Prosecution Insights
Last updated: April 19, 2026
Application No. 18/776,104

CUSTOMIZING RECIPES GENERATED FROM ONLINE SEARCH HISTORY USING MACHINE-LEARNED MODELS

Non-Final OA §103
Filed
Jul 17, 2024
Examiner
MACKES, KRIS E
Art Unit
2153
Tech Center
2100 — Computer Architecture & Software
Assignee
Maplebear Inc.
OA Round
3 (Non-Final)
76%
Grant Probability
Favorable
3-4
OA Rounds
2y 10m
To Grant
86%
With Interview

Examiner Intelligence

Grants 76% — above average
76%
Career Allow Rate
400 granted / 527 resolved
+20.9% vs TC avg
Moderate +10% lift
Without
With
+10.5%
Interview Lift
resolved cases with interview
Typical timeline
2y 10m
Avg Prosecution
12 currently pending
Career history
539
Total Applications
across all art units

Statute-Specific Performance

§101
14.1%
-25.9% vs TC avg
§103
47.5%
+7.5% vs TC avg
§102
20.9%
-19.1% vs TC avg
§112
6.0%
-34.0% vs TC avg
Black line = Tech Center average estimate • Based on career data from 527 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 . 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. This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention. Claim(s) 1, 3-8, 10-15, and 17-20 with an earliest effective filing date of 7/19/23 is/are rejected under 35 U.S.C. 103 as being unpatentable over Neumann (U.S. Patent No. 12,001,796 filed on 12/2/21) in view of Feller et al. (U.S. Patent No. 9,483,547 patented on 11/1/16) and further in view of Mostafazadeh et al. (U.S. Publication No. 2022/0343903 published on 10/27/22) and Noso et al. (U.S. Publication No. 2024/0420823 provisionally filed on 6/15/23). With respect to claim 1, the Neumann reference teaches a method comprising: obtaining, for a user of an online system, a set of factors including at least one of preferences of the user, inventory data of items at one or more retailers for the user, or dietary restrictions of the user (user preferences including dietary information utilized [col. 6 line 63 to col. 7 line 44]); selecting, from the set of recipes, a recipe to customize for the user (a personal recipe is a recipe selected to be customized for each individual user [col. 8 line 32 to col. 9 line 8]); generating a prompt for input to a machine-learned language model, the prompt specifying at least the obtained set of factors for the user and a request to customize the at least one recipe for the user (a prompt is used to collect user preferences [col. 6 line 63 to col. 7 line 44] and processed by a machine-learning language model [col. 11 line 9 to col. 12 line 43]); providing the prompt to a model serving system for execution by the machine-learned language model for execution (user input is processed by a machine-learning language model [col. 11 line 9 to col. 12 line 43]); and receiving, from the model serving system, a customized recipe for the user generated by executing the machine-learned language model on the prompt (a machine learning process is used to generate a personal recipe for the user [col. 10 lines 26-36]), wherein the machine-learned language model is executed on a sequence of input tokens encoding the prompt (the input it tokenized for processing [col. 11 line 9 to col. 12 line 3]), wherein the customized recipe is obtained from a sequence of output tokens generated by the machine-learned language model (the input is correlated with the personal recipe output [col. 11 lines 9-43]); and sending instructions that cause a client device to display the customized recipe for display on a webpage or an application page to the user of the client device (the personal recipe is sent to the user for display [col. 10 lines 26-36 and col. 24 lines 39-56]). The Neumann reference does not explicitly recite retrieving at least one recipe page from a set of recipes stored in a data store, wherein the at least one recipe page is retrieved based on search data including previous search queries submitted by users or that the machine-learned language model is configured as a transformer architecture. It also does not explicitly recite applying a multi-modal image generation model to at last a part of the customized recipe to generate an image corresponding to the customized recipe and displaying the image of the customized recipe. The Feller reference teaches retrieving at least one recipe page from a set of recipes stored in a data store, wherein the at least one recipe page is retrieved based on search data including previous search queries submitted by users (recommended recipes are determined based on past recipe searches by the user and other users and a recipe’s popularity [col. 3 lines 11-23]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the system of Neumann with the popularity modifier of Feller. Such a modification would have made the system more desirable to users by enabling them to more easily find popular recipes. The Mostafazadeh reference teaches that the machine-learned language model is configured as a transformer architecture (the AI system is used to recommend recipes [paragraph 47] and the machine-learned model has a transformer architecture [paragraph 51]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the system of Neumann and Feller with the system of Mostafazadeh. Such a modification would have made the system more efficient (paragraph 52 Mostafazadeh). The Noso reference teaches applying a multi-modal image generation model to at last a part of the customized recipe to generate an image corresponding to the customized recipe and displaying the image of the customized recipe (data is provided to an image generation model to generate an image related to the recipe [paragraph 49] for presentation [paragraph 50]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the system of Neumann, Feller, and Mostafazadeh with the image generation of Noso. Such a modification would have made the system more desirable to users by providing them with additional relevant information (the generated image). With respect to claim 3, the Neumann, Feller, Mostafazadeh, and Noso references teach all of the limitations of claim 1 as described above. In addition, the Feller reference teaches requesting a rating for the customized recipe from the user and generating a quality score for the customized recipe based at least on a received rating from the user (user feedback on recipes is used to score the recipe [col. 3 lines 11-23]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the system of Neumann with the popularity modifier of Feller. Such a modification would have made the system more desirable to users by enabling them to more easily find popular recipes. With respect to claim 4, the Neumann, Feller, Mostafazadeh, and Noso references teach all of the limitations of claim 3 as described above. Additionally, the Feller and Neumann references teach updating the machine-learned language model by using the quality score as a reward signal (user feedback on recipes is used to score the recipe [Feller col. 3 lines 11-23] by utilizing a machine-learning language model [Neumann col. 11 line 9 to col. 12 line 43]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the system of Neumann with the popularity modifier of Feller. Such a modification would have made the system more desirable to users by enabling them to more easily find popular recipes. With respect to claim 5, the Neumann, Feller, Mostafazadeh, and Noso references teach all of the limitations of claim 1 as described above. In addition, they teach applying a second machine-learned model to a subset of recipes including the customized recipe to generate a set of quality scores (multiple models are applied [Neumann col. 11 line 9 to col. 12 line 43 & col. 15 line 35 to col. 16 line 51] and recipes are scored [Feller col. 3 lines 11-23]); ranking the subset of recipes based on the respective quality score of each recipe (recipes are scored [Feller col. 3 lines 11-23]); and providing one or more recipes for display to the client device based on the ranking (the personal recipe is sent to the user for display [col. 10 lines 26-36 and col. 24 lines 39-56]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the system of Neumann with the popularity modifier of Feller. Such a modification would have made the system more desirable to users by enabling them to more easily find popular recipes. With respect to claim 6, the Neumann, Feller, Mostafazadeh, and Noso references teach all of the limitations of claim 5 as described above. In addition, they teach that the second machine-learned model is trained by performing steps of: obtaining a plurality of recipes and corresponding quality scores for the plurality of recipes (recipes are scored [Feller col. 3 lines 11-23]); applying the second machine-learned model to the plurality of recipes to generate estimated outputs (the machine learning process estimates an output using input-output pairs [Neumann col. 16 line 52 to col. 17 line 13]); and updating parameters of the second machine-learned model based on a loss function indicating a difference between the estimated outputs and the quality scores for the plurality of recipes (an expected loss is used by the model relating inputs to outputs [col. 16 line 52 to col. 17 line 13]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the system of Neumann with the popularity modifier of Feller. Such a modification would have made the system more desirable to users by enabling them to more easily find popular recipes. With respect to claim 7, the Neumann, Feller, Mostafazadeh, and Noso references teach all of the limitations of claim 1 as described above. In addition, the Neumann reference teaches that presenting the customized recipe to the user of the client device comprises: causing the client device to display the customized recipe on a user interface, wherein each ingredient in the customized recipe is displayed in an interactable user interface element in the user interface (the personal recipe is sent to the user for display [col. 10 lines 26-36 and col. 24 lines 39-56]). With respect to claims 8 and 10-14, the claims are merely the computer program product embodiment of claims 1 and 3-7 and they recite no further significant limitations therein. Therefore, the limitations of claims 8 and 10-14 are rejected in the analysis of claims 1 and 3-7 and are likewise rejected on the same basis. With respect to claims 15 and 17-20, the claims are merely the computer system embodiment of claims 1, 3, and 5-7 and they recite no further significant limitations therein. Therefore, the limitations of claims 15 and 17-20 are rejected in the analysis of claims 1, 3, and 5-7 and are likewise rejected on the same basis. Claim(s) 2, 9, and 16 with an earliest effective filing date of 7/19/23 is/are rejected under 35 U.S.C. 103 as being unpatentable over Neumann (U.S. Patent No. 12,001,796 filed on 12/2/21) in view of Feller et al. (U.S. Patent No. 9,483,547 patented on 11/1/16) and Mostafazadeh et al. (U.S. Publication No. 2022/0343903 published on 10/27/22) and Noso et al. (U.S. Publication No. 2024/0420823 provisionally filed on 6/15/23) and further in view of Hammond et al. (U.S. Publication No. 2019/0188776 published on 6/20/19). With respect to claim 2, the Neumann, Feller, Mostafazadeh, and Noso references teach all of the limitations of claim 1 as described above. They do not explicitly recite that identifying a list of items required to fulfill the customized recipe and wherein the list of items is identified based on a retailer for the user. The Hammond reference teaches that identifying a list of items required to fulfill the customized recipe, and wherein the list of items is identified based on a retailer for the user (retailer information is used to customize the recipe [paragraphs 18, 22, 30, 32, 38, and 44]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the system of Neumann and Feller with the retailer information of Hammond. Such a modification would have made the system more desirable to users by enabling them to more easily acquire the ingredients for their recipe. With respect to claim 9, the limitations of claim 9 are merely the computer program product embodiment of claim 2 and claim 9 recites no further significant limitations therein. Therefore, the limitations of claim 9 are rejected in the analysis of claim 2 and is likewise rejected on the same basis. With respect to claim 16, the limitations of claim 16 are merely the computer system embodiment of claim 2 and claim 16 recites no further significant limitations therein. Therefore, the limitations of claim 16 are rejected in the analysis of claim 2 and is likewise rejected on the same basis. Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to KRIS E MACKES whose telephone number is (571)270-3554. The examiner can normally be reached Monday-Friday 9:00-4:00 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, Kavita Stanley can be reached at 571-272-8352. 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. /KRIS E MACKES/Primary Examiner, Art Unit 2153
Read full office action

Prosecution Timeline

Jul 17, 2024
Application Filed
Mar 21, 2025
Non-Final Rejection — §103
Jul 28, 2025
Response Filed
Oct 10, 2025
Final Rejection — §103
Jan 16, 2026
Request for Continued Examination
Jan 22, 2026
Response after Non-Final Action
Jan 23, 2026
Non-Final Rejection — §103 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12602438
COOKIELESS DELIVERY OF PERSONALIZIED CONTENT
2y 5m to grant Granted Apr 14, 2026
Patent 12572501
INTEGRATED DIGITAL-ANALOG ARCHIVING SYSTEMS AND METHODS FOR DOCUMENT PRESERVATION
2y 5m to grant Granted Mar 10, 2026
Patent 12572547
Systems and Methods for Deployment of Continuous Access Evaluation Protocol (CAEP) Hub Engine
2y 5m to grant Granted Mar 10, 2026
Patent 12563365
SYSTEMS AND METHODS FOR LOCALIZED INFORMATION PROVISION USING WIRELESS COMMUNICATION
2y 5m to grant Granted Feb 24, 2026
Patent 12541433
DATA BACKUP METHOD, ELECTRONIC DEVICE, DATA BACKUP SYSTEM, AND CHIP SYSTEM
2y 5m to grant Granted Feb 03, 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
76%
Grant Probability
86%
With Interview (+10.5%)
2y 10m
Median Time to Grant
High
PTA Risk
Based on 527 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