DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-2, 4-5, 7-8, 18-20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor, or for pre-AIA the applicant regards as the invention.
Claims 1-2, 4-5, 7-8, 18-20 recite “ODEs”, however, these claims do not recite any definition for the acronym “ODEs”. Therefore, there is insufficient antecedent basis for this “ODEs”, and this renders the claim unclear and indefinite as it is not labeled in full term. For purposes of examination, Examiner will interpret this claim to recite “Ordinary Differential Equations (ODEs)”. Clarification is required.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention are directed to abstract ideas without significantly more.
Regarding Claim 1:
Step 1 - Is the claim directed to a process, a 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? - Yes, the claim recites the abstract ideas:
estimating a state of the system using an adaptive surrogate model of the system to produce an estimation of the state of the system, wherein the adaptive surrogate model includes a neural network employing a weighted combination of neural ODEs of dynamics of the system in latent space, such that weights of the weighted combination of neural ODEs represent the uncertainty: - This limitation recites the abstract idea of mathematical concepts, as when given the broadest reasonable interpretation in light of the specification, the ODEs are mathematical equations. Estimating the state of the system is done by using ODEs which are mathematical calculation of the state, therefore this limitation amounts to a mathematical concept.
and tuning the weights of the weighted combination of neural ODEs based on the controlling: - This limitation recites the abstract idea of mathematical concepts, as when given the broadest reasonable interpretation in light of the specification, the ODEs are mathematical equations. Tuning the weights of the neural ODEs based on the controlling is interpreted as mathematical changes to the values of the equations, therefore this limitation amounts to a mathematical concept.
Step 2A - Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application? - No, there are no additional elements that integrate the judicial exception into a practical application. The additional elements:
wherein the method uses a processor coupled with stored instructions implementing the method, wherein the instructions, when executed by the processor carry out steps of the method, comprising: - These generic computer components are recited at a high level of generality such that it amounts no more than mere instructions to apply the judicial exception using a computer (see MPEP 2106.05(f)).
controlling the system according to the task based on the estimation of the state of the system: - This limitation recites the use of the estimated state (the mathematical calculation explained at Prong 1, being an abstract idea) for the purpose of controlling a system for a desired task or outcome, therefore, given the broadest reasonable interpretation in light of the specification, this limitation merely indicates a field of use or technological environment such as controlling a robot, train, among other electro-mechanical systems. Therefore, it fails to integrate the judicial exception into a practical application (see MPEP 2106.05(h)).
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception? - No, there are no additional elements that amount to significantly more than the judicial exception. The additional elements:
wherein the method uses a processor coupled with stored instructions implementing the method, wherein the instructions, when executed by the processor carry out steps of the method, comprising: - These generic computer components are recited at a high level of generality such that it amounts no more than mere instructions to apply the judicial exception using a computer (see MPEP 2106.05(f)).
controlling the system according to the task based on the estimation of the state of the system: - This limitation recites the use of the estimated state (the mathematical calculation explained at Prong 1, being an abstract idea) for the purpose of controlling a system for a desired task or outcome, therefore, given the broadest reasonable interpretation in light of the specification, this limitation merely indicates a field of use or technological environment such as controlling a robot, train, among other electro-mechanical systems. Therefore, it fails to amount to significantly more than the judicial exception (see MPEP 2106.05(h)).
Regarding Claim 2:
Step 1 - Is the claim directed to a process, a 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? - Yes, the claim is dependent on claim 1 which included an abstract idea (see rejection for claim 1).
wherein the weighted combination is a polytopic weighted combination of neural ODEs of dynamics of the system in latent space: - This claim is directed to the abstract idea of mathematical concepts, as the polytopic weighted combination of neural ODEs uses a geometrical concept during its process (see MPEP 2106.04(a)(2)(I) subsection A).
Step 2A - Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application? - No, there are no additional elements that integrate the judicial exception into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception? - No, there are no additional elements that amount to significantly more than the judicial exception.
Regarding Claim 3:
Step 1 - Is the claim directed to a process, a 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? - Yes, the claim is dependent on claim 1 which included an abstract idea (see rejection for claim 1). Additionally, claim 3 recites the abstract ideas:
wherein the weights of the weighted combination are updated based on a difference between the estimation of the state of the system and measurements of the state of the system: - This limitation recites the abstract idea of mathematical concepts. Updating the weights of the weighted combination based on a difference between the estimation of the state of the system and measurements of the state of the system is interpreted as mathematical changes to the values, therefore this limitation amounts to a mathematical concept.
Step 2A - Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application? - No, there are no additional elements that integrate the judicial exception into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception? - No, there are no additional elements that amount to significantly more than the judicial exception.
Regarding Claim 4:
Step 1 - Is the claim directed to a process, a 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? - Yes, the claim is dependent on claim 1 which included an abstract idea (see rejection for claim 1).
Step 2A - Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application? - No, there are no additional elements that integrate the judicial exception into a practical application. The additional elements:
training the neural network for different values of parameters of the system, such that each of the neural ODEs is trained for a specific combination of values of the parameters of the system: - This limitation recites the training of neural network in high level of generality, as this limitation merely indicates a field of use or technological environment (see MPEP 2106.05(h)), therefore it fails to integrate the judicial exception into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception? - No, there are no additional elements that amount to significantly more than the judicial exception. The additional elements:
training the neural network for different values of parameters of the system, such that each of the neural ODEs is trained for a specific combination of values of the parameters of the system: - This limitation recites the training of neural network in high level of generality as this limitation merely indicates a field of use or technological environment (see MPEP 2106.05(h)), therefore it fails to amount to significantly more than the judicial exception.
Regarding Claim 5:
Step 1 - Is the claim directed to a process, a 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? - Yes, the claim is dependent on claim 1 which included an abstract idea (see rejection for claim 1).
Step 2A - Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application? - No, there are no additional elements that integrate the judicial exception into a practical application. The additional elements:
wherein the adaptive surrogate model includes an autoencoder architecture having an encoder trained to encode a previous state of the system into the latent space, the weighted combination of neural ODEs trained to propagate the encoding of the previous state in time, and a decoder trained to decode the estimated state of the system from the propagated encoding of the previous state: - This limitation does not integrate a judicial exception into a practical application as the neural network is recited at a high level of generality, therefore this amounts to mere instructions to implement an abstract idea 2106.05(f).
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception? - No, there are no additional elements that amount to significantly more than the judicial exception. The additional elements:
wherein the adaptive surrogate model includes an autoencoder architecture having an encoder trained to encode a previous state of the system into the latent space, the weighted combination of neural ODEs trained to propagate the encoding of the previous state in time, and a decoder trained to decode the estimated state of the system from the propagated encoding of the previous state: - This limitation does not amount to significantly more than the judicial exception as the neural network is recited at a high level of generality, therefore this amounts to mere instructions to implement an abstract idea 2106.05(f).
Regarding Claim 6:
Step 1 - Is the claim directed to a process, a 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? - Yes, the claim is dependent on claim 5, claim 5 is dependent on claim 1 which included an abstract idea (see rejection for claim 1).
Step 2A - Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application? - No, there are no additional elements that integrate the judicial exception into a practical application. The additional elements:
wherein the encoder includes a weighted combination of encoders, wherein the decoder includes a weighted combination of decoders: - This limitation does not integrate a judicial exception into a practical application as the neural network is recited at a high level of generality, therefore this amounts to mere instructions to implement an abstract idea 2106.05(f).
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception? - No, there are no additional elements that amount to significantly more than the judicial exception. The additional elements:
wherein the encoder includes a weighted combination of encoders, wherein the decoder includes a weighted combination of decoders: - This limitation does not amount to significantly more than the judicial exception as the neural network is recited at a high level of generality, therefore this amounts to mere instructions to implement an abstract idea 2106.05(f).
Regarding Claim 7:
Step 1 - Is the claim directed to a process, a 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? - Yes, the claim is dependent on claim 6 which included an abstract idea (see rejection for claim 6). Additionally, claim 7 recites the abstract ideas:
wherein weights in the weighted combination of encoders and weights in the weighted combination of decoders equal weights in the weighted combination of the neural ODEs, such that updates of the weights in the weighted combination of the neural ODEs automatically updates the weights in the weighted combination of encoders and the weights in the weighted combination of decoders: - This limitation recites the abstract idea of mathematical concepts. Updating the weights of the weighted combination based on a difference between the estimation of the state of the system and measurements of the state of the system is interpreted as mathematical changes to the values, therefore this limitation amounts to a mathematical concept.
Step 2A - Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application? - No, there are no additional elements that integrate the judicial exception into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception? - No, there are no additional elements that amount to significantly more than the judicial exception.
Regarding Claim 8:
Step 1 - Is the claim directed to a process, a 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? - Yes, the claim is dependent on claim 5, claim 5 is dependent on claim 1 which included an abstract idea (see rejection for claim 1). Additionally, claim 8 recites the abstract ideas:
wherein the weighted combination of neural ODEs propagates the encoding of the previous state in accordance with an input control command: - This limitation recites the abstract idea of mathematical concepts, as when given the broadest reasonable interpretation in light of the specification, the propagation is being executed by using nonlinear transformation algorithm which is a mathematical calculation.
Step 2A - Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application? - No, there are no additional elements that integrate the judicial exception into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception? - No, there are no additional elements that amount to significantly more than the judicial exception.
Regarding Claim 9:
Step 1 - Is the claim directed to a process, a 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? - Yes, the claim is dependent on claim 1 which included an abstract idea (see rejection for claim 1). Additionally, claim 9 recites the abstract ideas:
wherein state variables of the state of the system are augmented with weights of the weighted combination: - This claim is directed to a mathematical concept, as the process of augmenting variable with weights is a step of “determining” a variable or number using mathematical method (see MPEP 2106.04(a)(2) subsection C)
Step 2A - Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application? - No, there are no additional elements that integrate the judicial exception into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception? - No, there are no additional elements that amount to significantly more than the judicial exception.
Regarding Claim 10:
Step 1 - Is the claim directed to a process, a 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? - Yes, the claim is dependent on claim 9, which included an abstract idea (see rejection for claim 9). Additionally, claim 10 recites the abstract ideas:
wherein the weights of the weighted combination are updated using a probabilistic filter tracking the augmented state of the system: - This limitation recites the abstract idea of mathematical concepts, as when given the broadest reasonable interpretation in light of the specification, the probabilistic filter is being executed by using the combination of a Kalman filter algorithm which is a mathematical calculation.
Step 2A - Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application? - No, there are no additional elements that integrate the judicial exception into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception? - No, there are no additional elements that amount to significantly more than the judicial exception.
Regarding Claim 11:
Step 1 - Is the claim directed to a process, a 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? - Yes, the claim is dependent on claim 10, which included an abstract idea (see rejection for claim 10). Additionally, claim 11 recites the abstract ideas:
wherein the probabilistic filter includes one or a combination of a Kalman filter and a particle filter: - This claim is directed to the abstract idea of mathematical concepts, as the combination of a Kalman filter and a particle filter is a process of organizing information and manipulating information through mathematical correlation (see MPEP 2106.04(a)(2)(I) subsection A).
Step 2A - Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application? - No, there are no additional elements that integrate the judicial exception into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception? - No, there are no additional elements that amount to significantly more than the judicial exception.
Regarding Claim 12:
Step 1 - Is the claim directed to a process, a 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? - Yes, the claim is dependent on claim 1, which included an abstract idea (see rejection for claim 1). Additionally, claim 12 recites the abstract ideas:
wherein the weights of the weighted combination are updated using a probabilistic filter tracking the state of the system using one or a combination of a prediction model and a measurement model employing the neural network: - This limitation recites the abstract idea of mathematical concepts. Updating the weights of the weighted combination based on a difference between the estimation of the state of the system and measurements of the state of the system is interpreted as mathematical changes to the values, therefore this limitation amounts to a mathematical concept.
Step 2A - Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application? - No, there are no additional elements that integrate the judicial exception into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception? - No, there are no additional elements that amount to significantly more than the judicial exception.
Regarding Claim 13:
Step 1 - Is the claim directed to a process, a 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? - Yes, the claim is dependent on claim 12 which included an abstract idea (see rejection for claim 12).
Step 2A - Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application? - No, there are no additional elements that integrate the judicial exception into a practical application. The additional elements:
executing iteratively the probabilistic filter to produce a sequence of states of the system using the prediction model subject to process noise and the measurement model subject to measurement noise, wherein at least one of the prediction model and the measurement model includes the neural network: - This limitation is simply manipulating data on iterative manner which does not impose a meaningful limit on the claim, being insignificant as extra solution activity. This limitation does not integrate a judicial exception into a practical application as the neural network is recited at a high level of generality, therefore this amounts to mere instructions to implement an abstract idea 2106.05(f). This limitation is directed to manipulating data by produce the sequence of states of the system being an insignificant extra solution activity.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception? - No, there are no additional elements that amount to significantly more than the judicial exception. The additional elements:
executing iteratively the probabilistic filter to produce a sequence of states of the system using the prediction model subject to process noise and the measurement model subject to measurement noise, wherein at least one of the prediction model and the measurement model includes the neural network: - This limitation is directed to performing repetitive calculations. The courts (as per Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362) have recognized performing repetitive calculations as well-understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality) (see MPEP 2106.05(d) II).
Regarding Claim 14:
Step 1 - Is the claim directed to a process, a 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? - Yes, the claim is dependent on claim 13 which included an abstract idea (see rejection for claim 13). Additionally, claim 14 recites the abstract ideas:
wherein the probabilistic filter is an extended Kalman filter with a model linearization obtained by differentiation of the neural network: - This claim is directed to the abstract idea of mathematical concepts, as the extended Kalman filter with a model linearization is a process of organizing information and manipulating information through mathematical correlation (see MPEP 2106.04(a)(2)(I) subsection A).
Step 2A - Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application? - No, there are no additional elements that integrate the judicial exception into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception? - No, there are no additional elements that amount to significantly more than the judicial exception.
Regarding Claim 15:
Step 1 - Is the claim directed to a process, a 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? - Yes, the claim is dependent on claim 1 which included an abstract idea (see rejection for claim 1).
Step 2A - Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application? - No, there are no additional elements that integrate the judicial exception into a practical application. The additional elements:
wherein the system is a robot and a parameter with uncertainty is a value of mass of a robot arm: - This limitation does no more than generally link a judicial exception to a particular technological environment as this limitation recites the use of judicial exception to the technology of robot (see MPEP 2106.05(h)).
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception? - No, there are no additional elements that amount to significantly more than the judicial exception. The additional elements:
wherein the system is a robot and a parameter with uncertainty is a value of mass of a robot arm: - This limitation does no more than generally link a judicial exception to a particular technological environment as this limitation recites the use of judicial exception to the technology of robot (see MPEP 2106.05(h)).
Regarding Claim 16:
Step 1 - Is the claim directed to a process, a 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? - Yes, the claim is dependent on claim 1 which included an abstract idea (see rejection for claim 1).
Step 2A - Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application? - No, there are no additional elements that integrate the judicial exception into a practical application. The additional elements:
wherein the system is a train and a parameter with uncertainty is a value of friction between rails and wheels of the train: - This limitation does no more than generally link a judicial exception to a particular technological environment as this limitation recites the use of judicial exception to the technology of train (see MPEP 2106.05(h)).
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception? - No, there are no additional elements that amount to significantly more than the judicial exception. The additional elements:
wherein the system is a train and a parameter with uncertainty is a value of friction between rails and wheels of the train: - This limitation does no more than generally link a judicial exception to a particular technological environment as this limitation recites the use of judicial exception to the technology of train (see MPEP 2106.05(h)).
Regarding Claim 17:
Step 1 - Is the claim directed to a process, a 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? - Yes, the claim is dependent on claim 1 which included an abstract idea (see rejection for claim 1).
Step 2A - Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application? - No, there are no additional elements that integrate the judicial exception into a practical application. The additional elements:
wherein the system is an air-conditioning system and a parameter with uncertainty is a value of heat load or temperature of ambient air: - This limitation does no more than generally link a judicial exception to a particular technological environment as this limitation recites the use of judicial exception to the technology of air-conditioning (see MPEP 2106.05(h)).
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception? - No, there are no additional elements that amount to significantly more than the judicial exception. The additional elements:
wherein the system is an air-conditioning system and a parameter with uncertainty is a value of heat load or temperature of ambient air: - This limitation does no more than generally link a judicial exception to a particular technological environment as this limitation recites the use of judicial exception to the technology of air-conditioning (see MPEP 2106.05(h)).
Regarding independent Claim 18, this claim is directed to a system and is rejected on the same basis as independent claim 1 since they are analogous claims.
Regarding dependent Claim 19, this claim is directed to a system and is rejected on the same basis as dependent claim 2 since they are analogous claims.
Regarding independent Claim 20, this claim is directed to a non-transitory computer-readable storage medium and is rejected on the same basis as independent claim 1 since they are analogous claims.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-6, 8-12, 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Meeds et al (US-11030275-B2 - hereinafter Meeds) in view of Yakut et al (US-20230045548-A1 - hereinafter Yakut).
Referring to Claim 1, Meeds teaches a control method for controlling an electro-mechanical system:
estimating a state of the system using an adaptive surrogate model of the system to produce an estimation of the state of the system, wherein the adaptive surrogate model includes a neural network employing a weighted combination of neural ODEs of dynamics of the system in latent space, such that weights of the weighted combination of neural ODEs represent the uncertainty (see Meeds at Column 2 Lines 19-41: “According to one aspect disclosed herein, there is provided computer-implemented method as comprising, from each of multiple trials, obtaining a respective series of observations y(t) of a subject over time t; and using a variational auto encoder to model an ordinary differential equation, ODE. The variational auto encoder comprises an encoder for encoding the observations into a latent vector z and a decoder for decoding the latent vector, the encoder comprising at least a first neural network and the decoder comprising one or more second neural networks. The ODE as modelled by the decoder has a state x(t) representing one or more physical properties of the subject which result in the observations y, and the decoder models a rate of change of x with respect to time t as a function f of at least x and z: dx/dt=f(x, z). The method further comprises operating the variational auto encoder to learn the function f based on the obtained observations y by tuning weights of the first and second neural networks. The learning comprises performing variational inference over the latent vector z, whereby z has a plurality dimensions and in the encoder each dimension is constrained to comprising one or more samples of a predetermined type of probabilistic distribution parameterized by a respective one or more parameters”. Examiner interprets the variational auto encoder to be equivalent as the claimed “adaptive surrogate model of the system”; the ODE as modelled by the decoder has a state x(t) representing one or more physical properties, that state x(t) is interpreted to be equivalent as the claimed “estimation of the state of the system”; the variational auto encoder comprises an encoder and a decoder, each of them comprises at least one neural network, the encoder encodes the observation into latent vector and the decoder models a rate of change of x with respect to time t. These passages combined are interpreted to be equivalent as the claimed ”the adaptive surrogate model includes a neural network employing a weighted combination of neural ODEs of dynamics of the system in latent space”; each dimension of the latent vector z constrained to comprise a predetermined probabilistic distribution parameterized by a respective one or more parameters is interpreted to be equivalent as the claimed “such that weights of the weighted combination of neural ODEs represent the uncertainty”);
and tuning the weights of the weighted combination of neural ODEs based on the controlling (see Meeds at Column 2 Lines 19-41: “According to one aspect disclosed herein, there is provided computer-implemented method as comprising, from each of multiple trials, obtaining a respective series of observations y(t) of a subject over time t; and using a variational auto encoder to model an ordinary differential equation, ODE. The variational auto encoder comprises an encoder for encoding the observations into a latent vector z and a decoder for decoding the latent vector, the encoder comprising at least a first neural network and the decoder comprising one or more second neural networks. The ODE as modelled by the decoder has a state x(t) representing one or more physical properties of the subject which result in the observations y, and the decoder models a rate of change of x with respect to time t as a function f of at least x and z: dx/dt=f(x, z). The method further comprises operating the variational auto encoder to learn the function f based on the obtained observations y by tuning weights of the first and second neural networks. The learning comprises performing variational inference over the latent vector z, whereby z has a plurality dimensions and in the encoder each dimension is constrained to comprising one or more samples of a predetermined type of probabilistic distribution parameterized by a respective one or more parameters”. Examiner interprets the variational auto encoder tuning weights of the first and second neural networks to be equivalent as the claimed “tuning the weights of the weighted combination of neural ODEs”).
However, Meeds fails to teach:
controlling the system according to the task based on the estimation of the state of the system.
Yakut teaches, in analogous system,
controlling the system according to the task based on the estimation of the state of the system (see Yakut at Paragraph 36: “According to a second aspect of the present invention, there is provided an apparatus for predicting an industrial time dependent process. The apparatus comprises an input unit, a processing unit, and an output unit. The input unit is configured to receive currently measured data indicative of a current condition under which the industrial time dependent process currently takes place. At least one key performance indicator (KPI) is provided for quantifying the industrial time dependent process. The input unit is configured to receive at least one expected condition parameter indicative of a future condition under which the industrial time dependent process will take place within a prediction horizon. The processing unit is configured to apply a predictive data-driven model to an input dataset comprising the currently measured data and the at least one expected condition parameter to estimate a future value of the at least one KPI within the prediction horizon, wherein the predictive data-driven model is parametrized or trained according to a training dataset comprising historical data of the at least one condition parameter and the at least one KPI and synthetic samples of the at least one condition parameter and the at least one KPI. The output unit is configured to provide a prediction of the future value of at least one KPI within the prediction horizon, which is usable for monitoring and/or controlling the industrial time dependent process”. Examiner interprets the prediction of the future value of the KPI provided by the output unit and used to monitor and/or control the industrial time dependent process to be equivalent as the claimed “controlling the system according to the task based on the estimation of the state of the system”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Meeds with the above teachings of Yakut by developing the control policy that specifies an appropriate control action at every time on the system in order to achieve a desired outcome, as taught by Meeds, and controlling the system according to the task based on the estimation of the state of the system, as taught by Yakut. The modification would have been obvious because one of ordinary skill in the art would be motivated to provide a prediction of the future value to monitor the industrial time dependent process (as suggested by Yakut at Paragraph 36: “The output unit is configured to provide a prediction of the future value of at least one KPI within the prediction horizon, which is usable for monitoring and/or controlling the industrial time dependent process”).
Referring to Claim 2, Meeds - Yakut teaches the method of claim 1, Meeds further teaches:
wherein the weighted combination is a polytopic weighted combination of neural ODEs of dynamics of the system in latent space (see Meeds at Column 19 Lines 60-66: ”The m and s functions are deep neural networks whose first layer is a strided convolution over Y. The output of the first layer is a vector to which d is concatenated. This concatenated vector is then mapped into one dimension using a fully-connected network. The indicator random variables in d induce hyperplane separations of the input layer CNN, as in classical regression models”. Examiner interprets the mention of hyperplane separations induced by indicator variables to be equivalent as the claimed “polytopic weighted combination of neural ODEs”).
Referring to Claim 3, Meeds - Yakut teaches the method of claim 1, Meeds further teaches:
wherein the weights of the weighted combination are updated based on a difference between the estimation of the state of the system and measurements of the state of the system (see Meeds at Column 8 Lines 59-67 and Column 9 Lines 1-6: ”In the training phase, predicted versions ŷ of the observations y are generated from the predictions x generated by the decoder 404 using the predetermined function g, ŷ=g(x). The predicted observations ŷ and the actual observations y from the input experience data are fed into a comparison function 406 where they are compared. Based on this, the comparison function 406 tunes the weights ϕ of the neural network(s) 403 in the encoder 402 and the weights θ of the neural net(s) 405 in the decoder 404 y so as, over the various trials, to learn to minimize a measure of overall difference between the input observations y and the output of the decoder 404. Hence the VAE 401 learns to encode observations into a latent vector z and to decode a latent vector back again. Once trained, the model can be used to make predictions or inferences for existing or new data”. Examiner interprets tuning the weights of the neural networks in the encoder and the decoder to minimize the difference between the input observations and the output of the decoder to be equivalent as the claimed “the weights of the weighted combination are updated based on a difference between the estimation of the state of the system and measurements of the state of the system”).
Referring to Claim 4, Meeds - Yakut teaches the method of claim 1, Meeds further teaches:
training the neural network for different values of parameters of the system, such that each of the neural ODEs is trained for a specific combination of values of the parameters of the system (see Meeds at Column 8 Lines 59-67 and Column 9 Lines 1-6: ”In the training phase, predicted versions ŷ of the observations y are generated from the predictions x generated by the decoder 404 using the predetermined function g, ŷ=g(x). The predicted observations ŷ and the actual observations y from the input experience data are fed into a comparison function 406 where they are compared. Based on this, the comparison function 406 tunes the weights ϕ of the neural network(s) 403 in the encoder 402 and the weights θ of the neural net(s) 405 in the decoder 404 y so as, over the various trials, to learn to minimize a measure of overall difference between the input observations y and the output of the decoder 404. Hence the VAE 401 learns to encode observations into a latent vector z and to decode a latent vector back again. Once trained, the model can be used to make predictions or inferences for existing or new data”. Examiner interprets tuning over the various trials, the weights of the neural networks in the encoder and the decoder to minimize the difference between the input observations and the output of the decoder to be equivalent as the claimed “training the neural network for different values of parameters of the system, such that each of the neural ODEs is trained for a specific combination of values of the parameters of the system”).
Referring to Claim 5, Meeds - Yakut teaches the method of claim 1, Meeds further teaches:
wherein the adaptive surrogate model includes an autoencoder architecture having an encoder trained to encode a previous state of the system into the latent space, the weighted combination of neural ODEs trained to propagate the encoding of the previous state in time, and a decoder trained to decode the estimated state of the system from the propagated encoding of the previous state (see Meeds at Column 8 Lines 59-67 and Column 9 Lines 1-6: “Hence more generally, according to one aspect disclosed herein there is provided computer-implemented method comprising: from each of multiple trials, obtaining a respective series of observations y(t) of a subject over time t; using a variational auto encoder to model an ordinary differential equation, ODE, wherein the variational auto encoder comprises an encoder for encoding the observations into a latent vector z and a decoder for decoding the latent vector, the encoder comprising at least a first neural network and the decoder comprising one or more second neural networks, wherein the ODE as modelled by the decoder has a state x(t) representing one or more physical properties of the subject which result in the observations y, and the decoder models a rate of change of x with respect to time t as a function f of at least x and z: dx/dt=f(x, z); and operating the variational auto encoder to learn the function f based on the obtained observations y by tuning weights of the first and second neural networks, the learning comprising performing variational inference over the latent vector z, whereby z has a plurality dimensions and in the encoder each dimension is constrained to comprising one or more samples of a predetermined type of probabilistic distribution parameterized by a respective one or more parameters”. The use of the variational auto encoder (VAE interpreted as the surrogate model) to model an ordinary differential equation (ODE), the variational auto encoder having an encoder for encoding the observations into a latent vector and a decoder for decoding the latent vector, the encoder having at least a first neural network and the decoder having one or more second neural networks, the combination of these statements is interpreted to be equivalent as the claimed “the adaptive surrogate model includes an autoencoder architecture having an encoder trained to encode a previous state of the system into the latent space, the weighted combination of neural ODEs trained to propagate the encoding of the previous state in time, and a decoder trained to decode the estimated state of the system from the propagated encoding of the previous state”).
Referring to Claim 6, Meeds - Yakut teaches the method of claim 5, Meeds further teaches:
wherein the encoder includes a weighted combination of encoders, wherein the decoder includes a weighted combination of decoders (see Meeds at Column 8 Lines 59-67 and Column 9 Lines 1-6: ”In the training phase, predicted versions ŷ of the observations y are generated from the predictions x generated by the decoder 404 using the predetermined function g, ŷ=g(x). The predicted observations ŷ and the actual observations y from the input experience data are fed into a comparison function 406 where they are compared. Based on this, the comparison function 406 tunes the weights ϕ of the neural network(s) 403 in the encoder 402 and the weights θ of the neural net(s) 405 in the decoder 404 y so as, over the various trials, to learn to minimize a measure of overall difference between the input observations y and the output of the decoder 404. Hence the VAE 401 learns to encode observations into a latent vector z and to decode a latent vector back again. Once trained, the model can be used to make predictions or inferences for existing or new data”. Examiner interprets the case where the number of neural networks in the encoder is greater or equal to two to be equivalent as the claimed “the encoder includes a weighted combination of encoders” and the case where the number of neural networks in the decoder is greater or equal to two to be equivalent as the claimed “the decoder includes a weighted combination of decoders”).
Referring to Claim 8, Meeds - Yakut teaches the method of claim 5.
However, Meeds fails to teach:
wherein the weighted combination of neural ODEs propagates the encoding of the previous state in accordance with an input control command.
Yakut teaches, in analogous system,
wherein the weighted combination of neural ODEs propagates the encoding of the previous state in accordance with an input control command (see Yakut at Paragraph 36: “According to a second aspect of the present invention, there is provided an apparatus for predicting an industrial time dependent process. The apparatus comprises an input unit, a processing unit, and an output unit. The input unit is configured to receive currently measured data indicative of a current condition under which the industrial time dependent process currently takes place. At least one key performance indicator (KPI) is provided for quantifying the industrial time dependent process. The input unit is configured to receive at least one expected condition parameter indicative of a future condition under which the industrial time dependent process will take place within a prediction horizon. The processing unit is configured to apply a predictive data-driven model to an input dataset comprising the currently measured data and the at least one expected condition parameter to estimate a future value of the at least one KPI within the prediction horizon, wherein the predictive data-driven model is parametrized or trained according to a training dataset comprising historical data of the at least one condition parameter and the at least one KPI and synthetic samples of the at least one condition parameter and the at least one KPI. The output unit is configured to provide a prediction of the future value of at least one KPI within the prediction horizon, which is usable for monitoring and/or controlling the industrial time dependent process”. Examiner interprets the fact that at the processing time the data-driven model estimated the future value of the KPI within the prediction horizon and the future value being provided to the output unit for prediction to monitor and/or control the industrial time dependent to be equivalent as the claimed “the weighted combination of neural ODEs propagates the encoding of the previous state in accordance with an input control command”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Meeds with the above teachings of Yakut by developing the control policy that specifies an appropriate control action at every time on the system in order to achieve a desired outcome, as taught by Meeds, and propagate the encoding of the previous state in accordance with an input control command, as taught by Yakut. The modification would have been obvious because one of ordinary skill in the art would be motivated to provide a prediction of the future value to monitor the industrial time dependent process (as suggested by Yakut at Paragraph 36: “The output unit is configured to provide a prediction of the future value of at least one KPI within the prediction horizon, which is usable for monitoring and/or controlling the industrial time dependent process”).
Referring to Claim 9, Meeds - Yakut teaches the method of claim 1.
However, Meeds fails to teach:
wherein state variables of the state of the system are augmented with weights of the weighted combination.
Yakut teaches, in analogous system,
wherein state variables of the state of the system are augmented with weights of the weighted combination (see Yakut at Paragraph 36: “According to a second aspect of the present invention, there is provided an apparatus for predicting an industrial time dependent process. The apparatus comprises an input unit, a processing unit, and an output unit. The input unit is configured to receive currently measured data indicative of a current condition under which the industrial time dependent process currently takes place. At least one key performance indicator (KPI) is provided for quantifying the industrial time dependent process. The input unit is configured to receive at least one expected condition parameter indicative of a future condition under which the industrial time dependent process will take place within a prediction horizon. The processing unit is configured to apply a predictive data-driven model to an input dataset comprising the currently measured data and the at least one expected condition parameter to estimate a future value of the at least one KPI within the prediction horizon, wherein the predictive data-driven model is parametrized or trained according to a training dataset comprising historical data of the at least one condition parameter and the at least one KPI and synthetic samples of the at least one condition parameter and the at least one KPI. The output unit is configured to provide a prediction of the future value of at least one KPI within the prediction horizon, which is usable for monitoring and/or controlling the industrial time dependent process”. Examiner interprets the processing unit applying the predictive data-driven model to an input dataset comprising the currently measured data and the at least one expected condition parameter to estimate a future value of the at least one KPI within the prediction horizon”. Examiner interprets the currently measured data (interpreted as the state variable of the state) added to the expected condition parameter (interpreted as the weight) in the processing unit to be equivalent as the claimed “state variables of the state of the system are augmented with weights of the weighted combination”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Meeds with the above teachings of Yakut by developing the control policy that specifies an appropriate control action at every time on the system in order to achieve a desired outcome, as taught by Meeds, and augmenting state variables of the state of the system with weights of the weighted combination, as taught by Yakut. The modification would have been obvious because one of ordinary skill in the art would be motivated to estimate the future value of the KPI within the prediction horizon (as suggested by Yakut at Paragraph 36: “The processing unit is configured to apply a predictive data-driven model to an input dataset comprising the currently measured data and the at least one expected condition parameter to estimate a future value of the at least one KPI within the prediction horizon, wherein the predictive data-driven model is parametrized or trained according to a training dataset comprising historical data of the at least one condition parameter and the at least one KPI and synthetic samples of the at least one condition parameter and the at least one KPI”).
Referring to Claim 10, Meeds - Yakut teaches the method of claim 5, Meeds further teaches:
wherein the weights of the weighted combination are updated using a probabilistic filter tracking the augmented state of the system (see Meeds at Column 8 Lines 59-67 and Column 9 Lines 1-6: “Hence more generally, according to one aspect disclosed herein there is provided computer-implemented method comprising: from each of multiple trials, obtaining a respective series of observations y(t) of a subject over time t; using a variational auto encoder to model an ordinary differential equation, ODE, wherein the variational auto encoder comprises an encoder for encoding the observations into a latent vector z and a decoder for decoding the latent vector, the encoder comprising at least a first neural network and the decoder comprising one or more second neural networks, wherein the ODE as modelled by the decoder has a state x(t) representing one or more physical properties of the subject which result in the observations y, and the decoder models a rate of change of x with respect to time t as a function f of at least x and z: dx/dt=f(x, z); and operating the variational auto encoder to learn the function f based on the obtained observations y by tuning weights of the first and second neural networks, the learning comprising performing variational inference over the latent vector z, whereby z has a plurality dimensions and in the encoder each dimension is constrained to comprising one or more samples of a predetermined type of probabilistic distribution parameterized by a respective one or more parameters”. Examiner interprets each dimension of the latent vector constrained to have the predetermined type of probabilistic distribution parameterized by the respective parameters to be equivalent as the claimed “weights of the weighted combination are updated using a probabilistic filter tracking the augmented state”).
Referring to Claim 11, Meeds - Yakut teaches the method of claim 10, Meeds further teaches:
wherein the probabilistic filter includes one or a combination of a Kalman filter and a particle filter (see Meeds at Column 24 Lines 30-34: “ Latent-variable time series models are among the most heavily used tools from statistics and machine learning. Stochastic variational inference may be applied to particular classes of dynamical models, mostly in the Kalman filter family” Examiner interprets the variational inference being applied to particular classes of dynamical models, mostly in the Kalman filter family to be equivalent as the claimed “the probabilistic filter includes one or a combination of a Kalman filter and a particle filter”).
Referring to Claim 12, Meeds - Yakut teaches the method of claim 1, Meeds further teaches:
wherein the weights of the weighted combination are updated using a probabilistic filter tracking the state of the system using one or a combination of a prediction model and a measurement model employing the neural network (see Meeds at Column 8 Lines 59-67 and Column 9 Lines 1-6: “Hence more generally, according to one aspect disclosed herein there is provided computer-implemented method comprising: from each of multiple trials, obtaining a respective series of observations y(t) of a subject over time t; using a variational auto encoder to model an ordinary differential equation, ODE, wherein the variational auto encoder comprises an encoder for encoding the observations into a latent vector z and a decoder for decoding the latent vector, the encoder comprising at least a first neural network and the decoder comprising one or more second neural networks, wherein the ODE as modelled by the decoder has a state x(t) representing one or more physical properties of the subject which result in the observations y, and the decoder models a rate of change of x with respect to time t as a function f of at least x and z: dx/dt=f(x, z); and operating the variational auto encoder to learn the function f based on the obtained observations y by tuning weights of the first and second neural networks, the learning comprising performing variational inference over the latent vector z, whereby z has a plurality dimensions and in the encoder each dimension is constrained to comprising one or more samples of a predetermined type of probabilistic distribution parameterized by a respective one or more parameters”. Examiner interprets the fact that the variational auto encoder learned to tune the weights of the first and second neural networks and during the learning each dimension of the latent vector in the encoder (encoder interprets as measurement model) being constrained to have a predetermined type of probabilistic distribution parameterized by the respective parameters to be equivalent as the claimed “weights of the weighted combination are updated using a probabilistic filter tracking the state of the system using one or a combination of a prediction model and a measurement model employing the neural network”).
Referring to independent Claim 18 and Claim 20, they are rejected on the same basis as independent claim 1 since they are analogous claims of Claim 1.
Referring to dependent Claim 19, this claim is rejected on the same basis as dependent claim 2 since they are analogous claims.
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Meeds et al (US-11030275-B2 - hereinafter Meeds) in view of Yakut et al (US-20230045548-A1 - hereinafter Yakut) in further view of Verhulst et al (EP-3981173-B1 – hereinafter Verhulst).
Referring to Claim 7, Meeds - Yakut teaches the method of claim 6.
However, Meeds – Yakut fails to teach:
wherein weights in the weighted combination of encoders and weights in the weighted combination of decoders equal weights in the weighted combination of the neural ODEs, such that updates of the weights in the weighted combination of the neural ODEs automatically updates the weights in the weighted combination of encoders and the weights in the weighted.
Verhulst teaches, in analogous system,
wherein weights in the weighted combination of encoders and weights in the weighted combination of decoders equal weights in the weighted combination of the neural ODEs, such that updates of the weights in the weighted combination of the neural ODEs automatically updates the weights in the weighted combination of encoders and the weights in the weighted combination of decoders (see Verhulst at Paragraph 138: “After the training phase, the model was extended to work for an N-channel input sequence by applying the same calculated weights across this N-channel input array such that the trained IHC model module can calculate IHC potentials across all N channels corresponding to tonotopic locations along the BM. The architecture that was found to best approximate the IHC module was an auto-encoder with 6 convolution layers (3 for the encoder and 3 for the decoder) and 128 filters in each layer with a filter length of 64”. Examiner interprets the application of the same calculated weights to the model and the architecture being an auto-encoder with six convolution layers (three for the encoder and three for the decoder) to be equivalent as the claimed “weights in the weighted combination of encoders and weights in the weighted combination of decoders equal weights in the weighted combination of the neural ODEs”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Meeds and Yakut with the above teachings of Verhulst by specifying the appropriate control action at every time on the system in order to achieve the desired outcome, as taught by Meeds and Yakut, and having weights in the encoders and weights in the decoders equal weights in the weighted combination of the neural ODEs, as taught by Verhulst. The modification would have been obvious because one of ordinary skill in the art would be motivated to extend the model to work for an N-channel input sequence (as suggested by Verhulst at Paragraph 138: “After the training phase, the model was extended to work for an N-channel input sequence by applying the same calculated weights across this N-channel input array such that the trained IHC model module can calculate IHC potentials across all N channels corresponding to tonotopic locations along the BM. The architecture that was found to best approximate the IHC module was an auto-encoder with 6 convolution layers (3 for the encoder and 3 for the decoder) and 128 filters in each layer with a filter length of 64”).
Claims 13-14 are rejected under 35 U.S.C. 103 as being unpatentable over Meeds et al (US-11030275-B2 - hereinafter Meeds) in view of Yakut et al (US-20230045548-A1 - hereinafter Yakut) in further view of Xue et al (CN-110659722-B – hereinafter Xue).
Referring to Claim 13, Meeds – Yakut teaches the method of claim 12.
However, Meeds – Yakut fails to teach:
further comprising: executing iteratively the probabilistic filter to produce a sequence of states of the system using the prediction model subject to process noise and the measurement model subject to measurement noise, wherein at least one of the prediction model and the measurement model includes the neural network;
Xue teaches, in analogous system,
further comprising: executing iteratively the probabilistic filter to produce a sequence of states of the system using the prediction model subject to process noise and the measurement model subject to measurement noise, wherein at least one of the prediction model and the measurement model includes the neural network (see Xue at Paragraph 12: “Step 1.1: To address the nonlinearity and sensitivity of battery parameters, an extended Kalman filter algorithm is used to denoise the battery parameters. Taylor's algorithm is used to linearize the discharge voltage, discharge current, number of charge-discharge cycles, and capacity, respectively. The corresponding state equations and observation equations are expanded, and higher-order terms of the second order and above are removed to make the original data approximate a linear system. Then, based on the iterative and recursive operations of the standard Kalman filter algorithm, the state variables are estimated and updated to achieve noise reduction. Finally, the min-max normalization method is used for normalization”. Examiner interprets the state variables being estimated and updated based on the iterative operations of the standard Kalman filter (Kalman filter interprets as probabilistic filter) algorithm to achieve noise reduction to be equivalent as the claimed “executing iteratively the probabilistic filter to produce a sequence of states of the system using the prediction model subject to process noise and the measurement model subject to measurement noise”; the corresponding state equations and observation equations are interpreted to be equivalent as the claimed “prediction model” and “measurement model” respectively).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Meeds and Yakut with the above teachings of Xue by specifying the appropriate control action at every time on the system in order to achieve the desired outcome by using an adaptive model with weights equal to the weights of encoders and decoders, as taught by Meeds and Yakut, and executing iteratively the probabilistic filter to produce a sequence of states of the system, as taught by Xue. The modification would have been obvious because one of ordinary skill in the art would be motivated to estimate and update the state variables in order to achieve noise reduction (as suggested by Xue at Paragraph 12: “Step 1.1: To address the nonlinearity and sensitivity of battery parameters, an extended Kalman filter algorithm is used to denoise the battery parameters. Taylor's algorithm is used to linearize the discharge voltage, discharge current, number of charge-discharge cycles, and capacity, respectively. The corresponding state equations and observation equations are expanded, and higher-order terms of the second order and above are removed to make the original data approximate a linear system. Then, based on the iterative and recursive operations of the standard Kalman filter algorithm, the state variables are estimated and updated to achieve noise reduction. Finally, the min-max normalization method is used for normalization”).
Referring to Claim 14, Meeds – Yakut teaches the method of claim 13.
However, Meeds – Yakut fails to teach:
wherein the probabilistic filter is an extended Kalman filter with a model linearization obtained by differentiation of the neural network.
Xue teaches, in analogous system,
wherein the probabilistic filter is an extended Kalman filter with a model linearization obtained by differentiation of the neural network (see Xue at Paragraph 12: “Step 1.1: To address the nonlinearity and sensitivity of battery parameters, an extended Kalman filter algorithm is used to denoise the battery parameters. Taylor's algorithm is used to linearize the discharge voltage, discharge current, number of charge-discharge cycles, and capacity, respectively. The corresponding state equations and observation equations are expanded, and higher-order terms of the second order and above are removed to make the original data approximate a linear system. Then, based on the iterative and recursive operations of the standard Kalman filter algorithm, the state variables are estimated and updated to achieve noise reduction. Finally, the min-max normalization method is used for normalization”. Examiner interprets the extended Kalman filter algorithm and the Taylor's algorithm used to linearize to be equivalent as the claimed “the probabilistic filter is an extended Kalman filter” and “model linearization” respectively).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Meeds and Yakut with the above teachings of Xue by specifying the appropriate control action at every time on the system in order to achieve the desired outcome by using an adaptive model with weights equal to the weights of encoders and decoders, as taught by Meeds and Yakut, and executing iteratively the extended Kalman filter to produce a sequence of states of the system, as taught by Xue. The modification would have been obvious because one of ordinary skill in the art would be motivated to estimate and update the state variables in order to achieve noise reduction (as suggested by Xue at Paragraph 12: “Step 1.1: To address the nonlinearity and sensitivity of battery parameters, an extended Kalman filter algorithm is used to denoise the battery parameters. Taylor's algorithm is used to linearize the discharge voltage, discharge current, number of charge-discharge cycles, and capacity, respectively. The corresponding state equations and observation equations are expanded, and higher-order terms of the second order and above are removed to make the original data approximate a linear system. Then, based on the iterative and recursive operations of the standard Kalman filter algorithm, the state variables are estimated and updated to achieve noise reduction. Finally, the min-max normalization method is used for normalization”).
Claim 15 is rejected under 35 U.S.C. 103 as being unpatentable over Meeds et al (US-11030275-B2 - hereinafter Meeds) in view of Yakut et al (US-20230045548-A1 - hereinafter Yakut) and in further view of Kang et al (CN- 111618864-B – hereinafter Kang).
Referring to Claim 15, Meeds – Yakut teaches the method of claim 1.
However, Meeds – Yakut fails to teach:
wherein the system is a robot and a parameter with uncertainty is a value of mass of a robot arm;
Kang teaches, in analogous system,
wherein the system is a robot and a parameter with uncertainty is a value of mass of a robot arm (see Kang at Page 14: “In this embodiment, based on the updated action network, the updated weight value is obtained, combined with the tracking error at time tk, the actual control rate of the robotic arm at tk-tk+1 is calculated through the action network, and it acts on the robotic arm. . As in step A504 above.
In step S60, let k=k+1, and execute step S10-step S50 cyclically until the robot arm reaches the set target position”. Examiner interprets the updated weight value being used in calculation of the actual control rate of the robotic arm and the rate acts on the robotic arm as well as the process being cyclical to be equivalent as the claimed “the system is a robot and a parameter with uncertainty is a value of mass of a robot arm”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Meeds and Yakut, with the above teachings of Kang by specifying the appropriate control action at every time on the system in order to achieve the desired outcome by using Kalman filter repeatedly to produce sequence of state in order to reduce noise, as taught by Meeds and Yakut, and the system being a robot and a parameter with uncertainty is a value of mass of a robot arm, as taught by Kang. The modification would have been obvious because one of ordinary skill in the art would be motivated to execute steps iteratively until the robot arm reaches the set target position (as suggested by Kang: “In this embodiment, based on the updated action network, the updated weight value is obtained, combined with the tracking error at time tk, the actual control rate of the robotic arm at tk-tk+1 is calculated through the action network, and it acts on the robotic arm. . As in step A504 above. In step S60, let k=k+1, and execute step S10-step S50 cyclically until the robot arm reaches the set target position”).
Claim 16 is rejected under 35 U.S.C. 103 as being unpatentable over Meeds et al (US-11030275-B2 - hereinafter Meeds) in view of Yakut et al (US-20230045548-A1 - hereinafter Yakut) in further view of Danielson et al (US-10093331-B2– hereinafter Danielson).
Referring to Claim 16, Meeds – Yakut teaches the method of claim 1.
However, Meeds – Yakut fails to teach:
wherein the system is a train and a parameter with uncertainty is a value of friction between rails and wheels of the train.
Danielson teaches, in analogous system,
wherein the system is a train and a parameter with uncertainty is a value of friction between rails and wheels of the train (see Danielson at Column 1 Lines 41-67: “However, the generation of those velocity profiles are difficult and/or time and resource consuming. In addition, the selection of the optimal velocity profile is prone to errors due to uncertainty of some of the parameters of the movement of the train, such as the mass of the train, track friction along with other errors. In practice, many reference profiles are generated before the train operation and are based on different assumptions of train and environmental parameters. For example, a particular reference profile can be used in each operation of stopping which is selected based on evaluating the current conditions. Nonetheless, there is not guarantee that one velocity profile satisfies exactly the current conditions available, and/or that the current conditions are exactly known, and/or that the current conditions do not change during the execution of the stopping”. Examiner interprets the uncertainty of some of the parameters of the movement of the train, being the track friction to be equivalent as the claimed “the system is a train and a parameter with uncertainty is a value of friction between rails and wheels of the train”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Meeds and Yakut, with the above teachings of Danielson by specifying the appropriate control action at every time on the train in order to achieve the desired outcome by using Kalman filter repeatedly to produce sequence of state in order to reduce noise, as taught by Meeds and Yakut, and the system being a train and a parameter with uncertainty is a value of friction between rails and wheels of the train, as taught by Danielson. The modification would have been obvious because one of ordinary skill in the art would be motivated to evaluate the current position (as suggested by Danielson: However, the generation of those velocity profiles are difficult and/or time and resource consuming. In addition, the selection of the optimal velocity profile is prone to errors due to uncertainty of some of the parameters of the movement of the train, such as the mass of the train, track friction along with other errors. In practice, many reference profiles are generated before the train operation and are based on different assumptions of train and environmental parameters. For example, a particular reference profile can be used in each operation of stopping which is selected based on evaluating the current conditions. Nonetheless, there is not guarantee that one velocity profile satisfies exactly the current conditions available, and/or that the current conditions are exactly known, and/or that the current conditions do not change during the execution of the stopping”).
Claim 17 is rejected under 35 U.S.C. 103 as being unpatentable over Meeds et al (US-11030275-B2 - hereinafter Meeds) in view of Yakut et al (US-20230045548-A1 - hereinafter Yakut) and in further view of ElBsat et al (US- 10558180-B2– hereinafter ElBsat).
Referring to Claim 17, Meeds – Yakut teaches the method of claim 1.
However, Meeds – Yakut fails to teach:
wherein the system is an air-conditioning system and a parameter with uncertainty is a value of heat load or temperature of ambient air;
ElBsat teaches, in analogous system,
wherein the system is an air-conditioning system and a parameter with uncertainty is a value of heat load or temperature of ambient air (see ElBsat at Column 1 Lines 56-67: “Many buildings are equipped with a variety of energy-consuming equipment and devices. For example, a building may be equipped with heating, ventilation, and air conditioning (HVAC) equipment that consume energy to regulate the temperature, humidity, and/or air quality in the building. Other exemplary types of energy-consuming building equipment include lighting fixtures, security equipment, data networking infrastructure, and other such equipment”. Examiner interprets the building being equipped with air conditioning (HVAC) to be equivalent as the claimed “the system is an air-conditioning system”) and further (see ElBsat at Column 1 Lines 56-67 and Column 2 Lines 1-4: “One implementation of the present disclosure is a method for determining the uncertainty in parameters of a building energy use model. The method includes receiving an energy use model for a building site. The energy use model includes one or more predictor variables and one or more model parameters. The method further includes calculating a gradient of an output of the energy use model with respect to the model parameters, determining a covariance matrix using the calculated gradient, and using the covariance matrix to identify an uncertainty of the model parameters. The uncertainty of the model parameters may correspond to entries in the covariance matrix.
In some embodiments, at least one of the model parameters is a balance point parameter defining a range of outside air temperatures within which the output of the energy use model depends on the outside air temperature”; where Examiner interprets the uncertainty of the model parameters being a range of air temperature to be equivalent as the claimed “parameter with uncertainty is a value of heat load or temperature of ambient air”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Meeds and Yakut, with the above teachings of ElBsat by specifying the appropriate control action at every time on the air-conditioning in order to achieve the desired outcome by using Kalman filter repeatedly to produce sequence of state in order to reduce noise, as taught by Meeds and Yakut, and the system is an air-conditioning system and a parameter with uncertainty is a value of heat load or temperature of ambient air, as taught by ElBsat. The modification would have been obvious because one of ordinary skill in the art would be motivated to calculate the gradient of the output of the energy use model (as suggested by ElBsat: “One implementation of the present disclosure is a method for determining the uncertainty in parameters of a building energy use model. The method includes receiving an energy use model for a building site. The energy use model includes one or more predictor variables and one or more model parameters. The method further includes calculating a gradient of an output of the energy use model with respect to the model parameters, determining a covariance matrix using the calculated gradient, and using the covariance matrix to identify an uncertainty of the model parameters. The uncertainty of the model parameters may correspond to entries in the covariance matrix. In some embodiments, at least one of the model parameters is a balance point parameter defining a range of outside air temperatures within which the output of the energy use model depends on the outside air temperature”).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AWADAGBE G HOUNTON whose telephone number is (571)270-0670. The examiner can normally be reached Monday-Friday 8am-5pm.
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, David Yi can be reached at (571) 270-7519. 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.
/AWADAGBE G HOUNTON/ Examiner, Art Unit 2126
/DAVID YI/ Supervisory Patent Examiner, Art Unit 2126
Prosecution Insights