Prosecution Insights
Last updated: April 19, 2026
Application No. 18/746,940

SYSTEM AND METHOD FOR ENHANCING CHATBOT INTELLIGENCE THROUGH TRANSFORMER-BASED TABULAR QUESTION-ANSWERING MODEL INTEGRATION WITH CYCLICAL VECTOR DATASET GENERATION

Non-Final OA §101§102§103§112
Filed
Jun 18, 2024
Examiner
WALDRON, SCOTT A
Art Unit
2152
Tech Center
2100 — Computer Architecture & Software
Assignee
BANK OF AMERICA CORPORATION
OA Round
1 (Non-Final)
82%
Grant Probability
Favorable
1-2
OA Rounds
2y 11m
To Grant
99%
With Interview

Examiner Intelligence

Grants 82% — above average
82%
Career Allow Rate
387 granted / 474 resolved
+26.6% vs TC avg
Strong +31% interview lift
Without
With
+31.2%
Interview Lift
resolved cases with interview
Typical timeline
2y 11m
Avg Prosecution
17 currently pending
Career history
491
Total Applications
across all art units

Statute-Specific Performance

§101
18.4%
-21.6% vs TC avg
§103
32.8%
-7.2% vs TC avg
§102
22.4%
-17.6% vs TC avg
§112
18.2%
-21.8% vs TC avg
Black line = Tech Center average estimate • Based on career data from 474 resolved cases

Office Action

§101 §102 §103 §112
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 . Claims 1-20 are presented for examination. Claim Rejections - 35 USC § 112 The following is a quotation of 35 U.S.C. 112(b): (b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention. The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph: The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention. Claims 1-20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention. The intended use preamble of independent claims 1, 11 & 20 recites “for running an AI chatbot”. The use of the acronym “AI”, without an explanation recited in the claims, renders the claims indefinite. The examiner suggests amending to treat AI similar to the claim’s parenthetical handling of LLM to overcome this part of the rejection. Claims 1, 11 & 20 each recite three instances of “if”, which is optional language that makes the claims unclear if the corresponding limitation actually limits the claim. The examiner suggests replacing “if” with “whether” to positively recite an action taking place to overcome this part of the rejection. Claims 2, 12 & 20 recite “the database tables including answers to projected future queries in response to the event”. This is the second instance of “projected future queries” in each claim, and it appears the second instance should be amended to recite “the database tables including answers to the projected future queries in response to the event”. The remaining claims, not specifically addressed above, are rejected at least for their dependency on a rejected claim. 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 the judicial exception of an abstract idea without significantly more. Step 1 The claims recite a method, system, and method (claims 1, 11 & 20). These claims fall within at least one of the four categories of patentable subject matter. Step 2A Prong One Independent claim 1 recites “determining if the query is eligible for a bypass processing method; if the query is not eligible, using a large language model (“LLM”) to produce a first answer; if the query is eligible, processing the query using the bypass processing method to bypass the LLM and, instead of using the LLM, implementing a vector-based processing system by: using the retriever model to tokenize the query into an input vector; querying a vector database for tables associated with the input vector, wherein: the vector database is configured to capture semantic relationships between the tables, and, as a result, narrow down possible answers and assist parsing the tables to reduce a quantity of selected tables to be queried; and the selected tables are configured to be dynamically structured for querying; using the retriever model: running a similarity search to search the vector database for vectors that have at least a threshold level of commonality to the input vector; and returning vectors from the vector database that are identified by the similarity search as having at least the threshold level of commonality; using the transformer-based table reader to produce a second answer to the query by processing the vectors and the input vector using the pretrained routines; updating the vector database to include the input vector”. These steps perform analysis on information which has been received, which are acts of evaluating information that can be practically performed in the human mind. Thus, these steps are an abstract idea in the “mental process” grouping. Claims 3-10 recite limitations that are further extensions of the identified grouping. Claims 11-19 recite limitations which correspond to claims 1-9, respectively. Claims 11 & 20 recite limitations which correspond to claims 1 and 1 & 2, respectively. Step 2A Prong Two This judicial exception is not integrated into a practical application because the combination of additional elements includes only generic computer elements which do not add a meaningful limitation to the abstract idea because they amount to simply implementing the abstract idea on a computer. These additional elements include: AI chatbot, large language model, models, transformers, processing power, digital bandwidth, services, system, and computing processor. Independent claim 1 recites “receiving a query from a user; transmitting the query to a retriever model; transmitting the vectors and the input vector to a transformer-based table reader that includes pretrained routines for answering queries; providing to the user the second answer to the query; and processing the query using the bypass processing method uses less processing power and digital bandwidth than the LLM”. The claim recites limitations which amount to insignificant extra-solution activity of data gathering, such as receiving input, transmitting output, and updating/modifying data. Claim 2 recites limitations that are further extensions of the identified grouping. Claims 11-19 recite limitations which correspond to claims 1-9, respectively. Claims 11 & 20 recite limitations which correspond to claims 1 and 1 & 2, respectively. Step 2B The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the recitations of generic computer components performing generic computer functions at a high level of generality do not meaningfully limit the claim. Further, the insignificant extra-solution activities of data gathering and presentation do not meaningfully limit the claim. Claim Rejections - 35 USC § 102 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 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)(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. Claims 1 & 11 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Taheri (US 2025/0117630 A1, hereinafter “Taheri”). Taheri teaches: 1. A method for running an AI chatbot that leverages dynamically structured data sources using vector dataset processing for outputting query responses with reduced processing resources [Taheri, Abstract], the method comprising: receiving a query from a user [Taheri, ¶ 0034]; determining if the query is eligible for a bypass processing method [Taheri, ¶ 0045]; if the query is not eligible, using a large language model (“LLM”) to produce a first answer [Taheri, ¶ 0034]; if the query is eligible, processing the query using the bypass processing method to bypass the LLM and, instead of using the LLM, implementing a vector-based processing system by [Taheri, ¶¶ 0045 & 0046]: transmitting the query to a retriever model [Taheri, ¶¶ 0045 & 0046]; using the retriever model to tokenize the query into an input vector [Taheri, ¶ 0102]; querying a vector database for tables associated with the input vector [Taheri, ¶ 0102], wherein: the vector database is configured to capture semantic relationships between the tables, and, as a result, narrow down possible answers and assist parsing the tables to reduce a quantity of selected tables to be queried [Taheri, ¶¶ 0100 - 0102]; and the selected tables are configured to be dynamically structured for querying [Taheri, ¶¶ 0100 - 0102]; using the retriever model: running a similarity search to search the vector database for vectors that have at least a threshold level of commonality to the input vector [Taheri, ¶ 0100]; and returning vectors from the vector database that are identified by the similarity search as having at least the threshold level of commonality [Taheri, ¶ 0100]; transmitting the vectors and the input vector to a transformer-based table reader that includes pretrained routines for answering queries [Taheri, ¶ 0101]; using the transformer-based table reader to produce a second answer to the query by processing the vectors and the input vector using the pretrained routines [Taheri, ¶¶ 0101, 0102 & 0148-0150]; providing to the user the second answer to the query [Taheri, ¶ 0102]; and updating the vector database to include the input vector [Taheri, ¶ 0103]; wherein: processing the query using the bypass processing method uses less processing power and digital bandwidth than the LLM [Taheri, ¶ 0101]. Claim 11 recites limitations similar to those recited in claim 1 and is rejected for the same reasons discussed above. 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. 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. 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. Claims 2-10 & 12-20 are rejected under 35 U.S.C. 103 as being unpatentable over: (i) Taheri in view of (ii) Rumade et al. (US 2025/0086170 A1, hereinafter “Rumade”). Taheri does not explicitly teach, but Rumade teaches: 2. The method of claim 1 further comprising, prior to the querying, generating answers to projected future queries in response to an event [Rumade, ¶ 0046], the generating comprising: triggering, via the event, a data retriever service [Rumade, ¶ 0046]; using the data retriever service: receiving conventional database data from a cluster of database tables, the cluster of database tables containing the input vector [Rumade, ¶¶ 0042 & 0043]; transmitting the input vector and the conventional database data to a collection of common table generation services [Rumade, ¶¶ 0042 & 0043]; using the collection of common table generation services: running a similarity search to search the cluster of database tables for database tables that have at least a threshold level of commonality to the input vector and the conventional database data [Rumade, ¶¶ 0042 & 0043]; returning database tables that are identified by the similarity search as having at least the threshold level of commonality, the database tables including answers to projected future queries in response to the event [Rumade, ¶¶ 0044 & 0053]; transmitting the database tables to a vectorizing service; and using the vectorizing service [Rumade, ¶ 0044]: tokenizing the database tables into tokenized vectors, the tokenized vectors configured to be dynamically structured for the querying [Rumade, ¶ 0044]; and updating the vector database to include the tokenized vectors [Rumade, ¶ 0044]. 3. The method of claim 2 wherein the event is a cyclical event [Rumade, ¶¶ 0033 & 0034]. 4. The method of claim 2 wherein the cluster of database tables comprises data views, and the data views are configured to be available in a table format [Rumade, ¶¶ 0028 & 0086]. 5. The method of claim 2 wherein the collection of common table generation services includes categorical services [Rumade, ¶¶ 0033 & 0034]. 6. The method of claim 2 wherein the collection of common table generation services includes temporal services [Rumade, ¶¶ 0033 & 0034]. 7. The method of claim 2 wherein the collection of common table generation services includes both categorical and temporal services [Rumade, ¶¶ 0033 & 0034]. 8. The method of claim 2 wherein the threshold level of commonality is at least 10 strings of integers in common [Rumade, ¶ 0038]. 9. The method of claim 3 wherein the cyclical event includes a monthly scheduled event [Rumade, ¶¶ 0033 & 0034]. 10. The method of claim 3 wherein the cyclical event includes a mortgage filing [Rumade, ¶¶ 0033 & 0034]. Claims 12-19 recite limitations similar to those recited in claims 1-9, respectively, and are rejected for the same reasons discussed above. Claim 20 recites limitations similar to those recited in claims 1 & 2 combined, and is rejected for the same reasons discussed above. Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to Scott A. Waldron whose telephone number is (571)272-5898. The examiner can normally be reached Monday - Friday 9:00 am - 5:00 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, Neveen Abel-Jalil can be reached at (571)270-0474. 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. /Scott A. Waldron/Primary Examiner, Art Unit 2152 03/21/2026
Read full office action

Prosecution Timeline

Jun 18, 2024
Application Filed
Mar 21, 2026
Non-Final Rejection — §101, §102, §103 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12596704
Error Prediction Using Database Validation Rules and Machine Learning
2y 5m to grant Granted Apr 07, 2026
Patent 12591784
DECISION-MAKING METHOD FOR AGENT ACTION AND RELATED DEVICE
2y 5m to grant Granted Mar 31, 2026
Patent 12585667
PROVIDING INFORMATION ASSOCIATED WITH A CONTENT BASED ON CONTEXT
2y 5m to grant Granted Mar 24, 2026
Patent 12585701
IDEATION PLATFORM DEVICE AND METHOD USING DIAGRAM
2y 5m to grant Granted Mar 24, 2026
Patent 12579155
SYSTEMS AND METHODS FOR INTERFACE GENERATION USING EXPLORE AND EXPLOIT STRATEGIES
2y 5m to grant Granted Mar 17, 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

1-2
Expected OA Rounds
82%
Grant Probability
99%
With Interview (+31.2%)
2y 11m
Median Time to Grant
Low
PTA Risk
Based on 474 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