DETAILED ACTION
This action is responsive to claims filed on 06 July 2026. Claims 1-20 are pending examination.
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 .
Response to Arguments
Applicant’s arguments, see pages 9-13, filed 06 July 2026, with respect to the rejection(s) of claims 1-20 under Ryu et al. (US 2021/0328630 A1) in view of Tervo et al (US 2020/0169332 A1) and Oh et al (US 2024/0178862 A1) have been fully considered and are persuasive as to the prior rejection. Accordingly, the rejection has been withdrawn; however, upon further consideration, claims 1-11, 13-20 are rejected under 35 U.S.C 103 over Ryu et al. (US 2021/0328630 A1) in view of Namgoong et al (US 2017/0288759 A1) and claim 12 is rejected under U.S.C 103 over Ryu et al. (US 2021/0328630 A1) in view of Oh et al (US 2024/0178862 A1).
Claim Rejections - 35 USC § 103
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.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim 1-11, and 13-20 is rejected under 35 U.S.C. 103 as being unpatentable over Ryu et al. (US 2021/0328630 A1) (hereinafter Ry) in view of Namgoong et al. (US 2017/0288759 A1) (hereinafter Na):
Regarding claim 1, Ry-Na teaches a machine learning system (Ry, see fig. 9) for a wireless communication system, the machine learning system comprising:
processing circuitry configured to (Ry, Fig. 11, [0123]-[0160], [0161]-[0223], [0144]-[0153]: The device 1105 may also include a processor. Each of these components may be in communication with one another (e.g., via one or more buses).):
provide an output based on an input, the input representing a status of the wireless communication system comprising a plurality of radio nodes, the output representing an action for the wireless communication system, the machine learning system being configured for a … for providing the output…(Ry, Fig. 5, [0059]-[0095], [0096]-[0114], [0144]-[0160], [0161]-[0223]: Examiner views the reported measurements of reference signals from a base station and one or more other base stations as the input representing a status of the wireless communication system, with those base stations corresponding to the plurality of radio nodes. The Examiner further views the beam parameters determined using the selected predictive model and used for uplink and downlink communications as the output representing an action for the system. [0105] In some cases, the base station 105-c may generate multiple different predictive models for a particular function (e.g., the base station 105-c may generate different predictive models for delay spread based on UE RSRP and position information). In some cases, predictive models may be generated for a number of different functions, such as beam prediction functions (e.g., what transmit/receive beams to use for communications), channel property prediction functions (e.g., what will a delay spread be for communications), connectivity prediction functions (e.g., when to handover between base stations, which base station to receive a handover, etc.).. [0106] At 425, the UE 115-d may transmit a measurement report to the base station 105-c that includes values for various reference signal measurements made at the UE 115-d. [0107] At 430, the base station 105-c may select a model for UE 115-d communications. Such selection may be made based on the one or more measurement reports received from the UE 115-d. [0108] At 440, the UE 115-d may determine one or more beam parameters based on the selected predictive model. At 445, the UE 115-d and base station 105-c may communicate uplink and downlink communications based on beamforming parameters provided by the one or more models.).
Thus, the system of Ry does not explicitly teach …the phase ambiguity limitation including a limit on a number of phase formats, a phase format being a solution in a solution space of the machine learning system.
Similar to the system of Ry, Na teaches that the choices of the precoding matrix V(k) are not unique because different phase representations may be used for the same precoding result (Na, [0061]), which can be seen as, the phase ambiguity limitation including a limit on a number of phase formats, a phase format being a solution in a solution space of the machine learning system (Na, fig. 7, fig. 12, [0030]-[0054], [0055]-[0090]: The Examiner views the different phase representations as different phase formats representing equivalent precoding solutions. Na further teaches selecting a modified precoding matrix that maintains the same capacity while addressing the phase ambiguity (Na, [0063]). Na also teaches that the phase ambiguity may be eliminated and that the modified precoding matric removes the arbitrary phase (Na, [0064]-[0065]). Examiner views this as limiting the number of phase formats used to provide the precoding output. [0061] The choices of V.sub.k available to the precoding component 716, however, may not be unique. For example, U.sub.kΘ.sub.k and V.sub.kΘ.sub.K can also be the left singular vector matrix and right singular vector matrix of H.sub.k, where Θ.sub.k is an N.sub.r×N.sub.r diagonal matrix with the diagonal elements having unit amplitude. That is, |Θ.sub.k(i,i)| is 1, where i is from 1 to N.sub.r. [0063] In a second technique to determine a precoding matrix P.sub.k′, the precoding matrices P.sub.k′ are modified to address the ambiguity and discontinuity described supra. For any N.sub.r×N.sub.r unitary matrix Ξ.sub.k, the precoding component 716 may use V.sub.k Ξ.sub.K as a precoding matrix P.sub.k′ to achieve the same capacity as the precoding matrix P.sub.k (i.e., V.sub.k). Furthermore, the precoding component 716 may choose U.sub.k.sup.H as Ξ.sub.k. As such, the precoding component 716 determines:P′.sub.k=V.sub.kU.sub.k.sup.N. [0064] As such, the phase ambiguity in the left singular vector matrix and the right singular vector matrix may be eliminated. [0065] As shown, P.sub.k′ removes the arbitrary phase introduced by the left singular vector matrix and the right singular vector matrix on the precoded channels.).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Ry with Na by applying Na’s phase-ambiguity-elimination technique to the beamforming parameters determined using Ryu’s predictive model, to reduce phase ambiguity and discontinuity across tones while maintain the same capacity, which would improve channel estimate and UE throughput (Na, [0062]-[0063]).
Regarding claim 2, Ry-Na teach a machine learning system (Ry, see fig. 9) for a wireless communication system, the machine learning system comprising:
processing circuitry configured to (Ry, Fig. 11, [0123]-[0160], [0161]-[0223], [0144]-[0153]: The device 1105 may also include a processor. Each of these components may be in communication with one another (e.g., via one or more buses).):
provide an output based on an input, the input representing a status of the wireless(Ry, Fig. 5, [0059]-[0095], [0096]-[0114], [0144]-[0160], [0161]-[0223]: Examiner views the reported measurements of reference signals from a base station and one or more other base stations as the input representing a status of the wireless communication system, with those base stations corresponding to the plurality of radio nodes. The Examiner further views the beam parameters determined using the selected predictive model and used for uplink and downlink communications as the output representing an action for the system. The Examiner further views the use of measurement-report data in NN/AI/ML techniques to tune the predictive models as training the machine-learning system [0105] In some cases, the base station 105-c may generate multiple different predictive models for a particular function (e.g., the base station 105-c may generate different predictive models for delay spread based on UE RSRP and position information). In some cases, predictive models may be generated for a number of different functions, such as beam prediction functions (e.g., what transmit/receive beams to use for communications), channel property prediction functions (e.g., what will a delay spread be for communications), connectivity prediction functions (e.g., when to handover between base stations, which base station to receive a handover, etc.). [0106] At 425, the UE 115-d may transmit a measurement report to the base station 105-c that includes values for various reference signal measurements made at the UE 115-d. [0107] At 430, the base station 105-c may select a model for UE 115-d communications. Such selection may be made based on the one or more measurement reports received from the UE 115-d. [0108] At 440, the UE 115-d may determine one or more beam parameters based on the selected predictive model. At 445, the UE 115-d and base station 105-c may communicate uplink and downlink communications based on beamforming parameters provided by the one or more models. [0109] The base station 105-c may use the measurement report for further data points in the NN/AI/ML techniques to tune the predictive models, in some cases. ).
Thus, the system of Ry does not explicitly teach …the phase ambiguity limitation including a limit on a number of phase formats, a phase format being a solution in a solution space of the machine learning system.
Similar to the system of Ry, Na teaches that the choices of the precoding matrix V(k) are not unique because different phase representations may be used for the same precoding result (Na, [0061]), which can be seen as, the phase ambiguity limitation including a limit on a number of phase formats, a phase format being a solution in a solution space of the machine learning system (Na, fig. 7, fig. 12, [0030]-[0054], [0055]-[0090]: The Examiner views the different phase representations as different phase formats representing equivalent precoding solutions. Na further teaches selecting a modified precoding matrix that maintains the same capacity while addressing the phase ambiguity (Na, [0063]). Na also teaches that the phase ambiguity may be eliminated and that the modified precoding matric removes the arbitraty phase (Na, [0064]-[0065]). The Examiner views this as limiting the number of phase formats used to provide the precoding output. [0061] The choices of V.sub.k available to the precoding component 716, however, may not be unique. For example, U.sub.kΘ.sub.k and V.sub.kΘ.sub.K can also be the left singular vector matrix and right singular vector matrix of H.sub.k, where Θ.sub.k is an N.sub.r×N.sub.r diagonal matrix with the diagonal elements having unit amplitude. That is, |Θ.sub.k(i,i)| is 1, where i is from 1 to N.sub.r. [0063] In a second technique to determine a precoding matrix P.sub.k′, the precoding matrices P.sub.k′ are modified to address the ambiguity and discontinuity described supra. For any N.sub.r×N.sub.r unitary matrix Ξ.sub.k, the precoding component 716 may use V.sub.k Ξ.sub.K as a precoding matrix P.sub.k′ to achieve the same capacity as the precoding matrix P.sub.k (i.e., V.sub.k). Furthermore, the precoding component 716 may choose U.sub.k.sup.H as Ξ.sub.k. As such, the precoding component 716 determines:P′.sub.k=V.sub.kU.sub.k.sup.N. [0064] As such, the phase ambiguity in the left singular vector matrix and the right singular vector matrix may be eliminated. [0065] As shown, P.sub.k′ removes the arbitrary phase introduced by the left singular vector matrix and the right singular vector matrix on the precoded channels.).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Ry with Na to train/tune Ry’s predictive model using Na’s phase-ambiguity constraint when providing the beamforming output. Na teaches modifying the precoding matrices to address phase ambiguity and discontinuity while maintaining the same capacity and eliminating arbitrary phase (Na, [0062]-[0063]).
Regarding claim 3, 4, and 16, Na teaches a machine learning system (Ry, see fig. 9):
Thus, Ry does not explicitly teach wherein the phase ambiguity limitation is regarding the output.
Similar to the system of Ry, Na teaches that the choices of the precoding matrix V(k) are not unique because different phase representations may be used for the same precoding result (Na, [0061]), which can be seen as, wherein the phase ambiguity limitation is regarding the output (Na, fig. 7, fig. 12, [0030]-[0054], [0055]-[0090]: The Examiner views the different phase representations as different phase formats representing equivalent precoding solutions. Na further teaches selecting a modified precoding matrix that maintains the same capacity while addressing the phase ambiguity (Na, [0063]). Na also teaches that the phase ambiguity may be eliminated and that the modified precoding matric removes the arbitraty phase (Na, [0064]-[0065]). The Examiner views this as limiting the number of phase formats used to provide the precoding output. [0061] The choices of V.sub.k available to the precoding component 716, however, may not be unique. For example, U.sub.kΘ.sub.k and V.sub.kΘ.sub.K can also be the left singular vector matrix and right singular vector matrix of H.sub.k, where Θ.sub.k is an N.sub.r×N.sub.r diagonal matrix with the diagonal elements having unit amplitude. That is, |Θ.sub.k(i,i)| is 1, where i is from 1 to N.sub.r. [0063] In a second technique to determine a precoding matrix P.sub.k′, the precoding matrices P.sub.k′ are modified to address the ambiguity and discontinuity described supra. For any N.sub.r×N.sub.r unitary matrix Ξ.sub.k, the precoding component 716 may use V.sub.k Ξ.sub.K as a precoding matrix P.sub.k′ to achieve the same capacity as the precoding matrix P.sub.k (i.e., V.sub.k). Furthermore, the precoding component 716 may choose U.sub.k.sup.H as Ξ.sub.k. As such, the precoding component 716 determines:P′.sub.k=V.sub.kU.sub.k.sup.N. [0064] As such, the phase ambiguity in the left singular vector matrix and the right singular vector matrix may be eliminated. [0065] As shown, P.sub.k′ removes the arbitrary phase introduced by the left singular vector matrix and the right singular vector matrix on the precoded channels.).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Ry with Na by applying Na’s phase-ambiguity technique to the beamforming output determined using Ry’s predictive model. Na teaches that addressing phase ambiguity and discontinuity allows more accurate channel estimation and avoids reduced UE throughput (Na, [0062]-[0063]).
Regarding claim 5 and 18, Ry teaches a machine learning system (Ry, see fig. 9):
wherein the output corresponds to a set of beamforming parameters (Ry, fig. 1, fig. 4, fig. 7, [0059]-[0095], [0123]-[0131], [0104]-[0109]: [0095] One or more of the base stations 105 may include a base station communications manager 102. The base station communications manager 102 may identify multiple predictive models for a number of functions for beamformed communications with a UE 115. The base station communications manager 102 may provide the multiple predictive models to the UE 115 for use in determining one or more beamforming parameters for beamformed communications. In some cases, the base station communications manager 102 may receive one or more measurement reports from a UE 115, and select one of the predictive models for a function, and provide an indication of the selected model to the UE 115. The base station communications manager 102 may be an example of a communications manager 1310 of FIG. 13.).
Regarding claim 6 and 19, Ry teaches a machine learning system (Ry, see fig. 9):
wherein the status represents a channel estimate of the wireless communication system (Ry, Fig. 4, [0052]-[0095], [0096]-[0143], [0161]-[0177]: [0056] Further, in some cases the UE may update its predictive models based on the current channel environment observed at the UE. In such cases, the UE may measure channel characteristics between it and its serving base station, and transmit corresponding measurement reports to the base station. Based on the measurement reports, the base station may send an update to the UE to use a different predictive model, which the UE may use to update the model and any associated parameters. Additionally or alternatively, in some cases the base station may provide a model selection function that may be used at the UE to update its models. The UE in such cases may make measurements of the channel, or of its internal states (e.g., gyroscopic measurements that may indicate to switch antenna panels), that are provided to the model selection function. The model selection function may then output updates to apply to the UE's predictive models.).
Regarding claim 7 and 20, Ry teaches a machine learning system (Ry, see fig. 9):
wherein the output corresponds to a set of beamforming weights (Ry, fig. 1, [0059]-[0095]: [0093] A receiving device (e.g., a UE 115) may try multiple receive configurations (e.g., directional listening) when receiving various signals from the base station 105, such as synchronization signals, reference signals, beam selection signals, or other control signals. For example, a receiving device may try multiple receive directions by receiving via different antenna subarrays, by processing received signals according to different antenna subarrays, by receiving according to different receive beamforming weight sets (e.g., different directional listening weight sets) applied to signals received at multiple antenna elements of an antenna array, or by processing received signals according to different receive beamforming weight sets applied to signals received at multiple antenna elements of an antenna array, any of which may be referred to as “listening” according to different receive configurations or receive directions. In some examples, a receiving device may use a single receive configuration to receive along a single beam direction (e.g., when receiving a data signal). The single receive configuration may be aligned in a beam direction determined based on listening according to different receive configuration directions (e.g., a beam direction determined to have a highest signal strength, highest signal-to-noise ratio (SNR), or otherwise acceptable signal quality based on listening according to multiple beam directions).).
Regarding claim 8 and 17, Ry teaches a machine learning system according to claim 1 (Ry, see fig. 9):
wherein the output represents one action from an action space of available actions (Ry, fig. 4, fig. 5, [0053]-[0054], [0104]-[0109], [0110]-[0114]: [0054] In some cases, the base station may provide a number of different models for each of a number of different functions, and may assist the UE in model selection. For example, a UE may measure a channel between the UE and a serving base station or cell, and optionally one or more other base stations or cells from which the UE can receive a signal, and use the channel measurements for model selection. Such measurements may be made based on periodic synchronization signal blocks (SSBs) transmitted by base stations, and the UE may measure any detected SSBs from a serving base station or other base stations. Further, in some cases, the UE may measure its position (e.g., based on global positioning system (GPS) measurements, indoor positioning measurements, or combinations thereof), which may be provided as an input to one or more models or used to help in model selection. The UE, in some cases, may transmit one or more measurement reports to the serving base station that may provide the measured channel conditions, positioning information, or combinations thereof. In response to the measurement report, the serving base station may provide the UE with a prioritized list of predictive models to be used by the UE for each functionality (e.g., based on which models provide better results for the UE functions based on the UE measurement report). In some cases, the UE may provide feedback to the base station related to the accuracy of the prediction of the model indicated by the base station, which may be used by the base station to update recommendations for future indications of which model to select.).
Regarding claim 9, Ry-Na teach a machine learning system according to claim 1 (Ry, see fig. 9):
wherein the … limits an action space of available action by fixing at least one element or parameter of a beamforming weight representation (Ry, fig. 1, [0059]-[0095]: [0093] A receiving device (e.g., a UE 115) may try multiple receive configurations (e.g., directional listening) when receiving various signals from the base station 105, such as synchronization signals, reference signals, beam selection signals, or other control signals. For example, a receiving device may try multiple receive directions by receiving via different antenna subarrays, by processing received signals according to different antenna subarrays, by receiving according to different receive beamforming weight sets (e.g., different directional listening weight sets) applied to signals received at multiple antenna elements of an antenna array, or by processing received signals according to different receive beamforming weight sets applied to signals received at multiple antenna elements of an antenna array, any of which may be referred to as “listening” according to different receive configurations or receive directions. In some examples, a receiving device may use a single receive configuration to receive along a single beam direction (e.g., when receiving a data signal). The single receive configuration may be aligned in a beam direction determined based on listening according to different receive configuration directions (e.g., a beam direction determined to have a highest signal strength, highest signal-to-noise ratio (SNR), or otherwise acceptable signal quality based on listening according to multiple beam directions).).
Thus, Ry does not explicitly teach the term phase ambiguity limitation.
Similar to the system of Ry, Na teaches that the choices of the precoding matrix V(k) are not unique because different phase representations may be used for the same precoding result (Na, [0061]), which can be seen as, phase ambiguity limitation (Na, fig. 7, fig. 12, [0030]-[0054], [0055]-[0090]: The Examiner views the different phase representations as different phase formats representing equivalent precoding solutions. Na further teaches selecting a modified precoding matrix that maintains the same capacity while addressing the phase ambiguity (Na, [0063]). Na also teaches that the phase ambiguity may be eliminated and that the modified precoding matric removes the arbitraty phase (Na, [0064]-[0065]). Examiner views this as limiting the number of phase formats used to provide the precoding output. [0061] The choices of V.sub.k available to the precoding component 716, however, may not be unique. For example, U.sub.kΘ.sub.k and V.sub.kΘ.sub.K can also be the left singular vector matrix and right singular vector matrix of H.sub.k, where Θ.sub.k is an N.sub.r×N.sub.r diagonal matrix with the diagonal elements having unit amplitude. That is, |Θ.sub.k(i,i)| is 1, where i is from 1 to N.sub.r. [0063] In a second technique to determine a precoding matrix P.sub.k′, the precoding matrices P.sub.k′ are modified to address the ambiguity and discontinuity described supra. For any N.sub.r×N.sub.r unitary matrix Ξ.sub.k, the precoding component 716 may use V.sub.k Ξ.sub.K as a precoding matrix P.sub.k′ to achieve the same capacity as the precoding matrix P.sub.k (i.e., V.sub.k). Furthermore, the precoding component 716 may choose U.sub.k.sup.H as Ξ.sub.k. As such, the precoding component 716 determines:P′.sub.k=V.sub.kU.sub.k.sup.N. [0064] As such, the phase ambiguity in the left singular vector matrix and the right singular vector matrix may be eliminated. [0065] As shown, P.sub.k′ removes the arbitrary phase introduced by the left singular vector matrix and the right singular vector matrix on the precoded channels.).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Ry with Na by applying Na’s phase-ambiguity-elimination technique to the beamforming parameters determined using Ryu’s predictive model, to reduce phase ambiguity and discontinuity across tones while maintain the same capacity, which would improve channel estimate and UE throughput (Na, [0062]-[0063]).
Regarding claim 10, Ry teaches a machine learning system according to claim 1 (Ry, see fig. 9):
wherein the action is determined based on a capacity of the wireless communication system (Ry, fig. 1, [0059]-[0095]: [0092] In some examples, transmissions by a device (e.g., by a base station 105 or a UE 115) may be performed using multiple beam directions, and the device may use a combination of digital precoding or radio frequency beamforming to generate a combined beam for transmission (e.g., from a base station 105 to a UE 115). The UE 115 may report feedback that indicates precoding weights for one or more beam directions, and the feedback may correspond to a configured number of beams across a system bandwidth or one or more sub-bands. The base station 105 may transmit a reference signal (e.g., a cell-specific reference signal (CRS), a channel state information reference signal (CSI-RS)), which may be precoded or unprecoded. The UE 115 may provide feedback for beam selection, which may be a precoding matrix indicator (PMI) or codebook-based feedback (e.g., a multi-panel type codebook, a linear combination type codebook, a port selection type codebook). Although these techniques are described with reference to signals transmitted in one or more directions by a base station 105, a UE 115 may employ similar techniques for transmitting signals multiple times in different directions (e.g., for identifying a beam direction for subsequent transmission or reception by the UE 115) or for transmitting a signal in a single direction (e.g., for transmitting data to a receiving device).).
Regarding claim 11, Ry teaches a machine learning system according to claim 1 (Ry, see fig. 9):
wherein the action is determined based on an optimisation of the wireless communication system (Ry, fig. 1 and 5, [0059]-[0095], [0110]-[0116]: [0093] A receiving device (e.g., a UE 115) may try multiple receive configurations (e.g., directional listening) when receiving various signals from the base station 105, such as synchronization signals, reference signals, beam selection signals, or other control signals. For example, a receiving device may try multiple receive directions by receiving via different antenna subarrays, by processing received signals according to different antenna subarrays, by receiving according to different receive beamforming weight sets (e.g., different directional listening weight sets) applied to signals received at multiple antenna elements of an antenna array, or by processing received signals according to different receive beamforming weight sets applied to signals received at multiple antenna elements of an antenna array, any of which may be referred to as “listening” according to different receive configurations or receive directions. In some examples, a receiving device may use a single receive configuration to receive along a single beam direction (e.g., when receiving a data signal). The single receive configuration may be aligned in a beam direction determined based on listening according to different receive configuration directions (e.g., a beam direction determined to have a highest signal strength, highest signal-to-noise ratio (SNR), or otherwise acceptable signal quality based on listening according to multiple beam directions).).
Regarding claim 13, Ry-Na teach a radio node for a wireless communication system (Ry, see fig. 1) configured to one or both:
provide information for an input to a machine learning system (Ry, fig. 4 and fig. 5, [0073]-[0078], [0104]-[0109], [0110]-[0114]: [0075] Some UEs 115, such as MTC or IoT devices, may be low cost or low complexity devices and may provide for automated communication between machines (e.g., via Machine-to-Machine (M2M) communication). M2M communication or MTC may refer to data communication technologies that allow devices to communicate with one another or a base station 105 without human intervention. In some examples, M2M communication or MTC may include communications from devices that integrate sensors or meters to measure or capture information and relay such information to a central server or application program that makes use of the information or presents the information to humans interacting with the application program. Some UEs 115 may be designed to collect information or enable automated behavior of machines or other devices. Examples of applications for MTC devices include smart metering, inventory monitoring, water level monitoring, equipment monitoring, healthcare monitoring, wildlife monitoring, weather and geological event monitoring, fleet management and tracking, remote security sensing, physical access control, and transaction-based business charging. ); and
be controlled based on an action provided by a machine learning system; and
machine learning system being configured to provide an output based on the input, the input representing a status of a wireless communication system comprising a plurality of radio nodes, the output representing an action for the wireless communication system, the machine learning system being configured for a phase ambiguity limitation for providing the output…(Ry, Fig. 1 and 9, [0053], [0059]-[0095],[0144]-[0153]: [0089] Beamforming, which may also be referred to as spatial filtering, directional transmission, or directional reception, is a signal processing technique that may be used at a transmitting device or a receiving device (e.g., a base station 105, a UE 115) to shape or steer an antenna beam (e.g., a transmit beam, a receive beam) along a spatial path between the transmitting device and the receiving device. Beamforming may be achieved by combining the signals communicated via antenna elements of an antenna array such that some signals propagating at particular orientations with respect to an antenna array experience constructive interference while others experience destructive interference. The adjustment of signals communicated via the antenna elements may include a transmitting device or a receiving device applying amplitude offsets, phase offsets, or both to signals carried via the antenna elements associated with the device. The adjustments associated with each of the antenna elements may be defined by a beamforming weight set associated with a particular orientation (e.g., with respect to the antenna array of the transmitting device or receiving device, or with respect to some other orientation.).
Thus, Ry does not explicitly teach …the phase ambiguity limitation including a limit on a number of phase formats, a phase format being a solution in a solution space of the machine learning system.
Similar to the system of Ry, Na teaches that the choices of the precoding matrix V(k) are not unique because different phase representations may be used for the same precoding result (Na, [0061]), which can be seen as, …the phase ambiguity limitation including a limit on a number of phase formats, a phase format being a solution in a solution space of the machine learning system (Na, fig. 7, fig. 12, [0030]-[0054], [0055]-[0090]: The Examiner views the different phase representations as different phase formats representing equivalent precoding solutions. Na further teaches selecting a modified precoding matrix that maintains the same capacity while addressing the phase ambiguity (Na, [0063]). Na also teaches that the phase ambiguity may be eliminated and that the modified precoding matric removes the arbitraty phase (Na, [0064]-[0065]). Examiner views this as limiting the number of phase formats used to provide the precoding output. [0061] The choices of V.sub.k available to the precoding component 716, however, may not be unique. For example, U.sub.kΘ.sub.k and V.sub.kΘ.sub.K can also be the left singular vector matrix and right singular vector matrix of H.sub.k, where Θ.sub.k is an N.sub.r×N.sub.r diagonal matrix with the diagonal elements having unit amplitude. That is, |Θ.sub.k(i,i)| is 1, where i is from 1 to N.sub.r. [0063] In a second technique to determine a precoding matrix P.sub.k′, the precoding matrices P.sub.k′ are modified to address the ambiguity and discontinuity described supra. For any N.sub.r×N.sub.r unitary matrix Ξ.sub.k, the precoding component 716 may use V.sub.k Ξ.sub.K as a precoding matrix P.sub.k′ to achieve the same capacity as the precoding matrix P.sub.k (i.e., V.sub.k). Furthermore, the precoding component 716 may choose U.sub.k.sup.H as Ξ.sub.k. As such, the precoding component 716 determines:P′.sub.k=V.sub.kU.sub.k.sup.N. [0064] As such, the phase ambiguity in the left singular vector matrix and the right singular vector matrix may be eliminated. [0065] As shown, P.sub.k′ removes the arbitrary phase introduced by the left singular vector matrix and the right singular vector matrix on the precoded channels.).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Ry with Na by applying Na’s phase-ambiguity-elimination technique to the beamforming parameters determined using Ryu’s predictive model, to reduce phase ambiguity and discontinuity across tones while maintain the same capacity, which would improve channel estimate and UE throughput (Na, [0062]-[0063]).
Regarding claim 14, Ry-Na teaches a wireless communication system (Ry, see fig. 9):
one or more of:
comprising a plurality of radio nodes the radio node being configured to one or both (Ry, [0061]-[0068]: [0063] One or more of the base stations 105 described herein may include or may be referred to by a person having ordinary skill in the art as a base transceiver station, a radio base station, an access point, a radio transceiver, a NodeB, an eNodeB (eNB), a next-generation NodeB or a giga-NodeB (either of which may be referred to as a gNB), a Home NodeB, a Home eNodeB, or other suitable terminology.):
provide information for an input to a machine learning system (Ry, fig. 5, [0110]-[0114]: [0114] Optionally, at 540, the base station 105-d may identify a model selection function for switching among different predictive models. At 545, the base station 105-d may transmit the model selection function to the UE 115-e. While the operations of 540 and 545 are illustrated as occurring subsequent to uplink and downlink communications, in some cases such a model selection function may be provided along with the predictive models that are provided to the UE 115-e by the base station 105-d. At 550, the UE 115-e may select a new model based on the model selection function, which may then be used for subsequent communications. In some cases, the UE 115-e may provide one or more measurements as inputs to the model selection function, which may output an updated model for UE communications. For example, if the measurement indicates a UE 115-e position has changed, the model selection function may determine that a different model for delay spread is more suitable, and may output an indication that the UE 115-e is to switch the associated model. Such techniques may allow a UE 115-e to account for a changing channel environment (e.g., due to movement of the UE 115-e), by UE updating its models in order to appropriately match the current channel environment.); and
be controlled based on an action provided by the machine learning system (Ry, fig. 5, [0110]-[0114], [0144]-[0153]: [0144] FIG. 9 shows a diagram of a system 900 including a device 905 that supports machine learning model selection in beamformed communications in accordance with aspects of the present disclosure. The device 905 may be an example of or include the components of device 605, device 705, or a UE 115 as described herein. The device 905 may include components for bi-directional voice and data communications including components for transmitting and receiving communications, including a communications manager 910, an I/O controller 915, a transceiver 920, an antenna 925, memory 930, and a processor 940. These components may be in electronic communication via one or more buses (e.g., bus 945).); and
the machine learning system being configured to provide an output based on the input, the input representing a status of a wireless communication system comprising a plurality of radio nodes, the output representing an action for the wireless communication system, the machine learning system being configured for a phase ambiguity limitation for providing the output… (Ry, fig. 1 and fig. 5, [0059]-[0095], [0110]-[0114], [0144]-[0153]: [0089] Beamforming, which may also be referred to as spatial filtering, directional transmission, or directional reception, is a signal processing technique that may be used at a transmitting device or a receiving device (e.g., a base station 105, a UE 115) to shape or steer an antenna beam (e.g., a transmit beam, a receive beam) along a spatial path between the transmitting device and the receiving device. Beamforming may be achieved by combining the signals communicated via antenna elements of an antenna array such that some signals propagating at particular orientations with respect to an antenna array experience constructive interference while others experience destructive interference. The adjustment of signals communicated via the antenna elements may include a transmitting device or a receiving device applying amplitude offsets, phase offsets, or both to signals carried via the antenna elements associated with the device. The adjustments associated with each of the antenna elements may be defined by a beamforming weight set associated with a particular orientation (e.g., with respect to the antenna array of the transmitting device or receiving device, or with respect to some other orientation.);
configured to be controlled based on the output provided by the machine learning system and configured to provide information for the input for the machine learning (Ry, Fig. 1 and 9, [0053], [0059]-[0095],[0144]-[0153]: See above for paragraph [0089]).
Thus, Ry does not explicitly teach …the phase ambiguity limitation including a limit on a number of phase formats, a phase format being a solution in a solution space of the machine learning system.
Similar to the system of Ry, Na teaches that the choices of the precoding matrix V(k) are not unique because different phase representations may be used for the same precoding result (Na, [0061]), which can be seen as, …the phase ambiguity limitation including a limit on a number of phase formats, a phase format being a solution in a solution space of the machine learning system (Na, fig. 7, fig. 12, [0030]-[0054], [0055]-[0090]: The Examiner views the different phase representations as different phase formats representing equivalent precoding solutions. Na further teaches selecting a modified precoding matrix that maintains the same capacity while addressing the phase ambiguity (Na, [0063]). Na also teaches that the phase ambiguity may be eliminated and that the modified precoding matric removes the arbitraty phase (Na, [0064]-[0065]). Examiner views this as limiting the number of phase formats used to provide the precoding output. [0061] The choices of V.sub.k available to the precoding component 716, however, may not be unique. For example, U.sub.kΘ.sub.k and V.sub.kΘ.sub.K can also be the left singular vector matrix and right singular vector matrix of H.sub.k, where Θ.sub.k is an N.sub.r×N.sub.r diagonal matrix with the diagonal elements having unit amplitude. That is, |Θ.sub.k(i,i)| is 1, where i is from 1 to N.sub.r. [0063] In a second technique to determine a precoding matrix P.sub.k′, the precoding matrices P.sub.k′ are modified to address the ambiguity and discontinuity described supra. For any N.sub.r×N.sub.r unitary matrix Ξ.sub.k, the precoding component 716 may use V.sub.k Ξ.sub.K as a precoding matrix P.sub.k′ to achieve the same capacity as the precoding matrix P.sub.k (i.e., V.sub.k). Furthermore, the precoding component 716 may choose U.sub.k.sup.H as Ξ.sub.k. As such, the precoding component 716 determines:P′.sub.k=V.sub.kU.sub.k.sup.N. [0064] As such, the phase ambiguity in the left singular vector matrix and the right singular vector matrix may be eliminated. [0065] As shown, P.sub.k′ removes the arbitrary phase introduced by the left singular vector matrix and the right singular vector matrix on the precoded channels.).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Ry with Na by applying Na’s phase-ambiguity-elimination technique to the beamforming parameters determined using Ryu’s predictive model, to reduce phase ambiguity and discontinuity across tones while maintain the same capacity, which would improve channel estimate and UE throughput (Na, [0062]-[0063]).
Regarding claim 15, Ry-Na teaches a method of training a machine learning system (Ry, see fig. 9):
the machine learning system being configured to provide an output based on the input, the input representing a status of a wireless communication system comprising a plurality of radio nodes, the output representing an action for the wireless communication system, the machine learning system being configured for a phase ambiguity limitation for providing the output, the method comprising (Ry, Fig. 1, fig. 5, and fig. 9, [0053], [0059]-[0095], [0110]-[0114], [0144]-[0153]: See above for paragraph [0089]:
performing machine learning for the system…(Ry, fig. 4, [0104]-[0109]) .
Thus, Ry does not explicitly teach …the phase ambiguity limitation including a limit on a number of phase formats, a phase format being a solution in a solution space of the machine learning system.
Similar to the system of Ry, Na teaches that the choices of the precoding matrix V(k) are not unique because different phase representations may be used for the same precoding result (Na, [0061]), which can be seen as, …the phase ambiguity limitation including a limit on a number of phase formats, a phase format being a solution in a solution space of the machine learning system (Na, fig. 7, fig. 12, [0030]-[0054], [0055]-[0090]: The Examiner views the different phase representations as different phase formats representing equivalent precoding solutions. Na further teaches selecting a modified precoding matrix that maintains the same capacity while addressing the phase ambiguity (Na, [0063]). Na also teaches that the phase ambiguity may be eliminated and that the modified precoding matric removes the arbitraty phase (Na, [0064]-[0065]). Examiner views this as limiting the number of phase formats used to provide the precoding output. [0061] The choices of V.sub.k available to the precoding component 716, however, may not be unique. For example, U.sub.kΘ.sub.k and V.sub.kΘ.sub.K can also be the left singular vector matrix and right singular vector matrix of H.sub.k, where Θ.sub.k is an N.sub.r×N.sub.r diagonal matrix with the diagonal elements having unit amplitude. That is, |Θ.sub.k(i,i)| is 1, where i is from 1 to N.sub.r. [0063] In a second technique to determine a precoding matrix P.sub.k′, the precoding matrices P.sub.k′ are modified to address the ambiguity and discontinuity described supra. For any N.sub.r×N.sub.r unitary matrix Ξ.sub.k, the precoding component 716 may use V.sub.k Ξ.sub.K as a precoding matrix P.sub.k′ to achieve the same capacity as the precoding matrix P.sub.k (i.e., V.sub.k). Furthermore, the precoding component 716 may choose U.sub.k.sup.H as Ξ.sub.k. As such, the precoding component 716 determines:P′.sub.k=V.sub.kU.sub.k.sup.N. [0064] As such, the phase ambiguity in the left singular vector matrix and the right singular vector matrix may be eliminated. [0065] As shown, P.sub.k′ removes the arbitrary phase introduced by the left singular vector matrix and the right singular vector matrix on the precoded channels.).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Ry with Na by applying Na’s phase-ambiguity-elimination technique to the beamforming parameters determined using Ryu’s predictive model, to reduce phase ambiguity and discontinuity across tones while maintain the same capacity, which would improve channel estimate and UE throughput (Na, [0062]-[0063]).
Claim 12 is rejected under 35 U.S.C. 103 as being unpatentable over Ryu et al. (US 20210328630 A1) (hereinafter Ry) as applied to claim 1/2/13/14/15 above, and further in view of Oh (US 20240178862 A1) (hereinafter Oh)
Regarding claim 12, Oh teaches the machine learning system according to claim 1, (Ry, see fig. 9):
Wherein the machine learning system comprises is comprised on one or both of:
Thus, Ry does not teach one or more critic neural networks.
Similar to Ry, Oh teaches an artificial intelligence system employing one or more artificial neural networks used as learning cores, including deep neural networks, convolutional neural networks, and recurrent neural networks, which can be seen as, one or more critic neural networks (Oh, Fig. 23, [0233]-[0237]: [0234] As described above, an artificial intelligence system may be applied to a 6G system. Herein, as an example, the artificial intelligence system may operate based on a learning model corresponding to the human brain, as described above. Herein, a paradigm of machine learning, which uses a neural network architecture with high complexity like artificial neural network, may be referred to as deep learning. In addition, neural network cores, which are used as a learning scheme, are mainly a deep neural network (DNN), a convolutional deep neural network (CNN), and a recurrent neural network (RNN). Herein, as an example referring to FIG. 23, an artificial neural network may consist of a plurality of perceptrons. Herein, when an input vector x={x1, x2, . . . , xd} is input, each component is multiplied by a weight {W1, W2, . . . , Wd}, results are all added up, and then an activation function σ( ) is applied, of which the overall process may be referred to as a perceptron. For a large artificial neural network architecture, when expanding the simplified perceptron structure illustrated in FIG. 23, an input may be applied to different multidimensional perceptrons. For convenience of explanation, an input value or an output value will be referred to as a node.); and one or more agent neural networks.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Ry with Oh in order to employ known artificial neural network learning cores, such as deep neural networks, within the machine learning system of Ry, thereby enabling evaluative learning functions, including one or more critic neural networks.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, 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 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 Francesca Lima Santos whose telephone number is (571)272-6521. The examiner can normally be reached Monday thru Friday 7:30am-5pm, 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, Marcus R Smith can be reached at (571) 270-1096. 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.
/F.L.S./ Examiner, Art Unit 2468 /Thomas R Cairns/Primary Examiner, Art Unit 2468
Prosecution Insights