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 .
Response to Arguments
101 Rejection
Based on applicant’s filed amendments and arguments seen on pages 8-11, the previously set forth 101 Rejection has been withdrawn.
102 Rejection
Applicant’s arguments with respect to claim(s) 1, 15 and 20 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-5 and 13-21 is/are rejected under 35 U.S.C. 103 as being unpatentable over Strack (2008/0071709) in view of Salman et al. (WO 2018/148492).
With respect to claim 1, Strack teaches a method comprising: accessing wellbore measurement data (56; [0068]); identifying, by a machine learning process, data that corresponds to the wellbore measurement data (as ANN 58 uses machine learning process and inputted data from input Earth model 50, input type curves 52 and input petrophysical data, to find corresponding data to the wellbore measurement data 56; [0068]); implementing a function that constrains the machine learning process data when mapping the constrained machine learning process data to the wellbore measurement data (as Strack teaches integrating petrophysical data into ANN 60 via the initial model 62 constrained by petrophysical data; [0068]); comparing the constrained machine learning process data to the wellbore measurement data (as Strack teaches the expected responses 66 via the trained ANN 60 are compared, at 68, to the measured responses of the electromagnetic instrument, i.e. the wellbore measurement data; [0068]); identifying based on the comparison that the wellbore measurement data corresponds to the constrained machine learning process data based on an error being less than an error threshold (Strack teaches if the differences between the measured response and the expected response are not below a selected threshold, then at 70 the model is adjusted and the expected response is recalculated in the trained ANN 60; [00689]); in response to the error being less than an error threshold (i.e. when it is determined the difference between the measured responses and the expected responses are below the threshold as s68), implementing the machine learning process (using the final model; Fig. 5).
Strack remains silent regarding implementing the machine learning process to identify a parameter associated with a wellbore; and performing an operation in the wellbore based on the parameter identified by the machine learning process.
Salman et al. teaches in Fig. 3 a similar method that includes implementing (350; [0097], Fig. 3) a machine learning process (i.e. a trained framework) to identify a parameter associated with a wellbore (i.e. interpretation results); and performing an operation in the wellbore based on the parameter identified by the machine learning process (as Salman et al. teaches based on the interpretation results, outputting a signal that instructs one or more pieces of wellbore equipment; [0097]).
It would have been obvious to one of ordinary skill in the art before the effective filing of the instant invention to modify the method of Strack to include the implementation of the machine learning process and performing an operation based on the result, as taught by Salman et al. because Salman et al. teaches such a modification aids in providing a streamline process, thereby improving productivity; [0045].
With respect to claims 2 and 16, Strack teaches the method wherein the function that constrains the machine learning process data is implemented based on an assumption regarding the wellbore measurement data (as Strack teaches the measurement data assumes the data is collected and exists for the survey area or areas being analyzed, its compatible with the untrained ANN 58, and geographical alignment).
With respect to claims 3 and 17, Strack teaches the method wherein the function that constrains the machine learning process data extracts features from the machine learning process data (as Strack teaches the machine learning process data is constrained from a portion of machine learning process data, more specifically extracted features from petrophysical data; [0068]).
With respect to claims 4 and 18, Strack teaches the method further comprising classifying material properties of the machine learning process data by narrowing an output range associated with the machine learning process data (Stack teaches in [0063-0066] classifying the measurement data, i.e. response data, to exclude certain geologic scenario).
With respect to claims 5 and 19, Wang et al. teaches the method further comprising: generating a mapping of a space that associates the constrained machine learning process data with known wellbore properties ([0037]; The initial structure may be determined using surface seismic surveying in combination with any one or more well known subsurface mapping techniques, including using well logs from any one or more wellbores drilled through the reservoir and/or the sensor 120 measurements from the monitor wellbore 118).
With respect to claim 13, Strack as modified by Salman teaches the method wherein the function that constrains the machine learning process data limits a bandwidth associated with a portion of the wellbore measurement data (as Salman teaches the framework limit a bandwidth associated with a portion of the wellbore measurement data as a filtering technique; [0084], [00146], [00149] of Salman).
With respect to claim 14, Strack as modified by Salman teaches the method wherein the bandwidth is limited by applying a bandpass filter on the portion of the wellbore measurement data (as Salman teaches the limits imposed on the bandwidth measurements are imposed by a bandpass filter; [00149]).
With respect to claim 15, Strack. teaches a non-transitory computer-readable storage medium having embodied thereon instructions (i.e. steps) that when executed by one or more processor (as indirectly taught for performing the steps in a computer environment) result in the one or more processors (as indirectly taught): accessing wellbore measurement data (56; [0068]); identifying, by a machine learning process, data that corresponds to the wellbore measurement data (as ANN 58 uses machine learning process and inputted data from input Earth model 50, input type curves 52 and input petrophysical data, to find corresponding data to the wellbore measurement data 56; [0068]); implementing a function that constrains the machine learning process data when mapping the constrained machine learning process data to the wellbore measurement data (as Strack teaches integrating petrophysical data into a trained ANN 60 via the initial model 62 constrained by petrophysical data; [0068]); comparing the constrained machine learning process data to the wellbore measurement data (as Strack teaches the expected responses 66 via the trained ANN 60 are compared, at 68, to the measured responses of the electromagnetic instrument, i.e. the wellbore measurement data; [0068]); identifying based on the comparison that the wellbore measurement data corresponds to the constrained machine learning process data based on an error being less than an error threshold (Strack teaches if the differences between the measured response and the expected response are not below a selected threshold, then at 70 the model is adjusted and the expected response is recalculated in the trained ANN 60; [00689]); in response to the error being less than an error threshold (i.e. when it is determined the difference between the measured responses and the expected responses are below the threshold as s68), implementing the machine learning process (using the final model; Fig. 5).
Strack remains silent regarding implementing the machine learning process to identify a parameter associated with a wellbore; and performing an operation in the wellbore based on the parameter identified by the machine learning process.
Salman et al. teaches in Fig. 3 a similar method that includes implementing (350; [0097], Fig. 3) a machine learning process (i.e. a trained framework) to identify a parameter associated with a wellbore (i.e. interpretation results); and performing an operation in the wellbore based on the parameter identified by the machine learning process (as Salman et al. teaches based on the interpretation results, outputting a signal that instructs one or more pieces of wellbore equipment; [0097]).
It would have been obvious to one of ordinary skill in the art before the effective filing of the instant invention to modify the method of Strack to include the implementation of the machine learning process and performing an operation based on the result, as taught by Salman et al. because Salman et al. teaches such a modification aids in providing a streamline process, thereby improving productivity; [0045].
With respect to claim 20, Wang et al. teaches an apparatus comprising: a memory (as indirectly taught for performing the steps in a computer environment); and one or more processors (as indirectly taught when performing the steps in the computer environment) that execute instructions out of the memory (as indirectly taught) to: access wellbore measurement data (56; [0068]); identify, by a machine learning process, data that corresponds to the wellbore measurement data (as ANN 58 uses machine learning process and inputted data from input Earth model 50, input type curves 52 and input petrophysical data, to find corresponding data to the wellbore measurement data 56; [0068]); implement a function that constrains the machine learning process data when mapping the constrained machine learning process data to the wellbore measurement data (as Strack teaches integrating petrophysical data into a trained ANN 60 via the initial model 62 constrained by petrophysical data; [0068]); compare the constrained machine learning process data to the wellbore measurement data (as Strack teaches the expected responses 66 via the trained ANN 60 are compared, at 68, to the measured responses of the electromagnetic instrument, i.e. the wellbore measurement data; [0068]); identify based on the comparison that the wellbore measurement data corresponds to the constrained machine learning process data based on an error being less than an error threshold (Strack teaches if the differences between the measured response and the expected response are not below a selected threshold, then at 70 the model is adjusted and the expected response is recalculated in the trained ANN 60; [00689]); in response to the error being less than an error threshold (i.e. when it is determined the difference between the measured responses and the expected responses are below the threshold as s68), implement the machine learning process (using the final model; Fig. 5).
Strack remains silent regarding implementing the machine learning process to identify a parameter associated with a wellbore; and performing an operation in the wellbore based on the parameter identified by the machine learning process.
Salman et al. teaches in Fig. 3 a similar method that includes implementing (350; [0097], Fig. 3) a machine learning process (i.e. a trained framework) to identify a parameter associated with a wellbore (i.e. interpretation results); and performing an operation in the wellbore based on the parameter identified by the machine learning process (as Salman et al. teaches based on the interpretation results, outputting a signal that instructs one or more pieces of wellbore equipment; [0097]).
It would have been obvious to one of ordinary skill in the art before the effective filing of the instant invention to modify the method of Strack to include the implementation of the machine learning process and performing an operation based on the result, as taught by Salman et al. because Salman et al. teaches such a modification aids in providing a streamline process, thereby improving productivity; [0045].
With respect to claim 21, Strack as modified by Salman teaches the method wherein: the parameter is associated with whether material properties of a location within a formation in proximity to the wellbore are suitable for hydrocarbon extraction (as Salman teaches the output signal controls the operation of equipment of the wellbore and its production of hydrocarbons relative to assed its geological environment; [0038]); and the operation (of the equipment) is associated with preparing the location for the extraction of hydrocarbons (i.e. a drilling operation; [0002]), and extracting the hydrocarbons at the location (i.e. a production operation; [0030]).
Claim(s) 6-9, 11 and 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Strack (2008/0071709) in view of Salman et al. (WO 2018/148492), as applied to claim 4, further in view of Jain et al. (2016/0170065).
With respect to claim 6, Wang et al. teaches all that is claimed in the above rejection of claim 4, but remains silent regarding the method further comprising: performing calculations to identify an error value by: subtracting values forecasted data identified by operation of a computer model from portions the wellbore measurement data to create a set of difference values; squaring the each of the set of difference values; and generating a sum of the set of squared difference values.
Jain et al. teaches a machine learning process that includes the claimed sum of squared errors process between actual measurements and a theoretical model; [0026].
It would have been obvious to one of ordinary skill in the art before the effective filing of the instant invention to modify the machine learning process to include the sum of squared error process, as taught by Jain et al., because Jain et al. teaches such a modification allows to for the machine learning process to evaluate how well the system model predictions match real-world measurements, thereby improving the accuracy of the machine learning process of Wang et al.
With respect to claims 7 and 11, Wang et al. as modified by Jain et al. teaches the method wherein the generated sum also includes a set of weighted fitness estimate values (as Jain et al. teaches each measurement is weight by squared noise, as Jain et al. teaches λ being a weighted sum; [0043]).
With respect to claims 8 and 12, Wang et al. as modified by Jain et al. teaches the method iteratively applying a data misfit gradient equation and a prior knowledge constraint equation to identify the values of the forecasted data (as Jain et al. teaches using iterative convex optimization algorithms, first and second example data sets, to identify the values of the forecasted data; [0049]).
With respect to claim 9, Wang et al. as modified by Jain et al. teaches the method Wang et al. teaches the method further comprising: generating a mapping of a space that associates the constrained machine learning process data with known wellbore properties (as Wang et al. teaches the machine learning analysis can be performed across adjacent depths, or zones, in order to provide a more robust analysis of the borehole environment and the like, for example, mapping out different zones like a washout zone at different depths, mapping out a log of the scale factors to be displayed to a user in order to inform the user of which depths are of what data quality as well as which depths are associated with partial or total model-based processing. In some aspects, this may inform a user of where borehole complexity is impacting (e.g., decreasing) data quality; [0053]).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MATTHEW G MARINI whose telephone number is (571)272-2676. 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, Stephen Meier can be reached at 571-272-2149. 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.
/MATTHEW G MARINI/ Primary Examiner, Art Unit 2853
Prosecution Insights