DETAILED ACTION
1. This office action is a response to the Application/Control Number: 18/919,398 filed on 10/17/2024.
Claims Status
2. This office action is based upon claims received on 10/17/2024, which replace all prior or other submitted versions of the claims.
-Claims 1-20 are pending.
-Claims 1-5, 7-14, 16-20 are rejected.
-Claims 6, 15 are objected.
Notice of Pre-AIA or AIA Status
3. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Priority
4. Applicant’s claim for the benefit of a prior-filed application under 35 U.S.C. 119(e) or under 35 U.S.C. 120, 121, 365(c), or 386(c) is acknowledged.
Claim Rejections - 35 USC § 112
5. The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
6. Claim 4, 13 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor, or for pre-AIA the applicant regards as the invention.
A. Claim 4 (i.e. which depends from claim 1) and Claim 13 (i.e. which depends from claim 10) both recites terms “the dependency order for compression” after a preceding recitation of “dependency order for compression” in Claim 1 and claim 10, where the office action presents a lack of clarity as to where a second recitation of “compression” in Claim 4 and claim 13 after a first recitation of “compression” in claim 1 and claim 10 finds antecedent basis, i.e. whether the first recitation of “compression” in claim 1 and claim 10 serves as the antecedent basis for Claim 4 and claim 13, or whether the second recitation “compression” in claim 4 and claim 13 refers to a separate instance of “compression” different from claim 1 and claim 10.
Examiner interprets the subject claims listed as best possible. Applicant is requested and required to appropriately address and clarify as applicable to reflect applicant’s intent and objective for the claim language noted.
Claim Rejections - 35 USC § 103
7. 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.
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 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.
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.
8. Claims 1-5, 7, 10-14, 16, 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over ZHANG et al. (US 20250183968 A1) i.e. “ZHANG”, in view of LIEN (US 20260081660 A1) i.e. “LIEN”.
Regarding Claim 1. ZHANG teaches: A first wireless device (ZHANG – FIG. 5 & ¶0090 […] 501: the network device informs the terminal equipment of an AI/ML model that may be used, and for allocations of a specific number of bits;
NOTE-DISCLOSURE & TEACHING: Per FIG. 5 & ¶0090 i.e. the terminal equipment reads on: A first wireless device),
comprising: one or more memories storing processor-executable code; and one or more processors coupled with the one or more memories and individually or(note: limitations separated by a recitation “or” are interpreted as presented in the alternative and not required together i.e. for the purposes of patentable weight) collectively operable to execute the code to cause the first wireless device (ZHANG – FIG. 5, FIG. 12 & ¶0327 […] the memory 1202 stores data and programs, and is coupled to the processor 1201; ¶0328 […] processor 1201 may be configured to execute a program to implement the method;
NOTE-DISCLOSURE & TEACHING: Per FIG. 5, FIG. 12 & ¶0327 i.e. the memory 1202 stores data and programs, and is coupled to the processor 1201 reads on: comprising: one or more memories storing processor-executable code; and one or more processors coupled with the one or more memories, where furthermore per ¶0327 i.e. the memory 1202 stores data and programs and per ¶0328 i.e. processor 1201 may be configured to execute a program reads on: and individually or collectively operable to execute the code , Per ¶0328 i.e. to implement the method reads on: to cause the first wireless device ):
to communicate an indication of a dependency order for compression of a set of vectors (ZHANG FIG. 4 & ¶0058 […] 401 a terminal equipment receives first information transmitted by a network device, the first information indicating the terminal equipment to generate and feedback channel state information; ¶0092 […] 501 […] and via the first information, configures or indicates the terminal equipment to feedback CSI of at least two layers of the CSI of N layers (N≥2) by using unequal numbers of bits, and the number of feedback bits of CSI of each layer is performed according to the Standard Text; ¶0093 […] operation 501, the network device may inform the terminal equipment of an available AI/ML model via the first information; ¶0095 […] a pre-agreed item, i.e., the first rule (known to both the terminal equipment and the network device, and containing the standard document) includes: a serial number of an AI/ML model; a criterion for selecting an AI/ML model; a feedback order of an CSI vector; and how does a network device read CSI. Specific steps are listed as follows: ¶0096 S1: the network device configures four available AI/ML models for the terminal equipment, arranges the number of output bits of these four AI/ML models in a descending order, and gives serial numbers 1, 2, 3, 4; ¶0097 […] S2: the network device transmits a CSI-RS; ¶0098 […] S3: the terminal equipment receives the CSI-RS, measures a spatial channel, calculates a rank of a spatial channel matrix to be 2, and calculates a singular value of the spatial channel matrix to be σ.sub.k, k=1,2, and there is σ.sub.1>σ.sub.2>0; ¶0099 […] S4: for singular vectors corresponding to the above two singular values, the terminal equipment selects two models with the largest number of feedback bits among the four AI/ML models, namely model 1 and model 2, according to the standard regulations, and assigns model 1 to a singular vector corresponding to σ.sub.2, and assigns model 2 to a singular vector corresponding to σ.sub.1; ¶0100 […] S5: the terminal equipment compresses the two singular vectors by using a determined AI/ML model; ¶0235 […] the network device may further receive indication information from the terminal equipment, the indication information indicating a serial number or index or identifier of an AI/ML model used by the channel state information, the network device may perform post-processing on the received channel state information according to the serial number or index or identifier of the AI/ML model used by the channel state information […] ;
NOTE-DISCLOSURE & TEACHING: per FIG. 4 & ¶0058 i.e. 401 a terminal equipment receives first information and per ¶0092 i.e. 501 i.e. via the first information i.e. according to the Standard Text and per ¶0093 i.e. inform the terminal equipment of an available AI/ML model via the first information reads on: to communicate an indication and furthermore per ¶0235 i.e. the network device may further receive indication information from the terminal equipment, the indication information indicating a serial number or index or identifier of an AI/ML model used also reads on: to communicate an indication according to ¶0092 i.e. 501 i.e. via the first information i.e. according to the Standard Text and per ¶0095 i.e. standard document includes: a serial number of an AI/ML model; a criterion for selecting an AI/ML model; a feedback order of an CSI vector; and how does a network device read CSI. Per ¶0095 i.e. the standard document) includes: a serial number of an AI/ML model; As communicated per ¶0092 the first information i.e. according to the Standard Text and per ¶0095 i.e. the first rule (known to both the terminal equipment and the network device, and containing the standard document) which includes i.e. a criterion for selecting an AI/ML model; a feedback order of an CSI vector; and how does a network device read CSI reads on: an indication of a dependency order. Per ¶0095 i.e. a feedback order of i.e. an CSI vector and per ¶0099 i.e. a singular vector corresponding to σ.sub.2, and assigns model 2 to a singular vector corresponding to σ.sub.1, where per ¶0100 the terminal i.e. compresses the two singular vectors by using a determined AI/ML model reads on: for compression of a set of vectors),
the dependency order being associated with a compression sequence for the set of vectors (ZHANG FIG. 4 & ¶0059 402 […] the terminal equipment generates channel state information of N layers, wherein N≥2 and channel state information of at least two layers of the channel state information of N layers is indicated by unequal numbers of bits; ¶0095 See above; ¶0096 See above; ¶0097 See above; ¶0098 See above; ¶0099 See above; ¶0100 See above; ¶0101 […] S6: the terminal equipment feeds back the two compressed vectors to the network device in an order of σ.sub.1>σ.sub.2; ¶0102 […] S7: according to the received compressed vectors, the network device selects a reconstruction part of an appropriate AI/ML model for decompression according to the provisions of the Standard Text, and generates a precoding matrix;
NOTE-DISCLOSURE & TEACHING: Per ¶0095 i.e. a criterion for selecting an AI/ML model; a feedback order of an CSI vector; and how does a network device read CSI reads on: the dependency order, where per ¶0100 i.e. S5: the terminal equipment compresses the two singular vectors by using a determined AI/ML model; and per ¶0101 S6: the terminal equipment feeds back the two compressed vectors to the network device in an order of σ.sub.1>σ.sub.2 i.e. compresses the two singular vectors by using a determined AI/ML model, per ¶0095 according to i.e. a feedback order of an CSI vector and i.e. feeds back the i.e. two compressed vectors to the network device in an order of σ.sub.1>σ.sub.2 reads on: being associated with a compression sequence associated with compression. Furthermore, per ¶0100 i.e. compresses i.e. the two singular vectors by using a determined AI/ML model reads on: for the set of vectors);
encode the set of vectors based at least in part on the dependency order and the compression sequence to generate a set of compressed vectors respectively corresponding to the set of vectors (ZHANG FIG. 4, FIG. 5 & ¶0095 See above; ¶0096 See above; ¶0097 See above; ¶0098 See above; ¶0099 See above; ¶0100 See above; ¶0101 See above;
NOTE-DISCLOSURE & TEACHING: Per ¶0100 S5: the terminal equipment compresses the two singular vectors by using a determined AI/ML model reads on: encode the set of vectors. Furthermore per ¶0100 i.e. using a determined AI/ML model where per ¶0095 terminal has indication of i.e. a criterion for selecting an AI/ML model; a feedback order of an CSI vector; and how does a network device read CSI reads on: based at least in part on the dependency order associated with selection of the AI/AML, and then i.e. a feedback order of an CSI vector. Furthermore per ¶0095 i.e. a feedback order of an CSI vector and how does a network device read CSI, resulting in per ¶0100 i.e. the terminal equipment feeds back the two compressed vectors to the network device in an order of σ.sub.1>σ.sub.2 reads on: and the compression sequence to generate a set of compressed vectors respectively. Furthermore, per ¶0100 i.e. compresses i.e. the two singular vectors by using a determined AI/ML model reads on: corresponding to the set of vectors);
and transmit the set of compressed vectors (ZHANG FIG. 4, FIG. 5 & ¶0060 […] 403 [...] terminal equipment transmits the channel state information of N layers to the network device; ¶0094 […] the terminal equipment may feedback CSI of two or more layers to the network device; ¶0101 See above;
NOTE-DISCLOSURE & TEACHING: Per ¶0060 Step 403 & FIG. 5 step 502 ¶0094 i.e. the terminal equipment may feedback CSI of two or more layers reads on and transmit and per ¶0101 i.e. S6: the terminal equipment feeds back i.e. the two compressed vectors to the network device reads on: the set of compressed vectors in an order of σ.sub.1>σ.sub.2).
While ZHANG teaches dependency order as noted above and described Per ¶0095 associates with an order of i.e. a criterion for selecting an AI/ML model; a feedback order of an CSI vector; and how does a network device read CSI and which furthermore associates per ¶0095 with i.e. a feedback order of an CSI vector and with per ¶0100 i.e. S5: the terminal equipment compresses the two singular vectors by using a determined AI/ML model; and per ¶0101 S6: the terminal equipment feeds back the two compressed vectors to the network device in an order of σ.sub.1>σ.sub.2 i.e. compression sequence to generate a set of compressed vectors, assuming arguendo i.e. ZHANG implies dependency, and ZHANG does not appear to explicitly teach dependency, and therefore i.e.,
ZHANG does not appear to explicitly teach or strongly suggest (i.e. Zhang implies i.e. see italicized portions of claim limitations): dependency order;
LIEN teaches: communicate an indication of a dependency order for compression of a set of vectors (LIEN FIG. 4, FIG. 6 & ¶0037 […] an example of a sandwich structure of an autoencoder, in which the structures of the encoder and decoder are symmetric. In the sandwich structure, the input layer 410 and the output layer 420 are positioned on the outermost layers, while the hidden layers 430 are sandwiched in between […] First, the numbers of layers in the encoder and in the decoder may be the same, with the exception that there may be one additional layer known as the code or bottleneck layer 440 in the encoder. Second, the number of neural nodes in the input layer 410 of the encoder may be the same as the number of neural nodes in the output layer 420 of the decoder. Third, the number of encoder hidden layers 430 and decoder hidden layers 435 (i.e., a layer may be a hidden layer if the layer may not be an input layer 410, an output layer 420 or a code/bottleneck layer 440) in the encoder and in the decoder may be the same […] the vector of weights/parameters between the input layer 410 and the first hidden layer 450 in the encoder may be the transpose of the vector of weights/parameters between the output layer 420 and the first hidden layer 480 in the decoder. The vector of weights/parameters between the first hidden layer 450 and the second hidden layer 460 in the encoder may be the transpose of the vector of weights/parameters between the first hidden layer 480 and the second hidden layer 470 in the decoder, and so on. As shown in FIG. 4, W.sub.1.sup.T is the transpose of W.sub.1, W.sub.2.sup.T is the transpose of W.sub.2, and so on […] ; ¶0048 […] example of the implementation of a first alternative to the second stage is illustrated where the UE may provide updated weights/parameters to the base station in the implementation for CSI compression. The first alternative to the second stage may involve several steps. First, a base station 620 (i.e., gNB) may send reference signal RS 630 in one or more downlink transmissions. After receiving reference signal RS 630, UE 610 may estimate the channel condition H'. The AE encoder 650 in UE 610 then may reduce the dimension of the estimated channel condition to generate low dimensional information ; ¶0051 […] the UE may update the weights/parameters of the AE encoder in the UE and the AE decoder in the base station (using the autoencoder in the UE), and the UE may communicate the updated weights/parameters to the base station. A base station may allocate radio resources for the UE to upload the updated weights/parameters. After receiving the updated weights/parameters from the UE, the base station may further communicate or confirm to the UE the information including the adopted weights/parameters;
NOTE-DISCLOSURE & TEACHING: Per FIG. 6 & ¶0051 i.e. the UE may update the weights/parameters of the AE encoder in the UE and the AE decoder in the base station (using the autoencoder in the UE), and i.e. the UE may communicate and i.e. After receiving the updated weights/parameters from the UE, the base station may further communicate or confirm to the UE reads on: communicate an indication, furthermore per 0051 i.e. UE may communicate the updated weights/parameters to the base station and i.e. the base station may further communicate or confirm to the UE the information including i.e. the adopted weights/parameters and i.e. the updated weights/parameters reads on: of a dependency order for the layers depicted in the encoder and decoder. Per ¶0048 i.e. where the UE may provide updated weights/parameters to the base station in the implementation for CSI compression and i.e. a base station 620 (i.e., gNB) may send reference signal RS 630 in one or more downlink transmissions. After receiving reference signal RS 630, UE 610 may estimate the channel condition H'. The AE encoder 650 in UE 610 then may reduce the dimension of the estimated channel condition to generate low dimensional information i.e. RS 630 in one or more downlink transmissions to generate i.e. the channel condition H', where according to weights/parameters associated with layers i.e. reduce the dimension of the estimated channel condition to generate low dimensional information reads on: for compression of a set of vectors),
the dependency order being associated with a compression sequence for the set of vectors (LEIN FIG. 4 & FIG. 6 ¶0037 See above; ¶0048 See above; ¶0051 See above;
NOTE-DISCLOSURE & TEACHING: ¶0051 i.e. i.e. UE may communicate the updated weights/parameters to the base station and i.e. the base station may further communicate or confirm to the UE the information including i.e. the adopted weights/parameters and i.e. the updated weights/parameters reads on: the dependency order, and corresponding ¶0048 per FIG. 6 depicting weights /parameters for AE encoder and decoder and AE encoder/decoder structure analogous to FIG. 4 where FIG. 6 depicts AE encoder to input the channel condition H' i.e. reduce to generate low dimensional information based upon the weights and layers within the encoder depicted in FIG. 4 reads on: being associated with a compression sequence, where per ¶0048 the AE encoder associates with i.e. implementation for CSI compression i.e. RS 630 in one or more downlink transmissions to generate i.e. the channel condition H' i.e. reduce the dimension of the estimated channel condition to generate low dimensional information reads on: for the set of 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 ZHANG with teachings of LIEN, since LIEN address a challenge existing in precisely describing a channel condition when the dimension of the channel condition is high may require a high number of bits, by an autoencoder used to reduce the dimension of the CSI (LIEN - ¶0004; ¶0032; ¶0048).
Regarding Claim 2. ZHANG in view of LIEN teaches: The first wireless device of claim 1,
furthermore ZHANG teaches: wherein, to communicate the indication of the dependency order, the one or more processors are individually or collectively operable to execute the code to cause the first wireless device to: transmit the indication of the dependency order to a second wireless device in a message with the set of compressed vectors (ZHANG – FIG. 5 & ¶0234 See above;
NOTE-DISCLOSURE & TEACHING: per ¶0234 i.e. the network device may further receive indication information from the terminal equipment, the indication information indicating a serial number or index or identifier of an AI/ML model used by the channel state information, the network device may perform post-processing on the received channel state information according to the serial number or index or identifier of the AI/ML model used by the channel state information, and recovers the post-processed channel state information i.e. the network device may further receive indication information from the terminal equipment reads on: wherein, to communicate the indication of the dependency order, the one or more processors are individually or collectively operable to execute the code to cause the first wireless device to: transmit the indication of the dependency order to a second wireless device i.e. the network device may perform post-processing on the received channel state information according to the serial number or index or identifier of the AI/ML model used by the channel state information reads on: in a message with the set of compressed vectors )
or (note: limitations separated by a recitation “or” are interpreted as presented in the alternative and not required together i.e. for the purposes of patentable weight)
in a message separate from the set of compressed vectors that is transmitted with a same periodicity or a different periodicity as the set of compressed vectors (note: limitations separated by a recitation “or” are interpreted as presented in the alternative and not required together i.e. for the purposes of patentable weight).
furthermore LIEN also teaches: transmit the indication of the dependency order to a second wireless device in a message (LEIN FIG. 4 & FIG. 6 ¶0037 See above; ¶0048 See above; ¶0051 See above;
NOTE-DISCLOSURE & TEACHING: ¶0051 i.e. the UE may update the weights/parameters of the AE encoder in the UE and the AE decoder in the base station (using the autoencoder in the UE), and the UE may communicate the updated weights/parameters reads on: transmit the indication of the dependency order i.e. to the base station reads on: to a second wireless device in a message)
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 ZHANG in view of LIEN, further with the teachings of LIEN, since LIEN address a challenge existing in precisely describing a channel condition when the dimension of the channel condition is high may require a high number of bits, by an autoencoder used to reduce the dimension of the CSI (LIEN - ¶0004; ¶0032; ¶0048).
Regarding Claim 3. ZHANG in view of LIEN teaches: The first wireless device of claim 1,
furthermore ZHANG teaches: wherein, to communicate the indication of the dependency order, the one or more processors are individually or collectively operable to execute the code to cause the first wireless device to: receive the indication of the dependency order from a second wireless device for configuring the first wireless device with the dependency order (ZHANG FIG. 4 & ¶0058 See claim 1; ¶0092 See claim 1; ¶0093 See claim 1; ¶0095 See claim 1¶0096 See claim 1; ¶0097 See claim 1; ¶0098 See claim 1; ¶0099 See claim 1; ¶0100 See claim 1; ¶0235 See claim 1;
NOTE-DISCLOSURE & TEACHING: per FIG. 4 & ¶0058 i.e. 401 a terminal equipment receives first information and per ¶0092 i.e. 501 i.e. via the first information i.e. according to the Standard Text and per ¶0093 i.e. inform the terminal equipment of an available AI/ML model via the first information reads on: wherein, to communicate the indication of the dependency order, the one or more processors are individually or collectively operable to execute the code to cause the first wireless device to: receive the indication according to ¶0092 i.e. 501 i.e. via the first information i.e. according to the Standard Text and per ¶0095 i.e. standard document includes: a serial number of an AI/ML model; a criterion for selecting an AI/ML model; a feedback order of an CSI vector; and how does a network device read CSI. Per ¶0095 i.e. the standard document) includes: a serial number of an AI/ML model; i.e. a criterion for selecting an AI/ML model; a feedback order of an CSI vector; and how does a network device read CSI reads on: an indication of a dependency order. Per ¶0092 i.e. 501 i.e. and via the first information FIG. 5 step 501 i.e. network device informs the terminal device reads on: from a second wireless device. Furthermore per FIG. 5 network device information the terminal equipment of an AI/ML model that may be used for allocation of a specific number of bits reads on: for configuring the first wireless device, where and i.e. ¶0095 i.e. the standard document) includes: a serial number of an AI/ML model; i.e. a criterion for selecting an AI/ML model; a feedback order of an CSI vector reads on: for configuring the first wireless device with the dependency order where subsequently per ¶0100 i.e. the terminal equipment feeds back the two compressed vectors to the network device in an order of σ.sub.1>σ.sub.2).
furthermore LIEN also teaches: wherein, to communicate the indication of the dependency order, the one or more processors are individually or collectively operable to execute the code to cause the first wireless device to: receive the indication of the dependency order from a second wireless device (LEIN FIG. 4 & FIG. 6 ¶0037 See above; ¶0048 See above; ¶0051 See above;
NOTE-DISCLOSURE & TEACHING: ¶0051 i.e. the base station may further communicate or confirm to the UE the information including i.e. the adopted weights/parameters reads on: wherein, to communicate the indication of the dependency order and i.e. the adopted weights/parameters reads on: the dependency order, i.e. the base station may further communicate i.e. the adopted weights/parameters reads on: the one or more processors are individually or collectively operable to execute the code to cause the first wireless device to: receive the indication of the dependency order i.e. the base station may further communicate reads on: from a second wireless device)
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 ZHANG in view of LIEN, further with the teachings of LIEN, since LIEN address a challenge existing in precisely describing a channel condition when the dimension of the channel condition is high may require a high number of bits, by an autoencoder used to reduce the dimension of the CSI (LIEN - ¶0004; ¶0032; ¶0048).
Regarding Claim 4. ZHANG in view of LIEN teaches: The first wireless device of claim 1,
Furthermore LIEN teaches: wherein the indication of the dependency order for compression indicates at least one operational dependency in a set of encoder layers of the first wireless device (LEIN FIG. 4 & FIG. 6 ¶0037 See above; ¶0048 See above; ¶0051 See above;
NOTE-DISCLOSURE & TEACHING: ¶0051 i.e. UE may communicate the updated weights/parameters to the base station and i.e. the base station may further communicate or confirm to the UE the information including i.e. the adopted weights/parameters reads on: wherein the indication and i.e. the updated weights/parameters and i.e. the adopted weights/parameters reads on: the dependency order, and corresponding ¶0048 per FIG. 6 depicting weights /parameters for AE encoder and decoder and AE encoder/decoder structure analogous to FIG. 4 where FIG. 6 depicts AE encoder to input the channel condition H' i.e. reduce to generate low dimensional information based upon the weights and layers within the encoder depicted in FIG. 4 reads on: for compression, where per ¶0037 i.e. As shown in FIG. 4, W.sub.1.sup.T is the transpose of W.sub.1, W.sub.2.sup.T is the transpose of W.sub.2, and so on and FIG. 4 depicts encoder layers in sequence and symmetric order within AE encoder/decoder structure associated with weights for operation of the encoder layers within AE as depicted in FIG. 6 i.e. W.sub.1 and W.sub.2 in sequence as applied to the encoder side reads on: at least one operational dependency in a set of encoder layers , where per ¶0051 i.e. UE may communicate the updated weights/parameters reads on: of the first wireless device i.e. to the base station and i.e. the base station may further communicate or confirm to the UE the information including the adopted weights/parameters)
or (note: limitations separated by a recitation “or” are interpreted as presented in the alternative and not required together i.e. for the purposes of patentable weight)
at least one operational dependency in a set of decoder layers of a second wireless device (note: limitations separated by a recitation “or” are interpreted as presented in the alternative and not required together i.e. for the purposes of patentable weight).
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 ZHANG in view of LIEN, further with the teachings of LIEN, since LIEN address a challenge existing in precisely describing a channel condition when the dimension of the channel condition is high may require a high number of bits, by an autoencoder used to reduce the dimension of the CSI (LIEN - ¶0004; ¶0032; ¶0048).
Regarding Claim 5. ZHANG in view of LIEN teaches: The first wireless device of claim 1,
furthermore LIEN teaches: wherein, to encode the set of vectors, the one or more processors are individually or collectively operable to execute the code to cause the first wireless device to: encode the set of vectors using a set of encoder layers according to the dependency order, wherein each encoder layer of the set of encoder layers, after an initial encoder layer, is dependent on one or more compressed vectors respectively generated by one or more previous encoder layers of the set of encoder layers in the dependency order (LIEN FIG. 4 & ¶0037 See claim 1;
NOTE-DISCLOSURE & TEACHING: FIG. 4 depicts AE with encoder comprising layers 410, 430, 460 associated with weights W1, W2, W3 utilized per ¶0048 the AE encoder associates with i.e. implementation for CSI compression i.e. RS 630 in one or more downlink transmissions to generate i.e. the channel condition H' i.e. reduce the dimension of the estimated channel condition to generate low dimensional information reads on: wherein, to encode the set of vectors, the one or more processors are individually or collectively operable to execute the code to cause the first wireless device to: encode the set of vectors using a set of encoder layers, where per FIG. 4 depicting the compression or reduction direction of X i.e. weights X-> W1-> W2 ->W3 associated with the hidden layers of the encoder reads on: according to the dependency order , where per FIG. 4 as depicted i.e. weights X-> W1-> W2 ->W3 associated with the hidden layers of the encoder reads on: wherein each encoder layer of the set of encoder layers, after an initial encoder layer, is dependent on one or more compressed vectors respectively generated by one or more previous encoder layers of the set of encoder layers in the dependency order).
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 ZHANG in view of LIEN, further with the teachings of LIEN, since LIEN address a challenge existing in precisely describing a channel condition when the dimension of the channel condition is high may require a high number of bits, by an autoencoder used to reduce the dimension of the CSI (LIEN - ¶0004; ¶0032; ¶0048).
Regarding Claim 7. ZHANG in view of LIEN teaches: The first wireless device of claim 1,
furthermore ZHANG teaches: wherein, to encode the set of vectors, the one or more processors are individually or collectively operable to execute the code to cause the first wireless device to: encode each vector of the set of vectors using a respective neural network layer of a set of neural network layers (ZHANG - ¶0099 See claim 1; ¶0100 see claim 1;
NOTE-DISCLOSURE & TEACHING: per ¶0099 i.e. S4: for singular vectors corresponding to the above two singular values, the terminal equipment selects two models with the largest number of feedback bits among the four AI/ML models, namely model 1 and model 2 according to the standard regulations, and assigns model 1 to a singular vector corresponding to σ.sub.2, and assigns model 2 to a singular vector corresponding to σ.sub.1 and per ¶0100 i.e. S5: the terminal equipment compresses the two singular vectors by using a determined AI/ML model reads on: wherein, to encode the set of vectors, the one or more processors are individually or collectively operable to execute the code to cause the first wireless device to: encode each vector of the set of vectors using a respective neural network layer and per ¶0099 i.e. among the four AI/ML models, namely model 1 and model 2 according to the standard regulations, and assigns model 1 to a singular vector corresponding to σ.sub.2, and assigns model 2 to a singular vector corresponding to σ.sub.1 reads on: of a set of neural network layers)
Regarding Claim 10. ZHANG teaches: A second wireless device (ZHANG – FIG. 5 & ¶0090 […] 501: the network device informs the terminal equipment of an AI/ML model that may be used, and for allocations of a specific number of bits;
NOTE-DISCLOSURE & TEACHING: Per FIG. 5 & ¶0090 i.e. the network device reads on: A second wireless device),
comprising: one or more memories storing processor-executable code; and one or more processors coupled with the one or more memories and individually or (note: limitations separated by a recitation “or” are interpreted as presented in the alternative and not required together i.e. for the purposes of patentable weight) collectively operable to execute the code to cause the second wireless device (ZHANG – FIG. 5, FIG. 13 & ¶0331 [..] the memory 1302 is coupled to the processor 1301. The memory 1302 may store various data; moreover, also stores a program for information processing, and executes the program under the control of the central processor 1301; ¶0334 […] a computer readable program, wherein when a terminal equipment executes the program, the program enables a computer to execute the method;
NOTE-DISCLOSURE & TEACHING: Per FIG. 5, FIG. 12 & i.e. The memory 1302 may store various data; moreover, also stores a program for information processing reads on: comprising: one or more memories storing processor-executable code; ¶0331 i.e. the memory 1302 is coupled to the processor 1301 reads on: and one or more processors coupled with the one or more memories, where furthermore per ¶0331 i.e. The memory 1302 may store various data; moreover, also stores a program for information processing, and executes the program under the control of the central processor 1301 reads on: and individually or collectively operable to execute the code, Per ¶0334 i.e. a computer readable program, wherein when a terminal equipment executes the program, the program enables a computer to execute the method reads on: to cause the first wireless device )
(See the rejection of Claim 1, Claim 10 recites features in conjunction with a second wireless device that are similar, parallel and reciprocal to the features of Claim 1 in conjunction with a first wireless device, where the first wireless device for example associates with “encode the set of vectors” and “and transmit the set of compressed vectors” and reciprocally the second wireless device associates with “receive a set of compressed vectors” and “and decode the set of compressed vectors”. The rationale for the rejection of Claim 1 applies similarly to Claim 10. Where applicable, minor differences between claims are noted as appropriate)
to: communicate an indication of a dependency order for compression of a set of vectors, the dependency order being associated with a compression sequence for the set of vectors(See the rejection of Claim 1, Claim 10 recites features in conjunction with a second wireless device that are similar, parallel and reciprocal to the features of Claim 1 in conjunction with a first wireless device, where the first wireless device for example associates with “encode the set of vectors” and “and transmit the set of compressed vectors” and reciprocally the second wireless device associates with “receive a set of compressed vectors” and “and decode the set of compressed vectors”. The rationale for the rejection of Claim 1 applies similarly to Claim 10. Where applicable, minor differences between claims are noted as appropriate);
receive a set of compressed vectors that is based at least in part on the set of vectors (ZHANG FIG. 4, FIG. 5 & ¶0060 See claim 1; ¶0094 See claim 1; ¶0101 See Claim 1;
NOTE-DISCLOSURE & TEACHING: Per ¶0060 Step 403 & FIG. 5 step 502 ¶0094 i.e. the terminal equipment may feedback CSI of two or more layers reads on: receive and per ¶0101 i.e. S6: the terminal equipment feeds back i.e. the two compressed vectors to the network device reads on: a set of compressed vectors that is based at least in part on the set of vectors in an order of σ.sub.1>σ.sub.2 and per ¶0095 i.e. a feedback order of an CSI vector);
and decode the set of compressed vectors based at least in part on the dependency order and the compression sequence to generate a set of decompressed vectors respectively corresponding to the set of vectors (ZHANG FIG. 4 & ¶0059 See claim 1; ¶0095 See claim 1; ¶0096 See claim 1; ¶0097 See claim 1; ¶0098 See claim 1; ¶0099 See claim 1; ¶0100 See claim 1; ¶0101 See claim 1; ¶0102 See claim 1;
NOTE-DISCLOSURE & TEACHING: per ¶0102 i.e. according to the received compressed vectors, the network device selects i.e. a reconstruction part of an appropriate AI/ML model for decompression reads on: and decode the set of compressed vectors per ¶0102 i.e. according to the provisions of the Standard Text. Furthermore where encoding by first wireless device is per ¶0100 i.e. using a determined AI/ML model where per ¶0095 terminal has indication of i.e. a criterion for selecting an AI/ML model; a feedback order of an CSI vector; and how does a network device read CSI, reciprocally the second wireless device applies per ¶0102 i.e. a reconstruction part of an appropriate AI/ML model according to the provisions of the Standard Text reads on: based at least in part on the dependency order and the compression sequence , and furthermore per ¶0102 i.e. for decompression reads on: to generate a set of decompressed vectors respectively ¶0102 i.e. according to the received compressed vectors reads on: corresponding to the set of vectors )
(See the rejection of Claim 1, Claim 10 recites features in conjunction with a second wireless device that are similar, parallel and reciprocal to the features of Claim 1 in conjunction with a first wireless device, where the first wireless device for example associates with “encode the set of vectors” and “and transmit the set of compressed vectors” and reciprocally the second wireless device associates with “receive a set of compressed vectors” and “and decode the set of compressed vectors”. The rationale for the rejection of Claim 1 applies similarly to Claim 10. Where applicable, minor differences between claims are noted as appropriate).
Regarding Claim 11. ZHANG in view of LIEN teaches: The second wireless device of claim 10, wherein,
(See the rejection of Claim 2, Claim 11 recites features in conjunction with a second wireless device that are similar, parallel and reciprocal to the features of Claim 1 in conjunction with a first wireless device, where the first wireless device for example associates with “transmit the indication […]” and reciprocally the second wireless device associates with “receive the indication […]”. The rationale for the rejection of Claim 2 applies similarly to Claim 11. Where applicable, minor differences between claims are noted as appropriate) to communicate the indication of the dependency order, the one or more processors are individually or collectively operable to execute the code to cause the second wireless device to: receive the indication of the dependency order from a first wireless device in a message with the set of compressed vectors
or (note: limitations separated by a recitation “or” are interpreted as presented in the alternative and not required together i.e. for the purposes of patentable weight)
in a message separate from the set of compressed vectors that is received with a same periodicity or a different periodicity as the set of compressed vectors (note: limitations separated by a recitation “or” are interpreted as presented in the alternative and not required together i.e. for the purposes of patentable weight)
(See the rejection of Claim 2, Claim 11 recites features in conjunction with a second wireless device that are similar, parallel and reciprocal to the features of Claim 1 in conjunction with a first wireless device, where the first wireless device for example associates with “transmit the indication […]” and reciprocally the second wireless device associates with “receive the indication […]”. The rationale for the rejection of Claim 2 applies similarly to Claim 11. Where applicable, minor differences between claims are noted as appropriate).
Regarding Claim 12. ZHANG in view of LIEN teaches: The second wireless device of claim 10,
(See the rejection of Claim 3, Claim 12 recites features in conjunction with a second wireless device that are similar, parallel and reciprocal to the features of Claim 1 in conjunction with a first wireless device, where the first wireless device for example associates with “transmit the indication […]” and reciprocally the second wireless device associates with “receive the indication […]”. The rationale for the rejection of Claim 3 applies similarly to Claim 12. Where applicable, minor differences between claims are noted as appropriate) wherein, to communicate the indication of the dependency order, the one or more processors are individually or collectively operable to execute the code to cause the second wireless device to: transmit the indication of the dependency order to a first wireless device for configuring the first wireless device with the dependency order (See the rejection of Claim 3, Claim 12 recites features in conjunction with a second wireless device that are similar, parallel and reciprocal to the features of Claim 1 in conjunction with a first wireless device, where the first wireless device for example associates with “transmit the indication […]” and reciprocally the second wireless device associates with “receive the indication […]”. The rationale for the rejection of Claim 3 applies similarly to Claim 12. Where applicable, minor differences between claims are noted as appropriate).
Regarding Claim 13. ZHANG in view of LIEN teaches: The second wireless device of claim 10, (See the rejection of Claim 4, Claim 13 recites features in conjunction with a second wireless device that are similar, parallel and reciprocal to the features of Claim 1 in conjunction with a first wireless device. The rationale for the rejection of Claim 4 applies similarly to Claim 13. Where applicable, minor differences between claims are noted as appropriate) wherein the indication of the dependency order for compression indicates at least one operational dependency in a set of encoder layers of a first wireless device
or (note: limitations separated by a recitation “or” are interpreted as presented in the alternative and not required together i.e. for the purposes of patentable weight)
at least one operational dependency in a set of decoder layers of the second wireless device(note: limitations separated by a recitation “or” are interpreted as presented in the alternative and not required together i.e. for the purposes of patentable weight) (See the rejection of Claim 4, Claim 13 recites features in conjunction with a second wireless device that are similar, parallel and reciprocal to the features of Claim 1 in conjunction with a first wireless device. The rationale for the rejection of Claim 4 applies similarly to Claim 13. Where applicable, minor differences between claims are noted as appropriate).
Regarding Claim 14. ZHANG in view of LIEN teaches: The second wireless device of claim 10, (See the rejection of Claim 5, Claim 14 recites features in conjunction with a second wireless device that are similar, parallel and reciprocal to the features of Claim 1 in conjunction with a first wireless device, where the first wireless device for example associates with “encode […]” and reciprocally the second wireless device associates with “decode […]”. The rationale for the rejection of Claim 5 applies similarly to Claim 14. Where applicable, minor differences between claims are noted as appropriate) wherein, to decode the set of vectors, the one or more processors are individually or collectively operable to execute the code to cause the second wireless device to: decode the set of vectors using a set of decoder layers according to the dependency order, wherein each decoder layer of the set of decoder layers, after an initial decoder layer, is dependent on one or more decompressed vectors respectively generated by one or more previous decoder layers of the set of decoder layers in the dependency order (LIEN FIG. 4 & ¶0037 See claim 1; ¶0049 […] a TX/RX module 685 in base station 620 may provide the bit stream as input to a CSI bit-stream decoder 675. The CSI bit-stream decoder 675 in base station 620 may convert the bit stream to low dimensional information. The AE decoder 670 at base station 620 may then reconstruct the channel condition;
NOTE-DISCLOSURE & TEACHING: FIG. 4 depicts AE with decoder comprising layers 470, 480, 420 associated with weights WT3, WT2, WT1 and per ¶0037 i.e. the vector of weights/parameters between the input layer 410 and the first hidden layer 450 in the encoder may be the transpose of the vector of weights/parameters between the output layer 420 and the first hidden layer 480 in the decoder. The vector of weights/parameters between the first hidden layer 450 and the second hidden layer 460 in the encoder may be the transpose of the vector of weights/parameters between the first hidden layer 480 and the second hidden layer 470 in the decoder, and so on, further utilized as utilized per ¶0049 The AE decoder 670 at base station 620 may then reconstruct the channel condition reads on: wherein, to decode the set of vectors, the one or more processors are individually or collectively operable to execute the code to cause the first wireless device to: decode the set of vectors using a set of decoder layers, where per FIG. 4 depicting the decoding direction i.e. weights WT3 -> WT2-> WT1 –>
PNG
media_image1.png
32
19
media_image1.png
Greyscale
associated with the hidden layers of the decoder reads on: according to the dependency order , where per FIG. 4 as depicted i.e. weights WT3 -> WT2-> WT1 –>
PNG
media_image1.png
32
19
media_image1.png
Greyscale
associated with the hidden layers of the decoder reads on: wherein each decoder layer of the set of decoder layers, after an initial decoder layer, is dependent on one or more compressed vectors respectively generated by one or more previous decoder layers of the set of decoder layers in the dependency order) (See the rejection of Claim 5, Claim 14 recites features in conjunction with a second wireless device that are similar, parallel and reciprocal to the features of Claim 5 in conjunction with a first wireless device, where the first wireless device for example associates with “encode […]” and reciprocally the second wireless device associates with “decode […]”. The rationale for the rejection of Claim 5 applies similarly to Claim 14. Where applicable, minor differences between claims are noted as appropriate).
Regarding Claim 16. ZHANG in view of LIEN teaches: The second wireless device of claim 10,
(See the rejection of Claim 7, Claim 16 recites features in conjunction with a second wireless device that are similar, parallel and reciprocal to the features of Claim 7 in conjunction with a first wireless device, where the first wireless device for example associates with “encode […]” and reciprocally the second wireless device associates with “decode […]”. The rationale for the rejection of Claim 7 applies similarly to Claim 16. Where applicable, minor differences between claims are noted as appropriate)
furthermore ZHANG teaches: wherein, to decode the set of vectors, the one or more processors are individually or collectively operable to execute the code to cause the second wireless device to: decode each compressed vector of the set of compressed vectors using a respective neural network layer of a set of neural network layers (ZHANG - ¶0099 See claim 1; ¶0100 see claim 1; ¶0102 See claim 1; ¶0104 & ¶0126 […] In the S7, according to the first rule, the network device knows which AI/ML model is used by the terminal equipment, and the number of bits outputted by this AI/ML model.
NOTE-DISCLOSURE & TEACHING: per ¶0099 i.e. S4: for singular vectors corresponding to the above two singular values, the terminal equipment selects two models with the largest number of feedback bits among the four AI/ML models, namely model 1 and model 2 according to the standard regulations, and assigns model 1 to a singular vector corresponding to σ.sub.2, and assigns model 2 to a singular vector corresponding to σ.sub.1 and per ¶0100 i.e. S5: the terminal equipment compresses the two singular vectors by using a determined AI/ML model and per ¶0102 i.e. S7: according to the received compressed vectors, the network device selects a reconstruction part of an appropriate AI/ML model for decompression according to the provisions of the Standard Text S7: according to the received compressed vectors, the network device selects a reconstruction part of an appropriate AI/ML model for i.e. decompression according to the provisions of the Standard Text reads on: wherein, to decode the set of vectors, the one or more processors are individually or collectively operable to execute the code to cause the first wireless device to: decode each vector of the set of vectors , per ¶0104 i.e. In the S7, according to the first rule, the network device knows which AI/ML model is used by the terminal equipment reads on: using a respective neural network layer and per ¶0099 i.e. among the four AI/ML models, namely model 1 and model 2 according to the standard regulations, and assigns model 1 to a singular vector corresponding to σ.sub.2, and assigns model 2 to a singular vector corresponding to σ.sub.1 per ¶0102 i.e. a reconstruction part of an appropriate AI/ML model for decompression applied to ¶0099 i.e. a singular vector corresponding to σ.sub.2, and i.e. a singular vector corresponding to σ.sub.1 compressed by the encoder reads on: of a set of neural network layers)
(See the rejection of Claim 7, Claim 16 recites features in conjunction with a second wireless device that are similar, parallel and reciprocal to the features of Claim 7 in conjunction with a first wireless device, where the first wireless device for example associates with “encode […]” and reciprocally the second wireless device associates with “decode […]”. The rationale for the rejection of Claim 7 applies similarly to Claim 16. Where applicable, minor differences between claims are noted as appropriate).
Regarding claim 18. ZHANG teaches: A method for wireless communications at a first wireless device (ZHANG – FIG. 5 & ¶0090 […] 501: the network device informs the terminal equipment of an AI/ML model that may be used, and for allocations of a specific number of bits;
NOTE-DISCLOSURE & TEACHING: Per FIG. 5 & ¶0090 i.e. the network device informs the terminal equipment of an AI/ML model that may be used reads on: A method for wireless communications, i.e. informs the terminal equipment reads on: at a first wireless device),
(See the rejection of Claim 1, Claim 18 recites similar and parallel features to Claim 8, and the rationale for the rejection of claim 1 applies similarly to claim 18. Where applicable, minor differences between claims are noted as appropriate) comprising: communicating an indication of a dependency order for compression of a set of vectors, the dependency order being associated with a compression sequence for the set of vectors; encoding the set of vectors based at least in part on the dependency order and the compression sequence to generate a set of compressed vectors respectively corresponding to the set of vectors; and transmitting the set of compressed vectors(See the rejection of Claim 1, Claim 18 recites similar and parallel features to Claim 8, and the rationale for the rejection of claim 1 applies similarly to claim 18. Where applicable, minor differences between claims are noted as appropriate).
Regarding Claim 19. ZHANG in view of LIEN teaches: The method of claim 18,
(See the rejection of Claim 2, Claim 19 recites similar and parallel features to Claim 8, and the rationale for the rejection of Claim 2 applies similarly to Claim 19. Where applicable, minor differences between claims are noted as appropriate) wherein communicating the indication of the dependency order comprises: transmitting the indication of the dependency order to a second wireless device in a message with the set of compressed vectors or in a message separate from the set of compressed vectors that is transmitted with a same periodicity or a different periodicity as the set of compressed vectors (See the rejection of Claim 2, Claim 19 recites similar and parallel features to Claim 8, and the rationale for the rejection of Claim 2 applies similarly to Claim 19. Where applicable, minor differences between claims are noted as appropriate).
Regarding Claim 20. ZHANG in view of LIEN teaches: The method of claim 18, (See the rejection of Claim 3, Claim 20 recites similar and parallel features to Claim 8, and the rationale for the rejection of Claim 3 applies similarly to Claim 20. Where applicable, minor differences between claims are noted as appropriate) wherein communicating the indication of the dependency order comprises: receiving the indication of the dependency order from a second wireless device for configuring the first wireless device with the dependency order(See the rejection of Claim 3, Claim 20 recites similar and parallel features to Claim 8, and the rationale for the rejection of Claim 3 applies similarly to Claim 20. Where applicable, minor differences between claims are noted as appropriate).
9. Claims 8, 9, 17 are rejected under 35 U.S.C. 103 as being unpatentable over ZHANG in view of LIEN, further in view of SABER et al. (US 20250055534 A1) i.e. “SABER”.
Regarding Claim 8. ZHANG in view of LIEN teaches: The first wireless device of claim 7,
furthermore ZHANG teaches: wherein the set of neural network layers is trained to generate compressed vectors in the set of compressed vectors (ZHANG - ¶0099 See claim 1; ¶0100 see claim 1;
NOTE-DISCLOSURE & TEACHING: per ¶0100 i.e. S5: the terminal equipment compresses the two singular vectors by using a determined AI/ML model) reads on: wherein the set of neural network layers is trained to generate compressed vectors. Furthermore ¶0099 i.e. S4: for singular vectors corresponding to the above two singular values, the terminal equipment selects two models with the largest number of feedback bits among the four AI/ML models, namely model 1 and model 2 read on: in the set of compressed vectors);
furthermore LIEN teaches: wherein the set of neural network layers is trained to generate compressed vectors in the set of compressed vectors (LIEN – FIG. 3 ¶0034 […] an autoencoder and associated training on a dataset 330 to determine weights/parameters of encoder 310 and decoder 320.;
NOTE-DISCLOSURE & TEACHING: per ¶0034 i.e. an autoencoder and associated training on a dataset 330 to determine weights/parameters of encoder 310 and decoder 320 reads on: wherein the set of neural network layers is trained, ¶0048 The AE encoder 650 in UE 610 then may reduce the dimension of the estimated channel condition to generate low dimensional information i.e. RS 630 in one or more downlink transmissions to generate i.e. the channel condition H' i.e. reduce the dimension of the estimated channel condition to generate low dimensional information reads on: to generate compressed vectors in the set of compressed vectors);
ZHANG in view of Kim does not appear to explicitly teach or strongly suggest (i.e. see italicized portions of claim limitations): compressed vectors that satisfy an orthogonality condition.
SABER teaches: wherein the set of neural network layers is trained to generate compressed vectors in the set of compressed vectors that satisfy an orthogonality condition (SABER - ¶0351 […] a UE may only report one RI for all of the sub-bands specified in a CSI report configuration. The same approach may also be adopted for some embodiments of an AI/ML CSI reporting framework. In some additional embodiments, one or more RI values corresponding to one or more (e.g., each) sub-band may be reported by concatenating them into a vector and compressing the vector, which, depending on the implementation details, may be similar to CSI matrix compression; ¶0377 […] a UE may be provided with restriction information relating to a channel. This may enable the UE to ensure that a precoder or other CSI feedback determined using artificial intelligence and/or machine learning may result in beamforming that is orthogonal to (e.g., does not interfere with) a restricted sub-space for the channel.
NOTE-DISCLOSURE & TEACHING: per ¶0351 i.e. adopted for some embodiments of an AI/ML CSI reporting framework. i.e. one or more RI values corresponding to one or more (e.g., each) sub-band may be reported by concatenating them into a vector and compressing the vector, which, depending on the implementation details, may be similar to CSI matrix compression reads on: wherein the set of neural network layers is trained to generate compressed vectors in the set of compressed vectors . Furthermore per ¶0377 i.e. a UE may be provided with restriction information relating to a channel. This may enable the UE to ensure that i.e. a precoder or other CSI feedback determined using artificial intelligence and/or machine learning may result in beamforming that is orthogonal to (e.g., does not interfere with) a restricted sub-space for the channel reads on: that satisfy an orthogonality condition).
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 ZHANG in view of LIEN, with the teachings of SABER, since SABER enables UE to ensure that a precoder determined using a decoder model is orthogonal to (e.g., does not interfere with) a restricted sub-space for the channel (SABER ¶0004 , ¶0377).
Regarding Claim 9. ZHANG in view of Kim teaches: The first wireless device of claim 1,
furthermore ZHANG teaches: wherein the one or more processors are individually or collectively further operable to execute the code to cause the first wireless device to: receive a reference signal; and perform a decomposition based at least in part on the reference signal to generate the set of vectors (ZHANG - ¶0098 See claim 1; ¶0099 See claim 1;
NOTE-DISCLOSURE & TEACHING: per ¶0098 i.e. S3: the terminal equipment receives the CSI-RS reads on: wherein the one or more processors are individually or collectively further operable to execute the code to cause the first wireless device to: receive a reference signal; Furthermore per ¶0098 i.e. measures a spatial channel, calculates a rank of a spatial channel matrix to be 2, and calculates a singular value of the spatial channel matrix to be σ.sub.k, k=1,2, and there is σ.sub.1>σ.sub.2>0 reads on: and perform a decomposition based at least in part on the reference signal , where per ¶0099 i.e. S4: for singular vectors corresponding to the above two singular values and per ¶0100 i.e. the terminal equipment compresses the two singular vectors by using a determined AI/ML model reads on: to generate the set of vectors);
ZHANG in view of Kim does not appear to explicitly teach or strongly suggest (i.e. see italicized portions of claim limitations): wherein each vector is orthogonal with respect to at least one other vector;
SABER teaches: wherein each vector is orthogonal with respect to at least one other vector (SABER - ¶0351 See claim 8; ¶0377 See claim 8.
NOTE-DISCLOSURE & TEACHING: per ¶0351 i.e. adopted for some embodiments of an AI/ML CSI reporting framework. i.e. one or more RI values corresponding to one or more (e.g., each) sub-band may be reported by concatenating them into a vector and compressing the vector, which, depending on the implementation details, may be similar to CSI matrix compression reads on: wherein each vector. Furthermore per ¶0377 i.e. a UE may be provided with restriction information relating to a channel. This may enable the UE to ensure that i.e. a precoder or other CSI feedback determined using artificial intelligence and/or machine learning may result in beamforming that is orthogonal to (e.g., does not interfere with) a restricted sub-space for the channel reads on: is orthogonal with respect to at least one other vector).
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 ZHANG in view of LIEN, with the teachings of SABER, since SABER enables UE to ensure that a precoder determined using a decoder model is orthogonal to (e.g., does not interfere with) a restricted sub-space for the channel (SABER ¶0004 , ¶0377).
Regarding Claim 17. ZHANG in view of LIEN teaches: The second wireless device of claim 16,
(See the rejection of Claim 8, Claim 17 recites features in conjunction with a second wireless device that are similar, parallel and reciprocal to the features of Claim 8 in conjunction with a first wireless device, where the first wireless device for example associates with “compressed […]” and reciprocally the second wireless device associates with “decompressed […]”. The rationale for the rejection of Claim 8 applies similarly to Claim 17. Where applicable, minor differences between claims are noted as appropriate)
furthermore LIEN teaches: wherein the set of neural network layers is trained to generate decompressed vectors in the set of decompressed vectors (LIEN – FIG. 3 ¶0034 […] an autoencoder and associated training on a dataset 330 to determine weights/parameters of encoder 310 and decoder 320.;
NOTE-DISCLOSURE & TEACHING: per ¶0034 i.e. an autoencoder and associated training on a dataset 330 to determine weights/parameters of encoder 310 and decoder 320 reads on: wherein the set of neural network layers is trained, ¶0049 The AE decoder 670 at base station 620 may then reconstruct the channel condition reads on: to generate decompressed vectors in the set of decompressed vectors);
ZHANG in view of LIEN does not appear to explicitly teach or strongly suggest (i.e. see italicized portions of claim limitations): compressed vectors that satisfy an orthogonality condition.
SABER teaches: wherein the set of neural network layers is trained to generate vectors in the set of vectors that satisfy an orthogonality condition (SABER - ¶0351 […] a UE may only report one RI for all of the sub-bands specified in a CSI report configuration. The same approach may also be adopted for some embodiments of an AI/ML CSI reporting framework. In some additional embodiments, one or more RI values corresponding to one or more (e.g., each) sub-band may be reported by concatenating them into a vector and compressing the vector, which, depending on the implementation details, may be similar to CSI matrix compression; ¶0377 […] a UE may be provided with restriction information relating to a channel. This may enable the UE to ensure that a precoder or other CSI feedback determined using artificial intelligence and/or machine learning may result in beamforming that is orthogonal to (e.g., does not interfere with) a restricted sub-space for the channel.
NOTE-DISCLOSURE & TEACHING: per ¶0351 i.e. adopted for some embodiments of an AI/ML CSI reporting framework. i.e. one or more RI values corresponding to one or more (e.g., each) sub-band may be reported by concatenating them into a vector and compressing the vector, which, depending on the implementation details, may be similar to CSI matrix compression reads on: wherein the set of neural network layers is trained to generate vectors in the set of vectors. Furthermore per ¶0377 i.e. a UE may be provided with restriction information relating to a channel. This may enable the UE to ensure that i.e. a precoder or other CSI feedback determined using artificial intelligence and/or machine learning may result in beamforming that is orthogonal to (e.g., does not interfere with) a restricted sub-space for the channel reads on: that satisfy an orthogonality condition).
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 ZHANG in view of LIEN, with the teachings of SABER, since SABER enables UE to ensure that a precoder determined using a decoder model is orthogonal to (e.g., does not interfere with) a restricted sub-space for the channel (SABER ¶0004 , ¶0377).
(See the rejection of Claim 8, Claim 17 recites features in conjunction with a second wireless device that are similar, parallel and reciprocal to the features of Claim 8 in conjunction with a first wireless device, where the first wireless device for example associates with “compressed […]” and reciprocally the second wireless device associates with “decompressed […]”. The rationale for the rejection of Claim 8 applies similarly to Claim 17. Where applicable, minor differences between claims are noted as appropriate).
Allowable Subject Matter
10. Claims 6, 15 are objected to as being dependent upon a rejected base claim, but would be allowable contingent upon or subject to all of the following conditions:
(1) that the claims are rewritten in independent form including all of the limitations of the base claim and any intervening claims as presented by applicant and referenced herein,
(2) that all independent claims were amended with similar, identical and parallel features and amendments in the independent claims representing identical features were submitted in a formal response,
(3) that the claim limitation(s) are not taken alone but in view of the entirety of the claim language including any preceding claim limitations, any proceeding claim limitations, and any intervening claim limitations,
(4) that all pending issues associated with the claims including:
(a) clarifying applicable issues related with claim objections under minor informalities and 112 (b) rejections,
(b) issues related with the entirety of the claim language including any preceding claim limitations, any proceeding claim limitations, and any intervening claim limitations, including the independent claims,
are all acceptably resolved, and do not result in a case where, given the scope of any applicant claimed amendments and/or arguments, examination would require further consideration and search.
The following is a statement of reasons for the indication of allowable subject matter:
Regarding Claim 6. The first wireless device of claim 5, contingent upon or subject to the conditions noted herein above, the prior art of record fails to disclose, alone, individually or in any reasonable combination, as required by the dependent claim(s): “wherein, to encode the set of vectors, the one or more processors are individually or collectively operable to execute the code to cause the first wireless device to: encode a first vector of the set of vectors using a first encoder layer of the set of encoder layers to generate a first compressed vector of the set of compressed vectors; and encode, based at least in part on the first compressed vector, a second vector of the set of vectors using a second encoder layer of the set of encoder layers, wherein the second encoder layer operates after the first encoder layer in the compression sequence, and wherein the second encoder layer is dependent on the first compressed vector generated by the first encoder layer in the dependency order”.
Regarding Claim 15. The second wireless device of claim 14, contingent upon or subject to the conditions noted herein above, the prior art of record fails to disclose, alone, individually or in any reasonable combination, as required by the dependent claim(s): “wherein, to decode the set of vectors, the one or more processors are individually or collectively operable to execute the code to cause the second wireless device to: decode a first compressed vector of the set of compressed vectors using a first decoder layer of the set of decoder layers to generate a first decompressed vector of the set of decompressed vectors; and decode, based at least in part on the first decompressed vector, a second decompressed vector of the set of decompressed vectors using a second decoder layer of the set of decoder layers, wherein the second decoder layer operates after the first decoder layer in the compression sequence, and wherein the second decoder layer is dependent on the first decompressed vector generated by the first decoder layer in the dependency order”.
Please note: The examiner notes the above limitation(s) are not taken alone but in view of the entirety of the claim language including any preceding claim limitation, any proceeding claim limitations, and any intervening claim limitations.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MALICK A SOHRAB whose telephone number is (571)272-4347. The examiner can normally be reached on Mo-Fri 9:00 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, Edan Orgad can be reached on (571) 272-7884. 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 https://ppair-my.uspto.gov/pair/PrivatePair. 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.
/M.A.S./
Examiner, Art Unit 2414
09/24/2026
/EDAN ORGAD/Supervisory Patent Examiner, Art Unit 2414
