Prosecution Insights
Last updated: July 17, 2026
Application No. 18/946,726

EFFICIENT RAG MODEL FOR MEDICAL APPLICATIONS

Final Rejection §103
Filed
Nov 13, 2024
Priority
Nov 14, 2023 — provisional 63/598,873
Examiner
LE, DEBBIE M
Art Unit
2168
Tech Center
2100 — Computer Architecture & Software
Assignee
Datum Point Labs Inc.
OA Round
2 (Final)
89%
Grant Probability
Favorable
3-4
OA Rounds
1y 0m
Est. Remaining
99%
With Interview

Examiner Intelligence

Grants 89% — above average
89%
Career Allowance Rate
712 granted / 796 resolved
+34.4% vs TC avg
Moderate +10% lift
Without
With
+10.4%
Interview Lift
resolved cases with interview
Typical timeline
2y 8m
Avg Prosecution
7 currently pending
Career history
804
Total Applications
across all art units

Statute-Specific Performance

§101
2.1%
-37.9% vs TC avg
§103
60.0%
+20.0% vs TC avg
§102
24.6%
-15.4% vs TC avg
§112
0.5%
-39.5% vs TC avg
Black line = Tech Center average estimate • Based on career data from 796 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 . Response to Amendment Applicant’s remarks/amendments filed on February 9, 2026. Claims 1, 8 and 15 have been amended. Claims 1-20 are pending. Response to Arguments Applicant’s arguments with respect to claims 1-20, filed on February 9, 2026 were amended. These claims 1-20 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument. Applicant’s arguments, filed on February 9, 2026, with respect to the rejections §102 and §103 of claims 1-20, have been fully considered and are persuasive based on the claim amendments. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of Berglund et al. (US 2024/0403341 A1) in view of Grenader et al (US 2024/0362213) and further in view of Zhong et al. (US 2025/0094464 A1) Claim Rejections - 35 USC § 103 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 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, 7, 8, 14 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Berglund et al. (US 2024/0403341 A1) in view of Grenader et al (US 2024/0362213) As per claim 1, Berglund discloses a method of retrieval augmented generation, comprising: receiving, via a data interface, a query (para. 0032); retrieving a plurality of text chunks from a database based on a comparison of contents of the database with an embedding of the query (para. 0013); inputting a prompt to a neural network based language model, the prompt including the plurality of text chunks and the query (para. 0014; 0072); and outputting, via the neural network based language model, a text output based on the prompt (para. 0014; para. 0021). Burglund does not explicitly teach, but Grenader teaches wherein the embedding is generated by a quantized sentence embedding model; wherein the language model is executed locally on a client or on-premise computing device to preserve data privacy (para. 0070, 0185-0191, 194-196). Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention was made to modify the teachings of Berglund to implement the above steps as taught by Grenader because it would enable the system to keep a response data within the security boundary to user’s desired based on their privacy, as suggested by Grenader (para. 0181). As per claim 7, Berglund further teaches wherein the retrieving the plurality of text chunks includes retrieving a predetermined number of text chunks (para. 0014). As per claim 14 has similar limitations as recited in claim 7; therefore, it is rejected under the same subject matter. As per claims 8 and 15, these independent claims recite several elements that are similar to the elements recited in claim 1, except in the context of a computer-readable medium, and a system, respectively. Therefore, they are rejected at least for the same reasons as claim 1. Claims 2-6, 9-13, 16-20 are rejected under 35 U.S.C. 103 as being unpatentable over Berglund et al. (US 2024/0403341 A1) in view of Grenader et al (US 2024/0362213) and further in view of Zhong et al. (US 2025/0094464 A1). As per claim 2, Berglund teaches generating the plurality of text chunks from an input text based on a similarity of the input text (para. 0029). In additional, Berglund also teaches “sequential sentences” (para. 0029, as would be equivalent to “consecutive sentences”). However, Zhong discloses consecutive sentences of the input text (para. 0094-0095). Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention was made to modify the teachings of Berglund and Grenader to implement the above steps as taught by Zhong because it would improve the identified passages of text that are relevant in order for retrieval of text passages having highest similarity. As per claim 3, Berglund further teaches wherein the generating the plurality of text chunks further comprises: generating, via a neural network based model, respective embeddings of the consecutive sentences of the input text, wherein the similarity is based on a comparison of the respective embeddings (para. 0029). As per claim 4, Zhong further teaches wherein the similarity is further based on a weighting of the consecutive sentences according to a distance of the sentences from each other in the input text (para. 0092). As per claim 5, Zhong further teaches wherein the generating the plurality of text chunks further comprises grouping consecutive sentences together when the similarity is above a predetermined threshold (para. 0095). As per claim 6, Berglund and Zhong further teach wherein the generating the plurality of text chunks further comprises further grouping the consecutive sentences into smaller groups based on the grouping being over a threshold size (Berglund: para. 0029; Zhong: 0096). As per claims 9-13, 16-20 have similar limitations as recited in claims 2-6; therefore, they are rejected under the same subject matter. Conclusion The prior art made of record, listed on form PTO-892, and not relied upon, if any, is considered pertinent to applicant's disclosure. Any inquiry concerning this communication or earlier communications from the examiner should be directed to DEBBIE M LE whose telephone number is (571)272-4111. The examiner can normally be reached 9:00-5:00. 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, Charles Rones can be reached at 571-272-4085. 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. /DEBBIE M LE/Primary Examiner, Art Unit 2168 May 23, 2026
Read full office action

Prosecution Timeline

Nov 13, 2024
Application Filed
Sep 08, 2025
Non-Final Rejection mailed — §103
Feb 09, 2026
Response Filed
May 28, 2026
Final Rejection mailed — §103 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12681974
SYSTEMS AND METHODS FOR DATABASE CLUSTERING IN PARSING LEGAL SEARCH QUERIES
1y 10m to grant Granted Jul 14, 2026
Patent 12681984
Audiovisual content curation system
1y 5m to grant Granted Jul 14, 2026
Patent 12675538
GUIDED WEB CRAWLER FOR AUTOMATED IDENTIFICATION AND VERIFICATION OF WEBPAGE RESOURCES
1y 6m to grant Granted Jul 07, 2026
Patent 12669950
Implementing Guardrails For Non-Disruptive Migration Of Workloads
2y 2m to grant Granted Jun 30, 2026
Patent 12645722
METHOD AND SYSTEM FOR AI-BASED WEDDING PLANNING PLATFORM
1y 8m to grant Granted Jun 02, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

Strategy Recommendation AI-generated — please review before filing

Get a prosecution strategy drawn from examiner precedents, rejection analysis, and claim mapping.
Typically takes 5-10 seconds — AI-generated, attorney review required before filing

Prosecution Projections

3-4
Expected OA Rounds
89%
Grant Probability
99%
With Interview (+10.4%)
2y 8m (~1y 0m remaining)
Median Time to Grant
Moderate
PTA Risk
Based on 796 resolved cases by this examiner. Grant probability derived from career allowance 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