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 .
Priority
Applicant’s claim for the benefit of a prior-filed application under 35 U.S.C. 119(e) or under 35 U.S.C. 120, 121, 365(c), or 386(c) is acknowledged. Applicant has not complied with one or more conditions for receiving the benefit of an earlier filing date under 35 U.S.C. 119(e) as follows:
The later-filed application must be an application for a patent for an invention which is also disclosed in the prior application (the parent or original nonprovisional application or provisional application). The disclosure of the invention in the parent application and in the later-filed application must be sufficient to comply with the requirements of 35 U.S.C. 112(a) or the first paragraph of pre-AIA 35 U.S.C. 112, except for the best mode requirement. See Transco Products, Inc. v. Performance Contracting, Inc., 38 F.3d 551, 32 USPQ2d 1077 (Fed. Cir. 1994).
The disclosure of the prior-filed applications, Application Nos. 63/062,850 and 63/116,591, fails to provide adequate support or enablement in the manner provided by 35 U.S.C. 112(a) or pre-AIA 35 U.S.C. 112, first paragraph for one or more claims of this application. Neither provisional application disposes the specific inputs used as training data for the neural network; therefore, there is no enablement present in the provisional applications for the claim limitations pertaining to the training of the neural network. Therefore, the effective filing date is the filing date of parent application 17/396,710, August 8, 2021.
Response to Arguments
Applicant’s arguments, see page 8, filed 06/04/2026, with respect to the double patenting rejection have been fully considered and are persuasive in light of the filed terminal disclaimer. The double patenting rejection of 03/16/2026 has been withdrawn.
Applicant's arguments filed on 06/04/2026 with respect to the rejection under 35 USC 103 have been fully considered but they are not persuasive. The applicant makes the following arguments:
The neural network of Wang et al. is an autoencoder, which reconstructs input data and measures a reconstruction loss, which is fundamentally different from the neural network of the claimed invention, which takes diagnostic inputs and produces different outputs.
The remaining cited references also fail to teach the limitation.
Regarding argument A: The teachings of Seidel et al. are cited with respect to the output of a health metric using an unspecified objective function, with Wang et al. merely cited as teaching a specific objective function. A person possessing ordinary skill in the art would have found it obvious to use this particular objective function for the reasons discussed below.
Regarding argument B: As discussed above, the previously applied combination of references teaches the limitation in question. Therefore, the argument pertaining to the remaining cited references is moot.
Applicant’s argument that the Office action filed 03/16/2026 does not provide any specific reasoning for the rejection under 35 USC § 112(b) is persuasive. After further consideration, the claims are rejected under 35 USC § 112(b) for the reasons given below.
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.
Claims rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Regarding claims 1, 10, and 19: The claim recites “generate, based on collected diagnostic information, a set of one or more health metrics” and “collecting, from the components of the vehicular communication network of the first vehicle, diagnostic information including at least one loss metric”. It is unclear whether these two limitations refer to the same collected diagnostic information or different collected diagnostic information. For the purposes of examination, it will be assumed that the diagnostic information of both limitations is the same.
Regarding claims 4 and 13: The claim recites “retraining the trained neural network model based on collected diagnostic information”. It is not clear whether this is the same collected diagnostic information as in claim 1 or different collected diagnostic information. For the purposes of examination, the claim will be interpreted as referring to the same collected diagnostic information as claim 1.
Regarding claims 2, 3, 5-9, 11, 12, and 14-18: The claims fail to cure the deficiencies of the independent claims and are thus indefinite for at least the same reasons.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1, 2, 4-7, 10, 11, and 13-16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Seidel et al. (US 20210366207) in view of Chini et al. (US 20170134215) in view of Wang et al. (US 20220303288) in view of Keiser et al. (US 20220092321).
Claim 1.
Seidel et al. teaches:
the trained neural network model having been trained to generate, based on collected diagnostic information, a set of one or more health metrics indicating a likelihood of failure of components of the vehicular
(Seidel – [0005]) “configured to access diagnostic data for at least one component of the motor vehicle, wherein the diagnostic data links information about at least one operating parameter of the motor vehicle with information about the at least one component, wherein the diagnostic system is configured to evaluate information about a probability of an occurrence of a fault in the motor vehicle depending on the diagnostic data and depending on the information about the at least one operating parameter”
(Seidel – [0045]) “With other preferred embodiments, diagnostic system 300 is configured to execute algorithms of artificial intelligence, AI. For this purpose, for example, at least one AI subsystem 320 can be provided, which, for example, comprises one or more artificial neural networks”
collecting, from the components of the vehicular
(Seidel – [0009]) “it is provided that the diagnostic system is configured to receive vehicle information of the motor vehicle, wherein the vehicle information comprises at least one of the following elements: … operating data characterizing an operation of at least one component of the motor vehicle, one or more fault codes characterizing a fault of at least one component of the motor vehicle.”
for a given link, inputting the collected diagnostic information, including the at least one
(Seidel – [0009]) “it is provided that the diagnostic system is configured to receive vehicle information of the motor vehicle, wherein the vehicle information comprises at least one of the following elements: … operating data characterizing an operation of at least one component of the motor vehicle, one or more fault codes characterizing a fault of at least one component of the motor vehicle.”
outputting a maintenance recommendation based on the set of health metrics generated by the trained neural network model
(Seidel – [0062]) “After the execution 330 of the diagnosis, diagnostic system 300 can transmit another optional message n7 to data processing device 100 which may contain a diagnosis result or a repair recommendation, for example.”
While Seidel et al. teaches determining a fault in a vehicle system, Seidel et al. does not explicitly teach determining a fault in a vehicle communications system; however, Chini et al. teaches:
a vehicular communication network comprising communication links… a set of one or more health metrics indicating a likelihood of failure of components of the vehicular communication network to perform in a specified manner
(Chini – [0032]) “The PHY device 206a is configured to measure high resolution echo responses received over the UTP cable 210 (and potentially other components) to perform a communication link diagnosis.”
diagnostic information including at least one loss metric with respect to a strength of signals transmitted over the communication links
(Chini – [0031]) “Additional information can be provided to indicate signalling quality, insertion loss, and return loss of the communication links used in in-vehicle networks.”
It would have been obvious to one possessing ordinary skill in the art to combine these teachings, modifying the general vehicle diagnosis system of Seidel et al. with the vehicle communications diagnosis system of Chini et al. Both Seidel et al. and Chini et al. are directed towards diagnosing faults in vehicle systems; therefore, a person of ordinary skill in the art would have recognized that the teachings could be combined with predictable results.
Seidel et al. does not explicitly teach an objective function that is a weighted sum of a cross-entropy and a mean-square error; however, Wang et al. teaches:
wherein the neural network model is trained using an objective function that is a weighted sum of a cross-entropy and a mean-square error with respect to the link health indication and the at least one loss metric
(Wang – [0017]) “the overall reconstruction loss is formulated as a weighted sum of individual loss terms for each feature, where each loss term is something specific to and appropriate for that feature (e.g., for internet proxy data: mean-squared error for numerical features, cross-entropy for categorical, etc.)”
It would have been obvious to one possessing ordinary skill in the art before the effective filing date to combine these teachings, modifying the diagnosis system of Seidel et al. with the reconstruction loss of Wang et al. Both Seidel et al. and Wang et al. pertain to the use of neural networks to diagnose a fault; therefore, a person of ordinary skill in the art would have recognized that the teachings could be combined with predictable results. One would have been motivated to do this in order to arrive at a loss function which is appropriate for all features of the diagnosed system (Wang – [0017]).
Seidel et al. does not explicitly teach downloading the neural network to a vehicle computer; however, Keiser et al. teaches:
downloading a trained neural network model to a computer in a first vehicle
(Keiser – [0042]) “The retrained CNN 200 can be downloaded to a computing device 115 in a vehicle 110”
It would have been obvious to one possessing ordinary skill in the art before the effective filing date to combine these two teachings, downloading the diagnostic AI of Seidel in a similar fashion to the neural network of Keiser. One would be motivated to do this because one can save time and computational expense by training one neural network and distributing it to multiple vehicles, rather than training a separate neural network for each vehicle.
Claim 2.
The combination of Seidel et al., Chini et al., Wang et al., and Keiser et al. teaches all the limitations of claim 1, as discussed above. Seidel et al. further teaches:
wherein the neural network model is trained based on (i) collected diagnostic information from components of vehicular communication networks of a plurality of second vehicles, and (ii) collected failure information of one or more of the components of the vehicular communication networks in the plurality of second vehicles
(Seidel – [0009]) “it is provided that the diagnostic system is configured to receive vehicle information of the motor vehicle, wherein the vehicle information comprises at least one of the following elements: … operating data characterizing an operation of at least one component of the motor vehicle, one or more fault codes characterizing a fault of at least one component of the motor vehicle.”
(Seidel – [0010]) “it is provided that the diagnostic system is configured to use the vehicle information to… train or validate one or more AI subsystems of the diagnostic system.”
(Seidel – [0025]) “it is provided that the vehicle information is used to… build or supplement a database with the respective information, and/or to train or validate one or more AI subsystems of a diagnostic system. This enables a result of the diagnosis to be dependent on other vehicles for which the diagnostic data according to the vehicle information is also true.”
Claim 4.
The combination of Seidel et al., Chini et al., Wang et al., and Keiser et al. teaches all the limitations of claim 1, as discussed above. Seidel et al. further teaches:
further comprising retraining the trained neural network model based on the collected diagnostic information from the first vehicle
(Seidel – [0009]) “it is provided that the diagnostic system is configured to receive vehicle information of the motor vehicle, wherein the vehicle information comprises at least one of the following elements: … operating data characterizing an operation of at least one component of the motor vehicle, one or more fault codes characterizing a fault of at least one component of the motor vehicle.”
(Seidel – [0010]) “it is provided that the diagnostic system is configured to use the vehicle information to… train or validate one or more AI subsystems of the diagnostic system.”
Claim 5.
The combination of Seidel et al., Chini et al., Wang et al., and Keiser et al. teaches all the limitations of claim 1, as discussed above. Seidel et al. further teaches:
further comprising retraining the trained neural network model based on the failure information from one or both of (i) the first vehicle and (ii) the plurality of second vehicles
(Seidel – [0009]) “it is provided that the diagnostic system is configured to receive vehicle information of the motor vehicle, wherein the vehicle information comprises at least one of the following elements: … operating data characterizing an operation of at least one component of the motor vehicle, one or more fault codes characterizing a fault of at least one component of the motor vehicle.”
(Seidel – [0010]) “it is provided that the diagnostic system is configured to use the vehicle information to… train or validate one or more AI subsystems of the diagnostic system.”
Claim 6.
The combination of Seidel et al., Chini et al., Wang et al., and Keiser et al. teaches all the limitations of claim 1, as discussed above. Chini et al. further teaches:
wherein the at least one loss metric comprises one or more parameters selected from a group of parameters including an overall insertion loss (IL), an overall return loss (RL), a near-end RL and a far-end RL
(Chini – [0031]) “Additional information can be provided to indicate signalling quality, insertion loss, and return loss of the communication links used in in-vehicle networks.”
It would have been obvious to combine these teachings for the reasons given in discussion of claim 1.
Claim 7.
The combination of Seidel et al., Chini et al., Wang et al., and Keiser et al. teaches all the limitations of claim 1, as discussed above. Chini et al. further teaches:
wherein collecting the diagnostic information comprises collecting one or more link quality metrics for one or more of the communication links
(Chini – [0045]) “In addition, a Signal Quality Indicator (SQI) 324 can be used to provide an SCSI parameter indicative of the quality of any signal recovered by the receiver 304 over the communication link.”
It would have been obvious to combine these teachings for the reasons given in discussion of claim 1.
Claim 10.
Seidel et al. teaches:
a memory installed in a first vehicle
(Seidel – [0066]) “Data processing device 100a also comprises a computing device 120… Computing device 120 is assigned a memory device 122 which is configured to at least temporarily store a computer program PRG. Computer program PRG can be configured to execute the method, for example.”
a processor, configured to:
(Seidel – [0066]) “Data processing device 100a also comprises a computing device 120… Computing device 120 is assigned a memory device 122 which is configured to at least temporarily store a computer program PRG. Computer program PRG can be configured to execute the method, for example.”
The rest is rejected by the same rationale as claim 1.
Claim 11.
Rejected by the same rationale as claim 2.
Claim 13.
Rejected by the same rationale as claim 4.
Claim 14.
Rejected by the same rationale as claim 5.
Claim 15.
Rejected by the same rationale as claim 6.
Claim 16.
Rejected by the same rationale as claim 7.
Claim(s) 3 and 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over the combination of Seidel et al., Chini et al., Wang et al., and Keiser et al. as applied to claims 1 and 10 above, and further in view of Ricci (US 20190279447).
Claim 3.
The combination of Seidel et al., Chini et al., Wang et al., and Keiser et al. teaches all the limitations of claim 1, as discussed above. Seidel et al. does not explicitly teach collecting information from sensors; however, Ricci teaches:
wherein collecting the diagnostic information comprises collecting information from sensors associated with the components of the vehicular communication network in the first vehicle
(Ricci – [0021]) “Embodiments include a vehicle diagnostic detection and communication system comprising a vehicle control system configured to: receive sensor data from one or more vehicle sensors”
It would have been obvious to one possessing ordinary skill in the art before the effective filing date to combine these teachings, using the sensors of Ricci to provide input to the vehicle diagnostic system of Seidel et al. Both Seidel et al. and Ricci are directed towards vehicle diagnostics systems; therefore, a person of ordinary skill in the art would have recognized that the teachings could be combined with predictable results. This is a use of a known technique (using sensors to obtain input data) to improve a similar device (vehicle diagnostic systems) in the same way.
Claim 12.
Rejected by the same rationale as claim 3.
Claim(s) 8 and 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over the combination of Seidel et al., Chini et al., Wang et al., and Keiser et al. as applied to claims 1 and 10 above, and further in view of Cloetens (US 8639468).
Claim 8.
The combination of Seidel et al., Chini et al., Wang et al., and Keiser et al. teaches all the limitations of claim 1, as discussed above. Seidel et al. does not explicitly teach collecting a temperature; however, Cloetens teaches:
wherein collecting the diagnostic information comprises collecting at least one temperature of at least one of the components of the vehicular communication network
(Cloetens – Abstract) “an output providing the calculated die temperature value”
It would have been obvious to one possessing ordinary skill in the art before the effective filing date to combine these teachings, modifying the diagnostic system of Seidel et al. such that the die temperature of Cloetens is used as an input. One would have been motivated to do this because in a vehicle system, overheating of an integrated circuit may result in danger for a driver (Cloetens – Col. 1, lines 24-28).
Claim 17.
Rejected by the same rationale as claim 8.
Claim(s) 9 and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over the combination of Seidel et al., Chini et al., Wang et al., and Keiser et al. as applied to claims 1 and 10 above, and further in view of Dewan (US 11353517).
Claim 9.
The combination of Seidel et al., Chini et al., Wang et al., and Keiser et al. teaches all the limitations of claim 1, as discussed above. Seidel et al. does not explicitly teach a cable fault indication; however, Dewan teaches:
further comprising outputting from the trained neural network model one or more additional outputs selected from a group of outputs including a system reliability indication, one or more warnings, a cable fault indication, a cable fault location, and an Integrated Circuit (IC) fault indication
(Dewan – Col. 10, lines 6-8) “In some embodiments, the fault comparison circuit 184 is further configured to provide an indication of a fault, based on the comparison.”
It would have been obvious to one possessing ordinary skill in the art before the effective filing date to combine these teachings, modifying the diagnostic system of Seidel et al. with the fault indication of Dewan. Both Seidel et al. and Dewan are directed towards fault detection systems; therefore, a person of ordinary skill in the art would have recognized that this combination could be made with predictable results. One would have been motivated to combine these teachings in order to notify a driver of a detected fault in a vehicle system.
Claim 18.
Rejected by the same rationale as claim 9.
Claim(s) 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Seidel et al. in view of Chini et al. in view of Wang et al. in view of Keiser et al. in view of Rhee et al. (US 20200059484).
Claim 19.
Seidel et al. teaches:
for a given link, inputting the collected diagnostic information, including the at least one
(Seidel – [0009]) “it is provided that the diagnostic system is configured to receive vehicle information of the motor vehicle, wherein the vehicle information comprises at least one of the following elements: … operating data characterizing an operation of at least one component of the motor vehicle, one or more fault codes characterizing a fault of at least one component of the motor vehicle.”
Chini et al. teaches:
a state of health of the components of the vehicular communication network, wherein the set of health metrics includes a link health indication as a discrete output and a cable fault location as a continuous output
(Chini – [0031]) “Additional information can be provided to indicate signaling quality, insertion loss, and return loss of the communication links used in in-vehicle networks.”
[0041] “the link diagnostic processor 320 can process the high resolution impulse response to determine: … (3) whether the UTP cable 210 is shorted at any section of the link and the location of the short”
It would have been obvious to one possessing ordinary skill in the art before the effective filing date to combine these teachings for the reasons given in discussion of claim 1.
Seidel et al. does not explicitly teach a weighted sum objective function; however, Wang et al. teaches:
wherein the neural network model is trained using an objective function that is a weighted sum of a cross-entropy and a mean-square error, wherein the cross-entropy is applied with respect to the discrete output
(Wang – [0014]) “For the categorical features, a loss is measured by the cross-entropy loss. For numerical features, a loss is measured by the mean squared error”
(Wang – [0074]) “The categorical features are those which have values from a discrete set of possibilities”
It would have been obvious to one possessing ordinary skill in the art before the effective filing date to combine these teachings for the reasons given in discussion of claim 1.
While Wang et al. teaches the use of mean-square error for numerical features, Wang et al. does not explicitly teach continuous features. However, Rhee et al. teaches:
the mean-square error is applied with respect to the continuous output
(Rhee – [0054]) “mean square error can be used with continuous variable encoding.”
It would have been obvious to one possessing ordinary skill in the art to combine these teachings, modifying the objective function of Wang et al. to take into account continuous variables (e.g., the cable fault location of as taught by Rhee et al. Both Wang et al. and Rhee et al. teach types of data for which it is appropriate to use a mean square error as an objective function; therefore, it would have been obvious to one possessing ordinary skill in the art that the mean square error term of Wang et al. could further be applied to continuous variables, as taught by Rhee et al.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SARAH A MUELLER whose telephone number is (703)756-4722. The examiner can normally be reached M-Th 7:30-12:00, 1:00-5:30; F 8:00-12:00.
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, Navid Mehdizadeh can be reached at (571)272-7691. 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.A.M./Examiner, Art Unit 3669
/NAVID Z. MEHDIZADEH/Supervisory Patent Examiner, Art Unit 3669
Prosecution Insights