Prosecution Insights
Last updated: April 19, 2026
Application No. 18/895,222

MULTI-SECTIONAL USER INTERFACES FOR LLM-INTEGRATED PARAMETER SELECTION FOR SEARCHES

Final Rejection §103
Filed
Sep 24, 2024
Examiner
PEACH, POLINA G
Art Unit
2165
Tech Center
2100 — Computer Architecture & Software
Assignee
Navan Inc.
OA Round
2 (Final)
50%
Grant Probability
Moderate
3-4
OA Rounds
3y 7m
To Grant
73%
With Interview

Examiner Intelligence

Grants 50% of resolved cases
50%
Career Allow Rate
229 granted / 461 resolved
-5.3% vs TC avg
Strong +23% interview lift
Without
With
+23.2%
Interview Lift
resolved cases with interview
Typical timeline
3y 7m
Avg Prosecution
34 currently pending
Career history
495
Total Applications
across all art units

Statute-Specific Performance

§101
17.9%
-22.1% vs TC avg
§103
49.9%
+9.9% vs TC avg
§102
14.5%
-25.5% vs TC avg
§112
11.2%
-28.8% vs TC avg
Black line = Tech Center average estimate • Based on career data from 461 resolved cases

Office Action

§103
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 . Status of the Claims Claims 1, 5-8, 11, 15-18 have been amended, claims 9-10, 19-20 have been canceled. Claims 1-8 and 11-18 are pending. Priority The later-filed application must be an application for a patent for an invention which is also disclosed in the prior application (the parent or original non-provisional application or provisional application). The disclosure of the invention in the provisional application and in the later-filed application must be sufficient to comply with the requirements of 35 U.S.C. 112(a) or the first paragraph of pre-AlA 35 U.S.C. 112, except for the best mode requirement. See Transco Products, Inc. v. Performance Contracting, inc., 38 F.3d 551, 32 USPQ2d 1077 (Fed. Cir. 1994). Applicant’s claim for the benefit of a prior-filed provisional application 63/585,158 filed 09/25/2023 is acknowledged, however written description support for “generating a parameters data structure based on the selected set of parameters, wherein the parameters data structure is a data structure that stores parameters that have been selected by the user”, “updating the parameters data structure based on the new set of parameters” in claim 1 and 11, “receiving a value for each of the set of parameters” in claims and 12, “receiving a range of values for a parameter of the set of parameters” in claims 3, 13 and “the LLM prompt further comprises the generated parameters data structure “ in claims 5 and 15 and for claims 6-10, 16-20 is provided only in the currently filed application and thus, the presented claims and dependents thereof do not receive the benefit of the priority filing date. Co-pending applications must provide written description support for the claimed invention under 35 U.S.C. 112(a) (e.g., must provide support to show both possession and enablement of the claimed subject matter such as a parameters data structure in order for the earlier priority date to be recognized for the claims noted above. 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) 1-8 and 11-18 is/are rejected under 35 U.S.C. 103 as being unpatentable over SACHETI et al. (US 20240354309) (previously cited) in view of BATINA et al. (US 20240289361) and alternatively, in further view of the applicant’s admitted prior art Petricek et al. (US 11055305)(see IDS filed 03/25/2025). Regarding claim 1, SACHETI teaches a method comprising: receiving a request for a search user interface from a user device ([0030], [0032]); transmitting a search user interface to the user device for display to the user, wherein the search user interface comprises a primary section (F3:312) and a chat section (F3:300, [0034]), wherein the primary section comprises a first subsection and a second subsection (F3:320, 324), wherein the first subsection is a subsection for displaying content relating to a search of the user and the second subsection comprises parameter elements for selecting a set of parameters for the search (F3:320, 324), and wherein the chat section comprises elements for a chat interface with an automated chat system ([0030] “GLM 112 with an updated prompt that instructs the GLM 112 to generate a table and populate the table with values of attributes of entities that are relevant to the query, images that are relevant to the query”; “GLM 112 to provide interactive graphics that represent ways in which the table can be modified, such as identities of attributes”)(see NOTE); receiving a selection of a set of parameters through the parameter elements of the second subsection of the primary section ([0030] “The user can then provide additional interaction with respect to the interactive graphic elements, causing the GLM 112 to present an updated table (e.g., with additional values of attributes included, with values for attributes removed, and so forth)”, [0037] “user can interact with such list to cause attributes represented in the table to be updated. In another example, a pulldown button is presented in graphical relation to an entity name, where a list of entities that correspond to the query are presented upon user selection of such pulldown button. Through interaction with such list, the user can alter the entities that are represented in the table”, [0038]); generating a parameters data structure based on the selected set of parameters, wherein the parameters data structure is a data structure that stores values for the set of parameters that have been selected by the user through the parameter elements of the second subsection of the primary section ([0033] “generate a table and populate the table with attributes of entities identified by the search system 110 and provided to the GLM”, [0036]); updating the first subsection of the primary section to display content based on the selected set of parameters ([0038], [0039]); receiving text from the user through the chat section of the search user interface ([0038]); generating a large language model prompt based on received text, wherein the large language model prompt comprises instructions to generate a chat response to the received text and to generate an updated set of parameters based on the received text ([0037]-[0039]); receiving a response from the large language model, wherein the received response comprises a text for a chat response to the received text and an updated set of parameters from the large language model ([0042], [0046]); updating the parameters data structure based on the updated set of parameters ([0048]-[0050], [0055]); updating the chat section to include the text for a chat response to the received text ([0039], [0060]-[0062], [0066]); updating the first subsection of the primary section to display content based on the updated set of parameters ([0066], [0077]); and updating the parameter elements of the second subsection of the primary section based on the updated set of parameters from the response from the large language model ([0039], [0060]-[0062], [0066]). SACHETI teaches text entry filed F4:306, which initiates dialogue with generative language model (GLM) chat mode [0065] and “providing a chat-based conversational interface” [0006]. The “user initiates a search with a query that pertains to a comparison between entities, and then continues to interact with the GLM in a chat to specify important attributes of the entities for which the user is searching” [0026]. Such dialogue / chat with the GLM is subsequently saved. Although, SACHETI only teaches text entry filed F4:306 and does not explicitly and visually shows the “chat-based conversational interface” in the disclosed figures, it is still reasonable to conclude that the chat-based conversational interface (nor just the text entry filed) is the “a chat section” required by the claim. However, to merely obviate such statement, BATINA discloses a chat section ([0023], [0095]-[0096]), herein the chat section comprises elements for a chat interface with an automated chat system ([0044], [0104], [0108]); generate a chat response to the received text and to generate an updated set of parameters based on the received text ([0097]-[0098]) and updating the chat section to include the text for a chat response to the received text ([0042]); updating the first subsection of the primary section to display content based on the updated set of parameters; and updating the parameter elements of the second subsection of the primary section based on the updated set of parameters from the response from the large language model ([0044], [0096], [0100], [0110]). It would have been obvious to one of ordinary skill in the art at the time of invention to modify the teachings of SACHETI to include a chat section and continuously updating chat section and result interface based on the updated parameters as disclosed by BATINA. Doing so may improve search quality and provide ability to fully capture user's desired search parameters and preferences (BATINA [0041]). NOTE The claims are directed to the applicant’s Figure 3B, to further obviate on such display, alternatively, Petricek discloses a search user interface to the user device for display to the user, wherein the search user interface comprises a primary section and a chat section (F5:234), wherein the primary section comprises a first subsection and a second subsection, wherein the first subsection is a subsection for displaying content relating to a search of the user and the second subsection comprises parameter elements for selecting a set of parameters for the search (F5:246a, F6:246a), and wherein the chat section comprises elements for a chat interface with an automated chat system (F5:242); receiving a selection of a set of parameters through the parameter elements of the second subsection of the primary section (F5:246a, F6:246a). It would have been obvious to one of ordinary skill in the art at the time of invention to modify the teachings of SACHETI to include an interface with primary section comprises a first subsection and a second subsection and the second subsection comprises parameter elements for selecting a set of parameters for the search as disclosed by Petricek. Doing so may allow quickly and efficiently help the user to narrow her search and learn more about an item of interest with far fewer clicks (Petricek C4L26-29]). Regarding claim 11, SACHETI teaches a non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform operations comprising: receiving a request for a search user interface from a user device; transmitting a search user interface to the user device for display to the user, wherein the search user interface comprises a primary section and a chat section, wherein the primary section comprises a first subsection and a second subsection, wherein the first subsection is a subsection for displaying content relating to a search of the user and the second subsection comprises parameter elements for selecting a set of parameters for the search, and wherein the chat section comprises elements for a chat interface with an automated chat system; receiving a selection of a set of parameters through the parameter elements of the second subsection of the primary section; generating a parameters data structure based on the selected set of parameters, wherein the parameters data structure is a data structure that stores values for the set of parameters that have been selected by the user through the parameter elements of the second subsection of the primary section; updating the first subsection of the primary section to display content based on the selected set of parameters; receiving text from the user through the chat section of the search user interface; generating a large language model prompt based on received text, wherein the large language model prompt comprises instructions to generate a chat response to the received text and to generate an updated set of parameters based on the received text; receiving a response from the large language model, wherein the received response comprises a text for a chat response to the received text and an updated set of parameters from the large language model; updating the parameters data structure based on the updated set of parameters; updating the chat section to include the text for a chat response to the received text; updating the first subsection of the primary section to display content based on the updated set of parameters; and updating the parameter elements of the second subsection of the primary section based on the updated set of parameters from the response from the large language model. Claim 11 recites substantially the same limitations as claim 1, and is rejected for substantially the same reasons. Regarding claims 2 and 12, SACHETI as modified teaches the method and the medium, wherein receiving the selection of the set of parameters comprises: receiving a value for each of the set of parameters (SACHETI [0030], [0036], [0038], [0063]). Regarding claims 3 and 13, SACHETI as modified teaches the method and the medium, wherein receiving the selection of the set of parameters comprises: receiving a range of values for a parameter of the set of parameters (SACHETI [0054] see “return period”, Petricek F3:224, F7:248b,). Regarding claims 4 and 14, SACHETI as modified teaches the method and the medium, wherein receiving the selection of the set of parameters comprises: receiving a descriptor for content (SACHETI [0047], [0054]). Regarding claims 5 and 15, SACHETI as modified teaches the method and the medium, wherein the large language model prompt further comprises the generated parameters data structure (SACHETI [0030], [0038], BATINA [0029] “A prompt template may specify that prompts have a certain structure or constrained”, [0039]). Regarding claims 6 and 16, SACHETI as modified teaches the method and the medium, wherein the large language model prompt further comprises instructions to generate a score for an item of content based on user data associated with the user and content data associated with the item of content (SACHETI [0026], [0034], BATINA [0065], [0070], [0095], Petricek C5L31-36). Regarding claims 8 and 18, SACHETI as modified teaches the method and the medium, wherein the large language model prompt further comprises instructions to generate the updated set of parameters according to a particular structure (BATINA [0039], [0092] “metadata/attribute data may be saved (e.g., in a memory, database, or other data storage”, SACHETI [0030], [0066]). Claim(s) 7 and 17 and alternatively or additionally claims 3, 6, 13, 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over SACHETI as modified and in further view of Gruber et al. (US 20130275164). Regarding claims 7 and 17, SACHETI as modified does not explicitly teach, however Gruber discloses the method and the medium, wherein the large language model prompt further comprises instructions to generate text explaining why the item of content is relevant to the user (Gruber [0730] “assistant 1002 may reason that, when recommending restaurants within walking distance of a hotel, the useful criteria to solicit would be cuisine and table availability”) in response to the score for the item of content exceeding a threshold (Gruber [0719], [0722], F35). It would have been obvious to one of ordinary skill in the art at the time of invention to modify the teachings of Gruber to generate text explaining why the item of content is relevant as disclosed by Gruber. Doing so may help the user explore the space of possible choices and help with restaurant selection and meal planning (Gruber [0693], [0513]). Regarding claims 3 and 13, SACHETI as modified teaches the method and the medium as disclosed above, Gruber additionally discloses wherein receiving the selection of the set of parameters comprises: receiving a range of values for a parameter of the set of parameters ([0335], [0706]-[0707]). Regarding claims 6 and 16, SACHETI as modified teaches the method and the medium as disclosed above, Gruber additionally discloses, wherein the large language model prompt further comprises instructions to generate a score for an item of content based on user data associated with the user and content data associated with the item of content ([0709]-[0712], [0719], [0725], [0742], [0750], [0802]-[0803]). It would have been obvious to one of ordinary skill in the art at the time of invention to modify the teachings of Gruber to include value ranges and item scores as disclosed by Gruber. Doing so may help the user explore the space of possible choices and help with restaurant selection and meal planning (Gruber [0693], [0513]). Response to Arguments Applicant's arguments filed 10/28/2025 have been fully considered and are addressed in the updated rejections to the claims above. 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 POLINA G PEACH whose telephone number is (571)270-7646. The examiner can normally be reached Monday-Friday, 9:30 - 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, Aleksandr Kerzhner can be reached at 571-270-1760. 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. /POLINA G PEACH/Primary Examiner, Art Unit 2165 November 6, 2025
Read full office action

Prosecution Timeline

Sep 24, 2024
Application Filed
Aug 11, 2025
Non-Final Rejection — §103
Oct 15, 2025
Interview Requested
Oct 27, 2025
Examiner Interview Summary
Oct 27, 2025
Applicant Interview (Telephonic)
Oct 28, 2025
Response Filed
Nov 06, 2025
Final Rejection — §103 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12596921
Stochastic Bitstream Generation with In-Situ Function Mapping
2y 5m to grant Granted Apr 07, 2026
Patent 12585998
DETERMINING QUALITY OF MACHINE LEARNING MODEL OUTPUT
2y 5m to grant Granted Mar 24, 2026
Patent 12585632
METHOD, DEVICE, AND MEDIUM FOR MANAGING ACTIVITY DATA WITHIN AN APPLICATION
2y 5m to grant Granted Mar 24, 2026
Patent 12579191
IDENTIFYING SEARCH RESULTS IN A HISTORY REPOSITORY
2y 5m to grant Granted Mar 17, 2026
Patent 12572575
USING LARGE LANGUAGE MODELS TO GENERATE SEARCH QUERY ANSWERS
2y 5m to grant Granted Mar 10, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

AI Strategy Recommendation

Get an AI-powered prosecution strategy using examiner precedents, rejection analysis, and claim mapping.
Powered by AI — typically takes 5-10 seconds

Prosecution Projections

3-4
Expected OA Rounds
50%
Grant Probability
73%
With Interview (+23.2%)
3y 7m
Median Time to Grant
Moderate
PTA Risk
Based on 461 resolved cases by this examiner. Grant probability derived from career allow 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