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 .
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.
Response to Arguments
Applicant's arguments filed 07/23/26 have been fully considered but they are not persuasive.
In response to applicant’s arguments, it is noted that Ottersten was already relied upon for disclosing “wherein the representation of the RF spectrum conditions includes I/Q samples” (as recited within claim 2, see Ottersten at paragraph 106, 155), which are generated from wireless signals received at the communications device transceiver (see Fig. 12, paragraph 248-250) and transmitted to the network nodes.
Tan was specifically relied upon for disclosing Deep reinforcement Learning (DRL) tuples constructed from cell parameters (paragraph 62-68).
Thus, it is the combination of Ottersten and Tan which would mee the current claim limitations, as signal RF measurements such as I/Q samples (as disclosed by Ottersten) are a type of “cell parameter” which would then be used to construct the DRL tuples (as disclosed in Tan).
Therefore, applicant’s arguments aren’t persuasive, as it is the combination of Ottersten and Tan which meet the current limitations.
Further, it is noted that applicant’s arguments do not address dependent claim 2 which already contained “I/Q samples” and the new claim amendments appear to introduce new antecedence issues regarding this limitation.
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 2 is 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.
Claim 2 recites “wherein the representation of the RF spectrum conditions includes I/Q samples” which renders the claim indefinite as independent claim 1 already recites “the representation of the RF spectrum conditions at least partially derived from I/Q samples generated by the wireless transceiver”, and it is unclear if these are meant to reference the same or additional different “I/Q samples”.
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 are rejected under 35 U.S.C. 103 as being unpatentable over Ottersten et al. (Ottersten) (US 2021/0345134) (of record) in view of Luo et al. (Luo) (US 2021/0320678) (of record) and Tan et al. (Tan) (US 2019/0014488) (of record).
As to claim 1, while Ottersten discloses a networking device (UE 120, Fig. 1; paragraph 63-68), comprising:
a wireless transceiver configured to detect radio frequency (RF) spectrum conditions local to the networking device and generate a representation of the RF spectrum conditions (paragraph 57-58, 102-103, 105, 119, 238);
an operative neural network (ONN) (neural network machine learning model; paragraph 58, 143, 233) configured to determine transceiver parameters based on the representation of the RF spectrum conditions (paragraph 101-109); and
a controller configured to:
cause the representation of the RF spectrum conditions to be transmitted to a network node (measurement information sent from UE to intermediate node; Fig. 6, paragraph 126, 239), the representation of the RF spectrum conditions at least partially derived from I/Q samples generated by the wireless transceiver (Fig. 12, paragraph 106, 155, 248-250); and
reconfigure the ONN based on neural network (NN) weight parameters (the neural network model comprising weighted coefficients; paragraph 114-117, 143) generated by a training neural network (TNN) remote from the networked device, the NN weight parameters being a function of the representation of the RF spectrum conditions (updated model information from intermediate node sent to UE; Fig. 6, paragraph 121-126),
Ottersten fails to specifically disclose wherein the neural network is hardware implemented and constructing a Deep reinforcement Learning (DRL) tuple.
In an analogous art, Luo discloses a networking device for transmitting/receiving communications over a network (see Fig. 1-2b, 6a-b; paragraph 35-45) which includes a hardware implemented (FPGA; paragraph 57, 86, 129, 136, 190) neural network (Fig. 2a-b, 5a, 6a-b, 40; paragraph 48-52, 57, 82) configured to determine transceiver parameters (paragraph 50-52, 55-56) based on a representation of RF spectrum conditions (paragraph 48-49, 59) so as to reduce latency (paragraph 85) than can be achieved via software on a CPU.
Additionally, in an analogous art, Tan discloses a method for wireless network optimization by adjusting cell parameters using Deep reinforcement Learning (DRL) (Fig. 5-6, 10; paragraph 33, 40, 47, 50-51, 61) by constructing a Deep reinforcement Learning (DRL) tuples (paragraph 33, 51-53, 72-76) constructed from cell parameters (paragraph 62-68) so as to take advantage of a Deep reinforcement Learning process for adjusting one or more cell parameters of cells associated with base stations in the wireless network (paragraph 7-8, 39-40) and improve its intelligence for effectively selecting an action (paragraph 40).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Ottersten’s system to include wherein the neural network is hardware implemented, as taught in combination with Luo, for the typical benefit of reducing system latency (paragraph 85).
Additionally, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Ottersten and Luo’s system to include constructing a Deep reinforcement Learning (DRL) tuple, as taught in combination with Tan, for the typical benefit of optimizing one or more cell parameters of cells associated with base stations in the wireless network (paragraph 7-8, 39-40) and improving intelligence for effectively selecting an action (paragraph 40).
As to claim 2, Ottersten, Luo and Tan disclose wherein the representation of the RF spectrum conditions includes I/Q samples (see Ottersten at paragraph 106, 155).
As to claim 3, Ottersten, Luo and Tan disclose wherein the controller is further configured to generate an ONN input state based on the representation of the RF spectrum conditions see Ottersten at paragraph 102-105 and Luo at paragraph 48-49, 59) and wherein the ONN is further configured to process the ONN input state to determine the transceiver parameters (see Ottersten at paragraph 106-109 and Luo at paragraph 50-52, 55-56).
As to claim 4, Ottersten, Luo and Tan disclose wherein the wireless transceiver is further configured to reconfigure at least one internal transmission or reception protocol based on the transceiver parameters (see Ottersten at paragraph 106-109 and Luo at paragraph 50-52, 55-56).
As to claim 5, Ottersten, Luo and Tan disclose wherein, following the reconfiguration of the ONN based on the NN weight parameters, the ONN is further configured to determine subsequent transceiver parameters based on a subsequent representation of the RF spectrum conditions generated by the wireless transceiver (repeatedly reconfigured over time with new inputs; see Ottersten at Fig. 6, paragraph 58-59, 88-90, 126 and Luo at Fig. 5A-E; paragraph 82-115).
As to claim 6, Ottersten, Luo and Tan disclose wherein the networking device is a battery-powered Internet of things (IoT) device (see Ottersten at paragraph 57, 68 and Luo at paragraph 40).
As to claim 7, Ottersten, Luo and Tan disclose wherein the ONN is further configured to determine the transceiver parameters within 1 millisecond of the wireless transceiver generating a representation of the RF spectrum conditions (see Luo at paragraph 85).
As to claim 8, Ottersten, Luo and Tan disclose wherein the ONN is configured in a first processing pipeline, and further comprising a second processing pipeline configured to 1) buffer the representation of the RF spectrum conditions concurrently with the ONN determining the transceiver parameters, and 2) provide the representation of the RF spectrum conditions to the wireless transceiver in synchronization with the transceiver parameters (delay buffering and providing to the transceivers to adjust while also transmitting to the training unit; Fig. 5A-E, 6A-B; see Luo at paragraph 52, 82-115, 117-122).
As to claim 9, while Ottersten discloses a method of configuring a wireless transceiver (within UE 120, Fig. 1; paragraph 63-68), comprising:
detecting radio frequency (RF) spectrum conditions local to the networking device and generating a representation of the RF spectrum conditions (paragraph 57-58, 102-103, 105, 119, 238);
determining, at an operative neural network (ONN) (paragraph 58, 143, 233), transceiver parameters based on the representation of the RF spectrum conditions (paragraph 101-109);
reconfiguring at least one internal transmission or reception protocol of the wireless transceiver based on the transceiver parameters (paragraph 106-109);
transmitting the representation of the RF spectrum conditions to a network node remote from the wireless transceiver (measurement information sent from UE to intermediate node; Fig. 6, paragraph 126, 239), the representation of the RF spectrum conditions at least partially derived from I/Q samples generated by the wireless transceiver (Fig. 12, paragraph 106, 155, 248-250); and
reconfiguring the ONN based on neural network (NN) weight parameters (the neural network model comprising weighted coefficients; paragraph 114-117, 143) generated by a training neural network (TNN), the NN weight parameters being a function of the representation of the RF spectrum conditions (updated model information from intermediate node sent to UE; Fig. 6, paragraph 121-126),
Ottersten fails to specifically disclose wherein the neural network is hardware implemented and constructing a Deep reinforcement Learning (DRL) tuple.
In an analogous art, Luo discloses a networking device for transmitting/receiving communications over a network (see Fig. 1-2b, 6a-b; paragraph 35-45) which includes a hardware implemented (FPGA; paragraph 57, 86, 129, 136, 190) neural network (Fig. 2a-b, 5a, 6a-b, 40; paragraph 48-52, 57, 82) configured to determine transceiver parameters (paragraph 50-52, 55-56) based on a representation of RF spectrum conditions (paragraph 48-49, 59) so as to reduce latency (paragraph 85) than can be achieved via software on a CPU.
Additionally, in an analogous art, Tan discloses a method for wireless network optimization by adjusting cell parameters using Deep reinforcement Learning (DRL) (Fig. 5-6, 10; paragraph 33, 40, 47, 50-51, 61) by constructing a Deep reinforcement Learning (DRL) tuples (paragraph 33, 51-53, 72-76) constructed from cell parameters (paragraph 62-68) so as to take advantage of a Deep reinforcement Learning process for adjusting one or more cell parameters of cells associated with base stations in the wireless network (paragraph 7-8, 39-40) and improve its intelligence for effectively selecting an action (paragraph 40).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Ottersten’s system to include wherein the neural network is hardware implemented, as taught in combination with Luo, for the typical benefit of reducing system latency (paragraph 85).
Additionally, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Ottersten and Luo’s system to include constructing a Deep reinforcement Learning (DRL) tuple, as taught in combination with Tan, for the typical benefit of optimizing one or more cell parameters of cells associated with base stations in the wireless network (paragraph 7-8, 39-40) and improving intelligence for effectively selecting an action (paragraph 40).
As to claim 10, Ottersten, Luo and Tan disclose training the TNN based on the representation of the RF spectrum conditions (see Ottersten at Fig. 6, paragraph 126, 142-147); and
generating, via the TNN, the NN parameters as a result of the training (see Ottersten at Fig. 3, 4A, 6, paragraph 126, 142-147);
As to claim 11, Ottersten, Luo and Tan disclose training the TNN in a manner that is asynchronous to operation of the ONN (see Ottersten at Fig. 3, 4A, 6, paragraph 58, 126, 142-147, 231-233).
As to claim 12, Ottersten, Luo and Tan disclose training the TNN based on at least one state/action/reward generated from the representation of the RF spectrum (see Ottersten at Fig. 3, 4A, 6, paragraph 58-59, 118-122, 142-147 and Tan at paragraph 68-75).
As to claim 13, Ottersten, Luo and Tan disclose updating a TNN experience buffer to include the at least one state/action/reward tuple (see Ottersten at Fig. 3, 4A, 6, paragraph 58-59, 118-122, 142-147 and Tan at paragraph 68-75).
As to claim 14, Ottersten, Luo and Tan disclose transmitting the NN weight parameters from the network node to the wireless transceiver (updated model information from intermediate node sent to UE; see Ottersten at Fig. 6, paragraph 121-126, 145-147).
As to claim 15, Ottersten, Luo and Tan disclose training a software-defined NN to classify among different state conditions of a RF spectrum;
translating the state of the software-defined NN to ONN parameters (see Ottersten at paragraph 11, 56-58, 74, 88, 101, 121, 227-233);
comparing the ONN parameters against at least one of a size constraint and a latency constraint (different models with different data rates and latency requirements for different purposes; see Ottersten at paragraph 11, 56-58, 74, 88, 101, 121, 217, 227-233); and
causing the ONN to be configured based on the ONN parameters (see Ottersten at paragraph 11, 56-58, 74, 88, 101, 121, 217, 227-233).
Conclusion
THIS ACTION IS MADE FINAL. 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 James R Sheleheda whose telephone number is (571)272-7357. The examiner can normally be reached M-F 8 am-5 pm CST.
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, Benjamin Bruckart can be reached at (571) 272-3982. 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.
/James R Sheleheda/ Primary Examiner, Art Unit 2424
Prosecution Insights