Detailed Action
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.
Claim(s) 5 and 7-9 is/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.
In regards to claim 5, the claim recites in line 1 “wherein the mean and the variance of the ensemble model comprise”. Claims 2 and 3 defined a mean and a variance respectively. It is unclear if the mean and variance recited in claim 5 is referring to the mean and variance defined in claims 2 and 3 or to a mean and variance that has not been previously define. If the limitation of line 1 is referring to a mean and variance that have not been previously defined, there would be lack of antecedent basis for the limitations of line 1. For this reason, the claim is indefinite. The examiner has interpreted the claim in the following way in order to advance prosecution: “wherein the mean digital bit confidence and the variance of digital bit confidence
In regards to claim 7, the claim recites in line 3 “combining the predictions based at least in part on uncertainty in the predictions”. The claim previously defined predictions generated using a machine learning model and predictions generated using a physics based model. It is unclear each time the limitation of “the predictions” is recited if the limitation is referring to the predictions generated using a machine learning model or the prediction generated using a physics based model or both. For this reason, the claim is indefinite.
In regards to claim(s) 8-9, the claim(s) is/are indefinite due to its/their dependency on indefinite claim 7.
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.
Claim(s) 20 is/are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. The claim(s) does/do not fall within at least one of the four categories of patent eligible subject matter because it is directed to a signal.
In regards to claim 20, the claim recites in line 1 “One or more computer-readable storage media comprising”. The limitation of one or more computer-readable storage media can be interpreted as a signal. A signal does not fall within at least one of the four categories of patent eligible subject matter. The examiner has interpreted the claim in the following way in order to advance prosecution: “One or more non-transitory computer-readable storage media comprising”.
Claim Rejections - 35 USC § 102
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.
Claim(s) 1 and 18-20 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Miller et al. (US-11,814,954).
In regards to claim 1, Miller teaches a method comprising receiving data for field operations using equipment at a site [col. 8 L. 32-35, col. 27 L. 41-49]. Also, Miller teaches that the equipment comprises a downhole tool on a tool string disposed in a borehole in a geologic environment and a mud pulse telemetry system [fig. 1 element 14, col. 8 L. 30-33 and L. 35-37]. Furthermore, Miller teaches that the method comprise determining control parameters for the mud pulse telemetry system using at least a portion of the data and a trained machine learning model [col. 25 L. 44-50, col. 27 L. 45-60 and L. 63-67, col. 8 L. 1-11, L. 52-54 and L. 65-67]. Miller also teaches that the method comprises controlling the mud pulse telemetry system using the control parameters [col. 27 L. 55-60, col. 28 L. 6-11, L. 52-54 and L. 65-67].
In regards to claim 18, Miller, as applied in the rejection of claim 1 above, that the controlling comprises controlling the mud pulse telemetry system to transmit sensor data acquired by the downhole tool via generation of mud pulses in drilling fluid disposed in the borehole [col. 8 L. 35-37, 45-46 and L. 61-64, col. 27 L. 55-60, col. 28 L. 6-11, L. 52-54 and L. 65-67]. Also, Miller teaches that the tool string comprises a bore and wherein the drilling fluid is disposed in the bore [col. 5 L. 4-12, col. 8 L. 35-37].
In regards to claim 19, Miller, as shown in the rejection of claim 1 above, teaches the claimed functions. Furthermore, Miller teaches that the claimed functions can be performed by a processor executing instructions stored in memory [col. 1 L. 59-62]. Therefore, Miller also teaches the claimed system.
In regards to claim 20, Miller, as shown in the rejection of claim 1 above, teaches the claimed functions. Furthermore, Miller teaches that the claimed functions can be performed by a processor executing instructions stored in memory [col. 1 L. 59-62]. Therefore, Miller also teaches the claimed the claimed one or more non-transitory computer-readable storage media.
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.
Claim(s) 2 is/are rejected under 35 U.S.C. 103 as being unpatentable over Miller et al. (US-11,814,954), as applied to claim 1 above, and in view of Chari et al. (US-9,806,871).
In regards to claim 2, Miller, as applied in the rejection of claim 1 above, further teaches that a machine learning is used for the determining [col. 25 L. 44-50, col. 27 L. 45-60 and L. 63-67, col. 8 L. 1-11, L. 52-54 and L. 65-67]. However, Miller does not teach that the determining comprises predicting mean digital bit confidence.
On the other hand, Chari teaches that the determining comprises predicting mean digital bit confidence [col. 6 L. 57-63].
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to use Chari’s teachings of predicting mean digital bit confidence in the method taught by Miller because it will permit to accurately determine if bits have not been received with errors using the current communication settings.
Claim(s) 7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Miller et al. (US-11,814,954), as applied to claim 1 above, and in view of Jain et al. (US-11,066,917).
In regards to claim 7, Miller, as applied in the rejection of claim 1 above, does not teach generating predictions using the trained machine learning model, generating predictions using a physics-based model, and combining the predictions based at least in part on uncertainty in the predictions.
On the other hand, Jain teaches that a system can make accurate predictions of a condition by forming an hybrid prediction model that combines a physics model and a machine learning model and that accounts for introductions of new uncertainties [col. 4 L. 13-30]. This teaching means that the method comprises generating predictions using a trained machine learning model, generating predictions using a physics-based model, and combining the predictions based at least in part on uncertainty in the predictions.
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to use Jain’s teachings of making predictions using an hybrid prediction model in the method taught by Miller because it will permit the system to predict future conditions of the communication system and accurately adjust control parameters of the communication system to have reliable data communications.
Claim(s) 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Miller et al. (US-11,814,954) in view of Jain et al. (US-11,066,917) as applied to claim 7 above, and further in view of Plochowietz et al. (US-11,762,348).
In regards to claim 8, the combination of Miller and Jain, as applied in the rejection of claim 7 above, further teaches generating predictions using an hybrid model comprising a physics model and a machine learning model [see Jain col. 4 L. 13-30]. However, the combination does not teach that the combining comprises weighting the predictions of the physics-based model based at least in part on the predictions of the trained machine learning model.
On the other hand, Plochowietz teaches when using a hybrid model, predictions of the models can be aggregated by assigning the predictions from different models weights [col. 9 L. 48-65]. This teaching means that the combining comprises weighting the predictions of the physics-based model based at least in part on the predictions of the trained machine learning model.
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to use Plochowietz’s teachings of assigning weights to the predictions in the method taught by the combination because it will permit to obtain more accurate results.
Claim(s) 9 is/are rejected under 35 U.S.C. 103 as being unpatentable over Miller et al. (US-11,814,954) in view of Jain et al. (US-11,066,917) as applied to claim 7 above, and further in view of Wallace et al. (US-12,461,261).
In regards to claim 9, the combination of Miller and Jain, as applied in the rejection of claim 7 above, further teaches that a physics based model is used for the determination [see Jain col. 4 L. 13-30]. Also, the combination teaches that the transmitted signals are a mud pulses [see Miller col. 8 L. 35-37, col. 28 L. 52-54 and L. 65-67]. However, the combination does not teach that the physics-based model models at least attenuation of mud pulses (transmitted signals).
On the other hand, Wallace teaches that a physics model can model attenuation of the transmitted signals [col. 6 L. 8-12].
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to use Wallace’s teachings of modeling attenuation with the physics based model in the method taught by the combination because it will permit the system to determine how attenuation is affecting communications and adjust the control parameters accordingly.
Claim(s) 10-11 is/are rejected under 35 U.S.C. 103 as being unpatentable over Miller et al. (US-11,814,954) as applied to claim 1 above, and in view of Kusuma et al. (US-10,113,418).
In regards to claim 10, Miller, as applied in the rejection of claim 1 above, does not teach that the determining accounts for modulation.
On the other hand, Kusuma teaches that the determination used to adjust communication parameters of a telemetry system can include determining new modulation parameters such as modulation type. This teaching means that the determining accounts for modulation [col. 1 L. 27-34, col. 7 L. 10-22].
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to use Kusuma’s teachings of accounting for modulation in the determination in the method taught by Miller because it will permit the system to adjust the control parameters more accurately in order to have more reliable communications.
In regards to claim 11, the combination of Miller and Kusuma, as applied in the rejection of claim 10 above, further teaches that the modulation comprises QPSK modulation [see Kusuma col. 4 L. 45-49, col. 6 L. 36-38].
Claim(s) 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Miller et al. (US-11,814,954) as applied to claim 1 above, and in view of Kusuma et al. (US-10,113,418) and Conn et al. (US-2015/0218937).
In regards to claim 12, Miller, as applied in the rejection of claim 1 above, further teaches that the system determines control parameters to improve communications [col. 25 L. 44-50, col. 27 L. 45-60 and L. 63-67, col. 8 L. 1-11, L. 52-54 and L. 65-67]. However, Miller does not teach that the control parameters comprise one or more of telemetry mode, telemetry data rate, and telemetry frequency.
On the other hand, Kusuma teaches that determined control parameters can include telemetry mode and telemetry frequency [col. 7 L. 10-22].
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to use Kusuma’s teachings of determining control parameters that include telemetry mode and telemetry frequency in the method taught by Miller because it will permit the system to improve communications using mud pulse communications.
The combination of Miller and Kusuma does not teach that the control parameters include telemetry data rate.
On the other hand, Conn teaches that the determined control parameters can include data rate [par. 0023 L. 24-30].
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to use Conn’s teachings of determining control parameters that include telemetry data rate in the method taught by the combination because it will permit the system modify the data rate based on the current conditions of the wellbore thereby improving communications.
Claim(s) 13-14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Miller et al. (US-11,814,954) as applied to claim 1 above, and in view of Oyedotun et al. (Why Is Everyone Training Very Depp Neural Network with Skip Connections?)
In regards to claim 13, Miller, as applied in the rejection of claim 1 above, further teaches that the system uses machine learning models to perform the determination [col. 26 L. 33-44]. However, Miller does not teach that the trained machine learning model comprises at least one residual block.
On the other hand, Oyedotun teaches that one know type of machine learning model is a model comprising residual blocks [pg. 5963 left column section B L. 21-30].
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to use Oyedotun’s teachings of using machine learning with residual blocks in the method taught by the combination because it permit the model to provide accurate results.
In regards to claim 14, the combination of Miller and Oyedotun, as applied in the rejection of claim 13 above, further teaches that the at least one residual block comprises at least one residual block characterized by one or more skip connections [see Oyedotun pg. 5963 left column section B L. 21-30].
Claim(s) 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Miller et al. (US-11,814,954) as applied to claim 1 above, and in view of Malladi et al. (US-12,547,822).
In regards to claim 15, Miller, as applied in the rejection of claim 1 above, further teaches that the machine learning model is trained [col. 25 L. 51-56]. However, Miller does not teach that the model is trained using a negative log-likelihood loss function.
On the other hand, Malladi teaches that a machine learning model can be trained using a negative log-likelihood loss function [col. 18 L. 55-65].
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to use Malladi’s teachings of training the model using a negative log-likelihood loss function in the method taught by the combination because it will permit the model to provide accurate results.
Claim(s) 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Miller et al. (US-11,814,954) as applied to claim 1 above, and in view of Madasu et al. (US-11,493,664).
In regards to claim 16, Miller, as applied in the rejection of claim 1 above, further teaches that the machine learning model is trained [col. 25 L. 51-56]. However, Miller does not teach that the model is trained using tabular data, wherein the tabular data comprise data from field operations performed at other sites.
On the other hand, Madasu teaches that a machine learning model used in a wellbore environment can be trained using data from other wellbores [col. 5 L. 4-7]. This teaching means that the model is trained using tabular data, wherein the tabular data comprise data from field operations performed at other sites.
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to use Madasu’s teachings of training the model using tabular data from other sites in the method taught by the combination because it will permit the model to provide accurate results.
Allowable Subject Matter
Claim(s) 3-4, 6 and 17 is/are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
In regards to claim 3, the cited prior art does not teach either by anticipation or combination the following limitations: the determining comprises predicting variance of digital bit confidence using the trained machine learning model.
In regards to claims 4 and 6, the claims would be allowable due to their dependency on claim 3.
In regards to claim 17, the cited prior art does not teach either by anticipation or combination the following limitations: the trained machine learning model is trained using a feature tokenizer that tokenizes at least a portion of the tabular data from categories into numbers.
Claim(s) 5 would be allowable if rewritten or amended to overcome the rejection(s) under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), 2nd paragraph, set forth in this Office action.
In regards to claim 5, the claim would be allowable due to its dependency on claim 3.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to FRANKLIN D BALSECA whose telephone number is (571)270-5966. The examiner can normally be reached 6AM-4PM EST M-F.
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, STEVEN LIM can be reached at 571-270-1210. 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.
/FRANKLIN D BALSECA/Examiner, Art Unit 2688
Prosecution Insights