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 .
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1, 3, 6, 9-13 and 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Tang (WO2022257157), in view of HUTTUNEN (WO2023036437) in view of Oshea (US 20230342590).
With respect to independent claims:
Regarding claim(s) 1/13/15, Tang teaches A radio transmitter device ([Fig.15], TRP 452),
comprising: at least one processor; and
at least one memory storing instructions that, when executed by the at least one processor, cause the radio transmitter device at least to perform:
obtaining a most recent channel estimate formed based on a most recent reference signal transmission over an uplink, UL, radio channel ([Fig.15, step 1430 and 0239], “At 1434, TRP 452 obtains uplink channel state information based on the UL reference signal received from UE 402 at 1430 (e.g., at time slot n1)”);
obtaining a set of prior channel estimates comprising channel estimates formed based on at least one prior reference signal transmission over the UL radio channel ([Fig.15, step 1410 and 0237], “UE 402 and TRP 452 repeatedly send reference signals, obtain channel state information based on the corresponding reference signals,” so the TRP obtains multiple of channel estimates based on the repeatedly exchanged reference signals.) that is earlier than the most recent reference signal transmission ([Fig.15], step 1410 occurs before step 1430.);
generating ([0253], “the ML module at TRP 452 is trained at 1416 using the uplink channel state information as an input to the ML module and one or more MCS parameters as an output.”) an auxiliary data set representing one or more auxiliary channel characteristics of the radio channel ([0253], “one or more MCS parameters.”) via applying a first neural network, NN ([0253], ML module in the TRP.), to at least a part of the obtained set of prior channel estimates ([0253], “uplink channel state information.”).
However, Tang does not specifically disclose generating a set of downlink, DL, beamforming coefficients for the radio channel via applying a second NN to the generated auxiliary data set and the obtained most recent channel estimate,
wherein the first NN is configured to extract information related to the one or more auxiliary channel characteristics of the radio channel from the obtained set of prior channel estimates.
In an analogous art, HUTTUNEN discloses obtaining a set of prior channel estimates comprising channel estimates formed based on at least one prior reference signal transmission over the UL radio channel ([page 12-page 13 and Fig.4B], neural network “DeepRx 700” receives data and pilot signals from different UEs via uplink channel 410)...
generating ([Fig.4B], DeepRX 700 generates data representing channel estimates, the generated data can be stored in unit 253B.) an auxiliary data set representing one or more auxiliary channel characteristics of the radio channel ([Fig.4B], Data representing channel est.) via applying a first neural network, NN ([Fig.4b], DeepRX 700), to at least a part of the obtained set of prior channel estimates ([Fig.4B], “pilot signals from different UEs via uplink channel 410.”); and
generating a set of downlink, DL, beamforming ... for the radio channel via applying a second NN to the generated auxiliary data set and the obtained most recent channel estimate ([Fig.4B and page 12-page 13], “a neural network beamformer 500” determines beamforming parameters for the downlink signal based on received uplink pilots.),
wherein the first NN is configured to extract information related to the one or more auxiliary channel characteristics of the radio channel from the obtained set of prior channel estimates ([Fig.4B], neural network DeepRx determines data representing channel estimate based on the received uplink pilot sigals.).
Therefore, it would have been obvious to one with ordinary skill in the art at the time before the effective filing date of the claim invention to have modified the method of Tang to specify second neural network as taught by HUTTUNEN. The motivation/suggestion would have been because there is a need to determine beamforming for downlink signal.
However, the combination of Tang and HUTTUNEN does not specifically teach beamforming coefficients.
In an analogous art, Oshea teaches generating a set of downlink, DL, beamforming coefficients for the radio channel via applying a ... NN to the received channel estimates ([0098], “The L1 layer 204 implements one or more neural networks as a beamforming weight model 228 to determine, based on the determined scheduling, channel estimates 236, and/or other data, beamforming weights for transmission of downlink RF signal transmission by multiple antennas of the RU 202, e.g., to multiple user devices.”)
Therefore, it would have been obvious to one with ordinary skill in the art at the time before the effective filing date of the claim invention to have modified the method of Tang to specify beamforming weight as taught by Oshea. The motivation/suggestion would have been because there is a need to transmit downlink signal more efficiently.
With respect to dependent claims:
Regarding claim(s) 3, Tang teaches wherein the at least one prior reference signal transmission comprises a sounding reference signal, SRS, transmission ([0164], “uplink Sounding Reference Signal (SRS) , received by the TRP 452 from the UE 402.”).
Regarding claim(s) 6, Tang teaches wherein the applying of the first NN to the at least part of the obtained set of prior channel estimates to generate the auxiliary data set comprises applying the first NN to a subset of the obtained set of prior channel estimates ([0253], “the ML module at TRP 452 is trained at 1416 using the uplink channel state information as an input to the ML module and one or more MCS parameters as an output.”).
Regarding claim(s) 9, Tang teaches wherein the first NN comprises at least one of a convolutional neural network, CNN, a transformer network, or a recurrent neural network, RNN ([0155], “recurrent neural networks (RNN)”), or a combination thereof.
Regarding claim(s) 10, HUTTUNEN teaches wherein the second NN comprises at least one of a convolutional neural network ([page 3], “the NN comprises at least one of a convolutional neural network.”), a transformer neural network, or a combination thereof.
Therefore, it would have been obvious to one with ordinary skill in the art at the time before the effective filing date of the claim invention to have modified the method of Tang to specify second neural network as taught by HUTTUNEN. The motivation/suggestion would have been because there is a need to determine beamforming for downlink signal.
Regarding claim(s) 11, HUTTUNEN teaches wherein at least one of the first NN or the second NN utilizes one or more depthwise separable convolutions ([Page 3], “at least one of the at least one neural network layer utilizes depthwise separable convolution.”).
Therefore, it would have been obvious to one with ordinary skill in the art at the time before the effective filing date of the claim invention to have modified the method of Tang to specify depthwise separable convolutions as taught by HUTTUNEN. The motivation/suggestion would have been because there is a need to make communication more efficient by using neural network.
Regarding claim(s) 12, HUTTUNEN teaches the radio transmitter device to perform concurrent training of the first NN and the second NN via applying a cross-entropy loss ([Page 23], “Both the NN 700 and the NN 500 may be trained simultaneously. The loss may be, e.g., a combination of the cross-entropy loss of the NN 700 and the NN 500:”) measuring DL performance of one or more client devices transmitting the reference signals ([Page 20], “the loss function for the training may be specified using bit estimates of the UEs 130A, 130B, 130C in DL, using, e.g., the following crossentropy loss.”).
Therefore, it would have been obvious to one with ordinary skill in the art at the time before the effective filing date of the claim invention to have modified the method of Tang to specify cross entropy loss as taught by HUTTUNEN. The motivation/suggestion would have been because there is a need for AI training.
Claim(s) 2 is/are rejected under 35 U.S.C. 103 as being unpatentable over Tang in view of HUTTUNEN and Oshea, and further in view of Lorenz (US 20120129469).
Regarding claim(s) 2, Lorenz teaches wherein the channel estimates in the set of prior channel estimates comprise at least channel estimate averages over one or more subcarriers of the at least one prior reference signal transmission ([0069] “estimating the UL channel. This channel estimation commonly averages the pilots of a group of adjacent subcarriers.”).
Therefore, it would have been obvious to one with ordinary skill in the art at the time before the effective filing date of the claim invention to have modified the method of Tang to specify determining average of pilots as taught by Lorenz. The motivation/suggestion would have been because there is a need to reduce interference.
Claim(s) 7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Tang in view of HUTTUNEN and Oshea, and further in view of Ma (US 7042858).
Regarding claim(s) 7, Ma teaches wherein the auxiliary channel characteristics of the radio channel comprise velocity estimates of one or more client devices transmitting the reference signals ([col.9, lines 40-50], “uses a pilot signal for channel parameter estimation to keep track of channel characteristics caused by the movement of the mobile terminal.”).
Therefore, it would have been obvious to one with ordinary skill in the art at the time before the effective filing date of the claim invention to have modified the method of Tang to specify movement of a UE as taught by MA. The motivation/suggestion would have been because there is a need to keep track of channel characteristic.
Claim(s) 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Tang in view of HUTTUNEN and Oshea, and further in view of Chen (US 20250039881).
Regarding claim(s) 8, Chen teaches the radio transmitter device to perform applying the first NN to environmental information related to at least one of the radio channel ([0018], “the second channel environment information is used as an input of a second artificial intelligence AI model.”) or one or more client devices transmitting the reference signals, when generating the auxiliary data set ([0018], “an output of the second AI model is used to receive the first uplink signal..”).
Therefore, it would have been obvious to one with ordinary skill in the art at the time before the effective filing date of the claim invention to have modified the method of Tang to specify inputting environment information as taught by Chen. The motivation/suggestion would have been because there is a need to receive uplink data.
Allowable Subject Matter
Claim(s) 4-5 is/are 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.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ZHIREN QIN whose telephone number is (571)272-5444. The examiner can normally be reached on M-F 9-6 PM.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Derrick Ferris can be reached on 571-272-3123. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/ZHIREN QIN/Examiner, Art Unit 2411
Prosecution Insights