Prosecution Insights
Last updated: April 19, 2026
Application No. 18/760,578

MULTI-STEP LANGUAGE MODEL ENSEMBLE METHOD FOR ITEM ATTRIBUTE EXTRACTION

Non-Final OA §101
Filed
Jul 01, 2024
Examiner
GIBSON-WYNN, KENNEDY ANNA
Art Unit
3688
Tech Center
3600 — Transportation & Electronic Commerce
Assignee
Maplebear Inc.
OA Round
1 (Non-Final)
50%
Grant Probability
Moderate
1-2
OA Rounds
2y 10m
To Grant
90%
With Interview

Examiner Intelligence

Grants 50% of resolved cases
50%
Career Allow Rate
78 granted / 155 resolved
-1.7% vs TC avg
Strong +40% interview lift
Without
With
+40.0%
Interview Lift
resolved cases with interview
Typical timeline
2y 10m
Avg Prosecution
32 currently pending
Career history
187
Total Applications
across all art units

Statute-Specific Performance

§101
41.3%
+1.3% vs TC avg
§103
29.5%
-10.5% vs TC avg
§102
8.2%
-31.8% vs TC avg
§112
12.8%
-27.2% vs TC avg
Black line = Tech Center average estimate • Based on career data from 155 resolved cases

Office Action

§101
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 Claims This action is in reply to the claims filed on 07/01/2024. Claims 1-22 are currently pending and have been examined. Allowable Subject Matter Claims 1-22 would be allowable if rewritten or amended to overcome the rejection(s) under 35 U.S.C. 101, set forth in this Office action. The following is a statement of reasons for the indication of allowable subject matter: Pollak et al. (US 2022/0263455 A1) and Subramanian (US 2025/0390894 A1) have been identified as the most relevant prior art to the claimed invention. Pollak discloses obtaining an image of an item (¶ [0052]);prompting a first set of machine-learned models with a first set of prompts, wherein a prompt in the first set includes an image of the item and a request to determine if values for one or more attributes are present in the image (¶¶ [0033]-[0034]); receiving a set of outputs from the first set of machine-learned models, wherein an output describes whether a respective machine-learned model determines that the values are present in the image (¶ [0055]; ¶ [0060]); and prompting a second set of machine-learned models with a second set of prompts, wherein a prompt in the second set includes the image of the item and a request to extract the values of the one or more attributes in the image (¶ [0062]; ¶ [0070]). Pollak does not anticipate or render obvious prompting the second set of machine-learned models responsive to identifying that at least a threshold number of outputs indicate that the values are present in the image or responsive to identifying that at least a threshold number of outputs have matching values, updating a catalog database with the extracted values for the one or more attributes for the item. Subramanian discloses combining scores output by a set of machine-learned models using a voting ensemble, where each model’s prediction is treated as a “vote”, and the final prediction is determined by aggregated these votes in ¶ [0105] (identifying ... at least a threshold number of outputs). However, Subramanian does not anticipate or render obvious prompting the second set of machine-learned models responsive to identifying that at least a threshold number of outputs indicate that the values are present in the image or responsive to identifying that at least a threshold number of outputs have matching values, updating a catalog database with the extracted values for the one or more attributes for the item. Claim Rejections- 35 U.S.C. § 101 35 U.S.C. 101 reads as follows: Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title. Claims 1-22 are rejected under 35 U.S.C. § 101 because the claimed invention is directed to an abstract idea without significantly more. Under Step 1 of the subject matter eligibility (SME) analysis described in MPEP 2106.03, the instant claims fall within the four statutory categories of invention identified by 35 U.S.C. 101. In the instant case, claims 1-9 are directed to a method, claims 10-18 are directed to a manufacture, and claims 19-22 are directed to a system. Claims 1, 10, and 19 are parallel in nature, therefore, the analysis will use claim 1 as the representative claim. In Step 2A Prong One, it must be considered whether the claims recite a judicial exception. Claim 1, as exemplary, recites abstract concepts including: obtaining an image of an item; prompting ... with a first set of prompts, wherein a prompt in the first set includes an image of the item and a request to determine if values for one or more attributes are present in the image; receiving a set of outputs ... wherein an output describes whether ... the values are present in the image; responsive to identifying that at least a threshold number of outputs indicate that the values are present in the image, prompting ... with a second set of prompts, wherein a prompt in the second set includes the image of the item and a request to extract the values of the one or more attributes in the image; receiving a second set of outputs ... wherein an output describes extracted values of the one or more attributes ...; and responsive to identifying that at least a threshold number of outputs have matching values, updating a catalog ... with the extracted values for the one or more attributes for the item. These identified limitations recite the abstract idea of “updating a catalog with extracted item attributes based on an item image”, which falls within the “Certain Methods of Organizing Human Activities” grouping of abstract ideas as it relates to commercial interactions of sales activities or behaviors. Accordingly, claims 1, 10, and 19 recite an abstract idea. See MPEP 2106.04. In Step 2A Prong Two, examiners evaluate integration into a practical application by: (1) identifying whether there are any additional elements recited in the claim beyond the judicial exception(s); and (2) evaluating those additional elements individually and in combination to determine whether they integrate the exception into a practical application. Instant claims 1, 10, and 19 recite additional elements including: a first set of machine-learned models; a second set of machine-learned models; and updating a catalog. The machine-learned models and catalog are recited at a high-level of generality such that it amounts to no more than “apply it” or mere instruction to implement the abstract idea on a computer. For example, the machine-learned models are described as tools where input is received and output is provided, without any description of what happens in between. Implementing an abstract idea on a generic computer, does not integrate the abstract idea into a practical application in Step 2A Prong Two similar to how the recitation of the computer in the claim in Alice amounted to mere instructions to apply the abstract idea of intermediated settlement on a generic computer. See MPEP 2106.05(f). The combination of these additional elements is no more than mere instruction to apply an exception with a generic computer. Accordingly, even in combination, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. See MPEP 2106.05. Claims 1, 10, and 19 are thus directed to an abstract idea. Under Step 2B of the SME analysis, if it is determined that the claims recite a judicial exception that is not integrated into a practical application of that exception, it is then necessary to evaluate the additional elements individually and in combination to determine whether they provide an inventive concept (i.e., whether the additional elements amount to significantly more than the exception itself). The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because, as discussed above with respect to integration of the abstract idea into a practical application, the additional element(s) individually and in combination are merely being used to apply the abstract idea to a general computer components. For the same reason, the elements are not sufficient to provide an inventive concept. As explained in MPEP 2106.05(f), implementing an abstract idea with a generic computer does not add significantly more in Step 2B. Therefore, the additional elements, alone or in ordered combination, there is no inventive concept in the claim, and thus claims 1, 10, and 19 are not patent eligible. Dependent claim(s) 1-3, 5, 9, 11-12, 14, and 18 do not aid in the eligibility of the independent claims. These claims merely further define the abstract idea without reciting any further additional elements. Thus dependent claims 1-3, 5, 9, 11-12, 14, and 18 are also ineligible. Dependent claims 4, 8, 13, and 17 recite additional elements including: wherein in the first of machine-learned models, a machine learned model has a different set of parameters or architecture from another machine-learned model in the first set and wherein each of the first set of machine-learned models and the second set of machine-learned models include a same set of machine-learned models. The recitation of claim limitations that attempt to cover any solution to an identified problem with no restriction on how the result is accomplished and no description of the mechanism for accomplishing the result, does not integrate a judicial exception into a practical application or provide significantly more because this type of recitation is equivalent to the words "apply it". See Electric Power Group, LLC v. Alstom, S.A. and MPEP 2106.05(f). These limitations fail to provide any description of the architecture/parameters of the machine-learned models, only stating that they are different or the same. Claiming “different” and/or “same” models does not meaningful limit the generic computer implementation. Accordingly, claim(s) 4, 8, 13, and 17 are ineligible. Dependent claim 6-7 recite additional elements including: fine-tuning parameters of a machine-learned model using the first training dataset; and fine-tuning parameters of a machine-learned model using the second training dataset. Similar to the additional elements recited in claims 4 and 13, these limitations fail to recite how the model is fine-tuned or name any particular mechanisms for achieving the fine-tuning. As such these limitations do not amount to more than “apply it” and are ineligible. Conclusion The prior art made of record and not relied upon is considered pertinent to applicant's disclosure: Al-Yami et al. (US 2025/0053922 A1) relates to a method of automated cataloging relying on a catalog model. P. Das, Y. Xia, A. Levine, G. Di Fabbrizio and A. Datta (NPL Reference U) compares several classifiers to product taxonomy organization of top-level categories. Pan et al. (US 2021/0241076 A1) generally relates to a mismatch detection model and discloses combining respective outputs of multiple detection models to determine whether a quantity of results is at least a predetermined threshold in ¶ [0060]. Stiegler et al. (US 2023/0186364 A1) provides an ensemble model that can be trained using machine learning techniques to predict whether a given item's dimensions are erroneous. Any inquiry concerning this communication or earlier communications from the examiner should be directed to KENNEDY A GIBSON-WYNN whose telephone number is (571)272-8305. The examiner can normally be reached M-F 8:30-5:30 PM. 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, Jeffrey Smith can be reached at 571-272-6763. 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. /K.G.W./Examiner, Art Unit 3688 /Jeffrey A. Smith/Supervisory Patent Examiner, Art Unit 3688
Read full office action

Prosecution Timeline

Jul 01, 2024
Application Filed
Jan 29, 2026
Non-Final Rejection — §101 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12555153
RECOMMENDATION METHOD, PRODUCT, AND SYSTEM USING USER EMBEDDINGS HAVING STABLE LONG-TERM COMPONENT AND DYNAMIC SHORT-TERM SESSION COMPONENT
2y 5m to grant Granted Feb 17, 2026
Patent 12511680
EQUIPMENT RECOMMENDATION SYSTEM AND METHOD
2y 5m to grant Granted Dec 30, 2025
Patent 12499466
METHODS, SYSTEM, AND NON-TRANSITORY COMPUTER-READABLE MEDIUM FOR AUTOMATIC GENERATION OF IMAGE-BASED PRINT PRODUCT OFFERING
2y 5m to grant Granted Dec 16, 2025
Patent 12482029
MEDIUM, METHOD AND APPARATUS FOR NATIVE PAGE GENERATION
2y 5m to grant Granted Nov 25, 2025
Patent 12475501
SYSTEMS AND METHODS FOR VEHICLE RECOMMENDATIONS BASED ON USER GESTURES
2y 5m to grant Granted Nov 18, 2025
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

1-2
Expected OA Rounds
50%
Grant Probability
90%
With Interview (+40.0%)
2y 10m
Median Time to Grant
Low
PTA Risk
Based on 155 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