Notice of Pre-AIA or AIA Status
This Office Action is in response to the Reply filed on June 30, 2026.
Claims 1-20 remain pending in the application.
Response to Arguments
Applicant’s arguments, see pages 3-6 of the Reply, with respect to the rejection(s) of independent claims 1, 8, and 15 under 35 U.S.C. §103 have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of newly found prior art references.
Claim Rejections - 35 USC § 102
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 (i.e., changing from AIA to pre-AIA ) 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.
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, 8, and 15 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by U.S. Pub. No. 2026/0135608 (hereinafter “Bonfante,” newly cited).
Bonfante discloses, teaches, or suggests:
regarding claims 1, 8, and 15, a method of beam prediction by a user equipment (UE) (see at least paragraphs 73-82, UE), the UE comprising:
a transceiver (see at least paragraph 156, wireless transceiver);
a processor (see at least paragraph 156, processor); and
a non-transitory computer-readable storage medium that stores a computer program (see at least paragraph 156, memory), wherein the computer program, when executed by the processor, causes the processor to implement the method comprising:
receiving an input feature vector (see at least Fig. 7, Fig. 9, and paragraphs 73-76 and 96-99, at the UE, the set of N RSRP measurements from SSB beams recorded during Step 1 are combined with UE position information and vertical component obtained from UE device sensors, and then the aggregated data is used as input of the ML model, where the input data to the ML model is considered a vector);
comparing the input feature vector to a lookup table of rated predicted beams (see at least Fig. 7, Fig. 9, and paragraphs 75-81, input to ML model: N RSRP measurements of N best SSB beams and UE position information; and output of ML model is beam indices of K best transmit beams and estimated AoA of each of the beams; for each of the K best beams output by ML model, the UE selects a UE receive narrow beam from a beam codebook (a set of beams, each beam with its own AoA) that is closest to the estimated AoA);
selecting a corresponding predicted beam having a highest rating from the lookup table (see at least Fig. 7, Fig. 9, and paragraphs 75-81, input to ML model: N RSRP measurements of N best SSB beams and UE position information; and output of ML model is beam indices of K best transmit beams and estimated AoA of each of the beams; for each of the K best beams output by ML model, the UE selects a UE receive narrow beam from a beam codebook (a set of beams, each beam with its own AoA) that is closest to the estimated AoA, which corresponds to a beam having the highest rating); and
receiving, from a base station, a signal using the selected predicted beam (see at least paragraph 83, the UE receives data from the gNB using the UE receive narrow beam associated with the best gNB transmit narrow beam).
Claims 2, 9, and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Bonfante in view of U.S. Pub. No. 2025/0300900 (hereinafter “Shah”).
Regarding claims 2, 9, and 16, Bonfante discloses, teaches, or suggests that the input feature vector includes a previously used beam (see at least paragraphs 73 and 76, during P1, the UE measures RSRPs of SSB beams and later, during step 3A, the set of N RSRP measurements from SSB beams recorded during Step 1 are used as an input to the ML model) but Bonfante does not explicitly disclose that the input feature vector including a plurality of past normalized RSRP measurements.
However, in an analogous art, Shah discloses, teaches, suggests the input feature vector including a plurality of past normalized RSRP measurements (see at least paragraph 381, input data to the model includes normalizing input data such as RSRP measurements).
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to replace the L1-RSRP measurements of Tehrani, as modified by Pronovost, with the normalized RSRP measurement of Shah as an input data to the ML model because one of ordinary skill in the art would have been able to carry out such a substitution and the results were reasonably predictable.
Claims 3, 10, and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Bonfante in view of U.S. Pub. No. 2024/0056844 (hereinafter “Zhu,” newly cited).
Regarding claims 3, 10, and 17, Bonfante discloses, teaches, or suggests training of a machine learning (ML) model, where the ML model can be implemented in different forms, such as deep neural network (DNN), feedforward neural network (FNN), or convolutional neural network (CNN), where each entry in the rating matrix represents a rating of a feature that is assigned to a particular beam (see at least paragraphs 96-99, the ML model may be trained given a dataset collected from UEs placed in different positions of the gNB sector and reporting each one multiple measurements in time, where the RSRP signal measurements are measured and reported by the UE during the procedure P1 on the set of beams of size N). Bonfante does not explicitly disclose a graph neural network (GNN) trained rating matrix.
However, in an analogous art, Zhu discloses that a graph neural network (GNN) can be viewed as a further refinement to a DNN (see at least paragraphs 78-80).
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to further refine the DNN ML model of Bonfante with the GNN as suggested by Zhu in order to increase the expressive power of the computational graph for each node.
Claims 6, 13, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Bonfante in view of U.S. Pub. No. 2023/0075932 (hereinafter “Sikka,” newly cited).
Regarding claims 6, 13, and 20, Bonfante discloses, teaches, or suggests comparing the input feature vector to the lookup table of rated predicted beams comprises mapping the input feature vector to one of a plurality of feature nodes included in the lookup table (see at least Fig. 7, Fig. 9, and paragraphs 75-81, input to ML model: N RSRP measurements of N best SSB beams and UE position information; and output of ML model is beam indices of K best transmit beams and estimated AoA of each of the beams; for each of the K best beams output by ML model, the UE selects a UE receive narrow beam from a beam codebook (a set of beams, each beam with its own AoA) that is closest to the estimated AoA) but Bonfante does not explicitly disclose quantizing the input feature vector.
However, in an analogous art, Sikka discloses, teaches, or suggests quantizing the input feature vector (see at least paragraphs 35 and 40).
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to implement the technique of quantizing inputs into a machine learning model, as taught by Sikka, in to the invention of Bonfante in order to reduce power consumption and improve computation capabilities, network bandwidth, and processing time (see at least paragraphs 4 and 5 of Sikka).
Claims 7 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Bonfante in view of U.S. Pub. No. 2026/0019176 (hereinafter “Shojaeifard”).
Regarding claims 7 and 14, Bonfante discloses, teaches, or suggests all of the subject matter of the claimed invention except the processor configured to trigger beam prediction when a normalized reference signal received power (RSRP) measurement is below a predetermined threshold.
However, in an analogous art, Shojaeifard disclose, teaches, or suggests triggering beam prediction when a normalized reference signal received power (RSRP) measurement is below a predetermined threshold (see at least paragraphs 135-139, a beam sweep and/or retraining may be triggered if the L1-RSRP is below a threshold).
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to implement the technique as taught by Shojaeifard above in to the invention of Bonfante in order to predict and switch to a beam with better quality (i.e., a beam with L1-RSRP above the threshold).
Allowable Subject Matter
Claims 4, 5, 11, 12, 18, and 19 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Pawaris Sinkantarakorn whose telephone number is (571)270-1424. The examiner can normally be reached Monday-Friday 8:00am-4:00pm.
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, Hadi Armouche can be reached at (571) 270-3618. 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.
/PAO SINKANTARAKORN/Primary Examiner, Art Unit 2409 09/09/2026
Prosecution Insights