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 .
DETAILED ACTION
Claims 1-11 and 20-30 are pending.
Response to Arguments
Applicant’s arguments with respect to claim(s) 1-11 and 20-30 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
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 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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-2, 20-21 and 30 are rejected under 35 U.S.C. 103 as being unpatentable over Yogeeshwar et al. (Deep Generative Model based Channel Agnostic Communication System for Efficient Data Transmission", 2020 IEEE International Conference on Communication, Networks and Satellite, IEEE, 17 December 2020, pp.373-379, XP033883033, hereinafter referred as Yogeeshwar) in view of Jeong et al. (US 2024/0396766 A1, supported by PCT/EP2021/075202).
Regarding claim 1, Yogeeshwar discloses a processor-implemented method of generating simulated output data, comprising: receiving a first set of input data for data transmitted, from a transmitter, as a signal in a wireless channel (Pages 3-4, section III discloses When the data Y is transmitted through the channel, due to stochasticity of the channel and the addition of AWGN z, it transforms Y→ X where X is the received corrupted form of Y. So, in short, the channel effect H, can be denoted as H: \{Y, z\}→X. The process of converting X back to Y is done by conditional GAN. The X is given as the input to the generator G. Generator G has UNet architecture due to its capability to segment the input and predict each pixel’s class thereby making it easy to generate reconstructed data Y from the corrupted data X. The received data X and the transmitted data (ground truth) Y is passed to the discriminator as source data and target data respectively. Generally, source data is transformed into target data (ground truth). The discriminator D takes inputs X and Y and classifies that X→Y transformation is real (upon training). When source data X and the output of the generator G(X) are given. Figs a-d are all proposed channel modelling in wireless communication.); generating a channel model for the wireless channel using a generative adversarial network (GAN) (Pages 4-5, section III section IV discloses generating a channel model using GAN. GAN channel model improves performance. Page 5, discloses the parameters of channel GAN section B. GANs are generative models which can generate/produce new contents. Generally, GAN architecture consists of two neural networks; generator model, discriminator model. The generator model is used to generate new plausible examples from target domain and the discriminator model is used to classify the examples as real (from target domain) or fake (from generator). The algorithm of GANs is similar to minmax game, where the discriminator tries to maximize it’s efficiency as a classifier in order to classify the origin of the input data as real/fake according to the distribution of the data where it came from and the generator will maximize it’s efficiency to generate samples close to the distribution of the real data); and generating a first set of simulated output data by transforming the first set of input data using the channel model (Section V: Pages 5-6 Fig. 5, discloses the output data. Further with the tremendous increase on the need for bandwidth, a novel idea has been devised where the input data is encoded into a condensed latent space and impacted with noise which is then passed through a Generative Adversarial Network which proved excellent reconstruction results with a minute degradation when compared to the channel GAN).
Yogeeshwar in combination with Jeong discloses functions of GAN, specifically Fig. 6 discloses a GAN structure following convergence of a training procedure. This channel estimator then accepts pilot symbol data 501 as conditioning input to the generative part (the estimator), which then generates an estimate of the complete image, i.e., an estimate of the radio propagation channel realization at all the REs, including both pilot symbol REs and data REs. Further Fig. 9 also discloses the mechanism of using GAN model. Fig. 19 discloses the gNB trains a channel predictor by using an adversarial learner as discussed above, based on the obtained pilot symbol data. The input to the GAN structure during training is the SRS channel response at length-k sequence of time slots in a trajectory. The output from the GAN structure is an SRS channel response at some predetermined future point in time. Fig. 10 discloses processing circuitry 1010 arranged to transmit the channel estimator to an access point 110, 120 and/or to a wireless device 130, 140 comprised in the wireless communication system 100).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to provide the technique of Jeong to the system of Yogeeshwar to provide performing radio propagation channel estimation in a wireless communication system. The techniques are based on machine learning, and in particular machine learning techniques based on generative adversarial networks (GAN) (Abstract).
Regarding claim 20, claim 20 comprises similar limitations as claimed above in claim 1, claimed as a processing system comprising: memory comprising computer-executable instructions; and one or more processors configured to execute the computer-executable instructions and cause the processing system to perform an operation as disclosed above. Joeng discloses in Fig. 19 processor 1010 and memory 1030, paragraph 0132.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to provide the technique of Jeong to the system of Yogeeshwar to provide performing radio propagation channel estimation in a wireless communication system. The techniques are based on machine learning, and in particular machine learning techniques based on generative adversarial networks (GAN) (Abstract).
Regarding claim 30, claim 30 comprises similar limitations as claimed above in claim 1, claimed as a processing system. Joeng discloses in Fig. 19 processor 1010 and memory 1030, paragraph 0132. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to provide the technique of Jeong to the system of Yogeeshwar to provide performing radio propagation channel estimation in a wireless communication system. The techniques are based on machine learning, and in particular machine learning techniques based on generative adversarial networks (GAN) (Abstract).
Regarding claims 2 and 21, Yogeeshwar discloses wherein the GAN was trained by: training a generator network to generate the channel model (Pages 4-5, section III section IV discloses generating a channel model using GAN. GAN channel model improves performance. Page 5 discloses the parameters of channel GAN section B. GANs are generative models which can generate/produce new contents. Generally, GAN architecture consists of two neural networks: generator model, discriminator model. The generator model is used to generate new plausible examples from target domain and the discriminator model is used to classify the examples as real (from target domain) or fake (from generator). The algorithm of GANs is similar to minmax game, where the discriminator tries to maximize it’s efficiency as a classifier in order to classify the origin of the input data as real/fake according to the distribution of the data where it came from and the generator will maximize it’s efficiency to generate samples close to the distribution of the real data); and generating a first set of simulated output data by transforming the first set of input data using the channel model (Section V: Pages 5-6 Fig. 5, discloses the output data. Further with the tremendous increase on the need for bandwidth, a novel idea has been devised where the input data is encoded into a condensed latent space and impacted with noise which is then passed through a Generative Adversarial Network which proved excellent reconstruction results with a minute degradation when compared to the channel GAN).
Allowable Subject Matter
Claims 3-11 and 22-29 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
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Srivastava et al. (US 20210133539 A1) discloses a generator network of a variational autoencoder can be trained to approximate a simulator and generate a first result. The simulator is associated with input data, based on which the simulator outputs output data. A training data set for the generator network can include the simulator's input data and output data. Based on the simulator's output data and the first result of the generator network, an inference network of the variational autoencoder can be trained to generate a second result.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ROMANI OHRI whose telephone number is (571)272-5420. The examiner can normally be reached 8:00am-5:00pm.
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, UN C CHO can be reached at 5712727919. 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.
/ROMANI OHRI/Primary Examiner, Art Unit 2413
Prosecution Insights