DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of Claims
This Office Action is in response to the communication filed on 09 Jan 2026.
Claims 1-16 and 18-20 are being considered on the merits.
Information Disclosure Statement
The information disclosure statements (IDS) submitted on 09 February 2026 has been considered. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, initialed and dated copies of Applicant's IDS forms 1449 are attached to the instant Office action.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 16 recites the limitation "the combination" in the final limitation of the claim. There is insufficient antecedent basis for this limitation in the claim.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim 16 is rejected under 35 U.S.C. 102(1)(2) as being anticipated by Cella, et. al. (US 2019/0339688 A1; hereinafter, “Cella”).
Regarding Claim 16, Cella teaches:
A system, comprising: a processor in communication with one or more sensors, (Cella, para. 0422: “Methods and systems are disclosed herein for a remotely organized universal data collector that can power up and down sensor interfaces based on need and/or conditions identified in an industrial data collection environment. For example, interfaces can recognize what sensors are available and interfaces and/or processors can be turned on to take input from such sensors, including hardware interfaces that allow the sensors to plug in to the data collector, wireless data interfaces (such as where the collector can ping the sensor, optionally providing some power via an interrogation signal), and software interfaces (such as for handling particular types of data).”) wherein the processor is programmed to: receive data including one or more of real-time current information, real-time voltage information, or real-time vibrational information from a run-time device, (Cella, para. 0856: “The criteria may include a sensor's detection values at certain frequencies or phases relative to a timer signal where the frequencies or phases of interest may be based on the equipment geometry, equipment control schemes, system input, historical data, current operating conditions, and/or an anticipated response. The criteria may include a sensor's detection values at certain frequencies or phases relative to detection values of a second sensor. The criteria may include signal strength at certain resonant frequencies/harmonics relative to detection values associated with a system tachometer or anticipated based on equipment geometry and operation conditions. Criteria may include a predetermined peak value for a detection value from a specific sensor, a cumulative value of a sensor's corresponding detection value over time, a change in peak value, a rate of change in a peak value, and/or an accumulated value (e.g., a time spent above/below a threshold value, a weighted time spent above/below one or more threshold values, and/or an area of the detected value above/below one or more threshold values). The criteria may comprise combinations of data from different sensors such as relative values, relative changes in value, relative rates of change in value, relative values over time, and the like. The relative criteria may change with other data or information such as process stage, type of product being processed, type of equipment, ambient temperature and humidity, external vibrations from other equipment, and the like.”)
wherein the run-time device is an actuator or electric dive; (Cella, para. 0607: “In embodiments, a system for data collection that applies smart band data collection templates may be applied to an industrial environment, such as ball screw actuators in an automated production environment. Smart band analysis may be applied to ball screw actuators in industrial environments such as precision manufacturing or positioning applications (e.g., semiconductor photolithography machines, and the like).”)
utilizing a trained machine learning model and the data as an input to the trained machine learning model, (Cella, para. 0856, supra) output a sound prediction associated with estimated sound emitted from the run-time device; and (Cella, para. 0042 and 0050: “The mobile devices include one or more sensors that may be configured to record state-related measurements of the target, for example, based on vibrational, temperature, electrical, magnetic, sound, and/or other measurements. The data captured using some or all of these mobile devices may be processed by intelligent systems onboard those mobile devices and/or at a server in communication with those mobile devices over a network. The intelligent systems include intelligence for processing the data captured using the respective mobile devices. Processing the data can, for example, include identifying a state of a target for which measurements were recorded by comparing the state-related measurements from the wearable device against information stored in a database, which may, for example, be part of a knowledge base associated with the industrial environment” “The memory further includes instructions executable by the processor to record the one or more values; compare the recorded one or more values to corresponding predicted values and to generate a variance data set based on the comparison of the recorded one or more values and the corresponding predicted values.” Examiner notes that Cella teaches recording of sound as well as corresponding predicted values (i.e. a predicted sound))
utilizing the trained machine learning model and the combination as the input to the trained machine learning model, (Cella, para. 0856, supra. Examiner notes for examination purposes only “the combination” is interpreted to mean a combination of data) output a torque prediction associated with the run-time device, (Cella, para. 0389 and 0856: “In embodiments, the local data collection system 102 may include multiple sensors such as, without limitation, a temperature sensor, a pressure sensor, a torque sensor, a flow sensor, a heat sensor, a smoke sensor, an arc sensor, a radiation sensor, a position sensor, an acceleration sensor, a strain sensor, a pressure cycle sensor, a pressure sensor, an air temperature sensor, and the like.” “The criteria may include a sensor's detection values at certain frequencies or phases relative to a timer signal where the frequencies or phases of interest may be based on the equipment geometry, equipment control schemes, system input, historical data, current operating conditions, and/or an anticipated response.”).
wherein the torque prediction is utilized to at least diagnose the run-time device. (Cella, para. 0013: “Methods and systems are provided herein for data collection in industrial environments, as well as for improved methods and systems for using collected data to provide improved monitoring, control, and intelligent diagnosis of problems and intelligent optimization of operations in various heavy industrial environments.” Examiner notes Cella teaches examination and anticipated response of torque as set forth above as well as the use of such data for diagnoses of problems).
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 1-15 and 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Cella, in view of H. C. Siu, J. Sloboda, R. J. McKindles and L. A. Stirling, ("A Neural Network Estimation of Ankle Torques From Electromyography and Accelerometry," in IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 29, pp. 1624-1633, 2021, doi: 10.1109/TNSRE.2021.3104761.; hereinafter, “Siu”).
Regarding Claim 1, Cella teaches a computer-implemented method, comprising:
receiving current information, voltage information, vibrational information, and sound information from a first plurality of sensors (Cella, para. 0015: “Methods and systems are disclosed herein for training artificial intelligence (“AI”) models based on industry-specific feedback, including training an AI model based on industry-specific feedback that reflects a measure of utilization, yield, or impact, where the AI model operates on sensor data from an industrial environment; for an industrial IoT distributed ledger, including a distributed ledger supporting the tracking of transactions executed in an automated data marketplace for industrial IoT data; for a network-sensitive collector, including a network condition-sensitive, self-organizing, multi-sensor data collector that can optimize based on bandwidth, quality of service, pricing, and/or other network conditions; for a remotely organized universal data collector that can power up and down sensor interfaces based on need and/or conditions identified in an industrial data collection environment; and for a haptic or multi-sensory user interface, including a wearable haptic or multi-sensory user interface for an industrial sensor data collector, with vibration, heat, electrical, and/or sound outputs.”) associated with a test device in a laboratory environment; (Siu, sec. I: “Both of these methods typically incur substantial equipment and personnel costs and confine estimations to a laboratory setting…Moreover, this method enables real-time joint torque estimation outside of the confines of a laboratory or clinic after an initial data collection period, broadening the range of possibilities for dynamic assessments.” Examiner notes Cella and Siu both teach receiving information from a plurality of sensors where Cella teaches specifically voltage, vibrational and sound information and Siu specifically teaches a laboratory environment).
generating a training data set (Cella, para. 1005: “Training may include presenting the neural network with one or more training data sets that represent values, such as sensor data, event data, parameter data, and other types of data (including the many types described throughout this disclosure), as well as one or more indicators of an outcome, such as an outcome of a process, an outcome of a calculation, an outcome of an event, an outcome of an activity, or the like.”) utilizing the current information, the voltage information, the vibrational information, and the sound information; (Cella, para. 0015: “Methods and systems are disclosed herein for training artificial intelligence (“AI”) models based on industry-specific feedback, including training an AI model based on industry-specific feedback that reflects a measure of utilization, yield, or impact, where the AI model operates on sensor data from an industrial environment; for an industrial IoT distributed ledger, including a distributed ledger supporting the tracking of transactions executed in an automated data marketplace for industrial IoT data; for a network-sensitive collector, including a network condition-sensitive, self-organizing, multi-sensor data collector that can optimize based on bandwidth, quality of service, pricing, and/or other network conditions; for a remotely organized universal data collector that can power up and down sensor interfaces based on need and/or conditions identified in an industrial data collection environment; and for a haptic or multi-sensory user interface, including a wearable haptic or multi-sensory user interface for an industrial sensor data collector, with vibration, heat, electrical, and/or sound outputs.”)
inputting the training data set into a machine learning model; (Cella, para. 0015: “Methods and systems are disclosed herein for training artificial intelligence (“AI”) models based on industry-specific feedback, including training an AI model based on industry-specific feedback that reflects a measure of utilization, yield, or impact, where the AI model operates on sensor data from an industrial environment;
in response to a convergence threshold of the machine learning model being met by the training data set, (Cella, para. 1020: “In embodiments, methods and systems described herein that involve an expert system or self-organization capability may use a structure-adaptive neural network, where the structure of a neural network is adapted, such as based on a rule, a sensed condition, a contextual parameter, or the like. For example, if a neural network does not converge on a solution, such as classifying an item or arriving at a prediction, when acting on a set of inputs after some amount of training, the neural network may be modified, such as from a feedforward neural network to a recurrent neural network, such as by switching data paths between some subset of nodes from unidirectional to bi-directional data paths. The structure adaptation may occur under control of an expert system, such as to trigger adaptation upon occurrence of a trigger, rule or event, such as recognizing occurrence of a threshold (such as an absence of a convergence to a solution within a given amount of time) or recognizing a phenomenon as requiring different or additional structure (such as recognizing that a system is varying dynamically or in a non-linear fashion).”) outputting a trained machine learning model configured to output torque predictions; (Siu, sec. III(D): “In these experiments, the same training and testing procedure is followed, but instead of estimating a single pair of left and right foot target values (torques) per set of feature inputs, models are made to predict torque values for each time point in the provided sequence, resulting in 2⋅T regression outputs for each f⋅T input values, where T is the length of both the feature and output sequences and f is the number of input features per time point (f=112 ).”)
receiving a combination of either real-time current information, real-time voltage information, or real-time vibrational information from a second plurality of sensors associated with a run-time device; and (Cella, para. 0856: “The criteria may include a sensor's detection values at certain frequencies or phases relative to a timer signal where the frequencies or phases of interest may be based on the equipment geometry, equipment control schemes, system input, historical data, current operating conditions, and/or an anticipated response. The criteria may include a sensor's detection values at certain frequencies or phases relative to detection values of a second sensor. The criteria may include signal strength at certain resonant frequencies/harmonics relative to detection values associated with a system tachometer or anticipated based on equipment geometry and operation conditions. Criteria may include a predetermined peak value for a detection value from a specific sensor, a cumulative value of a sensor's corresponding detection value over time, a change in peak value, a rate of change in a peak value, and/or an accumulated value (e.g., a time spent above/below a threshold value, a weighted time spent above/below one or more threshold values, and/or an area of the detected value above/below one or more threshold values). The criteria may comprise combinations of data from different sensors such as relative values, relative changes in value, relative rates of change in value, relative values over time, and the like. The relative criteria may change with other data or information such as process stage, type of product being processed, type of equipment, ambient temperature and humidity, external vibrations from other equipment, and the like.”)
outputting a torque prediction (Siu, sec. III(D): “In these experiments, the same training and testing procedure is followed, but instead of estimating a single pair of left and right foot target values (torques) per set of feature inputs, models are made to predict torque values for each time point in the provided sequence, resulting in 2⋅T regression outputs for each f⋅T input values, where T is the length of both the feature and output sequences and f is the number of input features per time point (f=112 ).”) associated with the run-time device (Cella, para. 0856, supra) based on (i) the trained machine learning model (Siu, sec. III(D), supra) and (ii) the combination of either real-time current information, real-time voltage information, or real-time vibrational information as input to the trained machine learning model. (Cella, para. 0856, supra).
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the teachings of Siu into Cella. Cella teaches detecting an operating characteristic of an industrial machine using one or more sensors of a mobile data collector; transmitting data indicative of the operating characteristic to a server over a network; using intelligent systems associated with the server to process the operating characteristic against pre-recorded data for the industrial machine. Siu teaches learning the mapping for ankle plantarflexion and dorsiflexion torque during standing, walking, running, and sprinting, and consider both single-point torque estimation, as well as the prediction of a sequence of future torques. One of ordinary skill would have been motivated to combine the teachings of Siu into Cella in order to provide an improved understanding during which parts of the gait cycle the models are providing the most accurate estimates of joint torque and where the algorithms could be improved and could be useful for anticipatory robot control design. (Siu, sec. V(A) and Abstract).
Regarding claim 2, Cella, as modified, teaches claim 1 (above). Cella further teaches:
The computer-implemented method of claim 1, wherein the trained machine learning model (Cella, para. 0856, supra) is configured to output a sound prediction (Cella, para. 0042 and 0050: “The mobile devices include one or more sensors that may be configured to record state-related measurements of the target, for example, based on vibrational, temperature, electrical, magnetic, sound, and/or other measurements. The data captured using some or all of these mobile devices may be processed by intelligent systems onboard those mobile devices and/or at a server in communication with those mobile devices over a network. The intelligent systems include intelligence for processing the data captured using the respective mobile devices. Processing the data can, for example, include identifying a state of a target for which measurements were recorded by comparing the state-related measurements from the wearable device against information stored in a database, which may, for example, be part of a knowledge base associated with the industrial environment” “The memory further includes instructions executable by the processor to record the one or more values; compare the recorded one or more values to corresponding predicted values and to generate a variance data set based on the comparison of the recorded one or more values and the corresponding predicted values.” Examiner notes that Cella teaches recording of sound as well as corresponding predicted values (i.e. a predicted sound)) utilizing the combination of either real-time current information, real-time voltage information, or real-time vibrational information as input, (Cella, para. 0316, 0347 and 2256: “In embodiments, an analysis engine may be used in ultrasonic online monitoring as well as identifying other faults by combining the ultrasonic data with other parameters such as vibration, temperature, pressure, heat flux, magnetic fields, electrical fields, currents, voltage, capacitance, inductance, and combinations (e.g., simple ratios) of the same, among many others.” “The present disclosure can be applicable to not only digitizing a waveform signal based on a detected voltage but can also be applicable to digitizing waveform signals based on current waveforms, vibration waveforms, and image processing signals including video signal rasterization” “In embodiments, a monitoring subsystem with one or more sensors may collect, analyze, and/or report the real-time measurement of sensed data. Likewise, such a subsystem may collect, analyze, and/or report real-time failure data, such as to facilitate measuring and/or tracking material failure data, e.g., frequency, degree, time since deployment, and the like.”)
wherein the sound prediction is associated with perceived sound associated with operating the runtime device. (Cella, para. 0055: “ In embodiments, a fifth wearable device of the plurality of wearable devices captures a sound wave output from the industrial machine using a sound sensor. In embodiments, the signal is generated based on the severity unit and based on a fifth severity unit calculated based on the captured sound wave”)
Regarding claim 3, Cella, as modified, teaches claim 1 (above). Cella further teaches:
The computer-implemented method of claim 1, wherein the combination includes at least real-time voltage information. (Cella, para. 0316 and 2256: “In embodiments, an analysis engine may be used in ultrasonic online monitoring as well as identifying other faults by combining the ultrasonic data with other parameters such as vibration, temperature, pressure, heat flux, magnetic fields, electrical fields, currents, voltage, capacitance, inductance, and combinations (e.g., simple ratios) of the same, among many others.” “In embodiments, a monitoring subsystem with one or more sensors may collect, analyze, and/or report the real-time measurement of sensed data. Likewise, such a subsystem may collect, analyze, and/or report real-time failure data, such as to facilitate measuring and/or tracking material failure data, e.g., frequency, degree, time since deployment, and the like.”)
Regarding claim 4, Cella, as modified, teaches claim 1 (above). Cella further teaches:
The computer-implemented method of claim 1, wherein the trained machine learning model is a deep neural network. (Cella, para. 2772: “In embodiments, the computer vision system 15000 may implement a classification model (e.g., using a deep neural network, or other suitable neural or other networks).”)
Regarding claim 5, Cella, as modified, teaches claim 4 (above). Cella further teaches:
The computer-implemented method of claim 4, wherein the deep neural network is a U-net or transformer network. (Cella, para. 0985: “References to a neural net throughout this disclosure should be understood to encompass a wide range of different types of neural networks, machine learning systems, artificial intelligence systems, and the like, such as feed forward neural networks, radial basis function neural networks, self-organizing neural networks (e.g., Kohonen self-organizing neural networks), recurrent neural networks, modular neural networks, artificial neural networks, physical neural networks, multi-layered neural networks, convolutional neural networks, hybrids of neural networks with other expert systems (e.g., hybrid fuzzy logic—neural network systems), autoencoder neural networks, probabilistic neural networks, time delay neural networks, convolutional neural networks, regulatory feedback neural networks, radial basis function neural networks, recurrent neural networks, Hopfield neural networks, Boltzmann machine neural networks, self-organizing map (SOM) neural networks, learning vector quantization (LVQ) neural networks, fully recurrent neural networks, simple recurrent neural networks, echo state neural networks, long short-term memory neural networks, bi-directional neural networks, hierarchical neural networks, stochastic neural networks, genetic scale RNN neural networks, committee of machines neural networks, associative neural networks, physical neural networks, instantaneously trained neural networks, spiking neural networks, neocognition neural networks, dynamic neural networks, cascading neural networks, neuro-fuzzy neural networks, compositional pattern-producing neural networks, memory neural networks, hierarchical temporal memory neural networks, deep feed forward neural networks, gated recurrent unit (GCU) neural networks, auto encoder neural networks, variational auto encoder neural networks, de-noising auto encoder neural networks, sparse auto-encoder neural networks, Markov chain neural networks, restricted Boltzmann machine neural networks, deep belief neural networks, deep convolutional neural networks, deconvolutional neural networks, deep convolutional inverse graphics neural networks, generative adversarial neural networks, liquid state machine neural networks, extreme learning machine neural networks, echo state neural networks, deep residual neural networks, support vector machine neural networks, neural Turing machine neural networks, and/or holographic associative memory neural networks, or hybrids or combinations of the foregoing, or combinations with other expert systems, such as rule-based systems, model-based systems (including ones based on physical models, statistical models, flow-based models, biological models, biomimetic models, and the like).”)
Regarding claim 6, Cella, as modified, teaches claim 1 (above). Cella further teaches:
The computer-implemented method of claim 1, wherein the combination includes both real-time current information and real-time voltage information (Cella, para. 0316, 0347 and 2256: “In embodiments, an analysis engine may be used in ultrasonic online monitoring as well as identifying other faults by combining the ultrasonic data with other parameters such as vibration, temperature, pressure, heat flux, magnetic fields, electrical fields, currents, voltage, capacitance, inductance, and combinations (e.g., simple ratios) of the same, among many others.” “The present disclosure can be applicable to not only digitizing a waveform signal based on a detected voltage but can also be applicable to digitizing waveform signals based on current waveforms, vibration waveforms, and image processing signals including video signal rasterization” “In embodiments, a monitoring subsystem with one or more sensors may collect, analyze, and/or report the real-time measurement of sensed data. Likewise, such a subsystem may collect, analyze, and/or report real-time failure data, such as to facilitate measuring and/or tracking material failure data, e.g., frequency, degree, time since deployment, and the like.”) to output the torque prediction. (Siu, sec. III(D): “In these experiments, the same training and testing procedure is followed, but instead of estimating a single pair of left and right foot target values (torques) per set of feature inputs, models are made to predict torque values for each time point in the provided sequence, resulting in 2⋅T regression outputs for each f⋅T input values, where T is the length of both the feature and output sequences and f is the number of input features per time point (f=112 ).”)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the teachings of Siu into Cella, as modified, as set forth above with respect to claim 1.
Regarding claim 7, Cella, as modified, teaches claim 6 (above). Cella further teaches:
The computer-implemented method of claim 6, wherein the combination includes both real-time current information and real-time voltage information (Cella, para. 0316, 0347 and 2256: “In embodiments, an analysis engine may be used in ultrasonic online monitoring as well as identifying other faults by combining the ultrasonic data with other parameters such as vibration, temperature, pressure, heat flux, magnetic fields, electrical fields, currents, voltage, capacitance, inductance, and combinations (e.g., simple ratios) of the same, among many others.” “The present disclosure can be applicable to not only digitizing a waveform signal based on a detected voltage but can also be applicable to digitizing waveform signals based on current waveforms, vibration waveforms, and image processing signals including video signal rasterization” “In embodiments, a monitoring subsystem with one or more sensors may collect, analyze, and/or report the real-time measurement of sensed data. Likewise, such a subsystem may collect, analyze, and/or report real-time failure data, such as to facilitate measuring and/or tracking material failure data, e.g., frequency, degree, time since deployment, and the like.”) to output a sound prediction is associated with perceived sound associated with operating the run-time device. (Cella, para. 0042, 0050 and 0055: “The mobile devices include one or more sensors that may be configured to record state-related measurements of the target, for example, based on vibrational, temperature, electrical, magnetic, sound, and/or other measurements. The data captured using some or all of these mobile devices may be processed by intelligent systems onboard those mobile devices and/or at a server in communication with those mobile devices over a network. The intelligent systems include intelligence for processing the data captured using the respective mobile devices. Processing the data can, for example, include identifying a state of a target for which measurements were recorded by comparing the state-related measurements from the wearable device against information stored in a database, which may, for example, be part of a knowledge base associated with the industrial environment” “The memory further includes instructions executable by the processor to record the one or more values; compare the recorded one or more values to corresponding predicted values and to generate a variance data set based on the comparison of the recorded one or more values and the corresponding predicted values.” “ In embodiments, a fifth wearable device of the plurality of wearable devices captures a sound wave output from the industrial machine using a sound sensor. In embodiments, the signal is generated based on the severity unit and based on a fifth severity unit calculated based on the captured sound wave”. Examiner notes that Cella teaches recording of sound as well as corresponding predicted values (i.e. a predicted sound)).
Regarding claims 8, Cella, as modified, teaches claim 1 (above). Cella further teaches:
The computer-implemented method of claim 1, wherein the real-time current information is an input current reading and the real-time voltage information is an input voltage reading. (Cella, para. 0316, 0347 and 2256: “In embodiments, an analysis engine may be used in ultrasonic online monitoring as well as identifying other faults by combining the ultrasonic data with other parameters such as vibration, temperature, pressure, heat flux, magnetic fields, electrical fields, currents, voltage, capacitance, inductance, and combinations (e.g., simple ratios) of the same, among many others.” “The present disclosure can be applicable to not only digitizing a waveform signal based on a detected voltage but can also be applicable to digitizing waveform signals based on current waveforms, vibration waveforms, and image processing signals including video signal rasterization” “In embodiments, a monitoring subsystem with one or more sensors may collect, analyze, and/or report the real-time measurement of sensed data. Likewise, such a subsystem may collect, analyze, and/or report real-time failure data, such as to facilitate measuring and/or tracking material failure data, e.g., frequency, degree, time since deployment, and the like.”)
Regarding claims 9, Cella, as modified, teaches claim 1 (above). Cella further teaches:
The computer-implemented method of claim 1, wherein the torque prediction is in the form of either time series, spectrogram, or order spectrogram data. (Siu, sec I: “The major contributions in this paper are threefold: (1) a comparison of the performance of several modern types of neural network models on the problem of ankle torque regression from wearable sensors, (2) the evaluation of sequence regressions for estimating a time series of torques, with and without data augmentation, and (3) the use of these methods to predict future torque sequences.”).
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the teachings of Siu into Cella, as modified, as set forth above with respect to claim 1.
Regarding claims 10, Cella teaches:
A computer-implemented method, comprising: receiving current information, voltage information, vibrational information and sound information from a plurality of sensors (Cella, para. 0015: “Methods and systems are disclosed herein for training artificial intelligence (“AI”) models based on industry-specific feedback, including training an AI model based on industry-specific feedback that reflects a measure of utilization, yield, or impact, where the AI model operates on sensor data from an industrial environment; for an industrial IoT distributed ledger, including a distributed ledger supporting the tracking of transactions executed in an automated data marketplace for industrial IoT data; for a network-sensitive collector, including a network condition-sensitive, self-organizing, multi-sensor data collector that can optimize based on bandwidth, quality of service, pricing, and/or other network conditions; for a remotely organized universal data collector that can power up and down sensor interfaces based on need and/or conditions identified in an industrial data collection environment; and for a haptic or multi-sensory user interface, including a wearable haptic or multi-sensory user interface for an industrial sensor data collector, with vibration, heat, electrical, and/or sound outputs.”) associated with a test device in a laboratory environment; (Siu, sec. I: “Both of these methods typically incur substantial equipment and personnel costs and confine estimations to a laboratory setting…Moreover, this method enables real-time joint torque estimation outside of the confines of a laboratory or clinic after an initial data collection period, broadening the range of possibilities for dynamic assessments.” Examiner notes Cella and Siu both teach receiving information from a plurality of sensors where Cella teaches specifically voltage, vibrational and sound information and Siu specifically teaches a laboratory environment).
generating a training data set (Cella, para. 1005: “Training may include presenting the neural network with one or more training data sets that represent values, such as sensor data, event data, parameter data, and other types of data (including the many types described throughout this disclosure), as well as one or more indicators of an outcome, such as an outcome of a process, an outcome of a calculation, an outcome of an event, an outcome of an activity, or the like.”) utilizing the current information, the voltage information, the vibrational information and the sound information; (Cella, para. 0015: “Methods and systems are disclosed herein for training artificial intelligence (“AI”) models based on industry-specific feedback, including training an AI model based on industry-specific feedback that reflects a measure of utilization, yield, or impact, where the AI model operates on sensor data from an industrial environment; for an industrial IoT distributed ledger, including a distributed ledger supporting the tracking of transactions executed in an automated data marketplace for industrial IoT data; for a network-sensitive collector, including a network condition-sensitive, self-organizing, multi-sensor data collector that can optimize based on bandwidth, quality of service, pricing, and/or other network conditions; for a remotely organized universal data collector that can power up and down sensor interfaces based on need and/or conditions identified in an industrial data collection environment; and for a haptic or multi-sensory user interface, including a wearable haptic or multi-sensory user interface for an industrial sensor data collector, with vibration, heat, electrical, and/or sound outputs.”)
inputting the training data set is fed into a machine learning model; (Cella, para. 0015: “Methods and systems are disclosed herein for training artificial intelligence (“AI”) models based on industry-specific feedback, including training an AI model based on industry-specific feedback that reflects a measure of utilization, yield, or impact, where the AI model operates on sensor data from an industrial environment”)
in response to a convergence threshold of the machine learning model being met by the training data set, (Cella, para. 1020: “In embodiments, methods and systems described herein that involve an expert system or self-organization capability may use a structure-adaptive neural network, where the structure of a neural network is adapted, such as based on a rule, a sensed condition, a contextual parameter, or the like. For example, if a neural network does not converge on a solution, such as classifying an item or arriving at a prediction, when acting on a set of inputs after some amount of training, the neural network may be modified, such as from a feedforward neural network to a recurrent neural network, such as by switching data paths between some subset of nodes from unidirectional to bi-directional data paths. The structure adaptation may occur under control of an expert system, such as to trigger adaptation upon occurrence of a trigger, rule or event, such as recognizing occurrence of a threshold (such as an absence of a convergence to a solution within a given amount of time) or recognizing a phenomenon as requiring different or additional structure (such as recognizing that a system is varying dynamically or in a non-linear fashion).”) outputting a trained machine learning model configured to output torque predictions; (Siu, sec. III(D): “In these experiments, the same training and testing procedure is followed, but instead of estimating a single pair of left and right foot target values (torques) per set of feature inputs, models are made to predict torque values for each time point in the provided sequence, resulting in 2⋅T regression outputs for each f⋅T input values, where T is the length of both the feature and output sequences and f is the number of input features per time point (f=112 ).”)
receiving a combination of either real-time current information, real-time voltage information, or real-time vibrational information from a run-time device; and(Cella, para. 0856: “The criteria may include a sensor's detection values at certain frequencies or phases relative to a timer signal where the frequencies or phases of interest may be based on the equipment geometry, equipment control schemes, system input, historical data, current operating conditions, and/or an anticipated response. The criteria may include a sensor's detection values at certain frequencies or phases relative to detection values of a second sensor. The criteria may include signal strength at certain resonant frequencies/harmonics relative to detection values associated with a system tachometer or anticipated based on equipment geometry and operation conditions. Criteria may include a predetermined peak value for a detection value from a specific sensor, a cumulative value of a sensor's corresponding detection value over time, a change in peak value, a rate of change in a peak value, and/or an accumulated value (e.g., a time spent above/below a threshold value, a weighted time spent above/below one or more threshold values, and/or an area of the detected value above/below one or more threshold values). The criteria may comprise combinations of data from different sensors such as relative values, relative changes in value, relative rates of change in value, relative values over time, and the like. The relative criteria may change with other data or information such as process stage, type of product being processed, type of equipment, ambient temperature and humidity, external vibrations from other equipment, and the like.”)
based on (i) the trained machine learning model and (Siu, sec. III(D), supra) (ii) the combination of at least the real-time current information and real-time voltage information as input to the trained machine learning model (Cella, para. 0856, supra), outputting a torque prediction indicating a predicted torque (Siu, sec. III(D): “In these experiments, the same training and testing procedure is followed, but instead of estimating a single pair of left and right foot target values (torques) per set of feature inputs, models are made to predict torque values for each time point in the provided sequence, resulting in 2⋅T regression outputs for each f⋅T input values, where T is the length of both the feature and output sequences and f is the number of input features per time point (f=112 ).”) associated with the runtime device during operation. (Cella, para. 0856, supra)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the teachings of Siu into Cella, as modified, as set forth above with respect to claim 1.
Regarding claim 11, Cella, as modified, teaches claim 10 (above). Cella further teaches:
The computer-implemented method of claim 10, wherein the method includes utilizing the trained machine learning model (Siu, sec. III(D), supra) and the combination of at least the real-time current information and real-time voltage information as input to the trained machine learning model, (Cella, para. 0316, 0347 and 2256: “In embodiments, an analysis engine may be used in ultrasonic online monitoring as well as identifying other faults by combining the ultrasonic data with other parameters such as vibration, temperature, pressure, heat flux, magnetic fields, electrical fields, currents, voltage, capacitance, inductance, and combinations (e.g., simple ratios) of the same, among many others.” “The present disclosure can be applicable to not only digitizing a waveform signal based on a detected voltage but can also be applicable to digitizing waveform signals based on current waveforms, vibration waveforms, and image processing signals including video signal rasterization” “In embodiments, a monitoring subsystem with one or more sensors may collect, analyze, and/or report the real-time measurement of sensed data. Likewise, such a subsystem may collect, analyze, and/or report real-time failure data, such as to facilitate measuring and/or tracking material failure data, e.g., frequency, degree, time since deployment, and the like.”) outputting a sound prediction indicating a predicted sound associated with the run-time device. (Cella, para. 0042 and 0050: “The mobile devices include one or more sensors that may be configured to record state-related measurements of the target, for example, based on vibrational, temperature, electrical, magnetic, sound, and/or other measurements. The data captured using some or all of these mobile devices may be processed by intelligent systems onboard those mobile devices and/or at a server in communication with those mobile devices over a network. The intelligent systems include intelligence for processing the data captured using the respective mobile devices. Processing the data can, for example, include identifying a state of a target for which measurements were recorded by comparing the state-related measurements from the wearable device against information stored in a database, which may, for example, be part of a knowledge base associated with the industrial environment” “The memory further includes instructions executable by the processor to record the one or more values; compare the recorded one or more values to corresponding predicted values and to generate a variance data set based on the comparison of the recorded one or more values and the corresponding predicted values.” Examiner notes that Cella teaches recording of sound as well as corresponding predicted values (i.e. a predicted sound))
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the teachings of Siu into Cella, as modified, as set forth above with respect to claim 1.
Regarding Claim 12, Cella, as modified, teaches claim 10 (above). Cella further teaches:
The computer-implemented method of claim 10, wherein the combination includes utilizing the real-time vibration information (Cella, para. 0042 and 0050: “The mobile devices include one or more sensors that may be configured to record state-related measurements of the target, for example, based on vibrational, temperature, electrical, magnetic, sound, and/or other measurements. The data captured using some or all of these mobile devices may be processed by intelligent systems onboard those mobile devices and/or at a server in communication with those mobile devices over a network. The intelligent systems include intelligence for processing the data captured using the respective mobile devices. Processing the data can, for example, include identifying a state of a target for which measurements were recorded by comparing the state-related measurements from the wearable device against information stored in a database, which may, for example, be part of a knowledge base associated with the industrial environment” “The memory further includes instructions executable by the processor to record the one or more values; compare the recorded one or more values to corresponding predicted values and to generate a variance data set based on the comparison of the recorded one or more values and the corresponding predicted values.”) for outputting the torque prediction. (Siu, sec. III(D): “In these experiments, the same training and testing procedure is followed, but instead of estimating a single pair of left and right foot target values (torques) per set of feature inputs, models are made to predict torque values for each time point in the provided sequence, resulting in 2⋅T regression outputs for each f⋅T input values, where T is the length of both the feature and output sequences and f is the number of input features per time point (f=112 ).”)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the teachings of Siu into Cella, as modified, as set forth above with respect to claim 1.
Regarding Claim 13, Cella, as modified, teaches claim 10 (above). Cella further teaches:
The computer-implemented method of claim 10, wherein the combination does not include real-time vibrational information. (Cella, para. 0042: “The mobile devices include one or more sensors that may be configured to record state-related measurements of the target, for example, based on vibrational, temperature, electrical, magnetic, sound, and/or other measurements.” Examiner notes that Cella teaches one or more sensors that may record vibrational measurement and therefore also may not).
Regarding Claim 14, Cella, as modified, teaches claim 10 (above). Cella further teaches:
The computer-implemented method of claim 10, wherein the machine learning model is a deep learning network that is a U-Net network or transformer network. (Cella, para. 0985: “References to a neural net throughout this disclosure should be understood to encompass a wide range of different types of neural networks, machine learning systems, artificial intelligence systems, and the like, such as feed forward neural networks, radial basis function neural networks, self-organizing neural networks (e.g., Kohonen self-organizing neural networks), recurrent neural networks, modular neural networks, artificial neural networks, physical neural networks, multi-layered neural networks, convolutional neural networks, hybrids of neural networks with other expert systems (e.g., hybrid fuzzy logic—neural network systems), autoencoder neural networks, probabilistic neural networks, time delay neural networks, convolutional neural networks, regulatory feedback neural networks, radial basis function neural networks, recurrent neural networks, Hopfield neural networks, Boltzmann machine neural networks, self-organizing map (SOM) neural networks, learning vector quantization (LVQ) neural networks, fully recurrent neural networks, simple recurrent neural networks, echo state neural networks, long short-term memory neural networks, bi-directional neural networks, hierarchical neural networks, stochastic neural networks, genetic scale RNN neural networks, committee of machines neural networks, associative neural networks, physical neural networks, instantaneously trained neural networks, spiking neural networks, neocognition neural networks, dynamic neural networks, cascading neural networks, neuro-fuzzy neural networks, compositional pattern-producing neural networks, memory neural networks, hierarchical temporal memory neural networks, deep feed forward neural networks, gated recurrent unit (GCU) neural networks, auto encoder neural networks, variational auto encoder neural networks, de-noising auto encoder neural networks, sparse auto-encoder neural networks, Markov chain neural networks, restricted Boltzmann machine neural networks, deep belief neural networks, deep convolutional neural networks, deconvolutional neural networks, deep convolutional inverse graphics neural networks, generative adversarial neural networks, liquid state machine neural networks, extreme learning machine neural networks, echo state neural networks, deep residual neural networks, support vector machine neural networks, neural Turing machine neural networks, and/or holographic associative memory neural networks, or hybrids or combinations of the foregoing, or combinations with other expert systems, such as rule-based systems, model-based systems (including ones based on physical models, statistical models, flow-based models, biological models, biomimetic models, and the like).”)
Regarding Claim 15, Cella, as modified, teaches claim 10 (above). Cella further teaches
The computer-implemented method of claim 10, wherein the combination includes utilizing the real-time current information, real-time voltage information, the real-time vibrational information (Cella, para. 0316, 0347 and 2256: “In embodiments, an analysis engine may be used in ultrasonic online monitoring as well as identifying other faults by combining the ultrasonic data with other parameters such as vibration, temperature, pressure, heat flux, magnetic fields, electrical fields, currents, voltage, capacitance, inductance, and combinations (e.g., simple ratios) of the same, among many others.” “The present disclosure can be applicable to not only digitizing a waveform signal based on a detected voltage but can also be applicable to digitizing waveform signals based on current waveforms, vibration waveforms, and image processing signals including video signal rasterization” “In embodiments, a monitoring subsystem with one or more sensors may collect, analyze, and/or report the real-time measurement of sensed data. Likewise, such a subsystem may collect, analyze, and/or report real-time failure data, such as to facilitate measuring and/or tracking material failure data, e.g., frequency, degree, time since deployment, and the like.”) to output a sound prediction indicating a predicted sound associated with the run-time device. (Cella, para. 0042, 0050 and 0055: “The mobile devices include one or more sensors that may be configured to record state-related measurements of the target, for example, based on vibrational, temperature, electrical, magnetic, sound, and/or other measurements. The data captured using some or all of these mobile devices may be processed by intelligent systems onboard those mobile devices and/or at a server in communication with those mobile devices over a network. The intelligent systems include intelligence for processing the data captured using the respective mobile devices. Processing the data can, for example, include identifying a state of a target for which measurements were recorded by comparing the state-related measurements from the wearable device against information stored in a database, which may, for example, be part of a knowledge base associated with the industrial environment” “The memory further includes instructions executable by the processor to record the one or more values; compare the recorded one or more values to corresponding predicted values and to generate a variance data set based on the comparison of the recorded one or more values and the corresponding predicted values.” “ In embodiments, a fifth wearable device of the plurality of wearable devices captures a sound wave output from the industrial machine using a sound sensor. In embodiments, the signal is generated based on the severity unit and based on a fifth severity unit calculated based on the captured sound wave”. Examiner notes that Cella teaches recording of sound as well as corresponding predicted values (i.e. a predicted sound)).
Regarding Claim 18, Cella, as modified, teaches claim 16 (above). Cella further teaches
The system of claim 16, wherein the combination includes real-time current information and real-time voltage information. (Cella, para. 0316, 0347 and 2256: “In embodiments, an analysis engine may be used in ultrasonic online monitoring as well as identifying other faults by combining the ultrasonic data with other parameters such as vibration, temperature, pressure, heat flux, magnetic fields, electrical fields, currents, voltage, capacitance, inductance, and combinations (e.g., simple ratios) of the same, among many others.” “The present disclosure can be applicable to not only digitizing a waveform signal based on a detected voltage but can also be applicable to digitizing waveform signals based on current waveforms, vibration waveforms, and image processing signals including video signal rasterization” “In embodiments, a monitoring subsystem with one or more sensors may collect, analyze, and/or report the real-time measurement of sensed data. Likewise, such a subsystem may collect, analyze, and/or report real-time failure data, such as to facilitate measuring and/or tracking material failure data, e.g., frequency, degree, time since deployment, and the like.”)
Regarding Claim 19, Cella, as modified, teaches claim 16 (above). Cella further teaches:
The system of claim 16, where the combination does not include real-time current information. (Cella, para. 0042: “The mobile devices include one or more sensors that may be configured to record state-related measurements of the target, for example, based on vibrational, temperature, electrical, magnetic, sound, and/or other measurements.” Examiner notes that Cella teaches current waveforms in para 0347 and also teaches that sensors may include and therefore also may not any particular data).
Regarding Claim 20, Cella, as modified, teaches claim 16 (above). Cella further teaches:
The system of claim 16, wherein the combination includes real-time current information and either real-time voltage information or real-time vibrational information. (Cella, para. 0316, 0347 and 2256: “In embodiments, an analysis engine may be used in ultrasonic online monitoring as well as identifying other faults by combining the ultrasonic data with other parameters such as vibration, temperature, pressure, heat flux, magnetic fields, electrical fields, currents, voltage, capacitance, inductance, and combinations (e.g., simple ratios) of the same, among many others.” “The present disclosure can be applicable to not only digitizing a waveform signal based on a detected voltage but can also be applicable to digitizing waveform signals based on current waveforms, vibration waveforms, and image processing signals including video signal rasterization” “In embodiments, a monitoring subsystem with one or more sensors may collect, analyze, and/or report the real-time measurement of sensed data. Likewise, such a subsystem may collect, analyze, and/or report real-time failure data, such as to facilitate measuring and/or tracking material failure data, e.g., frequency, degree, time since deployment, and the like.”)
Response to Applicant Arguments/Remarks
35 USC § 103
Beginning on page 6 of applicant’s remarks, applicant argues that Siu does not teach “receiving current information, voltage information, vibrational information, and sound information from a first plurality of sensors associated with a test device in a laboratory environment; generating a training data set utilizing the current information, voltage information, vibrational information, and sound information”. Applicant specifically argues Cella does not specifically teach generating, assembling, structuring, labeling, or otherwise creating a training data set from sensor information.
However, as set forth in the rejection above, Cella at paragraph 1005 teaches:
Training may include presenting the neural network with one or more training data sets that represent values, such as sensor data, event data, parameter data, and other types of data (including the many types described throughout this disclosure), as well as one or more indicators of an outcome, such as an outcome of a process, an outcome of a calculation, an outcome of an event, an outcome of an activity, or the like.
(emphasis added). Cella teaches generating a training data set via aggregation of one or more training data sets. Applicant’s arguments are not persuasive.
35 USC § 103 – Claim 16
On page 7 of applicant’s response, applicant argues Cella and Siu do not teach the claim 16 as currently amended. Applicant further argues that a person of ordinary skill in the art would not have been motivated to combine Cella and Siu because Cella teaches industrial sensor monitoring and Siu teaches biomechanics-based torque prediction model.
In light of applicant’s amendments, the previously asserted rejection for claim 16 has been updated as set forth above. Claim 16 now stands rejected under 35 USC § 102 where Cella also teaches torque sensors and data.
Moreover, outside of claim 16 as set forth in the 103 rejection above, one would have been motivated to combine Siu into Cella in order to obtain an improved understanding during which parts of the gait cycle the models are providing the most accurate estimates of joint torque and where the algorithms could be improved. A person of ordinary skill in the art would recognize that the improvement of algorithms for more accurate estimates of joint torque could be broadly applied to other models of movement. The motivation to combine also now references the abstract, where Siu specifically states that predicting joint torques into the future can be useful for robot control design.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Sally T. Ley whose telephone number is (571)272-3406. The examiner can normally be reached Monday - Thursday, 10:00am - 6:00pm ET.
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, Viker Lamardo can be reached at (571) 270-5871. 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.
/STL/Examiner, Art Unit 2147
/VIKER A LAMARDO/Supervisory Patent Examiner, Art Unit 2147
Prosecution Insights