SMART GRIDS)
Regarding claim 9, Rashid teaches the non-transitory computer readable medium of claim 1. Rashid further teaches based on operating values of the first monitored device over a defined period of time…(See e.g. [P1:S1:C2], To develop an effective activity recognition framework for construction equipment, several previous studies have explored the feasibility of using location data and/or time-series vibration data [operating values over a defined period of time] from inertial measurement units (IMU) [a first monitored device])
Rashid does not teach based on determining the first value of the first data point is anomalous
McDonnell teaches based on determining the first value of the first data point is anomalous (See e.g. [0204], in response to determining that the change of operating mode corresponds to an anomaly, [identifying the first value as anomalous] generating the output to indicate one or more features of the first input time-series data that have the greatest impact in determining the second predicted time-series data.)
Accordingly, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention, having the teaching of Rashid and McDonnell before them, to include McDonnell’s time series predictor and anomalous detection which would allow Rashid’s model to check for anomalous values from historic data. One would have been motivated to make such a combination in order to prevent or reduce the impact that anomalous data might have on the operating state, as suggested by McDonnell (US 20230071667 A1) (0022)
Rashid and McDonnell do not teach associating a monetary value with a particular user account corresponding to the first monitored device; and omitting from the monetary value associated with the particular user account a first monetary value associated with the first value of the first data point.
CHIN teaches associating a monetary value with a particular user account corresponding to the first monitored device; (See e.g. [P32:S2.4.2.4], One of the ways is to turn back the number dials in the conventional analog meter [corresponding to the first monitored device] to reduce energy billings. [associating a monetary value with a particular user account])
omitting from the monetary value associated with the particular user account a first monetary value associated with the first value of the first data point. (See e.g. [P114: S6.3.1.1], Based on these results, the data collector can effectively detect all the energy thieves as well as the malicious SMs, then computes how much less [omitting from the monetary value associated with the particular user account] or more they have paid in their monthly bills [a first monetary value associated with the first value of the first data point])
Accordingly, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention, having the teaching of Rashid, McDonnell, and CHIN before them, to include CHIN’s monetary value associated with a user which would allow Rashid and McDonnell’s model to actively update bills for users. One would have been motivated to make such a combination in order to provide more accurate billing as well as lower utility costs, as suggested by CHIN (NPL: ANOMALY DETECTION FRAMEWORKS FOR IDENTIFYING ENERGY THEFT AND METER IRREGULARITIES IN SMART GRIDS) (P2:S1.1)
Regarding claim 19, Rashid teaches the method of claim 11. Rashid further teaches based on operating values of the first monitored device over a defined period of time…(See e.g. [P1:S1:C2], To develop an effective activity recognition framework for construction equipment, several previous studies have explored the feasibility of using location data and/or time-series vibration data [operating values over a defined period of time] from inertial measurement units (IMU) [a first monitored device])
Rashid does not teach based on determining the first value of the first data point is anomalous
McDonnell teaches based on determining the first value of the first data point is anomalous (See e.g. [0204], in response to determining that the change of operating mode corresponds to an anomaly, [identifying the first value as anomalous] generating the output to indicate one or more features of the first input time-series data that have the greatest impact in determining the second predicted time-series data.)
Accordingly, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention, having the teaching of Rashid and McDonnell before them, to include McDonnell’s time series predictor and anomalous detection which would allow Rashid’s model to check for anomalous values from historic data. One would have been motivated to make such a combination in order to prevent or reduce the impact that anomalous data might have on the operating state, as suggested by McDonnell (US 20230071667 A1) (0022)
Rashid and McDonnell do not teach associating a monetary value with a particular user account corresponding to the first monitored device; and omitting from the monetary value associated with the particular user account a first monetary value associated with the first value of the first data point.
CHIN teaches associating a monetary value with a particular user account corresponding to the first monitored device; (See e.g. [P32:S2.4.2.4], One of the ways is to turn back the number dials in the conventional analog meter [corresponding to the first monitored device to reduce energy billings. associating a monetary value with a particular user account])
omitting from the monetary value associated with the particular user account a first monetary value associated with the first value of the first data point. (See e.g. [P114: S6.3.1.1], Based on these results, the data collector can effectively detect all the energy thieves as well as the malicious SMs, then computes how much less [omitting from the monetary value associated with the particular user account] or more they have paid in their monthly bills [a first monetary value associated with the first value of the first data point])
Accordingly, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention, having the teaching of Rashid, McDonnell, and CHIN before them, to include CHIN’s monetary value associated with a user which would allow Rashid and McDonnell’s model to actively update bills for users. One would have been motivated to make such a combination in order to provide more accurate billing as well as lower utility costs, as suggested by CHIN (NPL: ANOMALY DETECTION FRAMEWORKS FOR IDENTIFYING ENERGY THEFT AND METER IRREGULARITIES IN SMART GRIDS) (P2:S1.1)
Conclusion
The following are suggested formats for either a Certificate of Mailing or Certificate of Transmission under 37 CFR 1.8(a). The certification may be included with all correspondence concerning this application or proceeding to establish a date of mailing or transmission under 37 CFR 1.8(a). Proper use of this procedure will result in such communication being considered as timely if the established date is within the required period for reply. The Certificate should be signed by the individual actually depositing or transmitting the correspondence or by an individual who, upon information and belief, expects the correspondence to be mailed or transmitted in the normal course of business by another no later than the date indicated.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KYLE ALLMAN THOMPSON whose telephone number is (571)272-3671. The examiner can normally be reached Monday - Thursday, 6 a.m. - 3 p.m. ET..
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Kamran Afshar can be reached at (571) 272-7796. 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.
/K.A.T./ Examiner, Art Unit 2125
/KAMRAN AFSHAR/ Supervisory Patent Examiner, Art Unit 2125
Prosecution Insights