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 .
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1, 10, and 38 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Tang et al. (Dilated Convolution based CSI Feedback Compression for Massive MIMO Systems, arXiv:2106.04043v1 [cs.IT] 8 Jun 2021).
.
Regarding claim 1, Tang et al. teach An information feedback method, wherein the method is performed by a terminal, comprising:
determining a first channel state information (CSI) matrix (section II by using the matrix Ha), wherein the first CSI matrix is a matrix used for indicating different angle values corresponding to different feedback paths (Fug. 1 shows horizontal axis of matrix Ha as Angle) in a case where the terminal feeds CSI by an antenna back to a base station (Tang Abstract it requires to feedback the downlink channel state information (CSI) from users to the base station (BS),););
obtaining a first correlation feature matrix (Section III A After passing though the encoder block, the 2 ×Na×Nt will be reshaped to a 1-D vector ) outputted from a first multi-feature analysis network (Section III A the CNN-based autoencoder can efficiently extract the spatially local correlation in the CSI matrices) and used for indicating a correlation among a plurality of pieces of feature information of the CSI by inputting the first CSI matrix into the first multi- feature analysis network (the input matrix of the encoder is Ha with the dimension of 2 × Na × Nt, where the first two independent channels represent the real and imaginary parts of the CSI matrix, respectively. We then use a 5×5 head convolution to extract the features from the input CSI matrix and fuse the information from the real and imaginary parts);
obtaining a target codeword corresponding to the CSI by compressing the first correlation feature matrix (Section III A the fully connected (FC) layers are used to compress the vector into a codeword); and
feeding the target codeword back to the base station by the antenna (Section III A After that, the codeword will be transmitted to the decoder at the BS via the wireless channel).
Regarding claim 10, Tang et al. teach The method according to claim 1, wherein obtaining the target codeword corresponding to the CSI by compressing the first correlation feature matrix comprises:
obtaining a first correlation feature vector by performing a dimensionality reduction on the first correlation feature matrix (Tang Section III A After passing though the encoder block, the 2 ×Na×Nt will be reshaped to a 1-D vector ); and
obtaining the target codeword by compressing the first correlation feature vector according to a preset compression rate (Tang Section III A the fully connected (FC) layers are used to compress the vector into a codeword).
Regarding claim 38, Tang et al. teach An information feedback apparatus (Tang section I user equipments (UEs)), comprising:
a processor (Note: inherent in a UE); and
a memory, configured to store a processor-executable instruction (Note: inherent in a UE);
wherein the processor is configured to:
determine a first channel state information (CSI) matrix (section II by using the matrix Ha), wherein the first CSI matrix is a matrix used for indicating different angle values corresponding to different feedback paths (Fug. 1 shows horizontal axis of matrix Ha as Angle) in a case where the terminal feeds CSI by an antenna back to a base station (Tang Abstract it requires to feedback the downlink channel state information (CSI) from users to the base station (BS),););
obtain a first correlation feature matrix (Section III A After passing though the encoder block, the 2 ×Na×Nt will be reshaped to a 1-D vector ) outputted from a first multi-feature analysis network (Section III A the CNN-based autoencoder can efficiently extract the spatially local correlation in the CSI matrices) and used for indicating a correlation among a plurality of pieces of feature information of the CSI by inputting the first CSI matrix into the first multi- feature analysis network (Section III A the input matrix of the encoder is Ha with the dimension of 2 × Na × Nt, where the first two independent channels represent the real and imaginary parts of the CSI matrix, respectively. We then use a 5×5 head convolution to extract the features from the input CSI matrix and fuse the information from the real and imaginary parts);
obtain a target codeword corresponding to the CSI by compressing the first correlation feature matrix (Section III A the fully connected (FC) layers are used to compress the vector into a codeword); and
feed the target codeword back to the base station by the antenna (Section III A After that, the codeword will be transmitted to the decoder at the BS via the wireless channel).
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 2 is rejected under 35 U.S.C. 103 as being unpatentable over Tang et al.
Regarding claim 2, Tang et al. teach The method according to claim 1, wherein determining the first channel state information (CSI) matrix comprises:
determining a second CSI matrix (Tang section II The CSI of all sub-carriers can be expressed by the matrix H =[h1, h2, …, hNc], where there are 2NcNt elements in total), wherein the second CSI matrix is a matrix used for indicating different parameter values corresponding to different space domains ( Tang section II there are Nt >> 1 transmit antennas at the BS) and frequency domains (Tang section II with Nc sub-carriers.) in a case where the terminal feeds the CSI by the antenna back to the base station (Tang Abstract it requires to feedback the downlink channel state information (CSI) from users to the base station (BS),);
obtaining a third CSI matrix by performing a two-dimensional discrete Fourier transform on the second CSI matrix (Tang section II the CSI feedback model is shown in Fig. 1. Specifically, the CSI matrix H is firstly transformed into the angular and delay domains, by using the discrete Fourier transformation (DFT), given by equation (2)); and
obtaining the first CSI matrix by retaining a first number of non-zero rows of parameter values in an order from front to back in the third CSI matrix (Tang section II The matrix
H
ˇ
is sparse and compressible, and it can be divided into two parts. One part is Ha which has Na rows composed of non-zero elements (Na < Nc), while the other part contains the rest Nc − Na rows composed of near-zero elements. In this way, we can compress the CSI matrix H, by using the matrix Ha).
Tang et al. do not explicitly teach
wherein the first number is a same as a total number of antennas deployed at the base station.
However, it would have been obvious to one of ordinary skill in the art before the effective filing date of the examined application to have selected Na =Nt as an obvious design choice such that the first number is a same as a total number of antennas deployed at the base station.
The motivation of doing so would have
Claim(s) 11-12 are rejected under 35 U.S.C. 103 as being unpatentable over Tang et al. in view of NAMGOONG et al. (US 20230114870 A1)
Regarding claim 11, Tang et al. teach The method according to claim 1,
further comprising: the target encoding neural network comprises the first multi-feature analysis network and a compression neural network used for compressing the first correlation feature matrix(Tang section III. A CNN-based autoencoder can efficiently extract the spatially local correlation in the CSI matrices ... and the fully connected (FC) layers are used to compress the vector into a codeword) but do not teach
receiving first signaling sent by the base station; wherein the first signaling
comprises first network parameters corresponding to a plurality of neural network
layers comprised in a target encoding neural network,; and
obtaining the target encoding neural network by configuring, based on the first
network parameters, network parameters corresponding to a plurality of neural
network layers comprised in an initial encoding neural network pre-deployed on the
terminal; wherein the initial encoding neural network is an untrained neural
network having the same network structure as the target encoding neural network.
In a similar endeavor, NAMGOONG et al. teach
receiving first signaling sent by the base station; wherein the first signaling
comprises first network parameters corresponding to a plurality of neural network
layers (NAMGOONG [0005] Convolutional neural networks may include layers of neurons that may be configured in a tiled receptive field) comprised in a target encoding neural network (NAMGOONG [0099] The UE may also receive, from the base station, model parameters for the receiver neural network.);
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the examined application to have modified Tang et al. by incorporating NAMGOONG et al. parameters received from the base station to arrive at the invention including
obtaining the target encoding neural network by configuring, based on the first
network parameters, network parameters corresponding to a plurality of neural
network layers comprised in an initial encoding neural network pre-deployed on the
terminal; wherein the initial encoding neural network is an untrained neural
network having the same network structure as the target encoding neural network.
The motivation of doing so would enable the UE to implement the target neural network.
Regarding claim 12, Tang et al. teach The method according to claim 1, further comprising:
The target encoding neural network comprises the first multi-feature analysis network and the compression neural network used for compressing the first correlation feature matrix (Tang section III. A CNN-based autoencoder can efficiently extract the spatially local correlation in the CSI matrices ... and the fully connected (FC) layers are used to compress the vector into a codeword) but do not teach
receiving second signaling sent by the base station; wherein the second signaling comprises updated first network parameters corresponding to the plurality of the neural network layers comprised in the target encoding neural network, and
obtaining an updated target encoding neural network by updating, based on
the updated first network parameters, the network parameters corresponding to the
plurality of the neural network layers comprised in the target encoding neural
network.
In a similar endeavor, NAMGOONG et al. teach
receiving second signaling sent by the base station; wherein the second signaling comprises updated first network parameters corresponding to the plurality of the neural network layers comprised in the target encoding neural network ((NAMGOONG [0005] Convolutional neural networks may include layers of neurons that may be configured in a tiled receptive field, NAMGOONG [0099] The UE may also receive, from the base station, model parameters for the receiver neural network.);
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the examined application to have modified Tang et al. by incorporating NAMGOONG et al. parameters received from the base station to arrive at the invention including:
obtaining an updated target encoding neural network by updating, based on
the updated first network parameters, the network parameters corresponding to the
plurality of the neural network layers comprised in the target encoding neural
network.
The motivation of doing so would enable the UE to implement the target neural network.
Allowable Subject Matter
Claims 3-8 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.
The following is a statement of reasons for the indication of allowable subject matter: .
Regarding claim 3, Tang et al. teach The method according to claim 1, but fail to teach or suggest wherein the plurality of pieces of feature information of the CSI at least comprise spatial feature information of the CSI and channel feature information of the CSI; and
the first multi-feature analysis network determines the first correlation feature matrix by:
determining, based on the first CSI matrix, a first spatial feature matrix used for indicating the spatial feature information of the CSI;
determining, based on the first CSI matrix, a first channel feature matrix used for indicating the channel feature information of the CSI;
obtaining a first fused feature matrix by fusing the first spatial feature matrix and the first channel feature matrix by column; and
obtaining the first correlation feature matrix outputted from a first composite convolutional layer by inputting the first fused feature matrix into the first composite convolutional layer, wherein the first composite convolutional layer being is obtained by compositing a first convolutional layer with at least one other neural network layer, wherein-a size of a convolutional kernel of the first convolutional layer is 1 x 1, and a number of the convolutional kernels of the first convolutional layer is a same as a number of channels inputted into the first composite convolutional layer.
Regarding claims 5-8, they are objected to for depending directly or indirectly from claim 3
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SAID M ELNOUBI whose telephone number is (571)272-9732. The examiner can normally be reached Monday-Friday 9:30AM to 6:00PM ET.
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, Kathy Wang-Hurst can be reached at 571-270-5371. 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.
/SAID M ELNOUBI/Examiner, Art Unit 2644
Prosecution Insights