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 § 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)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-20 are rejected under 35 U.S.C. 102(a1) as being anticipated by Tunstall-Pedoe et al., (US 2023/0316006 A1).
As per claim 1, Tunstall-Pedoe et al., teach a method for generating context-augmented responses, the method comprising:
receiving a job application (0421);
extracting, from the job application, a question directed to a job applicant (0449-0450);
generating, using an embedding model, a vector representation of the question (0455, 1201);
identifying, within a vector database, a most similar vector to the vector representation of the question, wherein the most similar vector is associated with an annotated historical question (0455, 1201);
extracting, from a question-response database, an encoded context group corresponding to the annotated historical question, wherein the encoded context group comprises a historical job applicant context and a job listing context (1201, 0352, 0700);
retrieving, from a job applicant database, professional context of the job applicant; generating, based on the context group and the professional context, a prompt chain for causing a language model to generate a response for the question directed to the job applicant; processing, using the language model, the prompt chain to generate the response (Fig.10, 0449);
receiving, from the language model, the generated response for the question directed to the job applicant, wherein the generated response is based on the prompt chain (0700, 0714, 1201);
calculating, using a risk scoring model, a risk score for the generated response (0715, 0816-0817); and
in response to the risk score being below a predetermined threshold, populating a portion of the job application with the generated response(1126, 1171, 1179, 0004).
As per claim 2, Tunstall-Pedoe et al., teach the method of claim 1, further comprising: in response to the risk score being above the predetermined threshold, requesting, from the job applicant, feedback for the generated response (0715, 0816-0817).
As per claim 3, Tunstall-Pedoe et al., teach the method of claim 2, further comprising: receiving, from the job applicant, feedback for the generated response; and populating the portion of the job application based on the feedback (1013, 0421), .
As per claim 4, Tunstall-Pedoe et al., teach the method of claim method of claim 3, further comprising storing, within a user feedback database, question data corresponding to the question, user data corresponding to the job applicant, and feedback data corresponding to the feedback and the populated portion of the job application (1013, 0421, 0004).
As per claim 5, Tunstall-Pedoe et al., teach the method of claim 3, wherein the feedback for the generated response comprises a written response for answering the question directed to the job applicant (0020, 0116, 0134, 0201).
As per claim 6, Tunstall-Pedoe et al., teach the method of claim 1, wherein generating, based on the context group and the professional context, the prompt chain for causing the language model to generate the response for the question directed to the job applicant further comprises: selecting, based on navigation of a decision tree, a prompt template for generating the prompt chain, wherein the navigation of the decision tree is based on the question directed to the job applicant and corresponding historical data from the question-response database (0020, 0116, 0134, 0201, 0004, 1201, 0352, 0700).
As per claim 7, Tunstall-Pedoe et al., teach the method of claim 1, wherein the risk score is based on one or more of a length of the generated response, a difference between required context and available context for the question, a sensitivity value for an impact measurement associated with the question, a frequency value for the question, and a hallucination risk score (0050, 0700, 0715, 0770, 0845, 0865).
As per claim 8, Tunstall-Pedoe et al., teach a processing system, comprising: one or more memories comprising computer-executable instructions; and one or more processors configured to execute the computer-executable instructions causing the processing system to:
receive a job application (0421);
extract, from the job application, a question directed to a job applicant (0449-0450);
generate, using an embedding model, a vector representation of the question (0455, 1201);
identify, within a vector database, a most similar vector to the vector representation of the question, wherein the most similar vector is associated with an annotated historical question (0455, 1201);
extract, from a question-response database, an encoded context group corresponding to the annotated historical question, wherein the encoded context group comprises a historical job applicant context and a job listing context (1201, 0352, 0700);
retrieve, from a job applicant database, professional context of the job applicant; generate, based on the context group and the professional context, a prompt chain for causing a language model to generate a response for the question directed to the job applicant (Fig.10, 0449);
process, using the language model, the prompt chain to generate the response; receive, from the language model, the generated response for the question directed to the job applicant, wherein the generated response is based on the prompt chain (0700, 0714, 1201);
calculate, using a risk scoring model, a risk score for the generated response (0700, 0714, 1201); and
in response to the risk score being below a predetermined threshold, populate a portion of the job application with the generated response (1126, 1171, 1179, 0004).
As per claim 9, Tunstall-Pedoe et al., teach the processing system of claim 8, wherein the one or more processors are further configured to cause the processing system to, in response to the risk score being above the predetermined threshold, request, from the job applicant, feedback for the generated response (0715, 0816-0817).
As per claim 10, Tunstall-Pedoe et al., teach the processing system of claim 8, wherein the one or more processors are further configured to cause the processing system to: receive, from the job applicant, feedback for the generated response; and populate the portion of the job application based on the feedback (1012, 0421).
As per claim 11, Tunstall-Pedoe et al., teach the processing system of claim 8, wherein the one or more processors are further configured to cause the processing system to store, within a user feedback database, question data corresponding to the question, user data corresponding to the job applicant, and feedback data corresponding to the feedback and the populated portion of the job application (1013, 0421, 0004).
As per claim 12, Tunstall-Pedoe et al., teach the processing system of claim 10, wherein the feedback for the generated response comprises a written response for answering the question directed to the job applicant (0020, 0116, 0134, 0201).
As per claim 13, Tunstall-Pedoe et al., teach the processing system of claim 8, wherein to generate, based on the context group and the professional context, the prompt chain for causing the language model to generate the response for the question directed to the job applicant, the one or more processors are further configured to cause the processing system to: select, based on navigation of a decision tree, a prompt template for generating the prompt chain, wherein the navigation of the decision tree is based on the question directed to the job applicant and corresponding historical data from the question-response database (0020, 0116, 0134, 0201, 0004, 1201, 0352, 0700).
As per claim 14, Tunstall-Pedoe et al., teach the processing system of claim 8, wherein the risk score is based on one or more of a length of the generated response, a difference between required context and available context for the question, a sensitivity value for an impact measurement associated with the question, a frequency value for the question, a hallucination risk score (0050, 0700, 0715, 0770, 0845, 0865).
As per claim 15, Tunstall-Pedoe et al., teach a method for generating context-augmented responses, the method comprising:
receiving a job application (0421);
extracting, from the job application, a question directed to a job applicant (0449-0450);
generating, using an embedding model, a vector representation of the question (0455, 1201);
identifying, within a vector database, a most similar vector to the vector representation of the question, wherein the most similar vector is associated with an annotated historical question (0455, 1201);
extracting, from a question-response database, an encoded context group corresponding to the annotated historical question, wherein the encoded context group comprises a historical job applicant context and a job listing context (1201, 0352, 0700);
retrieving, from a job applicant database, professional context of the job applicant (Fig.10, 0449);
generating, based on the context group and the professional context, a prompt chain for causing a language model to generate a response for the question directed to the job applicant (Fig.10, 0449);
processing, using the language model, the prompt chain to generate the response; receiving, from the language model, the generated response for the question directed to the job applicant, wherein the generated response is based on the prompt chain (Fig.10, 0449);
determining a category for the response (1013, 0421); and
in response to determining that the category for the response is associated with a predetermined list of categories, sending a feedback request to the job applicant (1013, 0421).
As per claim 16, Tunstall-Pedoe et al., teach the method of claim 15, further comprising: receiving, from the job applicant, feedback for the generated response; and populating a portion of the job application based on the feedback (1013, 0421).
As per claim 17, Tunstall-Pedoe et al., teach the method of claim 16, wherein the feedback for the generated response comprises a written response for answering the question directed to the job applicant (0020, 0116, 0134, 0201).
As per claim 18, Tunstall-Pedoe et al., teach the method of claim 15, wherein generating, based on the context group and the professional context, the prompt chain for causing the language model to generate the response for the question directed to the job applicant further comprises: selecting, based on navigation of a decision tree, a prompt template for generating the prompt chain, wherein the navigation of the decision tree is based on the question directed to the job applicant and corresponding historical data from the question-response database (0020, 0116, 0134, 0201, 0004, 1201, 0352, 0700).
As per claim 19, Tunstall-Pedoe et al., teach the method of claim 15, wherein determining the category for the response further comprises: determining, using a trained classifier neural network, a question category for the question based on the predetermined list of categories and corresponding labeled examples; and determining the category for the response based on the question category (1232, 1251, 1279, 0810).
As per claim 20, Tunstall-Pedoe et al., teach the method of claim 16, further comprising storing, within a user feedback database, question data corresponding to the question, user data corresponding to the job applicant, and feedback data corresponding to the feedback and the populated portion of the job application (0894, 0978, 1013, 0421).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Please see attached form PTO-892.
The following references are applicable prior art.
Baldua et al., (US 2025/0110957 A1) teach receiving a first query including at least one first query term and configuring at least one prompt to cause a large language model to translate the at least one first query term into a set of functions that can be executed to obtain at least one second query term and generate and output a plan that is executable to create a modified version of the first query based on the at least one second query term. The plan is obtained by applying the large language model to the at least one prompt as configured. The plan is executed to determine the at least one second query term and create the modified version of the first query. The modified version of the first query is executed to provide, via the user interface, a response to the first query.
Tunstall-Pedoe et al., (US 11,989,507 B2) teach a method of interacting with a large language model (LLM), including the step of a processing system using a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, to provide new context data for the LLM, in order to improve the output, such as continuation text output, generated by the LLM in response to a prompt; and such as a method of interacting with a LLM, including the step of providing continuation data generated by the LLM to a processing system that uses a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, in which the processing system is configured to analyse the continuation output generated by the LLM in response to a prompt to enable an improved version of that continuation output to be provided to a user.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to VIJAY B CHAWAN whose telephone number is (571)272-7601. The examiner can normally be reached 7-5 Monday thru Thursday.
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, Richemond Dorvil can be reached at 571-272-7602. 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.
/VIJAY B CHAWAN/Primary Examiner, Art Unit 2658
Prosecution Insights