DETAILED ACTION
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 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.
This action is in response to communications filed on 3/9/2026.
Claims 1-20 remain pending. Claims 1-20 have been examined and are rejected.
Priority
This application is a 371 of PCT/US2022/031520 filed 5/31/2022.
Response to Arguments
Applicant’s arguments filed in the communications above have been fully considered but are moot because the arguments do not apply to the reference Maggi et al. (US 2021/0368450 A1) used in the current rejection which was submitted in the information disclosure statement filed 12/16/2022.
For at least these reasons, applicant’s arguments are considered not persuasive.
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 of this title, 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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-2, 4-9, 11-16, & 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Estevez (US 2022/0052915 A1) in view of Maggi et al. (US 2021/0368450 A1).
With regard to Claim 1, Estevez teaches:
A method for determining an optimal functional split for a radio access network (RAN); (utilizing AI/analytics to enable computational elasticity at the RAN [Estevez: 0070]);
the method comprising:
obtaining network data relating to performance of RAN elements configured with a current functional split; (gathering historic computational metrics (e.g., CPU utilization, storage use, processing time, etc.) applicable to NFs running both on gNB-CU (i.e., cloud-enabled) as well as in the DU (by making use of the reporting capabilities of F1) [Estevez: 0052; 0045]);
analyzing, by artificial intelligence, the obtained network data to determine an optimum functional split, from among a predetermined plurality of functional splits, for optimizing network performance under current network conditions; (performing an AI-assisted determination of the optimal functional split point on CU-DU interface based on the computational metrics which may trigger re-orchestration of the RAN [Estevez: 0054; 0064; 0071; Fig. 3]);
and outputting the determined optimum functional split for configuring the RAN elements; (if the decision involves the reconfiguration of the gNB-DU(s), then the augmented F1 interface is utilized to carry the command to execute such a decision at the gNB-DU [Estevez: 0082; 0071; Fig. 3]).
While Estevez teaches management and orchestration of the RAN is performed using artificial intelligence (AI) and machine learning (ML) techniques using reinforcement learning solutions [Estevez: 0044; 0077], it does not explicitly teach that the obtained network data is analyzed by a machine learning model.
In a similar field of endeavor involving determining optimal network parameters, Maggi discloses:
analyzing, by a machine learning model, the obtained network data; (receiving a power allocation function and input network parameters used to compute an output of the power allocation function, wherein the power allocation function is based on radio channel statistics and network performance metrics and may be a neural network [Maggi: 0101-103; 0096; 0073]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Estevez in view of Maggi in order to analyze obtained network data by a machine learning model in the system of Estevez.
One of ordinary skill in the art would have been motivated to combine Estevez with Maggi as doing so would utilize ML models for predicting outcomes based on trained data instead of explicit programming which have the benefit of becoming more accurate as the amount of training data increases.
With regard to Claim 2, Estevez-Maggi teaches:
The method as claimed in claim 1, wherein the analyzing comprises analyzing the obtained network data and determining the optimum functional split by using a reinforcement learning machine learning (ML) model; (performing an AI-assisted determination of the optimal functional split point on CU-DU interface based on the computational metrics which may trigger re-orchestration of the RAN [Estevez: 0054; Fig. 3], wherein management of the RAN is performed using artificial intelligence (AI) and machine learning (ML) techniques using reinforcement learning solutions due to their ability to learn and continuously update an optimal orchestration policy based on on-line decisions that can be evaluated using the reward of the policy [Estevez: 0044; 0077]. Maggi teaches receiving a power allocation function and input network parameters used to compute an output of the power allocation function, wherein the power allocation function is based on radio channel statistics and network performance metrics and may be a neural network [Maggi: 0101-103; 0096; 0073]).
With regard to Claim 4, Estevez-Maggi teaches:
The method as claimed in claim 3, wherein the optimality of the current network performance corresponds to at least one of accommodation of current traffic load, satisfaction of latency requirements, and satisfaction of bitrate requirements; (determining the optimal functional split point based on the computational metrics (e.g., CPU utilization, storage use, processing time, etc.) [Estevez: 0054; 0064; 0071]. Maggi teaches target metrics may include, for example, communication reliability, communication delay, overall transmission power, and physical resource utilization [Maggi: 0040; 0024]).
With regard to Claim 5, Estevez-Maggi teaches:
The method as claimed in claim 1, wherein the obtaining the network data comprises obtaining the network data from at least one of a radio unit of the RAN, a centralized unit of the RAN, a distributed unit of the RAN, a transport network element, and a core network element; (the distributed AI/analytics engine 46 at the gNB-CU 42, 52 collects data (including computation-related metrics such as CPU or storage consumption) S10 from the VNFs running locally as well as data from the gNB-DU(s) 44, 54 that the F1 interface is equipped to carry [Estevez: 0079]).
With regard to Claim 6, Estevez-Maggi teaches:
The method as claimed in claim 1, wherein the obtaining, the analyzing, and the outputting are repeatedly performed; (performing the AI analytics and performance data collection continuously until the analytics algorithms yield a new decision to improve performance, wherein the AI algorithms for decision-making may be repeated [Estevez: 0079; Fig. 3]).
With regard to Claim 7, Estevez-Maggi teaches:
The method as claimed in claim 1, wherein the network data comprises at least one of fronthaul latency, end-to-end latency, end-to-end user downlink throughput, end-to-end user uplink throughput, end-to-end cell downlink throughput, end-to-end cell uplink throughput, delay, and jitter; (gathering historic computational metrics (e.g., CPU utilization, storage use, processing time, etc.) [Estevez: 0052; 0045]. Maggi teaches input parameters to the power allocation function may include, for example, uplink instantaneous channel measurement on each subcarrier for each of the legs, modulation scheme used on each subcarrier for each of the legs, overall reliability target, the UE's preference between delay and reliability, and/or uplink power budget [Maggi: 0102-103]).
With regard to Claims 8-9, 11-16, & 18-20, they appear substantially similar to the limitations recited by claims 1-2 & 4-7 and consequently do not appear to teach or further define over the citations provided for said claims. Accordingly, claims 8-9, 11-16, & 18-20 are rejected for the same reasons as set forth in claims 1-2 & 4-7.
Claims 3, 10, & 17 are rejected under 35 U.S.C. 103 as being unpatentable over Estevez (US 2022/0052915 A1) in view of in view of Maggi et al. (US 2021/0368450 A1) as applied to Claims 1, 8, & 15 above, and further in view of Childress (US 2024/0020715 A1).
With regard to Claim 3, Estevez-Maggi teaches:
The method as claimed in claim 1, wherein the analyzing comprises: determining the optimum functional split based on reinforcement learning; (performing an AI-assisted determination of the optimal functional split point on CU-DU interface based on the computational metrics which may trigger re-orchestration of the RAN [Estevez: 0054; Fig. 3], wherein management of the RAN is performed using artificial intelligence (AI) and machine learning (ML) techniques using reinforcement learning solutions [Estevez: 0044; 0077]).
While Estevez-Maggi teaches the use of reinforcement learning, it does not explicitly teach updating the ML model based on a negative or positive feedback value.
In a similar field of endeavor involving utilizing machine learning models to predict performance outcomes, Childress discloses:
determining a negative or positive feedback value based on analysis of optimality of current model performance; and updating the ML model and determining the optimum output based on the determined feedback value; (ML engine can update (further train) the ML models based on feedback that may include positive feedback (indicating that outputs closely align with expected outputs and/or that outputs serve their intended purpose) or negative feedback (indicating a mismatch between the outputs and the expected outputs and/or that the outputs do not serve their intended purpose) for purposes of reinforcing or removing weights associated with generation of the output [Childress: 0155]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Estevez-Maggi in view of Childress in order to update the ML model based on a negative or positive feedback value in the system of Estevez-Maggi.
One of ordinary skill in the art would have been motivated to combine Estevez-Maggi with Childress as doing so would strengthen or weaken weights associated with generation of the outputs to encourage or discourage the ML engine to generate similar outputs given similar inputs [Childress: 0155], thereby further improving model accuracy over time.
With regard to Claims 10 & 17, they appear substantially similar to the limitations recited by claims and consequently do not appear to teach or further define over the citations provided for said claim. Accordingly, claims 10 & 17 are rejected for the same reasons as set forth in claim 3.
Conclusion
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 extension fee 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.
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Mishra et al. (US 2020/0128414 A1) which teaches providing Radio Access Network (RAN) dynamic functional splits by determining a first split of different functionalities between a central Unit (CU) and a Distributed Unit (DU) [abstract].
Ouyang et al. (US 2017/0290024 A1) which teaches providing optimal network performance in view of the predicted impacts of the usage level by obtaining usage data associated with cells [0018] and utilizing a cell clustering module to implement a training process to fit a model that can be used to predict the target network resource [0058] using different regression algorithms to attempt to fit the KPI feature such as a generalized additive model (GAM), a gradient boost method (GBM), a neural network method, and a multivariate adaptive regression splines (MARS) method [0059; 0062].
In the case of amendments, Applicant is respectfully requested to indicate the portion(s) of the specification which dictate(s) the structure relied on for proper interpretation and support, for ascertaining the metes and bounds of the claimed invention.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AUSTIN J MOREAU whose telephone number is (571) 272-5179. The examiner can normally be reached Monday-Friday 9:00 - 6:00 ET.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Brian Gillis can be reached on 571-272-7952. 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.
/AUSTIN J MOREAU/Primary Examiner, Art Unit 2446
Prosecution Insights