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 .
DETAILED ACTION
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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 July 22, 2026 has been entered.
Status of Claims
Claims 1, 3 and 13 have been amended.
Claims 2 and 14 have been cancelled.
Claims 1, 3-10, 13, and 15-18 are currently pending and have been examined.
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, 3-10, 13, and 15-18 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1:
Claims 13 and 15-18 are drawn to methods while claim(s) 1 and 3-10 is/are drawn to an apparatus. As such, claims 1, 3-10, 13, and 15-18 are drawn to one of the statutory categories of invention (Step 1: YES).
Step 2A - Prong One:
Claim 13 (representative of independent claim(s) 1) recites the following steps:
A method, comprising: obtaining a first prompt from a user for generating a deep customized job description directed towards job candidates, wherein the deep customized job description is free from limitations of a human drafter
performing pre-processing operations on the request to generate an enriched prompt
wherein performing the pre-processing operations further comprises: determining one or more aspects contained in the first prompt, wherein the one or more aspects comprise at least one of a role or a skill associated with a job;
determining a plurality of qualified profiles that are other than prototype profiles specified by a user and contain the one or more aspects required by the first prompt wherein determining the plurality of qualified profiles further comprises:
calculating, based on a pre-calculated similarity or a similarity distance, a similarity value between a talent profile obtained from a database and at least one of the prototype profiles; and
classifying the talent profile as one of the plurality of qualified profiles responsive to determining that the talent profile is similar to the at least one of the prototype profiles based on the similarity value;
retrieving a plurality of common features from the plurality of qualified profiles,
wherein the common features include at least one of skills, years of experience, or education level; and
incorporating the plurality of common features into the first prompt to generate the enriched prompt to the large language model engine;
submitting the enriched prompt and receive a job description
performing post-processing operations on the generated job description to generate the deep customized job description;
providing the deep customized job description for presentation.
Alternatively, these steps, under its broadest reasonable interpretation, encompass a human manually (e.g., in their mind, or using paper and pen) generating a job description from qualified profiles (i.e., one or more concepts performed in the human mind, such as one or more observations, evaluations, judgments, opinions), but for the recitation of generic computer components. If one or more claim limitations, under their broadest reasonable interpretation, covers performance of the limitation(s) in the mind but for the recitation of generic computer components, then it falls within the "mental processes" subject matter grouping of abstract ideas.
As such, the Examiner concludes that claim 13 recites an abstract idea (Step 2A - Prong One: YES).
Independent claim(s) 1 is determined to recite an abstract idea under the same analysis.
Step 2A - Prong Two:
This judicial exception is not integrated into a practical application. The claim(s) recite the additional elements/limitations of:
a user interface (Claims 1 and 13)
the large language model engine (Claims 1 and 13)
A system comprising one or more processing devices and one or more storage devices for storing instructions that when executed by the one or more processing devices cause the one or more processing devices to (Claim 1)
The requirement to execute the claimed steps/functions listed above is equivalent to adding the words ''apply it'' on a generic computer and/or mere instructions to implement the abstract idea on a generic computer. This/these limitation(s) do/does not impose any meaningful limits on producing the abstract idea and therefore do/does not integrate the abstract idea into a practical application (see MPEP 2106.05(f)).
Additionally, “Step 2A - Prong 2”, the recited additional element(s) of "generated by the large language model engine;" serve merely to generally link the use of the judicial exception to a particular technological environment or field of use. These limitations therefore do not integrate the abstract idea into a practical application (see MPEP 2106.05(h)).
The Examiner has therefore determined that the additional elements, or combination of additional elements, do not integrate the abstract idea into a practical application. Accordingly, the claim(s) is/are directed to an abstract idea (Step 2A -Prong Two: NO).
Step 2B:
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
As discussed above in "Step 2A - Prong 2", the requirement to execute the claimed steps/functions listed above is equivalent to adding the words "apply it" on a generic computer and/or mere instructions to implement the abstract idea on a generic computer. These limitations therefore do not qualify as "significantly more" (see MPEP 2106.05 (f)).
As discussed above in “Step 2A - Prong 2”, the recited additional element(s) of “generated by the large language model engine” serves merely to generally link the use of the judicial exception to a particular technological environment or field of use. These limitations therefore do not qualify as “significantly more5' (see MPEP 2106.05(g, h)).
The Examiner has therefore determined that no additional element, or combination of additional claims elements is/are sufficient to ensure the claim(s) amount to significantly more than the abstract idea identified above (Step 2B: NO).
Regarding Dependent Claims:
Dependent claims 2, 3, 5-6, 14, 16 and 18 fail to include any additional elements and are further part of the abstract idea as identified by the Examiner.
Dependent claims 4, 7-10, 15 and 17 include additional limitations that are part of the abstract idea except for:
the large language model engine the second user interface
a talent database
a user interface
machine learning module
The additional elements of the dependent claims are equivalent to adding the words ''apply it'' on a generic computer and/or mere instructions to implement the abstract idea on a generic computer. Even in combination, these additional elements do not integrate the abstract idea into a practical application and do not amount to significantly more than the abstract idea itself. The claims are ineligible.
Prior Art
Examiner conducted a thorough search of the body of available prior art (see attached documents regards PTO-892 Notice of Reference Cited and PE2E Search History). Notably, Examiner discovered several patent literature documents that taught aspects of the invention, but no single disclosure taught “every element required by the claims under its broadest reasonable interpretation” [MPEP § 2131] to make a 35 USC § 102 rejection. Further, Examiner considered the individual elements of the recited claims taught across the prior art cited below, but did not find it obvious to combine such disclosures [MPEP § 2142] to make a 35 USC § 103 rejection. In particular, Hardtke et al. 2014/0122355 discloses automatically and rapidly surfacing optimal candidates but does not teach generating prompts for the large language model. U.S. Publication No. Yerastov 2023/0004941 et al., discloses techniques are described herein for automatically generating job descriptions using a corpus-based approach, e.g., based on a job description dataset, is silent with respect to perform post-processing operations and determine one or more exclusive words in the prompt using diversity rules.
Response to Arguments
Applicant’s amendments overcome the rejection under 35 USC 112. The rejection has been withdrawn.
Applicant's arguments filed with respect to the rejection under 35 USC 101 have been fully considered but they are not persuasive.
Applicant Argues: The claims contain patent-eligible subject matter when they are analyzed under the two-part analysis for abstract ideas laid out in Alice, the July 2024 Subject matter Eligibility Examples issued by the USPTO, the August 4, 2025 Memorandum from Deputy Commissioner for Patents, and the ex parte Desjardins Decision by Appeals Review Panel of the Patent Trial and Appeal Board.
Examiner respectfully disagrees. The instant claims are not at all like the claims of the ex parte Desjardins Decision. Applicant argues that the claims are similar to Ex Parte Desjardins in that they provide a technological improvement. This is not persuasive. Although the claims feature the training and execution of machine learning modules, this does not constitute an improvement in the realm of machine learning or computers. For example, the claims fail to introduce any unconventional method of prompt engineering as the Applicant claims. The claims merely determine various correlations for creating an optimal prompt in a LLM. The rejection is maintained.
Applicant Argues: In the Step 2A analysis, the Office action alleges that the original claim 13 includes steps encompassing "a human manually (e.g., in their mind, or using paper and pen) generating a job description." See Office action at page 3. Applicant submits that claim 13 as presented does not encompass a human manually generating a job description.
Examiner respectfully disagrees. The claims are directed to the abstract idea of generating a job description from other talent profiles. The consideration of the large language model that generates a deep customize job description is evaluated under Step 2A Prong II: additional elements.
Applicant Argues: In Step 2B analysis, applicant submits that claim 13 improves the computer technology in the prompt engineering. Claim 13 as presented includes features for generating an enriched prompt that when submitted to the large language model, causes the large language model generates a deep customized job description that is free from limitations of human drafter.
Examiner respectfully disagrees. Applicant’s alleged improvement is not directed to an improvement to computer functionality/capabilities, an improvement to a computer-related technology or technological environment, and do not amount to a technology-based solution to a technology-based problem. A showing that a claim is directed to any improvement does not automatically mean a claim is patent eligible (e.g., an improved business function or an improved idea itself is not patent eligible). In this case, generating a job description is an abstract idea, and an “improved” way of generating a job description by using a large language model engine (which is equivalent to adding the words "apply it" on a generic computer and/or mere instructions to implement the abstract idea on a generic computer) is, if anything, an improvement to the idea itself.
Conclusion
THIS ACTION IS MADE FINAL. 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 RASHIDA R SHORTER whose telephone number is (571)272-9345. The examiner can normally be reached Monday- Friday from 9am- 530pm.
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, Jessica Lemieux can be reached at (571) 270-3445. 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.
/RASHIDA R SHORTER/Primary Examiner, Art Unit 3626
Prosecution Insights