Prosecution Insights
Last updated: April 19, 2026
Application No. 18/782,617

METHOD OF EXECUTING TASK FOR LARGE LANGUAGE MODEL, DEVICE, AND STORAGE MEDIUM

Non-Final OA §103
Filed
Jul 24, 2024
Examiner
HOQUE, NAFIZ E
Art Unit
2693
Tech Center
2600 — Communications
Assignee
BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
OA Round
1 (Non-Final)
75%
Grant Probability
Favorable
1-2
OA Rounds
3y 1m
To Grant
99%
With Interview

Examiner Intelligence

Grants 75% — above average
75%
Career Allow Rate
456 granted / 608 resolved
+13.0% vs TC avg
Strong +24% interview lift
Without
With
+23.7%
Interview Lift
resolved cases with interview
Typical timeline
3y 1m
Avg Prosecution
20 currently pending
Career history
628
Total Applications
across all art units

Statute-Specific Performance

§101
11.5%
-28.5% vs TC avg
§103
42.7%
+2.7% vs TC avg
§102
23.6%
-16.4% vs TC avg
§112
11.3%
-28.7% vs TC avg
Black line = Tech Center average estimate • Based on career data from 608 resolved cases

Office Action

§103
DETAILED ACTION Notice of Pre-AIA or AIA Status The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . Claim Rejections - 35 USC § 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 1, 16, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Dao, Tri (“FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning”) in view of Wang et al. (US Pub 2023/0133305*). Regarding claim 1, Dao discloses a method of executing a task for a large language model, comprising: determining, by using a determination unit, a target attention task from a plurality of attention tasks to be processed (see section 3.1 – plurality of tile block sub computation), wherein the target attention task is a task corresponding to a non-fully masked region of the feature to be processed (see section 3.1 – Dao does not skip those that are non-fully masked and partially masked blocks), and the mask position represents mask endpoint positions in at least two non-intersecting intervals in a mask matrix corresponding to the feature to be processed (section 3.1, page 6 – “As FlashAttention and FlashAttention-2 already operate by blocks, for any blocks where all the column indices are more than the row indices (approximately half of the blocks for large sequence length), we can skip the computation of that block” – therefore mask matrix is divided into two regions); and executing the target attention task by using a computing unit, so as to obtain an attention feature (see section 3.1 – accumulated block outputs produces the final attention feature). Dao does not disclose based on a sparse representation corresponding to a feature to be processed, the sparse representation represents a mask position of the feature to be processed. Wang discloses based on a sparse representation corresponding to a feature to be processed, the sparse representation represents a mask position of the feature to be processed (para 0039-0044). Therefore, it would have been obvious to a person of ordinary skilled in the art before the effective filing date of the claimed invention to modify Dao with the teachings of Wang in order to avoid unnecessary computation on masked regions. Regarding claim 16, see rejection of claim 1. Regarding claim 20, see rejection of claim 1. Allowable Subject Matter Claims 2-15, and 17-19 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 NAFIZ E HOQUE whose telephone number is (571)270-1811. The examiner can normally be reached M-F 8-5. 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, Ahmad Matar can be reached at (571)272-7488. 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. /NAFIZ E HOQUE/ Primary Examiner, Art Unit 2693
Read full office action

Prosecution Timeline

Jul 24, 2024
Application Filed
Mar 07, 2026
Non-Final Rejection — §103 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12581017
COMMUNICATION ROUTING FOR CONTACT CENTER
2y 5m to grant Granted Mar 17, 2026
Patent 12579363
Incentive Aware-Aggregation Of Generative Models
2y 5m to grant Granted Mar 17, 2026
Patent 12573372
TEXT-TO-SPEECH SYSTEM WITH VARIABLE FRAME RATE
2y 5m to grant Granted Mar 10, 2026
Patent 12574459
VOICE-SYNCHRONIZED VISUAL INTERFACE
2y 5m to grant Granted Mar 10, 2026
Patent 12547848
One-Shot Visual Language Reasoning Over Graphical Depictions of Data
2y 5m to grant Granted Feb 10, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

AI Strategy Recommendation

Get an AI-powered prosecution strategy using examiner precedents, rejection analysis, and claim mapping.
Powered by AI — typically takes 5-10 seconds

Prosecution Projections

1-2
Expected OA Rounds
75%
Grant Probability
99%
With Interview (+23.7%)
3y 1m
Median Time to Grant
Low
PTA Risk
Based on 608 resolved cases by this examiner. Grant probability derived from career allow rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month