Prosecution Insights
Last updated: November 04, 2026
Application No. 19/065,900

METHOD AND APPARATUS FOR PROVIDING A PROMPT TO A LARGE LANGUAGE MODEL ENGINE

Non-Final OA §101§103
Filed
Feb 27, 2025
Priority
Mar 08, 2024 — provisional 63/562,858
Examiner
SIDDO, IBRAHIM
Art Unit
2681
Tech Center
2600 — Communications
Assignee
Emtelligent Software Ltd.
OA Round
1 (Non-Final)
85%
Grant Probability
Favorable
1-2
OA Rounds
5m
Est. Remaining
97%
With Interview

Examiner Intelligence

Grants 85% — above average
85%
Career Allowance Rate
427 granted / 504 resolved
+22.7% vs TC avg
Moderate +12% lift
Without
With
+12.4%
Interview Lift
resolved cases with interview
Fast prosecutor
2y 1m
Avg Prosecution
7 currently pending
Career history
523
Total Applications
across all art units

Statute-Specific Performance

§101
7.1%
-32.9% vs TC avg
§103
64.5%
+24.5% vs TC avg
§102
15.3%
-24.7% vs TC avg
§112
7.4%
-32.6% vs TC avg
Black line = Tech Center average estimate • Based on career data from 504 resolved cases

Office Action

§101 §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 § 101 Claim 20 is rejected under 35 U.S.C. § 101 because the claim is directed to non-statutory subject matter in the form of a “computer-readable storage medium.” The claim falls outside the scope of patent-eligible subject matter at least because the claimed computer-readable storage medium is broad enough to encompass transitory embodiments. (E.g., one of ordinary skill in the art could reasonably be expected to interpret the claimed computer readable medium as a carrier wave onto which instructions could be coded.) See also the Official Gazette Notice 1351 OG 212 February 23, 2010 “Subject Matter Eligibility of Computer Readable Media” which states in relevant part “[i]n an effort to assist the patent community in overcoming a rejection or potential rejection under 35 U.S.C. § 101 in this situation, the USPTO suggests the following approach. A claim drawn to such a computer readable medium that covers both transitory and non-transitory embodiments may be amended to narrow the claim to cover only statutory embodiments to avoid a rejection under 35 U.S.C. § 101 by adding the limitation ‘non-transitory’ to the claim.” 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. Claim(s) 1-2, 4-7, 9-12, 14-17, 19-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Weber (US 2025/0036673) in view of XU (US 10,929,420). With respect to claim 11 (similarly claims 1 and 20), Weber teaches an apparatus (e.g. electronic device 102 Fig 1 [0026] and/or 800 Fig 8 [0113]) for providing prompt input to a large language model (LLM) engine (e.g. for providing prompt input 302 and/or 312 Fig 3A-B [0070], [0072]), the apparatus (e.g. electronic device 102 Fig 1 [0026] and/or 800 Fig 8 [0113]) comprising: at least one processor (e.g. one or more processors 814, Fig 8 [0113]); at least one memory (e.g. memory 812, Fig 8 [0113]) stored instructions wherein the instructions, when executed by the at least one processor (e.g. storing instructions, when executed by processor 814), cause the processor to: receive one or more input documents containing unstructured text data (e.g. receive one or more input documents 202 Fig 2 containing unstructured text data [0063]); receive a prompt that references the one or more input documents (e.g. receive prompt 302/312 Fig 3A-B that references the one or more input documents 202 [0070], [0072]) and is associated with a task for the LLM engine to perform utilizing the one or more input documents (e.g. and is associated with generating a document as suggested in [0075], [0078] utilizing the document set 202); and transmit, to the LLM engine, the one or more input documents, the prompt, and the document vector data together with instructions to cause the LLM engine to perform the task based on the one or more input documents, the prompt and the document vector data (e.g. transmit to LLM engine 112 which uses LLM 110 to produce output, the one or more input documents, the prompt, and the document vector data together with instructions to cause the LLM engine 112 to perform the task i.e. generating a new document [0023], [0075], [0078] based on the one or more input documents, the prompt and the document vector data, Fig 3A-B [0069]-[0070], [0072]). However, Weber fails to teach generate structured data based on at least one of the one or more input documents; Xu teaches generate structured data based on at least one of the one or more input documents (e.g. generating structured report data based on one or more input sentences, see Figs 1-2 col 8 ln 61-67-col 9 ln 1-54); Weber and Xu are analogous art because they all pertain to generating document vector/structured report data from document set/sentences. Therefore, it would have been obvious to people having ordinary skill in the art before the effective filing date of the claimed invention to modify Weber with the teachings of Xu to include: generate structured data based on at least one of the one or more input documents as suggested by Xu in Figs 1-2 col 8 ln 61-67-col 9 ln 1-54; and Transmit (i.e. after the modification), to the LLM engine, the one or more input documents, the prompt, and the structured data together with instructions to cause the LLM engine to perform the task based on the one or more input documents and the structured data. The benefit of the modification would be to provide summaries of the document set, questions related to the content of the document set, and so forth, Weber [0069]. With respect to claim 12 (similarly claim 2), Weber in view of Xu teaches the apparatus according to claim 11, wherein the instructions, when executed by the at least one processor, cause the processor to generate the structured data comprises instructions that, when executed by the at least one processor, cause the processor to: identify, in the one or more input documents, a span of text (Xu e.g. labels 208, 210, 214, 216, 218 identify, in the one or more input documents, a span of text as suggested in Fig 2 col 9 ln 5-28); identify a concept that is associated with text included in the identified span of text (Xu e.g. identify a concept “Pulmonary arteries.” that is associated with text included in the identified span of text as suggested in col 9 ln 5-28 Fig 2); wherein the structured data includes the identified concept and an identification of the identified span of text associated with the identified concept (Xu e.g. the structured data 206/212 Fig 2 includes the identified concept and an identification of the identified span of text associated with the identified concept). With respect to claim 14 (similarly claim 4), Weber in view of Xu teaches the apparatus of claim 11, wherein the instructions, when executed by the at least one processor, cause the processor to identify the concept that is associated with text included in the identified span of text comprises instructions that, when executed by the at least one processor, cause the processor to identify two or more concepts associated with the text included in the span of text and a relationship between the two or more concepts (Xu e.g. Fig 2 206 and 212 identify two or more concepts associated with the text included in the span of text and a relationship between the two or more concepts). With respect to claim 15 (similarly claim 5), Weber in view of Xu teaches the apparatus of claim 11, wherein the one or more input documents are associated with a context (Weber e.g. the document set is associated with a context, as suggested in [0003], [0023]), and the structured data is generated by a fine-tuned language model engine that is specific to the context (e.g. and the structured data, in the combination, is generated by a fine-tuned language model engine that is specific to the context as suggested in [0040] and claim 5 of Weber). With respect to claim 16 (similarly claim 6), Weber in view of Xu teaches the apparatus of claim 15, wherein the context is medicine, and the one or more input documents are patient medical documents (Weber e.g. generating information derived from medical records and drafting medical forms [0023], the set of documents may be a group of documents pertaining to a specific event, such as medical records for an individual [0003] suggest the context is medicine, and the one or more input documents are patient medical documents). With respect to claim 17 (similarly claim 7), Weber in view of Xu teaches the apparatus of claim 16, wherein the fine-tuned language model engine specific to the context is trained using medical ontologies and human labelled medical data (Weber e.g. The model can be pre-trained using a large document corpus [0039], which include medical ontologies and human labelled medical data as suggested in [0020]). With respect to claim 19 (similarly claim 9), Weber in view of Xu teaches the apparatus of claim 11, wherein the instructions, when executed by the at least one processor, further cause the processor to receive from the LLM engine an output resulting from performing the task based on the one or more input documents and the structured data (Weber e.g. receive an output from LLM 110 resulting from performing the task based on the one or more input documents and the structured data, as suggested in Fig 3A-B [0070]-[0074], Fig 9 S912 [0120]). With respect to claim 10, Weber in view of Xu teaches the method of claim 9, further comprising transmitting the output to a remote device, or displaying the output on a display (Weber e.g. the generated document may be provided to the computing device 102 and rendered at a display [0032], [0080]). Claim(s) 18 and 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Weber (US 2025/0036673) in view of XU (US 10,929,420) and further in view of Wachira (US 2021/0050076). With respect to claim 18 (similarly claim 8), Weber in view of Xu teaches the apparatus of claim 17 including the medical ontologies as suggested in [0020] and [0039]). However, the combination fails to teach wherein the medical ontologies include SNOMED-CT. Wachira teaches medical ontologies that include SNOMED-CT, see [0017]. Weber and Wachira are analogous art because they all pertain to processing individual/patient’s medical records/conditions. Therefore, it would have been obvious to people having ordinary skill in the art before the effective filing date of the claimed invention to modify Weber with the teachings of Wachira to include: wherein the medical ontologies include SNOMED-CT, as suggested by Wachira in [0017]. The benefit of the modification would be to better train the AI model in the medical field. Claim(s) 13 and 3 is/are rejected under 35 U.S.C. 103 as being unpatentable over Weber (US 2025/0036673) in view of XU (US 10,929,420) and further in view of Gattani (US 8,255,786). With respect to claim 13 (similarly claim 3), Weber in view of Xu teaches the apparatus of claim 12 including to identify a concept associated with the text in the identified span of text. However, the combination fails to teach wherein the instructions, when executed by the at least one processor, cause the processor to identify a concept associated with the text in the identified span of text comprises instructions that, when executed by the at least one processor, cause the processor to perform disambiguation of an ambiguous term included in the span of text. Gattani teaches to perform disambiguation of an ambiguous term included in the span of text (e.g. Fig 5 col 11 ln 64-67-col 12 ln 1-38). Weber in view of Xu and Gattani are analogous art because they all pertain to processing documents to identify concepts. Therefore, it would have been obvious to people having ordinary skill in the art before the effective filing date of the claimed invention to modify the combination with the teachings of Gattani to include: wherein the instructions, when executed by the at least one processor, cause the processor to identify a concept associated with the text in the identified span of text comprises instructions that, when executed by the at least one processor, cause the processor to perform disambiguation of an ambiguous term included in the span of text, as suggested by Gattani in Fig 5. The benefit of the modification would be to ensure clarity and accuracy in the system. Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to IBRAHIM SIDDO whose telephone number is (571)272-4508. The examiner can normally be reached 9:00-5:30PM. 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, Akwasi Sarpong can be reached at 5712703438. 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. /IBRAHIM SIDDO/Primary Examiner, Art Unit 2681
Read full office action

Prosecution Timeline

Feb 27, 2025
Application Filed
Oct 21, 2026
Non-Final Rejection mailed — §101, §103 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12784751
USING VISUAL CONTEXT TO IMPROVE A VIRTUAL ASSISTANT
2y 3m to grant Granted Nov 03, 2026
Patent 12775442
AUTOMATED ASSISTANT PERFORMANCE OF A NON-ASSISTANT APPLICATION OPERATION(S) IN RESPONSE TO A USER INPUT THAT CAN BE LIMITED TO A PARAMETER(S)
2y 3m to grant Granted Oct 27, 2026
Patent 12776309
USING A NATURAL LANGUAGE MODEL TO INTERFACE WITH A CLOSED DOMAIN SYSTEM
2y 3m to grant Granted Oct 27, 2026
Patent 12763096
AI-BASED AUTOMATED PERSONALITY AND BEHAVIOR ANALYTIC AND ASSESSMENT SYSTEM AND METHOD
2y 2m to grant Granted Oct 13, 2026
Patent 12763078
INTELLIGENT DIGITAL ASSISTANT IN A MULTI-TASKING ENVIRONMENT
1y 9m to grant Granted Oct 13, 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

1-2
Expected OA Rounds
85%
Grant Probability
97%
With Interview (+12.4%)
2y 1m (~5m remaining)
Median Time to Grant
Low
PTA Risk
Based on 504 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