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 .
Response to Arguments
Applicant’s arguments, see Claim Rejections – 35 U.S.C. § 102 and § 103, filed September 17, 2025, with respect to the rejections of claims 1 – 20 under 35 U.S.C. § 102 and 103 have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new grounds of rejection is made in view of new art found in a search prompted by amendments. As amended, the claims read upon machine vision tasks.
Applicant’s arguments, see Claim Rejections – 35 U.S.C. § 112, filed September 17, 2025, with respect to the rejections of claims 8 and 10 under 35 U.S.C. § 112(b) have been fully considered and are persuasive. Therefore, the rejections have been withdrawn. However, amendments to the claims have introduced grounds for new rejections of claim 13 under 35 U.S.C. § 112(b).
Applicant’s arguments, see Objections to the Claims, filed September 17, 2025, with respect to the objections to claims 5 and 15 have been fully considered and are persuasive. Therefore, the rejections have been withdrawn.
Claim Objections
Claim 5 objected to because of the following informalities:
The word “parameter” in the second-to-last line is not pluralized.
The phrase “repackaging the values a plurality of parameters” in the last line is missing the word “of” following “values”.
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 7 and 13 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 7 recites the limitation “the PID controller”. It is not clear whether this is the same as the “regulator” recited in the same claim, as the two claim terms are part of a list of “at least one” parameters. There is therefore insufficient antecedent basis for this limitation in the claim.
Claim 13 recites the limitation "the characteristics of the anomalies". There is insufficient antecedent basis for this limitation in the claim.
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 – 8 and 10 – 21 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claims were not previously rejected under 35 U.S.C. 101, but a new rejection is made in view of amendments and a clarified interpretation of the claims bringing to light similarities to abstract ensemble techniques.
Below is an evaluation using the 2019 Revised Patent Subject Matter Eligibility Guidance.
Claim 1
Step 1:
Claim 1 is to a method.
Step 2A Prong 1: Abstract Idea
Claim 1 recites
generating at least two subsets of parameters from the collected data;
selecting at least two anomaly detectors from a plurality of anomaly detectors and selecting at least one corresponding subset of the parameters for each selected anomaly detector;
pre-processing each subset of the parameters and transmitting an output of the pre-processing to the corresponding anomaly detector;
detecting anomalies in each pre-processed subset using the corresponding anomaly detector
and
detecting a combined anomaly in the CPS by combining anomaly localization regions from individual anomaly detectors into a localized region of the combined anomaly, wherein said localization regions determine anomalies in space and/or time, if a spatial or temporal intersection of the anomaly localization regions exceeds a predetermined percentage of the localization region of the combined anomaly.
These are the abstract idea of a mental process that can practically be performed in the human mind, with or without the use of a physical aid such as pen and paper (including an observation, evaluation, judgment, opinion). See MPEP § 2106.04(a)(2)(III). As written, the claims are to broadly rearranging information to produce parameters, using the data in anomaly detectors to produce anomaly data, and manipulating the anomaly data to combine abstract structures. The claim term “anomaly detector” can be interpreted to include anything that takes parameters as input and outputs an anomaly detection, which can include the human mind. A human being could, for example, determine the location of an anomaly from an image. Choosing a detector to use can be performed by a human being. A human being could then, given two locations of anomalies, determine whether the anomalies overlap one another, and “combine” the two anomalies by declaring them to be the same anomaly.
Step 2A Prong 2: Additional elements
Claim 1 recites
for detecting anomalies in a cyber-physical system (CPS)
collecting data containing values of a plurality of parameters of the CPS
This is an additional element that amounts to adding insignificant extra-solution activity to the judicial exception. See MPEP §§ 2106.04(d), 2106.05(g). It only specifies a source of the data, and does not introduce any limitations on the data that would prevent the previously listed abstract ideas from being performed in the human mind. Collecting data is a necessary step in order to perform the rest of the method.
This is additionally an additional element that generally links the use of the judicial exception to a particular technological environment or field of use. See MPEP §§ 2106.04(d), 2106.05(h). Additionally, a CPS covers a wide range of possible applications, which does not clearly link the claims to a particular application.
Step 2B: Significantly more
Claim 1 recites
for detecting anomalies in a cyber-physical system (CPS)
collecting data containing values of a plurality of parameters of the CPS
This is an additional element that amounts to adding insignificant extra-solution activity to the judicial exception. See MPEP § 2106.05(g). It only specifies a source of the data, and does not introduce any limitations on the data that would prevent the previously listed abstract ideas from being performed in the human mind. Collecting data is a necessary step in order to perform the rest of the method.
This is additionally an additional element that generally links the use of the judicial exception to a particular technological environment or field of use. See MPEP § 2106.05(h). Additionally, a CPS covers a wide range of possible applications, which does not clearly link the claims to a particular application.
Claim 2
Step 1:
Claim 2 is to a method.
Step 2A Prong 1: Abstract Idea
Claim 2 recites the abstract ideas of Claim 1 by dependency.
Claim 2 recites
post-processing the detected anomalies from each selected anomaly detector; and combining the post-processing detected anomalies
These are the abstract idea of a mental process that can practically be performed in the human mind, with or without the use of a physical aid such as pen and paper (including an observation, evaluation, judgment, opinion). See MPEP § 2106.04(a)(2)(III). Post-processing amounts to rearranging information, and combining the anomalies is a continuation of the abstract idea of claim 1.
Step 2A Prong 2: Additional elements
Claim 2 does not recite additional elements.
Step 2B: Significantly more
Claim 2 does not recite additional elements.
Claim 3
Step 1:
Claim 3 is to a method.
Step 2A Prong 1: Abstract Idea
Claim 3 recites the abstract ideas of Claim 1 by dependency.
Claim 3 recites
wherein the selecting of the at least two anomaly detectors and the at least one corresponding subset of the parameters for each selected anomaly detector is performed based on at least one of:
characteristics of the CPS
a list of parameters of the CPS and their values from a subset of parameters; and
types of the collected data and an amount of the collected data.
which is the abstract idea of a mental process that can practically be performed in the human mind, with or without the use of a physical aid such as pen and paper (including an observation, evaluation, judgment, opinion). See MPEP § 2106.04(a)(2)(III). A human being would be able to consider the nature of the data being analyzed to select the most suitable method of detecting an anomaly.
Step 2A Prong 2: Additional elements
Claim 3 recites
characteristics of the CPS;
parameters of the CPS
which is an additional element that generally links the use of the judicial exception to a particular technological environment or field of use. See MPEP §§ 2106.04(d), 2106.05(h). “Characteristics” and “parameters” of the CPS are general and do not link the claims to a particular form of CPS which would not be practically analyzed in the human mind.
Step 2B: Significantly more
Claim 3 recites
characteristics of the CPS;
parameters of the CPS
which is an additional element that generally links the use of the judicial exception to a particular technological environment or field of use. See MPEP § 2106.05(h). “Characteristics” and “parameters” of the CPS are general and do not link the claims to a particular form of CPS which would not be practically analyzed in the human mind.
Claim 4
Step 1:
Claim 4 is to a method.
Step 2A Prong 1: Abstract Idea
Claim 4 recites the abstract ideas of Claim 1 by dependency.
Claim 4 recites
wherein the selecting of the at least two anomaly detectors and the at least one corresponding subset of the parameters for each selected anomaly detector is performed based on at least one of:
a quality metric;
Receiver Operating Characteristics (ROC) curve analysis results;
which is the abstract idea of a mental process that can practically be performed in the human mind, with or without the use of a physical aid such as pen and paper (including an observation, evaluation, judgment, opinion). See MPEP § 2106.04(a)(2)(III). A human being would be able to consider the quality of a detector in selecting it. A human being can perform ROC curve analysis.
Step 2A Prong 2: Additional elements
Claim 4 recites
execution time; and
an amount of resources used by a computer performing the anomaly detection.
which are additional elements that amount to adding insignificant extra-solution activity to the judicial exception. See MPEP §§ 2106.04(d), 2106.05(g). Although they indicate that detectors may be computers, these additional elements link the detector selection abstract idea to routine, conventional, and well-understood methods for considering a computer’s efficiency. See at least the Wikipedia article for Algorithmic efficiency (NPL, archived from most recent revision before effective filing date). Furthermore, these additional elements are part of a list of factors recited after “at least one of” rather than expressly required, and do not indicate that the anomaly detectors must be computers.
Step 2B: Significantly more
Claim 4 recites
execution time; and
an amount of resources used by a computer performing the anomaly detection.
which are additional elements that amount to adding insignificant extra-solution activity to the judicial exception. See MPEP § 2106.05(g). Although they indicate that detectors may be computers, these additional elements link the detector selection abstract idea to routine, conventional, and well-understood methods for considering a computer’s efficiency. See at least the Wikipedia article for Algorithmic efficiency. Furthermore, these additional elements are part of a list of factors recited after “at least one of” rather than expressly required, and do not indicate that the anomaly detectors must be computers.
Claim 5
Step 1:
Claim 5 is to a method.
Step 2A Prong 1: Abstract Idea
Claim 5 recites the abstract ideas of Claim 1 by dependency.
Claim 5 recites
wherein the pre-processing of a subset of the parameters includes at least one of:
data buffering with a time buffer of a pre-determined length;
filtering of invalid data or data that was received with a delay greater than a pre-determined period of time;
reordering based on time points of obtaining the values of a plurality of parameters of the CPS;
filling in gaps in the values of a plurality of parameters of the CPS;
interpolation to a uniform grid;
normalization of values of a plurality of parameter of the CPS;
repackaging the values a plurality of parameters of the CPS for processing by the anomaly detector
which are all continuations of the pre-processing abstract idea, each describing specific methods of rearranging the abstract information.
Step 2A Prong 2: Additional elements
Claim 5 recites
of the CPS
This is an additional element that amounts to adding insignificant extra-solution activity to the judicial exception. See MPEP §§ 2106.04(d), 2106.05(g). It only specifies a source of the data, and does not introduce any limitations on the data that would prevent the previously listed abstract ideas from being performed in the human mind.
This is additionally an additional element that generally links the use of the judicial exception to a particular technological environment or field of use. See MPEP §§ 2106.04(d), 2106.05(h).
Step 2B: Significantly more
Claim 5 recites
of the CPS
This is an additional element that amounts to adding insignificant extra-solution activity to the judicial exception. See MPEP § 2106.05(g). It only specifies a source of the data, and does not introduce any limitations on the data that would prevent the previously listed abstract ideas from being performed in the human mind.
This is additionally an additional element that generally links the use of the judicial exception to a particular technological environment or field of use. See MPEP § 2106.05(h).
Claim 6
Step 1:
Claim 6 is to a method.
Step 2A Prong 1: Abstract Idea
Claim 6 recites the abstract ideas of Claim 1 by dependency.
Claim 6 recites
detecting anomalies when a forecast error exceeds a pre-determined threshold value, wherein the forecast error is computed by predicting values of a plurality of parameters of the CPS, wherein the detector determined a total forecast error for the values of the parameters of the CPS;
detecting anomalies when a rule for detecting anomalies is applied;
detecting anomalies by comparing the values of a plurality of parameters of the CPS with limit values of ranges of values established for the respective parameters
which are all continuations of the detection abstract idea, each describing specific methods of detecting an anomaly.
Step 2A Prong 2: Additional elements
Claim 6 recites
of the CPS
This is an additional element that amounts to adding insignificant extra-solution activity to the judicial exception. See MPEP §§ 2106.04(d), 2106.05(g). It only specifies a source of the data, and does not introduce any limitations on the data that would prevent the previously listed abstract ideas from being performed in the human mind.
This is additionally an additional element that generally links the use of the judicial exception to a particular technological environment or field of use. See MPEP §§ 2106.04(d), 2106.05(h).
Claim 6 further recites
detecting anomalies by applying a machine learning model based on the values of a plurality of parameters of the CPS
which is an additional element that amounts to adding the words “apply it” (or an equivalent) with the judicial exception, or merely uses a computer in its ordinary capacity as a tool to perform an existing process. See MPEP §§ 2106.04(d), 2106.05(f)(2). The additional element merely states that a machine learning model is used, and does not link to a specific improvement.
Step 2B: Significantly more
Claim 6 recites
of the CPS
This is an additional element that amounts to adding insignificant extra-solution activity to the judicial exception. See MPEP § 2106.05(g). It only specifies a source of the data, and does not introduce any limitations on the data that would prevent the previously listed abstract ideas from being performed in the human mind.
This is additionally an additional element that generally links the use of the judicial exception to a particular technological environment or field of use. See MPEP § 2106.05(h).
Claim 6 further recites
detecting anomalies by applying a machine learning model based on the values of a plurality of parameters of the CPS
which is an additional element that amounts to adding the words “apply it” (or an equivalent) with the judicial exception, or merely uses a computer in its ordinary capacity as a tool to perform an existing process. See MPEP § 2106.05(f)(2). The additional element merely states that a machine learning model is used, and does not link to a specific improvement.
Claim 7
Step 1:
Claim 7 is to a method.
Step 2A Prong 1: Abstract Idea
Claim 7 recites the abstract ideas of Claim 1 by dependency.
Step 2A Prong 2: Additional elements
Claim 7 recites
wherein a value of at least one of the parameters of the CPS comprises at least one of:
a sensor measurement;
a value of a controlled parameter of an actuator;
a setpoint of an executive mechanism;
a value of at least one input signal of a proportional-integral-differentiating (PID) regulator; and
a value of an output signal of the PID controller
which are all additional elements that generally link the use of the judicial exception to a particular technological environment or field of use. See MPEP §§ 2106.04(d), 2106.05(h). The claim language merely indicates that at least one element of the input data should be from one of the listed sources. It does not limit the claims in a way that prevents the manipulation of the data from being performed in the human mind, or links the claims to a particular improvement.
Step 2B: Significantly more
Claim 7 recites
wherein a value of at least one of the parameters of the CPS comprises at least one of:
a sensor measurement;
a value of a controlled parameter of an actuator;
a setpoint of an executive mechanism;
a value of at least one input signal of a proportional-integral-differentiating (PID) regulator; and
a value of an output signal of the PID controller
which are all additional elements that generally link the use of the judicial exception to a particular technological environment or field of use. See MPEP § 2106.05(h). The claim language merely indicates that at least one element of the input data should be from one of the listed sources. It does not limit the claims in a way that prevents the manipulation of the data from being performed in the human mind, or links the claims to a particular improvement.
Claim 8
Step 1:
Claim 8 is to a method.
Step 2A Prong 1: Abstract Idea
Claim 8 recites the abstract ideas of Claim 1 by dependency.
Step 2A Prong 2: Additional elements
Claim 8 recites
wherein the values of a plurality of parameters of the CPS are collected from the CPS at a shared time interval with an indication of the parameters of the CPS or from individual parts of the CPS in a form of a plurality of separate streams of values of a plurality of parameters of the CPS indicating the parameters contained in each anomaly stream
which is an additional element that amounts to adding insignificant extra-solution activity to the judicial exception. See MPEP §§ 2106.04(d), 2106.05(g). The additional element amounts to stating that the data for a particular time frame being collected at the same time.
Step 2B: Significantly more
Claim 8 recites
wherein the values of a plurality of parameters of the CPS are collected from the CPS at a shared time interval with an indication of the parameters of the CPS or from individual parts of the CPS in a form of a plurality of separate streams of values of a plurality of parameters of the CPS indicating the parameters contained in each anomaly stream
which is an additional element that amounts to adding insignificant extra-solution activity to the judicial exception. See MPEP § 2106.05(g). The additional element amounts to stating that the data for a particular time frame being collected at the same time.
Claim 10
Step 1:
Claim 10 is to a method.
Step 2A Prong 1: Abstract Idea
Claim 10 recites the abstract ideas of Claim 1 by dependency.
Claim 10 recites
identifies the anomaly localization regions of the detected anomalies in each pre-processed subset as relating to the combined anomaly
which is the abstract idea of a mental process that can practically be performed in the human mind, with or without the use of a physical aid such as pen and paper (including an observation, evaluation, judgment, opinion). See MPEP § 2106.04(a)(2)(III). Identifying that two regions are related can be performed in the human mind.
Step 2A Prong 2: Additional elements
Claim 10 recites
wherein the anomaly localization regions from individual anomaly detectors are combined into the localization region of the combined anomaly if a trained neural network identifies the anomaly localization regions of the detected anomalies in each pre-processing subset as relating to the combined anomaly
which is an additional element that amounts to adding the words “apply it” (or an equivalent) with the judicial exception, or merely uses a computer in its ordinary capacity as a tool to perform an existing process. See MPEP §§ 2106.04(d), 2106.05(f)(2). The additional element merely states that a machine learning model is used to identify that the regions are related, and does not link to a specific improvement.
Step 2B: Significantly more
Claim 10 recites
wherein the anomaly localization regions from individual anomaly detectors are combined into the localization region of the combined anomaly if a trained neural network identifies the anomaly localization regions of the detected anomalies in each pre-processing subset as relating to the combined anomaly
which is an additional element that amounts to adding the words “apply it” (or an equivalent) with the judicial exception, or merely uses a computer in its ordinary capacity as a tool to perform an existing process. See MPEP §§ 2106.04(d), 2106.05(f)(2). The additional element merely states that a machine learning model is used to identify that the regions are related, and does not link to a specific improvement.
Claim 11
Step 1:
Claim 11 is to a method.
Step 2A Prong 1: Abstract Idea
Claim 11 recites the abstract ideas of Claim 1 by dependency.
Claim 11 recites
wherein a contribution of a particular detector to the combined anomaly is determined by setting a feature vector corresponding to a total number of anomaly detectors, and by performing at least one of the following actions:
equating the contribution to the combined anomaly to a number calculated from the contribution of the particular anomaly of a spatial or temporal region of the anomaly obtained by the particular detector to the combined anomaly;
determining the contribution of the particular anomaly by a degree of proximity to a center of the combined anomaly;
when a combined anomaly of the particular detector is not present, setting the contribution to zero; and
when there is information about a degree of reliability or criticality of the particular detector for a technological process (TP) of the CPS in which the said detector detects an anomaly, changing the contribution of the detector based on the information about the degree of reliability or criticality
which are abstract ideas of a mental process that can practically be performed in the human mind, with or without the use of a physical aid such as pen and paper (including an observation, evaluation, judgment, opinion). See MPEP § 2106.04(a)(2)(III). A human being can perform these calculations and judgements to determine the contribution of anomalies.
Step 2A Prong 2: Additional elements
Claim 11 recites
for a technological process (TP) of the CPS
This is an additional element that amounts to adding insignificant extra-solution activity to the judicial exception. See MPEP §§ 2106.04(d), 2106.05(g). It only specifies a source of the data, and does not introduce any limitations on the data that would prevent the contribution determination from being performed in the human mind.
This is additionally an additional element that generally links the use of the judicial exception to a particular technological environment or field of use. See MPEP §§ 2106.04(d), 2106.05(h).
Claim 11 further recites
determining the contribution of the particular anomaly by applying a pretrained neural network that evaluates contributions
which is an additional element that amounts to adding the words “apply it” (or an equivalent) with the judicial exception, or merely uses a computer in its ordinary capacity as a tool to perform an existing process. See MPEP §§ 2106.04(d), 2106.05(f)(2). The additional element merely states that a neural network is used, and does not link to a specific improvement.
Step 2B: Significantly more
Claim 11 recites
for a technological process (TP) of the CPS
This is an additional element that amounts to adding insignificant extra-solution activity to the judicial exception. See MPEP § 2106.05(g). It only specifies a source of the data, and does not introduce any limitations on the data that would prevent the contribution determination from being performed in the human mind.
This is additionally an additional element that generally links the use of the judicial exception to a particular technological environment or field of use. See MPEP § 2106.05(h).
Claim 11 further recites
determining the contribution of the particular anomaly by applying a pretrained neural network that evaluates contributions
which is an additional element that amounts to adding the words “apply it” (or an equivalent) with the judicial exception, or merely uses a computer in its ordinary capacity as a tool to perform an existing process. See MPEP §§ 2106.04(d), 2106.05(f)(2). The additional element merely states that a neural network is used, and does not link to a specific improvement.
Claim 12
Step 1:
Claim 12 is to a method.
Step 2A Prong 1: Abstract Idea
Claim 12 recites the abstract ideas of Claim 1 by dependency.
Claim 12 recites
wherein after identifying at least one anomaly by each selected anomaly detector, the output data is further post-processed, wherein the post-processing includes:
calculating an extended set of anomaly characteristics, including anomaly hazard assessment, determining types and sizes of the anomalies, normalizing and unifying output information about anomalies, and detecting the combined anomaly by combining results obtained from the selected detectors
which are abstract ideas of mental processes that can practically be performed in the human mind, with or without the use of a physical aid such as pen and paper (including an observation, evaluation, judgment, opinion). See MPEP § 2106.04(a)(2)(III). These limitations are all related to manipulating and interpreting the anomaly information, which can be performed in the human mind.
Step 2A Prong 2: Additional elements
Claim 12 does not recite additional elements.
Step 2B: Significantly more
Claim 12 does not recite additional elements.
Claim 13
Step 1:
Claim 13 is to a method.
Step 2A Prong 1: Abstract Idea
Claim 13 recites the abstract ideas of Claim 1 by dependency.
Claim 13 recites
when calculating the characteristics of the anomalies is not feasible or possible, setting a pre-determined value for the characteristics of the anomaly for which the calculation is not performed
which are abstract ideas of mental processes that can practically be performed in the human mind, with or without the use of a physical aid such as pen and paper (including an observation, evaluation, judgment, opinion). See MPEP § 2106.04(a)(2)(III). The limitation is to the concept of having a default value for calculation, which can be performed in the human mind.
Step 2A Prong 2: Additional elements
Claim 13 does not recite additional elements.
Step 2B: Significantly more
Claim 13 does not recite additional elements.
Claim 14
Step 1:
Claim 14 is to a method.
Step 2A Prong 1: Abstract Idea
Claim 14 recites the abstract ideas of Claim 1 by dependency.
Claim 14 recites
wherein at least one of the following grouped characteristics of an anomaly associated with the detector that detected the anomaly is calculated:
a hazard class of the anomaly, type, and size of the anomaly;
a probability of anomaly detection by the anomaly detector;
values of deviations of predicted values of a plurality of parameters of the CPS from true values or default values, values of specified deviations from settings, and root mean square values of measures of deviations of at least some of the parameters of the CPS used in the anomaly detector;
maximum or average values of deviations of observed values of parameters of the CPS from certain predetermined limits and durations in time and frequency of specified deviations; and
detector performance in detecting anomalies
which are abstract ideas of mental processes that can practically be performed in the human mind, with or without the use of a physical aid such as pen and paper (including an observation, evaluation, judgment, opinion). See MPEP § 2106.04(a)(2)(III). These limitations are all related to calculating different types of information from the data, all of which can be performed in the human mind.
Step 2A Prong 2: Additional elements
Claim 14 recites
of the CPS
This is an additional element that amounts to adding insignificant extra-solution activity to the judicial exception. See MPEP §§ 2106.04(d), 2106.05(g). It only specifies a source of the data, and does not introduce any limitations on the data that would prevent the previously listed abstract ideas from being performed in the human mind.
This is additionally an additional element that generally links the use of the judicial exception to a particular technological environment or field of use. See MPEP §§ 2106.04(d), 2106.05(h).
Step 2B: Significantly more
Claim 14 recites
of the CPS
This is an additional element that amounts to adding insignificant extra-solution activity to the judicial exception. See MPEP § 2106.05(g). It only specifies a source of the data, and does not introduce any limitations on the data that would prevent the previously listed abstract ideas from being performed in the human mind.
This is additionally an additional element that generally links the use of the judicial exception to a particular technological environment or field of use. See MPEP § 2106.05(h).
Claim 15
Step 1:
Claim 15 is to a method.
Step 2A Prong 1: Abstract Idea
Claim 15 recites the abstract ideas of Claim 1 by dependency.
Claim 15 recites
wherein, an anomaly detector is selected for a particular grouped subset of the parameters, such that: the selected anomaly detector provides a predetermined accuracy and completeness in anomaly detection for the particular subset, in accordance with a predetermined performance of the anomaly detector on the particular subset of parameters, or expert knowledge about the subset of parameters
which are abstract ideas of mental processes that can practically be performed in the human mind, with or without the use of a physical aid such as pen and paper (including an observation, evaluation, judgment, opinion). See MPEP § 2106.04(a)(2)(III). These limitations are to evaluating the effectiveness of a detector, which can be performed in the human mind. Furthermore, the claim term “expert knowledge” implies a human expert.
Step 2A Prong 2: Additional elements
Claim 15 does not recite additional elements.
Step 2B: Significantly more
Claim 15 does not recite additional elements.
Claim 16
Step 1:
Claim 16 is to a method
Step 2A Prong 1: Abstract Idea
Claim 16 recites the abstract ideas of Claim 1 by dependency.
Step 2A Prong 2: Additional elements
Claim 16 recites
wherein subsets of parameters are selected in accordance with at least one of the following characteristics of the subsets:
significances of the parameters of the CPS for a technological process;
the parameters of the CPS being associated with a particular type of equipment;
the parameters of the CPS belonging to one technological process; and
uniformity of physical parameters of the CPS in a subset
These are additional elements that amount to adding insignificant extra-solution activity to the judicial exception. See MPEP §§ 2106.04(d), 2106.05(g). They only limit the way the data is selected, and do not introduce any limitations on the data that would prevent the previously listed abstract ideas from being performed in the human mind.
This is additionally an additional element that generally links the use of the judicial exception to a particular technological environment or field of use. See MPEP §§ 2106.04(d), 2106.05(h). The claim terms “CPS”, “technological process”, “equipment”, and “physical parameters” restrict the data to being obtained based on some form of physical system, but are too general to link to any particular improvement.
Step 2B: Significantly more
Claim 16 recites
wherein subsets of parameters are selected in accordance with at least one of the following characteristics of the subsets:
significances of the parameters of the CPS for a technological process;
the parameters of the CPS being associated with a particular type of equipment;
the parameters of the CPS belonging to one technological process; and
uniformity of physical parameters of the CPS in a subset
These are additional elements that amount to adding insignificant extra-solution activity to the judicial exception. See MPEP § 2106.05(g). They only limit the way the data is selected, and do not introduce any limitations on the data that would prevent the previously listed abstract ideas from being performed in the human mind.
This is additionally an additional element that generally links the use of the judicial exception to a particular technological environment or field of use. See MPEP § 2106.05(h). The claim terms “CPS”, “technological process”, “equipment”, and “physical parameters” restrict the data to being obtained based on some form of physical system, but are too general to link to any particular improvement.
Claims 17 – 21
Step 1:
Claims 17 – 21 are to machines.
Step 2A Prong 1: Abstract Idea
Claims 17 – 21 recite similar language to claims 1, 5, 2, 12 and 10 respectively, and recite similar abstract ideas.
Step 2A Prong 2: Additional elements
Claim 17 recites
at least one processor of a computing device
a data collector
a generator
an ensemble tool
and claim 19 recites
at least one post-processing unit
each detector having a dedicated set of post-processing units
which are additional elements that amount to adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer. See MPEP §§ 2106.04(d), 2106.05(f)(1).
Claims 17, 18, 19, 20 and 21 recite similar language to claims 1, 5, 2, 12 and 10 respectively, and otherwise recited additional elements that do not integrate the abstract idea into a practical application.
Step 2B: Significantly more
Claim 17 recites
at least one processor of a computing device
a data collector
a generator
an ensemble tool
and claim 19 recites
at least one post-processing unit
each detector having a dedicated set of post-processing units
which are additional elements that amount to adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer. See MPEP § 2106.05(f)(1).
Claims 17, 18, 19, 20 and 21 recite similar language to claims 1, 5, 2, 12 and 10 respectively, and otherwise recited additional elements that do not integrate the abstract idea into a practical application.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1 – 8, 10 – 12, and 14 – 21 are rejected under 35 U.S.C. 103 as being unpatentable over Mienye et al. (NPL, A Survey of Ensemble Learning: Concepts, Algorithms, Applications, and Prospects), hereinafter Mienye, in view of Al-Badri et al. (NPL, Adaptive Non-Maximum Suppression for improving performance of Rumex detection), hereinafter Al-Badri.
Regarding claim 1, Mienye teaches a method for detecting anomalies (Page 99144, Section VI Conclusion, ensemble learning is frequently applied in anomaly detection) in a cyber-physical system (Section IV Ensemble Learning Application in Recent Literature and Section V Discussions and Future Research Directions, ensemble learning can be used in relation to a number of physical systems, including the human body, object recognition, human activity recognition, and battery monitoring), the method comprising:
collecting data containing values of a plurality of parameters of the CPS (Fig. 1, input data);
generating at least two subsets of parameters from the collected data (Fig. 1, the data being split among each learner);
selecting at least two anomaly detectors from a plurality of anomaly detectors and selecting at least one corresponding subset of the parameters for each selected anomaly detector (Page 99132, the process of ensemble selection chooses which base models are used in the ensemble);
pre-processing each subset of the parameters and transmitting an output of the pre-processing to the corresponding anomaly detector (Many ensemble learning methods preprocess data, For example, page 99136 describes encoding category features into numerical ones; Page 99139 describes missing values and outliers being preprocessed; Page 99140 describes the use of a Gaussian filter)
detecting anomalies in each pre-processed subset using the corresponding anomaly detector (Section VI Conclusion, ensemble learning is used for anomaly detection. Section IV describes detectors for disease and fraud. With respect to the mapping of the anomaly detectors, each learner in Fig. 1 would be an anomaly detector); and
detecting a combined anomaly in the CPS (Pages 99131/99132 teach voting methods for combining learner outputs; Pages 99136/99138 teach bagging and stacking for combining learner outputs.).
Mienye does not explicitly teach that detecting a combined anomaly is done by combining anomaly localization regions from individual anomaly detectors into a localization region of the combined anomaly, wherein said localization regions determine anomalies in space and/or time, if a spatial or temporal intersection of the anomaly localization regions exceeds a predetermined percentage of the localization region of the combined anomaly (Although Mienye describes ensemble learning for image analysis in page 99143, it does not describe methods of combining results specialized to object localization).
Al-Badri teaches an ensemble method (Fig. 2, the method uses three different object detectors) for anomaly localization (Detecting of Rumex weeds) where a combined anomaly is detected by combining anomaly localization regions from individual anomaly detectors into a localized region of the combined anomaly, wherein said localization regions determine anomalies in space and/or time (The bounding boxes of leaves), if a spatial or temporal intersection of the anomaly localization regions exceeds a predetermined percentage of the localization region of the combined anomaly (Fig. 2 and Pages 5 and 6, the different models produce different detections in the form of proposed bounding boxes. Then, an ANMS module combines overlapping bounding boxes by eliminating boxes with a high intersection over union above a threshold value).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to, as an extension of the various ensemble methods taught by Mienye, one method of combining anomaly localization regions would be based on intersection over union in the same manner as taught by Al-Badri. One of ordinary skill would be aware that the ensemble methods taught by Mienye would be applicable to an anomaly localization context, because Mienye teaches anomaly detection in images, and because a great deal of work has been done in the field as taught by Al-Badri section 1. It would be obvious to use the general metric of intersection over union because such non-maximum suppression is an extensively used technique in computer vision (Al-Badri page 1), and it would be obvious to use the specific version of the method taught in Al-Badri because it addresses performance issues in using traditional NMS for localization (Al-Badri page 2).
Regarding claim 2, Mienye in view of Al-Badri teaches the method of claim 1, further comprising: post-processing the detected anomalies from each selected anomaly detector; and combining the post-processed detected anomalies (Mienye page 99131, weighted majority voting postprocesses detections by applying a weight to them, page 99138 teaches stacking, where postprocessing for using the meta-learner comprises formatting the predictions to fit the meta-learner; Al-Badri Fig. 2, the bounding boxes are post-processed detected anomalies produced by a Bbox regressor. Alternatively, setting the bounding boxes up for use in NMS can also be considered post-processing).
Regarding claim 3, Mienye in view of Al-Badri teaches the method of claim 1, wherein the selecting of the at least two anomaly detectors and the at least one corresponding subset of the parameters for each selected anomaly is based on at least one of:
characteristics of the CPS (Al-Badri pages 4 column 2, the networks chosen were robust against real-world challenges of the task);
types of the collected data and an amount of the collected data (Mienye page 99132, some selection strategies select base models based on validation data).
Regarding claim 4, Mienye in view of Al-Badri teaches the method of claim 1, wherein the selecting of the at least two anomaly detectors and the at least one corresponding subset of the parameters for each selected anomaly detector is performed based on at least one of:
a quality metric (Mienye page 99132 column 1, a scoring function is used to select base classifiers).
Regarding claim 5, Mienye in view of Al-Badri teaches the method of claim 1, wherein the pre-processing of a subset of the parameters includes at least one of:
filling in gaps in the values of a plurality of parameters of the CPS (Mienye page 99139, there exists work that fills missing values and outliers in the dataset);
normalization of values of a plurality of parameters of the CPS (Al-Badri page 4 column 1 normalizes image values based on the mean);
repackaging the values of a plurality of parameters of the CPS for processing by the anomaly detector (Mienye algorithms, the training data is packed into variable S. Additionally, the previously described preprocessing steps constitute repackaging the values, as they output the modified values in some form of data structure).
Regarding claim 6, Mienye in view of Al-Badri teaches the method of claim 1, wherein a detector of the at least two anomaly detectors detects anomalies by at least one of:
detecting anomalies when a forecast error exceeds a pre-determined threshold value, wherein the forecast error is computed by predicting values of a plurality of parameters of the CPS, wherein the detector determines a total forecast error for the values of the parameters of the CPS (Al-Badri page 3, typical NMS uses a minimum confidence score, suppressing any pixel that does not have a confident score; Al-Badri page 4, the classifiers output a confidence score representing the likelihood of an anomaly);
detecting anomalies by applying a machine learning model based on the values of a plurality of parameters of the CPS (Mienye Fig. 1, the learners; Al-Badri Fig. 2, each detector in the ensemble is a machine learning model using image data as parameters);
detecting anomalies when a rule for detecting anomalies is applied (The other described detection methods constitute a rule applied to the data to detect an anomaly).
Regarding claim 7, Mienye in view of Al-Badri teaches the method of claim 1, wherein a value of at least one of the parameters of the CPS comprises at least one of:
a sensor measurement (Al-Badri Fig. 2, the camera taking the image being a sensor; Mienye pages 99138 – 99144 recites a number of applications, each of which would require data to be acquired through some measurement, which would constitute a sensor).
Regarding claim 8, Mienye in view of Al-Badri teaches the method of claim 1, wherein the values of a plurality of parameters of the CPS are collected from the CPS at a shared time interval with an indication of the parameters of the CPS (The claim language is broad as to what constitutes “a shared time interval”. As there is no limit to how long such an interval is, it may be interpreted that any two points of data can be collected in a shared time interval, as long as the interval is sufficiently long). or from individual parts of the CPS in a form of a plurality of separate streams of values of a plurality of parameters of the CPS indicating the parameters contained in each anomaly stream (Mienye page 99141, an ensemble is used to learn time series data; Mienye cites a number of methods for ensemble learning for data stream analysis, see citations [39], [66], [73], [184].).
Regarding claim 10, Mienye in view of Al-Badri teaches the method of claim 1, wherein the anomaly localization regions from individual anomaly detectors are combined into the localization region of the combined anomaly if a trained neural network identifies the anomaly localization regions of the detected anomalies in each pre-processed subset as relating to the combined anomaly (Mienye pages 99137 and 99138, stacking has another neural network combine the results of learners; Al-Badri Fig. 3, in addition to NMS, the outputs of the three detectors are fed into another neural network layer).
Regarding claim 11, Mienye in view of Al-Badri teaches the method of claim 1, wherein a contribution of a particular detector to the combined anomaly is determined by setting a feature vector corresponding to a total number of anomaly detectors (Mienye page 99131, there is a combination method that involves weighting each classifier, represented by weight vector W; Al-Badri page 4, weights are applied to the outputs), and by performing at least one of the following actions:
equating the contribution to the combined anomaly to a number calculated from the contribution of the particular anomaly of a spatial or temporal region of the anomaly obtained by the particular detector to the combined anomaly (The aforementioned weights are numbers calculated from the contribution).
Regarding claim 12, Mienye in view of Al-Badri teaches the method of claim 1, wherein after identifying at least one anomaly by each selected anomaly detector, the output data is further post-processed, wherein the post-processing includes:
calculating an extended set of anomaly characteristics, including anomaly hazard assessment (Al-Badri Fig. 2, classifying the image to determine if it is a weed or not; Mienye page 99139, classifying what type of disease is detected), determining types (Mienye page 99139, the type of disease; Al-Badri, whether or not the image is a weed) and sizes (Al-Badri, the bounding boxes) of anomalies, normalizing and unifying output information about anomalies (Mienye page 99133, there is a normalization factor to each classifier in training; Al-Badri Fig. 3, the feature maps, RoI pooling, RPN, and regularization layers), and detecting the combined anomaly by combining results obtained from the selected detectors (The ensemble RCNN of Al-Badri, and the combining methods of Mienye).
Regarding claim 14, Mienye in view of Al-Badri teaches the method of claim 1, wherein at least one of the following grouped characteristics of an anomaly associated with the detector that detected the anomaly is calculated:
a probability of anomaly detection by the anomaly detector (Al-Badri page 5, NMS selects boxes based on the one with highest calculated probability);
detector performance in detecting anomalies (Mienye page 99132, selecting the learners involves determining which of them maximizes performance; Mienye also describes a number of loss functions for training the ensemble model).
Regarding claim 15, Mienye in view of Al-Badri teaches the method of claim 1, wherein an anomaly detector is selected for a particular grouped subset of the parameters, such that: the selected anomaly detector provides a predetermined accuracy and completeness in anomaly detection for the particular subset (Mienye page 99132, selecting / ordering a classifier based on the performance / validation error / kappa measure on a validation set), in accordance with a predetermined performance of the anomaly detector on the particular subset of the parameters (The previously discussed validation performance).
Regarding claim 16, Mienye in view of Al-Badri teaches the method of claim 1, wherein subsets of parameters are selected in accordance with at least one of the following characteristics of the subsets:
significances of the parameters of the CPS for a technological process (Mieneye pages 99138 – 99143 discuss various fields of use and technological processes, and the data that was used to identify anomalies in them. For example, the disease detection methods use patient risk factor data because they are significant to the process of treating them).;
the parameters of the CPS belonging to one technological process (Mieneye pages 99138 – 99143 discuss various fields of use and technological processes, and the data that was used to identify anomalies in them. For example, the fraud detection methods use transaction data because they belong to the technological process of credit card operations).
Regarding claim 17, Mienye in view of Al-Badri teaches at least one processor of a computing device (Al-Badri Table 1, the processor), a data collector (Mienye, the means of collecting various datasets; Al-Badri, the camera); a generator (The previously indicated processor of Al-Badri, or the computer system responsible for transferring the input data); and an ensemble tool (The combination rules of Mienye Fig. 1, the Ensemble RCNN of Al-Badri Fig. 2, or the processor of Al-Badri).
Claim 17 otherwise recites similar language to claim 1, and is similarly rejected.
Claim 18 recites similar language to claim 5, and is similarly rejected.
Regarding claim 19, Mienye in view of Al-Badri teaches at least one post processing-unit designed to process the output of a corresponding anomaly detector before transmitting the output to the ensemble tool, each detector having a dedicated set of post-processing units (Al-Badri Fig. 2, the classification and Bbox regressors for each feature extractor).
Claim 20 recites similar language to claim 12, and is similarly rejected.
Claim 21 recites similar language to claim 10, and is similarly rejected.
Claim 13 is rejected under 35 U.S.C. 103 as being unpatentable over Mienye in view of Al-Badri as applied to claim 1 above, and further in view of Python (NPL, cited in previous action).
Regarding claim 13, Mienye in view of Al-Badri teach the method of claim 1.
Mienye and Al-Badri do not explicitly teach that, when calculating the characteristics of the anomalies is not feasible or possible, setting a pre-determined value for the characteristics of the anomaly for which the calculation is not performed.
Python teaches a pre-determined value that is set when calculating is not feasible or possible, for which calculation is not performed (4. Built-in_constants, None is frequently used to represent the absence of a value).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to, in the method of Mienye in view of Al-Badri, when calculating, the characteristics of the anomalies is not feasible or possible, to set the characteristics of the anomaly to a pre-determined value such as None, for which the calculation is not performed. It would be obvious because this act is so commonly known within the art that programming languages include special values specifically for this purpose. It would be clear to one of ordinary skill in the art that the infeasibility or impossibility of calculating any value, including characteristics of the anomaly by a detector, would be a fundamental scenario to consider when programming an ensemble anomaly detection system.
Previously Indicated Allowable Subject Matter
In the first Non-Final Rejection mailed December 17, 2024, it was indicated that the original claim 10 contained allowable subject matter. In light of the art found in response to amendments and clarified interpretation of the claims, the original claim 10 would not be allowable. Al-Badri page 3 column 2 teaches an existing variant of NMS which removes duplicates based on the center of the detected object.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Agrawal et al. (US Patent Application Publication 2023/0196787) discusses another non-maximum suppression method. Cunha et al. (US Patent Application Publication 2021/0366096) discusses an ensemble method for anomaly detection.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BRYAN PAI SONG HUANG whose telephone number is (571)272-0510. The examiner can normally be reached Monday - Friday 11:30 AM - 8:30 PM.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, ASHISH THOMAS can be reached at (571) 272-0631. 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.
/B.P.H./Examiner, Art Unit 2114
/ASHISH THOMAS/Supervisory Patent Examiner, Art Unit 2114