Notice of Pre-AIA or AIA Status
1. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
DETAILED ACTION
2. This Office Action is sent in response to Applicant’s Communication received on 06/12/2026 for application number 18/345,904.
Response to Amendments
3. The Amendment filed 06/12/2026 has been entered. Claims 1 and 31 have been amended. Claims 8-20, 27-30, and 32-42 have been canceled. Claims 43-49 have been added. Claims 1-7, 31, and 43-49 remain pending in the application.
Response to Arguments
Applicant argues that the cited references fail to disclose or suggest the features of amended independent claims 1 and 31. However, the argument is moot since this is a newly presented limitation, thus changes the scope of the claim. However, a newly found reference, Ye, is applied.
Claim Rejections – 35 USC § 103
4. 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 of this title, 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.
5. Claims 1, 2, 4-6, 31, and 43-49 are rejected under 35 U.S.C. 103 as being unpatentable over Lee et al. (U.S. Patent Application Pub. No. US 20210110261 A1) in view of Ye et al. (Channel Agnostic End-to-End Learning based Communication Systems with Conditional GAN, arXiv, published 2018, pages 1-5).
Claim 1: Lee teaches a neural network training method (i.e. The disclosure provides a method of efficiently learning and updating a weight of an autoencoder neural network (NN) when an autoencoder, which is a type of deep neural network (DNN), is utilized in signal transmission or reception between a UE and a BS. The training method in the disclosure is referred to as “shadow training; para. [0100]), comprising:
sending, by a first device, a first reference signal to a second device (i.e. BS needs to transmit a reference signal in order to measure a downlink channel state in a cellular system … the UE measures the reference signal that the BS transmits in the downlink, and feeds back, to the BS, information extracted from the measured reference signal in a form defined in the LTE/LTE-A standard; para. [0089, 0090]), BS transmits reference signal to the UE;
receiving, by the first device, first channel sample information from the second device (i.e. the UE measures the reference signal that the BS transmits in the downlink, and feeds back, to the BS, information extracted from the measured reference signal in a form defined in the LTE/LTE-A standard. As described above, the information that the UE feeds back in LTE/LTE-A is referred to as channel state information; para. [0090, 0125]), UE receives the BS’s reference signal, estimates channel related information from it, and then sends that information back to the BS; and
determining, by the first device, a first neural network (i.e. a method of transmitting or receiving a signal by a BS in a mobile communication system may include: identifying a neural network model for receiving first information from a UE; para. [0012, 0101, 0103]), wherein the first neural network is obtained through training based on the first channel sample information (i.e. the BS 1002 may estimate a channel matrix using a reference signal received from the UE 1001, and may perform shadow training using the estimated channel matrix as learning data. The reference signal that the UE 1001 transmits to the BS 1002 may include, for example, an SRS, a DMRS, and the like, but is not limited thereto. That is, the BS 1002 may continuously update connection weights of the autoencoder NN prepared for shadow training using a channel matrix estimated by the BS based on a signal (an SRS, a DMRS, . . . ) received from the UE 1001 or a channel matrix estimated by the UE and received from the UE; para. [0125]), using channel information/channel matrix as learning data for the neural network learning process, and is used to perform to obtain second channel sample information, wherein the second channel sample information is used to a second neural network (i.e. a method of transmitting or receiving a signal by a BS in a mobile communication system may include: identifying a neural network model for receiving first information from a UE; receiving, from the UE, second information for updating a weight of a second partial neural network corresponding to the BS; and updating the weight of the second partial neural network based on the second information … The UE 1001 and the BS 1002 may perform the autoencoder-based downlink channel feedback 700 shown in FIG. 7 using the Tx NN 1005 and the Rx NN 1008, the weights of which are updated; para. [0012, 0126, 0130]), and the second neural network is used for transmission of target information between the first device and the second device (i.e. transmitting or receiving information accurately using a limited number of bits during communication performed between a user equipment (UE) and a base station (BS) in a communication system … The UE 1001 and the BS 1002 may perform the autoencoder-based downlink channel feedback 700 shown in FIG. 7 using the Tx NN 1005 and the Rx NN 1008, the weights of which are updated; para. [0010, 0130]), transmitting/receiving a signal using neural networks between a UE and BS.
Lee does not explicitly teach perform inference to obtain second information; wherein the second information is used to train a second neural network, and wherein the first neural network, once trained, takes as input random noise and generates, via inference, the second channel sample information that is statistically similar to the first channel sample information.
However, Ye teaches perform inference to obtain second information (i.e. a conditional GAN can be employed for learning the output distribution of a channel by taking the x as the condition information. The generator will try to produce the samples similar to the output of the real channel while the discriminator will try to distinguish data coming from the real channel and the data coming from the generator; Section II, pages 2-3); wherein the second information is used to train a second neural network (i.e. a GAN is applied to model the distribution of the channel output and the learned model is then used as a surrogate of the real channel when training the transmitter so that the gradients can pass through to the transmitter; Section II, III, pages 2-4), and wherein the first neural network, once trained, takes as input random noise (i.e. During the training, the generator maps an input noise, z, with prior distribution, pz(z), to a sample; Section II, pages 2-3) and generates, via inference, the second channel sample information that is statistically similar to the first channel sample information (i.e. the generator, G, will learn to produce samples more similar to the real samples. The training procedure will end when reaching the equilibrium, where the discriminator, D, can do no better than random guessing to distinguish the real samples and the generated fake samples; Section I, II, pages 1-3).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to modify the invention of Lee to include the feature of Ye. One would have been motivated to make this modification because it improves channel modeling and training using generated channel samples.
Claim 2: Lee and Ye teach the method according to claim 1. Lee further teaches wherein the first channel sample information (i.e. In the case of the LTE-A system, a UE feeds back information associated with a channel state of a downlink to a BS, so the BS utilizes the same for downlink scheduling. That is, the UE measures the reference signal that the BS transmits in the downlink, and feeds back, to the BS, information extracted from the measured reference signal in a form defined in the LTE/LTE-A standard; para. [0090, 0114]).
Lee does not explicitly teach wherein the information is further used to train the second neural network.
However, Ye further teaches wherein the information is further used to train the second neural network (i.e. we propose a channel agnostic end-to-end learning based communication system where the distribution of channel output can be learned through a conditional generative adversarial net (GAN) [10]. The conditioning information is the encoded signals from the transmitter along with the received pilot information used for estimating the channel. By iteratively training the conditional GAN, the transmitter, and the receiver, the end-to-end loss can be optimized in a supervised way; Section I, pages 1-2.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to modify the invention of Lee to include the feature of Ye. One would have been motivated to make this modification because it improves channel modeling and training using generated channel samples.
Claim 4: Lee and Ye teach the method according to claim 1. Lee further teaches wherein the first channel sample information comprises channel state information (CSI) (i.e. the information that the UE feeds back in LTE/LTE-A is referred to as channel state information, and the channel state information; para. [0090]) or a second reference signal, and the second reference signal is the first reference signal propagated through a channel (i.e. the signal received from the BS may include, for example, a CRS, a CSI-RS, a synchronization signal, a DMRS, and the like, but is not limited thereto; para. [0125]).
Claim 5: Lee and Ye teach the method according to claim 1. Lee further teaches wherein the first neural network is an autoencoder (i.e. the autoencoder NN may include a Tx NN 603 including an input layer and an Rx NN 604 including an output layer; para. [0103]).
Lee does not explicitly teach wherein the first neural network is a generative adversarial network or a variational autoencoder.
However, Ye further teaches wherein the first neural network is a generative adversarial network or a variational autoencoder (i.e. we propose a channel agnostic end-to-end learning based communication system where the distribution of channel output can be learned through a conditional generative adversarial net (GAN); Section I, page 2).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to modify the invention of Lee to include the feature of Ye. One would have been motivated to make this modification because it improves channel modeling and training using generated channel samples.
Claim 6: Lee and Ye teach the method according to claim 1. Lee further teaches wherein the first reference signal comprises a demodulation reference signal (DMRS) or a channel state information reference signal (CSI-RS) (i.e. the signal received from the BS may include, for example, a CRS, a CSI-RS, a synchronization signal, a DMRS, and the like, but is not limited thereto; para. [0089, 0125]).
Claim 31 is similar in scope to Claim 1 and is rejected under a similar rationale.
Lee further teaches a communication apparatus, comprising a processor and a memory, wherein the memory is coupled to the processor (i.e. processor and memory; para. [0018, 0160-0162]).
Claims 43-48 are similar in scope to Claims 2-7 and are rejected under a similar rationale.
Claim 49: Lee and Ye teach a non-transitory computer-readable storage medium comprising program code, wherein the program code, when executed on one or more processors (i.e. The terms “application” and “program” refer to one or more computer programs, software components, sets of instructions, procedures, functions, objects, classes, instances, related data, or a portion thereof adapted for implementation in a suitable computer readable program code. The phrase “computer readable program code” includes any type of computer code, including source code, object code, and executable code … processor and memory; para. [0018, 0160-0162]), the method according to claim 1 (see rejection of claim 1 above).
6. Claim 3 is rejected under 35 U.S.C. 103 as being unpatentable over Lee in view of Ye, and further in view of Da Silva et al. (U.S. Patent Application Pub. No. US 20230300654 A1).
Claim 3: Lee and Ye teach the method according to claim 1. Lee further teaches wherein the method further comprises: sending, by the first device, information about a neural network to the second device (i.e. transmit, to the BS, second information for updating a weight of a second partial neural network corresponding to the BS based on a result of the learning; para. [0013]).
Lee does not explicitly teach sending, by the first device, information about a third neural network.
However, Da Silva teaches wherein the method further comprises: sending, by the first device, information about a third neural network to the second device (i.e. The network node 101 may transmit information indicating a prediction model to use for predicting the information to the UE 103; para. [0072]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to modify the combination of Lee and Ye to include the feature of Da Silva. One would have been motivated to make this modification because it enables staged learning, reuse intermediate learned representations, and improve downstream prediction/training efficiency in a system already using multiple neural networks.
7. Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Lee in view of Ye, and further in view of Huang et al. (U.S. Patent Application Pub. No. US 20220078777 A1).
Claim 7: Lee and Ye teach the method according to claim 1. Lee does not explicitly teach wherein a sequence type of the first reference signal comprises a Zadoff-Chu (ZC) sequence or a gold sequence.
However, Huang teaches wherein a sequence type of the first reference signal comprises a Zadoff-Chu (ZC) sequence or a gold sequence (i.e. a DMRS may be an example of a pilot signal, consisting of a Zadoff-Chu sequence in the frequency domain, transmitted between base stations and UEs, and also between two UEs to facilitate demodulation of data. The DMRS may be used by a wireless communication device to estimate a channel for demodulation of an associated physical channel. The DMRS may be device-specific, and thus, may directly correspond to data targeted to a particular UE. The DMRS may be transmitted on demand and may be configured with different patterns; para. [0064]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to modify the combination of Lee and Ye to include the feature of Huang. One would have been motivated to make this modification because it improves channel estimation/demodulation performance.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure.
Madani et al. (Pub. No. US 20190197358 A1), FIG. 1 is an example block diagram of a generative adversarial network (GAN). As shown in FIG. 1, the generator, G, takes a vector z, sampled from random Gaussian noise or conditioned with structured input, and transforms the noise to p.sub.G=G(z) to mimic the data distribution, p.sub.data. Batches of the generated (fake) images and real images are sent to the discriminator, D, where the discriminator assigns a label 0 for real or a label 1 for fake.
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 extension fee 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 date of this final action.
It is noted that any citation to specific pages, columns, lines, or figures in the prior art references and any interpretation of the references should not be considered to be limiting in any way. A reference is relevant for all it contains and may be relied upon for all that it would have reasonably suggested to one having ordinary skill in the art. In re Heck, 699 F.2d 1331, 1332-33, 216 U.S.P.Q. 1038, 1039 (Fed. Cir. 1983) (quoting In re Lemelson, 397 F.2d 1006, 1009, 158 U.S.P.Q. 275, 277 (C.C.P.A. 1968)).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to TAN TRAN whose telephone number is (303)297-4266. The examiner can normally be reached on Monday - Thursday - 8:00 am - 5:00 pm MT.
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, Matt Ell can be reached on 571-270-3264. 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.
/TAN H TRAN/Primary Examiner, Art Unit 2141
Prosecution Insights