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
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 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Mahar et al. (US 2025/0097345 A1), hereinafter “Mahar”, and in view of Cao (US 2025/0139413 A1), hereinafter “Cao”.
As per claim 1, Mahar teaches a method comprising:
“identifying, in a contact center application of a contact center agent, a start of an assisted leg of an interaction of a user with a system” at [0011]-[0012], [0050]-[0054];
(Mahar teaches a user communicates with the automated agent 366 that the user wants to change a product purchased to a new product. In the event the order of the originally purchased product may not be canceled, the automated agent 366 may transfer the case to a human agent as the automated agent 366 may not resolve the issue)
“retrieving, for the user, a user interaction summary that summarizes events that have previously occurred in the interaction” at [0012], [0044]-[0045], [0052]-[0054] and Figs. 1-2;
(Mahar teaches the system captures data associated with the actions (i.e., “events”) that were attempted by an automated agent during messaging session between the automated agent and the user, generates presents the summary of the actions in the messaging platform. The human agent may access the messaging platform 100 including the summary of the attempted action)
“extracting, based on the user interaction summary, a
(Mahar teaches extracting user information, case details, order information and actions based on the user interaction summary)
“providing the between the generative LLM AI engine and the contact center agent” at [0014]-[0022], [0030], [0054]-[0055];
(Mahar teaches a transcript of the messaging session including the communication 114 and the action summary 112 are stored in a database (i.e., “AI engine”) and associated with the case number 119. The distributed databases stores purchase orders, user information, product information. The transcript of the message session including communication and the summary may be stored in the transcript database 346. The human agent may use the customer service application 370 to query the transcript database to retrieve the transcript)
“receiving first event information regarding agent input and agent interaction with the user, wherein the first event information includes at least one query to the generative LLM AI engine; providing the at least one query to the generative LLM AI engine” at [0015], [0046], [0054]-[0055];
(Mahar teaches an agent may view a different messaging window 102 by selecting a new case number using window tab drop menu. A search input box 120 may be rendered on the top of the messaging platform. A human agent may retrieve the transcript of the communication between the automated agent 366 and the user at a later date to determine what actions were attempted during the messaging session. The human agent may use the customer service application 370 to query the transcript database to retrieve the transcript)
“receiving, for each query of the at least one query, a query response from the generative LLM AI engine; updating the contact center application in response to at least one query response received from the generative LLM AI engine” at [0015], [0046], [0054]-[0055] and Fig. 1.
(Mahar teaches the human agent may use the customer service application 370 to query the databases to retrieve the transcripts, orders, actions, customer information and update the application to display the response information, as shown at Fig. 1)
Mahar does not explicitly teach extracting, based on the user interaction summary, a generative large language model (LLM) artificial intelligence (AI) context prompt; providing the generative LLM AI context prompt to a generative LLM AI engine to set a context for the generative LLM AI engine for a generative LLM AI session between the generative LLM AI engine and the contact center agent as claimed. However, Cao teaches a method of using a generative large language model to response to user queries or requests at [0026], including the steps of:
“retrieving, for the user, a user interaction summary that summarized events that have previously occurred in the interaction” at [0040] and Fig. 4;
(Cao teaches retrieving a profile for the user and obtaining activity representing conversation between the user 210 and a host. Cao teaches at Fig. 4 a user interaction summary that summarizes activities that have previously occurred, e.g., “Prior to contact with the customer center, Messi mentioned Bot that his flight is canceled so he would like to cancel the reservation with full refund”)
“extracting, based on the user interaction summary, a generative large language model (LLM) artificial intelligence (AI) context prompt” at [0042] and Fig. 4;
(Cao teaches the prompt generation component 250 generates the prompt 400, shown in Fig. 4. The prompt 400 includes the LLM context prompt 420 which includes the user interaction summary)
“providing the generative LLM AI context prompt to a generative LLM AI engine to set a context for the generative LLM AI engine for a generative LLM AI session between the generative LLM AI engine and the contact center agent” at [0044] and Fig. 4;
(Cao teaches providing the prompt 420 to the generative machine learning model 260, which implement a LLM network. The LLM can process the prompt 400 and generate a customized, personalized, and intelligent message that is based on the prompt 400)
“receiving first event information regarding agent input and agent interaction with the user, wherein the first event information includes at least one query to the generative LLM AI engine; providing the at least one query to the generative LLM AI engine” at [0043]-[0044] and Fig. 4;
(Cao teaches receiving LLM receives the prompt 400 which include a query 410 to query the LLM to generate a greeting message to the user)
“receiving, for each query of the at least one query, a query response from the generative LLM AI engine; updating the contact center application in response to at least one query response received from the generative LLM AI engine” at [0043]-[0044] and Fig. 4.
(Cao teaches the LLM generates a greeting message in response to the query and updating the application to display the message to the user)
Thus, it would have been obvious to one of ordinary skill in the art to combine Cao with Mahar’s teaching by utilizing a generative ML model to generate a message that responses to the user interaction. “This, in effect reduces the amount of computational resources needed to be dedicated and consumed by a given user interface channel (e.g., associated with a human agent), which frees up such resources for other task and satisfying other search requests”, as suggested by Cao’s at [0016].
As per claim 2, Mahar and Cao teach the method of claim 1 discussed above. Mahar also teaches: wherein “the events that have previously occurred in the interaction occurred during a self-serve leg of the interaction” at [0050]-[0054].
As per claim 3, Mahar and Cao teach the method of claim 2 discussed above. Mahar also teaches: wherein “the assisted leg of the interaction starts in response to a transfer to the contact center agent during the self-serve leg of the interaction” at [0054].
As per claim 4, Mahar and Cao teach the method of claim 1 discussed above. Mahar also teaches: “displaying information from the user interaction summary in the contact center application” at Fig. 1.
As per claim 5, Mahar and Cao teach the method of claim 4 discussed above. Cao also teaches: “extracting a generative LLM AI generated greeting from the user interaction summary and displaying the generative LLM AI generated greeting in the contact center application, wherein the generative LLM AI generated greeting was previously generated by the generative LLM AI engine” at [0043]-[0044] and Figs. 4-5.
As per claim 6, Mahar and Cao teach the method of claim 1 discussed above. Cao also teaches: wherein “the generative LLM AI context prompt includes enriched event data for the events that have previously occurred in the interaction” at [0043]-[0044] and Fig. 4.
As per claim 7, Mahar and Cao teach the method of claim 6 discussed above. Cao also teaches: wherein “the enriched event data includes contact center application event data generated by a contact center application used by the user that is merged with event context prompts that provide semantic descriptions of the contact center application event data” at [0043]-[0044] and Fig. 4.
As per claim 8, Mahar and Cao teach the method of claim 7 discussed above. Cao also teaches: wherein “the enriched event data includes the contact center application event data that is merged with function output obtained by invoking at least one function of the system with contact center application event data as input” at [0033]-[0037], [0043]-[0044] and Fig. 4.
As per claim 9, Mahar and Cao teach the method of claim 1 discussed above. Cao also teaches: “providing the generative LLM AI context prompt to the generative LLM AI engine and an insight prompt that prompts the generative LLM AI engine to generate an insight from the generative LLM AI context prompt; receiving, from the generative LLM AI engine, the insight generated from the generative LLM AI context prompt; prompting the generative LLM AI engine to update the context of the generative LLM AI engine using the insight; and displaying the insight in the contact center application” at [0043]-[0044] and Figs. 4-5.
As per claim 10, Mahar and Cao teach the method of claim 1 discussed above. Mahar also teaches: “receiving second event information regarding agent interaction with the user, wherein the second event information comprises information for at least one event resulting from a query response received from the generative LLM AI engine” at [0024], [0039]-[0045].
As per claim 11, Mahar and Cao teach the method of claim 10 discussed above. Mahar also teaches: “the second event information describes the contact center agent providing at least some information in the query response to the user” at [0024], [0039]-[0045].
As per claim 12, Mahar and Cao teach the method of claim 10 discussed above. Cao also teaches: “prompting the generative LLM AI engine to update the context of the generative LLM AI engine with the first event information and the second event information” at [0043]-[0044].
As per claim 13, Mahar and Cao teach the method of claim 1 discussed above. Mahar also teaches: “determining a user identifier from the user interaction summary; using the user identifier to retrieve historical user information summaries of previous interaction of the user with the system; prompting the generative LLM AI engine to generate an overall summary of interactions of the user with the system based on the user interaction summary and the historical user interaction summaries; receiving the overall summary from the generative LLM AI engine; prompting the generative LLM AI engine to update the context of the generative LLM AI engine using the overall summary; and display the overall summary in the contact center application” at [0012], [0044]-[0045], [0052]-[0054] and Figs. 1-2.
As per claim 14, Mahar and Cao teach the method of claim 1 discussed above. Mahar also teaches: “the contact center application comprises a first user interface portion that display user-agent interaction information and a second user interface portion that displays agent- generative LLM AI engine interaction information” at Figs. 1-2.
Claims 15-20 recite similar limitations as in claims 1-14 and are therefore rejected by the same reasons.
Response to Arguments
Applicant's arguments filed 9/04/2026 have been fully considered but they are not persuasive. The examiner respectfully traverses Applicant’s arguments.
Regarding claim 1, Applicant argued that “nothing in either reference nor in their combination disclose a human contact center agent submitting a query to a generative LLM AI engine within a dedicated agent-engine session and using the engine’s response to assist the user, as required by claim 1”. On the contrary, Cao teaches at [0044] and Figs. 2, 4 the step of providing the prompt 420 to the generative machine learning model 260, which implements a LLM network. The LLM can process the prompt 400 and generate a customized, personalized, and intelligent message that is based on the prompt 400.
Applicant further argued that “Cao’s query 410 is not agent input at all – it is machine generated by the prompt generation component 250” and “no human (and no agent of any kind) formulates or submits that query”. On the contrary, the claim 1 does not recite “human contact center agent” as argued, by instead recites “contact center agent”, which could be interpreted as a bot or a virtual agent.
In light of the foregoing arguments, the 35 U.S.C 102 rejection is hereby sustained.
Conclusion
THIS ACTION IS MADE FINAL. 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 KHANH B PHAM whose telephone number is (571)272-4116. The examiner can normally be reached Monday - Friday, 8am to 4pm.
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, Sanjiv Shah can be reached at (571)272-4098. 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.
/KHANH B PHAM/Primary Examiner, Art Unit 2166
October 1, 2026
Prosecution Insights