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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on August 14, 2025 has been entered.
Response to Amendment
This Non-Final Office Action is in response to the applicant’s remarks and arguments filed on June 25, 2025.
Claims 1, 17 and 20 were amended.
Claim 18 was cancelled.
Claims 1-17 and 19-20 remain pending in the application. Claims 1-17 and 19-20 are being considered on the merits.
Response to Arguments
Applicant argues that:
“The rejection is respectfully traversed. With respect to independent claims 1, 17, and 20, each has been amended…use data comprising the first generative Al response to select from a plurality of candidate next prompts a selected prompt to be sent; and use data comprising the first generative Al response to generate the selected prompt."
Examiner respectfully disagree and submit that:
Applicant’s arguments with respect to the newly added limitations have been considered but are moot because the arguments do not apply to the reference Singh et al. (US 2024/0296315) and in view of Lamons et al. (US 2016/0098687) being used in the current rejection
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.
Claim(s) 1-17 and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Singh et al. (US 2024/0296315, Singh hereinafter) in view of Lamons et al. (US 2016/0098687, Lamons hereinafter)
As to claim 1, Singh teaches a generative artificial intelligence (AI) system (e.g., “100”, FIG. 1, para [0027] , “ a generative AI platform architecture 100”. Also, see FIG. 11, para 108, “FIG. 11 is a block diagram of architecture 100, shown in FIG. 1”) , comprising:
A network communication interface coupled to receive from a remote system via a network an API call comprising a request (e.g. , see FIG. 11, para 108, “cloud computing delivers the services over a wide area network, such as the internet”, “servers at a remote location”, “access for the user” and “ API 106, prompt response “, “user 594 uses a user device 596 to access those systems” in para 111 ) . Thus, A network communication interface coupled to receive from a remote system via a network an API call comprising a request); and
a processor coupled to the network communication interface (e.g., “processor(s), FIG. 1, para [0030] , “one or more processors”) and configured to:
execute a server-side prompt program comprising or otherwise associated with one or both of the API call and the request , including by sending two or more prompts to a generative AI service (e.g., e.g., see FIG. 5A/5B, para [0065] the request and makes calls to the target generative AI model, “, “ multiple calls (e.g., chained prompts) can be made to service the generative AI request, and those calls may be executed as chained prompts, or other calls. Making multiple calls to execute the generative AI request is indicated by block 374 in the flow diagram of FIG. 5).
However, Singh does not teach receive a final result obtained by sending the two or more prompts to the generative Al service; and return the final result to the remote system in response to the API call; wherein the server-side prompt program includes code to receive a first generative Al response in response to a first prompt included in the two or more prompts; use data comprising the first generative Al response to select from a plurality of candidate next prompts a selected prompt to be sent and use data comprising the first generative Al response to generate the selected prompt , to send to the generative Al service, including by incorporating into the selected prompt at least a selected portion of data comprising the first generative Al response.
Lamons teaches receive a final result obtained by sending the two or more prompts and return the final result to the remote system in response to the API call (e.g., (e.g., para 67, “to schedule at least one event” and “where inviting user (103A) has exhibited a pattern of declining candidate meetings scheduled within 24 hours of the invite (201),”, “to indicate his or her desire to accept or decline each of the one or more candidate meetings proposed”” in para [0101], [0106] “the invitation communication (209) is an e-mail message, the e-mail message may include a clickable link which, if clicked by a user (103), indicates that the user accepts (or declines) a particular candidate meeting.”, “a link or other navigation component which directs the user to web site or launches an application which provides an interface for accepting or declining” and ““ the scheduling server (119) sends a reminder communication (215) to invitee user (203B) indicating that the proposed meeting is awaiting the invitee user's (103B) feedback.” In para 111 .
[0105] The communication (209) is preferably sent as “push” messaging and may be preferably sent via push messaging to a mobile device
Thus, “declining candidate meetings scheduled within 24 hours of the invite” include the final result, the “a link or other navigation component” , “clickable link, “push” messaging” and “scheduling events” in abstract include the two or more prompts) to the generative Al service (e.g., “113”, FIG. 2, para 92-93 “ the decision engine (113) will suggest the first candidate meeting at the date/time/place proposed in the invite if all users (103) are available at the suggested time”, “ calendaring and event planning” ).
According to applicant’s specification in para [0028] Once the prompt program 206 has finished running, a final generative AI result provided in response to a final prompt in the sequence of prompts presented by the prompt program 206 or, in some embodiments, a final result or set of results determined by prompt program 206 based on the responses received to the prompts presented by the prompt program 206, is returned to the application server 106 via a results communication 212. The application server 106 in turn sends a results page/date 214 to the client device 102.
Thus, receive a final result obtained by sending the two or more prompts to the generative AI service; and return the final result to the remote system in response to the API call.);
wherein the server-side prompt program includes code to receive a first generative Al response in response to a first prompt included in the two or more prompts (e.g., see FIG. 1 and 2, para 71, “ a decision engine (113) (i.e., software program or set of programs) on the server (119) uses various algorithms to determine a suggested or proposed time, date, and/or location for the meeting” . Thus, the “a decision engine (113) (i.e., software program or set of programs)” represents the code) ; use data comprising the first generative Al response to select from a plurality of candidate next prompts a selected prompt to be sent and use data comprising the first generative Al response to generate the selected prompt , to send to the generative Al service, including by incorporating into the selected prompt at least a selected portion of data comprising the first generative Al response (e.g., see Figs 1, 2 and 3, para 72 and 73, “ a date/time/location for the meeting is referred to as a “candidate meeting” or “candidate date.” For sake of brevity and simplicity, the term “candidate date” should be understood to include a time and, if and as appropriate in a particular embodiment or case, a venue or location”, “the date, time, and/or place for the candidate meeting is not determined by any one individual user (103), but rather by the decision engine (113). Each user (103) may accept or decline the invitation. In the typical case, the invitation will be, at a minimum, for a time, place, and/or location for which calendar data (105).
Para 73, “a third-party calendaring system”, “ API calls to the calendar or, where the user does not maintain a separate calendar (105), the server (113) will schedule the event internally for the user (103)”, “the organizer may be presumed to accept the invitation, and reflected in the database as having accepted the date, time, and/or place for the event automatically”.
According to applicant’s specification in page 7 and 8,
“Use the calendar availability data to select a time/date for the meeting. Prompt the generative AI service to construct a communication to place the meeting on the participants' respective calendars and send the response to the enterprise calendar service to schedule the meeting”, “to select a set of candidate dates and sites for a three day offsite during the working week within the Western Region. Based on the output regarding each of the candidate attendees and the dates and sites, utilize branch logic comprising the prompt program to create new prompts depending on the attendee's home address and the intended gathering site to generate for each attendee”.
Thus, the “ a date/time/location” include the data , the decision engine (113)” include the generative Al service , the ““candidate date” , “date, time, and/or place for the candidate meeting “ for “ data in user models to select a date, time, and/or place to schedule a meeting between the users and store the meeting data in an event cloud using a dynamic software object” in abstract , therefore to select from a plurality of candidate next prompts a selected prompt to be sent and use data comprising the first generative Al response to generate the selected prompt , to send to the generative Al service, including by incorporating into the selected prompt at least a selected portion of data comprising the first generative Al response ) .
Thus, It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention was made to modify the teachings of Singh with the teachings of Lamons to enable the generative artificial intelligence (AI) system executing server prompt program/ a code to receive and return the final result of prompts, to use data of a generative AI response to generate and to select candidates next prompts sent to the generative AI service by incorporation at least portion of the data in order to increased system automation and reducing the burden on users or increased the likelihood that invitee user will accept or decline promptly as taught by Lamons, para 96, 111.
As to claim 2, Singh teaches wherein the API call is received at an API endpoint associated with the communication interface (e.g., e.g., see FIG. 11, para 108) [0108], “Cloud computing infrastructures can deliver services through shared data centers, even though they appear as a single point of access for the user”. Thus, the “Cloud computing infrastructures” include the API endpoint). .
As to claim 3, Singh teaches wherein the remote system comprises an application server and the API call is generated and sent by an application running on the application server (e.g., see FIG. 11, para [0108] FIG. 11 is a block diagram of architecture 100, shown in FIG. 1, except that its elements are disposed in a cloud computing architecture 590. Cloud computing provides computation, software”, “Software or components of architecture 100 as well as the corresponding data, can be stored on servers at a remote location”).
As to claim 4, Singh teaches wherein the prompt program is written in a scripting or other interpreted language (e.g., para [0047] data loading scripts 283”, [0041] “ data extraction scripts”. Also, see FIG. 10C).
As to claim 5, Singh teaches wherein the prompt program is executed in one or more of a runtime , a virtual machine, and a container (e.g., see FIG. 11, para 108, wherein “The computing resources in a cloud computing environment can be consolidated at a remote data center location or they can be dispersed. Cloud computing infrastructures can deliver services through shared data centers, even though they appear as a single point of access for the user. Thus, the components and functions described herein can be provided from a service provider at a remote location using a cloud computing architecture. Alternatively, they can be provided from a conventional server, or they can be installed on client devices directly, or in other ways”. Thus, wherein the prompt program is executed in one or more of a runtime , a virtual machine, and a container would have been inherent ) .
As to claim 6, Singh teaches further wherein the prompt program includes code to receive from the generative AI service a first response to a first prompt sent by the prompt program, and to generate a second prompt (e.g., para [0056] “the prompts and responses generated “). However, Singh does not teach use data comprising the first response to generate the second prompt. Lamons teaches use data comprising the first response to generate the second prompt (e.g., see rejection of claim1 above, [0059] , “submit prompts and receive responses on the actual types of generative AI models “).
Thus, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention was made to modify the teachings of Singh with the teachings of Lamons in order to have use data comprising the first response to generate the second prompt because it would have increased system automation and reducing the burden on users or increased the likelihood that invitee user will accept or decline promptly (see Lamons, para 96, 111).
As to claim 7, Singh teaches wherein the second prompt causes the generative AI service to generate a query to an external system (e.g., para [0049] , “new prompts that have been identified by an external system (manual or automated system) “) .
As to claim 8, Singh teaches wherein the prompt program includes code to use data comprising a first response to a first prompt to send a query to the remote system (e.g., see FIG. 5A para [0067] “. Response processor 189 returns the response to the calling client/user/tenant (e.g., calling client application 102 or development platform 114) “.).
As to claim 9, Singh and Harris do not explicitly teach wherein the prompt program includes code to use data comprising a first response to a first prompt to send a query to a third-party system. However, Lamons teaches wherein the prompt program includes code to use data comprising a first response to a first prompt to send a query to a third-party system ( see para 68, “a third-party calendaring service”).
Thus, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention was made to modify the teachings of Singh with the teachings of Lamons in order to have a first response to a first prompt to send a query to a third-party system because it would have increased system automation and reducing the burden on users or increased the likelihood that invitee user will accept or decline promptly (see Lamons, para 96, 111).
As to claim 10, Singh does not teach teaches wherein the prompt program includes two or more branches and the prompt program further includes code to receive from the generative AI service a first response to a first prompt sent by the prompt program and use data comprising the first response to select a branch from among the two or more branches along which to continue execution of the prompt program. However, Lamons teaches wherein the prompt program includes two or more branches and the prompt program further includes code to receive from the generative AI service a first response to a first prompt sent by the prompt program and use data comprising the first response to select a branch from among the two or more branches along which to continue execution of the prompt program ( see FIG. 2, para 133, wherein the “ user invites”, “ future scheduling invites (201), even invites (201)” , therefore includes two or more branches ).
Thus, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention was made to modify the teachings of Singh with the teachings of Lamons in order to have two or more branches and the prompt program further includes code to receive from the generative AI service a first response to a first prompt sent by the prompt program and use data comprising the first response to select a branch from among the two or more branches along which to continue execution of the prompt program because it would have increased system automation and reducing the burden on users or increased the likelihood that invitee user will accept or decline promptly (see Lamons, para 96, 111).
As to claim 12, Singh teaches wherein the generative AI service comprises a large language model (e.g., para [0019] As discussed above, generative artificial intelligence models (generative AI models) often take the form of large language models.).
As to claim13, Singh teaches wherein the prompt program comprises a first prompt program included in a plurality of prompt programs executable by the processor (e.g., para {0059] , “, API interaction system 296 can interact with API 106 to submit the generative AI requests “, “ the user or developer can submit prompts and receive responses on the actual types of generative AI models “, “ GPUs to execute the models”).
As to claim 14, Singh teaches wherein code comprising the prompt program is included in or with the API call (e.g., para 0065] “multiple calls (e.g., chained prompts) can be made to service the generative AI request” , “ calls to execute the generative AI request “)
As to claim 15, Singh teaches wherein an identifier associated with the prompt program the is included in or with the API call and the processor is further configured to map the identifier to the prompt program (e.g., para 41, “ identify chained prompts or calls that are to be made to service the request”).
As to claim 16, Singh teaches wherein the request includes one or more arguments operated on or otherwise used by the prompt program (e.g., para [0041] “words in the request, data extraction scripts, model parameters, etc.” , [0042] , “ identifier 198 identifies the type of generative AI model that is being called to service the request and model parameter identifier 200 identifies the operational model parameters that are provided with the generative AI request. “ ).
As to claim 17, see rejection of claim 1 above.
As to claim 18, see rejection of claim 6 above.
As to claim 19, see rejection of claim 7 above.
As to claim 20, see rejection of claim 1 above. Singh teaches further a computer program product embodied in a non-transitory computer readable medium and comprising computer instructions ( see FIG. 12).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Kim (US 11,902,225) discloses An operation method of a user terminal for participating in a group event through an instant messaging application includes receiving, by the user terminal, a group event invitation message including information about an event start time through the instant messaging application; receiving, by the user terminal, a response to the invitation message from a user of the user terminal; in response to the user accepting the invitation message, transmitting, by the user terminal, an acceptance message through the instant messaging application; and receiving, by the user terminal, a group event participation request through the instant messaging application at a time corresponding to the event start time.
Bhatia (US 2024/0177119) discloses a method includes receiving a meeting message from a host, where the meeting message initiates a meeting to be scheduled, and where the meeting message includes an invite list of at least one meeting participant; sending at least one invitation message to the at least one meeting participant, where the at least one invitation message provides meeting acceptance options; generating a human-like response in a user interface; enabling in the user interface a conversation between the human-like response and the at least one meeting participant; receiving, from the at least one meeting participant during the conversation, one or more questions about the hos; and sending, to the at least one meeting participant during the conversation, information responsive to the one or more questions about the host..
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ABDOU K SEYE whose telephone number is (571)270-1062. The examiner can normally be reached M-F 9-5:30.
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, Pierre Vital can be reached at 5712724215. 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.
/ABDOU K SEYE/Examiner, Art Unit 2198
/PIERRE VITAL/Supervisory Patent Examiner, Art Unit 2198