DETAILED ACTION
This FINAL action is responsive to the amendment filed 3/26/2026.
In the amendment Claims 1-8 and 11-20 are pending. Claims 9-10 were canceled. Claims 1 and 18 are the independent claims.
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Withdrawn Objections
4. The objection to claim 1 has been withdrawn in light of the persuasive arguments.
Withdrawn Rejections
5. The 35 U.S.C. 112(b) rejection of claims 1-20 have been withdrawn in light of the amendment.
6. The 35 U.S.C. 101 abstract idea rejection of claims 1-13 and 15-20 has been withdrawn in light of the amendment.
7. The 35 U.S.C. 102(a)(1) rejection of claims 1-2, 4-13, 16 and 18-20 with cited reference of Sallem (U.S. Pub 2021/0065733) has been withdrawn in light of the amendment.
8. The 35 U.S.C. 103 rejection of claim 3 with cited references of Sallem (U.S. Pub 2021/0065733) in view of Sharma (U.S. Pub 2021/0287661) has been withdrawn in light of the amendment.
9. The 35 U.S.C. 103 rejection of claims 14-15 with cited references of Sallem (U.S. Pub 2021/0065733) in view of DeLuca (U.S. Pub 2021/0174140) has been withdrawn in light of the amendment.
10. The 35 U.S.C. 103 rejection of claim 17 with cited references of Sallem (U.S. Pub 2021/0065733) in view of Brahma (U.S. Pub 2022/0261590) has been withdrawn in light of the amendment.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
11. Claims 1-2, 4-8, 11-13, 16 and 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Sallem (U.S. Pub 2021/0065733, filed Aug. 29, 2019) in view of Zahdeh (U.S. Pub 2016/0370255, filed Apr. 21, 2016).
Regarding Independent claim 1, Sallem discloses A system comprising:
a processor system; b) a memory system, the memory system storing machine instructions, which, when implemented, cause the processor system to generate tools for building an Artificial Intelligence (AI) model that identifies events associated with a vehicle (see paragraphs 66-67, discloses a processor and memory system for building a model via machine learning (ML) technologies and audio classification for vehicle application including classifier training to identify sound based events of the vehicle);
the tools including i) a tool for selecting datasets, characterizing a type of event, for training an AI module, the training of the AI module including training the AI model (see paragraphs 51 and 54, discloses receiving audio data of sounds in an environment and used for training machine learning object classifier with audio frames labeled based on a type of objects. Further disclosing augmentation selection unit that selects frames of the audio data to augment. In addition, paragraphs 31 and 47, discloses characterization of environmental and/or vehicle events);
ii) a tool for enhancing the datasets, the tool for enhancing the datasets being configured to alter the datasets to match parameters of the datasets to sounds, as received at the AI module while operating in a field of operation (see paragraphs 53 and 56, discloses expanding audio data into larger diverse audio data set via selectively augmenting frames of the audio data 401. Further describing multiple augmentation techniques such as temporal modification augmentation, distance adjustment augmentation and environmental augmentation technique that includes inserting noise. Also disclosing simulating the sound being emitted from the object in different environments and operational states while matching field conditions through environmental noise simulation);
iii) a tool for building the AI model based on the datasets that were enhanced (see paragraphs 7, 51 & 53, discloses generating augmented audio dataset 402 for training ML object classifier. Further describing enhanced datasets via allowing the ML classifier to be trained to classify sound measurements corresponding to object types such as with a lower generalization error and increased robustness); and Sallem discloses a vehicle-based acoustic sensing and classification system using audio as a sensor input that are mounted to the vehicle. Further suggesting its use to detect engine related faults via engine friction (see paragraph 31). Sallem fails to explicitly teaches that an AI module is placed on a housing of the engine to receive and analyze sounds from the engine.
Zahdeh discloses:
At least one of the AI modules being placed on a bell housing of an engine of the vehicle to receive and analyze sounds from the engine (see paragraphs 4 and 30-51, specifically paragraphs 31-32 discloses acoustic sensor may be mounted anywhere on the engine assembly including at or near the flywheel to detect engine events). It would have been obvious for one of ordinary skill in the art before the effective filing date of the application to have supported sensor-placement anywhere on the engine including the bell housing to identify engine events from sound signatures has doing so would improve the accuracy of vehicle-event identification in real operating conditions. Zahdeh further indicates in paragraph 31 that sensor can be mounted essentially anywhere on the engine assembly and closer placement improves event detection accuracy.
Regarding Dependent claim 2, with dependency of claim 1, Sallem discloses the tool for enhancing the datasets including a tool for adding sounds to the datasets, the sounds characterizing a background noise (see paragraphs 6 and 56, including the explanation provided in the Independent claim).
Regarding Dependent claim 4, with dependency of claim 2, Sallem discloses the tool for adding the sounds including a selection for setting a gain that determines the amplitude of the background noise (see paragraphs 6 and 56, including the explanation provided in the Independent claim).
Regarding Dependent claim 5, with dependency of claim 1, Sallem discloses a tool for filtering the datasets the tool for the filtering including a tool for selecting a range of mean values of a parameter characterizing an event to accept in a set of filtered data (see paragraphs 29 & 38, including the explanation provided in the Independent claim).
Regarding Dependent claim 6, with dependency of claim 5, Sallem discloses the tool for the filtering including a tool for selecting a range of sample rates to accept in a set of data (see paragraphs 29 & 38, including the explanation provided in the Independent claim).
Regarding Dependent claim 7, with dependency of claim 5, Sallem discloses the tool for the filtering including a tool for selecting a range of precisions of data to accept in a set of the data (see paragraphs 29 & 38, including the explanation provided in the Independent claim).
Regarding Dependent claim 8, with dependency of claim 5, Sallem discloses the tool for the filtering including a tool for selecting a range of alignments accepted a set of data (see paragraphs 29 & 38, including the explanation provided in the Independent claim).
Regarding Dependent claim 11, with dependency of claim 1, Sallem discloses the AI module being placed in a wheel well of the vehicle (see paragraphs 29 & 38, including the explanation provided in the Independent claim).
Regarding Dependent claim 12, with dependency of claim 1, Sallem discloses the machine instructions include instructions, which, when implemented by the processor system, cause the system to determine a range of the events that are detectable by the datasets (see paragraphs 51 & 53, including the explanation provided in the Independent claim).
Regarding Dependent claim 13, with dependency of claim 1, Sallem discloses an interrupt that communicates with the AI module, which is configured to send an alert to another device, when a specified event is detected (see paragraphs 7 & 31, including the explanation provided in the Independent claim).
Regarding Dependent claim 16, with dependency of claim 1, Sallem discloses an optical sensor, and the datasets include a combination of optical data and acoustic data (see paragraphs 22-24, 32 & 43, including the explanation provided in the Independent claim).
Regarding Independent claim 18, Sallem discloses A method comprising:
building, by a machine, an Artificial Intelligence (AI) module, the machine including a processor system and a memory system, the memory system storing machine instructions, which, when implemented by the processor system, causes the machine to implement the method, the building of the AI module including b) selecting datasets, by a data selection tool, the datasets characterizing a type of event, for training the AI module (see paragraphs 51 and 54, discloses receiving audio data of sounds in an environment and used for training machine learning object classifier with audio frames labeled based on a type of objects. Further disclosing augmentation selection unit that selects frames of the audio data to augment. In addition, paragraphs 31 and 47, discloses characterization of environmental and/or vehicle events); and
d) enhancing the datasets by a toolset for enhancing data, the enhancing including altering the data to match parameters of the datasets to sounds received at the AI module during a field operation (see paragraphs 53 and 56, discloses expanding audio data into larger diverse audio data set via selectively augmenting frames of the audio data 401. Further describing multiple augmentation techniques such as temporal modification augmentation, distance adjustment augmentation and environmental augmentation technique that includes inserting noise. Also disclosing simulating the sound being emitted from the object in different environments and operational states while matching field conditions through environmental noise simulation); and
the building of an AI model, the AI model being based on the datasets that were enhanced (see paragraphs 7, 51 & 53, discloses generating augmented audio dataset 402 for training ML object classifier. Further describing enhanced datasets via allowing the ML classifier to be trained to classify sound measurements corresponding to object types such as with a lower generalization error and increased robustness), and Sallem discloses a vehicle-based acoustic sensing and classification system using audio as a sensor input that are mounted to the vehicle. Further suggesting its use to detect engine related faults via engine friction (see paragraph 31). Sallem fails to explicitly teaches that an AI module is placed on a housing of the engine to receive and analyze sounds from the engine.
Zahdeh discloses:
b) placing at least one of the AI modules on a bell housing of an engine of a vehicle, therein, facilitating quick fault diagnosis via signals from sensors (see paragraphs 4 and 30-51, specifically paragraphs 31-32 discloses acoustic sensor may be mounted anywhere on the engine assembly including at or near the flywheel to detect engine events). It would have been obvious for one of ordinary skill in the art before the effective filing date of the application to have supported sensor-placement anywhere on the engine including the bell housing to identify engine events from sound signatures has doing so would improve the accuracy of vehicle-event identification in real operating conditions. Zahdeh further indicates in paragraph 31 that sensor can be mounted essentially anywhere on the engine assembly and closer placement improves event detection accuracy.
Regarding Dependent claim 19, with dependency of claim 18, Sallem discloses the building of the AI module further including extracting features from the datasets (see paragraph 52, including the explanation provided in the Independent claim).
Regarding Dependent claim 20, with dependency of claim 18, Sallem discloses the datasets including prior recorded data and publicly available data (see paragraph 51, including the explanation provided in the Independent claim).
12. Claim 3 is rejected under 35 U.S.C. 103 as being unpatentable over Sallem (U.S. Pub 2021/0065733, filed Aug. 29, 2019) in view of Zahdeh (U.S. Pub 2016/0370255, filed Apr. 21, 2016) further in view of Sharma (U.S. Pub 2021/0287661, filed Mar. 10, 2021).
Regarding Dependent claim 3, with dependency of claim 2, Sallem discloses a vehicle-based acoustic sensing and classification system using audio as a sensor input that are mounted to the vehicle. Further suggesting its use to detect engine related faults via engine friction (see paragraph 31). Sallem fails to explicitly teaches that an AI module is placed on a housing of the engine to receive and analyze sounds from the engine. Zahdeh discloses that acoustic sensor may be mounted anywhere on the engine assembly including at or near the flywheel to detect engine events (see paragraphs 31-32). Zahdeh fails to teach modifying a signal-to-noise-ratio. Sharma discloses the tool for adding the sounds including a selection for setting a signal-to-noise ratio (see paragraph 139, discloses an augmentation process that adds a target signal-to-noise ratio via gain factor to the audio data). It would have been obvious for one of ordinary skill in the art before the effective filing date of the application to have implemented known augmentation techniques that include signal-to-noise ratio adjustments which supports augmentation across different domains has disclosed by Sharma in paragraph 3.
13. Claims 14-15 are rejected under 35 U.S.C. 103 as being unpatentable over Sallem (U.S. Pub 2021/0065733, filed Aug. 29, 2019) in view of Zahdeh (U.S. Pub 2016/0370255, filed Apr. 21, 2016) further in view of DeLuca (U.S. Pub 2021/0174140, filed Dec. 5, 2019).
Regarding Dependent claim 14, with dependency of claim 13, Sallem discloses a vehicle-based acoustic sensing and classification system using audio as a sensor input that are mounted to the vehicle. Further suggesting its use to detect engine related faults via engine friction (see paragraph 31). Sallem fails to explicitly teaches that an AI module is placed on a housing of the engine to receive and analyze sounds from the engine. Zahdeh discloses that acoustic sensor may be mounted anywhere on the engine assembly including at or near the flywheel to detect engine events (see paragraphs 31-32). Zahdeh fails to teach IoT devices. DeLuca discloses a ML audio training system that support implementation in IoT devices (see abstract & paragraphs 20-21). It would have been obvious for one of ordinary skill in the art before the effective filing date of the application to have supported use of IoT modem has it improves connectivity and analytics has disclosed by DeLuca in paragraph 2.
Regarding Dependent claim 15, with dependency of claim 1, Sallem discloses a vehicle-based acoustic sensing and classification system using audio as a sensor input that are mounted to the vehicle. Further suggesting its use to detect engine related faults via engine friction (see paragraph 31). Sallem fails to explicitly teaches that an AI module is placed on a housing of the engine to receive and analyze sounds from the engine. Zahdeh discloses that acoustic sensor may be mounted anywhere on the engine assembly including at or near the flywheel to detect engine events (see paragraphs 31-32). Zahdeh fails to teach support for a mobile device for communicating with the AT module. DeLuca discloses a) the AI model being stored in the AT module; b) the AT model also being stored in a memory unit on a device deployed remotely from the AT module in a network; and c) an application stored on a mobile device for communicating with the AT module and the AT module being deployed remotely from the mobile device (see paragraph 17, 19 & 32). It would have been obvious for one of ordinary skill in the art before the effective filing date of the application to have supported use of IoT devices along with mobile phone support has it improves connectivity and analytics has disclosed by DeLuca in paragraph 2.
14. Claims 17 is rejected under 35 U.S.C. 103 as being unpatentable over Sallem (U.S. Pub 2021/0065733, filed Aug. 29, 2019) in view of Zahdeh (U.S. Pub 2016/0370255, filed Apr. 21, 2016) further in view of Brahma (U.S. Pub 2022/0261590, filed Feb. 18, 2021).
Regarding Dependent claim 17, with dependency of claim 1, Sallem discloses a vehicle-based acoustic sensing and classification system using audio as a sensor input that are mounted to the vehicle. Further suggesting its use to detect engine related faults via engine friction (see paragraph 31). Sallem fails to explicitly teaches that an AI module is placed on a housing of the engine to receive and analyze sounds from the engine. Zahdeh discloses that acoustic sensor may be mounted anywhere on the engine assembly including at or near the flywheel to detect engine events (see paragraphs 31-32). Zahdeh fails to teach fusion of sensors that include temperature measurements. Brahma discloses a temperature sensor, and the datasets include a combination of temperature data and acoustic data (see paragraph 29, discloses sensor fusion that includes temperature and audio data for training a machine learning model). It would have been obvious for one of ordinary skill in the art to have supported sensor fusion system that comprises temperature measurements with sound has it helps to improve classification using multiple attributes in detecting vehicle faults.
It is noted that any citation [[s]] to specific, pages, columns, lines, or figures in the prior art references and any interpretation of the references should not be considered to be limiting in any way. A reference is relevant for all it contains and may be relied upon for all that it would have reasonably suggested to one having ordinary skill in the art. [[See, MPEP 2123]]
Response to Arguments
15. Applicant’s arguments filed 3/26/2026 has been considered but are moot in view of the new grounds of rejection.
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 MANGLESH M PATEL whose telephone number is (571)272-5937. The examiner can normally be reached on M-F from 10:30 am to 7:30 pm.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Erin D. Bishop, can be reached at telephone number 571-270-3713. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from Patent Center. Status information for published applications may be obtained from Patent Center. Status information for unpublished applications is available through Patent Center for authorized users only. Should you have questions about access to Patent Center, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
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) Form at https://www.uspto.gov/patents/uspto-automated- interview-request-air-form.
/Manglesh M Patel/
Primary Examiner, Art Unit 3665
5/27/2026
Prosecution Insights