DETAILED ACTION
1. This action is responsive to remarks filed 4/20/2026.
Response to Amendment
2. The title has been amended. Claim 15 has been amended to recite a computer, and the 101 rejection is overcome.
Response to Arguments
3. Applicant's arguments filed 4/20/26 have been fully considered but they are not persuasive.
Applicant argues on pages 8-10 of remarks that cited prior art Gray does not anticipate the limitations of claim 1, and that claim 1 is novel over Gray.
Examiner respectfully disagrees.
Applicant argues that Gray does not teach the limitations of claim 1.
Applicant argues that Gray fails to disclose:
generating an initial prompt that includes information source data specifying one or more sources of factual information, said sources comprising one or more external databases and/or one or more APIs, conversation history data comprising information specifying a conversation history, and failed response data indicative of previous prompts which have failed to produce a satisfactory response.
Examiner respectfully disagrees.
Gray teaches utilizing an LLM in generating an NL based summary to be rendered (col 1 l. 67 – col 2 l. 1). Gray receives user input (a given query formulated and submitted based on user input col 2 l. 60-61) and generates an initial prompt using certain sets of information, where
A prompt…can be processed using the LLM to generate the NL based summary (col 3 l. 13-16). To generate the prompt Gray uses
Information source data (Col 2 l. 28-30, 36-44, Col 3 l. 10-20), conversation history data (col 2 l. 36-44, Col 12 l. 25-34, queries and responses), and previous response data (Col 2 l. 28-30, 36-44; Col 17 l. 11-15; l. 49-58).
Applicant argues that Gray fails to disclose that the answer generation module is configured to:
a) determine if the output is a plan to answer a user query, and if so, retrieve relevant data from the one or more external database and/or one or more APIs specified in the information source data
Examiner respectfully disagrees. Gray teaches determining the output is to answer the query, ensuring it meets specific user criteria, and uses information, including data/documents from databases to generate the NL based summary (col 3 l. 10-20;
col 5 l. 1-17; col 11 l. 50-60 query responsive search result documents).
Applicant argues that Gray fails to disclose that the answer generation module is configured to:
b) generate a further prompt for answering the user query and input the further prompt to the LLM module,
c) repeat a) and b) until the output of the LLM module provides a suitable answer to the user query.
Examiner respectfully disagrees. Gray teaches
b) generate a further prompt for answering the user query and input the further prompt to the LLM module (col 23 l. 40 revised prompt),
c) repeat a) and b) until the output of the LLM module provides a suitable answer to the user query (col 24 l. 4-15: At block 462, the system causes the revised NL based summary, generated at block 460, to be rendered (i.e., at the client device that submitted the query and/or a related client device). Following block 462, the system optionally proceeds back to block 458 and monitors for additional interaction(s) with additional search result document(s) that are responsive to the query and, if such additional interaction(s) are detected, proceeds to block 460 to generate a further revised NL based summary by processing additional revised input reflects such additional interaction(s) (and prior interaction(s) of prior iteration(s) of block 458). In some implementations, block 462 can include sub-block 462A and/or sub-block 462B.),
which, similar to the limitations, will continue until a suitable answer is provided, and there is no need to generate a further revision.
Therefore, the cited prior art of record reads on the limitations as currently recited. The additional independent and dependent claims are rejected based on arguments presented above and art rejections below.
Claim Rejections - 35 USC § 102
4. 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 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.
5. The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
6. Claims 1-15 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Gray et al (11,769,017).
Regarding claim 1 Gray et al (11,769,017) teaches A computer-implemented chatbot comprising:
a prompt generation module (figure 1 NL based response system - component of NL based response system);
a large language model (LLM) module and an answer generation module (figure 1 LLMs; NL based response system - component of NL based response system), wherein said prompt generation module is configured to:
generate an initial prompt based on a prompt template combined with a received user query, said initial prompt including information source data specifying one or more sources of factual information, said sources comprising one or more external databases and/or one or more APIs, conversation history data comprising information specifying a conversation history, and failed response data indicative of previous prompts which have failed to produce a satisfactory response
(fig 2 252 receive a query; figure 7A1 source 786, 788;
Col 2 l. 59-61: assume a given query is submitted, such as a given query formulated and submitted based on user input;
Col 2 l. 28-30: additional content that is processed…in generating the…summary…responsive to submission of a query; l. 36-44: related queries, in close temporal proximity, recent queries, within close temporal proximity, and implied queries, based on context and profile data;
Col 3 l. 10-20: Contents A, B, C, and D can then be included in the additional content that is processed using the LLM in generating the NL based summary to provide responsive to submission of the query. For instance, a prompt of “Summarize <Content A>, <Content B>, <Content C>, and <Content D>” (which omits the query itself) can be processed using the LLM to generate the NL based summary. Also, for instance, a prompt of “In the context of <query>, summarize <Content A>, <Content B>, <Content C>, and <Content D>” can be processed using the LLM to generate the NL based summary.;
Col 5 l. 1-16 - prompt based on user familiarity;
Col 12 l. 25-34: user-dependent measures; recent queries; recent non-query interactions;
Col 17 l. 11-15: the confidence measure(s) that are optionally reflected in the LLM output can be utilized in determining whether and/or how to provide the NL based summary; l. 49-58: fails to satisfy object conditions that indicate it is unlikely to be truly responsive to the query;
Col 38 l. 6-7: history of the user); and
input the initial prompt to the LLM module (col 3 l. 10-20: prompt…processed using the LLM; col 5 l. 1-16), wherein
the LLM module is configured to generate an output and communicate the output to the answer generation module (col 1 l. 67 – col 2 l. 13; Col 3 l. 10-20: Contents A, B, C, and D can then be included in the additional content that is processed using the LLM in generating the NL based summary to provide responsive to submission of the query; col 5 l. 1-16: a prompt…can be processed using the LLM in generating the NL based summary), responsive to which, the answer generation module is configured to:
a) determine if the output is a plan to answer a user query, and if so, retrieve relevant data from the one or more external database and/or one or more APIs specified in the information source data (col 3 l. 10-20; col 5 l. 1-17; col 11 l. 50-60 query responsive search result documents),
b) generate a further prompt for answering the user query and input the further prompt to the LLM module (col 23 l. 40 revised prompt),
c) repeat a) and b) until the output of the LLM module provides a suitable answer to the user query (col 24 l. 4-15: At block 462, the system causes the revised NL based summary, generated at block 460, to be rendered (i.e., at the client device that submitted the query and/or a related client device). Following block 462, the system optionally proceeds back to block 458 and monitors for additional interaction(s) with additional search result document(s) that are responsive to the query and, if such additional interaction(s) are detected, proceeds to block 460 to generate a further revised NL based summary by processing additional revised input reflects such additional interaction(s) (and prior interaction(s) of prior iteration(s) of block 458). In some implementations, block 462 can include sub-block 462A and/or sub-block 462B.), then
output the answer to the user query (fig 7A1 784 summary; col 17 l. 62 – col 18 l. 3: At block 262, the system causes the NL based summary, generated at block 260, to be rendered in response to the query. For example, the system can cause the NL based summary to be rendered graphically in an interface of an application of a client device via which the query was submitted. As another example, the system can additionally or alternatively cause the NL based summary to be audibly rendered via speaker(s) of a client device via which the query was submitted.).
Regarding claim 2 Gray teaches A computer-implemented chatbot according to claim 1, wherein the answer generation module is configured to determine if an answer to the user query is a suitable answer by generating a suitable-answer-assessment prompt including:
the answer, the initial user query, and an instruction for the LLM to determine if the answer is a suitable answer, said answer generation module configured to determine that the answer is a suitable answer if the LLM module outputs a response to the suitable-answer-assessment prompt indicating that the answer is a suitable answer
(fig 1; col 17 11-20: the confidence measure(s) that are optionally reflected in the LLM output can be utilized in determining whether and/or how to provide the NL based summary. For example, if confidence measure(s) for portion(s) and/or a confidence measure for the NL based summary as a whole satisfies upper threshold(s) most indicative of confidence, the NL based summary can be rendered responsive to the query and without any initial rendering of any additional search results; col 17 l 21-60).
Regarding claim 3 Gray teaches A computer-implemented chatbot according to claim 1, wherein each time the LLM module generates an output which is a plan to answer the user query, the answer generation module is configured to execute a self-critiquing process, whereby a critique-request instruction prompt is generated and input to the LLM module instructing the LLM module to determine if the output meets a suitability criteria, and if the LLM module generates an output indicative of the output not meeting the suitability criteria, the answer generation module is configured to perform a corrective action
(col 17 l. 11-60 confidence measure; upper/lower thresholds;
L 50-60: if measure(s) for portion(s) and/or a confidence measure for the NL based summary as a whole fails to satisfy lower threshold(s) less indicative of confidence, transmission and/or rendering of the NL based summary can be suppressed completely, and only additional search results transmitted and rendered. Accordingly, rendering and/or transmission of the NL based summary is selectively suppressed when it fails to satisfy object conditions that indicate it is unlikely to be truly responsive to the query. In these and other manners, network and/or computational efficiencies are achieved through selective bypassing of transmitting and/or rendering the NL based summary.).
Regarding claim 4 Gray teaches A computer-implemented chatbot according to claim 3, wherein the corrective action comprises restarting by inputting the initial prompt to the LLM module (prompts - col 3 l. 10-20; col 5 l. 1-17; | col 17 l. 11-60: l. 57-58: fails to satisfy object conditions that indicate it is unlikely to be truly responsive to the query; col 22 l 2 - 6: generating using an LLM, a revised NL based summary response to a query, where the revised NL based summary response is generated in response to user interaction with search result document(s)).
Regarding claim 5 Gray teaches A computer-implemented chatbot according to claim 3, wherein the corrective action comprises generating an output indicating the user query has not been answered (col 17 l. 11-60 As yet another example, if measure(s) for portion(s) and/or a confidence measure for the NL based summary as a whole fails to satisfy lower threshold(s) less indicative of confidence, transmission and/or rendering of the NL based summary can be suppressed completely, and only additional search results transmitted and rendered. Accordingly, rendering and/or transmission of the NL based summary is selectively suppressed when it fails to satisfy object conditions that indicate it is unlikely to be truly responsive to the query).
Regarding claim 6 Gray teaches A computer-implemented chatbot according to claim 1, wherein the initial prompt generated by the prompt generation module includes an instruction for the LLM to generate a plan to answer the user query if necessary
(Col 3 l. 10-20: Contents A, B, C, and D can then be included in the additional content that is processed using the LLM in generating the NL based summary to provide responsive to submission of the query;
col 5 l. 1-16: a prompt…can be processed using the LLM in generating the NL based summary; if it is determined that the user is familiar; if it is determined that the user is not familiar).
Regarding claim 7 Gray teaches A computer-implemented chatbot according to claim 1, wherein the one or more APIs provide access to an internet search engine
(fig 7A1; col 11 l. 50-60: At block 254, the system selects one or more query-responsive search result documents (SRDs), that are responsive to the query of block 252, for inclusion in a set. For example, the system can select, for inclusion in the set, a subset of query-responsive SRDs that the system and/or a separate search system have identified as responsive to the query. For instance, the system can select the top N (e.g., 2, 3, or other quantity) query-responsive SRDs as determined by a search system or can select up to N query-responsive SRDs that have feature(s), as determined by the system, that satisfy one or more criteria.).
Regarding claim 8 Gray teaches A method of generating a response using a computer-implemented chatbot, said method comprising:
generating an initial prompt based on a prompt template combined with a received user query, said prompt including information source data specifying one or more sources of factual information, said sources comprising one or more external databases and/or one or more APIs, conversation history data comprising information specifying a conversation history, and failed response data indicative of previous prompts which have failed to produce a satisfactory response;
inputting the initial prompt to a LLM to generate an output;
determining if the output is a plan to answer a user query, and if so,
a) retrieving relevant data from the one or more external database and/or one or more APIs specified in the information source data,
b) generating a further prompt for answering the user query and input the further prompt to the LLM;
c) repeating a) and b) until the output of the LLM provides a suitable response to the user query, then
outputting the response to the user query.
Claim recites limitations similar to claim 1 and is rejected for similar rationale and reasoning
Claims 9-14 recite limitations similar to claims 2-7 and are rejected for similar rationale and reasoning
Regarding claim 15 Gray teaches A computer including a computer program providing instructions which when implemented on a computing device implements a method according to claim 8.
Claim recites limitations similar to claim 1/8 and is rejected for similar rationale and reasoning
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 SHAUN A ROBERTS whose telephone number is (571)270-7541. The examiner can normally be reached Monday-Friday 9-5 EST.
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, Andrew Flanders can be reached on 571-272-7516. 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.
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 or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/SHAUN ROBERTS/Primary Examiner, Art Unit 2655
Prosecution Insights