DETAILED ACTION
This action is responsive to application filed on March 7th, 2025.
Claims 1~20 are examined.
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 03/07/25 and 05/01/25 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
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.
Claims 1~3, 6~8, and 15~20 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by 3GPP TSG RAN WG1 #109-e et al. hereinafter 3GPP (NPL: Other aspects on AI/ML for CSI feedback enhancement).
Regarding Claim 1,
3GPP taught a method of wireless communication at a user equipment (UE), comprising:
receiving, from a network entity, a downlink signal for monitoring a performance of a machine learning (ML) model for channel state information (CSI) compression [Pg. 2, UE applies a ML model known as the encoder to derive a compressed representation of the channel features derived from measurements on the CSI-RS resources], the monitoring the performance being based on a measurement value of the downlink signal [Pg. 3, UE may request data collection resources from gNB and collect data from the data collection resources configured by the gNB. Alternatively, UE may collect data from available DL channels or RSs. After that the UE may send the collected data to an over-the-top (OTT) server where training happens.]; and
transmitting, to the network entity based on the measurement value of the at least one downlink signal, information associated with the performance of the ML model used for the CSI compression [Pg. 4, the UE will take input the CSI-RS measurement to the encoder to generate a latent message]; and
communicating with the network entity when the information associated with the performance of the ML model indicates a performance failure], wherein a communication being applied to at least one of: an update to the ML model, a switch of the ML model to a different ML model, or non-ML CSI reporting [Pg. 5, the gNB may obtain assistance information reported from UE or proprietary OTT server. The gNB or UE may send the performance report to the other side to facilitate the potential determination of model deactivation or switching. In addition, the performance report may be sent to proprietary OTT server for model monitoring, retraining, or new model development decision; Pg. 3, assistance information used in model monitoring which assists the decision of model failure so that the UE vendor or gNB vendor can trigger model deactivation/retraining/switching].
Regarding Claim 2,
3GPP taught wherein receiving control signaling that indicates at least one of: activation of the ML model for the CSI compression [Pg. 2, UE applies a ML model known as the encoder to derive a compressed representation of the channel features derived from measurements on the CSI-RS resources], downlink signal information for the at least one downlink signal, parameter for the monitoring the performance of the ML model, feedback information for the information associated with the performance of the ML model, or a CSI decoder for the CSI compression.
Regarding Claim 3,
3GPP taught wherein the information associated with the performance of the ML model corresponds to at least one of: the feedback information or a performance failure report associated with detection of the performance failure, wherein the feedback information is indicative of whether the performance of the ML model contributed to the performance failure [Pg. 3, assistance information used in model monitoring which assists the decision of model failure so that the UE vendor or gNB vendor can trigger model deactivation/retraining/switching].
Regarding Claim 6,
3GPP taught further comprising: receiving, within a configured or predefined time duration after the transmitting the information associated with the performance of the ML model, a response to the information associated with the performance of the ML model, wherein the response is indicative of the communication that applies the at least one of: the update to the ML model, the switch of the ML model to the different ML model, or the non-ML CSI reporting [Pg. 3, gNB vendor can trigger model deactivation/retraining/switching].
Regarding Claim 7,
3GPP taught further comprising: retransmitting the information associated with the performance of the ML model if the UE does not receive a response to the information associated with the performance of the ML model within a configured or predefined time duration and if a number of retransmissions of the information associated with the performance of the ML model is below a maximum number of retransmissions [Pg. 5, the UE may obtain the inference results indicated from gNB periodically or occasionally].
Regarding Claim 8,
3GPP taught wherein the downlink signal for the monitoring the performance of the ML model corresponds to at least one of a demodulation reference signal (DMRS), a physical downlink shared channel (PDSCH) transmission, or a channel state information-reference signal (CSI-RS) transmitted from a same number of antenna ports as a maximum number of downlink layers configured based on radio resource control (RRC) signaling [Pg. 5, to evaluate the inference performance, there are various KPIs can be considered, such as PDSCH decoding performance].
Regarding Claims 15~20, the claims are similar in scope to claims 1~3 and 6~8, and therefore, rejected under the same rationale.
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.
Claims 4, 5, 10, 11 are rejected under 35 U.S.C. 103 as being unpatentable over 3GPP in view of Li et al. hereinafter Li (U.S 2025/0219898).
Regarding Claim 4,
3GPP-Li taught wherein the communicating with the network entity further comprises: transmitting the performance failure report to the network entity over at least one of a medium access control-control element (MAC-CE), a physical uplink control channel (PUCCH), or a physical random access channel (PRACH) [Li: ¶147, the UE performs ML-model performance monitoring and determines what information about the ML-model performance to include in the report, on which radio resources to send this periodic report (time slots and/or frames and/or subframes the allowed to be used for the transmissions, e.g., in case of PUCCH, frequency domain resources, exact control channel in the UL to be used].
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention was made, to combine, Li’s teaching of limitations with the teachings of 3GPP, because the combination allows the NW spot potential errors and inform the UE about this and/or enable/disable the UE to use the outcome of the ML-models for one or more procedures [¶258].
Regarding Claim 5,
3GPP-Li taught further comprising: transmitting a dedicated scheduling request (SR) for uplink resources for the transmitting the performance failure report to the network entity; receiving a configuration of the uplink resources for the transmitting the performance failure report to the network entity; and transmitting the performance failure report to the network entity on the uplink resources [¶163, if the UE is not provided with UL resources for transmission of the periodic report the UE transmits a scheduling request for UL resources, to then transmit the report e.g., over PUSCH]. The rationale to combine as discussed in claim 4, applies here as well.
Regarding Claim 10,
3GPP-Li taught wherein the performance failure of the ML model is based on a number of consecutive failure detection instances associated with the measurement value of the downlink signal [¶219, the UE is also configured with a COUNTER value so that the UE performs the report of the one or more indications of the ML-model performance as described above if a number of failure or problem instances in the ML-model reaches the COUNTER value. This COUNTER value could represent the maximum amount of failure which are tolerated]. The rationale to combine as discussed in claim 4, applies here as well.
Regarding Claim 11,
3GPP-Li taught wherein decompression of the CSI is based on the downlink signal [¶260, the NW may adjust its transmission/reception decisions, e.g., the selection of the downlink/uplink transmission rank, the downlink modulation and coding scheme] and at least one of: a subband size for decompressed CSI [¶253~¶256, subband recommended by UE’s ML model], a first number of bits for amplitude quantization, a second number of bits for phase quantization, or a third number of coefficients associated with the downlink signal. The rationale to combine as discussed in claim 4, applies here as well.
Claim 9 is rejected under 35 U.S.C. 102(a)(2) as being anticipated by 3GPP TSG RAN WG1 #109-e R1-2203141 hereinafter 3GPP_2 (NPL: Discussion on AI/ML for CSI feedback enhancement).
Regarding Claim 9,
3GPP-3GPP_2 taught wherein at least one of a cosine similarity or a square cosine similarity for the monitoring the performance of the ML model applies at least one of a normalized eigenvector, an estimated channel for the downlink signal, or a normalized channel for the downlink signal, and wherein the performance failure of the ML model is based on the at least one of the cosine similarity or the square cosine similarity fulfilling a threshold criterion [§3.1.4, for AI/ML-based CSI compression, an example of the intermediate result is the generalized cosine similarity (GCS) between original and recovered CSI].
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention was made, to combine, 3GPP_2’s teaching of limitations with the teachings of 3GPP, because the combination would improve throughput gains for the end-user.
Claims 12~14 are rejected under 35 U.S.C. 103 as being unpatentable over 3GPP in view of Soldati et al. hereinafter Soldati (U.S 2024/0314638).
Regarding Claim 12,
3GPP-Soldati taught wherein the monitoring the performance of the ML model is based on a block error rate (BLER) associated with the measurement value of the downlink signal [Pg. 5, to evaluate the inference performance, there are various KPIs can be considered, such as system throughput, error metric, PDSCH decoding performance, or BLER], and wherein the performance failure of the ML model corresponds to the BLER fulfilling a BLER threshold criterion [Soldati: ¶50, optimize the BLER target used for the link adaptation algorithm in a communication session with a user device].
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention was made, to combine, Soldati’s teaching of limitations with the teachings of 3GPP, because the combination leads to better user performance, better user experience, and an overall better network performance [¶54].
Regarding Claim 13,
3GPP-Soldati taught the BLER is based on at least one of: a first target average spectrum efficiency per layer or a second target average spectrum efficiency per number of layers [Soldati: ¶50, different machine learning based algorithms have been suggested to configure a proper BLER target for link adaptation, such as regression models of the spectral efficiency; ¶54]. The rationale to combine as discussed in claim 12, applies here as well.
Regarding Claim 14,
3GPP taught wherein the information associated with the performance of the ML model includes the BLER [Pg. 5, to evaluate the inference performance, there are various KPIs can be considered, such as system throughput, error metric, PDSCH decoding performance, or BLER].
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HEE SOO KIM whose telephone number is (571)270-3229. The examiner can normally be reached M-F 9AM-5PM.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Nicholas Taylor can be reached on (571) 272-3889. 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.
/HEE SOO KIM/Primary Examiner, Art Unit 2443
