DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
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.
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 of this title, 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 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over US 20130182569 A1 (Bertrand), in view of US 2024/0063938 A1 (Jovanovic) an in further view of US 2025/0385747 A1 (Elgabroun).
Regarding Claims 1, 2 and 13:
A method for adjusting a signal to interference and noise (SINR) backoff value, the method comprising: accessing first block error rate (BLER) data, wherein the first BLER data is collected by monitoring BLER at a gNodeB base station of a 5G network for a plurality of slots; accessing, for each slot of the plurality of slots, a set of features, wherein the set of features comprises at least one of: device type of a connected device, frequency, frequency band, time of day, geolocation, traffic load, weather conditions, or historical BLER patterns; providing, for each slot of the plurality of slots, the first BLER data and the set of features to a reinforcement learning agent; determining, for each slot of the plurality of slots, by the reinforcement learning agent using the first BLER data and the set of features, a SINR backoff value for the slot, wherein the SINR backoff value indicates an amount by which to adjust a transmission power; providing, for each slot of the plurality of slots, the SINR backoff value to a link adaptation algorithm (Bertrand: teaching a link adaptation for LTE; Figs. 3-4, illustrate an outer loop link adaptation “OLLA” algorithm assisted with an inner loop link adaptation “ILLA”, where link adaptation “LA” is through SINR backoff and LA is at transmission time interval (TTI)),
Bertrand does not teach explicitly on slot-based LA. However, Jovanovic teaches (Jovanovic: Fig. 1, eNodeB obtains channel info from CQI report; Fig. 6, obtain the measurement comprised a BLER per rank, MCS and slot; determine whether to use or not use LA and amount to adjust; accessing historical BLER patterns per slot, e.g., [0070] The percentage values in the table indicates the NACK/(ACK+NACK) ratio. ... A BLER heat map when used herein means a matrix of measured BLER values connected to slot, rank and MCS.").
It would have been obvious for one of ordinary skill in the art before the effective filling date of the claimed invention was made to modify Bertrand with slot-based LA as further taught by Jovanovic. The advantage of doing so is to enable a Q-learning reinforcement learning agent that observes BLER state and learns an optimal policy to improve the LA performance, especially from slow convergence and proposes in OLLA.
Bertrand does not teach explicitly on using reinforcement learning to assisting LA. However, Elgabroun teaches (Elgabroun: Figs. 4-7, [0090]-[0108], a LA scheme that leverages Q-learning, i.e., reinforcement learning; “The aim of the proposed method is to predict the suitable MCS value (the second MCS value) for UL transmission which results in a high link throughput while simultaneously also preferably decreasing the BLER. By using Q-Learning, the method can automatically adapt to any changes and inaccuracies in the estimated SINR values”).
It would have been obvious for one of ordinary skill in the art before the effective filling date of the claimed invention was made to modify Bertrand with using reinforcement learning to assisting LA as further taught by Elgabroun. The advantage of doing so is to enable a modulation and Coding Scheme (MCS) value which has a fix BLER target is then mapped based on this SINR, in order to keep the correctness of wireless transmission (Elgabroun: Background).
wherein the link adaptation algorithm comprising an outer loop link adaptation algorithm and an inner loop link adaptation algorithm, wherein the inner loop link adaptation algorithm is configured to adjust one or more transmission characteristics based on an outer loop offset determined by the outer loop link adaptation algorithm, a SINR estimate, and the SINR backoff value (Bertrand: [0009], “The current backoff parameter may be applied in an inner loop link adaptation process, and the new backoff parameter created as part of an outer loop link adaptation process. An SINR parameter for the UE may be modified using the current backoff parameter in an inner loop adaptation process”).
wherein the link adaptation algorithm causes a change in one or more of a modulation scheme, a coding rate, or a transmit power; accessing, for each slot of the plurality of slots, feedback comprising second BLER data; determining, for each slot of the plurality of slots based on the second BLER data, an updated SINR backoff value using the reinforcement learning agent; wherein the reinforcement learning agent is configured to learn a policy based on state information comprising BLER data (Jovanovic: teaches accessing subsequent feedback to update the data, e.g., [0127]-[0128], “At each received DL HARQ Feedback (at initial Tx), the network node 110 may perform the following: Calculate BLER table (NACK ratio per rank, mcs, slot) and count table (ACK+NACK count per rank, mcs, slot).”; Elgabroun: Figs. 4-7, [0090]-[0108], using Q-Learning, the method can automatically adapt to any changes and inaccuracies in the estimated SINR values).
Regarding Claim 3, Bertrand as modified further teaches:
The method of claim 2, wherein the SINR backoff value indicates an amount by which a transmission power of the base station is adjusted (Elgabroun: teaches using the RL agent to adjust transmission power, e.g., [0006] ... two very common examples of this are when the parameter to adjust is either an amount of channel coding ... or a transmit power).
. Regarding Claim 4, Bertrand as modified further teaches:
The method of claim 2, wherein the base station is a gNodeB base station of 5G wireless telecommunications network (Jovanovic: Fig. 1).
Regarding Claims 5 and 14, Bertrand as modified further teaches:
The method of claim 2, further comprising: providing the SINR backoff value to a link adaptation algorithm, wherein the link adaptation algorithm is configured to adjust one or more of a modulation scheme, a coding rate, or a transmit power (Elgabroun: teaches using the RL agent to adjust transmission power, e.g., [0006] ... two very common examples of this are when the parameter to adjust is either an amount of channel coding ... or a transmit power).
Regarding Claims 6 and 15, Bertrand as modified further teaches:
The method of claim 5, wherein the link adaptation algorithm comprises an outer loop link adaptation algorithm and an inner loop link adaptation algorithm (Bertrand: e.g., Figs. 3-4).
Regarding Claims 7 and 16, Bertrand as modified further teaches:
The method of claim 6, wherein the inner loop link adaptation algorithm is configured to determine transmission characteristics based on an outer loop offset determine by the outer loop link adaptation algorithm, a SINR estimate, and the SINR backoff value (Bertrand: e.g., Figs. 3-4; [0009], “The current backoff parameter may be applied in an inner loop link adaptation process, and the new backoff parameter created as part of an outer loop link adaptation process. An SINR parameter for the UE may be modified using the current backoff parameter in an inner loop adaptation process”).
Regarding Claims 8 and 17, Bertrand as modified further teaches:
The method of claim 2, wherein the reinforcement learning agent is trained using Q-learning (Elgabroun: Figs. 4-7).
Regarding Claims 9 and 18, Bertrand as modified further teaches:
The method of claim 2, wherein the SINR backoff value is greater than a current SINR backoff value when the first BLER data indicates a BLER level above a first threshold value (Jovanovic: teaches comparing BLER to a first threshold. [0105]-[0106], “the BLER per rank, MCS, and slot exceeds a first threshold, also referred to as High_BLER.")
Regarding Claims 10 and 19, Bertrand as modified further teaches:
The method of claim 2, wherein the SINR backoff value is less than a current SINR backoff value when the first BLER data indicates a BLER level below a second threshold value (Jovanovic: teaches applying threshold logic for negative tracking, e.g., [0109]-[0111] “the BLER per rank, MCS, and slot is below a first threshold ... determining to not adjust the initial ICC estimate").
Regarding Claims 11 and 20, Bertrand as modified further teaches:
The method of claim 2, wherein the slot comprises a plurality of slots, wherein the SINR backoff value comprises a plurality of SINR backoff values, each SINR backoff value of the plurality of SINR backoff values associated with a slot of the plurality of slots (Bertrand: Figs. 3-4, it is also noted that the core teaching of the prior art is applying link adaptation at the highest available granularity of the network's baseline scheduling unit. In LTE such as Bertrand, that baseline scheduling unit was the TTI/subframe. In 5G such as Elgabroun, the baseline scheduling unit evolved to be the slot. A person of ordinary skill in the art (POSITA) migrating Bertrand's scheduling logic to a 5G architecture would naturally map the parameter updates to the 5G baseline scheduling unit—the slot).
Regarding Claim 12, Bertrand as modified further teaches:
The method of claim 2, wherein the method is performed by the base station (Jovanovic: Fig, 1).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ZHITONG CHEN whose telephone number is (571) 270-1936. The examiner can normally be reached on M-F 9:30am - 5pm.
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, Yuwen Pan can be reached on 571-272-7855. 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 http://pair-direct.uspto.gov. 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.
/ZHITONG CHEN/
Primary Examiner, Art Unit 2649
Prosecution Insights