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 .
Status of Claims
Claims 1-5, 8, 11, 14-17, 19, and 52-59 are pending of which claims 1, 19 and 59 are in independent form.
Claims 1-5, 8, 11, 14-17, 19, and 52-59 are rejected under 35 U.S.C. 101.
Claims 1-5, 8, 11, 14-17, 19, and 52-59 are rejected under 35 U.S.C. 103.
Response to Arguments
Applicant’s arguments with respect to claim(s) 1-5, 8, 11, 14-17, 19, and 52-59 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Applicant argument and amendment to the claims are simply not persuasive. The claims simply recite the desired results of performing ML processing in a distributed radio network environment, without reciting how the alleged technological improvement is achieved.
Please see the detailed rejection below for further clarification.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-5, 8, 11, 14-17, 19, and 52-59 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
The claim(s) recite(s) network access using RF signal analysis through ML models.
With respect to step 1 of the patent subject matter eligibility analysis, the claims are directed to a process, machine, manufacture, or composition of matter.
Independent claims 1 and 59 are directed to a method, which is a process.
Independent claim 19 is directed to a system, comprising one or more processors, and one or more non-transitory, computer-readable storage media, which is directed to one of the four statutory subject matters.
Independent All other claims depend on claims 1, 19, and 59. As such, claims 1-5, 8, 11, 14-17, 19, and 52-59 are directed to a statutory category.
Regarding claims 1, 19 and 59:
With respect to step 2A, prong one (Judicial Exception), the claims recite an abstract idea, law of nature, or natural phenomenon. Specifically, the following limitations recite mathematical concepts and/or mental processes and/or certain methods of organizing human activity.
The claims recite:
“providing the samples of the RF uplink data signals as input to the at least one machine learning model” the limitation as drafted recites a Mathematical Algorithm/Concept involving mathematical analysis and evaluation of the data using a mathematical model or algorithm, including processing input data to derive output information.
“obtaining based on an output of the at least one machine learning model, recovered data of the RF uplink data signals” the limitation as drafted recites a Mathematical Algorithm/Concept involving mathematical processing, inference, prediction, and evaluation operation performed on a data using an ML model.
“wherein the at least one machine learning model is trained at the RIC” the limitation as drafted recites a Mathematical Algorithm/Concept involving mathematical relationships and statistical training processes for generating or configuring an ML model.
These limitations correspond to concept mathematical calculations, modeling, evaluation, and analysis of information, mathematical reasoning which falls within the Mathematical Algorithm/Concept category of abstract idea (see MPEP 2016.04(a)(2)).
Additionally, the evaluation and interpretation of RF signal data using a trained model constitutes observation and analysis that can be performed through mental evaluation/mathematical reasoning, and therefore also falls within the Mental Process category of abstract idea (see MPEP 2016.04(a)(2)).
There are no steps performed that provides a technical improvement to the computing system itself (improved caching algorithm, improved database indexing, improved memory efficiency, improved cache eviction strategy; improved computing architecture). All the steps are generic, and conventional.
With respect to step 2A, Prong Two (Particular Application), the claims do not recite additional elements that integrate the judicial exception into a practical application. The following limitations are considered “additional elements” and explanation will be given as to why these “additional elements” do not integrate the judicial exception into a practical application.
The claims are generic computer components preforming their routine functions. The claims include:
“a distributed unit (DU) of a radio access network” as drafted recites generic networking components operating in its ordinary capacity within a radio access network architecture, and merely identifies the environment in which the abstract idea is performed (see MPEP 2106.05(f)(2)).
“a radio access network intelligent controller (RIC)” as drafted recites generic networking control components performing conventional control and orchestration functions within a radio access network environment, and therefore amounts to mere instruction to apply the abstract idea.
“receiving, …, at least one machine learning model,” as drafted recites a generic receipt and deployment of model data, which amount to insignificant extra-solution activity and routine computer implementation.
“wherein the at least one machine learning model is trained at the RIC” as drafted recites a generic ML training functionality without reciting any specific training architecture, training algorithm, or technical improvement to ML operations.
“executing in an L1 layer of the DU” as drafted simply limits the abstract idea to a particular technological environment, without reciting any specific improvement to L1 processing, RF decoding, modulation, channel estimation, or wireless communication technology.
“obtaining, …, samples of radio-frequency (RF) uplink data signals” as drafted recites post-solution extra-solution activity, such as mere data gathering and collection (see MPEP 2106.05(g)).
“sending the recovered data of the RF uplink signals to a destination device” as drafted recites post-solution extra-solution activity, such as generic data transmission using conventional networking functionality (see MPEP 2106.05(g)).
The additional elements mentioned above fail to integrate the abstract idea into a practical application because the additional elements, individually and in combination, amount to no more that:
Generic networking and radio access network components performing conventional functions;
Generic ML implementation;
Insignificant extra solution activity, including data collection, and transmission; and
Limiting the abstract idea to a particular technological environment.
The claims do not:
Improve the functioning of the DU, RIC, or radio unit;
Improve L1 processing technology;
Recite a specific ML architecture or training technique;
Recite a specific RF signal recovery algorithm,
Improve modulation, demodulation, channel; estimation, or decoding operations, or
Provide a specific technological mechanism for recovering RF uplink data.
There are no improvements to computer functionality or any specific technical solution to a computer centric problem.
Instead, the computer components are used as tools to perform the abstract idea of collecting, organizing, and associating information about nodes and their relationships.
With respect to Step 2B. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The recited components are merely generic computer/database elements performing their routine, well-understood, and conventional functions. See Alive, MPEP 2016.05(d).
The steps mentioned: generic computer system performing generic functions of an abstract idea. These elements merely amount to applying an abstract idea using conventional computing and networking technology. Courts have consistently helped such high-level information management operations are conventional.
Considering claims as a whole, the ordered combination of elements also reflects nothing more than the typical workflow of distributed systems, and therefore DOES NOT add “significantly more” than the abstract idea.
Such generic, high‐level, and nominal involvement of a computer or computer‐based elements for carrying out the invention merely serves to tie the abstract idea to a particular technological environment, which is not enough to render the claims patent‐eligible, as noted at pg.74624 of Federal Register/Vol. 79, No. 241, citing Alice, which in turn cites Mayo. Further, See, e.g., Alice Corp. Pty. Ltd. v. CLS Bank Int'l, 134 S. Ct. 2347, 2359‐60, 110 USPQ2d 1976, 1984 (2014). See also OIP Techs. v. Amazon.com, 788 F.3d 1359, 1364, 115 USPQ2d 1090, 1093‐94 (Fed. Cir. 2015) ("Just as Diehr could not save the claims in Alice, which were directed to 'implement[ing] the abstract idea of intermediated settlement on a generic computer', it cannot save O/P's claims directed to implementing the abstract idea of price optimization on a generic computer.") (citations omitted). See also, Affinity Labs of Texas LLC v. DirecTV LLC, 838 F.3d 1253, 1257‐1258 (Fed. Cir. 2016) (mere recitation of a GUI does not make a claimpatent‐eligible); Intellectual Ventures I LLC v. Capital One Bank, 792 F.3d 1363, 1370 (Fed. Cir. 2015) ("the interactive interface limitation is a generic computer element".).
The additional elements are broadly applied to the abstract idea at a high level of generality ("similar to how the recitation of the computer in the claims in Alice amounted to mere instructions to apply the abstract idea of intermediated settlement on a generic computer,") as explained in MPEP § 2106.05(f)) and they operate in a well‐understood, routine, and conventional manner.
MPEP § 2106.0S(d)(II) sets forth the following:
The courts have recognized the following computer functions as well-understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity.
• Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec ... ; TLI Communications LLC v. AV Auto. LLC ... ; OIP Techs., Inc., v. Amazon.com, Inc ... ; buySAFE, Inc. v. Google, Inc ... ;
• Performing repetitive calculations, Flook ... ; Bancorp Services v. Sun Life ... ;
• Electronic recordkeeping, Alice Corp ... ; Ultramercial ... ;
• Storing and retrieving information in memory, Versata Dev. Group, Inc. v. SAP Am., Inc ... ;
• Electronically scanning or extracting data from a physical document, Content Extraction and Transmission, LLC v. Wells Fargo Bank ... ; and
• A web browser's back and forward button functionality, Internet Patent
• Corp. v. Active Network, Inc. ...
. . . Courts have held computer-implemented processes not to be significantly more than an abstract idea (and thus ineligible) where the claim as a whole amounts to nothing more than generic computer functions merely used to implement an abstract idea, such as an idea that could be done by a human analog (i.e., by hand or by merely thinking).
In addition, when taken as an ordered combination, the ordered combination adds nothing that is not already present as when the elements are taken individually. There is no indication that the combination of elements integrate the abstract idea into a practical application. Their collective functions merely provide conventional computer implementation. Therefore, when viewed as a whole, these additional claim elements do not provide meaningful limitations to transform the abstract idea into a practical application of the abstract idea or that the ordered combination amounts to significantly more than the abstract idea itself.
The dependent claims have been fully considered as well, however, similar to the findings for claims above, these claims are similarly directed to the “Mental Processes” grouping of abstract ideas set forth in the 2019 PEG, without integrating it into a practical application and with, at most, a general purpose computer that serves to tie the idea to a particular technological environment, which does not add significantly more to the claims. The ordered combination of elements in the dependent claims (including the limitations inherited from the parent claim(s)) add nothing that is not already present as when the elements are taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely provide conventional computer implementation. Accordingly, the subject matter encompassed by the dependent claims fails to amount to significantly more than the abstract idea.
Looking at the claim as a whole does not change this conclusion and the claim is ineligible.
Regarding claims 2, and 3 (Generic Data Transmission/Communication Flow),
The claim recites:
sending the recovered data of the RF uplink signals to one or more computer systems external to the radio access network (claim 2),
receiving downlink data and transmission of an RF data downlink signal encoding the downlink data (claim 3)
This merely recites: transmitting the processed information, routing data through network components controlling communication flow. These are: generic communication operations, data transmission. These are considered: Mental Process and post-solution extra-solution activity.
There is no technical mechanism provide for: how RF transmissions are technically improved, how encoding operations improve L1 processing, how communication is enhanced.
This does not change the nature of the abstract idea. It does not add a technical improvement to an abstract idea, such as improving computer functionality, data structure, or processing architecture.
There is no practical application, and no inventive step, the claims are still considered abstract.
Regarding claims 4, and 5 (Based Channel Estimation/Signal Processing),
The claim recites:
first machine learning model configured to perform channel estimation … a second machine learning model configured to perform symbol-demapping (claim 4),
obtaining channel estimates … transforming the samples of the RF uplink… RF uplink data signals as input to the second machine learning model… obtaining, recovered data from the second machine learning model (claim 5)
This merely recites: mathematical analysis of RF signal data, Sequential ML based data processing, signal estimation/transformation. These are considered: generic data analysis and Mathematical Algorithm/Concept.
There is no technical mechanism provide for: a specific NN architecture, a specific channel estimation algorithm, a specific signal demapping implementation, or a technical improvement to physical layer hardware.
This does not change the nature of the abstract idea. It does not add a technical improvement to an abstract idea, such as improving computer functionality, data structure, or processing architecture.
There is no practical application, and no inventive step, the claims are still considered abstract.
Regarding claims 8, 14-16, 52-54 and 58 (ML Training/Optimization/Retraining),
The claim recites:
joint training of ML models using RF resource grids…. (claim 8),
adjusting weights and parameters …based on a loss function, comparing with ground truth values (claims 14, 15),
simulating channel effects, to obtain simulated values (claim 16),
xApp, the rApp, or the zApp to update the ML model at the RIC (claim 52),
retrain ML models, updating models provided to the D, using DU ground truth data (claim 53-54),
generative channel modeling, using simulated results as training data (claim 58).
This merely recites: mathematical optimization of ML models, statistical training operation, comparison of prediction values to ground truth, model updating and retraining. These are considered: Mathematical Algorithm/Concept.
There is no technical mechanism provide for: a specific training architecture, a specific optimization algorithm, a particular gradient-update implementation, a specific improvement to wireless operation, or a specific technical implementation for simulation-based training.
This does not change the nature of the abstract idea. It does not add a technical improvement to an abstract idea, such as improving computer functionality, data structure, or processing architecture.
There is no practical application, and no inventive step, the claims are still considered abstract.
Regarding claim 11 (OFDM Resource Grid),
The claim recites:
OFDM resource grid formatting (claim 11),
This merely recites: formatting and organizing signal data. These are considered: Mathematical Algorithm/Concept.
There is no technical mechanism provide for: improving OFDM hardware operation.
This does not change the nature of the abstract idea. It does not add a technical improvement to an abstract idea, such as improving computer functionality, data structure, or processing architecture.
There is no practical application, and no inventive step, the claims are still considered abstract.
Regarding claims 55-57 (ML Model Selection/Resource Optimization),
The claim recites:
selecting from among a plurality of machine learning models (claim 55),
selecting the first machine learning model is based on: latency, or model size (claim 56),
retrain ML models, updating models provided to the D, using DU ground truth data (claim 56),
selecting the first machine learning model is based on: cell statistics, cell usage, load changes, coverage changes, or a network condition (claim 57).
This merely recites: evaluating operational criteria, selecting model based on analyzed conditions, and optimizing allocation decision. These are considered: Mental Process.
There is no technical mechanism provide for: a specific model selection algorithm, a specific network optimization mechanism, a technical improvement to resource scheduling, or a specialized architecture for model deployment decisions.
This does not change the nature of the abstract idea. It does not add a technical improvement to an abstract idea, such as improving computer functionality, data structure, or processing architecture.
There is no practical application, and no inventive step, the claims are still considered abstract.
Regarding claim 17 (Patch-Based RF Signal Processing),
The claim recites:
patch-based processing of the samples of the RF uplink.
This merely recites: segmenting signal data and organizing RF samples into patches. These are considered: Mathematical Algorithm/Concept.
There is no technical mechanism provide for: a specific patch generation architecture, a technical improvement to memory management, or an improved RF hardware processing.
This does not change the nature of the abstract idea. It does not add a technical improvement to an abstract idea, such as improving computer functionality, data structure, or processing architecture.
There is no practical application, and no inventive step, the claims are still considered abstract.
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.
Claim(s) 1-5, 8, 11, 14-17, 19, 53-59 are rejected under 35 U.S.C. 103 as being unpatentable over WEST; Nathan et al. (US 20200143279 A1) [West] in view of O`Shea; Timothy James et al. (US 20200343985 A1) [O’Shea] in view of ZHU; Xipeng et al. (US 20230100253 A1) [Zhu].
Regarding claims 1, 19 and 59, West discloses, obtaining, samples of radio-frequency (RF) uplink data signals received wirelessly at a radio unit of the radio access network (In some implementations, a sample of electromagnetic energy processed by one or more radio frequency (RF) communication receivers is received from the one or more receivers. The sample of electromagnetic energy is examined to detect one or more RF signals present in the sample. In response to detecting one or more RF signals present in the sample, the one or more RF signals are extracted from the sample, and time and frequency bounds are estimated for each of the one or more RF signals. For each of the one or more RF signals, at least one of a type of a signal present, or a likelihood of signal being present, in the sample is classified [Abstract]. Also see ¶ [0006], [0009], [0021]);
providing the samples of the RF uplink data signals as input to at least one machine learning model (In one general aspect, a method includes: receiving a training data set including a plurality of time-series radio frequency (RF) signal samples; generating a training vector from the plurality of time-series signal samples; generating one or more new training vectors by modifying the plurality of time-series signal samples; and using the training vector and the one or more new training vectors to train a machine learning model for at least one of RF band segmentation, RF signal detection, or RF signal labelling ¶ [0021], [0023], [0139]);
in response to providing the samples of the RF uplink data signals as input to the at least one machine learning model, obtaining, based on an output of the at least one machine learning model (In some implementations, generating the one or more bounding boxes includes generating one or more bounding boxes based on output of a neural network or a clustering algorithm that receives the signal class probabilities as input ¶ [0016]. Systems and techniques are disclosed herein detect, separate, and classify signals by operating on a time-frequency basis. In some implementations, a system includes a trained machine learning (“ML”) model such as a neural network, and uses the ML model in detecting, separating, and/or classifying the signals. The time-frequency basis may be a spectrogram computing technique using a discrete Fourier transform or other matrix-transformation methods. The ML model may be trained to output probability for each time-frequency bin that a particular type of signal is present in that bin, resulting in a grid of bins. The grid of bins can then be processed into bounding boxes by locating regions of similar signal probabilities ¶ [0039]).
However, West does not explicitly facilitate at the DU; recovered data of the RF uplink data signals; and sending, by the computer system, the recovered data of the RF uplink signals to a destination device.
O’Shea discloses, at the DU (a distributed unit (DU) processor ¶ [0111]-[0113], [0122], [0129]-[0131]);
recovered data of the RF uplink data signals (FIG. 2B is a diagram showing an example of improved error vector magnitude (EVM) upon using a machine-learning network for processing digital communications. The figure presents a performance comparison between a conventional approach to estimation and equalizing involving MMSE algorithms (plot 230) and a machine-learning network approach to the same task (plot 240). Plot 230 illustrates the recovered data symbol tiles produced by using MMSE, which involves multiplication of the estimated channel inverses from the network with the received symbol value tiles. Plot 240 illustrates recovered data symbol tiles produced by a machine-learning network approach as discussed with respect to FIGS. 1 and 2A ¶ [0086], [0136]); and
sending, by the computer system, the recovered data of the RF uplink signals to a destination device (FIG. 5 is an example of signal processing stages that typically take place within the RU, DU, or CU within an O-Ran or vRAN system for 5G-NR, 4G, or 5G+ deployment, where several options for splits between the RU and DU are possible given by options 8, 7*, and 6. 7 bears an asterisk in FIG. 5 as the option 7 split, as shown in item 520, generally includes 3 different common splits labeled 7-3, 7-2, and 7-1. Each split has different bandwidth and latency requirements between elements and varies per frequency-bandwidth, number of antenna elements and other parameters. Splits 7-2, 7-3 and similar are adopted by deployed virtual RAN (vRan) systems. The machine-learning approach can be targeted to the requirements and efficiency of the resulting DU within such a split but can similarly be used for a variety of split configurations. The split in the PHY layer typically concerns allotting processing stages to either a RU or DU within a system. FIG. 5 shows how a machine-learning network can fit into the communications system 500. In some cases, the machine learning network can reside instead within the RU, where processing stages before or after the FFT, inverse FFT (IFFT), or other processing stages including synchronization may be determined by these machine learning networks and updated based on signal quality metrics generated locally or passed as feedback from the DU or CU ¶ [0112]. Also see ¶ [0129]-[0131] and [0135]).
It would have been obvious to one ordinary skilled in the art before the effective filing date of the claimed invention to combine the teachings of the cited references because O’Shea’s system would have allowed West to facilitate at the DU; recovered data of the RF uplink data signals; and sending, by the computer system, the recovered data of the RF uplink signals to a destination device. The motivation to combine is apparent in the West’s reference, because there is a need to improve communications systems that use machine learning and includes processing of communications signals using a machine-learning network.
However, neither West nor O’Shea explicitly facilitates receiving, at a distributed unit (DU) of a radio access network, from a radio access network intelligent controller (RIC) of the radio access network, at least one machine learning model, wherein the at least one machine learning model is trained at the RIC; executing in an L1 layer of the DU.
Zhu discloses, receiving, at a distributed unit (DU) of a radio access network (at least one DU…The DU is for managing the radio link control (RLC) layer, the media access control (MAC) layer, and parts of the physical (PHY) layer of the base station ¶ [0094]), from a radio access network intelligent controller (RIC) of the radio access network (stores a neural network model for training …, such as a centralized unit (CU), a distributed unit (DU), or radio access network (RAN) intelligent controller (RIC) ¶ [0093]), at least one machine learning model (a neural network model for training or inference ¶ [0093], at least one machine learning model setup procedure where a network entity, which may be a DU or RIC, sets up ML model ¶ [0106], [0113], [0130]; the configured model may run in a network entity, such as a distributed unit (DU), radio access network (RAN) intelligent controller (RIC), centralized unit user plane (CU-UP), centralized unit control plane (CU-CP), centralized unit machine learning plane (CU-XP), or any other network entity. If the model and parameter set are not locally cached in the running host, such as DU/RIC/CU-UP, etc., the model and parameter set will be downloaded ¶ [0035]), wherein the at least one machine learning model is trained at the RIC (A centralized unit model repository (CU-MR) may be hosted by a third party or by a mobile network operator (MNO), for example, at a base station. The CU-MR stores a neural network model for training or inference for use at the UE or network entities, such as a centralized unit (CU), a distributed unit (DU), or radio access network (RAN) intelligent controller (RIC) ¶ [0093], a centralized unit control plane (CU-CP) and/or centralized unit machine learning plane (CU-XP) may decide to configure a network model for inference and/or training…The configured model may run in a network entity, such as a distributed unit (DU), radio access network (RAN) intelligent controller (RIC).¶ [0035]);
executing in an L1 layer of the DU (The DU is for managing the radio link control (RLC) layer, the media access control (MAC) layer, and parts of the physical (PHY) layer ¶ [0094], configured model may run in a network entity, such as a distributed unit (DU) ¶ [0035]).
It would have been obvious to one ordinary skilled in the art before the effective filing date of the claimed invention to combine the teachings of the cited references because Zhu’s system would have allowed West and O’Shea to facilitate receiving, at a distributed unit (DU) of a radio access network, from a radio access network intelligent controller (RIC) of the radio access network, at least one machine learning model, wherein the at least one machine learning model is trained at the RIC; executing in an L1 layer of the DU. The motivation to combine is apparent in the West and O’Shea’s reference, because there is a need to improve applying neural network processing to wireless communications to achieve greater efficiencies.
Regarding claim 2, the combination of West, O’Shea and Zhu discloses, wherein sending the recovered data of the RF uplink signals to the destination device comprises sending the recovered data of the RF uplink signals to one or more computer systems external to the radio access network (West: The processing unit 130 may save this classification and/or value regression as metadata and may store it on the data storage 120. For example, the processing unit 130 may transfer the matched classification and/or value regression data to one or more external devices through a network port as metadata 122. The processing unit 130 may save the matched classification and/or value regression data locally on a file disk as metadata 124 ¶ [0062]).
Regarding claim 3, the combination of West, O’Shea and Zhu discloses, receiving downlink data for a user device in response to sending the recovered data of the RF uplink signals to the destination device; and controlling transmission of an RF data downlink signal from the radio unit to the user device, the RF data downlink signal encoding the downlink data (O’Shea: In some implementations, the input data 110 is an OFDM or CP-OFDM signal (e.g., in the 3GPP 5G-NR uplink (UL) or downlink (DL) PHY), as shown graphically as an input plot 111 that is a time-frequency spectrum grid of pilot and data subcarriers and time slots within an OFDM signal block ¶ [0047]. In some cases, a 64-quadrature amplitude modulation (QAM) 5G-NR system, or other fixed or learned modulation schemes, transmitted over the air in the normal physical downlink shared channel (PDSCH) or physical uplink shared channel (PUSCH) form, can be received using the conventional MMSE, LMMSE, or similar case, in order to achieve a certain bit error rate (BER) or error vector magnitude (EVM) ¶ [0105]. Also see ¶ [0121], [0127]).
Regarding claim 4, the combination of West, O’Shea and Zhu discloses, wherein the at least one machine learning model comprises at least one of: a first machine learning model configured to perform channel estimation based on the samples of the RF uplink data signals (O’Shea: In some implementations, the set of ground truths are values of equalized data symbols or channel estimates determined from one or more of a process of generating the pilot and data information, a decision feedback process, pilot subcarriers, or an out-of-band communication ¶ [0012], [0034], [0086]); and
a second machine learning model configured to perform symbol-demapping on estimated symbols of the RF uplink data signals, wherein the estimated symbols are based on the channel estimation by the first machine learning model (O’Shea: The device 208 uses the output prediction from the machine-learning network 212 for detecting symbols, using symbol detection component 216, where the detected symbols are estimates of the symbols transmitted from the device 201, using the prediction output by the machine-learning network 212. The detected symbols are used in performance analysis 218 ¶ [0067], [0069], [0082]. The process can begin, as shown in the example of FIG. 5, with an RF signal being received. Pre-processing stages such as cyclic prefix removal, fast Fourier transform (FFT), port reduction and resource element de-mapping, can all be used to generate a form of an unequalized resource grid. The unequalized resource grid from pre-processing steps can be sent to a machine-learning network 522 of the system 500. In this case, the machine-learning network 522 performs channel estimation, diversity or other antenna combining, and equalization before sending the resulting equalized symbols to other elements in the process flow including inverse discrete Fourier transform (iDFT) ¶ [0115]).
Regarding claim 5, the combination of West, O’Shea and Zhu discloses, wherein providing the samples of the RF uplink data signals as input to the at least one machine learning model comprises: providing the samples of the RF uplink data signals as input to the first machine learning model (West: the system includes a machine learning model that is trained using samples that are received from one or more radio receivers or simulated throughout a signal environment simulator and that are saved to a dataset. The dataset may be labelled as part of a dataset for training machine-learned models ¶ [0005], [0007], [0013], [0021], [0023]);
obtaining, as an output of the first machine learning model, channel estimates characterizing channel effects on the RF uplink data signals (O’Shea: The machine-learning network 120 learns to accomplish these tasks jointly and, in doing so, learns to compensate for channel effects and to interpolate the channel response estimate properly across a sparse grid, in some cases leveraging both data aided (e.g., reference) and non-data aided (e.g., non-reference) resource elements ¶ [0053], [0153]);
transforming the samples of the RF uplink data signals based on the channel estimates (West: Implementations may include one or more of the following features. For example, in some implementations, estimating time and frequency bounds for each of the one or more RF signals includes: transforming the sample of electromagnetic energy from a time-series representation to a time-frequency representation ¶ [0010], [0053]);
providing the transformed samples of the RF uplink data signals as input to the second machine learning model (O’Shea: These incremental changes, such as transmitter adaptation of shaping, modulation, or pre-coding, may occur as feedback mechanisms within a system including a machine-learning network (e.g., where the channel estimation can be exploited or transformed to improve or implement these functions) ¶ [0042]. The machine-learning network 212 includes several fully connected layers (FC), with a layer performing matrix multiplications of an input vector with a weight vector followed by summation to produce an output vector. In some implementations, the machine-learning network 212 includes non-linearity, such as a rectified linear unit (ReLU), sigmoid, parametric rectified linear unit (PReLU), MISH neural activation function, SWISH activation function, or other non-linearity. In some cases, the machine-learning network 212 leverages convolutional layers, skip connections, transformer layers, recurrent layers, residual layers, upsampling or downsampling layers, or a number of other techniques that serve to improve the performance of the machine-learning network 212, for example by achieving an improved performance architecture. In some implementations, the machine-learning network 212 is a convolutional neural network ¶ [0064]); and
obtaining, as an output of the second machine learning model, data indicative of the recovered data (West: In some implementations, generating the one or more bounding boxes includes generating one or more bounding boxes based on output of a neural network or a clustering algorithm that receives the signal class probabilities as input ¶ [0016]. Systems and techniques are disclosed herein detect, separate, and classify signals by operating on a time-frequency basis. In some implementations, a system includes a trained machine learning (“ML”) model such as a neural network, and uses the ML model in detecting, separating, and/or classifying the signals. The time-frequency basis may be a spectrogram computing technique using a discrete Fourier transform or other matrix-transformation methods. The ML model may be trained to output probability for each time-frequency bin that a particular type of signal is present in that bin, resulting in a grid of bins. The grid of bins can then be processed into bounding boxes by locating regions of similar signal probabilities ¶ [0039]).
Regarding claim 6, (Canceled).
Regarding claim 7, (Canceled).
Regarding claim 8, the combination of West, O’Shea and Zhu discloses, comprising training the at least one machine learning model at the RIC (Zhu: a neural network model for training or inference ¶ [0093], at least one machine learning model setup procedure where a network entity, which may be a DU or RIC, sets up ML model ¶ [0106], [0113], [0130]; the configured model may run in a network entity, such as a distributed unit (DU), radio access network (RAN) intelligent controller (RIC), centralized unit user plane (CU-UP), centralized unit control plane (CU-CP), centralized unit machine learning plane (CU-XP), or any other network entity. If the model and parameter set are not locally cached in the running host, such as DU/RIC/CU-UP, etc., the model and parameter set will be downloaded ¶ [0035]), wherein the training comprises training the first machine learning model and the second machine learning model in a joint training process, wherein training data in the joint training process comprises RF resource grids, and wherein labels for the training data includes ground-truth inferred bits corresponding to the RF resource grids or ground-truth recovered data corresponding to the RF resource grids (O’Shea: In some implementations, a set of profiles, such as urban, rural, indoor, macro, micro, femto, or other profiles related to channel behavior correlated to or predicted by deployment scenario, is used to determine an initial model of the machine-learning network 212 that is deployed, and used to configure processes for determining augmentation or other training parameters for the machine-learning network 212. In some instances, data or models may be shared in cloud environments or network sharing configurations between specific gNB cells to improve initial machine-learning network models, or to jointly improve models within multiple environments with shared phenomena. For example, cells within a grid of cells that share similar interference, cells with similar delay spreads, or cells with other similar behaviors, can be used to improve the effectiveness, speed, or performance of the machine-learning network 212 ¶ [0079]. Also see ¶ [0052], [0053]).
Regarding claim 9, (Canceled).
Regarding claim 10, (Canceled).
Regarding claim 11, the combination of West, O’Shea and Zhu discloses, wherein the samples of the RF uplink data signals are provided as input in an orthogonal frequency division multiplexing (OFDM) resource grid form (O’Shea: The data signal is generated using a modulator for orthogonal frequency-division multiplexing (OFDM) systems [Abstract]. Also see ¶ [0006], [0007], [0018]).
Regarding claim 12, (Canceled).
Regarding claim 13, (Canceled).
Regarding claim 14, the combination of West, O’Shea and Zhu discloses, wherein the samples of the RF uplink data signals comprise pilot signals de-rotated in reference to a demodulation reference signal (O’Shea: OFDM or CP-OFDM signal (e.g., in the 3GPP 5G-NR uplink (UL) or downlink (DL) PHY), as shown graphically as an input plot 111 that is a time-frequency spectrum grid of pilot and data subcarriers and time slots within an OFDM signal block ¶ [0047], [0062], demodulation or decoding, either through conventional statistical methods such as MMSE or believe propagation, can estimate the most likely bits, symbols, or values seen based on values in the received signal ¶ [0069], uses a demodulation reference signal (DM-RS) approach ¶ [0098], the demodulation, the descrambling, the rate matching, the decoding processes, or even cascaded source-decoding tasks such as video decoding processes in specialized cases, or additional probabilistic learning and correction of MAC content based on historical probabilistic information and training ¶ [0119], also see [Abstract]).
Regarding claim 15, the combination of West, O’Shea and Zhu discloses, comprising training a first machine learning model of the at least one machine learning model at the RIC, wherein the training comprises adjusting weights and parameters of the first machine learning model based on a loss function, wherein the loss function (O’Shea: In some implementations, updating the machine-learning network based on the error term includes determining, based on a loss function, a rate of change of one or more weight values within the machine-learning network; and performing an optimization process using the rate of change to update the one or more weight values within the machine-learning network ¶ [0013], [0068], [0097]) is based on a comparison of (i) data values in uplink resource grids and (ii) ground truth values corresponding to the data values (O’Shea: a number of systems use multi-carrier signal modulation schemes, such as OFDM, to transmit information. Some of the time-frequency subcarriers within an OFDM grid can be allocated as reference tones or pilot signals. Pilot signals can be resource elements with known values; these can be referred to as pilot resource elements. Other resource elements within the OFDM grid can carry data; these can be referred to as data resource elements ¶ [0031], [0052], [0058]. Upon knowledge of a correct frame (e.g., the checksum passes, LDPC check bits are correct), bits can be re-modulated to provide ground truth symbol values, correct bits, or log-likelihood ratios can be computed from the received and ground truth symbol locations or channel estimates. These ground truth symbol values, correct bits, or log-likelihood ratios, among others, can be used within the distance metric in order to update the machine learning model and its weights ¶ [0069], [0095]).
Regarding claim 16, the combination of West, O’Shea and Zhu discloses, comprising: at the RIC, simulating channel effects on signal values, to obtain the data values as simulated pilot values (O’Shea: Implementations may include one or more of the following features. In some implementations, a machine-learning network performs operations corresponding to pilot estimation, interpolation, and equalization. The communications channel may be a simulated channel that includes one or more of an Additive White Gaussian Noise (AWGN) or Rayleigh fading channel model, International Telecommunication Union (ITU) or 3.sup.rd Generation Partnership Project (3GPP) fading channel models, emulated radio emissions, propagation models, ray tracing within simulated geometry or an environment to produce channel effects, or a machine-learning network trained to approximate measurements over a real channel ¶ [0016]. O’Shea: The modified pilot and data information are processed using a machine-learning network. A prediction corresponding to the data signal transmitted through the communications channel is obtained from the machine-learning network. The prediction is compared to a set of ground truths and updates, based on a corresponding error term, are applied to the machine-learning network [Abstract]. Also see ¶ [0007], [0012], [0095]).
Regarding claim 17, the combination of West, O’Shea and Zhu discloses, wherein the at least one machine learning model is configured to perform patch-based processing of the samples of the RF uplink data signals (O’Shea: see Fig. 1, wherein input and output are patches which is processed by ML model).
Regarding claim 18, (Canceled).
Regarding claim 53, the combination of West, O’Shea and Zhu discloses, comprising training the at least one machine learning model at the RIC (Zhu: a neural network model for training or inference ¶ [0093], at least one machine learning model setup procedure where a network entity, which may be a DU or RIC, sets up ML model ¶ [0106], [0113], [0130]; the configured model may run in a network entity, such as a distributed unit (DU), radio access network (RAN) intelligent controller (RIC), centralized unit user plane (CU-UP), centralized unit control plane (CU-CP), centralized unit machine learning plane (CU-XP), or any other network entity. If the model and parameter set are not locally cached in the running host, such as DU/RIC/CU-UP, etc., the model and parameter set will be downloaded ¶ [0035]), wherein the training the at least one machine learning model and providing the at least one machine learning model to the DU (DU model activation ¶ [0117], a neural network model for training or inference … The CU-MR stores a neural network model for training or inference for use at the UE or network entities, such as a centralized unit (CU) , a distributed unit (DU) ¶ [0093]) comprises:
retraining the at least one machine learning model at the RIC (training or inference/training nodes ¶ [0035], [0093], [0117], [0130]); and
based on the retraining, providing, to the DU, an update to the at least one machine learning model (O’Shea: a distributed unit (DU) processor, or within a small cell or distributed antenna system (DAS) system. In some cases, the update process, or other processes shown in FIG. 4A or FIG. 4B can be performed on the unit itself, on a cloud server for updating models ¶ [0111]), wherein the at least one machine learning model was previously provided to the DU (ZHU: DU model activation ¶ [0117]).
Regarding claim 54, the combination of West, O’Shea and Zhu discloses, wherein the at least one machine learning model was previously provided to the DU as a generic model (Zhu: configured model ¶ [0035], stores a NN model ¶ [0093], determining the NN model ¶ [0130]), and wherein retraining the at least one machine learning model is performed based on ground truth data from the DU (O’Shea: The prediction is compared to a set of ground truths and updates, … applied to the machine-learning network [Abstract], also see ¶ [0007], [0012], [0069], [0095]).
Regarding claim 55, the combination of West, O’Shea and Zhu discloses, at the RIC, selecting, from among a plurality of machine learning models, a first machine learning model to provide to the DU (Zhu: a neural network model for training or inference …centralized unit model repository…stores NN models ¶ [0093], at least one machine learning model setup procedure where a network entity, which may be a DU or RIC, sets up ML model ¶ [0106], [0113], [0130]; the configured model may run in a network entity, such as a distributed unit (DU), radio access network (RAN) intelligent controller (RIC), centralized unit user plane (CU-UP), centralized unit control plane (CU-CP), centralized unit machine learning plane (CU-XP), or any other network entity. If the model and parameter set are not locally cached in the running host, such as DU/RIC/CU-UP, etc., the model and parameter set will be downloaded ¶ [0035]).
Regarding claim 56, the combination of West, O’Shea and Zhu discloses, wherein selecting the first machine learning model is based on at least one of: a latency of the first machine learning model, or a size of the first machine learning model (Zhu: maximum model size ¶ [0097], also see ¶ [0060]).
Regarding claim 57, the combination of West, O’Shea and Zhu discloses, wherein selecting the first machine learning model is based on at least one of cell statistics, cell usage, load changes, coverage changes, or a network condition of the radio access network (Zhu: and at least one radio unit (RU) (only one shown.) The CU includes a centralized unit control plane (CU-CP) for managing the radio resource control (RRC) layer and packet data convergence protocol (PDCP) layer of the base station, a centralized unit user plane (CU-UP) for managing the user plane part of the PDCP layer and the user plane part of the service data adaptation protocol (SDAP) layer, and a centralized unit machine learning plane (CU-XP) for managing machine learning functions, such as which model to select to execute an NNF ¶ [0094], also see ¶ [0100], [0106], [0111]-[0112], [0129]).
Regarding claim 58, the combination of West, O’Shea and Zhu discloses, executing, at the RIC, a generative channel modeling application configured to simulate channel effects on a signal, to obtain a simulation result, wherein training the at least one machine learning model comprises using the simulation result as training data (O’Shea: channel generative adversarial network (GAN) machine learning networks trained to reproduce the channel response of one or more cells based on prior measurement or simulation ¶ [0081], The communications channel may be a simulated channel that includes one or more of an Additive White Gaussian Noise (AWGN) or Rayleigh fading channel model ¶ [0008]. Also see ¶ [0044], [0068], [0080], [0092]).
Claim(s) 52 is rejected under 35 U.S.C. 103 as being unpatentable over WEST in view of O`Shea in view of ZHU in view of SIVARAJ; Rajarajan et al. (US 20220232452 A1) [SIVARAJ].
Regarding claim 52, the combination of West, O’Shea and Zhu teaches all the limitation of claim 1.
However, neither one of West, O’Shea or Zhu does not explicitly facilitate wherein the at least one machine learning model is configured to perform patch-based processing of the samples of the RF uplink data signals.
SIVARAJ discloses, wherein the at least one machine learning model is configured to perform patch-based processing of the samples of the RF uplink data signals (called the RAN Intelligent Controller (RIC) using open interfaces and extensible applications, called xApps, from third parties (including the mobile network operators themselves) can be deployed in the RIC that can use advanced analytics ¶ [0012], O-RAN nodes received over the O1 interface and uses RIC applications (called rApps) that train and develop machine learning (ML) models ¶ [0045], By enabling unique identification of individual UEs in the RIC, the mechanism serves as an important component in building service and information models for the E2/O1 interfaces and extensible applications (xApps and rApps) in the near-RT RIC and non-RT RIC that can control and optimize the radio resource management decisions on a per-UE basis for a wide variety of RIC use-cases ¶ [0191]).
It would have been obvious to one ordinary skilled in the art before the effective filing date of the claimed invention to combine the teachings of the cited references because SIVARAJ’s system would have allowed West, O’Shea, and Zhu to facilitate wherein the at least one machine learning model is configured to perform patch-based processing of the samples of the RF uplink data signals. The motivation to combine is apparent in the West, O’Shea. And Zhu’s reference, because there is a need to provide an improved mechanism for controlling the RAN from the RIC on a per-UE basis.
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 MOHAMMAD S ROSTAMI whose telephone number is (571)270-1980. The examiner can normally be reached Mon-Fri From 9 a.m. to 5 p.m..
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, Boris Gorney can be reached at (571)270-5626. 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.
5/15/2026
/MOHAMMAD S ROSTAMI/ Primary Examiner, Art Unit 2154
Prosecution Insights