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 Status
Claims 1-20 are currently pending and under exam herein.
Claims 1-20 are rejected.
Priority
The instant application does not claim benefit to a provisional application. At this point in the examination, the effective filling date of the claims is 06/13/2022.
Information Disclosure Statement
The Information Disclosure Statements filed 13 June 2022 and 14 December 2023 are in compliance with the provisions of 37 CFR 1.97 and have therefore been considered.
Drawings
The drawings filed on 06/13/2022 are accepted.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claims recite: (a) mathematical concepts, (e.g., mathematical relationships, formulas or equations, mathematical calculations); and (b) mental processes, i.e., concepts performed in the human mind, (e.g., observation, evaluation, judgment, opinion).
Subject matter eligibility evaluation in accordance with MPEP 2106:
Eligibility Step 1: Claims 1-11 are directed to a computing system (machine). Claims 12-19 are directed to a method (process) for use with a computing system. Claim 20 is directed to a computing system (machine).
[Step 1: YES]
Eligibility Step 2A: First it is determined in Prong One whether a claim recites a judicial exception, and if so, then it is determined in Prong Two whether the recited judicial exception is integrated into a practical application of that exception.
Eligibility Step 2A Prong One: In determining whether a claim is directed to a judicial exception, examination is performed that analyzes whether the claim recites a judicial exception, i.e., whether a law of nature, natural phenomenon, or abstract idea is set forth or described in the claim.
Independent claims 1 and 12 recite the following steps which fall within the mental processes and/or mathematical concepts groupings of abstract ideas:
generate a training data set at least in part by: generating a plurality of training molecular structures (i.e., mathematical concepts)
computing a respective plurality of training Hamiltonians of the training molecular structures (i.e., mathematical concepts: calculating)
based at least in part on the plurality of training Hamiltonians, computing a plurality of training energy terms associated with the training molecular structures, wherein computing the plurality of training energy terms includes: for each of the training Hamiltonians, computing respective estimated values of a kinetic energy term, a nuclear potential energy term, an electron repulsion energy term, and an exchange energy term using Hartree-Fock (HF) estimation (i.e., mathematical concepts: calculating)
for each training Hamiltonian included in a first proper subset of the plurality of training Hamiltonians, computing a respective dynamical correlation energy term using coupled cluster estimation (i.e., mathematical concepts: calculation of energy term)
and for each training Hamiltonian included in a second proper subset of the first proper subset: generating a truncated Hamiltonian for the training molecular structure (i.e., mathematical concepts: truncation)
and based at least in part on the truncated Hamiltonian, computing a respective static correlation energy term using complete active space (CAS) estimation (i.e., mathematical concepts: calculating)
and train an electron energy estimation machine learning model using the plurality of training molecular structures and the plurality of training energy terms included in the training data set (i.e., mathematical concepts)
Dependent claims 2-11, 13-19 further recite the following steps which fall within the mental processes and/or mathematical concepts groupings of abstract ideas, as noted below.
Dependent claims 3 and 14 further recite:
generate a respective plurality of training molecular orbital feature matrices based at least in part on the plurality of training Hamiltonians, wherein each of the training molecular orbital feature matrices includes: a plurality of training vertex inputs including a plurality of on-diagonal elements of a training Fock matrix and a plurality of on-diagonal elements of a training composite two-electron integral matrix (i.e., mathematical concepts: matrices)
and a plurality of training edge inputs including a plurality of off-diagonal elements of the training Fock matrix and a plurality of off-diagonal elements of the training composite two-electron integral matrix (i.e., mathematical concepts: matrix)
and compute the plurality of training energy terms based at least in part on the plurality of training molecular orbital feature matrices (i.e., mathematical concepts: calculation)
Dependent claims 4 and 15 further recite:
estimate a total electronic energy of the runtime molecular structure based at least in part on the runtime input (i.e., mathematical concepts: energy estimation)
Dependent claim 5 further recites:
the one or more processing devices are configured to generate the plurality of truncated Hamiltonians at least in part by truncating and sparsifying the plurality of training molecular orbital feature matrices (i.e., mathematical concepts: truncation and sparsification )
Dependent claims 7 and 17 further recite:
the static correlation energy terms are estimated at least in part via complete-active-space configuration interaction (CAS- CI) estimation (i.e., mathematical concepts)
Dependent claim 8 and 18 further recite:
the coupled cluster estimation is coupled cluster single-double-triple (CCSD(T)) estimation (i.e., mathematical concepts)
Dependent claim 9 further recites:
the computing system of claim 1, wherein, for each truncated Hamiltonian, the one or more processing devices are configured to compute the respective static correlation energy term at least in part by: computing a CAS energy value and a corresponding coupled cluster energy value for the truncated Hamiltonian (i.e., mathematical concepts: calculation)
and computing the static correlation energy term as a difference between the CAS energy value and the coupled cluster energy value (i.e., mathematical concepts: calculation)
Dependent claim 10 and 19 further recite:
in a first training phase, train the electron energy estimation machine learning model based at least in part on the kinetic energy terms, the nuclear potential energy terms, the electron repulsion energy terms, and the exchange energy terms (i.e., mathematical concepts)
in a second training phase, train the electron energy estimation machine learning model based at least in part on the dynamical correlation energy terms (i.e., mathematical concepts)
and in a third training phase, train the electron energy estimation machine learning model based at least in part on the static correlation energy terms (i.e., mathematical concepts)
Dependent claim 11 further recites:
generating a plurality of conformers of one or more stable molecules ((i.e., mental processes: can be done with pen and paper)
and applying a plurality of perturbations to each of the conformers to obtain the plurality of training molecular structures (i.e., mental processes and mathematical concepts)
Independent claim 20 recites the following steps which fall within the mental processes and/or mathematical concepts groupings of abstract ideas:
generating a training data set at least in part by: generating a plurality of training molecular structures (i.e., mathematical concepts)
computing a respective plurality of training Hamiltonians of the training molecular structures (i.e., mathematical concepts)
based at least in part on the plurality of training Hamiltonians, computing a plurality of training energy terms associated with the training molecular structures, wherein computing the plurality of training energy terms includes: for each of the training Hamiltonians, computing respective estimated values of a kinetic energy term, a nuclear potential energy term, an electron repulsion energy term, and an exchange energy term (i.e., mathematical concepts)
for each training Hamiltonian included in a first proper subset of the plurality of training Hamiltonians, computing a respective dynamical correlation energy term (i.e., mathematical concepts)
and for each training Hamiltonian included in a second proper subset of the first proper subset: generating a truncated Hamiltonian for the training molecular structure (i.e., mathematical concepts)
and based at least in part on the truncated Hamiltonian, computing a respective static correlation energy term (i.e., mathematical concepts)
and using the plurality of training molecular structures and the plurality of training energy terms included in the training data set, train an electron energy estimation machine learning model at least in part by: in a first training phase, training the electron energy estimation machine learning model based at least in part on the kinetic energy terms, the nuclear potential energy terms, the electron repulsion energy terms, and the exchange energy terms; in a second training phase, training the electron energy estimation machine learning model based at least in part on the dynamical correlation energy terms (i.e., mathematical concepts)
and in a third training phase, training the electron energy estimation machine learning model based at least in part on the static correlation energy terms (i.e., mathematical concepts)
Therefore, claims 1,3,5,7-12,14,17-20 recite an abstract idea.
[Step 2A Prong One: YES]
Eligibility Step 2A Prong Two: In determining whether a claim is directed to a judicial exception, further examination is performed that analyzes if the claim recites additional elements that when examined as a whole integrates the judicial exception(s) into a practical application (MPEP 2106.04(d)). A claim that integrates a judicial exception into a practical application will apply, rely on, or use the judicial exception in a manner that imposes a meaningful limit on the judicial exception. The claimed additional elements are analyzed to determine if the abstract idea is integrated into a practical application (MPEP 2106.04(d)(I); MPEP 2106.05(a-h)). If the claim contains no additional elements beyond the abstract idea, the claim fails to integrate the abstract idea into a practical application (MPEP 2106.04(d)(III)).
The judicial exceptions identified in Eligibility Step 2A Prong One are not integrated into a practical application because of the reasons noted below.
Claims 3,5,7-11,14,17-20 do not recite any elements in addition to the judicial exception, and thus are part of the judicial exception.
The additional element in independent claims 1 and 12 include: a computing system comprising: one or more processing devices
The additional element in dependent claims 2 and 13 include: wherein the electron energy estimation machine learning model is a graph neural network.
The additional element in dependent claims 4 and 15 include: receive a runtime input, receive a plurality of runtime edge inputs, and output the total electronic energy.
The additional element in dependent claims 6 and 16 include: the static correlation energy terms are estimated at least in part at a quantum computing device
The additional element of a computing system comprising: one or more processing devices, the electron energy estimation machine learning model is a graph neural network, receiving a runtime input, receiving a plurality of runtime edge inputs, and outputting the total electronic energy, and the static correlation energy terms being estimated at least in part at a quantum computing device are insignificant extra-solution activity that are part of the data gathering process used in the recited judicial exceptions (see MPEP 2106.05(g)).
When all limitations in claims 1-20 have been considered as a whole, the claims are deemed to not recite any additional elements that would integrate a judicial exception into a practical application, and therefore claims 1-20 are directed to an abstract idea (MPEP 2106.04(d)).
[Step 2A Prong Two: NO]
Eligibility Step 2B: Because the claims recite an abstract idea, and do not integrate that abstract idea into a practical application, the claims are probed for a specific inventive concept. The judicial exception alone cannot provide that inventive concept or practical application (MPEP 2106.05). Identifying whether the additional elements beyond the abstract idea amount to such an inventive concept requires considering the additional elements individually and in combination to determine if they amount to significantly more than the judicial exception (MPEP 2106.05A i-vi).
The claims do not include any additional elements that are sufficient to amount to significantly more than the judicial exception(s) because the reasons noted below.
Claims 3,5,7-11,14,17-20 do not recite any elements in addition to the judicial exception, and thus are part of the judicial exception.
The additional elements recited in Independent claims 1 and 12, Dependent claims 2 and 13, Dependent claims 4 and 15 and Dependent claims 6 and 16 are identified above, and carried over from Step 2A: Prong Two along with their conclusions for analysis at Step 2B. Any additional element or combination of elements that was considered to be insignificant extra-solution activity at step Step 2A: Prong Two was re-evaluated at step 2B, because if such re-evaluation finds that the element is unconventional or otherwise more than what is well-understood, routine, conventional activity in the field, this finding may indicate that the additional element is no longer considered to be insignificant; and all additional elements and combination of elements are other than what is well-understood, routine, conventional activity in the field, or simply append well-understood, routine, conventional activities previously known to the industry, specified at a high level of generality, to the judicial exception, per MPEP 2106.05(d).
The additional element of a computing system comprising: one or more processing devices (claims 1 and claim 12) are conventional. One or more processors are conventional computer components. The courts have found the use of a computer or other machinery in its ordinary capacity for economic or other tasks (e.g., to receive, store, or transmit data) or simply adding a general-purpose computer or computer components after the fact to an abstract idea (e.g., a fundamental economic practice or mathematical equation) does not provide significantly more. See Affinity Labs v. DirecTV, 838 F.3d 1253, 1262, 120 USPQ2d 1201, 1207 (Fed. Cir. 2016) (cellular telephone); TLI Communications LLC v. AV Auto, LLC, 823 F.3d 607, 613, 118 USPQ2d 1744, 1748 (Fed. Cir. 2016).
The additional element of the electron energy estimation machine learning model is a graph neural network (claims 2 and 13) are conventional. Evidence of conventionality is shown by Manzhos and Carrington. (“Chemical Reviews, vol. 121, no. 16, 25 Aug. 2021, pp. 10187–10217”). In this review, Manzhos and Carrington. teach the use of neural networks to predict electronic energy, “The goal of DTNN is to produce a computer program that gives the electronic energy and also dipole moment, densities, orbital energies, etc.” and “The DTNN can be and has been used to predict multiple molecular properties such as orbital energies or charges” (col.2, para.4, lns.5-18,pg.10192), meaning that neural networks were commonly used to predict the electronic energy of molecules, showing this was a known and conventional technique.
The additional element of the static correlation energy terms being estimated at least in part at a quantum computing device (claim 6 and 16) is conventional. Evidence for conventionality is demonstrated by Wecker et al. (“Physical Review, vol.92, no.6, 10 Dec. 2015). In this review, Wecker et al. teach using a quantum computer to solve strongly correlated electron models, “we give explicit circuits to measure arbitrary local observables and static and dynamic correlation functions” (introduction, page 062318-1), meaning that quantum computers have conventionally been used to study and estimate energy properties of correlated electron systems, which are characterized by static correlation effects.
The additional elements of receiving a runtime input, receiving a plurality of runtime edge inputs and outputting the total electronic energy (claim 4 and claim 15) merely invokes a computer tool and does not improve the technology of a generic computer (see MPEP 2106.05(a)). Therefore, when taken alone, all additional elements in dependent claims 2 and 13, dependent claims 6 and 16 and dependent claims 4 and 15 do not amount to significantly more than the above-identified judicial exceptions(s). Even when evaluated as combination, the additional elements fail to transform the exceptions (s) into patent-eligible application of that exception. Thus, claims 1-20 are deemed to not contribute an inventive concept, i.e., amount to significantly more than the judicial exception(s) (MPEP 2106.05(II)).
[Step 2B: NO]
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
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 1-4, 8, 10-15, and 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Qiao et al. (OrbNet: Deep Learning for Quantum Chemistry Using Symmetry-Adapted Atomic-Orbital Features. arXiv preprint, arXiv:2007.08026v3,2022) in view of Bauman and Kowalski. (The Journal of chemical physics vol. 156,9 (2022): 094106). The italicized text corresponds to the instant claim limitations.
Claims 1, 12 and 20 are drawn to a computer system comprising one or more processors configured to generate a training data set at least in part by: generating a set of training molecular structures; computing Hamiltonians from the molecular structurers; based at least in part of the Hamiltonians, calculating energy terms associated with the molecular structures; wherein calculating the energy terms includes: for each Hamiltonian, calculating estimated values of a kinetic energy term, a nuclear potential energy term, an electron repulsion energy term, and an exchange energy term using Hartree-Fock (HF) estimation; for each Hamiltonian included in a first subset of the Hamiltonians, calculating a respective dynamical correlation energy term using coupled cluster estimation; and for each Hamiltonian included in a second subset of the first subset: generating a truncated Hamiltonian for the training molecular structure; and based at least in part on the truncated Hamiltonian, calculating a respective static correlation energy term using complete active space (CAS) estimation; and train an electron energy estimation machine learning model using the plurality of training molecular structures and the plurality of training energy terms included in the training data set. In some embodiments: the electron energy estimation machine learning model is a graph neural network (claims 2 and 13); when calculating the energy terms, generate training molecular orbital feature matrices based at least in part on the training Hamiltonians; these matrices include : vertex inputs including on diagonal elements of a training Fock matrix and of on diagonal elements of the training composite two electron matrix; and calculate the training energy terms based at least in part on the molecular orbital feature matrices (claims 3 and 14); during runtime, processors are configured to receive a runtime input including, for a runtime molecular structure: runtime vertex inputs including a plurality of on-diagonal elements of a runtime Fock matrix and of on-diagonal elements of a runtime composite two-electron integral matrix; and runtime edge inputs including a plurality of off-diagonal elements of the runtime Fock matrix and of off-diagonal elements of the runtime composite two-electron integral matrix; estimate a total electronic energy of the runtime molecular structure based at least in part on the runtime input; and output the total electronic energy (claims 4 and 15); the coupled cluster estimation is coupled cluster single-double-triple (CCSD(T)) estimation (claims 8 and 18); in a first training phase, train the electron energy estimation machine learning model based at least in part on the kinetic energy terms, the nuclear potential energy terms, the electron repulsion energy terms, and the exchange energy terms; in a second training phase, train the electron energy estimation machine learning model based at least in part on the dynamical correlation energy terms; and in a third training phase, train the electron energy estimation machine learning model based at least in part on the static correlation energy terms (Claims 10 and 19-20); generating conformers of one or more stable molecules; and applying a plurality of perturbations to each of the conformers to obtain the training molecular structures (claim 11);
With respect to claims 1, 12, and 20, Qiao et al. discloses a computer system with one or more processors (col.1, para.3, lns.1-2m pg.6; A computing system comprising: one or more processing devices). Qiao et al. discloses generating a training data set by training molecular structures (Fig.1a and col.2, para.2, lns.5-6, pg.5; configured to generate a training data set at least in part by: generating a plurality of training molecular structures). Qiao et al. discloses calculating training Hamiltonians from molecular structures (Fig.1a-1b and col.2, para.3, lns.8-12, pg.2; computing a respective plurality of training Hamiltonians of the training molecular structures). Qiao et al. discloses using hamiltonians as input to calculate energy terms (Fig.1g-legend and col.2, para.1, lns.1-5, pg.3; based at least in part on the plurality of training Hamiltonians, computing a plurality of training energy terms associated with the training molecular structures). Qiao et al. discloses using Hamiltonian, Coulomb (J), and exchange (K) operators as input features, representing fundamental quantum energy components, such as kinetic energy, nuclear potential energy, electron repulsion energy and exchange energy coming from the molecular structure (Fig.1a-c and col.2, para.3, lns.5-12, pg.2; wherein computing the plurality of training energy terms includes: for each of the training Hamiltonians, computing respective estimated values of a kinetic energy term, a nuclear potential energy term, an electron repulsion energy term, and an exchange energy term using Hartree-Fock (HF) estimation). Qiao et al. discloses training a machine learning model to estimate electron energy using molecular structures and their corresponding energy values in a dataset (Fig.1a-h and Eq.1-col.2, para.1, lns.1-3, pg.1; train an electron energy estimation machine learning model using the plurality of training molecular structures and the plurality of training energy terms included in the training data set).
Regarding claims 2 and 13, Qiao et al. teaches that the electron energy estimation machine learning model is a graph neural network (col.1, para.3, lns.3-7; the computing system of claim 1, wherein the electron energy estimation machine learning model is a graph neural network).
Regarding claims 3 and 14, Qiao et al. teaches that the molecular orbital matrices such as Fock matrix (F) and two electron Coulomb (J) and exchange matrices (K) (Fig.1b) are calculated from the molecular structure (Fig.1a), converted into graph node (vertex) features using on-diagonal matrix elements (Fig.c) and off-diagonal matrix elements. These vertex features are then used to compute energy terms and predict energy (Fig1.a-g, pg.2; generate a respective plurality of training molecular orbital feature matrices based at least in part on the plurality of training Hamiltonians, wherein each of the training molecular orbital feature matrices includes: a plurality of training vertex inputs including a plurality of on-diagonal elements of a training Fock matrix and a plurality of on-diagonal elements of a training composite two-electron integral matrix; and a plurality of training edge inputs including a plurality of off-diagonal elements of the training Fock matrix and a plurality of off-diagonal elements of the training composite two-electron integral matrix; and compute the plurality of training energy terms based at least in part on the plurality of training molecular orbital feature matrices).
Regarding claims 4 and 15, Qiao et al. teaches that OrbNet receives a molecular structure as an input and performs calculations to generate features, which corresponds to runtime prediction (Fig1.a-g, pg.2; during runtime, the one or more processing devices are configured to: at the electron energy estimation machine learning model, receive a runtime input including, for a runtime molecular structure). Qiao et al. teaches that the molecular orbital matrices such as Fock matrix (F) and two electron Coulomb (J) and exchange matrices (K) (Fig.1b) are calculated from the molecular structure (Fig.1a), converted into graph node (vertex) features using on-diagonal matrix elements (Fig.c) and off-diagonal matrix elements. These vertex features are then used to compute energy terms and predict energy (Fig1.a-g, pg.2; a plurality of runtime vertex inputs including a plurality of on-diagonal elements of a runtime Fock matrix and a plurality of on-diagonal elements of a runtime composite two-electron integral matrix; and a plurality of runtime edge inputs including a plurality of off-diagonal elements of the runtime Fock matrix and a plurality of off-diagonal elements of the runtime composite two-electron integral matrix; estimate a total electronic energy of the runtime molecular structure based at least in part on the runtime input). Qiao et al. teach outputting electronic energy (Fig1.h and col.1, para.2, ln.6, pg.4; and output the total electronic energy).
Regarding claims 8 and 18, Qiao et al. teaches using CCSD(T) (Fig.4, col.2, para.2, lns.7-9, pg.7; wherein the coupled cluster estimation is coupled cluster single-double-triple (CCSD(T)) estimation).
Regarding claim 11, Qiao et al. teaches generating conformers of stable molecules using MD simulations, that causes perturbation to atomic positions. Perturbed conformers are then sampled and used as training molecular structures (col.1-2, para.1, lns.1-19, pg.5; generating a plurality of conformers of one or more stable molecules; and applying a plurality of perturbations to each of the conformers to obtain the plurality of training molecular structures).
Regarding claims 10 , 19-20, Qiao et al. teaches that when training the models an initial epoch, a next epoch and a final epoch were performed (col.1, para.4,lns.1-8, pg.6; in a first training phase, training the electron energy estimation machine learning model based at least in part on the kinetic energy terms, the nuclear potential energy terms, the electron repulsion energy terms, and the exchange energy terms; in a second training phase, training the electron energy estimation machine learning model based at least in part on the dynamical correlation energy terms; and in a third training phase, training the electron energy estimation machine learning model based at least in part on the static correlation energy terms).
Qiao et al. is silent to: for each training Hamiltonian included in a first proper subset of the plurality of training Hamiltonians, computing a respective dynamical correlation energy term using coupled cluster estimation; and for each training Hamiltonian included in a second proper subset of the first proper subset: generating a truncated Hamiltonian for the training molecular structure and based at least in part on the truncated Hamiltonian, computing a respective static correlation energy term using complete active space (CAS) estimation in claim 1 and claim 12. However, these limitations were known in the art at the time of the effective filing date of the invention, as taught by Bauman and Kowalski.
As to claims 1 and 12, Bauman and Kowalski. disclose using coupled cluster on one subset to calculate dynamical correlation energy (col.2, para.5, lns.7-11, pgs.2-3; for each training Hamiltonian included in a first proper subset of the plurality of training Hamiltonians, computing a respective dynamical correlation energy term using coupled cluster estimation). Bauman and Kowalski. disclose creating truncated Hamiltonians using results from first subset (S3, Table 1 and col.1, para.1, lns.4-6, pg. 3; and for each training Hamiltonian included in a second proper subset of the first proper subset: generating a truncated Hamiltonian for the training molecular structure). Bauman and Kowalski. discloses that the truncated Hamiltonian constructed using coupled cluster amplitudes is used in the active space subset (second subset) to calculate energy (Eq2. and col.2, para.2, lns.1-11, pg.20; and based at least in part on the truncated Hamiltonian, computing a respective static correlation energy term using complete active space (CAS) estimation).
It would have been obvious to one of ordinary skill in the art at the time the invention was made to modify the deep learning for quantum chemistry method of Qiao et al. with the active space Hamiltonian downfolding methods of Bauman and Kowalski., because Bauman and Kowalski. shows that downfolding techniques lead to “energy accuracies” (col.2, para.3, lns.1-3, pg.8). A person of ordinary skill in the art would therefore have been motivated to add the downfolding techniques because Bauman and Kowalski. mentions that “The downfolding Hamiltonians also open an opportunity for utilizing ma chine learning methods to extract the analytical form of the effective inter-electron interactions” (col.2, para.3, lns.4-7, pg.8). One would have had a reasonable expectation of success for making this combination because the electron energy calculation would be more accurate.
Claims 5, 6 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Qiao et al. (OrbNet: Deep Learning for Quantum Chemistry Using Symmetry-Adapted Atomic-Orbital Features. arXiv preprint, arXiv:2007.08026v3,2022) in view of Bauman and Kowalski. (The Journal of chemical physics vol. 156,9 (2022): 094106), as applied to claims 1-4, 8, 10-15, and 18-20 above, and in further view of Cohn et al. (PRX Quantum, vol. 2, no. 4, 15 Dec. 2021).
Claim 5 is drawn to generating the truncated Hamiltonians at least in part by truncating and sparsifying the training molecular orbital feature matrices. Claims 6 and 16 are drawn to the static correlation energy terms being estimated at least in part at a quantum computing device.
The limitations of claims 1-4, 8, 10-15, and 18-20 have been taught by Qiao et al. and Bauman and Kowalski.
Qiao et al. and Bauman and Kowalski. are silent to the static correlation energy terms being estimated at least in part at a quantum computing device (claims 6 and 16) and generating the truncated Hamiltonians at least in part by truncating and sparsifying the training molecular orbital feature matrices (claim 5). However, these limitations were known in the art at the time of the effective filing date of the invention, as taught by Cohn et al.
Regarding claims 6 and 16, Cohn et al. teaches using a quantum computer (Fig.1 and col.1, para.2, lns.9-12, pg. 040352-2) to solve of the time-independent electronic Schrödinger equation, including correlation energies (Fig.19 and col.2, para.3, lns.1-6, pg. 040352-17; the static correlation energy terms are estimated at least in part at a quantum computing device).
Regarding claim 5, Cohn et al. teaches truncating the hamiltonians by truncating and sparsifying matrices from molecular orbitals, as the Hamilton is a matrix operator, meaning the Hamiltonian matrix is compressed (Fig1-3., and abstract, ln. 4, pg. 040352-1; generate the plurality of truncated Hamiltonians at least in part by truncating and sparsifying the plurality of training molecular orbital feature matrices).
It would have been obvious to one of ordinary skill in the art at the time the invention was made to modify the deep learning for quantum chemistry method of Qiao et al. with the active space Hamiltonian downfolding methods of Bauman and Kowalski., and the quantum filter diagonalization of Cohn et al., because Cohn et al. shows that “the method is found to provide accurate predictions for low-lying eigenspectra in a number of representative molecular systems” (abstract, pg.1). A person of ordinary skill in the art would therefore have been motivated to add the quantum computer and truncation/sparsifying techniques because quantum computers have superior simulation capabilities and truncation/sparsifying techniques because they make the hamiltionian smaller so that the quantum computer can handle the calculations in a faster and efficient way. One would have had a reasonable expectation of success for making this combination because it would provide more accurate predictions.
Claims 9, 7, 17 are rejected under 35 U.S.C. 103 as being unpatentable over Qiao et al. (OrbNet: Deep Learning for Quantum Chemistry Using Symmetry-Adapted Atomic-Orbital Features. arXiv preprint, arXiv:2007.08026v3,2022) in view of Bauman and Kowalski. (The Journal of chemical physics vol. 156,9 (2022): 094106), as applied to claims 1-4, 8, 10-15, and 18-20 above, and in further view of Aroeira et al. (Journal of Chemical Theory and Computation, vol. 17, no. 1, 4 Dec. 2020, pp. 182–190).
Claims 7 and 17 are drawn to the static correlation energy terms are estimated at least in part via complete-active-space configuration interaction (CAS- CI) estimation. Claim 9 is drawn to calculating the respective static correlation energy term at least in part by: calculating a CAS energy value and a corresponding coupled cluster energy value for the truncated Hamiltonian; and calculating the static correlation energy term as a difference between the CAS energy value and the coupled cluster energy value.
The limitations of claims 1-4, 8, 10-15, and 18-20 have been taught by Qiao et al. and Bauman and Kowalski.
Qiao et al. and Bauman and Kowalski. are silent to using complete-active-space configuration interaction (CAS-CI) estimation (claims 7 and 17) and to calculating a CAS energy value and a corresponding coupled cluster energy value for the truncated Hamiltonian; and calculating the static correlation energy term as a difference between the CAS energy value and the coupled cluster energy value (claim 9).
Regarding claims 7 and 17, Aroeira et al. teaches using complete-active-space configuration interaction (CAS-CI) estimation (col1., para.3, lns.5-7, pg.183; the static correlation energy terms are estimated at least in part via complete-active-space configuration interaction (CAS-CI) estimation).
Regarding claim 9, Aroeira et al. teaches calculating both CAS energy and a coupled cluster energy for a Hamiltonian and correlating the CAS energy and coupled cluster energy, which allows to determine static energy contribution (Tables 1 and 2, pgs. 185 and 187; computing a CAS energy value and a corresponding coupled cluster energy value for the truncated Hamiltonian and computing the static correlation energy term as a difference between the CAS energy value and the coupled cluster energy value).
It would have been obvious to one of ordinary skill in the art at the time the invention was made to modify the deep learning for quantum chemistry method of Qiao et al. with the active space Hamiltonian downfolding methods of Bauman and Kowalski., and the coupled cluster method of Aroeira et al., because Aroeira et al. shows that it produced “good results compared to other corrected CC methods” (abstract, pg.182). A person of ordinary skill in the art would therefore have been motivated to add Aroeira et al., techniques because it shows improvement. One would have had a reasonable expectation of success for making this combination because coupled cluster and CAS methods are known techniques to calculate electronic energy for a Hamiltonian, and this would lead to improvements when compared to standard coupled cluster.
Conclusion
No claims are allowed.
Inquiries
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ANDRIELE EICHNER whose telephone number is (571)272-9956. The examiner can normally be reached M-F, 9-5 ET.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Karlheinz R. Skowronek can be reached at (571) 272-9047. 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.
/A.S.E./Examiner, Art Unit 1687
/Karlheinz R. Skowronek/Supervisory Patent Examiner, Art Unit 1687