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 .
Priority
Acknowledgment is made of applicant’s claim for foreign priority under 35 U.S.C. 119 (a)-(d). The certified copy has been filed on 3/8/2022.
Respond to Amendment
This action is in response to the amendment filed on ----2/12/2026 for application 17/667,214. Claim 1 – 11 are withdrawn. Claim 12 – 22 are pending and have been examined.
Claim 15 is amended.
Claim rejection under 35 U.S.C. 112 section has been withdrawn in light of the amendment.
Claim rejection under 35 U.S.C. 101 section has been withdrawn in light of the amendment .
Respond to Argument
Applicant's remark filed on 2/12/2026 regarding claim rejection under 102 and 103 section has been fully considered but they are not persuasive.
Applicant stated in page 9 that “the ‘changing’ step” of the invention “is part of a design-time process”, which “is different than the method in Grichnik, which is a run-time process”; “the sensor configuration in Grichnik is never actually changed or reduced to a final sensor configuration, as that method merely switches from a primary signal source to a backup signal source during operation”. Examiner notes that the “design time” limitation is not in the claim. Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993). Examiner further notes that the Fig. 8 of Grichnik teaches “Obtain output parameters from physical 808 SenSOS” (808) and “Control engine based on the output parameters from physical sensors” (814), if physical sensor is not failed, thus, by default (preliminary configuration) physical sensor is to be used. If physical sensor is failed, “control engine based on the output parameters from virtual sensor” (812) thus final configuration is to use virtual sensor and reduce/remove the use of failed physical sensor. Thus Grichnik teaches changing the sensors configuration, into another configuration (final configuration) for the controlling of the vehicle. Thus, within BRI, Grichnik fulfilled the claimed limitation.
Applicant stated in page 10 – 11 that “Marlin is not ‘in the same field of endeavor’ nor is it ‘analogous’ as alleged” because “Marlin and Grichnik, claim 13 is not focused on data processing with missing data, rather it is focused on designing and optimizing the physical architecture of a vehicle sensor system so that it uses fewer real sensors.” Examiner respectfully disagrees. The invention as claimed in the independent claim Claim 12 requires using other information to recreate/replace a sensor information. Grichnik also teaches using other information to recreate/replace a faulty sensor information, thus Grichnik is analogous. Marlin teaches using restricted Boltzmann machine to “making predictions for missing data values” (Marlin page 82), thus Marlin is also analogous. Claim 13 depends on Claim 12, thus both references are analogous to the claims.
Applicant further state in page 11 that “there is no teaching or motivation in the applied prior art to replace the relatively simple method in Grichnik with the complex, computationally intensive models taught by Marlin, which is a dense academic paper on machine learning in general.” Examiner respectfully disagrees. Marlin’s academic paper points out advantages of using Restricted Boltzmann Machine RBM specifically using its generative process to replace/deal with missing data. The prior office action points out at least one of the aspect when the missing data is not random, in this case one of a model input is systematically missing, and how its teaching can prevent the bias that is introduced by the non-random missing data (Marlin, chapter 5). For further detail, see claim rejection under 35 U.S.C. 103 section.
The remaining arguments are essentially the same as those addressed above and/or below and are unpersuasive for at least the same reasons. Therefore, Examiner is unpersuaded and maintains the corresponding rejections.
Claim Rejections - 35 USC § 102
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 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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim 12 and 22 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Grichnik et al., (hereinafter Grichnik), US20080312756.
Claim 12. Grichnik discloses: A method for determining a sensor configuration in a vehicle which includes a plurality of sensors (fig. 8 & 0082 – 0087, “virtual sensor system 130 may be used in combination with physical sensors or as a back up for physical sensors. For example, virtual sensor system 130 may be used when one or more physical NO, emission sensors have failed. ECM 120 may perform a control process based on virtual sensor system 130 and corresponding physical sensors.”), comprising the steps of:
- establishing a preliminary sensor configuration for the vehicle, which sensor configuration includes a first number of real sensors, each of which outputting a real sensor signal (refer to the mapping above, using all physical sensor to control the vehicle is the preliminary sensor configuration);
- determining whether at least one of the real sensors can be replaced by a virtual sensor (0010, “The virtual sensor may be created by a process. The process may include obtaining data records including data from the plurality of sensors and the Supporting physical sensor; and calculating correlation values between the Supporting physical sensor and the plurality of sensors based on the data records. The process may also include selecting correlated sensors from the plurality of sensors based on the correlation values; and creating the virtual sensor of the Supporting physical sensor based on the correlated sensors.”);
- changing the preliminary sensor configuration into a final sensor configuration which includes a second number of real sensors and at least one virtual sensor, wherein the second number is smaller than the first number (refer to the mapping above & fig. 8, when some physical sensor fails, the system control vehicle with a mix of other physical sensor and the replacement virtual sensor (final sensor configuration) which uses less number of physical sensors),
wherein the determining step includes:
- recording the real sensor signals of at least a subset of the first number of real sensors (refer to the mapping above & 0010, the process uses data records of sensors), and
- evaluating the recorded real sensor signals in order to determine whether at least a first one of the real sensors can be replaced by a first virtual sensor that receives at least one real sensor signal from a second real sensor and outputs a virtual sensor signal that emulates the real sensor signal of the first real sensor (refer to the mapping above, the process finds/evaluates the correlations of sensors and to determine which sensors can be replaced by virtual sensor using data of other physical sensors ).
Claim 22. Grichnik teaches all the limitation of Claim 12. Grichnik further teach: a mathematical model for the real sensor that has been determined to be replaceable is determined on the basis of a statistic or deterministic approach (algorithm) (0031, “The relationship may include any appropriate relationship. Such as statistical relationship or other mathematical relationship. The relationship may be measured by any appropriate physical or mathematical term.”).
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 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.
Claim(s) 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Grichnik et al., (hereinafter Grichnik), US20080312756 as applied to claim 12 above, and further in view of Marlin, “Missing Data Problem in Machine Learning”.
Claim 13. Grichnik teaches all the limitation of Claim 12. Grichnik does not explicitly teach: the evaluating step includes the use of a Boltzmann machine having a number of visible nodes, each visible node representing a real sensor, and having a number of hidden nodes, the hidden nodes being computed by exploiting combinations of nodes.
Marlin, in the same field of endeavor, explicitly teach:
the evaluating step includes the use of a Boltzmann machine (Marlin, sec. 5.7, “restricted Boltzmann machines (RBMs) … that can efficiently cope with missing data … making predictions for missing data values”) having a number of visible nodes, each visible node representing a real sensor, and having a number of hidden nodes (Marlin, sec. 5.7.1, “one layer of visible units or observed variables … with one layer of hidden units … the data xn and the hidden units zn”), the hidden nodes being computed by exploiting combinations of nodes (Marlin, sec. 5.7.1, “energy function consisting of weights between the visible and hidden units parameterized by W”; i.e., use parameter W to compute the value of hidden nodes /exploiting from visible data nodes).
Grichnik and Marlin both teach data processing with missing data and are analogous. It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention with a reasonable likelihood of success to further include the use of Boltzmann Machine to learn the weights/relations and to proximate the missing data taught by Marlin in the system of Grichnik to achieve the claimed teaching. One of the ordinary skill in the art would have motivated to make this modification in order to reduce the systematic bias of the prediction model when the sensor data is missing (Marlin, chapter 1, page 1 – 2, & chapter 5.7 where RBM is used when the missing data is not random, “conditional RBM specify only the distribution of P(X|R)”; i.e., build the model based on the condition that certain input/sensor data is missing).
Claim(s) 14 – 15 are rejected under 35 U.S.C. 103 as being unpatentable over Grichnik et al., (hereinafter Grichnik), US20080312756 and Marlin, “Missing Data Problem in Machine Learning” as applied to claim 13 above, and further in view of Zhang, “Attention-Based Recurrent Temporal Restricted Boltzmann Machine for Radar High Resolution Range Profile Sequence Recognition”.
Claim 14. Grichnik and Marlin combination renders obviousness of all the limitation of Claim 13. The combination does not explicitly teach: the Boltzmann machine is a Recurrent Temporal Restricted Boltzmann machine.
Zhang, in the same field of endeavor, explicitly teach:
the Boltzmann machine is a Recurrent Temporal Restricted Boltzmann machine (Zhang, sec. 1, “a new method that combines the RTRBM (Recurrent Temporal Restricted Boltzmann Machine) model with the attention mechanism for sequential radar HRRP recognition is proposed in this paper”; i.e., use Recurrent model to handle time series data and combine with the Boltzmann machine to handle noise in the data).
Grichnik (in view of Marlin) and Zhang both teach processing of continuous time sequence sensor data with missing/noise and are analogous. It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention with a reasonable likelihood of success to further include the combination of recurrent temporal structure with restricted Boltzmann Machine taught by Zhang in the system of Grichnik (in view of Marlin) to achieve the claimed teaching. One of the ordinary skill in the art would have motivated to make this modification in order to “extract the information of temporal and spatial correlation” in the sensor data (Zhang, abs.).
Claim 15. Grichnik, Marlin and Zhang combination renders obviousness of all the limitation of Claim 14. The combination further teach: the Recurrent Temporal Restricted Boltzmann machine is implemented by a RNN-Gaussian dynamic Boltzmann machine (Zhang, sec. 2, “The RBM … model a joint distribution (Gaussian)”; i.e., the model of Zhang is to model based on the distribution of continuous variables; sec. 3, “brings the idea of the attention mechanism … paying more attention to major part … αt stands for the weight coefficient for the hidden layer at time step t”; i.e., the weight/attention is dynamic).
Claim(s) 16 – 21 are rejected under 35 U.S.C. 103 as being unpatentable over Grichnik et al., (hereinafter Grichnik), US20080312756 and Marlin, “Missing Data Problem in Machine Learning” as applied to claim 12 above, and further in view of Pearl, “An Introduction to Causal Inference”.
Claim 16. Grichnik teach all the limitation of Claim 12, Grichnik further teach:
- detecting and recording the outputs of at least a subset of the real sensors for a predetermined number of temporally subsequent sampling steps (Grichnik, 0003, “continuous emission monitoring”, 0040, “virtual sensor may provide enough information to continue operation of machine“; i.e., the sensing data is continuous over time for continuing the operation of the machine; 0030, “obtain data records containing data records or readings from the plurality of sensors”; 0047, “Virtual sensor process model 404 may be trained and validated using data records collected from a particular engine application for which virtual sensor process model 404 is established”; i.e., the amount/time range of data is selective/pre-determined ), and
- conducting a causation analysis which determines causations between the recorded outputs of the real sensors (0032, “A correlation between two variables may Suggest a certain causal relationship between the two variables (sensor outputs)”; i.e., the system shows causations between outputs of real sensors)
wherein the causations between the recorded outputs of the real sensors are determined for at least a subset of the samples (refer to the mapping above, the causations between two (a subset) variables (samples))
Grichnik does not explicitly teach:
wherein the causations determined for the subset of samples are subjected a post-processing in order to determine a final causation set or matrix between the recorded outputs of the real sensors.
Pearl, in the same field of endeavor, explicitly teach:
wherein the causations determined for the subset of samples are subjected a post-processing in order to determine a final causation set or matrix between the recorded outputs of the real sensors (Pearl, 3.2.3, “Causal analysis in graphical models begins with the realization that all causal effects are identifiable whenever the model is Markovian, that is, the graph is acyclic (i.e., containing no directed cycles) and all the error terms are jointly independent … permit identification only under certain conditions”; Grichnik teaches the use of correlation matrix which is bi-directional as illustrated in the correlation matrix of 0033 (for example S1 is correlated to S2 and S2 is also correlated to S1), Pearl teaches that the causal effect are identifiable only when certain conditions are true, i.e., further/post process from the known correlation to determine the final causation set).
Grichnik and Pearl both teach data processing with causation analysis and are analogous. It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention with a reasonable likelihood of success to further include the identification of causal effect taught by Pearl in the system of Grichnik to achieve the claimed teaching. One of the ordinary skill in the art would have motivated to make this modification in order to reduce prediction error by non-effective causation (Pearl, 3.2.3).
Claim 17. Grichnik and Pearl combination renders obviousness of all the limitations in Claim 16. The combination further teach: a directed cyclic graph (DCG) is established on the basis of the determined causations (refer to the mapping in Claim 16 & Grichnik, 0033, as shown in the correlation matrix the correlation is bi-directional, i.e., S1 is correlated to S2 and S2 is also correlated to S1, in a graphical representation, it is directed cycles).
Claim 18, Grichnik and Pearl combination renders obviousness of all the limitations in Claim 17. The combination further teach: wherein the DCG is converted into a directed acyclic graph (DAG) (refer to the mapping in Claim 16 – 17 & Pearl, 3.2.3, the causal analysis of Pearl finds identifiable causal effect among variables (sensors). “that is, the graph is acyclic”; i.e., from these correlation (acyclic) relationship, identify/convert into the cyclic relationship), wherein either the real sensor with the highest or the one with the lowest causation is taken as a root for the directed acyclic graph (Pearl, fig. 3, the Z1 is one of the root because it has causation effect on other variable but no measuring variable has causation effect on it).
Claim 19. Grichnik and Pearl combination renders obviousness of all the limitations in Claim 18. The combination further teach: at least one real sensor which forms a leaf or a root, respectively, in the DAG is determined to be replaceable (Grichnik, 0041, “virtual sensor for sensor S in that most or all of information provided by sensor S may be obtained from other correlated sensors (e.g., S2. S3, and Sn, etc.) because of the significant amount of relationships”; i.e., Grichnik and Pearl teaches to represent causal relationship of sensors in a DAG graph with leaf and root to represent variables (sensors). The root can be used to calculate a virtual sensor that replaces the leaf.).
Claim 20. Grichnik and Pearl combination renders obviousness of all the limitations in Claim 17. The combination further teach: a rank matrix is computed from the DCG, wherein at least one real sensor is determined to be low rank and replaceable (Grichnik, 0086, “If the deviation is beyond a predetermined threshold, ECM 120 may declare a failure and switch to virtual sensor system 130”; i.e., the system monitors/record the performance of each sensors and compute the deviation (rank matrix) of the sensor records to determine if a sensor has high deviation/low confidence).
Claim 21. Grichnik and Pearl combination renders obviousness of all the limitations in Claim 17. The combination further teach: a stochastic probabilistic process is generated from the DCG, wherein a state of at least one real sensor can be reached by the state of another real sensor state and can be determined to be replaceable (Pearl, 3.4, “Not all questions of causal character can be encoded in P(y|do(x)) type expressions, thus implying that not all causal questions can be answered from experimental studies”, “a probabilistic analysis of counterfactuals is required”).
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SHIEN MING CHOU whose telephone number is (571)272-9354. The examiner can normally be reached Monday- Friday 9 am - 5 pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, HITESH PATEL can be reached on 571-270-5442. 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.
/SHIEN MING CHOU/Examiner, Art Unit 3666
/Hitesh Patel/Supervisory Patent Examiner, Art Unit 3667
5/11/26
Prosecution Insights