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 action is in response to the original filing on 06/30/2023. Claims 1-7 and 31 are pending and have been considered below.
Election/Restrictions
3. Claims 8-12, 21-26, and 33 are withdraw from further consideration pursuant to 37 CFR 1.142(b) as being drawn to nonelected groups II and III. Election was made with traverse in the reply filed on 03/19/2026.
Information Disclosure Statement
4. The information disclosure statement (IDS(s)) submitted on 03/11/2024, 09/03/2024 is/are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Response to Arguments
Applicant’s argument that claims 1 and 8 share subject matter relating to a fist reference signal and first channel sample information is acknowledged but is not persuasive because overlap in some subject matter does not, by itself, defeat restriction. The proper inquiry is whether the inventions as claimed are distinct and whether examination of all claims together would require materially different search efforts. Here, Group I and Group II are directed to related processes under MPEP § 806.05(j). In the instant application, Group I is directed to first device side operations including sending a first reference signal, receiving first channel sample information from a second device, determining a first neural network based on that information, using the first neural network to perform inference to obtain second channel sample information, and using the second sample channel information to train a second neural network for transmission of target information. Group II, by contrast, is directed to a second device side operations including performing channel estimation based on a received first reference signal, determining first channel sample information, sending that first channel sample information to the first device, and receiving information about a third neural network. Thus, although the groups arise in the same general technological environment, they are claimed from different device perspectives and recite different operative acts, different immediate functions, and different claimed outputs. On this record, the inventions as claimed do not overlap in scope, and there is nothing of record establishing that they are obvious variants.
Applicant argues that all claims are simply in the “field of training of neural networks,” that characterization is too broad to negate burden. The claimed inventions are not directed merely to the same generic concept of neural network training; rather, they are directed to different device side implementations within a communication system, with different claimed actions and different technical subject matter to be searched.
According, Applicant has not persuasively rebutted the prima facie showing of distinctness and serious search burden. The traversal is therefore not persuasive, and the restriction requirement between Groups I and II is maintained.
Claim Rejections – 35 USC § 103
5. 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.
6. Claims 1, 2, 4, 6, and 31 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 Li (U.S. Patent Application Pub. No. US 20230237841 A1).
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.
However, Li teaches perform inference to obtain second information; wherein the second information is used to train a second neural network (i.e. training a first neural network, so that the first neural network outputs coordinate values of a predicted key point based on the input first face image; selecting output of a hidden layer in the first neural network, using the output of the hidden layer as input, to train a second neural network, and outputting an occlusion probability of the predicted key point; para. [0034-0037]).
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 Li. 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.
Claim 2: Lee and Li 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, Li further teaches wherein the information is further used to train the second neural network (i.e. training a first neural network, so that the first neural network outputs coordinate values of a predicted key point based on the input first face image; selecting output of a hidden layer in the first neural network, using the output of the hidden layer as input, to train a second neural network, and outputting an occlusion probability of the predicted key point; para. [0034-0037]).
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 Li. 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.
Claim 4: Lee and Li 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 6: Lee and Li 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]).
7. Claim 3 is rejected under 35 U.S.C. 103 as being unpatentable over Lee in view of Li, and further in view of Da Silva et al. (U.S. Patent Application Pub. No. US 20230300654 A1).
Claim 3: Lee and Li 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 Li 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.
8. Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over Lee in view of Li, and further in view of Behboodi et al. (U.S. Patent Application Pub. No. US 20220123966 A1).
Claim 5: Lee and Li 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, Behboodi teaches wherein the first neural network is a generative adversarial network or a variational autoencoder (i.e. Machine learning systems may implement generative modeling to learn a latent representation z of data x in a dataset {x.sub.i, i=1, . . . , m}. The latent representation may be learned based on a generative process P.sub.θ(x|z). The generative process refers to a conditional distribution of the data x given the latent representation z. The generative model may improve inference and may learn directed probabilistic models. A variational auto-encoder (VAE) and a generative adversarial network (GAN) are examples of generative models; para. [0029]).
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 Li to include the feature of Behboodi. One would have been motivated to make this modification because it improves latent representation and probabilistic modeling of channel information in the communication system.
9. Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Lee in view of Li, and further in view of Huang et al. (U.S. Patent Application Pub. No. US 20220078777 A1).
Claim 7: Lee and Li 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 Li 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.
Song et al. (Pub. No. US 20220376957 A1), a first device determines a signal quality that is expected in transmission of a reference signal from a second device to the first device and receives the reference signal from the second device.
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