Prosecution Insights
Last updated: May 29, 2026
Application No. 18/219,905

SYSTEMS AND METHODS FOR CONVERSATION ORCHESTRATION USING LARGE LANGUAGE MODELS

Final Rejection §101
Filed
Jul 10, 2023
Priority
Feb 21, 2023 — provisional 63/447,274
Examiner
JACKSON, JAKIEDA R
Art Unit
2657
Tech Center
2600 — Communications
Assignee
Kore AI Inc.
OA Round
3 (Final)
74%
Grant Probability
Favorable
4-5
OA Rounds
2m
Est. Remaining
90%
With Interview

Examiner Intelligence

Grants 74% — above average
74%
Career Allowance Rate
675 granted / 911 resolved
+12.1% vs TC avg
Strong +15% interview lift
Without
With
+15.4%
Interview Lift
resolved cases with interview
Typical timeline
3y 0m
Avg Prosecution
24 currently pending
Career history
946
Total Applications
across all art units

Statute-Specific Performance

§101
13.3%
-26.7% vs TC avg
§103
66.8%
+26.8% vs TC avg
§102
12.8%
-27.2% vs TC avg
§112
1.1%
-38.9% vs TC avg
Black line = Tech Center average estimate • Based on career data from 911 resolved cases

Office Action

§101
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 Applicants argue that the prior art cited fails to teach the claims as amended including selecting a large language model (LLM) from a plurality of LLMs to perform response generation for the one or more utterances received from the customer device based on an execution state of the dialog flow. Applicants’ arguments are persuasive and the art rejection has been withdrawn. Regarding the 101 rejection, according to Step 1, it includes determining whether the claims fall within a statutory category. The claims include a method, server and medium. Therefore, the claims fall within a statutory category. Step 2A Prong one, includes evaluating whether the claims recite a judicial exception. The claims recite a judicial exception, therefore an evaluation is done to determine if the claims fit into one of the categories. As explained below, the claims fit into the mental processing and organized human activity concept. Prong 2B is used to evaluate whether the claims recite additional elements that integrate the exception into a practical application. As explained below the judicial exception is not integrated into a practical application. In particular, the claim only recites additional elements which are recited at a high-level of generality (i.e., as a generic processor performing a generic computer function) such that it amounts no more than mere instructions to apply the exception using a generic computer component. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements amount to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The claims are not patent eligible. It is explained that the present invention teaches orchestrating an online customer conversation with natural language inputs by way of example, by executing a dialog flow comprising a plurality of interconnected nodes, selecting an LLM based on an execution state of the dialog flow, prompting an LLM and validating the adherence of the LLM output to business rules and conversation rules, and transmitting a response to the customer device are not mental steps and simply cannot be performed by a human mind. As explained below, such steps are non-statutory (abstract), Furthermore, Applicants explain that the claims recite specific improvements to the technical solution directed towards improving the functionality of conversational artificial intelligence systems to a technical problem relating to prior issues with the accuracy of functional conversational artificial intelligence systems. The claims execute a dialog flow, selects a LLM, receives a plurality of outputs, extracts entities and transmits the response and does not meaningfully apply the gathered information to some useful process in a particular technological environment or employ a particular machine. Even if there are aspects of the invention being tied to a particular technology, merely limiting the field of use of the abstract idea to a particular existing technological environment does not render the claims any less abstract. Furthermore, the claims need to explicitly recite the details of the improvements. Therefore, the claims remain non-statutory under 101. Lastly, it is noted that automating requires routine skill in the art and providing an automatic or mechanical means to replace a manual activity which accomplished the same result is not sufficient to transform the abstract idea into patent eligible subject matter. Claim Rejections - 35 USC § 101 35 U.S.C. 101 reads as follows: Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title. Claims 1-15 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. The claims are directed to organizing human activity (managing and conducting customer service conversations), extracting and validating information (collecting entities, checking them against business rules), and using probabilistic language processing to select appropriate responses. These concepts fall within the realm of the judicially excepted categories of abstract ideas, specifically certain methods of organizing human activity and mental processes/information processing that can be performed by a person. Statutory Category; Claim 1 recites “A method for orchestrating an online customer conversation by a virtual assistant server….” The claim is directed to a process and therefore meets the statutory category of 35 U.S.C. § 101. Step 2A — Judicial Exception (Abstract Idea): Claim 1 recites the steps including, inter alia, “automatically executing a dialog flow corresponding to a use case of one or more utterances received from a customer device,” “selecting a large language model (LLM) from a plurality of LLMs,” “receiving a plurality of outputs from the selected one of the plurality of LLMs,” “validating adherence of: the extracted one or more entities to one or more business rules; and the response to one or more conversation rules,” and “transmitting the response … to the customer device when the corresponding validation is successful.” These recited concepts are considered an abstract idea, specifically certain methods of organizing human activity and information processing (managing customer interactions, extracting entities, applying business/conversation rules, and generating/validating responses). As such, claim 1 recites a judicial exception. Step 2A — Integration into a Practical Application Claim 1 refers to a “virtual assistant server,” selection among LLMs, and a “probabilistic approach to language generation,” but the claim does not recite specific, unconventional machine implementation details or a specific technological improvement to the functioning of the “virtual assistant server” or the LLMs themselves. The claim elements are recited at a high level of generality and use generic computer functions (selection, prompting, receiving outputs, validation, transmission). Accordingly, the claim does not integrate the abstract idea into a practical application sufficient to render the claim eligible under step 2A. Step 2B — “Inventive Concept” / Significantly More: Because claim 1 is directed to an abstract idea, the additional elements must supply an inventive concept that transforms the abstract idea into patent-eligible subject matter. The additional elements recited in claim 1 — including “selecting a large language model (LLM) from a plurality of LLMs,” “receiving a plurality of outputs … based on a plurality of prompts,” and “validating adherence … using a probabilistic approach to language generation based on patterns learned from the one or more conversation rules and the one or more business rules” — are presented functionally and at a high level. The claim does not identify a particular, unconventional algorithm, specialized hardware, or a specific non-generic configuration that provides a technological improvement beyond the abstract idea. On the present record, the recited additional elements do not amount to “significantly more” than the judicial exception. Therefore, Claim 1 is rejected under 35 U.S.C. § 101 as being directed to a judicial exception (an abstract idea) without additional elements that amount to significantly more. The dependent claims recite making determinations, generating data based on validation failure and receiving data, which is non-statutory (abstract). Conclusion Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a). A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action. Any inquiry concerning this communication or earlier communications from the examiner should be directed to JAKIEDA R JACKSON whose telephone number is (571)272-7619. The examiner can normally be reached Mon - Fri 6:30a-2:30p. 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, Daniel Washburn can be reached at 571.272.5551. 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. /JAKIEDA R JACKSON/Primary Examiner, Art Unit 2657
Read full office action

Prosecution Timeline

Show 1 earlier event
May 05, 2025
Non-Final Rejection mailed — §101
Aug 01, 2025
Response Filed
Oct 16, 2025
Non-Final Rejection mailed — §101
Jan 13, 2026
Response Filed
Apr 01, 2026
Final Rejection mailed — §101
Apr 30, 2026
Interview Requested
May 14, 2026
Applicant Interview (Telephonic)
May 15, 2026
Examiner Interview Summary

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12639530
SYSTEMS AND METHODS FOR A CONVERSATIONAL ASSISTANT USING ARTIFICIAL INTELLIGENCE IN A FREIGHT MANAGEMENT PLATFORM
2y 6m to grant Granted May 26, 2026
Patent 12633282
PROCESSING METHOD AND PROCESSING APPARATUS OF SOUND SIGNAL
2y 2m to grant Granted May 19, 2026
Patent 12609102
TRAINING DATASET GENERATION FOR SPEECH-TO-TEXT SERVICE
4y 6m to grant Granted Apr 21, 2026
Patent 12609111
CLUSTERING AND MINING ACCENTED SPEECH FOR INCLUSIVE AND FAIR SPEECH RECOGNITION
2y 1m to grant Granted Apr 21, 2026
Patent 12603079
PROVIDING A REPOSITORY OF AUDIO FILES HAVING PRONUNCIATIONS FOR TEXT STRINGS TO PROVIDE TO A SPEECH SYNTHESIZER
3y 3m to grant Granted Apr 14, 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

4-5
Expected OA Rounds
74%
Grant Probability
90%
With Interview (+15.4%)
3y 0m (~2m remaining)
Median Time to Grant
High
PTA Risk
Based on 911 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