Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Amendment
This action is in response to the request for continued examination as well as amendments and remarks filed on 01/20/2026. Claims 1, 6, and 7 are amended, Claims 4 and 5 are cancelled, Claims 1-3 and 6-14 are pending examination.
The applicant's amendment necessitated new grounds of rejection therefore, claims 1-3 and 6-14 are rejected.
Response to Arguments
Applicant presents the following arguments regarding the previous office action:
The amendments to claim 1 overcome the rejections under 35 U.S.C. § 103.
Applicant’s argument A, with respect to the independent claims has been fully considered and is moot in light of new grounds for rejection below.
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 1-2, and 6-10 are all rejected under 35 U.S.C. 103 as being unpatentable over Kim et al (US20210335064A1) in view of Yoshizawa et al. (US20100030562A1), further in view of Remboski et al. (US6775642B2)..
Regarding claim 1, Kim discloses, a computer-implemented method of training a diagnostic model (0118, the audio data associated with a component that failed may be classified for use by the machine learning model to identify faults in the future. As such, the first audio data (as well as other audio data associated with other vehicles), may be used as training data) for identifying a fault condition (“faults of the component (e.g., energy level) and/or components that are not properly functioning.” Para 118, lines _??_) in a vehicle system (0009, FIG. 6 illustrates an example process for training a machine learned model for use in monitoring a health of a vehicle), the method comprising: receiving a plurality of vehicle fault condition data sets (the first audio data (as well as other audio data associated with other vehicles), may be used as training data. The training data may include a designation of an operating status of the component (e.g., fair, poor, healthy, defective, etc.), each vehicle fault condition data set being associated with a known fault condition (the audio data associated with a component that failed may be classified for use by the machine learning model to identify faults in the future), of a vehicle system (0009, FIG. 6 illustrates an example process for training a machine learned model for use in monitoring a health of a vehicle).), wherein the vehicle fault condition data sets each comprise: audio data representing an audio signal generated by a microphone during operation of the vehicle system having the known fault condition (Abstract, the systems and methods receive audio data generated by a microphone of the vehicle, where the audio data represents sound of the component), and operating data indicating an operating state of the vehicle system (Abstract, Based on the audio data, a condition of the vehicle or the component may be determined, and based on the condition, the vehicle may be commissioned for use or decommissioned),processing each vehicle fault condition data set, the processing comprising: applying a Fast Fourier Transform to the audio data to generate a computed frequency domain representation of the audio signal (0017, processing the audio data may include setting limits for a signal-to-noise ratio of the audio data, setting a target frequency of the audio data, including performing FFT processing on the audio data to transform the audio data from a time domain to a frequency domain), and training the diagnostic model (Kim, 0137, Lines 12-18, the training component 448 may generate the training data 454 using the log data 450. to identify the at least one fault condition in dependence on the identification of the at least one fault indicator component (0137, the training component 448 may label audio data associated with vehicle components with one or more measured parameters and/or characteristics of the vehicle components associated with the audio data 438. The audio data 438 and/or the measured parameters or characteristics may be obtained from the log data 450, the audio signatures 456, and/or the fault log 458), in each vehicle fault condition data set (The label may include an indication of an operating status (e.g., normal, failed, time-to-failure, etc.) associated with the vehicle component (e.g., brake system, HVAC system, door/window seal, etc.) and/or any other characteristics of the vehicle component at the time the audio data was captured).
However, Kim does not explicitly disclose, decoupling from the frequency domain representation an audio profile that is associated with the vehicle system, identifying one or more active orders in the audio profile that represent an audio component that is in-phase with the vehicle system with respect to a resonant frequency or a whole number multiple thereof, analyzing the active orders to identify at least one fault indicator component corresponding to the known fault condition, based on at least one of magnitude or location of the active orders.
Nevertheless, Yoshizawa who is in the same field of endeavor of sound detection determination devices and methods discloses, decoupling from the computed frequency domain representation an audio profile that is associated with the vehicle system (0129, The noise elimination processing unit 101 is a processing unit which eliminates noise, from the frequency signal obtained by the FFT analysis unit 2402, by extracting a frequency signal of the to-be-extracted sound from the mixed sound) … (0201, the noise elimination device of the present invention is built into a different vehicle detection device, for example, the driver can be notified of the approach of a vehicle when a frequency signal of an engine sound is extracted from a mixed sound for each time-frequency domain).
It would have been prima facie obvious to one of ordinary skill in the art before the
effective filing date of the claimed invention to have modified Kim’s disclosure to incorporate the teachings of Yoshizawa. Yoshizawa teaches performing FFT processing on mixed sound to obtain a frequency signal and then eliminating noise from the FFT obtained frequency signal by extracting the frequency signal of the sound. Under BRI the extracted frequency signal of the extracted sound corresponds to a decoupled audio profile because it is a sound component separated from the computed frequency domain representation of the mixed audio signal. Kim further teaches that the isolated signature is associated with a vehicle component. This combination would be beneficial for the purpose to improve isolation of the vehicle component audio signature form the background noise and other mixed sounds, which would improve the accuracy of the vehicle condition determination.
Further justification for combining Kim with Yoshizawa not only comes from the state of the art but from Yoshizawa who shows the noise eliminating feature used on automotive engine sounds (0201, the noise elimination device of the present invention is built into a different vehicle detection device, for example, the driver can be notified of the approach of a vehicle when a frequency signal of an engine sound is extracted from a mixed sound for each time-frequency domain).
However even the combination of Kim and Yoshizawa does not explicitly disclose identifying one or more active orders in the audio profile that represent an audio component that is in-phase with the vehicle system with respect to a resonant frequency or a whole number multiple thereof, Analyzing the active orders to identify at least one fault indicator component corresponding to the known fault condition based on at least one of magnitude or location of the active orders.
However, Remboski who is in the same field of endeavor of fault detection systems having audio analysis discloses, identifying one or more active orders in the audio profile that represent an audio component that is in-phase with the vehicle system with respect to a resonant frequency or a whole number multiple thereof, (Paragraph 40, the present invention uses FFTF techniques to generate spectra that is “order” based as shown in FIGS. 2A-2E. The “orders” shown in the figures are defined as a sine wave cycle per revolution. It has been discovered that noise generated from rotating elements comes out at predictable orders), analyzing the active orders to identify at least one fault indicator component corresponding to the known fault condition (1, determining from the formed spectra whether the fault exists with the rotating element by comparing an amplitude of the formed spectra over a plurality of orders with a predetermined threshold for each order), based on at least one of magnitude or location of the active orders, (Paragraph 46, by analyzing the amplitude spikes associated with these repeating orders, one can determine if a fault has occurred by comparing the current spectra with spectra known to represent a rotating element that is operating properly (without faults)).
It would have been prima facie obvious to one of ordinary skill in the art before the
effective filing date of the claimed invention to have modified the combination of Kim and Yoshizawa to incorporate the teachings of Remboski for the benefit of order domain features, and per component decoupled spectra as inputs in Kim’s training pipeline. This would improve accuracy and be a routine design choice for predictable results.
Further justification for combining the combination of Kim and Yoshizawa with Remboski not only comes from the state of the art but from Remboski (Paragraph 26, the rectification process may be a mathematical absolute model or other digital representation known to those of ordinary skill in the art).
Regarding claim 2, Kim, Yoshizawa, and Remboski disclose the computer-implemented method as claimed in claim 1, as discussed supra. Additionally, Kim discloses each vehicle fault condition data set comprises a fault condition identifier for identifying the known fault condition (Kim, 0096, Lines 12-18, the fault log 458 may include an indication of the failure measurement detected and an identifier of the component(s)/system(s) involved (e.g., an audio signature associated with a failed operating status of a vehicle component). The fault log 458 may also store a snapshot of operating conditions leading up to the failure (e.g., a series of progressive audio signatures over at least a portion of the lifespan of the vehicle component)).
Regarding claim 6, Kim, Yoshizawa, and Remboski disclose the computer-implemented method as claimed in claim 1, as discussed supra. Additionally, Kim discloses identifying the at least one fault indicator component in the computed frequency domain representation comprises decomposing the computed frequency domain representation of the audio signal in dependence on the operating state of the vehicle system (Kim, 0017, Lines 5-12, one or more fast Fourier transforms (FFTs), Laplace transforms, principle component analysis, harmonic decomposition, and/or any other method of determining features associated therewith. Additionally, processing the audio data may include setting limits for a signal-to-noise ratio of the audio data, setting a target frequency of the audio data, including performing FFT processing on the audio data to transform the audio data from a time domain to a frequency domain), in dependence on the operating state of the vehicle system (0024, the first audio signature may be associated with operating conditions (or parameters) of the vehicle (and/or components, subcomponents, etc.). As non-limiting examples, the first audio signature may be associated with an engine speed, operating status of other components).
Regarding claim 7, Kim, Yoshizawa, and Remboski disclose the computer-implemented method as claimed in claim 6, as discussed supra. Additionally, Kim discloses decomposing the computed frequency domain representation of the audio signal comprising normalizing the computed frequency domain representation with respect to the operating state of the vehicle system (Kim, 0056, Lines 1-13, the scenario 200 describes generating different reference audio signatures, one while the vehicle 100 is parked and one while the vehicle 100 is in motion, other reference audio signatures may be generated under different operating condition. For example, rather than generating reference audio signatures while the vehicle 100 is parked and in transmit, reference audio signatures may be generated for the air suspension compressor under different ambient temperatures (e.g., 0 degrees, 100 degrees, etc.), environmental conditions (e.g., rain, snow, etc.), and so forth. Each of the different operating conditions may have impact the audio characteristics captured by the microphones, or as generated by the air suspension compressor, for example. Such references may therein be used to ensure a proper comparison and testing to ensure the functioning of the components).
Regarding claim 8, Kim, Yoshizawa, and Remboski disclose the computer-implemented method claimed in claim 1. Additionally, Kim discloses a non-transitory computer-readable medium having a set of instructions stored therein which, when executed, cause a processor to implement the computer-implemented method claimed in claim 1 (Kim, 0098, Lines 1-6, the memory 416 of the vehicle computing device(s) 404 and/or the memory 446 of the computing device(s) 440 are examples of non-transitory computer-readable media. The memory 416 and 446 may store an operating system and one or more software applications, instructions, programs, and/or data to implement the methods described herein and the functions attributed to the various systems).
Regarding claim 9, Kim, Yoshizawa, and Remboski disclose the computer-implemented method claimed in claim 1. Additionally, Kim discloses a diagnostic model for identifying a fault condition in a vehicle, the diagnostic model being trained in accordance with the computer-implemented method claimed in claim 1 (Kim, 0093, Lines 5-21, the training component 448 may generate the training data 454 using the log data 450. For instance, the training component 448 may label audio data associated with vehicle components with one or more measured parameters and/or characteristics of the vehicle components associated with the audio data 438. The audio data 438 and/or the measured parameters or characteristics may be obtained from the log data 450, the audio signatures 456, and/or the fault log 458. The label may include an indication of an operating status (e.g., normal, failed, time-to-failure, etc.) associated with the vehicle component (e.g., brake system, HVAC system, door/window seal, etc.) and/or any other characteristics of the vehicle component at the time the audio data was captured and/or at one or more times subsequent to the time the audio data was captured. The training component 448 may then use the training data 454 to train the machine learning component 452 to predict operating statuses associated with vehicle components based at least in part on receiving, as an input, the audio data 438 and/or the audio signatures 456 (or the audio signatures 436)).
Regarding claim 10, Kim, Yoshizawa, and Remboski disclose the diagnostic model claimed in claim 9. Additionally, Kim discloses a computational device having at least one electronic processor configured to implement the diagnostic model claimed in claim 9 (Kim, 0092, Lines 1-9, the vehicle 402 may connect to computing device(s) 440 via a network(s) 442 and may include one or more processor(s)).
Claims 3, and 11-14 are all rejected under 35 U.S.C. 103 as being unpatentable over Kim et al (US20210335064A1) in view of Yoshizawa et al. (US20100030562A1) Further in view of .Remboski et al. (US6775642B2), further in view of Ekkizogloy et al (US20180350167A1).
Regarding claim 3, Kim, Yoshizawa, and Remboski disclose the computer-implemented method as claimed in claim 1, as discussed supra. However, Ekkizogloy who is in the same field of endeavor of utilizing audio to diagnose vehicle malfunctions discloses, the operating data and the audio data are synchronized with each other (Ekkizogloy, 0055 Lines 1-6, in some embodiments, sensor data 570 can be correlated with audio data to help diagnose certain vehicular malfunctions. For instance, sensor data 570 and audio data can be correlated based on time to help determine the cause of an anomalous audio signal. For example, logic 550 may determine that an anomalous audio signal only occurs when an A/C compressor is turned on or when the engine RPMs rise above a certain threshold value).
One of ordinary skill in the art prior to the effective filing date of the given invention would have been motivated to combine the combination of Kim, Yoshizawa, and Remboski with Ekkizogloy to ensure that the vehicle sensor data did not disrupt the diagnostic audio. Utilizing time based synchronization would ensure that the noises picked up by the machine learning algorithm would not be misinterpreted for sensor data from a different time, or be misinterpreted for data from a different vehicle sensor.
Justification for combining Kim, Remboski and Ekkizogloy’s disclosures not only comes from the state of the art but from Ekkizogloy, (Ekkizogloy, 0073, Lines 9-10, one of ordinary skill in the art would recognize and appreciate many variations, modifications, and alternatives of the method 1000). Thus, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Kim, Yoshizawa, and Ekkizogloy to ensure that the vehicle sensor data did not disrupt the diagnostic audio.
Regarding claim 11, Ekkizogloy discloses, a vehicle monitoring system for identifying a fault condition in a vehicle system of a vehicle; the vehicle monitoring system comprising a controller (Ekkizogloy, 0040, In some cases, processor 440 may include one or more microcontrollers (MCUs), digital signal processors (DSPs), or the like, with supporting hardware and/or firmware (e.g., memory, programmable I/Os, etc.), as would be understood by one of ordinary skill in the art). However Ekkizogloy does not explicitly disclose the method of claim 1.
However, as discussed supra Kim, Yoshizawa, and Ekkizogloy disclose the method of claim 1. Kim discloses, a computer-implemented method of training a diagnostic model for identifying a fault condition in a vehicle system, the method comprising: receiving a plurality of vehicle fault condition data sets, each vehicle fault condition data set being associated with a known fault condition of a vehicle system (Kim, 0118, Lines 8-17, a health of the component may be determined by a human labeler to generate labeled training data to train the machine learned model. Moreover, the labels may be applied based on training data indicative of previous faults and/or replaced components. For example, the audio data associated with a component that failed may be classified for use by the machine learning model to identify faults in the future), wherein the vehicle fault condition data sets each comprise: audio data representing an audio signal generated by a microphone during operation of the vehicle system having the known fault condition (Abstract, the systems and methods receive audio data generated by a microphone of the vehicle, where the audio data represents sound of the component),
and operating data indicating an operating state of the vehicle system (Abstract, Based on the audio data, a condition of the vehicle or the component may be determined, and based on the condition, the vehicle may be commissioned for use or decommissioned), processing each vehicle fault condition data set, the processing comprising: applying a Fast Fourier Transform to the audio data to generate a computed frequency domain representation of the audio signal, (0017, processing the audio data may include setting limits for a signal-to-noise ratio of the audio data, setting a target frequency of the audio data, including performing FFT processing on the audio data to transform the audio data from a time domain to a frequency domain)
), and training the diagnostic model (Kim, 0137, Lines 12-18, the training component 448 may generate the training data 454 using the log data 450. to identify the at least one fault condition in dependence on the identification of the at least one fault indicator component (0137, the training component 448 may label audio data associated with vehicle components with one or more measured parameters and/or characteristics of the vehicle components associated with the audio data 438. The audio data 438 and/or the measured parameters or characteristics may be obtained from the log data 450, the audio signatures 456, and/or the fault log 458), in each vehicle fault condition data set (The label may include an indication of an operating status (e.g., normal, failed, time-to-failure, etc.) associated with the vehicle component (e.g., brake system, HVAC system, door/window seal, etc.) and/or any other characteristics of the vehicle component at the time the audio data was captured).However even the combination of Kim and Yoshizawa does not explicitly disclose identifying one or more active orders in the audio profile that represent an audio component that is in-phase with the vehicle system with respect to a resonant frequency or a whole number multiple thereof, Analyzing the active orders to identify at least one fault indicator component corresponding to the known fault condition based on at least one of magnitude or location of the active orders.
However, Remboski who is in the same field of endeavor of fault detection systems having audio analysis discloses, identifying one or more active orders in the audio profile that represent an audio component that is in-phase with the vehicle system with respect to a resonant frequency or a whole number multiple thereof, (Paragraph 40, the present invention uses FFTF techniques to generate spectra that is “order” based as shown in FIGS. 2A-2E. The “orders” shown in the figures are defined as a sine wave cycle per revolution. It has been discovered that noise generated from rotating elements comes out at predictable orders), analyzing the active orders to identify at least one fault indicator component corresponding to the known fault condition (1, determining from the formed spectra whether the fault exists with the rotating element by comparing an amplitude of the formed spectra over a plurality of orders with a predetermined threshold for each order), based on at least one of magnitude or location of the active orders, (Paragraph 46, by analyzing the amplitude spikes associated with these repeating orders, one can determine if a fault has occurred by comparing the current spectra with spectra known to represent a rotating element that is operating properly (without faults)).
Regarding claim 12, Kim, Yoshizawa, Remboski, and Ekkizogloy disclose, a vehicle monitoring system as claimed in claim 11, as discussed supra. Additionally, Ekkizogloy discloses the controller comprises at least one electronic processor (Ekkizogloy, 0040, Lines 1-8, in some embodiments, processor 440 can include one or more microprocessors (μCs) and may control the execution of software (e.g., logic, database management, access, and retrieval), controls, and communication between various electrical components of system 400. In some cases, processor 440 may include one or more microcontrollers (MCUs), digital signal processors (DSPs), or the like, with supporting hardware and/or firmware (e.g., memory, programmable I/Os, etc.), as would be understood by one of ordinary skill in the art), the at least one electronic processor comprising: at least one electrical input for receiving the audio signal from the microphone and for receiving the operating data from a vehicle communication system (Ekkizogloy, 0006, Lines 3-5, the one or more processors to perform operations including: receiving, by a processor, audio data from at least one microphone disposed on a vehicle, the audio data corresponding to sounds generated by the vehicle); and at least one electrical output for outputting the audio data and the operating data (Ekkizogloy, 0004, Lines 1-7, inputting, by the processor, sensor data into the analysis module having the trained model, the sensor data from at least one sensor disposed on the vehicle, where the trained model further associates various sensor data, along with the various audio sounds, and the corresponding vehicular malfunction conditions, and where the hypothesized vehicular malfunction condition obtained from the analysis module can be based on the audio data and the sensor data).
Regarding claim 13, Kim, Yoshizawa, Remboski, and Ekkizogloy disclose a vehicle monitoring system as claimed in claim 11, as discussed supra. Additionally, Ekkizogloy discloses the audio data and the operating data are output to a remote server for processing by the diagnostic model; (Ekkizogloy, 0004, Lines 1-7, each vehicle 810-830 can offload resources configured for automatic detection of vehicular malfunctions to off-site resources in cloud 840. In some embodiments, cloud 840 may contain logic (as described above), a database, and one or more processors to execute some or all aspects of the analysis discussed above); and a fault identification report is received from the remote server indicating the one or more identified fault condition (Ekkizogloy, 0059, Lines 21-23, the many variations and alternatives of sharing resources between individual vehicles (e.g., vehicles 810-830) and cloud 840 would be understood by one of ordinary skill in the art).
Regarding claim 14, Kim, Yoshizawa, Remboski, and Ekkizogloy disclose a vehicle comprising a vehicle monitoring system as claimed in claim 11, as discussed supra. Additionally, Ekkizogloy discloses, the vehicle comprising a microphone for capturing the audio signal (Ekkizogloy, 0059, Lines 8-10, vehicle 810 may receive audio data from a local array of microphones and transfer the audio data to the cloud to determine a location of the audio source).
Additional Prior Art
Additional prior art references that were not used in the rejections discussed supra, but may be relevant to the applicant include the following: US20170257073A1 Hera et al. March 2, 2016. And US6289735B1 Dister et al. September 29, 1998. US6289735B1 appears to disclose a machine component health diagnostic system that generates a frequency domain vibration signature and analyzes magnitude at critical frequencies to determine operating conditions. This maps to the amended claim language of a “fault indicator component” based on magnitude. Additionally, US20170257073A1 appears to disclose a vehicle engine sound system that receives a transducer signal, uses vehicle data to determine a frequency, and extracts harmonics from the engine sound, including phase and frequency information. This supports the amended claim limitation of active audio profile processing.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SHANE E DOUGLAS whose telephone number is (703)756-1417. The examiner can normally be reached Monday - Friday 7:30AM - 5:00PM.
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, Christian Chace can be reached on (571) 272-4190. 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.
/S.E.D./Examiner, Art Unit 3665
/CHRISTIAN CHACE/Supervisory Patent Examiner, Art Unit 3665
Prosecution Insights