6/DETAILED ACTION
This action is a response to an application filed on 6/10/24 in which claims 1-4, 6-11, 13-15, 17 and 19-24 are pending.
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) 1-4, 6, 7, 10, 11, 13 and 19-23 is/are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Yoo et al. (Pub. No.: 2021/0266763 A1), herein Yoo.
As to claim 1, Yoo teaches a method, performed by a first node comprising an Auto Encoder, AE-encode, for training the AE-encoder to provide encoded Channel State Information, CSI, the method comprising:
providing AE-encoder data to a second node comprising an AE-decoder and having access to channel data representing a communications channel between a first communications node and a second communications node, wherein the AE-encoder data including encoder output data computed with the AE-encoder based on the channel data (Yoo [0083] The UE (first node) trains the encoder 610 and decoder 620 and occasionally transmits the decoder coefficients to the base station (second node). At a higher frequency, the UE sends the outputs of the encoder 610 (e.g., channel state feedback or compressed output of the encoder 610) to the base station. As the UE moves from location to location, the weights of the decoder 620 may change. That is, when the channel environment changes, the decoder weights (e.g., coefficients) may change. Updated decoder coefficients can thus be fed back to the base station from the UE to reflect the changing environment)
receiving, from the second node, training assistance information (Yoo [0084] After receiving updated decoder/encoder coefficients from multiple UEs, the base station (second node) can learn common features from the feedback, and then make or propose to the UEs updates to the network coefficients); and
determining, based on the training assistance information, whether or not to continue the training by updating encoder parameters of the AE-encoder based on the received training assistance information (Yoo [0053] The instructions loaded into the general-purpose processor 302 may also include code to receive an updated CSI decoder and updated CSI encoder from the base station, for further training)
As to claim 14, Yoo teaches a method, performed by a second node comprising an Auto Encoder, AE,-decoder, for assisting in training an AE-encoder, comprised in a first node, to provide encoded Channel State Information, CSI, the method comprising:
receiving AE-encoder data from the first node, wherein the AE-encoder data including encoder output data (Yoo [0083] The UE (first node) trains the encoder 610 and decoder 620 and occasionally transmits the decoder coefficients to the base station (second node). At a higher frequency, the UE sends the outputs of the encoder 610 (e.g., channel state feedback or compressed output of the encoder 610) to the base station. As the UE moves from location to location, the weights of the decoder 620 may change. That is, when the channel environment changes, the decoder weights (e.g., coefficients) may change. Updated decoder coefficients can thus be fed back to the base station from the UE to reflect the changing environment)
and
providing training assistance information to the first node, the training assistance information is computed based on the encoder output data and based on channel data used by the AE-encoder in the first node to compute the encoder output data (Yoo [0084] After receiving updated decoder/encoder coefficients from multiple UEs, the base station (second node) can learn common features from the feedback, and then make or propose to the UEs updates to the network coefficients);
As to claim 21, Yoo teaches a first node, comprising an Auto Encoder, AE,- encoder, configured for training the AE-encoder to provide encoded Channel State Information, CSI, wherein the first node is being further configured to:
provide AE-encoder data to a second node comprising an AE-decoder and having access to channel data representing a communications channel between a first communications node and a second communications node, wherein the AE-encoder data includes including encoder output data computed with the AE-encoder based on the channel data (Yoo [0083] The UE (first node) trains the encoder 610 and decoder 620 and occasionally transmits the decoder coefficients to the base station (second node). At a higher frequency, the UE sends the outputs of the encoder 610 (e.g., channel state feedback or compressed output of the encoder 610) to the base station. As the UE moves from location to location, the weights of the decoder 620 may change. That is, when the channel environment changes, the decoder weights (e.g., coefficients) may change. Updated decoder coefficients can thus be fed back to the base station from the UE to reflect the changing environment)
receive, from the second node, training assistance information (Yoo [0084] After receiving updated decoder/encoder coefficients from multiple UEs, the base station (second node) can learn common features from the feedback, and then make or propose to the UEs updates to the network coefficients);
and
determine, based on the training assistance information, whether or not to continue the training by updating encoder parameters of the AE-encoder based on the received training assistance information (Yoo [0053] The instructions loaded into the general-purpose processor 302 may also include code to receive an updated CSI decoder and updated CSI encoder from the base station, for further training)
As to claim 23, Yoo teaches a second node, comprising an Auto Encoder, AE,- decoder , configured for assisting in training an AE-encoder comprised in a first node , to provide encoded Channel State Information, CSI, wherein the second node is being further configured to:
receive AE-encoder data from the first node, wherein the AE-encoder data includes including encoder output data (Yoo [0083] The UE (first node) trains the encoder 610 and decoder 620 and occasionally transmits the decoder coefficients to the base station (second node). At a higher frequency, the UE sends the outputs of the encoder 610 (e.g., channel state feedback or compressed output of the encoder 610) to the base station. As the UE moves from location to location, the weights of the decoder 620 may change. That is, when the channel environment changes, the decoder weights (e.g., coefficients) may change. Updated decoder coefficients can thus be fed back to the base station from the UE to reflect the changing environment)
and
provide training assistance information to the first node, the training assistance information is computed based on the encoder output data and based on channel data used by the AE-encoder in the first node to compute the encoder output data (Yoo [0084] After receiving updated decoder/encoder coefficients from multiple UEs, the base station (second node) can learn common features from the feedback, and then make or propose to the UEs updates to the network coefficients);
As to claim 2, Yoo teaches the method according to claim 1, further comprising: if it is determined to continue the training, updating the encoder parameters based on the received training assistance information (Yoo [0053] The instructions loaded into the general-purpose processor 302 may also include code to receive an updated CSI decoder and updated CSI encoder from the base station, for further training)
As to claim 3, Yoo teaches the method according to claim 1, further comprising: if it is determined to not continue the training, selecting latest updated encoder parameters of the AE-encoder as trained parameters for the AE-encoder which is configured to provide the encoded CSI, based on the trained parameters, from the first communications node to the second communications node in an operational phase of the AE-encoder in which operational phase the AE-encoder is comprised in the first communications node (Yoo [0080] The UE can encode the channel state feedback and transmit the encoded feedback over the air to the base station. The channel state feedback can be sent from the UE in accordance with timelines configured by radio resource control (RRC) signaling. Upon receiving the information, the base station feeds the received compressed channel state feedback values into the decoder to approximate the channel state feedback)
As to claim 4, Yoo teaches the method according to claim 1, the wherein the training assistance information comprises one or more of:
a gradient vector of a loss function computed by the second node with respect to a respective encoder parameter of the AE-encoder,
an indication of the loss value of the loss function,
an indication of whether or not the AE-encoder has achieved sufficient training performance on the channel data when used with the AE-decoder such that a pass criterion is fulfilled (Yoo [0098] As shown in FIG. 8, in some aspects, the process 800 may include receiving an updated CSI decoder and updated CSI encoder from the base station, for further training (block 850) and [0088] Subsets of the UEs may receive common layer weights that are associated with the other UEs of the subset. Referring to the previous example, new users entering the coffee shop where five other users are sitting may receive the common layer weights. By receiving the common layer weights, the subset of UEs can more efficiently learn decoder and encoder coefficients. That is, the base station can push the coefficients to the new user. The new user can start with those coefficients when training its neural network, to reduce the training process for the new UE. Another example of a new user in the coffee shop is a UE waking up from deep sleep or a UE receiving a new data burst)
As to claim 6, Yoo teaches the method according to claim 1, wherein determining whether or not to continue the training comprises determining whether or not a pass criterion of the loss value of the AE is fulfilled based on the received training assistance information (Yoo [0098] As shown in FIG. 8, in some aspects, the process 800 may include receiving an updated CSI decoder and updated CSI encoder from the base station, for further training (block 850) and [0088] Subsets of the UEs may receive common layer weights that are associated with the other UEs of the subset. Referring to the previous example, new users entering the coffee shop where five other users are sitting may receive the common layer weights. By receiving the common layer weights, the subset of UEs can more efficiently learn decoder and encoder coefficients. That is, the base station can push the coefficients to the new user. The new user can start with those coefficients when training its neural network, to reduce (determine whether or not a pass criterion of the loss value is fulfilled) the training process for the new UE. Another example of a new user in the coffee shop is a UE waking up from deep sleep or a UE receiving a new data burst)
As to claim 7, Yoo teaches the method according to claim 1, wherein the AE-encoder data further includes the channel data (Yoo [0083] The UE (first node) trains the encoder 610 and decoder 620 and occasionally transmits the decoder coefficients to the base station (second node). At a higher frequency, the UE sends the outputs of the encoder 610 (e.g., channel state feedback or compressed output of the encoder 610) to the base station. As the UE moves from location to location, the weights of the decoder 620 may change. That is, when the channel environment changes, the decoder weights (e.g., coefficients) may change. Updated decoder coefficients can thus be fed back to the base station from the UE to reflect the changing environment)
As to claim 10, Yoo teaches the method according to claim 1, wherein the implementation of the AE-decoder is not known to the first node (Yoo [0087] That is, after the base station transmits the initial neural network structure (not known to UE (first node)), the base station can later identify common layers and transmit common layer weights to multiple UEs, such as a UE subset. Subsets may be defined as neighbors having common weights, for example, because of a common environment)
As to claim 11, Yoo teaches the method according to claim 1, further comprising obtaining the channel data from the second node, or a third node comprising a channel data base (Yoo [0084] After receiving updated decoder/encoder coefficients from multiple UEs, the base station (second node) can learn common features from the feedback, and then make or propose to the UEs updates to the network coefficients);
Claim 19 is rejected for the same reasons stated in claim 11.
As to claim 13, Yoo teaches the method according to claim 1, wherein the AE-encoder is trained to provide encoded CSI from the first communications node to the second communications node over the communications channel in the communications network, wherein the CSI is provided in the operational phase of the AE-encoder (Yoo [0083] The UE (first node) trains the encoder 610 and decoder 620 and occasionally transmits the decoder coefficients to the base station (second node). At a higher frequency, the UE sends the outputs of the encoder 610 (e.g., channel state feedback or compressed output of the encoder 610) to the base station. As the UE moves from location to location, the weights of the decoder 620 may change. That is, when the channel environment changes, the decoder weights (e.g., coefficients) may change. Updated decoder coefficients can thus be fed back to the base station from the UE to reflect the changing environment)
As to claim 20, Yoo teaches the method method according to claim 14, further comprising obtaining the channel data from a channel data database which is comprised in or co-located with the second node (Yoo [0084] After receiving updated decoder/encoder coefficients from multiple UEs, the base station (second node) can learn common features from the feedback, and then make or propose to the UEs updates to the network coefficients);
As to claim 22, Yoo teaches the method first node according to claim 21, further configured to perform the method if it is determined to continue the training, update the encoder parameters based on the received training assistance information (Yoo [0084] After receiving updated decoder/encoder coefficients from multiple UEs, the base station (second node) can learn common features from the feedback, and then make or propose to the UEs updates to the network coefficients);
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(s) 8, 15, 17 and 24 is/are rejected under 35 U.S.C. 103 as being unpatentable over Yoo and Chen et al. (Pub. No.: 2023/0084164 A1), herein Chen.
As to claim 8, Yoo teaches the method according to claim 1,
Yoo does not teach
further comprising: providing the second node
with meta data associated with the AE, the meta data comprises an indication of any one or more of:
an AE-encoder type or preferred AE-decoder type for the AE-encoder
a preferred loss function to use among a set of predefined loss functions;
a number of AE nodes in the output layer (Y) of the AE-encoder an indication to a reference AE-decoder architecture that the AE-encoder has been pre-trained with;
a preferred method for data normalization; or
a method for quantizing AE-encoder outputs.
However Chen does teach
further comprising: providing the second node
with meta data associated with the AE, the meta data comprises an indication of any one or more of:
an AE-encoder type or preferred AE-decoder type for the AE-encoder (Chen [0084] In baseline federated learning, the base station maintains an encoder/decoder NN for each UE. The UE downloads the model maintained at the base station. Additionally, the UE trains and updates the model based on the channel/interference realizations observed at the UE. The UE then sends the encoder and decoder networks to the gNB. The gNB then aggregates the models from multiple UEs and generates new models for the UEs. The process is then repeated)
a preferred loss function to use among a set of predefined loss functions;
a number of AE nodes in the output layer (Y) of the AE-encoder an indication to a reference AE-decoder architecture that the AE-encoder has been pre-trained with;
a preferred method for data normalization; or
a method for quantizing AE-encoder outputs.
It would have been obvious before the effective filing date of the claimed invention to combine the teachings of Yoo and Chen, because Chen teaches us [0092] According to further aspects of the present disclosure, a base station indicates to UE(s) the different CSF configurations with different neural network frameworks through an RRC message. The message may include a number of neural network pairs to be trained at the UE, and which pair to use for a specific CSI quantity feedback instance. The message can also indicate a neural network architecture with hyperparameters used for CSF training for each CSI learning instance.
Claim 17 is rejected for the same reasons stated in claim 8.
As to claim 15, the combination of Yoo and Chen teach the method according to claim 14, wherein the training assistance information comprises one or more of:
a gradient vector of a loss function computed by the second node with respect to a respective encoder parameter of the AE-encoder,
a loss value of the loss function (Chen [0087] Different hyperparameters may be configured for different encoder/decoder neural network configurations. The hyperparameters for different UEs can be based on desired feedback accuracy, feedback overhead, UE computational capability, and base station antenna configuration. The different hyperparameters may indicate a number of layers in the neural network, the type of layer (e.g., convolutional layer or fully connection), a number of hidden units for each layer/dimension of the kernel (e.g., the size of the kernel) and/or a loss function/loss metric of the neural network. For example, a different loss metric can be pre-defined and configured for different CSI quantities (e.g., RI, CQI, interference, etc.))
an indication of the loss (Chenn [0087] Different hyperparameters may be configured for different encoder/decoder neural network configurations. The hyperparameters for different UEs can be based on desired feedback accuracy, feedback overhead, UE computational capability, and base station antenna configuration. The different hyperparameters may indicate a number of layers in the neural network, the type of layer (e.g., convolutional layer or fully connection), a number of hidden units for each layer/dimension of the kernel (e.g., the size of the kernel) and/or a loss function/loss metric of the neural network. For example, a different loss metric can be pre-defined and configured for different CSI quantities (e.g., RI, CQI, interference, etc.)
an indication of whether or not the AE-encoder has achieved sufficient training performance on the shared channel data when used with the AE-decoder such that a pass criterion is fulfilled,
wherein the loss quantifies a reconstruction error of the shared channel data.
It would have been obvious before the effective filing date of the claimed invention to combine the teachings of Yoo and Chen for the same reasons stated in claim 8.
Claim 24 is rejected for the same reasons stated in claim 15.
Allowable Subject Matter
Claim 9 is 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
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AYANAH S GEORGE whose telephone number is (571)272-8880. The examiner can normally be reached 7:00 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, Hassan Phillips can be reached at 572-272-3940. 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.
AYANAH S. GEORGE
Primary Examiner
Art Unit 2467
/AYANAH S GEORGE/Primary Examiner, Art Unit 2467
Prosecution Insights