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 .
Summary
Claims 1-20 are pending. Claims 1-16 are rejected herein. Claims 17-20 are allowed. This is a Final Rejection as necessitated by the amendment and arguments (hereinafter “the Response”) dated 01 April 2026.
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) 1-9 and 12-16 is/are rejected under 35 U.S.C. 103 as being unpatentable over RUSTAD et al. (US 20160115395) in view of FENG et al. (US 20210372838).
Regarding claims 1-8: RUSTAD discloses: A method for generating a fluid classification, comprising: receiving measurement data, the measurement data corresponding to a microwave signal reflected from a fluid (open-ended microwave coaxial probe in para. 28); determining a set of fluid properties based on the measurement data (hydrate condition in step 126 in FIG. 7; ratio of water to injected chemical in step 152 of FIG. 8); and transmitting the fluid data to a control system of an oil and gas extraction system (step 156 in FIG. 8), wherein the control system is configured to adjust operation of one or more components of the oil and gas extraction system based on the fluid classification (step 158 in FIG. 8).
RUSTAD does not disclose using a decision-tree model for determining a set of fluid classification probabilities based on an analysis of the measurement data, the set of fluid properties, or a combination thereof; or generating a fluid classification associated with the fluid based on the set of fluid classification probabilities.
FENG however does teach determining a set of fluid classification probabilities comprising inputting at least one of the set of fluid properties to a decision-tree model (para. 66) comprising a plurality of threshold decision nodes (This is the structure of a decision tree), each threshold decision node comparing a fluid-property value to a corresponding threshold fluid-property value and selecting a branch of the decision-tree model based on the comparing until reaching a terminal node associated with the set of fluid classification probabilities (This is a general statement of how the decision-tree algorithm works.); generating a fluid classification associated with the fluid based on the set of fluid classification probabilities (This is the output of the model such as shown in FIGS. 7-8 of FENG.), the generating the fluid classification comprising selecting a fluid classification corresponding to a highest fluid classification probability associated with the terminal node (The terminal node is the step of the final calculation in the decision-tree model, which then gives the output probability such as those shown in FIG. 8 of FENG.). All decision-tree models will inherently involve comparing calculated values with thresholds values by a threshold decision node of the plurality of threshold decision nodes, thus meeting the limitations of claim 2. Each step in the decision-tree is determining a first set of fluid classification probabilities associated with a first set of fluid classifications; and based on the at least one fluid property falling within the threshold fluid property, determining a second set of fluid classification probabilities associated with a second set of fluid classifications, thus meeting the limitations of claim 3. The calculations of the algorithm keep creating new nodes in the decision tree until a desired accuracy is reached or some other condition is met, thus meeting the limitations of claim 4. FENG teaches determining phase fraction and phase distribution in a multiphase fluid (abstract) using microwave sensors (para. 5, 43, and 57). FENG teaches that the data is analyzed using a machine learning model (para. 63-64). This model is trained using experimentally measured data (para. 63-64), thus meeting the limitations of claim 5. The details of how such training is done including the thresholding procedure are discussed in para. 67, thus meeting the limitations of claims 6 and 7. Training such machine learning models is an iterative process and is repeated many times with different training data as discussed in para. 67, thus meeting the limitations of claim 8.
One skilled in the art at the time the application was effectively filed would be motivated to use the decision-tree machine learning model of FENG to process the data of RUSTAD because decision-tree models are simple to understand and interpret. Please note that FENG teaches many different machine learning algorithms in para. 66 and the use of one over another would be an obvious engineering choice based on available computational resources and the desired accuracy of the data output by the model.
One skilled in the art at the time the application was effectively filed would be motivated to use the historical measurement data of RUSTAD in the machine learning algorithm training as taught by FENG (para. 67) because the more data a machine learning model is trained with the more accurate it becomes (para. 90 of FENG).
Regarding claim 9: RUSTAD discloses: the measurement data comprises permittivity measurements (para. 28), conductivity measurements (para. 28), or a combination thereof.
Regarding claim 12: RUSTAD discloses: A system, comprising: a sensor (microwave sensor in para. 28) configured to measure a microwave signal reflected from a fluid and configured to generate measurement data based on the reflected microwave signal (para. 28); and a processor configured to perform operations comprising: receive the measurement data (step 122 in FIG. 7); determine a set of fluid properties based on the measurement data (step 124); receive fluid classification data associated with the fluid (hydrate condition in step 126); generate a water in liquid ratio estimation based on an analysis of the measurement data, the fluid classification data, the set of fluid properties, or any combination thereof (step 152 in FIG. 8); and transmit the water in liquid ratio estimation to a control system of an oil and gas extraction system (step 156 in FIG. 8), wherein the control system is configured to adjust chemical injection in an injection well based on the water in liquid ratio estimation (step 158 in FIG. 8).
RUSTAD does not disclose using a decision-tree model for determining a set of fluid classification probabilities based on an analysis of the measurement data, the set of fluid properties, or a combination thereof; or generating a fluid classification associated with the fluid based on the set of fluid classification probabilities.
FENG however does teach determining a set of fluid classification probabilities comprising inputting at least one of the set of fluid properties to a decision-tree model (para. 66) comprising a plurality of threshold decision nodes (This is the structure of a decision tree), each threshold decision node comparing a fluid-property value to a corresponding threshold fluid-property value and selecting a branch of the decision-tree model based on the comparing until reaching a terminal node associated with the set of fluid classification probabilities (This is a general statement of how the decision-tree algorithm works); generating a fluid classification associated with the fluid based on the set of fluid classification probabilities (This is the output of the model such as shown in FIGS. 7-8 of FENG.), the generating the fluid classification comprising selecting a fluid classification corresponding to a highest fluid classification probability associated with the terminal node (The terminal node is the step of the final calculation in the decision-tree model, which then gives the output probability such as those shown in FIG. 8 of FENG.).
One skilled in the art at the time the application was effectively filed would be motivated to use the decision-tree machine learning model of FENG to process the data of RUSTAD because decision-tree models are simple to understand and interpret. Please note that FENG teaches many different machine learning methods in para. 66 and the use of one over another would be an obvious engineering choice based on available computational resources and the desired accuracy of the data output by the model.
Regarding claim 13: RUSTAD discloses: the operations further comprising: generate an initial water in liquid ratio estimation based on a mixing model associated with the fluid classification data (para. 30); and generate the water in liquid ratio estimation based on the analysis comprising the initial water in liquid ratio estimation (Because it is a real-time process [para. 26] for controlling chemical injection [FIG. 8], the ratio is constantly being updated based on the previous measurements and calculations.).
Regarding claims 14-16: RUSTAD does not disclose machine learning.
FENG however teaches determining phase fraction and phase distribution in a multiphase fluid (abstract) using microwave sensors (para. 5, 43, and 57). FENG teaches that the data is analyzed using a machine learning model (para. 63-64). This model is trained using experimentally measured data (para. 63-64). The details of how such training is done including the thresholding procedure are discussed in para. 67. Training such machine learning models is an iterative process and is repeated many times with different training data as discussed in para. 67. FENG also discloses using one or more machine learning models (para. 63), thus meeting the limitations of claims 15 and 16.
One skilled in the art at the time the application was effectively filed would be motivated to use the historical measurement data of RUSTAD as modified by CHEN in the method as taught by FENG because the more data a machine learning model is trained with the more accurate it becomes (para. 90 of FENG).
Claim(s) 10 and 11 is/are rejected under 35 U.S.C. 103 as being unpatentable over RUSTAD and FENG in view of BLACK et al. (US 20180356356).
Regarding claims 10 and 11: Although RUSTAD discloses permittivity in para. 28, RUSTAD does not specify exactly how the permittivity relates to the fluid.
BLACK however teaches finding an average permittivity at different frequencies (para. 10) using microwave sensors (para. 26). BLACK also teaches finding the difference between each permittivity (para. 7, 10), thus meeting the limitations of claim 11.
One skilled in the art at the time the application was effectively filed would be motivated to use the multiple permittivity measurements of BLACK in the method of RUSTAD as modified by FENG because it allows for a more accurate measurement of water cut and salinity (para. 27 of BLACK).
Allowable Subject Matter
Claims 17-20 are allowed.
The following is an examiner’s statement of reasons for allowance: Independent claim 17 contains allowable subject matter. None of the prior art of record teaches or suggests the claimed invention. Specifically not found in the prior art of record are the limitations of using a decision-tree model wherein at each of the plurality of threshold decision nodes: comparing a permittivity standard deviation value to a threshold permittivity standard deviation value; responsive to the permittivity standard deviation value falling within the threshold permittivity standard deviation value, comparing an average permittivity value to a first threshold average permittivity value to reach the classification terminal mode, the classification terminal mode comprising at least one of: a dry gas terminal node corresponding to a dry gas fluid classification when the average permittivity value falls within the first threshold average permittivity value; or an oil fluid terminal node corresponding to an oil fluid classification when the average permittivity value meets or exceeds the first threshold average permittivity value, and generating the salinity value comprising generating the salinity value based on the fluid classification data associated with the classification terminal node, in combination with the other limitations of claim 17. As discussed above, it is known to use a decision-tree model of machine learning in calculations of this type. It is also known to use different types of permittivity measurements to calculate salinity as discussed above and in the previous office action in relation to BLACK. However, none of the prior art of record teaches this specific algorithm implemented in a decision-tree model.
Claims 18-20 are allowed due to their dependence on claim 17.
Any comments considered necessary by applicant must be submitted no later than the payment of the issue fee and, to avoid processing delays, should preferably accompany the issue fee. Such submissions should be clearly labeled “Comments on Statement of Reasons for Allowance.”
Response to Amendment/Argument
The Applicant has argued (pages 21-26 of the Response) that the independent claims do not teach the added limitations. The Examiner agrees with this statement and new grounds of rejection are presented herein for the rejections of claims 1 and 12 as necessitated by amendment. Claim 17 has been found allowable.
Conclusion
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 NATHANIEL J KOLB whose telephone number is (571)270-7601. The examiner can normally be reached M-F 9-5 EST.
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, LAURA MARTIN can be reached at (571) 272-2160. 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.
/NATHANIEL J KOLB/Examiner, Art Unit 2896
Prosecution Insights