Prosecution Insights
Last updated: November 20, 2026
Application No. 18/928,670

SYSTEMS AND METHODS FOR GENERATING CONTENT SUMMARIES WITH MINIMAL HALLUCINATIONS

Non-Final OA §101§103
Filed
Oct 28, 2024
Examiner
RUSS, COREY V
Art Unit
3629
Tech Center
3600 — Transportation & Electronic Commerce
Assignee
Ford Motor Company
OA Round
3 (Non-Final)
27%
Grant Probability
At Risk
3-4
OA Rounds
10m
Est. Remaining
65%
With Interview

Examiner Intelligence

Grants only 27% of cases
27%
Career Allowance Rate
48 granted / 179 resolved
-25.2% vs TC avg
Strong +38% interview lift
Without
With
+38.2%
Interview Lift
resolved cases with interview
Typical timeline
2y 11m
Avg Prosecution
34 currently pending
Career history
224
Total Applications
across all art units

Statute-Specific Performance

§101
43.2%
+3.2% vs TC avg
§103
42.9%
+2.9% vs TC avg
§102
7.6%
-32.4% vs TC avg
§112
4.9%
-35.1% vs TC avg
Black line = Tech Center average estimate • Based on career data from 179 resolved cases

Office Action

§101 §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 Claims The following is a non-final office action. Claims [1-20] are currently pending and have been examined on their merits. Claims 1, 8, and 15, are currently amended see REMARKS June 08, 2026. 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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 June 08, 2026 has been entered. Claim Rejections - 35 USC § 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 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception that is an abstract idea without a practical application or significantly more. Step 1: Claims 1-7 recite a system, claims 8-14 recite a method (i.e. a process such as an act or series of steps), and claims 15-20 recite a non-transitory computer readable storage medium and therefore each claim falls within one of the four statutory categories. Step 2A prong 1 (Is a judicial exception recited?): The representative claim 1 recites: A method comprising: receiving, at a first time, first input data from one or more data sources, the first input data including first user reviews of one or more electric vehicle (EV) charging stations, the first user reviews including one or more problems associated with the one or more EV charging stations and one or more solutions to the one or more problems; causing to predict first output data, the first output data including a first category associated with the first input data; causing to generate one or more first summaries based on the first input data and the first output data, the one or more first summaries including the one or more problems and the one or more solutions; causing to determine that the one or more first summaries include a hallucination; causing to generate one or more first questions using the first input data and the one or more first summaries, the one or more first questions being related to the one or more problems; causing to generate one or more first answers to the one or more first questions based on the first input data and one or more second answers to the one or more first questions based on the one or more first summaries; and determining a difference between the one or more first answers and the one or more second answers; causing, based on the determination that the one or more first summaries include a hallucination, generate one or more second summaries, the one or more second summaries including the one or more problems and the one or more solutions, generate one or more second summaries; and causing to present the one or more second summaries. The claims recite a certain method of organizing human activity. The claims recite a certain method of organizing human activity as the disclosure recites commercial or legal interactions. The claims merely recite a method for receiving user review information from a plurality of sources, generating a summary of the reviews, and presenting the summary to users. As the claims recite a method for generating a summary of customer reviews for services such as electric vehicle charging stations and presenting the summary to other users to include aspects such as sentiment, reliability, availability, safety, price, etc. which can be used to help influence a person’s perspective of a location. Therefore, the claims recite an abstract idea of a commercial interaction. Alternatively, the claims recite a mental process. The examiner finds the claims to be similar to a claim to "collecting information, analyzing it, and displaying certain results of the collection and analysis." The claims merely recite a method for generating summaries of reviews pertaining to an electric vehicle charging station. The claims recite a series of steps to receive input data and analyze the data to generate a summary to be shared with other users as well as determining if the summaries are accurate to the original input data by determining questions and comparing the answers to the questions using the input data and the summary information. Therefore, the examiner finds the claims to be similar to examples the courts have identified as reciting a mental process including observations, evaluations, judgements, and opinions. As the method of receiving user provided input data and evaluating the data to generate a summary to present to other users is a mental process. Therefore, the examiner finds the claims to be directed to an abstract idea. Step 2A Prong 2 (Is the exception integrated into a practical application?): The claims additionally recite; Claim 1: A system comprising: memory that stores computer-executable instructions; and one or more processors configured to access the memory and execute the computer- executable instructions, a first model, a second model, a third model, and a user interface of a device. Claim 8: a first model, a second model, a third model, and a user interface of a device. Claim 15: A non-transitory computer-readable medium storing computer-executable instructions, that when executed by one or more processors, cause the one or more processors to perform operations, a first model, a second model, a third model, and a user interface of a device. The additional element of using generic computer elements to perform the abstract idea are directed to merely applying the known use of a computer to store and execute the method in the recited claim limitations. Therefore, the limitations merely amount to adding the words “apply it” (or an equivalent) to the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea, as discussed in MPEP 2106.05(f). Accordingly, the 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. As the claims are merely directed to utilizing generic computer elements of a plurality of models to receive and process information and a graphical user interface to present information to perform the abstract idea of receiving input data, generating summaries based on the input data, and present the summaries. Step 2B (Does the claim recite additional elements that amount to significantly more that the judicial exception?): As discussed above, the additional imitations amount to adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea, as discussed in MPEP 2106.05(f). The claims merely recite using generic computer elements and a plurality of generic models elements to perform the abstract idea. Therefore, the additional elements do not amount to significantly more as they do not recite any improvements to a technology or technical field. Dependent claims 2-7, 9-14, and 16-20 further narrow the abstract idea of generating a summary of reviews and determining a summary includes a hallucination. The dependent claims recite the following additional elements: Claims 2, 9, and 16: first model is an aspect-based sentiment analysis (ABSA) model and the second model is a summarization model. However, the additional elements are directed to merely “apply it” or applying generic computer elements to perform the abstract idea. Therefore, claims 1-20 are rejected under 35 U.S.C. 101. Response to arguments Applicant’s arguments, see REMARKS, filed June 08, 2026, with respect to the rejections of claims 1-20 under U.S.C. 101 have been fully considered but are not persuasive. Representative argues that the currently amended claim limitations are directed to a practical application as they claims recite a plurality of models to determine a summary of customer reviews with minimal hallucinations. However, the examiner respectfully disagrees as the claims recite a series of steps including receiving a first input data including user reviews, predicting a first output data including a first category; generate one or more first summaries based on the first input data and first output data; determine that the first summaries include a hallucination by generating one or more first questions using the first input data and first summaries; generating one or more first answers to the one or more first questions based on the first input data and second answers based on the first summaries; determining a differences between the first and second answers; and determining that the first summaries include a hallucination; and determining a second summary. The claims recite a mental process as they recite a series of steps that can be practically performed in the human mind. As a person is capable of performing the steps of receiving a first input data including customer reviews, generating a plurality of summaries of the reviews, generating a plurality of questions, and determining if the summaries are accurate based on the difference in answers to the questions using the original data and the generated summaries. Therefore, the claims recite concepts the courts have identified as being mental processes such as observations, evaluations, judgment, and opinions. Additionally, the additional elements of a system comprising a plurality of generic computer elements and a series of models to perform the abstract idea of receiving customer review input information, generating a plurality of summaries, and verifying if the summaries accurately portray the original information are directed to “apply it” or applying a generic computer to perform the abstract idea. As the claims do not recite an improvement to a technology or technical field but merely using a plurality of models to perform the basic action of receiving and analyzing information to generate an output. Such as generating a summary of input review data and verifying if the summaries contain any hallucinations by confirming if the information contained in the summaries would produce similar answers to a plurality of questions as the original input data. Therefore, the examiner maintains the current 101 rejection. Claims 2-7, 9-14, and 16-20 are dependent on claims 1, 8, and 15 and therefore are rejected under the same rejection. Applicant’s arguments, see REMARKS, filed June 08, 2026, with respect to the rejections of 1-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chatterjee (US 2020/0285662) in view of Manfield (US 2015/0032660) further in view of Choubey (US 2023/0119109) even further in view of Emrey (US 2024/0386207) are persuasive. Claims 1, 8, and 15: The applicant argues that the current prior art does not disclose the newly amended claim limitations of “the first user reviews including one or more problems associated with the one or more EV charging stations and one or more solutions to the one or more problems.” Upon further search and consideration the examiner agrees that the current combination of prior art does not disclose the newly amended claim limitations. The closest prior art Chatterjee (US 2020/0285662) discloses a system of generating sentiment-based summaries for user reviews of products. Chatterjee further discloses using a trained machine learning model to receive a plurality of user reviews and to generate summaries of the reviews. The second closest prior art Manfield (US 2015/0032660) discloses a system of allowing a user to review electric vehicle charging stations. Manfield teaches a system of receiving a plurality of user reviews for a plurality of EV charging stations and combining the reviews onto a graphical display for other users to view. The third closest prior art Choubey (US 2023/0119109) teaches a system of controlling hallucinations in text-based summarization. Choubey teaches a system of receiving a dataset including a plurality of documents and text-based summaries, generated from the documents by a machine learning model, and determining a degree of hallucinations in the summaries. The fourth closest prior art Emrey (US 2024/0386207) teaches a system for detecting errors and hallucinations in a model output. Emrey teaches a system for comparing information output of a model to information stored in a “truth” database that can be used to determine if the output from the model includes any hallucinations. Therefore, claims 1, 8, and 15 are allowed over U.S.C. 103 Claims 2-7, 9-14, and 16-20 are argued as being allowable as being dependent on claims 1, 8, and 15. Therefore, they are also allowed over U.S.C. 103. Conclusion The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure. Ouyang (US 2025/0094728) Summary of reviews generated by a generative language model. Kadambi (US 2023/0410023) Generating an intelligent summary graph and text from qualitative reviews. Ma (US 2024/0412115) Method, apparatus, device, and medium for verifying output data of processing model. Garcia Duran (US 2019/0080383) Method and system for combining user, item, and review representations for recommender systems. Any inquiry concerning this communication or earlier communications from the examiner should be directed to COREY RUSS whose telephone number is (571)270-5902. The examiner can normally be reached on M-F 7:30-4:30. 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, Lynda Jasmin can be reached on 5712726782. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300. Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see https://ppair-my.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, 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. /COREY RUSS/Primary Examiner, Art Unit 3629
Read full office action

Prosecution Timeline

Show 2 earlier events
Jan 22, 2026
Response Filed
May 18, 2026
Final Rejection mailed — §101, §103
Jun 08, 2026
Response after Non-Final Action
Jul 14, 2026
Request for Continued Examination
Jul 20, 2026
Response after Non-Final Action
Aug 11, 2026
Non-Final Rejection mailed — §101, §103
Nov 10, 2026
Applicant Interview (Telephonic)
Nov 14, 2026
Examiner Interview Summary

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12802086
MEMORY REDUCTION IN FRAUD DETECTION MODEL PERFORMANCE OPTIMIZATION USING COMPRESSED DATA
3y 8m to grant Granted Nov 17, 2026
Patent 12718256
ARTIFICIAL INTELLIGENCE-AIDED RECOMMENDATION FOR EXPLORATORY NETWORK ANALYSIS
3y 5m to grant Granted Aug 25, 2026
Patent 12688509
SYSTEM AND METHOD RELATING TO PLANNING EVENT FOR A NETWORK
3y 11m to grant Granted Jul 21, 2026
Patent 12682362
AUTOMATED DOMAIN CRAWLER AND CHECKOUT SIMULATOR FOR PROACTIVE AND REAL-TIME SCAM WEBSITE DETECTION
2y 7m to grant Granted Jul 14, 2026
Patent 12614194
Compliance Evaluation System for an Organization
2y 2m to grant Granted Apr 28, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

Strategy Recommendation AI-generated — please review before filing

Get a prosecution strategy drawn from examiner precedents, rejection analysis, and claim mapping.
Typically takes 5-10 seconds — AI-generated, attorney review required before filing

Prosecution Projections

3-4
Expected OA Rounds
27%
Grant Probability
65%
With Interview (+38.2%)
2y 11m (~10m remaining)
Median Time to Grant
High
PTA Risk
Based on 179 resolved cases by this examiner. Grant probability derived from career allowance 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