DETAILED ACTION
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 .
1. Claims 1-14 are pending. Claims 15-20 are withdrawn.
Response to Arguments
2. In light of the amendments to the claims, the claim objections of claims 8-14 are withdrawn.
3. Applicant's arguments filed 07/11/2026 have been fully considered but they are not persuasive.
Argument 1
Regarding claims 1-14, on page 10, the applicant argues that “the Examiner's reliance on Chi to cure this deficiency is misplaced and represents an impermissible piecemeal reconstruction based on hindsight.”
In response to applicant's argument that the examiner's conclusion of obviousness is based upon improper hindsight reasoning, it must be recognized that any judgment on obviousness is in a sense necessarily a reconstruction based upon hindsight reasoning. But so long as it takes into account only knowledge which was within the level of ordinary skill at the time the claimed invention was made, and does not include knowledge gleaned only from the applicant's disclosure, such a reconstruction is proper. See In re McLaughlin, 443 F.2d 1392, 170 USPQ 209 (CCPA 1971).
Argument 2
Regarding claims 1-14, on page 10, the applicant argues that Chi entirely fails to disclose or suggest a multi-TRP scheme where multiple disparate channel matrices from different physical points are individually processed by CNNs, subsequently joined, and then collectively compressed by FCNNs.
In response to applicant's argument, the examiner respectfully disagrees with the applicant's response. Claim 1 does not disclose “multiple disparate channel matrices from different physical points are individually processed by CNNs.” The scope of claim 1 recites “obtaining a plurality of first channel matrices that each indicates CSI of a communication channel between the UE and a respective one of multiple transmission-reception-points (TRPs).” Claim 1 recites a plurality of first channel matrices from one TRP is compressed and concatenated in the subsequent method steps. Claim 1 does not recite or include within the scope of the claim limitations “multiple disparate channel matrices from different physical points are individually processed by CNNs.”
In response to applicant's argument that the references fail to show certain features of the invention, it is noted that the features upon which applicant relies (i.e., multiple disparate channel matrices from different physical points are individually processed by CNNs) are not recited in the rejected claim(s). Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993).
Argument 3
Regarding claims 1-14, on page 10, the applicant argues that the claimed architecture effectively captures cross-point channel correlations unique to a multi-TRP environment.
In response to applicant's argument that the references fail to show certain features of the invention, it is noted that the features upon which applicant relies (i.e., capturing cross-point channel correlations unique to a multi-TRP environment) are not recited in the rejected claim(s). Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993).
Argument 4
Regarding claims 1-14, on page 10, the applicant argues that the cited references fail to provide the required motivation to combine and fail to disclose the claimed two-stage structural compression of a multi-TRP joint feature vector. As previously outlined by the Examiner, claim 1 does not discloses a multi-TRP joint feature vector. Claim 1 recites a joint feature vector for a single TRP.
For these reasons, claim(s) 1-2, 7-9 and 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Janco et al, US 2022/0399920 hereafter Janco in view of Truong, US 2023/0153602 hereafter Truong in view of Chi, US 2025/0007583 hereafter Chi.
Claim Objections
4. Claims 1 and 8 are objected to because of the following informalities: Claim 1 recites “the plurality of feature vectors” which should read “the plurality of respective feature vectors” for clarity. Appropriate correction is required.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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 nonobviousness.
5. Claim(s) 1-2, 7-9 and 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Janco et al, US 2022/0399920 hereafter Janco in view of Truong, US 2023/0153602 hereafter Truong in view of Chi, US 2025/0007583 hereafter Chi.
As for claim 1, Janco discloses:
A method for channel state information (CSI) compression at a user equipment (UE), (Janco, Fig. 3A, [0099], one or more beamformee devices (e.g., one or more of STA devices 306a-306c)) the method comprising:
obtaining a plurality of first channel matrices that each indicates CSI of a communication channel between the UE and a respective one of multiple transmission-reception-points (TRPs); (Janco, Fig. 2, 200a, 204, [0072]-[0074], [0148], [0244], obtaining a plurality of first channel matrices that each indicates CSI of a communication channel between the UE (beamformee) and a respective AP (beamformer)),
…a respective feature vector (Janco, [0119], Calculate/producing from at least one CSI information at least one feature vector) through one or more convolutional neural networks (CNNs); (Janco, [0131], the ML implemented as a convolutional neural network (CNN))
Janco does not explicitly disclose compressing each of the plurality of first channel matrices into a respective feature vector through one or more convolutional neural networks (CNNs); concatenating the plurality of feature vectors into a joint feature vector.
However, Truong discloses concatenating the plurality of feature vectors into a joint feature vector. (Truong, [0005], concatenate the first set of feature vectors with the second set of feature vectors to generate concatenated feature vectors)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Janco with concatenating the plurality of feature vectors into a joint feature vector as taught by Truong to provide enhance performance of the first machine learning model. (Truong, [0003])
The combination of Janco and Truong does not explicitly disclose compressing each of the plurality of first channel matrices into a respective feature vector through one or more convolutional neural networks (CNNs); compressing the joint feature vector into a compressed joint feature vector through one or more fully connected neural networks (FCNNs).
However, Chi discloses compressing each of the plurality of first channel matrices into a respective feature vector through one or more convolutional neural networks (CNNs); (Chi, Fig. 2, 201-203, Fig14A, [0068]-[0071], [0093]-[0095], [0256], the first correlation feature matrix comprising channel/CSI information may first be subjected to a dimensionality reduction to be converted to a first correlation feature vector through the CNN. The Examiner interprets the dimensionality reduction to correspond to compressing since reducing the dimensionality reduction reduces the amount of information required to represent the data,) compressing the joint feature vector into a compressed joint feature vector through one or more fully connected neural networks (FCNNs). (Chi, [0112], [0139], Compressing the first correlation feature vector into a target codeword which is amplified to obtain a second correlation feature vector through the neural network consisting of a fully connected layer)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the combination of the teachings of Janco and Truong with compressing the joint feature vector into a compressed joint feature vector through one or more fully connected neural networks (FCNNs) as taught by Chi to provide improved performance for feature analysis at the base station. (Chi, [0141])
As for claims 2 and 9, Janco discloses receiving, from the multiple TRPs, a plurality of reference signals; determining a plurality of second channel matrices based on the plurality of reference signals; and transforming each of the plurality of second channel matrices into a respective one of the plurality of first channel matrices. (Janco, Fig. 2, 200a, 204, 206, 208, [0072]-[0082], Receiving, from the respective AP (beamformer), the NDP 200a; calculating the CSI matrices based on the NDP; transforming the CSI matrices to produce one or more respective “feedback” matrices, or V matrices)
As for claims 7 and 14, Janco discloses each of the multiple TRPs. (Janco, [0017], [0092]-[0093], [0244], The plurality of beamformers may include devices such as wireless routers, wireless switches, base stations)
The combination of Truong and Janco does not explicitly disclose sending, to the TRP, the compressed joint feature vector for CSI feedback.
However, Chi discloses sending, to the TRP, the compressed joint feature vector for CSI feedback (Chi, Fig. 11, [0139], fully connected layer amplifies the target codeword based on a preset compression rate η, thus a second correlation feature vector is obtained. [0051] Step 1, a low-dimensional measured value is obtained by transforming CSI to a sparse matrix under a specified basis, and randomly compressing and sampling the CSI at a terminal side by using a compressive sensing method, and is transmitted to a base station through a feedback link.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the combination of the teachings of Janco and Truong with sending, to each of the multiple TRPs, the compressed joint feature vector for CSI feedback as taught by Chi to provide improved performance for feature analysis at the base station. (Chi, [0141])
As for claim 8, Janco discloses:
A user equipment (UE), (Janco, Fig. 3A, [0099], one or more beamformee devices (e.g., one or more of STA devices 306a-306c)) comprising:
processing circuitry (Janco, [0302] These computer readable program instructions may be provided to a hardware processor of a general-purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine) configured to obtain a plurality of first channel matrices that each indicates CSI of a communication channel between the UE and a respective one of multiple transmission-reception-points (TRPs); (Janco, Fig. 2, 200a, 204, [0072]-[0074], obtaining a plurality of first channel matrices that each indicates CSI of a communication channel between the UE (beamformee) and a respective AP (beamformer)),
…a respective feature vector (Janco, [0119], Calculate/producing from at least one CSI information at least one feature vector) through one or more convolutional neural networks (CNNs); (Janco, [0131], the ML implemented as a convolutional neural network (CNN))
Janco does not explicitly disclose concatenate the plurality of feature vectors into a joint feature vector.
However, Truong discloses concatenate the plurality of feature vectors into a joint feature vector. (Truong, [0005], concatenate the first set of feature vectors with the second set of feature vectors to generate concatenated feature vectors)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Janco with concatenate the plurality of feature vectors into a joint feature vector as taught by Truong to provide enhance performance of the first machine learning model. (Truong, [0003])
The combination of Janco and Truong does not explicitly disclose compressing each of the plurality of first channel matrices into a respective feature vector through one or more convolutional neural networks (CNNs); compressing the joint feature vector into a compressed joint feature vector through one or more fully connected neural networks (FCNNs).
However, Chi discloses compressing each of the plurality of first channel matrices into a respective feature vector through one or more convolutional neural networks (CNNs); (Chi, Fig. 2, 201-203, Fig14A, [0068]-[0071], [0093]-[0095], [0256], the first correlation feature matrix comprising channel/CSI information may first be subjected to a dimensionality reduction to be converted to a first correlation feature vector through the CNN. The Examiner interprets the dimensionality reduction to correspond to compressing since reducing the dimensionality reduction reduces the amount of information required to represent the data,) compressing the joint feature vector into a compressed joint feature vector through one or more fully connected neural networks (FCNNs). (Chi, [0112], [0139], Compressing the first correlation feature vector into a target codeword which is amplified to obtain a second correlation feature vector through the neural network consisting of a fully connected layer)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the combination of the teachings of Janco and Truong with compressing each of the plurality of first channel matrices into a respective feature vector through one or more convolutional neural networks (CNNs); compressing the joint feature vector into a compressed joint feature vector through one or more fully connected neural networks (FCNNs) as taught by Chi to provide improved performance for feature analysis at the base station. (Chi, [0141])
6. Claim(s) 3, 5, 10 and 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Janco et al, US 2022/0399920 in view of Truong, US 2023/0153602 in view of Chi, US 2025/0007583 as applied to claims 2 and 8 above, and further in view of Remireddy et al, US 2022/0029676 hereafter Remireddy.
As for claims 3 and 10, Janco discloses wherein each of the plurality of second channel matrices is in a three dimensional domain that is represented by a transmit antenna index of one of the multiple TRPs. (Janco [0116]… Each entry of feature vector 316a may represent steering data pertaining to at least one of: (i) a specific subcarrier of the wireless channel, (ii) a specific antenna of a beamformer device (e.g., AP 304), and (iii) a specific antenna of a specific beamformee device (e.g., STA 306)).
The combination of Janco and Truong does not explicitly disclose each of the plurality of second channel matrices is in a three dimensional domain that is represented by a time domain index, and a frequency domain index.
Chi discloses wherein each of the plurality of second channel matrices is in a three dimensional domain that is represented by a time domain index, and a frequency domain index. (Chi, [0077], the second CSI matrix is a matrix used for indicating different parameter values corresponding to different space domains and frequency domains)
The combination of Janco, Truong and Chi does not explicitly disclose a time domain index and each of the plurality of first channel matrices is in a three dimensional domain that is represented by a transmit beam index of the one of the multiple TRPs, a delay component index, and a Doppler component index.
However, Ramireddy discloses a time domain index, (Ramireddy, Fig. 7, Fig. 8, [0047], [0059]-[0060], [0603]-[0605], The time index) and a frequency domain index, (Ramireddy, [0238], Doppler-frequency components are employed in the precoder matrix construction) and each of the plurality of first channel matrices is in a three dimensional domain (Ramireddy, Fig. 4, 250, [0034], [0078], [0277]-[0278], [0291], The explicit CSI may be represented by a three-dimensional channel tensor (a three-dimensional array)) that is represented by a transmit beam index of the one of the multiple TRPs, (Ramireddy, Fig. 4, 250, [0034], [0078], [0277]-[0278], [0291], The matrix including a Doppler-delay-beam matrix) a delay component index, (Ramireddy, Fig. 4, 250, [0034], [0078], [0277]-[0278], [0291], The matrix including a Doppler-delay-beam matrix) and a Doppler component index. (Ramireddy, Fig. 4, 250, [0034], [0078], [0277]-[0278], [0291], The matrix including a Doppler-delay-beam matrix)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the combination of the teachings of Janco, Truong and Chi with a time domain index, and a frequency domain index, and each of the plurality of first channel matrices is in a three dimensional domain that is represented by a transmit beam index of the one of the multiple TRPs, a delay component index, and a Doppler component index as taught by Ramireddy to organize known dimensions of CSI data into a multi-dimensional structure which reduces the calculation complexity at the UE and further reducing the feedback overhead. (Ramireddy, [0235])
As for claims 5 and 12, Janco discloses wherein each of the plurality of second channel matrices is in a three dimensional domain that is represented by a transmit antenna index of one of the multiple TRPs. (Janco [0116]… Each entry of feature vector 316a may represent steering data pertaining to at least one of: (i) a specific subcarrier of the wireless channel, (ii) a specific antenna of a beamformer device (e.g., AP 304), and (iii) a specific antenna of a specific beamformee device (e.g., STA 306)).
The combination of Janco and Truong does not explicitly disclose each of the plurality of second channel matrices is in a three dimensional domain that is represented by a time domain index, and a frequency domain index.
Chi discloses wherein each of the plurality of second channel matrices is in a three dimensional domain that is represented by a time domain index, and a frequency domain index. (Chi, [0077], the second CSI matrix is a matrix used for indicating different parameter values corresponding to different space domains and frequency domains)
The combination of Janco, Truong and Chi does not explicitly disclose a time domain index and each of the plurality of first channel matrices is in a three dimensional domain that is represented by a transmit beam index of the one of the multiple TRPs, a delay component index, and a Doppler component index.
The combination of Janco, Truong and Chi does not explicitly disclose a time domain index, and a frequency domain index, and each of the plurality of first channel matrices is in a four dimensional domain that is represented by a receive beam index of the UE, a transmit beam index of the one of the multiple TRPs, a delay component index, and a Doppler component index.
However, Ramireddy discloses a time domain index, (Ramireddy, Fig. 7, Fig. 8, [0047], [0059]-[0060], [0603]-[0605], The time index) and a frequency domain index, (Ramireddy, [0238], Doppler-frequency components are employed in the precoder matrix construction) and each of the plurality of first channel matrices is in a four dimensional domain (Ramireddy, [0279], [0578], The explicit CSI may be represented by a four-dimensional channel tensor) that is represented by a receive beam index of the one of the multiple TRPs, (Ramireddy, Fig. 4, 250, [0034], [0078], [0277]-[0278], [0291], The matrix including a Doppler-delay-beam matrix), a transmit beam index of the one of the multiple TRPs, (Ramireddy, Fig. 4, 250, [0034], [0078], [0277]-[0278], [0291], The matrix including a Doppler-delay-beam matrix), a delay component index, (Ramireddy, Fig. 4, 250, [0034], [0078], [0277]-[0278], [0291], The matrix including a Doppler-delay-beam matrix) and a Doppler component index. (Ramireddy, Fig. 4, 250, [0034], [0078], [0277]-[0278], [0291], The matrix including a Doppler-delay-beam matrix)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the combination of the teachings of Janco, Truong and Chi with a time domain index, and a frequency domain index, and each of the plurality of first channel matrices is in a four dimensional domain that is represented by a receive beam index of the UE, a transmit beam index of the one of the multiple TRPs, a delay component index, and a Doppler component index.as taught by Ramireddy as taught by Ramireddy to organize known dimensions of CSI data into a multi-dimensional structure which reduces the calculation complexity at the UE and further reducing the feedback overhead. (Ramireddy, [0235])
7. Claim(s) 4 and 11 is/are rejected under 35 U.S.C. 103 as being unpatentable over Janco et al, US 2022/0399920 in view of Truong, US 2023/0153602 in view of Chi, US 2025/0007583 in view of Remireddy et al, US 2022/0029676 as applied to claims 3, 5, 10 and 12 above, and further in view of Tzadok, US 2022/0003840 hereafter Tzadok.
As for claims 4 and 11, the combination of Janco, Truong, Chi and Remireddy does not explicitly disclose wherein each of the one or more CNNs is a three dimensional CNN.
However, discloses wherein each of the one or more CNNs is a three dimensional CNN. (Tzadok, [0024], [0037], The 3D CNN processes input data over three dimensions to extract features according to the training of the 3D CNN)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the combination of the teachings of Janco, Truong, Chi and Remireddy with wherein each of the one or more CNNs is a three dimensional CNN as taught by Tzadok to apply known CNN processing techniques for multi-dimensional tensors to other types of multi-dimensional data such as CSI matrices to enable rapid volumetric analysis by recognizing scenarios from the training data. (Tzadok, [0039])
8. Claim(s) 6 and 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Janco et al, US 2022/0399920 in view of Truong, US 2023/0153602 in view of Chi, US 2025/0007583 in view of Remireddy et al, US 2022/0029676 as applied to claims 5 and 12 above, and further in view of Katchi et al, US 2023/0236984 hereafter Katchi.
As for claims 6 and 13, the combination of Janco, Truong, Chi and Remireddy does not explicitly disclose wherein each of the one or more CNNs is a four dimensional CNN.
However, Kathi discloses wherein each of the one or more CNNs is a four dimensional CNN. (Katchi, [0062], As illustrated in FIG. 3, for example, data handled by a convolutional neural network (CNN) has up to four dimensions.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the combination of the teachings of Janco, Truong, Chi and Remireddy with wherein each of the one or more CNNs is a four dimensional CNN as taught by Katchi to apply known CNN processing techniques for multi-dimensional tensors to other types of multi-dimensional data such as CSI matrices which optimizes memory usage for multi-dimensional data processed by CNNs. (Katchi, [0075]-[0076])
Conclusion
9. The prior art made of record and not relied upon is considered pertinent to applicant's disclosure: Saber et al, US 2023/0131694.
10. THIS ACTION IS MADE FINAL. 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.
11. Any inquiry concerning this communication or earlier communications from the examiner should be directed to JENEE HOLLAND whose telephone number is (571)270-7196. The examiner can normally be reached 8:30 AM - 5:00 PM.
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, IAN MOORE can be reached at (571)272-3085. 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.
JENEE HOLLAND
Examiner
Art Unit 2469
/JENEE HOLLAND/Primary Examiner, Art Unit 2469
Prosecution Insights