DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application is being examined under the pre-AIA first to invent provisions.
Response to Arguments
112f Claim Interpretation Arguments
Applicant asserts:
Applicant argues, on page 8, that the limitation “units” is not used as a generic placeholder as shows in the specification and therefore does not invoke 112f.
Examiner response:
Examiner respectfully disagrees. According to MPEP 2181, a 3-prong analysis is used for the determination of whether a claim limitation invokes 112f. (A) the claim limitation uses the term "means" or "step" or a term used as a substitute for "means" that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function. The claims term “to” following “unit” is a substitute for “means.” (B) the term "means" or "step" or the generic placeholder is modified by functional language, typically, but not always linked by the transition word "for" (e.g., "means for") or another linking word or phrase, such as "configured to" or "so that." The term “to” is modified by the functional language / what the unit is doing. (C) the term "means" or "step" or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function. The term “unit” is the generic placeholder because there is no sufficient structure that is recited in the claims.
112b Rejection Arguments
Applicant asserts:
Applicant argues, on page 9, that the term “unit” has sufficient structure as expressed in Paragraph 0045 showing each unit is implemented by a processor.
Examiner response:
Examiner respectfully disagrees. The language of Paragraph 0047 suggests that the “units” may refer to operations and/or processes of a computer. This language does not make certain that the units are implemented by a generic processor or specialized processor for performing the task. Paragraphs 0076 – 0082 does not provide definitive structure for the “units.”
101 Rejection Arguments
Applicant asserts:
Applicant argues, on page 10, that the claimed steps collectively provide a practical application that “improves the accuracy, automation, and computational efficiency of forecasting systems”. Applicant further points that experiments show the “efficacy of the methodology in yielding high forecast accuracy even in the presence of irregular patterns.” Applicant further points to paragraph 0084 to show that the present invention allows for a high degree of accuracy compared with classical models. The improvements provided by the invention represent significantly more than the implementation of an abstract, mathematical concept, or a mental process
Examiner response:
Applicant's arguments have been fully considered but they are not persuasive. Arguments provided sets forth an improvement but in a conclusory manner. Examiner notes that there is no clear detail as to what aspect of the claimed invention shows an improvement over prior inventions and in what way.
103 Rejection Arguments
Applicant asserts:
Applicant argues, on page 12, that the reference Jian does not teach the entirety of claim 1.
Examiner response:
Applicant's arguments have been fully considered but they are not persuasive. In response to applicant's arguments against the references individually, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986).
Applicant asserts:
Applicant argues, on page 13, that the reference Hang does not teach the entirety of the claimed invention.
Examiner response:
Applicant's arguments have been fully considered but they are not persuasive. In response to applicant's arguments against the references individually, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986).
Applicant asserts:
Applicant argues, on page 15, that the reference Sven does not teach the entirety of the claimed invention.
Examiner response:
Applicant's arguments have been fully considered but they are not persuasive. In response to applicant's arguments against the references individually, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986).
Applicant asserts:
Applicant argues, on page 16, that the reference Abbas does not teach the entirety of the claimed invention.
Examiner response:
Applicant's arguments have been fully considered but they are not persuasive. In response to applicant's arguments against the references individually, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986).
Applicant asserts:
Applicant argues, on page 17, that the reference Higginson does not teach the entirety of the claimed invention.
Examiner response:
Applicant's arguments have been fully considered but they are not persuasive. In response to applicant's arguments against the references individually, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986).
Applicant asserts:
Applicant argues, on page 17, that the reference Newton does not teach the entirety of the claimed invention.
Examiner response:
Applicant's arguments have been fully considered but they are not persuasive. In response to applicant's arguments against the references individually, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986).
Applicant asserts:
Applicant argues, on page 17, that the reference Khuyen does not teach the entirety of the claimed invention.
Examiner response:
Applicant's arguments have been fully considered but they are not persuasive. In response to applicant's arguments against the references individually, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986).
Applicant asserts:
Applicant argues, on page 18, that the combination of references Jian, Hang, and Sven cannot be blended into a forecasting architecture in an obvious way.
Examiner response:
Applicant's arguments have been fully considered but they are not persuasive. In response to applicant’s argument that there is no teaching, suggestion, or motivation to combine the references, the examiner recognizes that obviousness may be established by combining or modifying the teachings of the prior art to produce the claimed invention where there is some teaching, suggestion, or motivation to do so found either in the references themselves or in the knowledge generally available to one of ordinary skill in the art. See In re Fine, 837 F.2d 1071, 5 USPQ2d 1596 (Fed. Cir. 1988), In re Jones, 958 F.2d 347, 21 USPQ2d 1941 (Fed. Cir. 1992), and KSR International Co. v. Teleflex, Inc., 550 U.S. 398, 82 USPQ2d 1385 (2007). In this case, it would be reasonable to combine the references to use certain techniques present within each invention that help solve their own problems to be leveraged and applied on time series data for forecasting.
Applicant asserts:
Applicant argues, on page 20, that the combination of references Jian, Hang, Sven, Abbas, Higginson, Newton, and Khuyen does not disclose the combination of wavelet based time frequency transformations, deep learning embeddings, unsupervised cluster, and regime-specific forecasting.
Examiner response:
Applicant's arguments have been fully considered but they are not persuasive. In response to applicant’s argument that there is no teaching, suggestion, or motivation to combine the references, the examiner recognizes that obviousness may be established by combining or modifying the teachings of the prior art to produce the claimed invention where there is some teaching, suggestion, or motivation to do so found either in the references themselves or in the knowledge generally available to one of ordinary skill in the art. See In re Fine, 837 F.2d 1071, 5 USPQ2d 1596 (Fed. Cir. 1988), In re Jones, 958 F.2d 347, 21 USPQ2d 1941 (Fed. Cir. 1992), and KSR International Co. v. Teleflex, Inc., 550 U.S. 398, 82 USPQ2d 1385 (2007). In this case, the combination of references do teach the combination of wavelet based time frequency transformations, deep learning embeddings, unsupervised cluster, and regime-specific forecasting as shown in the office action.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitation(s) is/are:
“a generating unit” in claim 10
“an applying unit” in claim 10
“an obtaining unit” in claim 10
“a partitioning unit” in claim 10
“a mapping unit” in claim 10
“an assembling unit” in claim 10
“a maintaining unit” in claim 10
“an applying unit” in claim 14
“a selecting unit” in claim 14
“a removing unit” in claim 15
“a performing unit” in claim 16
“a passing unit” in claim 17
“an identification unit” in claim 17
“a forecasting unit” in claim 17
“a storing unit” in claim 18
“a collecting unit” in claim 19
“a dividing unit” in claim 19
“a discarding unit” in claim 19
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Claim Rejections - 35 USC § 112b
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.
Claim 1 and 10-19 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 limitation “a generating unit, an applying unit, an obtaining unit, a partitioning unit, a mapping unit, an assembling unit, a maintaining unit, an applying unit, a selecting unit, a removing unit, a performing unit, a passing unit, an identification unit, forecasting unit, a storing unit, a collecting unit, a dividing unit, a discarding unit” invokes 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. However, the written description fails to disclose the corresponding structure, material, or acts for performing the entire claimed function and to clearly link the structure, material, or acts to the function. no association between the structure and the function can be found in the specification. Therefore, the claim is indefinite and is rejected under 35 U.S.C. 112(b) or pre-AIA 35 U.S.C. 112, second paragraph.
Applicant may:
(a) Amend the claim so that the claim limitation will no longer be interpreted as a limitation under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph;
(b) Amend the written description of the specification such that it expressly recites what structure, material, or acts perform the entire claimed function, without introducing any new matter (35 U.S.C. 132(a)); or
(c) Amend the written description of the specification such that it clearly links the structure, material, or acts disclosed therein to the function recited in the claim, without introducing any new matter (35 U.S.C. 132(a)).
If applicant is of the opinion that the written description of the specification already implicitly or inherently discloses the corresponding structure, material, or acts and clearly links them to the function so that one of ordinary skill in the art would recognize what structure, material, or acts perform the claimed function, applicant should clarify the record by either:
(a) Amending the written description of the specification such that it expressly recites the corresponding structure, material, or acts for performing the claimed function and clearly links or associates the structure, material, or acts to the claimed function, without introducing any new matter (35 U.S.C. 132(a)); or
(b) Stating on the record what the corresponding structure, material, or acts, which are implicitly or inherently set forth in the written description of the specification, perform the claimed function. For more information, see 37 CFR 1.75(d) and MPEP §§ 608.01(o) and 2181.
For Examination purposes “a generating unit, an applying unit, an obtaining unit, a partitioning unit, a mapping unit, an assembling unit, a maintaining unit, an applying unit, a selecting unit, a removing unit, a performing unit, a passing unit, an identification unit, forecasting unit, a storing unit, a collecting unit, a dividing unit, a discarding unit” will be interpreted as a generic processor.
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 1-19 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
In reference to claim 1:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a process
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“generating (S1502) a plurality of time-frequency images for a plurality of overlapping time-series segments of a user-specified window size, wherein the time- frequency images are generated by employing a continuous wavelet and obtaining the continuous wavelet transform at different scales;” which is an abstract idea because it is directed to a mathematical concept. The limitation as drafted, and under a broadest reasonable interpretation (MPEP 2106.04(a)(2)(l)(c)).
“obtaining (S1506) a 2D representation for each output numerical vector by applying the Uniform Manifold Approximation and Projection (UMAP) on the collection of numerical vectors;” which is an abstract idea because it is directed to a mathematical concept. The limitation as drafted, and under a broadest reasonable interpretation (MPEP 2106.04(a)(2)(l)(c)).
“partitioning automatically (S1508) the 2D representations into clusters by applying a clustering algorithm and an objective criterion such as Bayesian Information Criterion (BIC) to select the optimal number of clusters;” which is an abstract idea because it is directed to a mathematical concept. The limitation as drafted, and under a broadest reasonable interpretation (MPEP 2106.04(a)(2)(l)(c)).
mapping (S1510) each sample of the time-series to the cluster corresponding to the time-frequency image of the time-series segment that the sample belongs to, for collecting time-series segments from stretches identified within the time-series samples; which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could map each sample of the time-series to the cluster corresponding to the time frequency image of the time series segment that the sample belongs to.
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
“applying (S1504) a pre-trained deep convolutional neural network trained on a plurality of images to the time-frequency images to output a high dimensional numerical vector for each time-frequency image;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“assembling (S1512) a cluster-specific Auto-Regressive Moving Average (ARMA) forecast model considering all the non-overlapping segments of the time-series that belong to the cluster;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“and maintaining (S 1514) all cluster specific ARMA models in a repository.” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
“generating (S1502) a plurality of time-frequency images for a plurality of overlapping time-series segments of a user-specified window size, wherein the time- frequency images are generated by employing a continuous wavelet and obtaining the continuous wavelet transform at different scales;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“applying (S1504) a pre-trained deep convolutional neural network trained on a plurality of images to the time-frequency images to output a high dimensional numerical vector for each time-frequency image;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“assembling (S1512) a cluster-specific Auto-Regressive Moving Average (ARMA) forecast model considering all the non-overlapping segments of the time-series that belong to the cluster;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“and maintaining (S 1514) all cluster specific ARMA models in a repository.” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 2:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a process
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“and wherein the default wavelet is set to Morlet wavelet.” which is an abstract idea because it is directed to a mathematical concept. The limitation as drafted, and under a broadest reasonable interpretation (MPEP 2106.04(a)(2)(l)(c)).
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
“wherein any continuous wavelet is used to generate time-frequency images for each time-series segment;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)). The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
“wherein any continuous wavelet is used to generate time-frequency images for each time-series segment;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)). The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 3:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a process
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
No
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
“wherein the pre-trained deep convolutional neural network is applied to each time-frequency image to output a high dimensional numerical vector;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“and wherein the neural network is set to ResNet50.” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
“wherein the pre-trained deep convolutional neural network is applied to each time-frequency image to output a high dimensional numerical vector;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“and wherein the neural network is set to ResNet50.” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 4:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a process
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“wherein partitioning automatically (1508) the 2D representation points into clusters further comprises: applying the BIC over a plurality of different clusters;” which is an abstract idea because it is directed to a mathematical concept. The limitation as drafted, and under a broadest reasonable interpretation (MPEP 2106.04(a)(2)(l)(c)).
“and selecting a plurality of clusters that correspond to the maximal BIC.” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could select a plurality of clusters from evaluating the maximal BIC.
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
No
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
No
In reference to claim 5:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a process
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“wherein assembling (S1512) a cluster-specific forecast model further comprises: removing trend from each time-series segment of the collection to convert each window- size segment of the time-series into a stationary time-series segment;” which is an abstract idea because it is directed to a mathematical concept. The limitation as drafted, and under a broadest reasonable interpretation (MPEP 2106.04(a)(2)(l)(a)).
“wherein the model is identified by selecting the number of autoregressive terms, p, and the number of moving average terms, q according to the Akaike Information Criterion (AIC).” which is an abstract idea because it is directed to a mathematical concept. The limitation as drafted, and under a broadest reasonable interpretation (MPEP 2106.04(a)(2)(l)(c)).
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
“and applying an ARMA model over the collection of stationarized segments of the cluster,” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)). The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
“and applying an ARMA model over the collection of stationarized segments of the cluster,” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)). The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 6:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a process
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“performing (S1516) forecasts on the time-series at any time t for a future horizon, h, at every new instant.” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could evaluate the time series at any time t for a future horizon h, at every new instant and perform a forecast.
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
No
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
No
In reference to claim 7:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a process
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“performing (S1516) forecasts on the time-series at any time t for a future horizon, h, at every new instant.” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could consider a window length segment of the time-series backwards from t.
“generating the time-frequency image corresponding to the window length segment of the time-series by applying the continuous wavelet transform using the user-selected wavelet;” which is an abstract idea because it is directed to a mathematical concept. The limitation as drafted, and under a broadest reasonable interpretation (MPEP 2106.04(a)(2)(l)(c)).
“identifying the matching cluster for the time-frequency image by applying the UMAP;” which is an abstract idea because it is directed to a mathematical concept. The limitation as drafted, and under a broadest reasonable interpretation (MPEP 2106.04(a)(2)(l)(c)).
“and forecasting the h future values using the selected cluster -based model.” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)). For example, a person could evaluate the time series data and forecast the future values.
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
“passing the generated time-frequency image through the deep convolutional neural network to extract a numerical vector from the said time-frequency image;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“selecting the corresponding cluster specific model in the repository using the index of the identified cluster;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
“passing the generated time-frequency image through the deep convolutional neural network to extract a numerical vector from the said time-frequency image;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“selecting the corresponding cluster specific model in the repository using the index of the identified cluster;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 8:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a process
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
No
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
“performing (51518) the method (1500) periodically whenever the time-series collects a fixed number of new points;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“and storing (S 1520) the cluster -specific refined models in the repository.” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
“performing (51518) the method (1500) periodically whenever the time-series collects a fixed number of new points;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“and storing (S 1520) the cluster -specific refined models in the repository.” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 9:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a process
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“identifying different contiguous stretches of the time-series within the time-series samples mapped to the same cluster;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could identify different contiguous stretches of the time series.
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
“dividing each stretch into non-overlapping window-size segments;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“and discarding the last segment of the stretch and collecting the remaining segments from each stretch.” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
“dividing each stretch into non-overlapping window-size segments;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“and discarding the last segment of the stretch and collecting the remaining segments from each stretch.” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 10:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a manufacture
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“wherein the time-frequency images are generated by employing a continuous wavelet” which is an abstract idea because it is directed to a mathematical concept. The limitation as drafted, and under a broadest reasonable interpretation (MPEP 2106.04(a)(2)(l)(c)).
“an obtaining unit (1606) for obtaining 2D representation for each output numerical vector by applying any dimensionality reduction technique on the collection of numerical vectors;” which is an abstract idea because it is directed to a mathematical concept. The limitation as drafted, and under a broadest reasonable interpretation (MPEP 2106.04(a)(2)(l)(c)).
“a partitioning unit (1608) for automatically partitioning the 2D representations into clusters by applying a clustering algorithm and an objective criterion such as Bayesian Information Criterion (BIC) to select the optimal number of clusters;” which is an abstract idea because it is directed to a mathematical concept. The limitation as drafted, and under a broadest reasonable interpretation (MPEP 2106.04(a)(2)(l)(c)).
“a mapping unit (1610) for mapping each sample of the time-series to the cluster corresponding to the time-frequency image of the time-series segment that the sample belongs to, for collecting time-series segments from stretches identified within the time- series samples;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)). For example, a person could evaluate each sample of the time-series and map them to the cluster corresponding to the time-frequency image.
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
“an applying unit (1604) for applying a pre-trained deep convolutional neural network trained on a plurality of images to the time-frequency images to output a high dimensional numerical vector for each time-frequency image;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“a generating unit (1602) for generating a plurality of time-frequency images for a plurality of overlapping time-series segments of a user-specified window size,” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“and obtaining the continuous wavelet transform at different scales;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“an applying unit (1604) for applying a pre-trained deep convolutional neural network trained on a plurality of images to the time-frequency images to output a high dimensional numerical vector for each time-frequency image;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“an assembling unit (1612) for assembling a cluster-specific Auto-Regressive Moving Average (ARMA) forecast model considering all the non-overlapping segments of the time-series that belong to the cluster;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“and a maintaining unit (1614) for maintaining all cluster specific ARMA models in a repository.” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
“an applying unit (1604) for applying a pre-trained deep convolutional neural network trained on a plurality of images to the time-frequency images to output a high dimensional numerical vector for each time-frequency image;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“a generating unit (1602) for generating a plurality of time-frequency images for a plurality of overlapping time-series segments of a user-specified window size,” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“and obtaining the continuous wavelet transform at different scales;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“an applying unit (1604) for applying a pre-trained deep convolutional neural network trained on a plurality of images to the time-frequency images to output a high dimensional numerical vector for each time-frequency image;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“an assembling unit (1612) for assembling a cluster-specific Auto-Regressive Moving Average (ARMA) forecast model considering all the non-overlapping segments of the time-series that belong to the cluster;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“and a maintaining unit (1614) for maintaining all cluster specific ARMA models in a repository.” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 11:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a manufacture
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“wherein any continuous wavelet is used to generate time-frequency images for each time-series segment;” which is an abstract idea because it is directed to a mathematical concept. The limitation as drafted, and under a broadest reasonable interpretation (MPEP 2106.04(a)(2)(l)(c)).
“and wherein the default wavelet is set to Morlet wavelet.” which is an abstract idea because it is directed to a mathematical concept. The limitation as drafted, and under a broadest reasonable interpretation (MPEP 2106.04(a)(2)(l)(c)).
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
No
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
No
In reference to claim 12:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a manufacture
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
No
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
“wherein the pre-trained deep convolutional neural network is applied to each time-frequency image to output a high dimensional numerical vector;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“and wherein the neural network is set to ResNet50.” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
“wherein the pre-trained deep convolutional neural network is applied to each time-frequency image to output a high dimensional numerical vector;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“and wherein the neural network is set to ResNet50.” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 13:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a manufacture
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“wherein the obtaining unit (1606) for obtaining 2D representation for each output numerical vector by applying any dimensionality reduction technique such as the Uniform Manifold Approximation and Projection (UMAP) on the collection of numerical vectors.” which is an abstract idea because it is directed to a mathematical concept. The limitation as drafted, and under a broadest reasonable interpretation (MPEP 2106.04(a)(2)(l)(c)).
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
No
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
No
In reference to claim 14:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a manufacture
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“an applying unit (16081) for applying the BIC over a plurality of different clusters;” which is an abstract idea because it is directed to a mathematical concept. The limitation as drafted, and under a broadest reasonable interpretation (MPEP 2106.04(a)(2)(l)(c)).
“and a selecting unit (16082) for selecting a plurality of clusters that correspond to the maximal BIC.” which is an abstract idea because it is directed to a mathematical concept. The limitation as drafted, and under a broadest reasonable interpretation (MPEP 2106.04(a)(2)(l)(c)).
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
No
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
No
In reference to claim 15:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a manufacture
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“a removing unit (16122) for removing trend from each time-series segment of the collecting unit (1610a) to convert each window-size segment of the time-series into a stationary time-series segment;” which is an abstract idea because it is directed to a mathematical concept. The limitation as drafted, and under a broadest reasonable interpretation (MPEP 2106.04(a)(2)(l)(a)).
“and an applying unit (16123) for applying an ARMA model over the collection of stationarized partitions of the cluster, wherein the model is identified by selecting the number of autoregressive terms, p, and the number of moving average terms, q according to the Akaike Information Criterion (AIC).” which is an abstract idea because it is directed to a mathematical concept. The limitation as drafted, and under a broadest reasonable interpretation (MPEP 2106.04(a)(2)(l)(a)).
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
No
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
No
In reference to claim 16:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a manufacture
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“a performing unit (1616) for performing forecasts on the time-series at any time t for a future horizon, h, at every new instant.” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could perform forecasts on the time-series at any time t for a future horizon from evaluating the time-series data.
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
No
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
No
In reference to claim 17:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a manufacture
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“a generating unit (16162) for generating the time-frequency image corresponding to the window length segment of the time-series by applying the continuous wavelet transform using the user-selected wavelet;” which is an abstract idea because it is directed to a mathematical concept. The limitation as drafted, and under a broadest reasonable interpretation (MPEP 2106.04(a)(2)(l)(c)).
“an identification unit (16164) for identifying the matching cluster for the time-frequency image by applying the UMAP;” which is an abstract idea because it is directed to a mathematical concept. The limitation as drafted, and under a broadest reasonable interpretation (MPEP 2106.04(a)(2)(l)(c)).
“and a forecasting unit (16166) for forecasting the h future values using the selected cluster - based model.” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)). For example, a person could evaluate the time-series data and forecast future values.
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
“a window length segment unit (16161) for considering a window length segment of the time-series backwards from t;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“a passing unit (16163) for passing the generated time-frequency image through the deep convolutional neural network to extract a numerical vector from the said time-frequency image;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“a selecting unit (16165) for selecting the corresponding cluster specific model in the repository using the index of the identified cluster;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
“a window length segment unit (16161) for considering a window length segment of the time-series backwards from t;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“a passing unit (16163) for passing the generated time-frequency image through the deep convolutional neural network to extract a numerical vector from the said time-frequency image;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“a selecting unit (16165) for selecting the corresponding cluster specific model in the repository using the index of the identified cluster;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 18:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a manufacture
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“further comprising a performing unit (1618) to periodically evaluate the forecasting model whenever the time- series collects a fixed number of new samples;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could evaluate the forecasting model whenever the time-series collects a fixed number of new samples.
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
“and a storing unit (1620) for storing the cluster -specific refined models in the repository.” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)). The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
“and a storing unit (1620) for storing the cluster -specific refined models in the repository.” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)). The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 19:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a manufacture
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“a collecting unit (16101) for identifying different contiguous stretches of the time-series within the time-series samples mapped to a cluster;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could _.
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
“a dividing unit (16102) for dividing each stretch into contiguous non-overlapping window size segments;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“and a discarding unit (16103) for discarding the last segment of the stretch and collecting the remaining segments from each stretch.” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
“a dividing unit (16102) for dividing each stretch into contiguous non-overlapping window size segments;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“and a discarding unit (16103) for discarding the last segment of the stretch and collecting the remaining segments from each stretch.” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
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.
Claim(s) 1, 4-10, 13-19 are rejected under 35 U.S.C. 103 as being unpatentable over LV, Jian-ming et al; CN 110570613 A (hereinafter “Jian”) in view of Hang Hu et al; “Spatial Segmentation of Mass Spectrometry Imaging Data by Combining Multivariate Clustering and Univariate Thresholding” (hereinafter “Hang”) in further view of Sven Stringer; “Dealing with abrupt market changes in your analysis - a brief tutorial on time series change point detection” (hereinafter “Sven”) in further view Abbas Keshvani; “Using AIC to Test ARIMA Models” (hereinafter “Abbas”) in further view of Higginson; Antony Stephen et al; US 20210081492 A1 (hereinafter “Higginson”).
Regarding claim 1, Jian teaches generating (S1502) a plurality of time-frequency images for a plurality of overlapping time-series segments of a user-specified window size, wherein the time- frequency images are generated by employing a continuous wavelet and obtaining the continuous wavelet transform at different scales; (Jian Paragraph 0025; "step of obtaining wavelet time-frequency pattern as follows: S1, selecting a wavelet mother function ψ (t), and generated continuous wavelet at a different scale according to wavelet mother function ψ (t) a, b belongs to R a≠0, this step uses the mother wavelet is Haar wavelet" Examiner notes that steps S1-S4 shows generating a plurality of time-frequency images/time-frequency pattern for a plurality of overlapping time-series segments, wherein the images are generated by employing a continuous wavelet and obtaining the continuous wavelet transform at different scales; the different scales chosen affect the window size of the overlapping time series segments making it user defined.)
applying (S1504) a pre-trained deep convolutional neural network trained on a plurality of images to the time-frequency images to output a high dimensional numerical vector for each time-frequency image; (Jian Paragraph 0029; "the scaled wavelet time-frequency graph is input into a pre-trained convolutional neural network, and the output obtained is the event type corresponding to the vibration signal. The event type is numbered using a one-hot vector." Examiner notes that the image input/time-frequency images is applied to a pre-trained deep convolutional neural network/convolution neural network trained to output a high dimensional numerical vector/one-hot vector for each time frequency image.)
Jian does not teach obtaining (S1506) a 2D representation for each output numerical vector by applying the Uniform Manifold Approximation and Projection (UMAP) on the collection of numerical vectors;
partitioning automatically (S1508) the 2D representations into clusters by applying a clustering algorithm and an objective criterion including Bayesian Information Criterion (BIC) to select the optimal number of clusters;
mapping (S1510) each sample of the time-series to the cluster corresponding to the time-frequency image of the time-series segment that the sample belongs to, for collecting time-series segments from stretches identified within the time-series samples;
assembling (S1512) a cluster-specific Auto-Regressive Moving Average (ARMA) forecast model considering all the non-overlapping segments of the time-series that belong to the cluster;
and maintaining (S 1514) all cluster specific ARMA models in a repository.
However, Hang does teach obtaining (S1506) a 2D representation for each output numerical vector by applying the Uniform Manifold Approximation and Projection (UMAP) on the collection of numerical vectors; (Hang Section "Experimental Section" Sub-section "Image Segmentation by multivariate clustering" Paragraph 1; "Both UMAP48 and PCA49 were used for dimensionality reduction. UMAP was performed to transform MSI data arrays into a low-dimensional space, in which each pixel is represented by a vector of transformed feature values (SI 1.2)." Examiner notes that MSI data arrays is the collection of numerical vectors where UMAP is applied to obtain 2d representations/fig 4A.)
partitioning automatically (S1508) the 2D representations into clusters by applying a clustering algorithm and an objective criterion including Bayesian Information Criterion (BIC) to select the optimal number of clusters; (Hang Section "Results and Discussion" Sub-section "Hyperparameter search for PCA+GMM Clustering" Paragraph 3; "the optimal number of clusters may be estimated using UMAP visualizations. Furthermore, we use the information criteria described in the experimental section to validate this parameter search strategy. Since GMM is a probabilistically grounded method, the probability of the clustering assignment for each pixel is traceable, which enables the calculation of the likelihood and AIC/BIC values in the fitted model." Examiner notes the 2d representations are automatically partitioned into clusters by applying a clustering algorithm/GMM and objective criterion/BIC to select the optimal number of clusters.)
mapping (S1510) each sample of the time-series to the cluster corresponding to the time-frequency image of the time-series segment that the sample belongs to, [for collecting time-series segments from stretches identified within the time-series samples]; (Hang Section "Results and Discussion" Sub-section "Dimensionality reduction for multivariate clustering" Paragraph 4; "Individual pixels are color-coded based on their cluster assignments indicated by the color bar on the right of Figure 2." Examiner notes that cluster assignments is mapping each sample to the cluster)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian and Hang. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. One of ordinary skill would have motivation to combine Jian and Hang to use UMAP to visualize the embedded clusters in the data arrays "UMAP is a powerful technique for the visualization of the embedded local clusters that present in the high-dimensional MSI data." (Hang Section "Results and Discussion" Sub-section "Dimensionality reduction for multivariate clustering" Paragraph 5;).
Jian in view of Hang does not teach for collecting time-series segments from stretches identified within the time-series samples
However, Sven does teach for collecting time-series segments from stretches identified within the time-series samples (Sven Paragraph 1; "we will apply change point detection to a single stock value time series (SPYD) showing a large drop when the Covid-19 crisis started… In practice you would apply these methods to one or more time series of your sales volume over time or economic activity in your industry and region of interest… an abrupt deviation from the previous trend is typically observed." Examiner notes that the cluster that contains one or more time series of your sales volume over time or economic activity in your industry or region of interest is used in identifying different contiguous stretches of the time series within the time series samples/ identifying an abrupt deviation from the previous trend in single stock value time series (SPYD))
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian, Hang, and Sven. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. Sven teaches identifying different stretches of trend in time series data, breaks them into a pre-crisis period and crisis period, and ignores the crisis period. One of ordinary skill would have motivation to combine Jian, Hang, and Sven to remove segments within the time series graph that do not represent daily business decision making "The rationale would be that this period is not representative and therefore uninformative for daily business decision making after the crisis." (Sven Paragraph 15).
Jian in view of Hang in further view of Sven does not teach assembling (S1512) a cluster-specific Auto-Regressive Moving Average (ARMA) forecast model considering all the non-overlapping segments of the time-series that belong to the cluster;
However, Abbas does teach assembling (S1512) a cluster-specific Auto-Regressive Moving Average (ARMA) forecast model considering all the non-overlapping segments of the time-series that belong to the cluster; (Abbas Paragraph 7; "Now, we can test various ARMA models against the DJIA 1988-1989 First Difference. I will test 25 ARMA models: ARMA(1,1); ARMA(1,2), … , ARMA(3,3), … , ARMA(5,5). To compare these 25 models, I will use the AIC…Since ARMA(2,3) is the best model for the First Difference of DJIA 1988-1989, we use ARIMA(2,1,3) for DJIA 1988-1989." Examiner notes selecting best model using AIC is assembling a cluster specific ARMA forecast model considering all the non-overlapping segments of the time-series/DJIA 1988-1989 that belong to the cluster)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian, Hang, Sven, and Abbas. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. Sven teaches identifying different stretches of trend in time series data, breaks them into a pre-crisis period and crisis period, and ignores the crisis period. Abbas teaches determining an ARMA model using AIC to find the best fit. One of ordinary skill would have motivation to combine Jian, Hang, Sven, and Abbas to utilize AIC in determining the ARMA model for goodness of fit and simplicity of the model into a single statistic for time series forecasting. "The Akaike Information Critera (AIC) is a widely used measure of a statistical model. It basically quantifies 1) the goodness of fit, and 2) the simplicity/parsimony, of the model into a single statistic." (Abbas Paragraph 1).
Jian in view of Hang in further view of Sven in further view of Abbas does not teach and maintaining (S 1514) all cluster specific ARMA models in a repository.
However, Higginson does teach and maintaining (S 1514) all cluster specific ARMA models in a repository. (Higginson Paragraph 0037; "populated time-series models are stored in the data repository 200 for use in later forecasts… The time-series models 220 include one or more … Trigonometric Seasonality Box-Cox ARMA")
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian, Hang, Sven, Abbas, and Higginson. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. Sven teaches identifying different stretches of trend in time series data, breaks them into a pre-crisis period and crisis period, and ignores the crisis period. Abbas teaches determining an ARMA model using AIC to find the best fit. Higginson teaches a tuning operation to determine the best time series model to use to best fit the historical time series data. One of ordinary skill would have motivation to combine Jian, Hang, Sven, Abbas, and Higginson to select the best time series model for the type of time series data for better accuracy. "These components of the time-series models 221 improve the accuracy of the models and allow the models 220 to be adapted to various types of time-series data collected from the monitored systems." (Higginson Paragraph 0038).
Regarding claim 4, Jian does not teach The method as claimed in claim 1, wherein partitioning automatically (1508) the 2D representation points into clusters further comprises: applying the BIC over a plurality of different clusters;
and selecting a plurality of clusters that correspond to the maximal BIC.
However, Hang does teach The method as claimed in claim 1, wherein partitioning automatically (1508) the 2D representation points into clusters further comprises: applying the BIC over a plurality of different clusters; (Hang Section "Results and Discussion" Sub-section "Hyperparameter search for PCA+GMM Clustering" Paragraph 3; "Since UMAP effectively separates complex MSI data in 2D/3D feature space, the optimal number of clusters may be estimated using UMAP visualizations. Furthermore, we use the information criteria described in the experimental section to validate this parameter search strategy. Since GMM is a probabilistically grounded method, the probability of the clustering assignment for each pixel is traceable, which enables the calculation of the likelihood and AIC/BIC values in the fitted model.")
and selecting a plurality of clusters that correspond to the maximal BIC. (Hang Section "Results and Discussion" Sub-section "Hyperparameter search for PCA+GMM Clustering" Paragraph 4; "a shallow minimum is observed in the BIC plot spanning over 15–25 mixture components…the number of mixture component determined by analyzing AIC/BIC values is consistent with the number of clusters estimated by UMAP visualizations." Examiner notes that the maximal/best BIC is the lowest/minimum BIC value.)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian and Hang. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. One of ordinary skill would have motivation to combine Jian and Hang to use UMAP to visualize the embedded clusters in the data arrays "UMAP is a powerful technique for the visualization of the embedded local clusters that present in the high-dimensional MSI data." (Hang Section "Results and Discussion" Sub-section "Dimensionality reduction for multivariate clustering" Paragraph 5;).
Regarding claim 5, Jian does not teach The method as claimed in claim 1, wherein assembling (S1512) a cluster-specific forecast model further comprises: removing trend from each time-series segment of the collection to convert each window- size segment of the time-series into a stationary time-series segment;
and applying an ARMA model over the collection of stationarized segments of the cluster, wherein the model is identified by selecting the number of autoregressive terms, p, and the number of moving average terms, q according to the Akaike Information Criterion (AIC).
However, Abbas does teach The method as claimed in claim 1, wherein assembling (S1512) a cluster-specific forecast model further comprises: removing trend from each time-series segment of the collection to convert each window- size segment of the time-series into a stationary time-series segment; (Abbas Paragraph 5; "So, we may want to take the first difference of the DJIA 1988-1989 index. This is expressed in the equation below: Delta Y = Y_t - Y_{t-1} The first difference is thus, the difference between an entry and entry preceding it. The timeseries and AIC of the First Difference are shown below. They indicate a stationary time series." Examiner notes that differencing is removing trend from each DJIA index/time series segment of the collection to convert them into stationary time series segments.)
and applying an ARMA model over the collection of stationarized segments of the cluster, wherein the model is identified by selecting the number of autoregressive terms, p, and the number of moving average terms, q according to the Akaike Information Criterion (AIC). (Abbas Paragraph 7; "Now, we can test various ARMA models against the DJIA 1988-1989 First Difference. I will test 25 ARMA models: ARMA(1,1); ARMA(1,2), … , ARMA(3,3), … , ARMA(5,5). To compare these 25 models, I will use the AIC…Since ARMA(2,3) is the best model for the First Difference of DJIA 1988-1989, we use ARIMA(2,1,3) for DJIA 1988-1989." Abbas Paragraph 11; "Next: Determining the above coefficients, and forecasting the DJIA." Examiner notes that the model is identified by using AIC to select the autoregressive terms and moving average terms; ARMA model is used to forecast the DJIA/collection of stationarized segments of the cluster.)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian, Hang, Sven, and Abbas. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. Sven teaches identifying different stretches of trend in time series data, breaks them into a pre-crisis period and crisis period, and ignores the crisis period. Abbas teaches determining an ARMA model using AIC to find the best fit. One of ordinary skill would have motivation to combine Jian, Hang, Sven, and Abbas to utilize AIC in determining the ARMA model for goodness of fit and simplicity of the model into a single statistic for time series forecasting. "The Akaike Information Critera (AIC) is a widely used measure of a statistical model. It basically quantifies 1) the goodness of fit, and 2) the simplicity/parsimony, of the model into a single statistic." (Abbas Paragraph 1).
Regarding claim 6, Jian does not teach The method as claimed in claim 1, further comprising: performing (S1516) forecasts on the time-series at any time t for a future horizon, h, at every new instant.
However, Higginson does teach The method as claimed in claim 1, further comprising: performing (S1516) forecasts on the time-series at any time t for a future horizon, h, at every new instant. (Higginson Paragraph 0056; "The forecast module 134 obtains a time series of recently collected metrics for each entity from the data repository 200 and inputs the data into the corresponding time-series model generated by the training module 133. In turn, the time-series model outputs predictions 135 of future values in the time series as a predicted workload, resource utilization, and/or performance associated with the entity." Higginson Paragraph 0071; "the resource management system selects the size of test dataset to represent the forecast horizon of each time-series model, which depends on the granularity of the time-series data.")
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian, Hang, Sven, Abbas, and Higginson. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. Sven teaches identifying different stretches of trend in time series data, breaks them into a pre-crisis period and crisis period, and ignores the crisis period. Abbas teaches determining an ARMA model using AIC to find the best fit. Higginson teaches a tuning operation to determine the best time series model to use to best fit the historical time series data. One of ordinary skill would have motivation to combine Jian, Hang, Sven, Abbas, and Higginson to select the best time series model for the type of time series data for better accuracy. "These components of the time-series models 221 improve the accuracy of the models and allow the models 220 to be adapted to various types of time-series data collected from the monitored systems." (Higginson Paragraph 0038).
Regarding claim 7, Jian teaches generating the time-frequency image corresponding to the window length segment of the time-series by applying the continuous wavelet transform using the user-selected wavelet; (Jian Paragraph 0025; "step of obtaining wavelet time-frequency pattern as follows: S1, selecting a wavelet mother function ψ (t), and generated continuous wavelet at a different scale according to wavelet mother function ψ (t) a, b belongs to R a≠0, this step uses the mother wavelet is Haar wavelet" Examiner notes that steps S1-S4 shows generating a plurality of time-frequency images/time-frequency pattern for a plurality of overlapping time-series segments, wherein the images are generated by employing a continuous wavelet and obtaining the continuous wavelet transform at different scales; the different scales chosen affect the window size of the overlapping time series segments making it user defined.)
passing the generated time-frequency image through the deep convolutional neural network to extract a numerical vector from the said time-frequency image; (Jian Paragraph 0029; "the scaled wavelet time-frequency graph is input into a pre-trained convolutional neural network, and the output obtained is the event type corresponding to the vibration signal. The event type is numbered using a one-hot vector." Examiner notes that the image input/time-frequency images is passed to a pre-trained deep convolutional neural network/convolution neural network trained to output a high dimensional numerical vector/one-hot vector for each time frequency image.)
Jian does not teach The method as claimed in claim 6, wherein performing forecasts on the time-series at any time t for a future horizon, h further comprises: considering a window length segment of the time-series backwards from t;
identifying the matching cluster for the time-frequency image by applying the UMAP;
selecting the corresponding cluster specific model in the repository using the index of the identified cluster;
and forecasting the h future values using the selected cluster -based model.
However, Higginson does teach The method as claimed in claim 6, wherein performing forecasts on the time-series at any time t for a future horizon, h further comprises: considering a window length segment of the time-series backwards from t; (Higginson Paragraph 0071; "the resource management system may include, in test dataset, 24 observations spanning a day for data that is collected hourly; seven observations spanning a week for data that is collected daily; and/or four observations spanning approximately a month for data that is collected weekly." Examiner notes that the window length backwards can be considered from array of spanning time frames)
selecting the corresponding cluster specific model in the repository using the index of the identified cluster; (Higginson Paragraph 0073; "By performing the tuning operation, the resource management system determines whether the historical data includes seasonal patterns (Operation 403), multi-seasonal patterns (Operation 404), trends (Operation 405), and outliers or shocks (Operation 406). Based on the identified characteristics of the historical time-series data, the resource management system selects particular time-series models that are likely a good fit for the historical data." Examiner notes that the determinations of the historical data is the index that the management system is using to select the cluster specific model)
and forecasting the h future values using the selected cluster -based model. (Higginson Paragraph 0056; "The forecast module 134 obtains a time series of recently collected metrics for each entity from the data repository 200 and inputs the data into the corresponding time-series model generated by the training module 133. In turn, the time-series model outputs predictions 135 of future values in the time series as a predicted workload, resource utilization, and/or performance associated with the entity.")
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian, Hang, Sven, Abbas, and Higginson. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. Sven teaches identifying different stretches of trend in time series data, breaks them into a pre-crisis period and crisis period, and ignores the crisis period. Abbas teaches determining an ARMA model using AIC to find the best fit. Higginson teaches a tuning operation to determine the best time series model to use to best fit the historical time series data. One of ordinary skill would have motivation to combine Jian, Hang, Sven, Abbas, and Higginson to select the best time series model for the type of time series data for better accuracy. "These components of the time-series models 221 improve the accuracy of the models and allow the models 220 to be adapted to various types of time-series data collected from the monitored systems." (Higginson Paragraph 0038).
Jian in view of Higginson does not teach identifying the matching cluster for the time-frequency image by applying the UMAP;
However, Hang does teach identifying the matching cluster for the time-frequency image by applying the UMAP; (Hang Section "Results and Discussion" Sub-section "Hyperparameter search for PCA+GMM Clustering" Paragraph 3; "Since UMAP effectively separates complex MSI data in 2D/3D feature space, the optimal number of clusters may be estimated using UMAP visualizations. Furthermore, we use the information criteria described in the experimental section to validate this parameter search strategy. Since GMM is a probabilistically grounded method, the probability of the clustering assignment for each pixel is traceable, which enables the calculation of the likelihood and AIC/BIC values in the fitted model." Examiner notes UMAP is applied to the MSI data to obtain time frequency images and clustered using GMM)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian and Hang. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. One of ordinary skill would have motivation to combine Jian and Hang to use UMAP to visualize the embedded clusters in the data arrays "UMAP is a powerful technique for the visualization of the embedded local clusters that present in the high-dimensional MSI data." (Hang Section "Results and Discussion" Sub-section "Dimensionality reduction for multivariate clustering" Paragraph 5;).
Regarding claim 8, Jian does not teach The method as claimed in claim 1, further comprising: performing (51518) the method (1500) periodically whenever the time-series collects a fixed number of new points;
and storing (S 1520) the cluster -specific refined models in the repository.
However, Higginson does teach The method as claimed in claim 1, further comprising: performing (51518) the method (1500) periodically whenever the time-series collects a fixed number of new points; (Higginson Paragraph 0059; "if the staleness determining module 136 determines that the models are more than one week old or have an error rate that exceeds a predetermined threshold, the resource management system 130 may re-train a model using the training module 133 and the most recent historical data 210 obtained by the monitoring module 131." Examiner notes after collecting a weeks' worth of data/fixed number of new points, perform retraining/the method.)
and storing (S 1520) the cluster -specific refined models in the repository. (Higginson Paragraph 0037; "populated time-series models are stored in the data repository 200 for use in later forecasts.")
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian, Hang, Sven, Abbas, and Higginson. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. Sven teaches identifying different stretches of trend in time series data, breaks them into a pre-crisis period and crisis period, and ignores the crisis period. Abbas teaches determining an ARMA model using AIC to find the best fit. Higginson teaches a tuning operation to determine the best time series model to use to best fit the historical time series data. One of ordinary skill would have motivation to combine Jian, Hang, Sven, Abbas, and Higginson to select the best time series model for the type of time series data for better accuracy. "These components of the time-series models 221 improve the accuracy of the models and allow the models 220 to be adapted to various types of time-series data collected from the monitored systems." (Higginson Paragraph 0038).
Regarding claim 9, Jian does not teach The method as claimed in claim 1 wherein mapping (S1510) each sample of the time-series to the cluster corresponding to the time-frequency image of the time-series segment that the sample belongs to, further comprises the steps of: identifying different contiguous stretches of the time-series within the time-series samples mapped to the same cluster;
dividing each stretch into non-overlapping window-size segments;
and discarding the last segment of the stretch and collecting the remaining segments from each stretch.
However, Sven does teach The method as claimed in claim 1 wherein mapping (S1510) each sample of the time-series to the cluster corresponding to the time-frequency image of the time-series segment that the sample belongs to, further comprises the steps of: identifying different contiguous stretches of the time-series within the time-series samples mapped to the same cluster; (Sven Paragraph 1; "we will apply change point detection to a single stock value time series (SPYD) showing a large drop when the Covid-19 crisis started… In practice you would apply these methods to one or more time series of your sales volume over time or economic activity in your industry and region of interest… an abrupt deviation from the previous trend is typically observed.")
dividing each stretch into non-overlapping window-size segments; (Sven Paragraph 4; "The aim of our analysis is to identify distinct time periods: for example a pre-crisis and crisis period. It makes sense to set the number of lines to two during the crisis, and to three once a clear post-crisis period has emerged. Below we see the fitted lines of PLR with two lines. In this particular case the crisis period seems to consist of a significant drop followed by a relatively strong upswing.")
and discarding the last segment of the stretch and collecting the remaining segments from each stretch. (Sven Paragraph 15; "The easiest and safest option is to completely ignore the crisis period during model training of future models.")
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian, Hang, and Sven. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. Sven teaches identifying different stretches of trend in time series data, breaks them into a pre-crisis period and crisis period, and ignores the crisis period. One of ordinary skill would have motivation to combine Jian, Hang, and Sven to remove segments within the time series graph that do not represent daily business decision making "The rationale would be that this period is not representative and therefore uninformative for daily business decision making after the crisis." (Sven Paragraph 15).
Regarding claim 10, Jian teaches [a generating unit] (1602) for generating a plurality of time-frequency images for a plurality of overlapping time-series segments of a user-specified window size, wherein the time-frequency images are generated by employing a continuous wavelet and obtaining the continuous wavelet transform at different scales; (Jian Paragraph 0025; "step of obtaining wavelet time-frequency pattern as follows: S1, selecting a wavelet mother function ψ (t), and generated continuous wavelet at a different scale according to wavelet mother function ψ (t) a, b belongs to R a≠0, this step uses the mother wavelet is Haar wavelet" Examiner notes that steps S1-S4 shows generating a plurality of time-frequency images/time-frequency pattern for a plurality of overlapping time-series segments, wherein the images are generated by employing a continuous wavelet and obtaining the continuous wavelet transform at different scales; the different scales chosen affect the window size of the overlapping time series segments making it user defined.)
[an applying unit] (1604) for applying a pre-trained deep convolutional neural network trained on a plurality of images to the time-frequency images to output a high dimensional numerical vector for each time-frequency image; (Jian Paragraph 0029; "the scaled wavelet time-frequency graph is input into a pre-trained convolutional neural network, and the output obtained is the event type corresponding to the vibration signal. The event type is numbered using a one-hot vector." Examiner notes that the image input/time-frequency images is applied to a pre-trained deep convolutional neural network/convolution neural network trained to output a high dimensional numerical vector/one-hot vector for each time frequency image.)
Jian does not teach an obtaining unit (1606) for obtaining 2D representation for each output numerical vector by applying any dimensionality reduction technique on the collection of numerical vectors;
a partitioning unit (1608) for automatically partitioning the 2D representations into clusters by applying a clustering algorithm and an objective criterion including Bayesian Information Criterion (BIC) to select the optimal number of clusters;
a mapping unit (1610) for mapping each sample of the time-series to the cluster corresponding to the time-frequency image of the time-series segment that the sample belongs to, for collecting time-series segments from stretches identified within the time- series samples;
an assembling unit (1612) for assembling a cluster-specific Auto-Regressive Moving Average (ARMA) forecast model considering all the non-overlapping segments of the time-series that belong to the cluster;
and a maintaining unit (1614) for maintaining all cluster specific ARMA models in a repository.
Hang does teach [an obtaining unit] (1606) for obtaining 2D representation for each output numerical vector by applying any dimensionality reduction technique on the collection of numerical vectors; (Hang Section "Experimental Section" Sub-section "Image Segmentation by multivariate clustering" Paragraph 1; "Both UMAP48 and PCA49 were used for dimensionality reduction. UMAP was performed to transform MSI data arrays into a low-dimensional space, in which each pixel is represented by a vector of transformed feature values (SI 1.2)." Examiner notes that MSI data arrays is the collection of numerical vectors where UMAP is applied to obtain 2d representations/fig 4A.)
[a partitioning unit] (1608) for automatically partitioning the 2D representations into clusters by applying a clustering algorithm and an objective criterion including Bayesian Information Criterion (BIC) to select the optimal number of clusters; (Hang Section "Results and Discussion" Sub-section "Hyperparameter search for PCA+GMM Clustering" Paragraph 3; "the optimal number of clusters may be estimated using UMAP visualizations. Furthermore, we use the information criteria described in the experimental section to validate this parameter search strategy. Since GMM is a probabilistically grounded method, the probability of the clustering assignment for each pixel is traceable, which enables the calculation of the likelihood and AIC/BIC values in the fitted model." Examiner notes the 2d representations are automatically partitioned into clusters by applying a clustering algorithm/GMM and objective criterion/BIC to select the optimal number of clusters.)
[a mapping unit] (1610) for mapping each sample of the time-series to the cluster corresponding to the time-frequency image of the time-series segment that the sample belongs to, [for collecting time-series segments from stretches identified within the time- series samples]; (Hang Section "Results and Discussion" Sub-section "Dimensionality reduction for multivariate clustering" Paragraph 4; "Individual pixels are color-coded based on their cluster assignments indicated by the color bar on the right of Figure 2." Examiner notes that cluster assignments is mapping each sample to the cluster)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian and Hang. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. One of ordinary skill would have motivation to combine Jian and Hang to use UMAP to visualize the embedded clusters in the data arrays "UMAP is a powerful technique for the visualization of the embedded local clusters that present in the high-dimensional MSI data." (Hang Section "Results and Discussion" Sub-section "Dimensionality reduction for multivariate clustering" Paragraph 5;).
Jian in view of Hang does not teach for collecting time-series segments from stretches identified within the time- series samples
However, Sven does teach for collecting time-series segments from stretches identified within the time- series samples (Sven Paragraph 1; "we will apply change point detection to a single stock value time series (SPYD) showing a large drop when the Covid-19 crisis started… In practice you would apply these methods to one or more time series of your sales volume over time or economic activity in your industry and region of interest… an abrupt deviation from the previous trend is typically observed." Examiner notes that the cluster that contains one or more time series of your sales volume over time or economic activity in your industry or region of interest is used in identifying different contiguous stretches of the time series within the time series samples/ identifying an abrupt deviation from the previous trend in single stock value time series (SPYD))
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian, Hang, and Sven. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. Sven teaches identifying different stretches of trend in time series data, breaks them into a pre-crisis period and crisis period, and ignores the crisis period. One of ordinary skill would have motivation to combine Jian, Hang, and Sven to remove segments within the time series graph that do not represent daily business decision making "The rationale would be that this period is not representative and therefore uninformative for daily business decision making after the crisis." (Sven Paragraph 15).
Jian in view of Hang in further view of Sven does not teach an assembling unit (1612) for assembling a cluster-specific Auto-Regressive Moving Average (ARMA) forecast model considering all the non-overlapping segments of the time-series that belong to the cluster;
However, Abbas does teach [an assembling unit] (1612) for assembling a cluster-specific Auto-Regressive Moving Average (ARMA) forecast model considering all the non-overlapping segments of the time-series that belong to the cluster; (Abbas Paragraph 7; "Now, we can test various ARMA models against the DJIA 1988-1989 First Difference. I will test 25 ARMA models: ARMA(1,1); ARMA(1,2), … , ARMA(3,3), … , ARMA(5,5). To compare these 25 models, I will use the AIC…Since ARMA(2,3) is the best model for the First Difference of DJIA 1988-1989, we use ARIMA(2,1,3) for DJIA 1988-1989." Examiner notes selecting best model using AIC is assembling a cluster specific ARMA forecast model considering all the non-overlapping segments of the time-series/DJIA 1988-1989 that belong to the cluster)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian, Hang, Sven, and Abbas. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. Sven teaches identifying different stretches of trend in time series data, breaks them into a pre-crisis period and crisis period, and ignores the crisis period. Abbas teaches determining an ARMA model using AIC to find the best fit. One of ordinary skill would have motivation to combine Jian, Hang, Sven, and Abbas to utilize AIC in determining the ARMA model for goodness of fit and simplicity of the model into a single statistic for time series forecasting. "The Akaike Information Critera (AIC) is a widely used measure of a statistical model. It basically quantifies 1) the goodness of fit, and 2) the simplicity/parsimony, of the model into a single statistic." (Abbas Paragraph 1).
Jian in view of Hang in further view of Sven in further view of Abbas does not teach
a generating unit
an applying unit
an obtaining unit
a partitioning unit
a mapping unit
an assembling unit
and a maintaining unit (1614) for maintaining all cluster specific ARMA models in a repository.
However, Higginson does teach
a generating unit
an applying unit
an obtaining unit
a partitioning unit
a mapping unit
an assembling unit (Higginson Paragraph 0125; “Bus 802 carries the data to main memory 806, from which processor 804 retrieves and executes the instructions. The instructions received by main memory 806 may optionally be stored on storage device 810 either before or after execution by processor 804.” Examiner notes that the plurality of units listed are performed on a generic processor.)
and a maintaining unit (1614) for maintaining all cluster specific ARMA models in a repository. (Higginson Paragraph 0037; "populated time-series models are stored in the data repository 200 for use in later forecasts… The time-series models 220 include one or more … Trigonometric Seasonality Box-Cox ARMA")
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian, Hang, Sven, Abbas, and Higginson. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. Sven teaches identifying different stretches of trend in time series data, breaks them into a pre-crisis period and crisis period, and ignores the crisis period. Abbas teaches determining an ARMA model using AIC to find the best fit. Higginson teaches a tuning operation to determine the best time series model to use to best fit the historical time series data. One of ordinary skill would have motivation to combine Jian, Hang, Sven, Abbas, and Higginson to select the best time series model for the type of time series data for better accuracy. "These components of the time-series models 221 improve the accuracy of the models and allow the models 220 to be adapted to various types of time-series data collected from the monitored systems." (Higginson Paragraph 0038).
Regarding claim 13, Jian does not teach The system as claimed in claim 10, wherein the obtaining unit (1606) for obtaining 2D representation for each output numerical vector by applying any dimensionality reduction technique such as the Uniform Manifold Approximation and Projection (UMAP) on the collection of numerical vectors.
However, Hang does teach The system as claimed in claim 10, wherein the obtaining unit (1606) for obtaining 2D representation for each output numerical vector by applying any dimensionality reduction technique such as the Uniform Manifold Approximation and Projection (UMAP) on the collection of numerical vectors. (Hang Section "Experimental Section" Sub-section "Image Segmentation by multivariate clustering" Paragraph 1; "Both UMAP48 and PCA49 were used for dimensionality reduction. UMAP was performed to transform MSI data arrays into a low-dimensional space, in which each pixel is represented by a vector of transformed feature values (SI 1.2)." Examiner notes that MSI data arrays is the collection of numerical vectors where UMAP is applied to obtain 2d representations/fig 4A.)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian and Hang. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. One of ordinary skill would have motivation to combine Jian and Hang to use UMAP to visualize the embedded clusters in the data arrays "UMAP is a powerful technique for the visualization of the embedded local clusters that present in the high-dimensional MSI data." (Hang Section "Results and Discussion" Sub-section "Dimensionality reduction for multivariate clustering" Paragraph 5;).
Regarding claim 14, Jian does not teach The system as claimed in claim 10, wherein the partitioning unit (1608) for automatically partitioning the 2D representation points into clusters further comprises:an applying unit (16081) for applying the BIC over a plurality of different clusters;
and a selecting unit (16082) for selecting a plurality of clusters that correspond to the maximal BIC.
However, Hang does teach The system as claimed in claim 10, wherein the partitioning unit (1608) for automatically partitioning the 2D representation points into clusters further comprises: [an applying unit] (16081) for applying the BIC over a plurality of different clusters; (Hang Section "Results and Discussion" Sub-section "Hyperparameter search for PCA+GMM Clustering" Paragraph 3; "Since UMAP effectively separates complex MSI data in 2D/3D feature space, the optimal number of clusters may be estimated using UMAP visualizations. Furthermore, we use the information criteria described in the experimental section to validate this parameter search strategy. Since GMM is a probabilistically grounded method, the probability of the clustering assignment for each pixel is traceable, which enables the calculation of the likelihood and AIC/BIC values in the fitted model.")
and [a selecting unit] (16082) for selecting a plurality of clusters that correspond to the maximal BIC. (Hang Section "Results and Discussion" Sub-section "Hyperparameter search for PCA+GMM Clustering" Paragraph 4; "a shallow minimum is observed in the BIC plot spanning over 15–25 mixture components…the number of mixture component determined by analyzing AIC/BIC values is consistent with the number of clusters estimated by UMAP visualizations." Examiner notes that the maximal/best BIC is the lowest/minimum BIC value.)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian and Hang. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. One of ordinary skill would have motivation to combine Jian and Hang to use UMAP to visualize the embedded clusters in the data arrays "UMAP is a powerful technique for the visualization of the embedded local clusters that present in the high-dimensional MSI data." (Hang Section "Results and Discussion" Sub-section "Dimensionality reduction for multivariate clustering" Paragraph 5;).
Jian does not teach an applying unit
A selecting unit
However, Higginson does teach applying unit
A selecting unit (Higginson Paragraph 0125; “Bus 802 carries the data to main memory 806, from which processor 804 retrieves and executes the instructions. The instructions received by main memory 806 may optionally be stored on storage device 810 either before or after execution by processor 804.” Examiner notes that the plurality of units listed are performed on a generic processor.)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian, Hang, Sven, Abbas, and Higginson. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. Sven teaches identifying different stretches of trend in time series data, breaks them into a pre-crisis period and crisis period, and ignores the crisis period. Abbas teaches determining an ARMA model using AIC to find the best fit. Higginson teaches a tuning operation to determine the best time series model to use to best fit the historical time series data. One of ordinary skill would have motivation to combine Jian, Hang, Sven, Abbas, and Higginson to select the best time series model for the type of time series data for better accuracy. "These components of the time-series models 221 improve the accuracy of the models and allow the models 220 to be adapted to various types of time-series data collected from the monitored systems." (Higginson Paragraph 0038).
Regarding claim 15, Jian does not teach The system as claimed in claim 10, wherein the assembling unit (1612) for assembling a cluster-specific forecast model further comprises:a removing unit (16122) for removing trend from each time-series segment of the collecting unit (1610a) to convert each window-size segment of the time-series into a stationary time-series segment;
and an applying unit (16123) for applying an ARMA model over the collection of stationarized partitions of the cluster, wherein the model is identified by selecting the number of autoregressive terms, p, and the number of moving average terms, q according to the Akaike Information Criterion (AIC).
However, Abbas does teach The system as claimed in claim 10, wherein the assembling unit (1612) for assembling a cluster-specific forecast model further comprises:[a removing unit] (16122) for removing trend from each time-series segment of the collecting unit (1610a) to convert each window-size segment of the time-series into a stationary time-series segment; (Abbas Paragraph 5; "So, we may want to take the first difference of the DJIA 1988-1989 index. This is expressed in the equation below: Delta Y = Y_t - Y_{t-1} The first difference is thus, the difference between an entry and entry preceding it. The timeseries and AIC of the First Difference are shown below. They indicate a stationary time series." Examiner notes that differencing is removing trend from each DJIA index/time series segment of the collection to convert them into stationary time series segments.)
and [an applying unit] (16123) for applying an ARMA model over the collection of stationarized partitions of the cluster, wherein the model is identified by selecting the number of autoregressive terms, p, and the number of moving average terms, q according to the Akaike Information Criterion (AIC). (Abbas Paragraph 7; "Now, we can test various ARMA models against the DJIA 1988-1989 First Difference. I will test 25 ARMA models: ARMA(1,1); ARMA(1,2), … , ARMA(3,3), … , ARMA(5,5). To compare these 25 models, I will use the AIC…Since ARMA(2,3) is the best model for the First Difference of DJIA 1988-1989, we use ARIMA(2,1,3) for DJIA 1988-1989." Abbas Paragraph 11; "Next: Determining the above coefficients, and forecasting the DJIA." Examiner notes that the model is identified by using AIC to select the autoregressive terms and moving average terms; ARMA model is used to forecast the DJIA/collection of stationarized segments of the cluster.)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian, Hang, Sven, and Abbas. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. Sven teaches identifying different stretches of trend in time series data, breaks them into a pre-crisis period and crisis period, and ignores the crisis period. Abbas teaches determining an ARMA model using AIC to find the best fit. One of ordinary skill would have motivation to combine Jian, Hang, Sven, and Abbas to utilize AIC in determining the ARMA model for goodness of fit and simplicity of the model into a single statistic for time series forecasting. "The Akaike Information Critera (AIC) is a widely used measure of a statistical model. It basically quantifies 1) the goodness of fit, and 2) the simplicity/parsimony, of the model into a single statistic." (Abbas Paragraph 1).
Jian does not teach a removing unit
an applying unit
However, Higginson does teach a removing unit
An applying unit(Higginson Paragraph 0125; “Bus 802 carries the data to main memory 806, from which processor 804 retrieves and executes the instructions. The instructions received by main memory 806 may optionally be stored on storage device 810 either before or after execution by processor 804.” Examiner notes that the plurality of units listed are performed on a generic processor.)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian, Hang, Sven, Abbas, and Higginson. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. Sven teaches identifying different stretches of trend in time series data, breaks them into a pre-crisis period and crisis period, and ignores the crisis period. Abbas teaches determining an ARMA model using AIC to find the best fit. Higginson teaches a tuning operation to determine the best time series model to use to best fit the historical time series data. One of ordinary skill would have motivation to combine Jian, Hang, Sven, Abbas, and Higginson to select the best time series model for the type of time series data for better accuracy. "These components of the time-series models 221 improve the accuracy of the models and allow the models 220 to be adapted to various types of time-series data collected from the monitored systems." (Higginson Paragraph 0038).
Regarding claim 16, Jian does not teach The system as claimed in claim 10, further comprises: a performing unit (1616) for performing forecasts on the time-series at any time t for a future horizon, h, at every new instant.
However, Higginson does teach The system as claimed in claim 10, further comprises: a performing unit (1616) for performing forecasts on the time-series at any time t for a future horizon, h, at every new instant. (Higginson Paragraph 0056; "The forecast module 134 obtains a time series of recently collected metrics for each entity from the data repository 200 and inputs the data into the corresponding time-series model generated by the training module 133. In turn, the time-series model outputs predictions 135 of future values in the time series as a predicted workload, resource utilization, and/or performance associated with the entity." Higginson Paragraph 0071; "the resource management system selects the size of test dataset to represent the forecast horizon of each time-series model, which depends on the granularity of the time-series data." Higginson Paragraph 0125; “Bus 802 carries the data to main memory 806, from which processor 804 retrieves and executes the instructions. The instructions received by main memory 806 may optionally be stored on storage device 810 either before or after execution by processor 804.” Examiner notes that the plurality of units listed are performed on a generic processor.)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian, Hang, Sven, Abbas, and Higginson. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. Sven teaches identifying different stretches of trend in time series data, breaks them into a pre-crisis period and crisis period, and ignores the crisis period. Abbas teaches determining an ARMA model using AIC to find the best fit. Higginson teaches a tuning operation to determine the best time series model to use to best fit the historical time series data. One of ordinary skill would have motivation to combine Jian, Hang, Sven, Abbas, and Higginson to select the best time series model for the type of time series data for better accuracy. "These components of the time-series models 221 improve the accuracy of the models and allow the models 220 to be adapted to various types of time-series data collected from the monitored systems." (Higginson Paragraph 0038).
Regarding claim 17, Jian teaches [a generating unit] (16162) for generating the time-frequency image corresponding to the window length segment of the time-series by applying the continuous wavelet transform using the user-selected wavelet; (Jian Paragraph 0025; "step of obtaining wavelet time-frequency pattern as follows: S1, selecting a wavelet mother function ψ (t), and generated continuous wavelet at a different scale according to wavelet mother function ψ (t) a, b belongs to R a≠0, this step uses the mother wavelet is Haar wavelet" Examiner notes that steps S1-S4 shows generating a plurality of time-frequency images/time-frequency pattern for a plurality of overlapping time-series segments, wherein the images are generated by employing a continuous wavelet and obtaining the continuous wavelet transform at different scales; the different scales chosen affect the window size of the overlapping time series segments making it user defined.)
[a passing unit] (16163) for passing the generated time-frequency image through the deep convolutional neural network to extract a numerical vector from the said time-frequency image; (Jian Paragraph 0029; "the scaled wavelet time-frequency graph is input into a pre-trained convolutional neural network, and the output obtained is the event type corresponding to the vibration signal. The event type is numbered using a one-hot vector." Examiner notes that the image input/time-frequency images is passed to a pre-trained deep convolutional neural network/convolution neural network trained to output a high dimensional numerical vector/one-hot vector for each time frequency image.)
Jian does not teach The system as claimed in claim 15, wherein the performing unit (1616) for performing forecasts on the time-series at any time t for a future horizon, h further comprises: a window length segment unit (16161) for considering a window length segment of the time-series backwards from t;
an identification unit (16164) for identifying the matching cluster for the time-frequency image by applying the UMAP;
a selecting unit (16165) for selecting the corresponding cluster specific model in the repository using the index of the identified cluster;
and a forecasting unit (16166) for forecasting the h future values using the selected cluster - based model.
However, Hang does teach [an identification unit] (16164) for identifying the matching cluster for the time-frequency image by applying the UMAP; (Hang Section "Results and Discussion" Sub-section "Hyperparameter search for PCA+GMM Clustering" Paragraph 3; "Since UMAP effectively separates complex MSI data in 2D/3D feature space, the optimal number of clusters may be estimated using UMAP visualizations. Furthermore, we use the information criteria described in the experimental section to validate this parameter search strategy. Since GMM is a probabilistically grounded method, the probability of the clustering assignment for each pixel is traceable, which enables the calculation of the likelihood and AIC/BIC values in the fitted model." Examiner notes UMAP is applied to the MSI data to obtain time frequency images and clustered using GMM)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian and Hang. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. One of ordinary skill would have motivation to combine Jian and Hang to use UMAP to visualize the embedded clusters in the data arrays "UMAP is a powerful technique for the visualization of the embedded local clusters that present in the high-dimensional MSI data." (Hang Section "Results and Discussion" Sub-section "Dimensionality reduction for multivariate clustering" Paragraph 5;).
Jian in view of Hang does not teach a generating unit
A passing unit
An identification unit
The system as claimed in claim 15, wherein the performing unit (1616) for performing forecasts on the time-series at any time t for a future horizon, h further comprises: a window length segment unit (16161) for considering a window length segment of the time-series backwards from t;
a selecting unit (16165) for selecting the corresponding cluster specific model in the repository using the index of the identified cluster;
and a forecasting unit (16166) for forecasting the h future values using the selected cluster - based model.
However, Higginson does teach a generating unit
A passing unit
An identification unit(Higginson Paragraph 0125; “Bus 802 carries the data to main memory 806, from which processor 804 retrieves and executes the instructions. The instructions received by main memory 806 may optionally be stored on storage device 810 either before or after execution by processor 804.” Examiner notes that the plurality of units listed are performed on a generic processor.)
The system as claimed in claim 15, wherein the performing unit (1616) for performing forecasts on the time-series at any time t for a future horizon, h further comprises: a window length segment unit (16161) for considering a window length segment of the time-series backwards from t; (Higginson Paragraph 0071; "the resource management system may include, in test dataset, 24 observations spanning a day for data that is collected hourly; seven observations spanning a week for data that is collected daily; and/or four observations spanning approximately a month for data that is collected weekly." Examiner notes that the window length backwards can be considered from array of spanning time frames)
a selecting unit (16165) for selecting the corresponding cluster specific model in the repository using the index of the identified cluster; (Higginson Paragraph 0073; "By performing the tuning operation, the resource management system determines whether the historical data includes seasonal patterns (Operation 403), multi-seasonal patterns (Operation 404), trends (Operation 405), and outliers or shocks (Operation 406). Based on the identified characteristics of the historical time-series data, the resource management system selects particular time-series models that are likely a good fit for the historical data." Examiner notes that the determinations of the historical data is the index that the management system is using to select the cluster specific model)
and a forecasting unit (16166) for forecasting the h future values using the selected cluster - based model. (Higginson Paragraph 0056; "The forecast module 134 obtains a time series of recently collected metrics for each entity from the data repository 200 and inputs the data into the corresponding time-series model generated by the training module 133. In turn, the time-series model outputs predictions 135 of future values in the time series as a predicted workload, resource utilization, and/or performance associated with the entity.")
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian, Hang, Sven, Abbas, and Higginson. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. Sven teaches identifying different stretches of trend in time series data, breaks them into a pre-crisis period and crisis period, and ignores the crisis period. Abbas teaches determining an ARMA model using AIC to find the best fit. Higginson teaches a tuning operation to determine the best time series model to use to best fit the historical time series data. One of ordinary skill would have motivation to combine Jian, Hang, Sven, Abbas, and Higginson to select the best time series model for the type of time series data for better accuracy. "These components of the time-series models 221 improve the accuracy of the models and allow the models 220 to be adapted to various types of time-series data collected from the monitored systems." (Higginson Paragraph 0038).
Regarding claim 18, Jian does not teach The system as claimed in claim 10, further comprising a performing unit (1618) to periodically evaluate the forecasting model whenever the time- series collects a fixed number of new samples;
and a storing unit (1620) for storing the cluster -specific refined models in the repository.
However, Higginson does teach The system as claimed in claim 10, further comprising a performing unit (1618) to periodically evaluate the forecasting model whenever the time- series collects a fixed number of new samples; (Higginson Paragraph 0059; "if the staleness determining module 136 determines that the models are more than one week old or have an error rate that exceeds a predetermined threshold, the resource management system 130 may re-train a model using the training module 133 and the most recent historical data 210 obtained by the monitoring module 131." Higginson Paragraph 0125; “Bus 802 carries the data to main memory 806, from which processor 804 retrieves and executes the instructions. The instructions received by main memory 806 may optionally be stored on storage device 810 either before or after execution by processor 804.” Examiner notes that the plurality of units listed are performed on a generic processor; after collecting a weeks' worth of data/fixed number of new samples, perform retraining/the method.)
and a storing unit (1620) for storing the cluster -specific refined models in the repository. (Higginson Paragraph 0037; "populated time-series models are stored in the data repository 200 for use in later forecasts." Higginson Paragraph 0125; “Bus 802 carries the data to main memory 806, from which processor 804 retrieves and executes the instructions. The instructions received by main memory 806 may optionally be stored on storage device 810 either before or after execution by processor 804.” Examiner notes that the plurality of units listed are performed on a generic processor.)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian, Hang, Sven, Abbas, and Higginson. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. Sven teaches identifying different stretches of trend in time series data, breaks them into a pre-crisis period and crisis period, and ignores the crisis period. Abbas teaches determining an ARMA model using AIC to find the best fit. Higginson teaches a tuning operation to determine the best time series model to use to best fit the historical time series data. One of ordinary skill would have motivation to combine Jian, Hang, Sven, Abbas, and Higginson to select the best time series model for the type of time series data for better accuracy. "These components of the time-series models 221 improve the accuracy of the models and allow the models 220 to be adapted to various types of time-series data collected from the monitored systems." (Higginson Paragraph 0038).
Regarding claim 19, Jian does not teach The system as claimed in claim 10, wherein the mapping unit (1610) further comprises: a collecting unit (16101) for identifying different contiguous stretches of the time-series within the time-series samples mapped to a cluster;
a dividing unit (16102) for dividing each stretch into contiguous non-overlapping window size segments;
and a discarding unit (16103) for discarding the last segment of the stretch and collecting the remaining segments from each stretch.
However, Sven does teach The system as claimed in claim 10, wherein the mapping unit (1610) further comprises: [a collecting unit] (16101) for identifying different contiguous stretches of the time-series within the time-series samples mapped to a cluster; (Sven Paragraph 1; "we will apply change point detection to a single stock value time series (SPYD) showing a large drop when the Covid-19 crisis started… In practice you would apply these methods to one or more time series of your sales volume over time or economic activity in your industry and region of interest… an abrupt deviation from the previous trend is typically observed.")
[a dividing unit] (16102) for dividing each stretch into contiguous non-overlapping window size segments; (Sven Paragraph 4; "The aim of our analysis is to identify distinct time periods: for example a pre-crisis and crisis period. It makes sense to set the number of lines to two during the crisis, and to three once a clear post-crisis period has emerged. Below we see the fitted lines of PLR with two lines. In this particular case the crisis period seems to consist of a significant drop followed by a relatively strong upswing.")
and [a discarding unit] (16103) for discarding the last segment of the stretch and collecting the remaining segments from each stretch. (Sven Paragraph 15; "The easiest and safest option is to completely ignore the crisis period during model training of future models.")
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian, Hang, and Sven. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. Sven teaches identifying different stretches of trend in time series data, breaks them into a pre-crisis period and crisis period, and ignores the crisis period. One of ordinary skill would have motivation to combine Jian, Hang, and Sven to remove segments within the time series graph that do not represent daily business decision making "The rationale would be that this period is not representative and therefore uninformative for daily business decision making after the crisis." (Sven Paragraph 15).
Jian does not teach a collecting unit
A dividing unit
A discarding unit
However, Higginson does teach a collecting unit
A dividing unit
A discarding unit (Higginson Paragraph 0125; “Bus 802 carries the data to main memory 806, from which processor 804 retrieves and executes the instructions. The instructions received by main memory 806 may optionally be stored on storage device 810 either before or after execution by processor 804.” Examiner notes that the plurality of units listed are performed on a generic processor.)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian, Hang, Sven, Abbas, and Higginson. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. Sven teaches identifying different stretches of trend in time series data, breaks them into a pre-crisis period and crisis period, and ignores the crisis period. Abbas teaches determining an ARMA model using AIC to find the best fit. Higginson teaches a tuning operation to determine the best time series model to use to best fit the historical time series data. One of ordinary skill would have motivation to combine Jian, Hang, Sven, Abbas, and Higginson to select the best time series model for the type of time series data for better accuracy. "These components of the time-series models 221 improve the accuracy of the models and allow the models 220 to be adapted to various types of time-series data collected from the monitored systems." (Higginson Paragraph 0038).
Claim(s) 2 and 11 are rejected under 35 U.S.C. 103 as being unpatentable over LV, Jian-ming et al; CN 110570613 A (hereinafter “Jian”) in view of Hang Hu et al; “Spatial Segmentation of Mass Spectrometry Imaging Data by Combining Multivariate Clustering and Univariate Thresholding” (hereinafter “Hang”) in further view of Sven Stringer; “Dealing with abrupt market changes in your analysis - a brief tutorial on time series change point detection” (hereinafter “Sven”) in further view Abbas Keshvani; “Using AIC to Test ARIMA Models” (hereinafter “Abbas”) in further view of Higginson; Antony Stephen et al; US 20210081492 A1 (hereinafter “Higginson”) in further view of Howard; Newton; US 20170258390 A1 (hereinafter “US 20170258390 A1”).
Regarding claim 2, Jian in view of Hang in further view of Sven in further view of Abbas in further view of Higginson does not teach The method as claimed in claim 1, wherein any continuous wavelet is used to generate time-frequency images for each time-series segment;
and wherein the default wavelet is set to Morlet wavelet.
However, Newton does teach The method as claimed in claim 1, wherein any continuous wavelet is used to generate time-frequency images for each time-series segment; (Newton Paragraph 0353; "The wavelet transform is a more sophisticated method for analyzing non-stationary signals, which does not have a tradeoff between time and frequency resolution. It was most appropriate to use Morlet wavelet, which is commonly used in EEG time-frequency decomposition. Because Morlet wavelets have a sinusoid shape weighted by a Gaussian kernel it can capture local oscillatory components in a time-series." Examiner notes wavelet transform/continuous wavelet is generating Morlet wavelets/time frequency images for each time series)
and wherein the default wavelet is set to Morlet wavelet. (Newton Paragraph 0320; "The Morlet wavelet can be defined as a “mother” wavelet from which a range of wavelets can be generated by scaling and translating," Examiner notes default/mother wavelet is Morlet wavelet)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian, Hang, Sven, Abbas, Higginson, and Newton. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. Sven teaches identifying different stretches of trend in time series data, breaks them into a pre-crisis period and crisis period, and ignores the crisis period. Abbas teaches determining an ARMA model using AIC to find the best fit. Higginson teaches a tuning operation to determine the best time series model to use to best fit the historical time series data. Newton teaches wavelet transformation that changes time series data into Morlet wavelets. One of ordinary skill would have motivation to combine Jian, Hang, Sven, Abbas, Higginson, and Newton to use wavelet transformation to obtain Morlet wavelets to account for the frequency and location of time series data. "A Morlet waveform was used because it accounts for frequency and location" (Newton Paragraph 0308).
Regarding claim 11, Jian in view of Hang in further view of Sven in further view of Abbas in further view of Higginson does not teach The system as claimed in claim 10, wherein any continuous wavelet is used to generate time-frequency images for each time-series segment;
and wherein the default wavelet is set to Morlet wavelet.
However, Newton does teach The system as claimed in claim 10, wherein any continuous wavelet is used to generate time-frequency images for each time-series segment; (Newton Paragraph 0353; "The wavelet transform is a more sophisticated method for analyzing non-stationary signals, which does not have a tradeoff between time and frequency resolution. It was most appropriate to use Morlet wavelet, which is commonly used in EEG time-frequency decomposition. Because Morlet wavelets have a sinusoid shape weighted by a Gaussian kernel it can capture local oscillatory components in a time-series." Examiner notes wavelet transform/continuous wavelet is generating Morlet wavelets/time frequency images for each time series)
and wherein the default wavelet is set to Morlet wavelet. (Newton Paragraph 0320; "The Morlet wavelet can be defined as a “mother” wavelet from which a range of wavelets can be generated by scaling and translating," Examiner notes default/mother wavelet is Morlet wavelet)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian, Hang, Sven, Abbas, Higginson, and Newton. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. Sven teaches identifying different stretches of trend in time series data, breaks them into a pre-crisis period and crisis period, and ignores the crisis period. Abbas teaches determining an ARMA model using AIC to find the best fit. Higginson teaches a tuning operation to determine the best time series model to use to best fit the historical time series data. Newton teaches wavelet transformation that changes time series data into Morlet wavelets. One of ordinary skill would have motivation to combine Jian, Hang, Sven, Abbas, Higginson, and Newton to use wavelet transformation to obtain Morlet wavelets to account for the frequency and location of time series data. "A Morlet waveform was used because it accounts for frequency and location" (Newton Paragraph 0308).
Claim(s) 3 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over LV, Jian-ming et al; CN 110570613 A (hereinafter “Jian”) in view of Hang Hu et al; “Spatial Segmentation of Mass Spectrometry Imaging Data by Combining Multivariate Clustering and Univariate Thresholding” (hereinafter “Hang”) in further view of Sven Stringer; “Dealing with abrupt market changes in your analysis - a brief tutorial on time series change point detection” (hereinafter “Sven”) in further view Abbas Keshvani; “Using AIC to Test ARIMA Models” (hereinafter “Abbas”) in further view of Higginson; Antony Stephen et al; US 20210081492 A1 (hereinafter “Higginson”) in further view of ALBRILE; Khuyen Le; “A quick overview of ResNet models” (hereinafter “Khuyen”).
Regarding claim 3, Jian teaches The method as claimed in claim 1, wherein the pre-trained deep convolutional neural network is applied to each time-frequency image to output a high dimensional numerical vector; (Jian Paragraph 0029; "the scaled wavelet time-frequency graph is input into a pre-trained convolutional neural network, and the output obtained is the event type corresponding to the vibration signal. The event type is numbered using a one-hot vector." Examiner notes that the image input/time-frequency images is applied to a pre-trained deep convolutional neural network/convolution neural network trained to output a high dimensional numerical vector/one-hot vector for each time frequency image.)
Jian does not teach and wherein the neural network is set to ResNet50.
However, Khuyen does teach and wherein the neural network is set to ResNet50. (Khuyen Section I Paragraph 2; "Microsoft proposed a deep convolutional neural network, namely ResNet, in 2015. This network is composed of multiple residual blocks regarding the input layers, and their operating principle is concerned with optimizing a residual function." Khuyen Section II Paragraph 1; "There are different versions of ResNet models which are available on the Keras platform, such as ResNet-50")
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian, Hang, Sven, Abbas, Higginson, and Khuyen. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. Sven teaches identifying different stretches of trend in time series data, breaks them into a pre-crisis period and crisis period, and ignores the crisis period. Abbas teaches determining an ARMA model using AIC to find the best fit. Higginson teaches a tuning operation to determine the best time series model to use to best fit the historical time series data. Khuyen teaches a deep convolutional neural network that is composed of multiple residual blocks called ResNet50. One of ordinary skill would have motivation to combine Jian, Hang, Sven, Abbas, Higginson, and Khuyen to use ResNet50 to overcome drawbacks of other convolutional neural networks and increase in accuracy from increasing layer depth. "we discovered some popular convolutional neural networks (CNNs) such as LeNet, AlexNet, VGG, NiN, GoogLeNet at which the model performance increases proportionally with the number of layers. One may ask if models can learn better with a higher number of layers? Generally, it is not always correct. Because the vanishing gradient phenomena in models, which have a large layer number, harms the convergence of these models from the beginning." (Khuyen Section I Paragraph 1) “This special architecture allows gaining accuracy from increasing layer depth” (Khuyen Section I Paragraph 2).
Regarding claim 12, Jian teaches The system as claimed in claim 10, wherein the pre-trained deep convolutional neural network is applied to each time-frequency image to output a high dimensional numerical vector; (Jian Paragraph 0029; "the scaled wavelet time-frequency graph is input into a pre-trained convolutional neural network, and the output obtained is the event type corresponding to the vibration signal. The event type is numbered using a one-hot vector." Examiner notes that the image input/time-frequency images is applied to a pre-trained deep convolutional neural network/convolution neural network trained to output a high dimensional numerical vector/one-hot vector for each time frequency image.)
Jian does not teach and wherein the neural network is set to ResNet50.
However, Khuyen does teach and wherein the neural network is set to ResNet50. (Khuyen Section I Paragraph 2; "Microsoft proposed a deep convolutional neural network, namely ResNet, in 2015. This network is composed of multiple residual blocks regarding the input layers, and their operating principle is concerned with optimizing a residual function." Khuyen Section II Paragraph 1; "There are different versions of ResNet models which are available on the Keras platform, such as ResNet-50")
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Jian, Hang, Sven, Abbas, Higginson, and Khuyen. Jian teaches using continuous wavelet transformation to obtain time frequency pattern and inputting the graph is input into a pre trained convolutional neural network to get a one-hot vector. Hang teaches using UMAP to transform data arrays into 2D feature space and using BIC to determine the best fit the clustering algorithm and number of clusters. Sven teaches identifying different stretches of trend in time series data, breaks them into a pre-crisis period and crisis period, and ignores the crisis period. Abbas teaches determining an ARMA model using AIC to find the best fit. Higginson teaches a tuning operation to determine the best time series model to use to best fit the historical time series data. Khuyen teaches a deep convolutional neural network that is composed of multiple residual blocks called ResNet50. One of ordinary skill would have motivation to combine Jian, Hang, Sven, Abbas, Higginson, and Khuyen to use ResNet50 to overcome drawbacks of other convolutional neural networks and increase in accuracy from increasing layer depth. "we discovered some popular convolutional neural networks (CNNs) such as LeNet, AlexNet, VGG, NiN, GoogLeNet at which the model performance increases proportionally with the number of layers. One may ask if models can learn better with a higher number of layers? Generally, it is not always correct. Because the vanishing gradient phenomena in models, which have a large layer number, harms the convergence of these models from the beginning." (Khuyen Section I Paragraph 1) “This special architecture allows gaining accuracy from increasing layer depth” (Khuyen Section I Paragraph 2).
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DANIEL DUC TRAN whose telephone number is (571)272-6870. The examiner can normally be reached Mon-Fri 8:00-5:00 EST.
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, Viker Lamardo can be reached at (571) 270-5871. 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.
/D.D.T./Examiner, Art Unit 2147
/VIKER A LAMARDO/Supervisory Patent Examiner, Art Unit 2147