Response to Amendment
This office action in response to an amendment received on December 15, 2025.
Claims 1, 16, 18, 19, 23, and 28-30 have been amended.
Claims 1-30 are pending
Response to Arguments
The objection to the specification has been withdrawn for the reasons stated in applicant’s response (see Pg. 13).
The 35 U.S.C §112(b) rejection of claims 15-16 has been withdrawn in light of applicant’s amendments and remarks (see remarks Pg. 13).
The 35 U.S.C §103 rejection is hereby withdrawn in light of applicant’s amendments and arguments (see remarks Pg. 13-15). However, upon further consideration, a new ground(s) of rejection has been made.
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.
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 non-obviousness.
Claim(s) 1-11, 13-16, 18 and 28-30 are rejected under 35 U.S.C. 103 as being unpatentable over SUN et al., US 20150124638 A1, (hereinafter SUN), in view of O`Shea et al., US 20180367192 A1, (hereinafter O`Shea) and in further view of Wang et al., US 11792055 B2, (hereinafter Wang).
Regarding claim 1, and 29, SUN teaches a method of wireless communication performed by a first device, comprising: transmitting a capability indication that indicates a capability of the first device for facilitating providing CSF (see Fig. 2, e.g., element 201, ¶ [0049] e.g., Step 201: A base station receives indication information indicating a capability of a UE for measuring CSI and indication information indicating a capability of receiving data transmission that are reported by the UE); and
receiving, based at least in part on the capability of the first device, a CSF configuration that indicates at least one parameter associated with the at least one CSF (see Fig. 2, e.g., element 202, ¶ [0065] e.g., Step 202: The base station selects a CSI measurement set for the UE according to the indication information indicating the capability of the UE for measuring CSI, and notifies the CSI measurement set to the UE.),
however, it does not explicitly teach this indication over a neural network which is associated with training at least one channel state feedback (CSF) neural network and wherein the CSF neural network configuration further indicates a neural network based channel state information (CSI) reference signal (CSI-RS).
O`Shea teaches, a neural network associated with training at least one channel state feedback (CSF) neural network (¶ [0097]- [0098], e.g., the CSI estimator 370 may itself implement a machine-learning network, for example as shown in FIG. 3B, including one or more neural network layers. The CSI machine-learning network in the CSI estimator 370 may be trained to learn a representation of the received RF signals 364 into a CSI 368 that indicates the random state of the channel. For example, the CSI machine-learning network may be trained to generate the CSI as a representation of channel information).
Wang teaches, a neural network based channel state information (CSI) reference signal (CSI-RS) (see Fig. 2 element 200, S201, S202, Col. 7, lines 27-44, e.g., the terminal may input a downlink control channel to the neural network of the terminal. For example, in a case where the base station is configured with RSs and the RS configuration is available, the base station may transmit the RSs on the downlink control channel. Accordingly, the terminal may input the downlink control channel to the neural network of the terminal, so that the terminal performs channel estimation on the downlink control channel in a subsequent step S202. The downlink control channel herein may be, for example, a Physical Downlink Control CHannel (PDCCH), a Physical Broadcast CHannel (PBCH), or a Physical Control Format Indicator CHannel (PCFICH), and so on. The reference signals herein may be one or more of Channel State Information Reference Signal (CSI-RSs), Primary Synchronization Signals (PSSs)/Secondary Synchronization Signals (SSSs), DMRSs, or Synchronization Signal Blocks (SSBs), and so on.).
It would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to have modified transmitting of capability indication and CSF configuration of SUN to incorporate the teachings of O`Shea to include a neural network which is associated with training at least one channel state feedback (CSF) neural network and incorporate teachings of Wang to include a neural network based channel state information (CSI) reference signal (CSI-RS). Doing so would facilitate in achieving meeting system performance needs in terms of bit error rate, information density, signal linearity, and computational complexity as suggested by O`Shea (see ¶ [0098], e.g., The CSI embedding may be optimized for certain SNR levels, numbers of antennas, or multi-antenna propagation conditions. In some cases, a hyper-parameter optimization method or system may be used in order to select CSI machine-learning network in the CSI estimator 370 which best meet the engineering and performance needs of the resulting system in terms of bit error rate, information density, signal linearity, and computational complexity), and more intelligent and efficient communication between the base station and the terminal as suggested by Wang (see Col. 3, lines 49-55, e.g., and the method performed by the base station and the corresponding base station, the terminal may determine whether to use the neural network-based codebook with the indication from the base station, thereby making the communication between the base station and the terminal more intelligent and efficient.).
Regarding claim 2, SUN as combined with O`Shea and Wang teaches the limitations of Claim 1.
SUN further teaches, wherein the at least one parameter indicates a number of CSF to be configured (see ¶ [0052], e.g., Specifically, the capability of the UE for measuring CSI may be as follows: the number of carriers on which the UE supports CSI measurement, and/or, the number of carriers on which the UE supports concurrent CSI measurement),
however, it does not explicitly teach the number of carriers on which the UE supports concurrent CSI measurement; to run these using a corresponding one or more neural network layers.
O`Shea teaches, a number of neural networks (see ¶ [0093], e.g., the example of FIG. 3B shows that a encoder network in the transmitter 352 includes one or more neural network layers that transform the input information 358 into multiple RF signals 362 for transmission over the MIMO channel 356. The receiver 354 includes one or more neural network layers that transform multiple RF signals 364 received from the MIMO channel 356 into reconstructed information 360.).
It would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to have modified the number of carriers on which the UE supports concurrent CSI measurement of SUN to incorporate the teachings of O`Shea to run these using a corresponding one or more neural network layers. Doing so would facilitate in achieving meeting system performance needs in terms of bit error rate, information density, signal linearity, and computational complexity as suggested by O`Shea (see ¶ [0098], e.g., The CSI embedding may be optimized for certain SNR levels, numbers of antennas, or multi-antenna propagation conditions. In some cases, a hyper-parameter optimization method or system may be used in order to select CSI machine-learning network in the CSI estimator 370 which best meet the engineering and performance needs of the resulting system in terms of bit error rate, information density, signal linearity, and computational complexity).
Regarding claim 3, SUN as combined with O`Shea and Wang teaches the limitations of Claim 1.
SUN does not teach but O`Shea teaches, wherein the at least one CSF neural network comprises a plurality of CSF neural networks (¶ [0093], e.g., Analogous to the example that was discussed with reference to FIG. 3A, above, the example of FIG. 3B shows that a encoder network in the transmitter 352 includes one or more neural network layers that transform the input information 358 into multiple RF signals 362 for transmission over the MIMO channel 356. The receiver 354 includes one or more neural network layers that transform multiple RF signals 364 received from the MIMO channel 356 into reconstructed information 360).
It would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to have modified the number of carriers on which the UE supports concurrent CSI measurement of SUN to incorporate the teachings of O`Shea to run these using a corresponding one or more neural network layers. Doing so would facilitate in achieving meeting system performance needs in terms of bit error rate, information density, signal linearity, and computational complexity as suggested by O`Shea (see ¶ [0098], e.g., The CSI embedding may be optimized for certain SNR levels, numbers of antennas, or multi-antenna propagation conditions. In some cases, a hyper-parameter optimization method or system may be used in order to select CSI machine-learning network in the CSI estimator 370 which best meet the engineering and performance needs of the resulting system in terms of bit error rate, information density, signal linearity, and computational complexity).
Regarding claim 4, SUN as combined with O`Shea and Wang teaches the limitations of Claim 1.
SUN further teaches, wherein the at least one parameter indicates at least one of:
a plurality of bandwidths corresponding to a plurality of CSF,
a plurality of bandwidth parts corresponding to the plurality of CSF,
a plurality of resources corresponding to the plurality of CSF,
a plurality of frequency ranges corresponding to the plurality of CSF,
a plurality of component carriers corresponding to the plurality of CSF,
a plurality of radio access network (RAN) modes corresponding to the plurality of CSF, or
a combination thereof (see ¶ [0052], e.g., the number of carriers on which the UE supports CSI measurement, and/or, the number of carriers on which the UE supports concurrent CSI measurement),
however, it does not explicitly teach a plurality of neural networks (¶ [0093], e.g., the example of FIG. 3B shows that a encoder network in the transmitter 352 includes one or more neural network layers that transform the input information 358 into multiple RF signals 362 for transmission over the MIMO channel 356. The receiver 354 includes one or more neural network layers that transform multiple RF signals 364 received from the MIMO channel 356 into reconstructed information 360.).
It would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to have modified the number of carriers on which the UE supports concurrent CSI measurement of SUN to incorporate the teachings of O`Shea to run these using a corresponding one or more neural network layers. Doing so would facilitate in achieving meeting system performance needs in terms of bit error rate, information density, signal linearity, and computational complexity as suggested by O`Shea (see ¶ [0098], e.g., The CSI embedding may be optimized for certain SNR levels, numbers of antennas, or multi-antenna propagation conditions. In some cases, a hyper-parameter optimization method or system may be used in order to select CSI machine-learning network in the CSI estimator 370 which best meet the engineering and performance needs of the resulting system in terms of bit error rate, information density, signal linearity, and computational complexity).
Regarding claim 5, SUN as combined with O`Shea and Wang teaches the limitations of Claim 4.
SUN further teaches, wherein the at least one parameter indicates:
a first CSF neural network of the plurality of CSF neural networks corresponding to a first bandwidth of the plurality of bandwidths; and
a second CSF neural network of the plurality of CSF neural networks corresponding to a second bandwidth of the plurality of bandwidths (see ¶ [0052], e.g., the number of carriers on which the UE supports concurrent CSI measurement; ¶ [0080] - [0081], e.g., A first frequency band combination parameter used for CSI measurement includes two frequency band parameters that correspond to two frequency bands respectively, where a first frequency band parameter corresponds to frequency band 1, and the type of CSI downlink bandwidth corresponding to the first frequency band parameter is b, that is, the maximum number of CCs on which the UE supports CSI measurement at the frequency band is 2 and the aggregate bandwidth is less than 100 RB. A second frequency band parameter corresponds to frequency band 2, and the type of CSI downlink bandwidth corresponding to the second frequency band parameter is c, that is, the maximum number of CCs on which the UE supports CSI measurement at the frequency band is 2 and the aggregate bandwidth is greater than 100 RB and less than 200 RB. Therefore, the UE can perform CSI measurement concurrently on a maximum of four CCs).
Regarding claim 6, SUN as combined with O`Shea and Wang teaches the limitations of Claim 4.
SUN further teaches, wherein the at least one parameter indicates:
a first CSF neural network of the plurality of CSF neural networks corresponding to a first bandwidth part of the plurality of bandwidth parts; and
a second CSF neural network of the plurality of CSF neural networks corresponding to a second bandwidth part of the plurality of bandwidth parts (see ¶ [0052], e.g., the number of carriers on which the UE supports concurrent CSI measurement; ¶ [0080] - [0081], e.g., A first frequency band combination parameter used for CSI measurement includes two frequency band parameters that correspond to two frequency bands respectively, where a first frequency band parameter corresponds to frequency band 1, and the type of CSI downlink bandwidth corresponding to the first frequency band parameter is b, that is, the maximum number of CCs on which the UE supports CSI measurement at the frequency band is 2 and the aggregate bandwidth is less than 100 RB. A second frequency band parameter corresponds to frequency band 2, and the type of CSI downlink bandwidth corresponding to the second frequency band parameter is c, that is, the maximum number of CCs on which the UE supports CSI measurement at the frequency band is 2 and the aggregate bandwidth is greater than 100 RB and less than 200 RB. Therefore, the UE can perform CSI measurement concurrently on a maximum of four CCs).
Regarding claim 7, SUN as combined with O`Shea and Wang teaches the limitations of Claim 4.
SUN further teaches, wherein the at least one parameter indicates:
a first CSF neural network of the plurality of CSF neural networks corresponding to a first resource of the plurality of resources; and a
second CSF neural network of the plurality of CSF neural networks corresponding to a second resource of the plurality of resources (see ¶ [0052], e.g., the number of carriers on which the UE supports concurrent CSI measurement; ¶ [0080] - [0081], e.g., A first frequency band combination parameter used for CSI measurement includes two frequency band parameters that correspond to two frequency bands respectively, where a first frequency band parameter corresponds to frequency band 1, and the type of CSI downlink bandwidth corresponding to the first frequency band parameter is b, that is, the maximum number of CCs on which the UE supports CSI measurement at the frequency band is 2 and the aggregate bandwidth is less than 100 RB. A second frequency band parameter corresponds to frequency band 2, and the type of CSI downlink bandwidth corresponding to the second frequency band parameter is c, that is, the maximum number of CCs on which the UE supports CSI measurement at the frequency band is 2 and the aggregate bandwidth is greater than 100 RB and less than 200 RB. Therefore, the UE can perform CSI measurement concurrently on a maximum of four CCs).
Regarding claim 8, SUN as combined with O`Shea and Wang teaches the limitations of Claim 4.
SUN further teaches, wherein the at least one parameter indicates:
a first CSF neural network of the plurality of CSF neural networks corresponding to a first frequency range of the plurality of frequency ranges; and
a second CSF neural network of the plurality of CSF neural networks corresponding to a second frequency range of the plurality of frequency ranges (see ¶ [0052], e.g., the number of carriers on which the UE supports concurrent CSI measurement; ¶ [0080] - [0081], e.g., A first frequency band combination parameter used for CSI measurement includes two frequency band parameters that correspond to two frequency bands respectively, where a first frequency band parameter corresponds to frequency band 1, and the type of CSI downlink bandwidth corresponding to the first frequency band parameter is b, that is, the maximum number of CCs on which the UE supports CSI measurement at the frequency band is 2 and the aggregate bandwidth is less than 100 RB. A second frequency band parameter corresponds to frequency band 2, and the type of CSI downlink bandwidth corresponding to the second frequency band parameter is c, that is, the maximum number of CCs on which the UE supports CSI measurement at the frequency band is 2 and the aggregate bandwidth is greater than 100 RB and less than 200 RB. Therefore, the UE can perform CSI measurement concurrently on a maximum of four CCs (Note that, implicitly implied from frequency band is a defined frequency range)).
Regarding claim 9, SUN as combined with O`Shea and Wang teaches the limitations of Claim 8.
SUN does not teach but O`Shea teaches, wherein the first frequency range comprises a sub-6 gigahertz frequency range (see ¶ [0064], e.g., The spectrum of RF signals that are processed by system 100 may be in a range of 1 kHz to 300 GHz. For example, such RF signals include very low frequency (VLF) RF signals between 1 kHz to 30 kHz, low frequency (LF) RF signals between 30 kHz to 300 kHz, medium frequency (MF) RF signals between 300 kHz to 1 MHz, high frequency (HF) RF signals between 1 MHz to 30 MHz, and higher-frequency RF signals up to 300 GHz. (Note that, implicitly implied from “The Sub-6 Gigahertz (GHz) range in wireless communication includes frequencies below 6 GHz, specifically between 410 MHz and 7.125 GHz, offering a balance of good coverage and faster speeds than 4G, and enabling wide-scale 5G deployment. This band, also known as FR1”)).
It would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to have modified first frequency range of SUN to incorporate the teachings of O`Shea to include sub-6 gigahertz frequency range. Doing so would facilitate in achieving transmitted and received by system any suitable radio-frequency signal, such as acoustic signals, optical signals, or other analog waveforms as suggested by O`Shea (see ¶ [0064], e.g., RF signals that are transmitted and received by system 100 may include any suitable radio-frequency signal, such as acoustic signals, optical signals, or other analog waveforms).
Regarding claim 10, SUN as combined with O`Shea and Wang teaches the limitations of Claim 9.
SUN does not teach but O`Shea teaches, wherein the second frequency range comprises a millimeter wave frequency range (see ¶ [0064], e.g., The spectrum of RF signals that are processed by system 100 may be in a range of 1 kHz to 300 GHz. For example, such RF signals include very low frequency (VLF) RF signals between 1 kHz to 30 kHz, low frequency (LF) RF signals between 30 kHz to 300 kHz, medium frequency (MF) RF signals between 300 kHz to 1 MHz, high frequency (HF) RF signals between 1 MHz to 30 MHz, and higher-frequency RF signals up to 300 GHz. (Note that, implicitly implied from “Millimeter wave (mmWave) in wireless communication uses frequencies from 24 GHz to 100 GHz or 30 GHz to 300 GHz. This high-frequency range is important for 5G technology”).
It would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to have modified second frequency range of SUN to incorporate the teachings of O`Shea to include millimeter wave frequency range. Doing so would facilitate in achieving transmitted and received by system any suitable radio-frequency signal, such as acoustic signals, optical signals, or other analog waveforms as suggested by O`Shea (see ¶ [0064], e.g., RF signals that are transmitted and received by system 100 may include any suitable radio-frequency signal, such as acoustic signals, optical signals, or other analog waveforms).
Regarding claim 11, SUN as combined with O`Shea and Wang teaches the limitations of Claim 4.
SUN further teaches, wherein the at least one parameter indicates:
a first CSF neural network of the plurality of CSF neural networks corresponding to a first component carrier of the plurality of component carriers; and
a second CSF neural network of the plurality of CSF neural networks corresponding to a second component carrier of the plurality of component carriers (see ¶ [0052], e.g., the number of carriers on which the UE supports CSI measurement, and/or, the number of carriers on which the UE supports concurrent CSI measurement).
Regarding claim 13, SUN as combined with O`Shea and Wang teaches the limitations of Claim 1.
SUN further teaches, wherein the capability of the first device is based at least in part on an amount of available memory of the first device (see ¶ [0173], e.g., all or a part of the steps of the foregoing method embodiments may be implemented by a program instructing relevant hardware. The foregoing programs may be stored in a computer readable storage medium. When the program runs, the foregoing steps of the method embodiments are performed. The foregoing storage medium includes various mediums capable of storing program code, such as a ROM, a RAM, a magnetic disk, or an optical disc.).
Regarding claim 14, SUN as combined with O`Shea and Wang teaches the limitations of Claim 13.
SUN further teaches, wherein the amount of available memory corresponds to at least one bandwidth (see ¶ [0173], e.g., Persons of ordinary skill in the art may understand that, all or a part of the steps of the foregoing method embodiments may be implemented by a program instructing relevant hardware. The foregoing programs may be stored in a computer readable storage medium. When the program runs, the foregoing steps of the method embodiments are performed. The foregoing storage medium includes various mediums capable of storing program code, such as a ROM, a RAM, a magnetic disk, or an optical disc.).
Regarding claim 15, SUN as combined with O`Shea and Wang teaches the limitations of Claim 1.
SUN further teaches, wherein the neural network capability indication indicates at least one neural network complexity parameter corresponding to a neural network complexity that can be supported by the first device ([0052] Specifically, the capability of the UE for measuring CSI may be as follows: the number of carriers on which the UE supports CSI measurement, and/or, the number of carriers on which the UE supports concurrent CSI measurement (Note that, complexity is implicitly implied from concurrent CSI measurement)).
Regarding claim 16, SUN as combined with O`Shea and Wang teaches the limitations of Claim 15.
SUN does not teach but O`Shea teaches, wherein the at least one neural network complexity parameter indicates at least one of:
a number of layers associated with the at least one CSF neural network,
a number of layers corresponding to a bandwidth part associated with the at least one CSF neural network,
a layer characteristic associated with the at least one CSF neural network,
a non-linear activation function associated with the at least one CSF neural network,
a time dependency capturing type associated with the at least one CSF neural network,
a number of stackable layers of time dependencies associated with the at least one CSF neural network,
a maximum layer size associated with the at least one CSF neural network,
a maximum size of a hidden state in [[a]] the time dependency layer associated with the at least one CSF neural network,
a maximum size of a cell state in a time dependency layer associated with the at least one CSF neural network,
a number of delay taps to be used for channel compression,
a tap energy pruning criterion,
or a combination thereof (see ¶ [0093], e.g., the example of FIG. 3B shows that a encoder network in the transmitter 352 includes one or more neural network layers that transform the input information 358 into multiple RF signals 362 for transmission over the MIMO channel 356. The receiver 354 includes one or more neural network layers that transform multiple RF signals 364 received from the MIMO channel 356 into reconstructed information 360. ¶ [0116], e.g., the machine-learning networks may include selecting a machine-learning model for the encoder network 402 from among a plurality of encoding models, selecting a machine-learning model for the decoder network 404, and/or selecting a machine-learning model for the CSI estimator 420 from among a plurality of CSI estimation models. In such implementations, selecting machine-learning models may include selecting a specific network architecture, such as choice of layers, layer-hyperparameters, or other network features).
It would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to have modified the complexity parameter of SUN to incorporate the teachings of O`Shea to include one or more neural network layers. Doing so would facilitate in achieving meeting system performance needs in terms of bit error rate, information density, signal linearity, and computational complexity as suggested by O`Shea (see ¶ [0098], e.g., The CSI embedding may be optimized for certain SNR levels, numbers of antennas, or multi-antenna propagation conditions. In some cases, a hyper-parameter optimization method or system may be used in order to select CSI machine-learning network in the CSI estimator 370 which best meet the engineering and performance needs of the resulting system in terms of bit error rate, information density, signal linearity, and computational complexity).
Regarding claim 18, SUN as combined with O`Shea and Wang teaches the limitations of Claim 1.
SUN as combined with O`Shea does not teach but Wang teaches, further comprising: receiving an indication to determine the CSF (see Col. 10, lines 62-67, e.g., (43) According to another example of the present disclosure, the terminal may determine whether to transmit the feedback information to the base station with the base station. For example, the terminal may determine whether to transmit the feedback information to the base station according to indication information from the base station.),
based at least in part on the neural network based CSI-RS (see Fig. 2 element 200, S201, S202, Col. 7, lines 59-67, e.g., Then, in step S202, the neural network of the terminal processes the input and outputs feedback information. For example, the neural network of the terminal may perform channel estimation on the downlink channel to obtain channel information, and output the channel information as the feedback information from the terminal to the base station. In addition, the “feedback information” herein may also be referred to as feedback information based on the neural network, or channel information encoded by the neural network, or feedback information encoded by the neural network; see Col. 14, lines 4-17, e.g., For another example, the terminal may measure the DMRSs in the downlink data channel to perform the channel estimation to obtain the feedback information. The above feedback information may be, for example, one or more of Channel State Information (CSI), a Reference Signal Receiving Power (RSRP), a Reference Signal Receiving Quality (RSRQ), a Signal to Interference plus Noise Ratio (SINR), or a Synchronous Signal Block Index (SSB-index), and so on. In addition, the CSI may include one or more of a Channel Quality Indicator (CQI), a Precoding Matrix Indicator (PMI), a Rank Indication (RI), or a CSI-RS Indicator (CRI), and so on.),
using a neural signal processor (see Col. 5, lines 3-11, e.g., The terminal 120 may be configured with an artificial intelligence-enabled signal processor 120-1 (for example, a signal encoder), so as to process the signals transmitted to the base station 110 with the artificial intelligence. Accordingly, the base station 110 may be configured with an artificial intelligence-enabled signal processor 110-1 (for example, a signal decoder) corresponding to the terminal 120, so as to process the signals received from the terminal 120 with the artificial intelligence.).
It would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to have modified CSF of SUN as improved by O`Shea to incorporate the teachings of Wang to include determining CSF based at least in part on the neural network based CSI-RS. Doing so would facilitate in achieving more intelligent and efficient communication between the base station and the terminal as suggested by Wang (see Col. 3, lines 49-55, e.g., and the method performed by the base station and the corresponding base station, the terminal may determine whether to use the neural network-based codebook with the indication from the base station, thereby making the communication between the base station and the terminal more intelligent and efficient.).
Regarding claim 28, and 30, SUN teaches a method of wireless communication performed by a second device, comprising: receiving a capability indication that indicates a capability of the first device for facilitating providing CSF (see Fig. 2, e.g., element 201, ¶ [0049] e.g., Step 201: A base station receives indication information indicating a capability of a UE for measuring CSI and indication information indicating a capability of receiving data transmission that are reported by the UE); and
transmitting, based at least in part on the capability of the first device, a CSF configuration that indicates at least one parameter associated with the at least one CSF (see Fig. 2, e.g., element 202, ¶ [0065] e.g., Step 202: The base station selects a CSI measurement set for the UE according to the indication information indicating the capability of the UE for measuring CSI, and notifies the CSI measurement set to the UE.),
however, it does not explicitly teach this indication over a neural network which is associated with training at least one channel state feedback (CSF) neural network and wherein the CSF neural network configuration further indicates a neural network based channel state information (CSI) reference signal (CSI-RS).
O`Shea teaches, a neural network associated with training at least one channel state feedback (CSF) neural network (¶ [0097]- [0098], e.g., the CSI estimator 370 may itself implement a machine-learning network, for example as shown in FIG. 3B, including one or more neural network layers. The CSI machine-learning network in the CSI estimator 370 may be trained to learn a representation of the received RF signals 364 into a CSI 368 that indicates the random state of the channel. For example, the CSI machine-learning network may be trained to generate the CSI as a representation of channel information).
Wang teaches, a neural network based channel state information (CSI) reference signal (CSI-RS) (see Fig. 2 element 200, S201, S202, Col. 7, lines 27-44, e.g., the terminal may input a downlink control channel to the neural network of the terminal. For example, in a case where the base station is configured with RSs and the RS configuration is available, the base station may transmit the RSs on the downlink control channel. Accordingly, the terminal may input the downlink control channel to the neural network of the terminal, so that the terminal performs channel estimation on the downlink control channel in a subsequent step S202. The downlink control channel herein may be, for example, a Physical Downlink Control CHannel (PDCCH), a Physical Broadcast CHannel (PBCH), or a Physical Control Format Indicator CHannel (PCFICH), and so on. The reference signals herein may be one or more of Channel State Information Reference Signal (CSI-RSs), Primary Synchronization Signals (PSSs)/Secondary Synchronization Signals (SSSs), DMRSs, or Synchronization Signal Blocks (SSBs), and so on.).
It would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to have modified transmitting of capability indication and CSF configuration of SUN to incorporate the teachings of O`Shea to include a neural network which is associated with training at least one channel state feedback (CSF) neural network and incorporate teachings of Wang to include a neural network based channel state information (CSI) reference signal (CSI-RS). Doing so would facilitate in achieving meeting system performance needs in terms of bit error rate, information density, signal linearity, and computational complexity as suggested by O`Shea (see ¶ [0098], e.g., The CSI embedding may be optimized for certain SNR levels, numbers of antennas, or multi-antenna propagation conditions. In some cases, a hyper-parameter optimization method or system may be used in order to select CSI machine-learning network in the CSI estimator 370 which best meet the engineering and performance needs of the resulting system in terms of bit error rate, information density, signal linearity, and computational complexity), and more intelligent and efficient communication between the base station and the terminal as suggested by Wang (see Col. 3, lines 49-55, e.g., and the method performed by the base station and the corresponding base station, the terminal may determine whether to use the neural network-based codebook with the indication from the base station, thereby making the communication between the base station and the terminal more intelligent and efficient.).
Claim(s) 12, 17, are rejected under 35 U.S.C. 103 as being unpatentable over SUN, in view of O`Shea, Wang and in further view of Wang et al., US 11397893 B2, (hereinafter Wang 7893).
Regarding claim 12, SUN as combined with O`Shea and Wang teaches the limitations of Claim 4.
SUN and O`Shea does not teach but Wang teaches, wherein the at least one parameter indicates:
a first CSF neural network of the plurality of CSF neural networks corresponding to a first RAN mode of the plurality of RAN modes; and
a second CSF neural network of the plurality of CSF neural networks corresponding to a second RAN mode of the plurality of RAN modes (see Col. 6, lines 49-67, e.g., The base stations 120 are collectively a Radio Access Network 140 (e.g., RAN, Evolved Universal Terrestrial Radio Access Network, E-UTRAN, 5G NR RAN or NR RAN). The base stations 121 and 122 in the RAN 140 are connected to a core network 150. see Col. 21, lines 24-42, e.g., the base station 121 communicates multiple neural network formation configurations to the UE 110. For example, the base station transmits a first message that directs the UE to use a first neural network formation configuration for uplink encoding, and a second message that directs the UE to use a second neural network formation configuration for downlink decoding. In some scenarios, the base station 121 communicates multiple neural network formation configurations, and the respective processing assignments, in a single message. As yet another example, the base station communicates the multiple neural network formation configurations using different radio access technologies (RATs). The base station can, for instance, transmit a first neural network formation configuration for downlink communication processing to the UE 110 using a first RAT and/or carrier, and transmit a second neural network formation configuration for uplink communication processing to the UE 110 using a second RAT and/or carrier).
It would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to have modified the CSF neural network of the plurality of CSF neural networks of SUN combined with O`Shea to incorporate the teachings of Wang 7893 to include neural network corresponding to a RAN mode of the plurality of RAN modes. Doing so would facilitate in achieving multiple neural network formation configurations on the UE, some for uplink encoding and some for downlink encoding as suggested by Wang 7893 (see Col. 21, lines 24-42, e.g., the base station 121 communicates multiple neural network formation configurations to the UE 110. For example, the base station transmits a first message that directs the UE to use a first neural network formation configuration for uplink encoding, and a second message that directs the UE to use a second neural network formation configuration for downlink decoding. In some scenarios, the base station 121 communicates multiple neural network formation configurations, and the respective processing assignments, in a single message.).
Regarding claim 17, SUN as combined with O`Shea and Wang teaches the limitations of Claim 1.
SUN and O`Shea does not teach but Wang teaches, wherein the neural network capability indication indicates a number of neural signal processors available on the first device (see Col. 25, lines 38-55, e.g., the neural network formation configuration based upon the updated information (e.g., UE capabilities particular to the UE 110), such as by removing layers and/or nodes to reduce a corresponding complexity of the deep neural network at the UE 110 based available processing capabilities, batter power, available radios, etc. at the UE).
It would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to have modified the CSF neural network of the plurality of CSF neural networks of SUN combined with O`Shea to incorporate the teachings of Wang 7893 to include neural network corresponding to a RAN mode of the plurality of RAN modes. Doing so would facilitate in achieving multiple neural network formation configurations on the UE, some for uplink encoding and some for downlink encoding as suggested by Wang 7893 (see Col. 21, lines 24-42, e.g., the base station 121 communicates multiple neural network formation configurations to the UE 110. For example, the base station transmits a first message that directs the UE to use a first neural network formation configuration for uplink encoding, and a second message that directs the UE to use a second neural network formation configuration for downlink decoding. In some scenarios, the base station 121 communicates multiple neural network formation configurations, and the respective processing assignments, in a single message.).
Claim(s) 24-27, are rejected under 35 U.S.C. 103 as being unpatentable over SUN, in view of O`Shea, Wang and in further view of WANG et al., WO 2021086308 A1, (hereinafter WANG).
Regarding claim 24, SUN as combined with O`Shea and Wang teaches the limitations of Claim 1.
SUN, O`Shea and Wang does not teach but WANG teaches, further comprising receiving a capability request, wherein transmitting the neural network capability indication comprises transmitting the neural network capability indication based at least in part on receiving the capability request (see Fig. 22, e.g., element 2200, 2210 – Request ML capabilities, 2220, ¶ [0211], e.g., At 2210, the base station 120 transmits a request for ML capabilities to the UE 110, where the request explicitly or implicitly requests ML capabilities. As one example, the base station 120 relays the ML capabilities request from the core network server 302. As another example, the base station 120 generates and transmits an ML capabilities request message to the UE 110 in response to receiving the ML capabilities request from the core network server 302. ¶ [0212], e.g., at 2220, the UE 110 transmits user equipment machine-learning capabilities (UE ML capabilities) to the base station, where the base station 120 relays the UE ML capabilities to the core network server at 2225. At times, the core network server forwards the BS ML capabilities and/or the UE ML capabilities to the E2E ML controller 318.).
It would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to have modified the capabilities indication of SUN combined with O`Shea and Wang to incorporate the teachings of WANG to include the request where it explicitly or implicitly requests ML capabilities. Doing so would facilitate in achieving multiple end-to-end machine-learning configurations targeted for each UE, as suggested by WANG (see ¶ [0010], e.g., the network entity requests the capabilities, such as by requesting UE capabilities, machine- learning capabilities (ML capabilities), base station (BS) capabilities, and so forth, from one or more devices participating in the E2E communications. In response to obtaining the capabilities, the network entity determines an end-to-end machine-learning configuration (E2E ML configuration) based on the received capabilities. After determining the E2E ML configuration, the network entity communicates the E2E ML configuration to the devices, such as by communicating a first neural network (NN) format configuration to a first device, a second NN format configuration to a second device, etc.).
Regarding claim 25, SUN as combined with O`Shea, Wang and WANG teaches the limitations of Claim 24.
SUN, O`Shea and Wang does not teach but WANG teaches, wherein the capability request is carried in at least one of:
a radio resource control (RRC) message,
an RRC channel state information message,
a medium access control (MAC) control element (MAC-CE), downlink control information,
or a combination thereof (see ¶ [0136], e.g., the base station 121 transmits the neural network table to the UE 110. As one example, the base station transmits the neural network table using layer 3 messaging (e.g., Radio Resource Control (RRC) messages). In transmitting the neural network table, the base station transmits any combination of architecture and/or parameter configurations that can be used to form a deep neural network).
It would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to have modified the capabilities indication of SUN combined with O`Shea and Wang to incorporate the teachings of WANG to include the request where it explicitly or implicitly requests ML capabilities using layer 3 messaging. Doing so would facilitate in achieving multiple end-to-end machine-learning configurations targeted for each UE, as suggested by WANG (see ¶ [0010], e.g., the network entity requests the capabilities, such as by requesting UE capabilities, machine- learning capabilities (ML capabilities), base station (BS) capabilities, and so forth, from one or more devices participating in the E2E communications. In response to obtaining the capabilities, the network entity determines an end-to-end machine-learning configuration (E2E ML configuration) based on the received capabilities. After determining the E2E ML configuration, the network entity communicates the E2E ML configuration to the devices, such as by communicating a first neural network (NN) format configuration to a first device, a second NN format configuration to a second device, etc.).
Regarding claim 26, SUN as combined with O`Shea teaches the limitations of Claim 1.
SUN, O`Shea and Wang does not teach but WANG teaches, wherein the capability request is carried in a group message addressed to at least one additional first device (see ¶ [0135], e.g., the base station 121 maintains multiple neural network tables, where each neural network table includes multiple neural network formation configurations and/or neural network formation configuration elements for a designated purpose. ¶ [0136], e.g., In some implementations, the base station 121 broadcasts the neural network table(s) to a group of UEs. Other times, the base station 121 transmits a UE- dedicated neural network table to the UE 110.).
It would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to have modified the capabilities indication of SUN combined with O`Shea and Wang to incorporate the teachings of WANG to include transmitting the request to multiple device, where it explicitly or implicitly requests ML capabilities. Doing so would facilitate in achieving multiple end-to-end machine-learning configurations targeted for each UE, as suggested by WANG (see ¶ [0010], e.g., the network entity requests the capabilities, such as by requesting UE capabilities, machine- learning capabilities (ML capabilities), base station (BS) capabilities, and so forth, from one or more devices participating in the E2E communications. In response to obtaining the capabilities, the network entity determines an end-to-end machine-learning configuration (E2E ML configuration) based on the received capabilities. After determining the E2E ML configuration, the network entity communicates the E2E ML configuration to the devices, such as by communicating a first neural network (NN) format configuration to a first device, a second NN format configuration to a second device, etc.).
Regarding claim 27, SUN as combined with O`Shea teaches the limitations of Claim 1.
SUN, O`Shea and Wang does not teach but WANG teaches, wherein the CSF neural network configuration is carried in a group message addressed to at least one additional first device, and wherein the at least one parameter indicates at least one of:
a number of delay taps to be used for channel compression,
a tap energy pruning criterion,
or a combination thereof (¶ [0136], e.g., the base station 121 broadcasts the neural network table(s) to a group of UEs. Other times, the base station 121 transmits a UE- dedicated neural network table to the UE 110. ¶ [0256], e.g., obtaining at least one quality-of-service parameter or quality-of-service characteristic associated with the end-to-end communication; and determining the end-to-end machine- learning configuration based, at least in part, on the at least one quality-of-service parameter or quality-of-service characteristic. ¶ [0257], e.g., example 5, wherein the at least one quality-of-service parameter or quality-of-service characteristic comprises at least one of: a priority level; a packet delay budget; a packet error rate; a maximum data burst volume; or an averaging window. (Note that, implicitly implied from “the size of an averaging window is fundamentally associated with the number of delay taps used for channel compression in wireless communication”).
It would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to have modified the transmitting of network configuration by second device of SUN combined with O`Shea and Wang to incorporate the teachings of WANG to include transmitting the network configuration to multiple first device. Doing so would facilitate in achieving multiple end-to-end machine-learning configurations targeted for each UE, as suggested by WANG (see ¶ [0010], e.g., the network entity requests the capabilities, such as by requesting UE capabilities, machine-learning capabilities (ML capabilities), base station (BS) capabilities, and so forth, from one or more devices participating in the E2E communications. In response to obtaining the capabilities, the network entity determines an end-to-end machine-learning configuration (E2E ML configuration) based on the received capabilities. After determining the E2E ML configuration, the network entity communicates the E2E ML configuration to the devices, such as by communicating a first neural network (NN) format configuration to a first device, a second NN format configuration to a second device, etc.).
Allowable Subject Matter
Claim 19, objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Claims 20-23 would be allowable because they are dependent on claim 19.
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 POONAM SHARMA whose telephone number is (571)272-6579. The examiner can normally be reached Monday thru 8:30-5:30 pm, 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, Kevin Bates can be reached at (571) 272-3980. 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.
/POONAM SHARMA/Examiner, Art Unit 2472
/KEVIN T BATES/Supervisory Patent Examiner, Art Unit 2472