DETAILED ACTION
Claims 1-15 and 19-20 are presented for examination. This Final Office Action is made in response to the communication filed June 11, 2026.
Claims 1, 9, and 15 are objected to.
Claims 1-15 and 19-20 are rejected under 35 USC 112(b) as indefinite.
Claims 1-15 and 19 are rejected under 35 USC 103 as obvious over Rommel in view of Cella and Logan.
Claim 20 is rejected under 35 USC 103 as obvious over Rommel in view of Cella, Logan, and Kusuma.
Response To Amendments/Arguments
35 USC 112(a): The Applicant’s arguments and amendments have been considered and are persuasive. The rejections are withdrawn.
35 USC 101: The Applicant’s arguments and amendments have been considered and are persuasive. The rejections are withdrawn.
35 USC 103: The Applicant’s arguments and amendments have been considered and are persuasive. The rejections are withdrawn. However, new art rejections have been provided.
Claim Objections
Claims 1, 6, 9, and 15 are objected to because of the following informalities:
The independent claims recite,
“receive/ing formation model data corresponding to characteristics of a formation;”
[…]
“generate/ing […] based directly on measurement logs instead of based on predicted formation models”
The independent claims receive prediction formation model data in the receiving step, but the claim does not appear to use this data. Further, the generating step is based on measurement logs, rather than the received formation data. It is unclear what the Applicant’s intended relationship between the recited, “formation model data,” “measurement logs,” and “predicted formation models.”
Claim 6 recites, “wherein the second channel selection comprises a second set of data channels of the logging tool of the second well that corresponding to a second predetermined portion of measurements to transmit from the logging tool.” This appears to be a typo.
Appropriate correction is required.
Claim Rejections - 35 USC § 112(b)
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.
Claims 1-15 and 19-20 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 applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Directly
Claims 1, 9, and 15 recite “directly.” Directly is a relative term of degree with no clear basis for what would be direct v. indirect. The Applicant is advised to remove the language.
Instead of
Independent claims 1, 9, and 15 recite, “based directly on measurement logs instead of based on predicted formation models.” “Instead of” can be interpreted a number of ways. For example, “instead of” could reasonably be interpreted to mean (1) that the method first considers the use of formation models, but, after a determination, the model uses measurement logs instead of the formation models. This would imply an additional determination step. The most reasonable interpretation is not clear in light of the Applicant’s specification paragraphs [0050]-[0051], where such a consideration (e.g., an additional determination step of whether it makes sense to use measurement logs) is made based on the availability of the data. Another potential reasonable interpretation is (2) that the ML model selects the channels based on measurement logs to the exclusion of formation model data. This is also a reasonable interpretation for a number of reasons, not the least of which is that “based on formation models” is within the scope of “based on measurement logs,” as formation models are generated from (“based on”) measurement logs.
For purposes of examination, the limitation will be interpreted to mean (2) that the ML model selects the channels based on measurements logs to the exclusion of formation data. However, the Applicant is advised to remove this language and replace it with a more explicit recitation of the Applicant’s intended interpretation. Because two different interpretations with different scopes are both reasonable interpretations, the person of ordinary skill in the art would not be able to appropriately discern the metes and bounds of the claims. Therefore, appropriate correction is required.
Dependent claims that depend from the rejected claims are rejected based on their dependency.
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.
Claims 1-19: Rommel, Cella, and Logan
Claim(s) 1-19 are rejected under 35 U.S.C. 103 as being unpatentable over US 2003/0193837 A1 to Rommel (Rommel) in view of US 2020/0103894 A1 to Cella et al. (Cella), US 2022/0333483 A1 to Logan et al. (Logan).
Claims 1 and 9
Regarding claim 9, Rommel teaches:
A tangible and non-transitory machine readable medium comprising instructions to cause a processing system to: (Rommel [0075] “The apparatus 16 comprises a programmable data processor 17 with a program memory 18, for instance in the form of a read only memory (ROM), storing a program for controlling the data processor 17 to simulate and process seismic data by a method of the invention.” - Computer)
receive formation model data corresponding to characteristics of a formation; receive at least one drilling parameter corresponding to an attribute related to a well in the formation; (Rommel [0005] “The travel time of seismic energy from the source 1 to the receiver 6 along a path involving reflection within the earth's interior will depend on, inter alia, the horizontal distance between the source 1 and the receiver 6. The horizontal distance between the source 1 and the receiver 6 is generally known as "offset". It is well-known in seismic surveying to derive information about the earth's structure from the variation with offset of travel time from the source to the receiver. However, as the source-receiver offset varies the amplitude of the energy received at the receiver along a particular reflection path--for example the path involving reflection at the interface 4--will also vary. This variation in amplitude of the acquired seismic energy occurs because a change in source-receiver offset changes the angle of incidence that the seismic energy makes with the interface 4, and this change in angle of incidence alters the ratio between the amplitude of seismic energy transmitted along path 5' and the amplitude of seismic energy reflected along path 5". It is possible to derive further information about the earth's interior from analysis of the variation of amplitude of acquired seismic energy with offset, and this process is known as "AVO inversion". AVO inversion provides information about the difference in elasticity or impedance or velocity and density across an interface within the earth. The differences in elasticity or impedance or velocity and density are therefore known as "AVO parameters". In the present application, the term "AVO uncertainty" will be understood as comprising all distributions of possible AVO parameters that are consistent with a seismic surveying arrangement.” – This teaches that data representing the formation and the devices therein for measuring seismic data are determined and provided for analysis.)
generate a synthetic response based upon the formation model data and the at least one drilling parameter; (Rommel [0042]-[0049] “Initially, at step 7, the best model of the geologic structure and seismic properties of the earth's interior is made for a desired survey location. The model is constructed using the best available information about the survey location, for example information that has been obtained in previous seismic surveys at the survey location. At step 8 the parameters of a seismic surveying arrangement (or "acquisition geometry") are defined. The parameters of the seismic surveying arrangement may include, for example, the following: number of seismic sources; details of the source array such as the arrangement of the sources and the separation between two adjacent sources (if there is more than one seismic source); the number of seismic receivers; details of the source array such as the arrangement of the receivers and the separation between adjacent receivers (if there is more than one seismic receiver); and the separation between the source or source array and the receiver or receiver array. Next, at step 9, one or more raypaths of seismic energy are simulated. That is, step 9 simulates one or more raypaths that would be obtained if the seismic surveying arrangement defined in step 8 were used to carry out a seismic survey at the survey location, in the light of the best model of the seismic properties of earth's interior at the survey location as defined at step 7. The simulation of raypaths of seismic energy is a known step in the SED phase of a seismic survey, and will not be described in detail here. In outline, however, step 9 may consist of using ray tracing to evaluate the propagation of the seismic wavefield produced by the source array of the seismic surveying arrangement defined at step 8 through the model of the survey location defined at step 7. This will allow the raypaths incident on the receiver array of'the seismic surveying arrangement defined at step 8 to be determined. It should be noted that the present invention does not require a simulation of the amplitude of the seismic energy incident on the receivers of the seismic surveying arrangement. It is sufficient for step 9 to simulate the raypaths of the seismic energy--that is, for step 9 to consist of a kinematic simulation of the seismic data--and it is not necessary to perform a full dynamic simulation that also simulates the amplitude of the seismic data (although in principle a full simulation could be carried out at step 9). – Synthetic logs for traces and their underlying data are generated to determine which channels are to be trusted.)
undertake channel selection corresponding to the synthetic response as training data, wherein the channel selection comprises a set of data channels of a logging tool of the well that prioritizes a predetermined portion of measurements to transmit from the logging tool; (Rommel [0057] “The output of step 11 is one or more parameters of AVO uncertainty for the seismic surveying arrangement defined at step 8 at the survey location as modelled by the model chosen at step 7. The parameters of the AVO uncertainty output from step 11 may comprise the resolution, the posterior covariance, or both the resolution and the posterior covariance. Steps 7-11 of the method shown in FIG. 2(a) therefore allow one or more parameters of AVO uncertainty, such as the resolution and/or posterior covariance, to be predicted at the SED phase of the seismic survey.” [0061] “It should be noted that the resolution and posterior covariance are, in general, matrices, The step of comparing the resolution (or posterior covariance) with its threshold may therefore comprise comparing each element of the resolution (or posterior covariance) with a threshold value for that element of the resolution (or posterior covariance), with a "yes" determination being obtained if each element of the resolution (or posterior covariance) is lower than its respective threshold value. Alternatively, the step of comparing the resolution (or posterior covariance) with its threshold may consist of comparing one or more selected elements of the resolution (or posterior covariance) with respective threshold values, rather than performing the comparison for each element of the resolution (or posterior covariance).” – The reference performs analysis to determine which sensor element channels represented in the resolution matrix are less trustworthy. [0073] “From equation (6), the rows of the resolution matrix can be considered filters acting on the true earth model m to give the observed model m.sub.obs as deduced from seismic data d. Ideally, if the observed model m.sub.obs was identical to the true earth model m the diagonal elements of the resolution matrix would be unity and off-diagonal elements would be zero; using the prior model compensates any deviations (see equation (7)). Hence, the resolution indicates how much of the seismic data will actually be used in arriving at the best solution of a later AVO inversion.” – The system only uses data that is reliable, e.g., from reliable channels. Abstract “A method of evaluating a seismic survey to be carried out at a particular survey location comprises choosing an initial seismic surveying arrangement. One or more parameters of AVO (amplitude versus offset) uncertainty are then determined from the seismic surveying arrangement using a model of the earth's interior at the survey location. If the parameter(s) of AVO uncertainty are not acceptable the seismic surveying arrangement is changed, and the AVO uncertainty parameter(s) re-determined for the new acquisition geometry.” [0073] “Hence, the resolution indicates how much of the seismic data will actually be used in arriving at the best solution of a later AVO inversion.” – The sensor array can be adjusted to move or ignore the sensors with weak signals.)
selects a reduced number of channels from which to transmit well measurements(Rommel [0057] “The output of step 11 is one or more parameters of AVO uncertainty for the seismic surveying arrangement defined at step 8 at the survey location as modelled by the model chosen at step 7. The parameters of the AVO uncertainty output from step 11 may comprise the resolution, the posterior covariance, or both the resolution and the posterior covariance. Steps 7-11 of the method shown in FIG. 2(a) therefore allow one or more parameters of AVO uncertainty, such as the resolution and/or posterior covariance, to be predicted at the SED phase of the seismic survey.” [0061] “It should be noted that the resolution and posterior covariance are, in general, matrices, The step of comparing the resolution (or posterior covariance) with its threshold may therefore comprise comparing each element of the resolution (or posterior covariance) with a threshold value for that element of the resolution (or posterior covariance), with a "yes" determination being obtained if each element of the resolution (or posterior covariance) is lower than its respective threshold value. Alternatively, the step of comparing the resolution (or posterior covariance) with its threshold may consist of comparing one or more selected elements of the resolution (or posterior covariance) with respective threshold values, rather than performing the comparison for each element of the resolution (or posterior covariance).” – The reference performs analysis to determine which sensor element channels represented in the resolution matrix are less trustworthy. [0073] “From equation (6), the rows of the resolution matrix can be considered filters acting on the true earth model m to give the observed model m.sub.obs as deduced from seismic data d. Ideally, if the observed model m.sub.obs was identical to the true earth model m the diagonal elements of the resolution matrix would be unity and off-diagonal elements would be zero; using the prior model compensates any deviations (see equation (7)). Hence, the resolution indicates how much of the seismic data will actually be used in arriving at the best solution of a later AVO inversion.” – The system only uses data that is reliable, e.g., from reliable channels. Abstract “A method of evaluating a seismic survey to be carried out at a particular survey location comprises choosing an initial seismic surveying arrangement. One or more parameters of AVO (amplitude versus offset) uncertainty are then determined from the seismic surveying arrangement using a model of the earth's interior at the survey location. If the parameter(s) of AVO uncertainty are not acceptable the seismic surveying arrangement is changed, and the AVO uncertainty parameter(s) re-determined for the new acquisition geometry.” [0073] “Hence, the resolution indicates how much of the seismic data will actually be used in arriving at the best solution of a later AVO inversion.” – The sensor array can be adjusted to move or ignore the sensors with weak signals. The sensor array can be adjusted to move or ignore the sensors with weak signals. These are merely repetition of the steps for a different well using historical data.)
selecta reduced number of channels of a second logging tool disposed in the second well from which to transmit a reduced number of well measurements of the second well(Rommel [0057] “The output of step 11 is one or more parameters of AVO uncertainty for the seismic surveying arrangement defined at step 8 at the survey location as modelled by the model chosen at step 7. The parameters of the AVO uncertainty output from step 11 may comprise the resolution, the posterior covariance, or both the resolution and the posterior covariance. Steps 7-11 of the method shown in FIG. 2(a) therefore allow one or more parameters of AVO uncertainty, such as the resolution and/or posterior covariance, to be predicted at the SED phase of the seismic survey.” [0061] “It should be noted that the resolution and posterior covariance are, in general, matrices, The step of comparing the resolution (or posterior covariance) with its threshold may therefore comprise comparing each element of the resolution (or posterior covariance) with a threshold value for that element of the resolution (or posterior covariance), with a "yes" determination being obtained if each element of the resolution (or posterior covariance) is lower than its respective threshold value. Alternatively, the step of comparing the resolution (or posterior covariance) with its threshold may consist of comparing one or more selected elements of the resolution (or posterior covariance) with respective threshold values, rather than performing the comparison for each element of the resolution (or posterior covariance).” – The reference performs analysis to determine which sensor element channels represented in the resolution matrix are less trustworthy. [0073] “From equation (6), the rows of the resolution matrix can be considered filters acting on the true earth model m to give the observed model m.sub.obs as deduced from seismic data d. Ideally, if the observed model m.sub.obs was identical to the true earth model m the diagonal elements of the resolution matrix would be unity and off-diagonal elements would be zero; using the prior model compensates any deviations (see equation (7)). Hence, the resolution indicates how much of the seismic data will actually be used in arriving at the best solution of a later AVO inversion.” – The system only uses data that is reliable, e.g., from reliable channels. Abstract “A method of evaluating a seismic survey to be carried out at a particular survey location comprises choosing an initial seismic surveying arrangement. One or more parameters of AVO (amplitude versus offset) uncertainty are then determined from the seismic surveying arrangement using a model of the earth's interior at the survey location. If the parameter(s) of AVO uncertainty are not acceptable the seismic surveying arrangement is changed, and the AVO uncertainty parameter(s) re-determined for the new acquisition geometry.” [0073] “Hence, the resolution indicates how much of the seismic data will actually be used in arriving at the best solution of a later AVO inversion.” – The sensor array can be adjusted to move or ignore the sensors with weak signals. These are merely repetition of the steps for a different well using historical data.)
generate a control signal to configure the second logging tool to transmit the reduced number of well measurements of the second well. (ALSO FOR CLAIM 1 “transmitting the reduced number of well measurements of the second well from the second logging tool”) (Rommel [0073] “From equation (6), the rows of the resolution matrix can be considered filters acting on the true earth model m to give the observed model m.sub.obs as deduced from seismic data d. Ideally, if the observed model m.sub.obs was identical to the true earth model m the diagonal elements of the resolution matrix would be unity and off-diagonal elements would be zero; using the prior model compensates any deviations (see equation (7)). Hence, the resolution indicates how much of the seismic data will actually be used in arriving at the best solution of a later AVO inversion.” – The system only transmits data that is reliable, e.g., from reliable channels.)
Rommel discusses using modeling to make these determinations (Rommel [0057] “The output of step 11 is one or more parameters of AVO uncertainty for the seismic surveying arrangement defined at step 8 at the survey location as modelled by the model chosen at step 7. The parameters of the AVO uncertainty output from step 11 may comprise the resolution, the posterior covariance, or both the resolution and the posterior covariance. Steps 7-11 of the method shown in FIG. 2(a) therefore allow one or more parameters of AVO uncertainty, such as the resolution and/or posterior covariance, to be predicted at the SED phase of the seismic survey.”), but does not appear to explicitly teach, but Rommel in view of Cella teaches:
train a machine learning system into a trained machine learning system utilizing the training data comprising the channel selection corresponding to the synthetic response as a matched pair of inputs for the machine learning system; generate a final model as the trained machine learning system via the training of the machine learning system, wherein the trained machine learning system in operation selects. generate a final model as the trained machine learning system via the training of the machine learning system, wherein the trained machine learning system in operation selects receive, at the trained machine learning system, utilizing the trained machine learning system, a reduced number of channels of a second logging tool disposed in the second well from which to transmit a reduced number of well measurements of the second well
(Cella [0320] “The data collection system 102 may be configured to take input from a host processing system 112, such as input from an analytic system 4018, which may operate on data from the data collection system 102 and data from other input sources 116 to provide analytic results, which in turn may be provided as a learning feedback input 4012 to the data collection system, such as to assist in configuration and operation of the data collection system 102.” [0321] “Combination of inputs (including selection of what sensors or input sources to turn “on” or “off”) may be performed under the control of machine-based intelligence, such as using a local cognitive input selection system 4004, an optionally remote cognitive input selection system 4114, or a combination of the two. The cognitive input selection systems 4004, 4014 may use intelligence and machine learning capabilities described elsewhere in this disclosure, such as using detected conditions (such as conditions informed by the input sources 116 or sensors), state information (including state information determined by a machine state recognition system 4020 that may determine a state), such as relating to an operational state, an environmental state, a state within a known process or workflow, a state involving a fault or diagnostic condition, or many others. This may include optimization of input selection and configuration based on learning feedback from the learning feedback system 4012, which may include providing training data (such as from the host processing system 112 or from other data collection systems 102 either directly or from the host 112) and may include providing feedback metrics, such as success metrics calculated within the analytic system 4018 of the host processing system 112. For example, if a data stream consisting of a particular combination of sensors and inputs yields positive results in a given set of conditions (such as providing improved pattern recognition, improved prediction, improved diagnosis, improved yield, improved return on investment, improved efficiency, or the like), then metrics relating to such results from the analytic system 4018 can be provided via the learning feedback system 4012 to the cognitive input selection systems 4004, 4014 to help configure future data collection to select that combination in those conditions (allowing other input sources to be de-selected, such as by powering down the other sensors).” – Data collected is processed, and the processed data is used to train the model. In combination with Rommel, this includes taking in the model and seismic data and determining which channels to prioritize based on the analysis. This data can be used by the learning system to train a model.)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claims to modify the manual determination of which signals/channels to prioritize in Rommel by the automation provided by the machine learning system of Cella because the person of ordinary skill in the art would be motivated by the aim of Rommel to predict and mitigate noise levels in seismic signals to an acceptable error level to look to Cella, which teaches how to optimize multi sensor data collection and select less noisy channels using machine learning. (Rommel [0039] “the present invention makes it possible to predict in advance whether a proposed seismic surveying arrangement will allow the AVO parameters to be estimated with an acceptable error level.“; Cella [0009] “These methods and systems include a range of ways for providing improved data include a range of methods and systems for providing improved data collection, as well as methods and systems for deploying increased intelligence at the edge, in the network, and in the cloud or premises of the controller of an industrial environment.” [0010] “a self-organizing collector, including a self-organizing, multi-sensor data collector that can optimize data collection, power and/or yield based on conditions in its environment, a self-organizing storage for a multi-sensor data collector, including self-organizing storage for a multi-sensor data collector for industrial sensor data, a self-organizing network coding for a multi-sensor data network, including self-organizing network coding for a data network that transports data from multiple sensors in an industrial data collection environment.” [0317] “s a result, signal processing applies to almost all disciplines and applications in the industrial environment such as audio and video processing, image processing, wireless communications, process control, industrial automation, financial systems, feature extraction, quality improvements such as noise reduction, image enhancement, and the like.“ [0321] “. For example, if a data stream consisting of a particular combination of sensors and inputs yields positive results in a given set of conditions (such as providing improved pattern recognition, improved prediction, improved diagnosis, improved yield, improved return on investment, improved efficiency, or the like), then metrics relating to such results from the analytic system 4018 can be provided via the learning feedback system 4012 to the cognitive input selection systems 4004, 4014 to help configure future data collection to select that combination in those conditions (allowing other input sources to be de-selected, such as by powering down the other sensors).”)
Rommel in view of Cella teach that machine learning is used to determine which data to transmit, but does not appear to explicitly teach, but Rommel in view of Cella and Logan teaches:
train a machine learning system into a trained machine learning system utilizing the training data comprising the channel selection corresponding to the synthetic response as a matched pair of inputs for the machine learning system; generate a final model as the trained machine learning system via the training of the machine learning system, wherein the trained machine learning system in operation selects a reduced number of channels from which to transmit well measurements based directly on measurement logs instead of based on predicted formation models; generate a final model as the trained machine learning system via the training of the machine learning system, wherein the trained machine learning system in operation selects a reduced number of channels from which to transmit well measurements based directly on measurement logs instead of based on predicted formation models; (Logan [0160] “By being able to operate in a number of different telemetry modes, downhole systems as described in the present examples offer an operator flexibility to operate the system in a preferred manner. For example, the operator can increase the transmission bandwidth of the telemetry tool by operating in the concurrent shared mode, since both the EM and MP telemetry systems are concurrently transmitting telemetry data through separate channels. Or, the operator can increase the reliability and accuracy of the transmission by operating in the concurrent confirmation mode, since the operator has the ability to select the telemetry channel having a higher confidence value. Or, the operator can conserve power by operating in one of MP-only or EM-only telemetry modes. Or the operator can reduce latency for transmission of individual parameters or other blocks of information by operating in a ‘byte-splitting’ mode.” – A reduced subset of channels is selected. [0006] “data acquisition; measuring properties of the surrounding geological formations (e.g. well logging); measuring downhole conditions as drilling progresses; controlling downhole equipment; monitoring status of downhole equipment; directional drilling applications; measuring while drilling (MWD) applications; logging while drilling (LWD) applications; measuring properties of downhole fluids; and the like. A probe may comprise one or more systems for: telemetry of data to the surface; collecting data by way of sensors (e.g. sensors for use in well logging)” – Raw well log data is used.)
receive, at the trained machine learning system, a set of measurement logs corresponding to a second well in a second formation; (Logan [0006] “data acquisition; measuring properties of the surrounding geological formations (e.g. well logging); measuring downhole conditions as drilling progresses; controlling downhole equipment; monitoring status of downhole equipment; directional drilling applications; measuring while drilling (MWD) applications; logging while drilling (LWD) applications; measuring properties of downhole fluids; and the like. A probe may comprise one or more systems for: telemetry of data to the surface; collecting data by way of sensors (e.g. sensors for use in well logging)” – This is a repetition of steps with a different data source)
select, utilizing the trained machine learning system, a reduced number of channels of a second logging tool disposed in the second well from which to transmit a reduced number of well measurements of the second well based directly on the set of measurement logs instead of based on predicted formation models; (Logan [0160] “By being able to operate in a number of different telemetry modes, downhole systems as described in the present examples offer an operator flexibility to operate the system in a preferred manner. For example, the operator can increase the transmission bandwidth of the telemetry tool by operating in the concurrent shared mode, since both the EM and MP telemetry systems are concurrently transmitting telemetry data through separate channels. Or, the operator can increase the reliability and accuracy of the transmission by operating in the concurrent confirmation mode, since the operator has the ability to select the telemetry channel having a higher confidence value. Or, the operator can conserve power by operating in one of MP-only or EM-only telemetry modes. Or the operator can reduce latency for transmission of individual parameters or other blocks of information by operating in a ‘byte-splitting’ mode.” – A reduced subset of channels is selected. [0006] “data acquisition; measuring properties of the surrounding geological formations (e.g. well logging); measuring downhole conditions as drilling progresses; controlling downhole equipment; monitoring status of downhole equipment; directional drilling applications; measuring while drilling (MWD) applications; logging while drilling (LWD) applications; measuring properties of downhole fluids; and the like. A probe may comprise one or more systems for: telemetry of data to the surface; collecting data by way of sensors (e.g. sensors for use in well logging)” – Raw well log data is used.)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claims to modify the manual determination of which signals/channels to prioritize in Rommel by the automation provided by the logging channel discrimination of Logan because the person of ordinary skill in the art would be motivated by the aim of Rommel to predict and mitigate noise levels in seismic signals to an acceptable error level to look to Logan, which teaches how to optimize multi sensor data collection and select less noisy channels using machine learning. (Rommel [0039] “the present invention makes it possible to predict in advance whether a proposed seismic surveying arrangement will allow the AVO parameters to be estimated with an acceptable error level.“; Logan [0239] “As another example, data that might otherwise be transmitted by EM telemetry could be transmitted by MP telemetry instead in cases where rotating noise makes EM reception unduly difficult or unreliable or where horizontal drilling is being performed and overlying formations may impair the effectiveness of EM telemetry. In an example method, data is sent simultaneously by MP telemetry and EM telemetry. The EM telemetry data may be different from the MP telemetry data. A controller of a downhole system 40, 40A, 50 determines that EM telemetry is ineffective or undesired. The controller may make this determination, for example, based on one or more of: a current of an EM signal generator (too high current indicates conductive formations in which EM telemetry may be ineffective); a downlink signal from the surface using any available telemetry mode or predefined pattern of manipulation of drill string rotation and/or mud flow; an inclinometer reading (the system may be configured to not use EM telemetry once the inclination of the BHA is closer to horizontal than a threshold angle); and a measure of rotating noise. Upon determining that EM telemetry is ineffective or undesired the controller may automatically shut off the EM telemetry system and reallocate data being transmitted to the MP telemetry system such that a desired set of data is transmitted by MP telemetry.”)
Claim 1 recites the method performed by claim 9, so claim 1 is rejected for at least the same reasons as claim 9.
Claims 2 and 10
Regarding claim 10, Rommel in view of Cella teaches the features of claim 9 and further teaches:
undertaking the channel selection by generating a resolution matrix based upon the synthetic response, wherein the resolution matrix is indicative of relative importance of each data channel of the set of data channels of the logging tool. (Rommel [0073] “From equation (6), the rows of the resolution matrix can be considered filters acting on the true earth model m to give the observed model m.sub.obs as deduced from seismic data d. Ideally, if the observed model m.sub.obs was identical to the true earth model m the diagonal elements of the resolution matrix would be unity and off-diagonal elements would be zero; using the prior model compensates any deviations (see equation (7)). Hence, the resolution indicates how much of the seismic data will actually be used in arriving at the best solution of a later AVO inversion.” [0061] “It should be noted that the resolution and posterior covariance are, in general, matrices, The step of comparing the resolution (or posterior covariance) with its threshold may therefore comprise comparing each element of the resolution (or posterior covariance) with a threshold value for that element of the resolution (or posterior covariance), with a "yes" determination being obtained if each element of the resolution (or posterior covariance) is lower than its respective threshold value. Alternatively, the step of comparing the resolution (or posterior covariance) with its threshold may consist of comparing one or more selected elements of the resolution (or posterior covariance) with respective threshold values, rather than performing the comparison for each element of the resolution (or posterior covariance).” – A resolution matrix is generated for each channel/signal. [0073] “Hence, the resolution indicates how much of the seismic data will actually be used in arriving at the best solution of a later AVO inversion.” – The matrix is used to determine which data from which channels should be used.)
Claim 2 recites features similar to the features of claim 10 and is rejected for at least the same reasons as claim 10.
Claims 3 and 11
Regarding claim 11, Rommel in view of Cella teaches the feature of claim 10 and further teaches:
determine which data channel of the set of data channels along a diagonal of the resolution matrix has a smallest value as a selected data channel; determine whether the selected data channel has a value less than a predetermined cutoff value; generate a recomputed resolution matrix without the selected data channel in response the value of the selected data channel being determined to be less than the predetermined cutoff value; (Rommel [0073] “From equation (6), the rows of the resolution matrix can be considered filters acting on the true earth model m to give the observed model m.sub.obs as deduced from seismic data d. Ideally, if the observed model m.sub.obs was identical to the true earth model m the diagonal elements of the resolution matrix would be unity and off-diagonal elements would be zero; using the prior model compensates any deviations (see equation (7)). Hence, the resolution indicates how much of the seismic data will actually be used in arriving at the best solution of a later AVO inversion.” [0061] “It should be noted that the resolution and posterior covariance are, in general, matrices, The step of comparing the resolution (or posterior covariance) with its threshold may therefore comprise comparing each element of the resolution (or posterior covariance) with a threshold value for that element of the resolution (or posterior covariance), with a "yes" determination being obtained if each element of the resolution (or posterior covariance) is lower than its respective threshold value. Alternatively, the step of comparing the resolution (or posterior covariance) with its threshold may consist of comparing one or more selected elements of the resolution (or posterior covariance) with respective threshold values, rather than performing the comparison for each element of the resolution (or posterior covariance).” – All of the sensor data channels are selected, including the ones represented as the lowest values. These are compared against a threshold to determine whether the data is included in considerations.)
determine whether a number of data channels of the recomputed resolution matrix is less than a telemetry threshold value; and provide the data channels of the recomputed resolution matrix as the set of data channels of the logging tool in response to the number of data channels of the recomputed resolution matrix being determined to be less than the telemetry threshold value. (Rommel [0065] “For example, step 15 may comprise determining whether further the geologic uncertainty parameter and/or the petrophysical uncertainty parameter each fall below a respective pre-determined threshold value. If this comparison step should show that either of the geologic uncertainty or the petrophysical uncertainty parameter does not meet its design criterion (for example if one or both exceeds their respective pre-determined threshold) the parameters of the seismic surveying arrangement are again be adjusted at step 13, and the simulation repeated.” [0073] “From equation (6), the rows of the resolution matrix can be considered filters acting on the true earth model m to give the observed model m.sub.obs as deduced from seismic data d. Ideally, if the observed model m.sub.obs was identical to the true earth model m the diagonal elements of the resolution matrix would be unity and off-diagonal elements would be zero; using the prior model compensates any deviations (see equation (7)). Hence, the resolution indicates how much of the seismic data will actually be used in arriving at the best solution of a later AVO inversion.” – The data channels are compared with thresholds to determine which channels’ data to use in determinations.)
Regarding claim 3, claim 3 recites features similar to claim 11, so claim 3 is rejected for at least the same reasons as claim 11.
Claims 4 and 12
Regarding claim 12, Rommel and Cella teach the features of claim 10 and further teach:
determine a pair of data channels in an off-diagonal region of the resolution matrix as having a largest value indicating a largest redundancy between a first data channel and a second data channel of the pair of data channels and generating a recomputed resolution matrix without the first data channel or the second data channel in response to a value of an off-diagonal term corresponding to the pair of data channels being determined to be greater than a predetermined cutoff value; (Rommel [0073] “From equation (6), the rows of the resolution matrix can be considered filters acting on the true earth model m to give the observed model m.sub.obs as deduced from seismic data d. Ideally, if the observed model m.sub.obs was identical to the true earth model m the diagonal elements of the resolution matrix would be unity and off-diagonal elements would be zero; using the prior model compensates any deviations (see equation (7)). Hence, the resolution indicates how much of the seismic data will actually be used in arriving at the best solution of a later AVO inversion.” [0061] “It should be noted that the resolution and posterior covariance are, in general, matrices, The step of comparing the resolution (or posterior covariance) with its threshold may therefore comprise comparing each element of the resolution (or posterior covariance) with a threshold value for that element of the resolution (or posterior covariance), with a "yes" determination being obtained if each element of the resolution (or posterior covariance) is lower than its respective threshold value. Alternatively, the step of comparing the resolution (or posterior covariance) with its threshold may consist of comparing one or more selected elements of the resolution (or posterior covariance) with respective threshold values, rather than performing the comparison for each element of the resolution (or posterior covariance).” – All of the sensor data channels are selected, including the ones represented as the highest correlation off-diagonal values. These are compared against a threshold to determine whether the data is included in considerations.)
determine whether a number of data channels of the recomputed resolution matrix is less than a telemetry threshold value; and provide the data channels of the recomputed resolution matrix as the set of data channels of the logging tool when the number of data channels of the recomputed resolution matrix is determined to be less than the telemetry threshold value. (Rommel [0065] “For example, step 15 may comprise determining whether further the geologic uncertainty parameter and/or the petrophysical uncertainty parameter each fall below a respective pre-determined threshold value. If this comparison step should show that either of the geologic uncertainty or the petrophysical uncertainty parameter does not meet its design criterion (for example if one or both exceeds their respective pre-determined threshold) the parameters of the seismic surveying arrangement are again be adjusted at step 13, and the simulation repeated.” [0073] “From equation (6), the rows of the resolution matrix can be considered filters acting on the true earth model m to give the observed model m.sub.obs as deduced from seismic data d. Ideally, if the observed model m.sub.obs was identical to the true earth model m the diagonal elements of the resolution matrix would be unity and off-diagonal elements would be zero; using the prior model compensates any deviations (see equation (7)). Hence, the resolution indicates how much of the seismic data will actually be used in arriving at the best solution of a later AVO inversion.” – The data channels are compared with thresholds to determine which channels’ data to use in determinations.)
Regarding claim 4, claim 4 recites features similar to claim 12, so claim 4 is rejected for at least the same reasons as claim 12.
Claims 5 and 13
Regarding claim 13, Rommel in view of Cella teaches the features of claim 9 and further teaches:
determine whether a total number of synthetic responses and corresponding channel selection is equal to a threshold value selected to correspond to a predetermined amount of model coverage of the final model and output the [results] when it is determined that the total number of synthetic responses and corresponding channel selection is equal to the threshold value.
(Rommel [0060]-[0061] “In a preferred embodiment in which more than one parameter of AVO uncertainty is output at step 11, step 12 consists of comparing each parameter with a respective pre-determined threshold. For example, if the posterior covariance and the resolution are obtained at step 11, step 12 would consist of comparing the resolution with a pre-determined threshold for the resolution, and also comparing the posterior covariance with a pre-determined threshold for the posterior covariance. A "yes" determination would be obtained if both the resolution and the posterior covariance compared satisfactorily with their respective threshold, otherwise a "no" determination would be obtained and the method would then move on to the step 13 of adjusting the survey parameters and repeating the simulation. t should be noted that the resolution and posterior covariance are, in general, matrices, The step of comparing the resolution (or posterior covariance) with its threshold may therefore comprise comparing each element of the resolution (or posterior covariance) with a threshold value for that element of the resolution (or posterior covariance), with a "yes" determination being obtained if each element of the resolution (or posterior covariance) is lower than its respective threshold value.” [0065] “For example, step 15 may comprise determining whether further the geologic uncertainty parameter and/or the petrophysical uncertainty parameter each fall below a respective pre-determined threshold value. If this comparison step should show that either of the geologic uncertainty or the petrophysical uncertainty parameter does not meet its design criterion (for example if one or both exceeds their respective pre-determined threshold) the parameters of the seismic surveying arrangement are again be adjusted at step 13, and the simulation repeated.” – The total number of synthetic responses corresponding to channel selection is equal to a threshold value with the selected channels.)
Rommel discusses using modeling to make these determinations (Rommel [0057] “The output of step 11 is one or more parameters of AVO uncertainty for the seismic surveying arrangement defined at step 8 at the survey location as modelled by the model chosen at step 7. The parameters of the AVO uncertainty output from step 11 may comprise the resolution, the posterior covariance, or both the resolution and the posterior covariance. Steps 7-11 of the method shown in FIG. 2(a) therefore allow one or more parameters of AVO uncertainty, such as the resolution and/or posterior covariance, to be predicted at the SED phase of the seismic survey.”), but does not appear to explicitly teach, but Rommel in view of Cella teaches:
the final model as the trained machine learning system (Cella [0928] “Therefore, the auto encoders may operate as an unsupervised learning model. An auto encoder may be used, for example, for unsupervised learning of efficient codings, such as for dimensionality reduction, for learning generative models of data, and the like. In embodiments, an auto-encoding neural network may be used to self-learn an efficient network coding for transmission of analog sensor data from an industrial machine over one or more networks. In embodiments, an auto-encoding neural network may be used to self-learn an efficient storage approach for storage of streams of analog sensor data from an industrial environment.” [0945] “In embodiments, cascade correlation may be used as an architecture and supervised learning algorithm, supplementing adjustment of the weights in a network of fixed topology. Cascade-correlation may begin with a minimal network, then automatically trains and adds new hidden units one by one, creating a multi-layer structure. Once a new hidden unit has been added to the network, its input-side weights may be frozen. This unit then becomes a permanent feature-detector in the network, available for producing outputs or for creating other, more complex feature detectors. The cascade-correlation architecture may learn quickly, determine its own size and topology, and retain the structures it has built even if the training set changes and requires no back-propagation.” – The Cella reference uses machine learning as an inference model to replace mathematical determinations like the use of the Matrices in Rommel with inferential trained models, the training of which finishes when the output error satisfies a threshold as in supervised and unsupervised learning disclosed in Cella.)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claims to modify the manual determination of which signals/channels to prioritize in Rommel by the automation provided by the machine learning system of Cella because the person of ordinary skill in the art would be motivated by the aim of Rommel to predict and mitigate noise levels in seismic signals to an acceptable error level to look to Cella, which teaches how to optimize multi sensor data collection and select less noisy channels using machine learning. (Rommel [0039] “the present invention makes it possible to predict in advance whether a proposed seismic surveying arrangement will allow the AVO parameters to be estimated with an acceptable error level.“; Cella [0009] “These methods and systems include a range of ways for providing improved data include a range of methods and systems for providing improved data collection, as well as methods and systems for deploying increased intelligence at the edge, in the network, and in the cloud or premises of the controller of an industrial environment.” [0010] “a self-organizing collector, including a self-organizing, multi-sensor data collector that can optimize data collection, power and/or yield based on conditions in its environment, a self-organizing storage for a multi-sensor data collector, including self-organizing storage for a multi-sensor data collector for industrial sensor data, a self-organizing network coding for a multi-sensor data network, including self-organizing network coding for a data network that transports data from multiple sensors in an industrial data collection environment.” [0317] “s a result, signal processing applies to almost all disciplines and applications in the industrial environment such as audio and video processing, image processing, wireless communications, process control, industrial automation, financial systems, feature extraction, quality improvements such as noise reduction, image enhancement, and the like.“ [0321] “. For example, if a data stream consisting of a particular combination of sensors and inputs yields positive results in a given set of conditions (such as providing improved pattern recognition, improved prediction, improved diagnosis, improved yield, improved return on investment, improved efficiency, or the like), then metrics relating to such results from the analytic system 4018 can be provided via the learning feedback system 4012 to the cognitive input selection systems 4004, 4014 to help configure future data collection to select that combination in those conditions (allowing other input sources to be de-selected, such as by powering down the other sensors).”)
Regarding claim 5, claim 5 recites features similar to claim 13, so claim 5 is rejected for at least the same reasons as claim 13.
Claim 6
Regarding claim 6, Rommel in view of Cella teaches the features of claim 5 and further teaches the features of claim 6 which are merely a repetition of features of claim 1 for a different formation. These limitations are rejected in the same manner as claim 1.
Claim 7
Regarding claim 7, Rommel in view of Cella teaches the features of claim 5 and further teaches:
further comprising outputting the final model as the trained machine learning system in response to determining that the total number of synthetic responses and corresponding channel selection is equal to the threshold value. (Cella [0928] “Therefore, the auto encoders may operate as an unsupervised learning model. An auto encoder may be used, for example, for unsupervised learning of efficient codings, such as for dimensionality reduction, for learning generative models of data, and the like. In embodiments, an auto-encoding neural network may be used to self-learn an efficient network coding for transmission of analog sensor data from an industrial machine over one or more networks. In embodiments, an auto-encoding neural network may be used to self-learn an efficient storage approach for storage of streams of analog sensor data from an industrial environment.” [0945] “In embodiments, cascade correlation may be used as an architecture and supervised learning algorithm, supplementing adjustment of the weights in a network of fixed topology. Cascade-correlation may begin with a minimal network, then automatically trains and adds new hidden units one by one, creating a multi-layer structure. Once a new hidden unit has been added to the network, its input-side weights may be frozen. This unit then becomes a permanent feature-detector in the network, available for producing outputs or for creating other, more complex feature detectors. The cascade-correlation architecture may learn quickly, determine its own size and topology, and retain the structures it has built even if the training set changes and requires no back-propagation.” – The Cella reference uses machine learning as an inference model to replace mathematical determinations like the use of the Matrices in Rommel with inferential trained models, the training of which finishes when the output error satisfies a threshold as in supervised and unsupervised learning disclosed in Cella.)
Claims 8 and 14
Regarding claim 14, Rommel in view of Cello teaches the features of claim 9, and further teaches:
receive a measurement log corresponding to a measured characteristic of a second formation; (Rommel [0005] “The travel time of seismic energy from the source 1 to the receiver 6 along a path involving reflection within the earth's interior will depend on, inter alia, the horizontal distance between the source 1 and the receiver 6. The horizontal distance between the source 1 and the receiver 6 is generally known as "offset". It is well-known in seismic surveying to derive information about the earth's structure from the variation with offset of travel time from the source to the receiver. However, as the source-receiver offset varies the amplitude of the energy received at the receiver along a particular reflection path--for example the path involving reflection at the interface 4--will also vary. This variation in amplitude of the acquired seismic energy occurs because a change in source-receiver offset changes the angle of incidence that the seismic energy makes with the interface 4, and this change in angle of incidence alters the ratio between the amplitude of seismic energy transmitted along path 5' and the amplitude of seismic energy reflected along path 5". It is possible to derive further information about the earth's interior from analysis of the variation of amplitude of acquired seismic energy with offset, and this process is known as "AVO inversion". AVO inversion provides information about the difference in elasticity or impedance or velocity and density across an interface within the earth. The differences in elasticity or impedance or velocity and density are therefore known as "AVO parameters". In the present application, the term "AVO uncertainty" will be understood as comprising all distributions of possible AVO parameters that are consistent with a seismic surveying arrangement.” – This teaches that data representing the formation and the devices therein for measuring seismic data re determined and provided for analysis.)
compare, , the measurement log against a set of synthetic responses comprising the synthetic response; determine a matching synthetic response from the set of synthetic responses that matches the measurement log; determine corresponding channel selection paired with the matching synthetic response. (Rommel [0042]-[0049] “Initially, at step 7, the best model of the geologic structure and seismic properties of the earth's interior is made for a desired survey location. The model is constructed using the best available information about the survey location, for example information that has been obtained in previous seismic surveys at the survey location. At step 8 the parameters of a seismic surveying arrangement (or "acquisition geometry") are defined. The parameters of the seismic surveying arrangement may include, for example, the following: number of seismic sources; details of the source array such as the arrangement of the sources and the separation between two adjacent sources (if there is more than one seismic source); the number of seismic receivers; details of the source array such as the arrangement of the receivers and the separation between adjacent receivers (if there is more than one seismic receiver); and the separation between the source or source array and the receiver or receiver array. Next, at step 9, one or more raypaths of seismic energy are simulated. That is, step 9 simulates one or more raypaths that would be obtained if the seismic surveying arrangement defined in step 8 were used to carry out a seismic survey at the survey location, in the light of the best model of the seismic properties of earth's interior at the survey location as defined at step 7. The simulation of raypaths of seismic energy is a known step in the SED phase of a seismic survey, and will not be described in detail here. In outline, however, step 9 may consist of using ray tracing to evaluate the propagation of the seismic wavefield produced by the source array of the seismic surveying arrangement defined at step 8 through the model of the survey location defined at step 7. This will allow the raypaths incident on the receiver array of'the seismic surveying arrangement defined at step 8 to be determined. It should be noted that the present invention does not require a simulation of the amplitude of the seismic energy incident on the receivers of the seismic surveying arrangement. It is sufficient for step 9 to simulate the raypaths of the seismic energy--that is, for step 9 to consist of a kinematic simulation of the seismic data--and it is not necessary to perform a full dynamic simulation that also simulates the amplitude of the seismic data (although in principle a full simulation could be carried out at step 9). – Synthetic logs for traces and their underlying data are generated to determine which channels are to be trusted. [0057] “The output of step 11 is one or more parameters of AVO uncertainty for the seismic surveying arrangement defined at step 8 at the survey location as modelled by the model chosen at step 7. The parameters of the AVO uncertainty output from step 11 may comprise the resolution, the posterior covariance, or both the resolution and the posterior covariance. Steps 7-11 of the method shown in FIG. 2(a) therefore allow one or more parameters of AVO uncertainty, such as the resolution and/or posterior covariance, to be predicted at the SED phase of the seismic survey.” [0061] “It should be noted that the resolution and posterior covariance are, in general, matrices, The step of comparing the resolution (or posterior covariance) with its threshold may therefore comprise comparing each element of the resolution (or posterior covariance) with a threshold value for that element of the resolution (or posterior covariance), with a "yes" determination being obtained if each element of the resolution (or posterior covariance) is lower than its respective threshold value.” – The reference performs analysis to generate a matrix that relates the log data to the channel trustworthiness.)
Rommel discusses using modeling to make these determinations (Rommel [0057] “The output of step 11 is one or more parameters of AVO uncertainty for the seismic surveying arrangement defined at step 8 at the survey location as modelled by the model chosen at step 7. The parameters of the AVO uncertainty output from step 11 may comprise the resolution, the posterior covariance, or both the resolution and the posterior covariance. Steps 7-11 of the method shown in FIG. 2(a) therefore allow one or more parameters of AVO uncertainty, such as the resolution and/or posterior covariance, to be predicted at the SED phase of the seismic survey.”), but does not appear to explicitly teach, but Rommel in view of Cella teaches:
compare, , the measurement log against a set of synthetic responses comprising the synthetic response; determine a matching synthetic response from the set of synthetic responses that matches the measurement log; determine corresponding channel selection paired with the matching synthetic response; and (Cella [0320] “The data collection system 102 may be configured to take input from a host processing system 112, such as input from an analytic system 4018, which may operate on data from the data collection system 102 and data from other input sources 116 to provide analytic results, which in turn may be provided as a learning feedback input 4012 to the data collection system, such as to assist in configuration and operation of the data collection system 102.” [0321] “Combination of inputs (including selection of what sensors or input sources to turn “on” or “off”) may be performed under the control of machine-based intelligence, such as using a local cognitive input selection system 4004, an optionally remote cognitive input selection system 4114, or a combination of the two. The cognitive input selection systems 4004, 4014 may use intelligence and machine learning capabilities described elsewhere in this disclosure, such as using detected conditions (such as conditions informed by the input sources 116 or sensors), state information (including state information determined by a machine state recognition system 4020 that may determine a state), such as relating to an operational state, an environmental state, a state within a known process or workflow, a state involving a fault or diagnostic condition, or many others. This may include optimization of input selection and configuration based on learning feedback from the learning feedback system 4012, which may include providing training data (such as from the host processing system 112 or from other data collection systems 102 either directly or from the host 112) and may include providing feedback metrics, such as success metrics calculated within the analytic system 4018 of the host processing system 112. For example, if a data stream consisting of a particular combination of sensors and inputs yields positive results in a given set of conditions (such as providing improved pattern recognition, improved prediction, improved diagnosis, improved yield, improved return on investment, improved efficiency, or the like), then metrics relating to such results from the analytic system 4018 can be provided via the learning feedback system 4012 to the cognitive input selection systems 4004, 4014 to help configure future data collection to select that combination in those conditions (allowing other input sources to be de-selected, such as by powering down the other sensors).” – Data collected is processed, and the processed data is used to train the model. In combination with Rommel, this includes taking in the model and seismic data and determining which channels to prioritize based on the analysis. This data can be used by the learning system to train a model. The model is then used for inference to determine which channels have low enough noise to be prioritized for data.)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claims to modify the manual determination of which signals/channels to prioritize in Rommel by the automation provided by the machine learning system of Cella because the person of ordinary skill in the art would be motivated by the aim of Rommel to predict and mitigate noise levels in seismic signals to an acceptable error level to look to Cella, which teaches how to optimize multi sensor data collection and select less noisy channels using machine learning. (Rommel [0039] “the present invention makes it possible to predict in advance whether a proposed seismic surveying arrangement will allow the AVO parameters to be estimated with an acceptable error level.“; Cella [0009] “These methods and systems include a range of ways for providing improved data include a range of methods and systems for providing improved data collection, as well as methods and systems for deploying increased intelligence at the edge, in the network, and in the cloud or premises of the controller of an industrial environment.” [0010] “a self-organizing collector, including a self-organizing, multi-sensor data collector that can optimize data collection, power and/or yield based on conditions in its environment, a self-organizing storage for a multi-sensor data collector, including self-organizing storage for a multi-sensor data collector for industrial sensor data, a self-organizing network coding for a multi-sensor data network, including self-organizing network coding for a data network that transports data from multiple sensors in an industrial data collection environment.” [0317] “As a result, signal processing applies to almost all disciplines and applications in the industrial environment such as audio and video processing, image processing, wireless communications, process control, industrial automation, financial systems, feature extraction, quality improvements such as noise reduction, image enhancement, and the like.“ [0321] “. For example, if a data stream consisting of a particular combination of sensors and inputs yields positive results in a given set of conditions (such as providing improved pattern recognition, improved prediction, improved diagnosis, improved yield, improved return on investment, improved efficiency, or the like), then metrics relating to such results from the analytic system 4018 can be provided via the learning feedback system 4012 to the cognitive input selection systems 4004, 4014 to help configure future data collection to select that combination in those conditions (allowing other input sources to be de-selected, such as by powering down the other sensors).”)
Claim 15
Regarding claim 15, Rommel teaches:
A system comprising: a processing system (Rommel [0075] “The apparatus 16 comprises a programmable data processor 17 with a program memory 18, for instance in the form of a read only memory (ROM), storing a program for controlling the data processor 17 to simulate and process seismic data by a method of the invention.” - Computer)
configured to determine which data channels of a downhole tool to prioritize as a portion of measurements to use for processing and/or decision making based on received measurement logs and their correspondence to respective synthetic responses : (Rommel [0005] “The travel time of seismic energy from the source 1 to the receiver 6 along a path involving reflection within the earth's interior will depend on, inter alia, the horizontal distance between the source 1 and the receiver 6. The horizontal distance between the source 1 and the receiver 6 is generally known as "offset". It is well-known in seismic surveying to derive information about the earth's structure from the variation with offset of travel time from the source to the receiver. However, as the source-receiver offset varies the amplitude of the energy received at the receiver along a particular reflection path--for example the path involving reflection at the interface 4--will also vary. This variation in amplitude of the acquired seismic energy occurs because a change in source-receiver offset changes the angle of incidence that the seismic energy makes with the interface 4, and this change in angle of incidence alters the ratio between the amplitude of seismic energy transmitted along path 5' and the amplitude of seismic energy reflected along path 5". It is possible to derive further information about the earth's interior from analysis of the variation of amplitude of acquired seismic energy with offset, and this process is known as "AVO inversion". AVO inversion provides information about the difference in elasticity or impedance or velocity and density across an interface within the earth. The differences in elasticity or impedance or velocity and density are therefore known as "AVO parameters". In the present application, the term "AVO uncertainty" will be understood as comprising all distributions of possible AVO parameters that are consistent with a seismic surveying arrangement.” – This teaches that data representing the formation and the devices therein for measuring seismic data are determined and provided for analysis.)
select, transmit an instruction to transmit the data channels that were selected; (Rommel [0073] “From equation (6), the rows of the resolution matrix can be considered filters acting on the true earth model m to give the observed model m.sub.obs as deduced from seismic data d. Ideally, if the observed model m.sub.obs was identical to the true earth model m the diagonal elements of the resolution matrix would be unity and off-diagonal elements would be zero; using the prior model compensates any deviations (see equation (7)). Hence, the resolution indicates how much of the seismic data will actually be used in arriving at the best solution of a later AVO inversion.” – Because some sensors are not properly aligned to provide a noiseless signal, the channels with the data that is determined to be less noisy is prioritized.)
receive an update on a formation model and/or a drilling condition based on new information acquired during operation; and (Rommel [0042]-[0050] “Initially, at step 7, the best model of the geologic structure and seismic properties of the earth's interior is made for a desired survey location. The model is constructed using the best available information about the survey location, for example information that has been obtained in previous seismic surveys at the survey location. At step 8 the parameters of a seismic surveying arrangement (or "acquisition geometry") are defined. The parameters of the seismic surveying arrangement may include, for example, the following: number of seismic sources; details of the source array such as the arrangement of the sources and the separation between two adjacent sources (if there is more than one seismic source); the number of seismic receivers; details of the source array such as the arrangement of the receivers and the separation between adjacent receivers (if there is more than one seismic receiver); and the separation between the source or source array and the receiver or receiver array. Next, at step 9, one or more raypaths of seismic energy are simulated. That is, step 9 simulates one or more raypaths that would be obtained if the seismic surveying arrangement defined in step 8 were used to carry out a seismic survey at the survey location, in the light of the best model of the seismic properties of earth's interior at the survey location as defined at step 7. The simulation of raypaths of seismic energy is a known step in the SED phase of a seismic survey, and will not be described in detail here. In outline, however, step 9 may consist of using ray tracing to evaluate the propagation of the seismic wavefield produced by the source array of the seismic surveying arrangement defined at step 8 through the model of the survey location defined at step 7. This will allow the raypaths incident on the receiver array of'the seismic surveying arrangement defined at step 8 to be determined.“
recompute which of the data channels of the downhole tool to select as corresponding a second portion of measurements to use for processing and/or decision making based on the update on the formation model and/or the drilling condition. (Rommel [0042]-[0049] “Initially, at step 7, the best model of the geologic structure and seismic properties of the earth's interior is made for a desired survey location. The model is constructed using the best available information about the survey location, for example information that has been obtained in previous seismic surveys at the survey location. At step 8 the parameters of a seismic surveying arrangement (or "acquisition geometry") are defined. The parameters of the seismic surveying arrangement may include, for example, the following: number of seismic sources; details of the source array such as the arrangement of the sources and the separation between two adjacent sources (if there is more than one seismic source); the number of seismic receivers; details of the source array such as the arrangement of the receivers and the separation between adjacent receivers (if there is more than one seismic receiver); and the separation between the source or source array and the receiver or receiver array. Next, at step 9, one or more raypaths of seismic energy are simulated. That is, step 9 simulates one or more raypaths that would be obtained if the seismic surveying arrangement defined in step 8 were used to carry out a seismic survey at the survey location, in the light of the best model of the seismic properties of earth's interior at the survey location as defined at step 7. The simulation of raypaths of seismic energy is a known step in the SED phase of a seismic survey, and will not be described in detail here. In outline, however, step 9 may consist of using ray tracing to evaluate the propagation of the seismic wavefield produced by the source array of the seismic surveying arrangement defined at step 8 through the model of the survey location defined at step 7. This will allow the raypaths incident on the receiver array of'the seismic surveying arrangement defined at step 8 to be determined. It should be noted that the present invention does not require a simulation of the amplitude of the seismic energy incident on the receivers of the seismic surveying arrangement. It is sufficient for step 9 to simulate the raypaths of the seismic energy--that is, for step 9 to consist of a kinematic simulation of the seismic data--and it is not necessary to perform a full dynamic simulation that also simulates the amplitude of the seismic data (although in principle a full simulation could be carried out at step 9). – Synthetic logs for traces and their underlying data are generated to determine which channels are to be trusted. [0057] “The output of step 11 is one or more parameters of AVO uncertainty for the seismic surveying arrangement defined at step 8 at the survey location as modelled by the model chosen at step 7. The parameters of the AVO uncertainty output from step 11 may comprise the resolution, the posterior covariance, or both the resolution and the posterior covariance. Steps 7-11 of the method shown in FIG. 2(a) therefore allow one or more parameters of AVO uncertainty, such as the resolution and/or posterior covariance, to be predicted at the SED phase of the seismic survey.” [0061] “It should be noted that the resolution and posterior covariance are, in general, matrices, The step of comparing the resolution (or posterior covariance) with its threshold may therefore comprise comparing each element of the resolution (or posterior covariance) with a threshold value for that element of the resolution (or posterior covariance), with a "yes" determination being obtained if each element of the resolution (or posterior covariance) is lower than its respective threshold value. Alternatively, the step of comparing the resolution (or posterior covariance) with its threshold may consist of comparing one or more selected elements of the resolution (or posterior covariance) with respective threshold values, rather than performing the comparison for each element of the resolution (or posterior covariance).” – The reference performs analysis to determine which sensor element channels represented in the resolution matrix are less trustworthy. [0073] “From equation (6), the rows of the resolution matrix can be considered filters acting on the true earth model m to give the observed model m.sub.obs as deduced from seismic data d. Ideally, if the observed model m.sub.obs was identical to the true earth model m the diagonal elements of the resolution matrix would be unity and off-diagonal elements would be zero; using the prior model compensates any deviations (see equation (7)). Hence, the resolution indicates how much of the seismic data will actually be used in arriving at the best solution of a later AVO inversion.” – The system only uses data that is reliable, e.g., from reliable channels. Abstract “A method of evaluating a seismic survey to be carried out at a particular survey location comprises choosing an initial seismic surveying arrangement. One or more parameters of AVO (amplitude versus offset) uncertainty are then determined from the seismic surveying arrangement using a model of the earth's interior at the survey location. If the parameter(s) of AVO uncertainty are not acceptable the seismic surveying arrangement is changed, and the AVO uncertainty parameter(s) re-determined for the new acquisition geometry.” [0073] “Hence, the resolution indicates how much of the seismic data will actually be used in arriving at the best solution of a later AVO inversion.” – The sensor array can be adjusted to move or ignore the sensors with weak signals.)
Rommel discusses using modeling to make these determinations (Rommel [0057] “The output of step 11 is one or more parameters of AVO uncertainty for the seismic surveying arrangement defined at step 8 at the survey location as modelled by the model chosen at step 7. The parameters of the AVO uncertainty output from step 11 may comprise the resolution, the posterior covariance, or both the resolution and the posterior covariance. Steps 7-11 of the method shown in FIG. 2(a) therefore allow one or more parameters of AVO uncertainty, such as the resolution and/or posterior covariance, to be predicted at the SED phase of the seismic survey.”), but does not appear to explicitly teach, but Rommel in view of Cella teaches:
A system comprising: a processing system comprising a trained machine learning model. […] select,utilizing the trained machine learning model transmit an instruction to transmit the data channels that were selected; (Cella [0320] “The data collection system 102 may be configured to take input from a host processing system 112, such as input from an analytic system 4018, which may operate on data from the data collection system 102 and data from other input sources 116 to provide analytic results, which in turn may be provided as a learning feedback input 4012 to the data collection system, such as to assist in configuration and operation of the data collection system 102.” [0321] “Combination of inputs (including selection of what sensors or input sources to turn “on” or “off”) may be performed under the control of machine-based intelligence, such as using a local cognitive input selection system 4004, an optionally remote cognitive input selection system 4114, or a combination of the two. The cognitive input selection systems 4004, 4014 may use intelligence and machine learning capabilities described elsewhere in this disclosure, such as using detected conditions (such as conditions informed by the input sources 116 or sensors), state information (including state information determined by a machine state recognition system 4020 that may determine a state), such as relating to an operational state, an environmental state, a state within a known process or workflow, a state involving a fault or diagnostic condition, or many others. This may include optimization of input selection and configuration based on learning feedback from the learning feedback system 4012, which may include providing training data (such as from the host processing system 112 or from other data collection systems 102 either directly or from the host 112) and may include providing feedback metrics, such as success metrics calculated within the analytic system 4018 of the host processing system 112. For example, if a data stream consisting of a particular combination of sensors and inputs yields positive results in a given set of conditions (such as providing improved pattern recognition, improved prediction, improved diagnosis, improved yield, improved return on investment, improved efficiency, or the like), then metrics relating to such results from the analytic system 4018 can be provided via the learning feedback system 4012 to the cognitive input selection systems 4004, 4014 to help configure future data collection to select that combination in those conditions (allowing other input sources to be de-selected, such as by powering down the other sensors).” – Data collected is processed, and the processed data is used to train the model. In combination with Rommel, this includes taking in the model and seismic data and determining which channels to prioritize based on the analysis. This data can be used by the learning system to train a model.)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claims to modify the manual determination of which signals/channels to prioritize in Rommel by the automation provided by the machine learning system of Cella because the person of ordinary skill in the art would be motivated by the aim of Rommel to predict and mitigate noise levels in seismic signals to an acceptable error level to look to Cella, which teaches how to optimize multi sensor data collection and select less noisy channels using machine learning. (Rommel [0039] “the present invention makes it possible to predict in advance whether a proposed seismic surveying arrangement will allow the AVO parameters to be estimated with an acceptable error level.“; Cella [0009] “These methods and systems include a range of ways for providing improved data include a range of methods and systems for providing improved data collection, as well as methods and systems for deploying increased intelligence at the edge, in the network, and in the cloud or premises of the controller of an industrial environment.” [0010] “a self-organizing collector, including a self-organizing, multi-sensor data collector that can optimize data collection, power and/or yield based on conditions in its environment, a self-organizing storage for a multi-sensor data collector, including self-organizing storage for a multi-sensor data collector for industrial sensor data, a self-organizing network coding for a multi-sensor data network, including self-organizing network coding for a data network that transports data from multiple sensors in an industrial data collection environment.” [0317] “s a result, signal processing applies to almost all disciplines and applications in the industrial environment such as audio and video processing, image processing, wireless communications, process control, industrial automation, financial systems, feature extraction, quality improvements such as noise reduction, image enhancement, and the like.“ [0321] “. For example, if a data stream consisting of a particular combination of sensors and inputs yields positive results in a given set of conditions (such as providing improved pattern recognition, improved prediction, improved diagnosis, improved yield, improved return on investment, improved efficiency, or the like), then metrics relating to such results from the analytic system 4018 can be provided via the learning feedback system 4012 to the cognitive input selection systems 4004, 4014 to help configure future data collection to select that combination in those conditions (allowing other input sources to be de-selected, such as by powering down the other sensors).”)
Rommel in view of Cella teach that machine learning is used to determine which data to transmit, but does not appear to explicitly teach, but Rommel in view of Cella and Logan teaches:
A system comprising: a processing system comprising a trained machine learning model. […] receive a set of measurement logs corresponding to a second well in a second formation […] select, utilizing the trained machine learning model, a reduced number of channels of a logging tool disposed in a well from which to transmit a reduced number of well measurements of the well based directly on the set of measurement logs instead of based on predicted formation models: transmit an instruction to the downhole tool to configure the downhole tool to transmit the reduced number of measurements using the data channels that were selected; (Logan [0160] “By being able to operate in a number of different telemetry modes, downhole systems as described in the present examples offer an operator flexibility to operate the system in a preferred manner. For example, the operator can increase the transmission bandwidth of the telemetry tool by operating in the concurrent shared mode, since both the EM and MP telemetry systems are concurrently transmitting telemetry data through separate channels. Or, the operator can increase the reliability and accuracy of the transmission by operating in the concurrent confirmation mode, since the operator has the ability to select the telemetry channel having a higher confidence value. Or, the operator can conserve power by operating in one of MP-only or EM-only telemetry modes. Or the operator can reduce latency for transmission of individual parameters or other blocks of information by operating in a ‘byte-splitting’ mode.” – A reduced subset of channels is selected. [0006] “data acquisition; measuring properties of the surrounding geological formations (e.g. well logging); measuring downhole conditions as drilling progresses; controlling downhole equipment; monitoring status of downhole equipment; directional drilling applications; measuring while drilling (MWD) applications; logging while drilling (LWD) applications; measuring properties of downhole fluids; and the like. A probe may comprise one or more systems for: telemetry of data to the surface; collecting data by way of sensors (e.g. sensors for use in well logging)” – Raw well log data is used.)
Claim 19
Regarding claim 19, Rommel in view of Cella and Logan teaches the features of claim 15, and further teaches:
wherein the trained machine learning model is trained via a training dataset generated by computing synthetic logs for a given formation model and performing automated channel selection based on based on a data resolution technique, generated by computing the synthetic logs for the given formation model and a first received input corresponding to first manually selected channels, or generated by measurement logs and a second received input corresponding to second manually selected channels(Cella [0320] “The data collection system 102 may be configured to take input from a host processing system 112, such as input from an analytic system 4018, which may operate on data from the data collection system 102 and data from other input sources 116 to provide analytic results, which in turn may be provided as a learning feedback input 4012 to the data collection system, such as to assist in configuration and operation of the data collection system 102.” [0321] “Combination of inputs (including selection of what sensors or input sources to turn “on” or “off”) may be performed under the control of machine-based intelligence, such as using a local cognitive input selection system 4004, an optionally remote cognitive input selection system 4114, or a combination of the two. The cognitive input selection systems 4004, 4014 may use intelligence and machine learning capabilities described elsewhere in this disclosure, such as using detected conditions (such as conditions informed by the input sources 116 or sensors), state information (including state information determined by a machine state recognition system 4020 that may determine a state), such as relating to an operational state, an environmental state, a state within a known process or workflow, a state involving a fault or diagnostic condition, or many others. This may include optimization of input selection and configuration based on learning feedback from the learning feedback system 4012, which may include providing training data (such as from the host processing system 112 or from other data collection systems 102 either directly or from the host 112) and may include providing feedback metrics, such as success metrics calculated within the analytic system 4018 of the host processing system 112. For example, if a data stream consisting of a particular combination of sensors and inputs yields positive results in a given set of conditions (such as providing improved pattern recognition, improved prediction, improved diagnosis, improved yield, improved return on investment, improved efficiency, or the like), then metrics relating to such results from the analytic system 4018 can be provided via the learning feedback system 4012 to the cognitive input selection systems 4004, 4014 to help configure future data collection to select that combination in those conditions (allowing other input sources to be de-selected, such as by powering down the other sensors).” – Data collected is processed, and the processed data is used to train the model. In combination with Rommel, this includes taking in the model and seismic data and determining which channels to prioritize based on the analysis. This data is used by the learning system to train a model to automate this otherwise manual determination. The data from a second well is used to determine which channels to transmit based on the training from the first well.)
Claim 20: Rommel, Cella, Logan, and Kusuma
Claim(s) 20 is rejected under 35 U.S.C. 103 as being unpatentable over US 2003/0193837 A1 to Rommel (Rommel) in view of US 2020/0103894 A1 to Cella et al. (Cella), US 2022/0333483 A1 to Logan et al. (Logan), and US 2011/0050452 A1 to Kusuma et al. (Kusuma).
Claim 20
Regarding claim 20, Rommel in view of Cella and Logan teaches the features of claim 15, and further teaches:
wherein the processing system is further configured to select which data channels of the downhole tool or another downhole tool to prioritize. (Rommel [0073] “From equation (6), the rows of the resolution matrix can be considered filters acting on the true earth model m to give the observed model m.sub.obs as deduced from seismic data d. Ideally, if the observed model m.sub.obs was identical to the true earth model m the diagonal elements of the resolution matrix would be unity and off-diagonal elements would be zero; using the prior model compensates any deviations (see equation (7)). Hence, the resolution indicates how much of the seismic data will actually be used in arriving at the best solution of a later AVO inversion.” Cella [0211] “In embodiments, local machine learning may turn on or off one or more sensors in a multi-sensor data collector 102 in permutations over time, while tracking success outcomes such as contributing to success in predicting a failure, contributing to a performance indicator (such as efficiency, effectiveness, return on investment, yield, or the like), contributing to optimization of one or more parameters, identification of a pattern (such as relating to a threat, a failure mode, a success mode, or the like) or the like.” – Both references teach that sensors are prioritized based on the determinations of the machine learning model based on the training data that utilizes the resolution matrices.)
While Rommel, Cella, and Logan concern seismic/oil and gas determinations (Rommel [0004] “In practice the earth's interior contains a large number of structures that act as partial reflectors of seismic energy. When the source 1 is actuated to emit a pulse of seismic energy, the energy acquired at the receiver 6 will contain "events" arising from reflection at a number of different reflectors within the earth.” Abstract “A method of evaluating a seismic survey to be carried out at a particular survey location comprises choosing an initial seismic surveying arrangement. One or more parameters of AVO (amplitude versus offset) uncertainty are then determined from the seismic surveying arrangement using a model of the earth's interior at the survey location. If the parameter(s) of AVO uncertainty are not acceptable the seismic surveying arrangement is changed, and the AVO uncertainty parameter(s) re-determined for the new acquisition geometry.”; Cella [0309] “In embodiments, the platform 100 may include the local data collection system 102 deployed in the environment 104 to monitor signals from marine industrial equipment, marine diesel engines, shipbuilding, oil and gas plants, refineries, petrochemical plant, ballast water treatment solutions, marine pumps and turbines, and the like.”), Rommel in view of Cella do not appear to explicitly teach, but Rommel in view of Cella and Kusuma teach:
wherein the processing system is internal to the downhole tool, wherein the processing system is further configured to select which data channels of the downhole tool or another downhole tool to prioritize. (Kusuma [0028] “In the present invention, the transceiver 16A in the wellbore instruments, and the controller 27 in one or more of the repeaters 22A may be programmer to reconfigure the telemetry format used to communicate measurement signals and command signals in response to factors such as the actual capacity of the telemetry channel (e.g., the wired drill pipe channel and the mud modulation telemetry channel) and the importance of continuity and timing ("priority") of the particular signals to be transmitted in either direction. Such programming may include allocating selected portions of each buffer 25, 16B for particular types of signals based on the assigned signal priority. The telemetry format may be selected to interrogate signals from such allocated buffer portions for communication using reconfigurable priority selection techniques. The following description provides examples of such telemetry format and/or signal priority reconfiguration.”)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claims to modify the determinations of which data to transmit and account for from which sensors in Rommel by the downhole placement of the telemetry determination computing element of Kusuma because the person of ordinary skill in the art would be motivated by the aim of Rommel to use downhole data in seismic determinations to look to Kusuma, which optimizes the use of the data channels for seismic data determinations and transmission. (Rommel [0022] ” The model covariance may be estimated from, for example borehole seismic data or vertical seismic profile (VSP) seismic data covering the survey location, or from petrophysical assumptions about the survey location. The noise covariance may be estimated from, for example, assumptions about random noise in the data d, and these assumptions can be based on other data acquired at the survey location provided that the earlier data are sufficiently oversampled to allow separation of the data into their signal and noise components, for example according to the method disclosed in co-pending UK patent application No 0114744.6.”; Kusuma [0009] “Even when using multiple data communication systems, e.g., both wired drill pipe and mud flow modulation (or electromagnetic), the volume of data generated by typical MWD/LWD instrument configurations is such that optimized use of the data communication channels is desirable. The present invention addresses various forms of data communication to optimize use of available communication channels.”)
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.
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
(Current Auction)
838 Inc. "An Assessment of the Various Types of Real-Time Data Monitoring Systems Available for Offshore Oil and Gas Operations". 2014 (Year: 2014) (Teaches general background for downhole tool monitoring)
Rodriguez, Joaquin."Communications System for Down-Hole Measurements." Journal of Applied Research and Technology, Universidad Nacional Autonoma de Mexico, 2013. (Year: 2013) (Teaches techniques for managing downhole data)
(Prior Action)
US 2018/0292563 A1 to Zhong et al. (Teaches determining reliability of sensors in downhole tool)
US 2003/0220744 A1 to Schonewille (Teaches using a frequency matrix to attenuate multiples of signals)
US 2006/0167784 A1 to Hoffberg (Teaches prioritization schema for communication channels)
US 2006/0133207 A1 to Vossen et al. (Teaches calibration of sensors to using AVO)
US 2004/0000910 A1 to Tryggvason (Teaches using matrices for seismic calculations of density)
US 2024/0240551 A1 to Omar et al. (Teaches prioritizing sensors for seismic determinations)
US 2024/0275608 A1 to Cook et al. (Teaches a telemetry system that uses machine learning for prioritization)
US 2008/0078544 A1 to Christian et al. (Teaches downhole tool arrangements and different channels of downhole data)
US 2010/0194586 A1 to Tjhang et al. (Teaches selecting different telemetry schemes for downhole tools)
US 2021/0087927 A1 to Miller et al. (Teaches automated switching of telemetry modes for downhole tools)
US 2020/0088028 A1 to Benson (Teaches downhole tool telemetry noise reduction methods)
US 2018/0135408 A1 to Cooley et al. (Teaches a specialized telemetry system for a downhole tool)
US 2017/0370202 A1 to Tegeler et al. (Teaches a downhole telemetry device that saves power by alternatively activating or deactivating elements, such as sensors)
US 2017/0191359 A1 to Dursun et al. (Teaches a downhole telemetry system that transmits only the most important data e.g., from the most important sensors/channels)
US 2016/0032714 A1 to Rao et al. (Teaches a downhole telemetry system that prioritizes different messages)
US 2016/0003035 A1 to Logan et al. (Teaches a downhole tool with manifold telemetry subsystems for selective/prioritized transmission of data)
US 2014/0290941 A1 to Villareal et al. (Teaches sample capture prioritization in downhole telemetry tools)
US 2014/0286538 A1 to Yu et al. (Teaches a downhole telemetry unit with data transmission prioritization)
US 2014/0240141 A1 to Logan et al. (Teaches a multi-sensor, downhole telemetry system with prioritization of specified data)
US 2010/0195441 A1 to Camwell et al. (Teaches specialized telemetry encoding for tools in wells)
US 2009/0267790 A1 to Hall et al. (Teaches changing communication priorities for different types of well data)
US 2007/0153629 A1 to Drumheller et al. (Teaches isolating telemetry signals in downhole systems)
US 2007/0126594 A1 to Atkinson et al. (Teaches a borehole telemetry system)
US 2007/0057811 A1 to Mehta (Teaches selective downhole telemetry bandwidth allocation to a downhole component)
US 2006/0232438 A1 to Golla et al. (Teaches a downhole telemetry system that alternates between transmitting compressed and uncompressed data)
US 2005/0046592 A1 to Cooper et al. (Teaches prioritizing data transmitted from a downhole telemetry system)
US 2004/0164876 A1 to Krueger (Teaches modulating tones to control bandwidth allocation for downhole telemetry systems)
US 2003/0151977 A1 to Shah et al. (Teaches a multichannel downhole telemetry system that gives better, less available signal paths to more crucial downhole data)
US 2002/0101359 A1 to Huckaba et al. (Teaches dynamic bandwidth allocation to different downhole tool devices for telemetry)
US 5,560,367 A to Haardt et al. (Teaches matrix-based analysis of multichannel detections)
US 6,636,809 B1 to Herrmann (Teaches using a matrix to separate signals)
US 7,295,490 B1 to Chiu et al. (Teaches phase encoding of seismic data)
US 5,684,693 A to Li (Teaches compression of downhole data for efficient transmission)
US 5,833,623 A to Mann et al. (Teaches channel management in an implantable device)
US 7,990,282 B2 to Huang et al. (Teaches a borehole telemetry system)
US 6,552,665 B1 to Miyamae et al. (Teaches a telemetry system for borehole logging tools that optimizes transmission of data from sensors, sometimes prioritizing log data)
US 4,736,204 A to Davison (Teaches a downhole telemetry system that prioritizes certain data)
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JAY MICHAEL WHITE whose telephone number is (571)272-7073. The examiner can normally be reached Mon-Fri 11:00-7:00 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, Ryan Pitaro can be reached at (571) 272-4071. 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.
/J.M.W./Examiner, Art Unit 2188
/RYAN F PITARO/Supervisory Patent Examiner, Art Unit 2188
Prosecution Insights