DETAILED ACTION
Claims 1-5 are pending.
Priority
The examiner finds support under 35 USC § 112(a) for pending claims 1-5 within Provisional Application No. 63/584672 (filed 9/22/2023).
Information Disclosure Statement
The listing of references in the specification is not a proper information disclosure statement. 37 CFR 1.98(b) requires a list of all patents, publications, or other information submitted for consideration by the Office, and MPEP § 609.04(a) states, "the list may not be incorporated into the specification but must be submitted in a separate paper." Therefore, unless the references have been cited by the examiner on form PTO-892, they have not been considered.
Drawings
The drawings are objected to because the drawings are of low resolution and not fully readable as printed in the corresponding PG Pub 2025/0105959. The text within the drawings is not readable. Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
The drawings are objected to as failing to comply with 37 CFR 1.84(p)(5) because they include the following reference character(s) not mentioned in the description: element 400 of Fig. 4, elements 500 and 501 of Fig. 5, element 600 of Fig. 6, and elements 700-702 of Fig. 7. Corrected drawing sheets in compliance with 37 CFR 1.121(d), or amendment to the specification to add the reference character(s) in the description in compliance with 37 CFR 1.121(b) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Specification
The disclosure is objected to because of the following informalities:
The specification filed in the instant, Non-Provisional Application, omits the inclusion of descriptive subject matter for at least Figs. 3-6, which may be found in the Provisional Application No. 63/584672 (filed 9/22/2023). Specifically, see pages 4-7 of the Provisional Application. This descriptive text is important for understanding Figs. 3-7, inasmuch as they can be read (see Objection to Drawings, above). The examiner respectfully requests that the specification within the instant application be amended to include subject matter from the Provisional Application.
Appropriate correction is required.
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 1-5 are rejected under 35 U.S.C. 103 as being unpatentable over Bonati et al. (NPL, see PTO-892) in view of Tang et al. (NPL, see PTO-892).
As per claim 1, Bonati et al. teach a method for providing a Real-Time PHY model at a RAN edge [Bonati, pg. 6, section 2.5], comprising:
running an Artificial Intelligence (AI) model on a general purpose processor in a cloud using telecommunications data as inputs, to generate outputs [Bonati, section 5.1, pg. 11, “The O-RAN Architecture”, “The near-real-time RIC can also leverage machine learning algorithms trained in the non-real-time RIC. The remaining components of the O-RAN architecture concern the CU/DU/RU into which 5G gNBs are split, and the 4G eNBs (bottom of Fig. 8)”, O-RAN architecture runs on generic (or COTS) hardware (see section 5.1, pg. 10). The near-real-time radio intelligent controller (RIC) may perform machine learning (or AI) modeling as part of its deployment (see section 2.5, pg. 6). The modeling uses telecommunications inputs to generate outputs for controlling the RAN (for example, via the E2 interface, see fig. 8). See also, fig. 9, first bullet of pg. 12.];
…
deploying the stored inputs and outputs in the lookup format to a Virtual Base Band Unit (VBBU) [Bonati, section 5.1, pg. 11, “The near-real-time RIC exposes the E2 interface [142] to multiple elements, i.e., the CU, the DU and the eNB. This interface only concerns control functionalities, related to the deployment of near-real-time RIC control actions to the nodes terminating the E2 interface, and to the management of the interaction of the RIC and these nodes”, The applicant’s specification (see fig. 7) shows a vBBU as containing a DU and CU. Similarly, Bonati shows that the near-real-time RIC may communicate with the O-CU and O-DU over the same E2 interface. Therefore, it is reasonable to conclude that the vBBU of the instant application is an abstract name for the virtualized combination of the CU and DU. Likewise, Bonati shows these functions as sharing the same interface from the near-real-time RIC, and therefore reasonably teaches a vBBU as disclosed by the applicant.]; and
using…parameters at the VBBU of real time telecommunications data [Bonati, pg. 6, section 2.5, “Another key component of the 5G ecosystem is the application of
machine learning and artificial intelligence-based technologies to network optimization [72]. The scale of 5G deployments makes traditional optimization and manual configuration of the network impossible. Therefore, automated, data-driven solutions are fundamental for self organizing 5G networks. Additionally, the heterogeneity of use cases calls for a tight integration of the learning process to the communication stack, which is needed to swiftly adapt to quickly changing scenarios”, Machine learning techniques are tied in with the protocol stack (which includes physical and MAC data). Protocol stack data represents telecommunications data for the RAN. Learning techniques, including stack data, may be used for forecasting and scheduling (see sections 2.5 and 5.1). Results from the learning techniques are shared over the E2 interface (see pg. 12, bullet 2).].
Bonati et al. do not explicitly teach storing the inputs and the outputs in a lookup format to facilitate lookup, without storing the AI model concurrently.
However, in an analogous art, Tang et al. teach storing the inputs and the outputs in a lookup format to facilitate lookup, without storing the AI model concurrently… using in-memory lookup of parameters [Tang, pg. 1, section 1, “Fig. 1 shows an overview of LUT-NN using real data samples of a model. LUT-NN is the first to empower end-to-end DNN inference by table lookup. It achieves comparable accuracy with the original models on real and complex datasets and tasks”, Lookup Table (LUT) neural network (NN) is used to store model inputs, outputs, and centroid search (for approximation). The LUT-NN is deployed to harness speed in obtaining machine learning model outputs, without having to deploy the full model. In other words, tables may be stored in memory as opposed to running inputs through a full model, which saves on systems and cost. See pg. 2, section 1, right hand column.]
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to implement the LUT-NN of Tang et al. into the O-RAN implementation of Bonati et al. One would have been motivated to do this because the COTS hardware of Bonati et al. would more effectively implement the simplistic LUT implementation of Tang et al. with a reasonable expectation of success.
As per claim 2, Bonati et al. in view of Tang et al. teach the method of claim 1. Bonati et al. do not explicitly teach further comprising storing the inputs and the outputs with compression.
However, in an analogous art, Tang et al. teach storing the inputs and the outputs with compression [Tang, pg. 1, section 1, “Fig. 1 shows an overview of LUT-NN using real data samples of a model. LUT-NN is the first to empower end-to-end DNN inference by table lookup. It achieves comparable accuracy with the original models on real and complex datasets and tasks”, Lookup Table (LUT) neural network (NN) is used to store model inputs, outputs, and centroid search (for approximation). The LUT-NN is deployed to harness speed in obtaining machine learning model outputs, without having to deploy the full model. In other words, tables may be stored in memory as opposed to running inputs through a full model, which saves on systems and cost. See pg. 2, section 1, right hand column. Compression may be used to handle inference situations (see section 7.1).].
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to implement the LUT-NN of Tang et al. into the O-RAN implementation of Bonati et al. One would have been motivated to do this because the COTS hardware of Bonati et al. would more effectively implement the simplistic LUT implementation of Tang et al. with a reasonable expectation of success.
As per claim 3, Bonati et al. in view of Tang et al. teach the method of claim 1. Bonati et al. also teach further comprising refreshing the stored inputs and outputs by re-running the AI model periodically and deploying a new lookup format to the VBBU [Bonati, section 5.1, pg. 11, “The O-RAN Architecture”, “The near-real-time RIC can also leverage machine learning algorithms trained in the non-real-time RIC. The remaining components of the O-RAN architecture concern the CU/DU/RU into which 5G gNBs are split, and the 4G eNBs (bottom of Fig. 8)”, O-RAN architecture runs on generic (or COTS) hardware (see section 5.1, pg. 10). The near-real-time radio intelligent controller (RIC) may perform machine learning (or AI) modeling as part of its deployment (see section 2.5, pg. 6). The modeling uses telecommunications inputs to generate outputs for controlling the RAN (for example, via the E2 interface, see fig. 8). See also, fig. 9, first bullet of pg. 12. Network control algorithms are reasonably construed as being dynamic and rerun based on network conditions. (see pg. 12).].
As per claim 4, Bonati et al. in view of Tang et al. teach the method of claim 1. Bonati et al. also teach wherein the telecommunications data is radio frequency physical layer data [Bonati, pg. 6, section 2.5, “Another key component of the 5G ecosystem is the application of machine learning and artificial intelligence-based technologies to network optimization [72]. The scale of 5G deployments makes traditional optimization and manual configuration of the network impossible. Therefore, automated, data-driven solutions are fundamental for self organizing 5G networks. Additionally, the heterogeneity of use cases calls for a tight integration of the learning process to the communication stack, which is needed to swiftly adapt to quickly changing scenarios”, Machine learning techniques are tied in with the protocol stack (which includes physical and MAC data). Protocol stack data represents telecommunications data for the RAN. Learning techniques, including stack data, may be used for forecasting and scheduling (see sections 2.5 and 5.1).].
As per claim 5, Bonati et al. in view of Tang et al. teach the method of claim 1. Bonati et al. also teach wherein the telecommunications data is 4G or 5G media access control (MAC) layer data [Bonati, pg. 6, section 2.5, “Another key component of the 5G ecosystem is the application of machine learning and artificial intelligence-based technologies to network optimization [72]. The scale of 5G deployments makes traditional optimization and manual configuration of the network impossible. Therefore, automated, data-driven solutions are fundamental for self organizing 5G networks. Additionally, the heterogeneity of use cases calls for a tight integration of the learning process to the communication stack, which is needed to swiftly adapt to quickly changing scenarios”, Machine learning techniques are tied in with the protocol stack (which includes physical and MAC data). Protocol stack data represents telecommunications data for the RAN. Learning techniques, including stack data, may be used for forecasting and scheduling (see sections 2.5 and 5.1).].
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
The reference, Boonstra (US PG Pub 20240005138), teaches interpolation methods for LUT operations with machine learning inputs and outputs (see figs. 2, 6, ¶s 0029 and 0030).
The reference, Yang et al. (US 20170237831), teaches a lookup table found within a RRU for determining I/Q modulation data (see ¶s 0040 and 0048).
The reference, Masur et al. (NPL, see PTO-892), teaches implementing artificial intelligence into O-RAN architecture (see pgs. 10-13).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Paul H. Masur whose telephone number is (571)270-7297. The examiner can normally be reached Monday to Friday, 4:30 AM to 5PM.
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, Rebecca Song can be reached at (571) 270-3667. 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.
/Paul H. Masur/
Primary Examiner
Art Unit 2417
Prosecution Insights