DETAILED ACTION
Introduction
1. This office action is in response to Applicant’s submission filed on 9/1/2026. Claims 1-13 are pending in the application and have been examined. This application has been made Special by the Petition decision of 4/24/2026.
Notice of Pre-AIA or AIA Status
2. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
3. The information disclosure statements (IDSs) submitted on 5/30/2026 and 8/21/2026 are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statements are being considered by the examiner.
Response to Amendment
4. With regard to the double patenting rejections, those rejections are overcome by the extensive amendments to Claim 1. With regard to the rejection under 35 USC 103, the submitted arguments are moot in view of the new grounds of rejection described below.
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.
5. Claims 1, 6, and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Rammani et al. (US 20230068338, hereinafter “Ram”) in view of “ReviewerGPT? An Exploratory Study on Using Large Language Models for Paper Reviewing” (Liu et al, hereinafter “Liu”) and “Decisions about Turns in Multiparty Conversation: From Perception to Action” (Bohus et al, hereinafter “Bohus”)
With regard to Claim 1, Ram describes:
“An artificial intelligence system that moderates and evaluates discussions, comprising:
an artificial intelligence engine (Paragraph 17, virtual agent 130) comprising a processor; (Paragraph 18, processor 112) and
a large language model; (Paragraph 27, content selection model)
wherein said artificial intelligence engine is configured to, prior to a discussion between said artificial intelligence engine and a plurality of participants:
receive a context from one or more of teacher, student, dialog participant himself or herself, one or more persons ,one or more data sources, a user other than said plurality of participants, or other data sources other than said plurality of participants; (Paragraph 7, an input document is received to generate questions for a user.) and
transmit said context to said artificial intelligence engine; (Paragraph 7, an input document is analyzed by the model to generate questions for a user.)
wherein said artificial intelligence engine is configured to
during said discussion, repeatedly:
receive ongoing conversation from said plurality of participants; (Paragraph 4, the user can answer a series of questions.)
analyze said ongoing conversation to generate one or more analyses, (Paragraph 5, the answers to the series of questions are analyzed.) and
based on said one or more analyses, communicate with said plurality of participants [[to direct a flow of said discussion,]] and, (Paragraph 5, the answers to the series of questions are analyzed to generate feedback to the user.)
at an end of or after said discussion, generate one or more assessments of said one or more participants. (Paragraph 5, the feedback may be answer scores.)
Ram does not explicitly describe “wherein said one or more analyses comprise an analysis of reasoning skills of said plurality of participants” or “wherein directing said flow of said discussion comprises directing one participant of said plurality of participants to respond to reasoning of another participant of said plurality of participants.”
However, section 3 of Liu describes an LLM that evaluates the reasoning of an academic paper and detects errors.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the reasoning evaluation as described by Liu into the system of Ram to automatically evaluate scholarship, as described in Section 1 of Liu.
Ram in view of Liu does not explicitly describe “wherein directing said flow of said discussion comprises directing one participant of said plurality of participants to respond to reasoning of another participant of said plurality of participants.”
However, section 4 of Bohus describes a model that determines which participant in a conversation should speak next.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the speaker determination as described by Bohus into the system of Ram in view of Liu to automatically choose a next speaker in a conversation, as described in Section 1 of Bohus.
With regard to Claim 6, Ram describes “said one or more assessments comprise one or more of: an assessment of a contribution of each participant of said one or more participants; an assessment of behavior of each participant of said one or more participants; and, an assessment of reasoning patterns and skills of said one or more participants.” Paragraph 5 describes that feedback including answer scores for the user is generated and provided to the user. This is cited as “an assessment of a contribution of each participant of said one or more participants.”
With respect to Claim 12, Ram describes “said context comprises written work of one participant of said plurality of participants, and wherein said one or more assessments comprise an assessment of ownership of ideas that measures an ability of said one participant to explain, defend, or adapt arguments in said written work during said discussion.”
Paragraph 5 of Ram describes that feedback scores are generated by the model based on how well the user responds to questions on the subject.
6. Claims 2-5, 7, and 8 are rejected under 35 U.S.C. 103 as being unpatentable over Ram in view of Liu and Bohus and further in view of Bar-On et al. (US 20220270603, hereinafter “Bar”)
With regard to Claim 2, Ram in view of Liu and Bohus does not explicitly describe this subject matter. However, Bar describes “said discussion comprises a videoconference among said one or more participants; each participant of said one or more participants interacts with a videoconferencing client; and, said artificial intelligence engine is coupled to a videoconferencing server that coordinates said videoconference.” Paragraph 29 describes that multiple participants can participate through a video conference system, and the conference is coordinated by the voice interface system (AI engine).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the videoconference interface as described by Bar into the system of Ram in view of Liu and Bohus to facilitate a meeting with multiple remote participants, as described in paragraph 29 of Bar.
With regard to Claim 3, Ram in view of Liu and Bohus does not explicitly describe this subject matter. However, Bar describes “said discussion comprises an in-person meeting among said one or more participants; and, said artificial intelligence engine is coupled to: one or more speakers located at said in-person meeting; and, one or more microphones located at said in-person meeting.” Paragraph 29 describes that the meeting participants may be physically present, and paragraph 52 describes that the voice interface system may include a microphone for voice input.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the microphone interface as described by Bar into the system of Ram in view of Liu and Bohus to facilitate a meeting with multiple physically present participants, as described in paragraph 29 of Bar.
With regard to Claim 4, Ram in view of Liu and Bohus does not explicitly describe this subject matter. However, Bar describes “said one or more analyses comprise one or more of: analysis of participation patterns of said one or more participants; analysis of a flow of topics in said discussion; and, analysis of reasoning skills of said one or more participants.” Paragraph 46 of Bar describes that the AI agent determines the current topic being discussed. Over time, this will provide the flow of topics.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the topic tracking as described by Bar into the system of Ram in view of Liu and Bohus to allow the agent to respond with content pertinent to the current topic, as described in paragraph 46 of Bar.
With regard to Claim 5, Ram in view of Liu and Bohus does not explicitly describe this subject matter. However, Bar describes “direct the flow of said discussion comprises one or more of: determine who should speak next; direct one participant to respond to another participant’s reasoning; interrupt or redirect said discussion; and, adjust said discussion based on observed reasoning behavior.” Paragraph 82 describes that the AI agent includes a flow interactor 212 which adjusts the discussion based on the previous discussion.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the flow interactor as described by Bar into the system of Ram in view of Liu and Bohus to allow the agent to direct the topic flow, as described in paragraph 82 of Bar.
With regard to Claim 7, Ram in view of Liu and Bohus does not explicitly describe this subject matter. However, Bar describes “a text-to-speech module that converts text into audio output; and, a speech-to-text module that converts audio input into text.” Paragraph 52 describes that the AI agent includes a voice-to-text module. Paragraph 54 describes that the AI agent may include a voice synthesizer that generates voice based on text.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the speech-to-text module and voice synthesizer as described by Bar into the system of Ram in view of Liu and Bohus to allow the agent to communicate with the users, as described in paragraphs 52 and 54 of Bar.
With regard to Claim 8, Ram in view of Liu and Bohus does not explicitly describe this subject matter. However, Bar describes “receive said ongoing conversation from said one or more participants as audio input; (Paragraph 52 describes that the AI agent receives audio input from the users.)
translate said audio input to text input via said speech-to-text module; (Paragraph 52 describes that the AI agent generates text with a voice-to-text module.)
generate communication to said one or more participants as text output; (Paragraph 54 describes that the AI agent receives text to communicate to the users.)
translate said text output to audio output via said text-to-speech module; (Paragraph 54 describes that the AI agent generates voice communication based on the input text.) and,
communicate with said one or more participants to direct said flow of said discussion via said audio output.” (Paragraph 54 describes that the AI agent outputs the voice communication to the users.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the speech-to-text module and voice synthesizer as described by Bar into the system of Ram in view of Liu and Bohus to allow the agent to communicate with the users, as described in paragraphs 52 and 54 of Bar.
7. Claims 9-11 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over Ram in view of Liu and Bohus and further in view of Anders et al. (US 20190042556, hereinafter “Anders”).
With respect to Claim 9, Ram in view of Liu and Bohus does not explicitly describe this subject matter. However, Anders describes “said context comprises participant-submitted written work submitted by one participant of said plurality of participants, and wherein said one or more assessments comprise a determination, based on said ongoing conversation received from said one participant, of whether said one participant authored said participant-submitted written work.”
Paragraph 25 of Anders describes that a model determines phrases associated with an author to identify writing by that author.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the author identification as described by Anders into the system of Ram in view of Liu and Bohus to allow the model to identify a writing style of an author, as described in paragraph 25 of Anders.
With respect to Claim 10, Ram in view of Liu and Bohus does not explicitly describe this subject matter. However, Anders describes “said context comprises written work generated by one participant of said plurality of participants, wherein said artificial intelligence engine is further configured to generate at least one question based on said written work, and wherein said one or more assessments comprise a determination of whether said one participant authored said written work based on at least a portion of said ongoing conversation received from said one participant.
Paragraph 25 of Anders describes that a model determines phrases associated with an author to identify writing by that author. Paragraph 28 describes that the user can enter further natural language input to be analyzed by the model.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the author identification as described by Anders into the system of Ram in view of Liu and Bohus to allow the model to identify a writing style of an author, as described in paragraph 25 of Anders.
With respect to Claim 11, Ram in view of Liu and Bohus does not explicitly describe this subject matter. However, Anders describes “said context comprises written work of one participant of said plurality of participants, and wherein said one or more assessments comprise an assessment of authorial consistency that measures alignment between reasoning of said one participant during said discussion and prior claims in said written work.
Paragraph 25 of Anders describes that a model determines phrases consistent with an author’s previous work to identify writing by that author.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the author identification as described by Anders into the system of Ram in view of Liu and Bohus to allow the model to identify a writing style of an author, as described in paragraph 25 of Anders.
With respect to Claim 13, Ram in view of Liu and Bohus does not explicitly describe this subject matter. However, Anders describes “said context comprises written work of one participant of said plurality of participants, and wherein said one or more assessments comprise an assessment of authenticity of scholarship that measures consistency between reasoning of said one participant during said discussion and said written work.
Paragraph 25 of Anders describes that a model determines phrases associated with an author to identify writing by that author. Paragraph 28 describes that the user can enter further natural language input to be analyzed by the model.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the author identification as described by Anders into the system of Ram in view of Liu and Bohus to allow the model to identify a writing style of an author, as described in paragraph 25 of Anders.
Conclusion
8. The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
“Exploring Emerging Technologies for Requirements Elicitation Interview Training: Empirical Assessment of Robotic and Virtual Tutors” (Gorer et al.) describes an AI tutor that interacts with students.
9. 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.
10. Any inquiry concerning this communication or earlier communications from the examiner should be directed to EDWARD TRACY whose telephone number is (571)272-8332. The examiner can normally be reached Monday-Friday 9 AM- 5PM.
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, Bhavesh Mehta can be reached on 571-272-7453. 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.
/EDWARD TRACY JR./Examiner, Art Unit 2656
/BHAVESH M MEHTA/Supervisory Patent Examiner, Art Unit 2656
