DETAILED ACTION
1. This action is responsive to remarks filed 6/8/2026.
Notice of Pre-AIA or AIA Status
2. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Amendment
3. The title has been amended and is accepted. Claim 16 has been cancelled and claim 17 amended to incorporate “a computer”, overcoming the 101 rejection.
Response to Arguments
4. Applicant’s arguments filed have been fully considered but are not persuasive.
Applicant argues on pages 7-8 of remarks that Zha fails to disclose:
generating an initial prompt instructing an LLM to produce a plurality of candidate prompt-templates for generating test prompts, said initial prompt defining:
an input data type to be included with a prompt generated using a candidate prompt-template, and
output data to be produced by an LLM that has processed a prompt generated using a candidate prompt-template;
passing the initial prompt through an LLM to generate a plurality of candidate prompt-templates.
Examiner respectfully disagrees.
Regarding claim 1 Zha teaches A computer implemented method of generating validated prompt-templates for generating prompts for instructing large language models (LLMs) to perform specific tasks (Abstract: Prompt discovery is performed for identifying prompts to natural language processing machine learning models. A request to determine a prompt for a natural language processing task performed by a pre-trained natural language processing machine learning model may be received. A task classification for the natural language processing task may be determined and candidate prompts for the natural language processing prompt task collection selected. Respective prompt results for the candidate prompts are evaluated to generate a prompt recommendation for the natural language processing task.;
Figures 1, 4, 9, 11- computer system, processor;
0020: prompt; [0025] NLP ML model(s) 124 may be pre-trained or custom NLP ML models and may be based on various different ML model architectures (e.g., Generative Pre-trained Transformer (GPT)-based ML models), and frameworks (e.g., PyTorch, TensorFlow, etc.). These NLP Models may be trained to perform various NLP processing tasks, such as document or dialogue summarization, paraphrasing, structure to text, relation extraction and/or coreference resolution, among others), said method comprising the steps of:
generating an initial prompt instructing an LLM to produce a plurality of candidate prompt-templates for generating test prompts (figure 1; paragraphs 0038: prompt ingestion; prompt submission may include the prompt; may also include various other information for the prompt, such as NLP processing task; description; information that can be included in an entry for the prompt; sample output;
43: prompt and NLP ML candidate selection 420. Prompt and NLP ML candidate selection 420 may utilize an NLP task classification, as well as other information from discovery request(s) 400 to select candidate prompts), said initial prompt defining:
an input data type to be included with a prompt generated using a candidate prompt-template (38: processing task, task categories; 42: prompt task classification; 43: prompt and NLP ML candidate selection 420. Prompt and NLP ML candidate selection 420 may utilize an NLP task classification, as well as other information from discovery request(s) 400 to select candidate prompts), and
output data to be produced by an LLM that has processed a prompt generated using a candidate prompt-template (38: sample output; 41: the sample output may an example of expected results);
passing the initial prompt through an LLM to generate a plurality of candidate prompt-templates (fig 1; 0025; 0038: interactions to submit prompts for discovery, selection, and development through a machine learning service; 43: prompt and NLP ML candidate selection 420. Prompt and NLP ML candidate selection 420 may utilize an NLP task classification, as well as other information from discovery request(s) 400 to select candidate prompts);
generating a plurality of test prompts, each test prompt constructed from one of the candidate prompt-templates using input data from a set of pre-labelled input data comprising a plurality of items of input data and corresponding labels (fig 4 435 test data; 0039: prompt validation tests; performance evaluations; 0046: evaluate performance of the candidate prompts;
46: Test data 435 may be obtained. Test data 435 may be specified or identified as part of discovery request 410 (e.g., by identifying a file, storage location, or other path for accessing test data 435, or test data 435 may be sample input 413). In some embodiments, test data 435 may be maintained by machine learning service 210 for evaluating the identified NLP task. When the test data 435 is obtained, the candidate prompts 432 may be used to generate inferences using the candidate NLP ML model(s) 433 on the test data; labeled or ground truth data for test data 435 is used to score the accuracy of the candidate prompt),
passing each test prompt through a further LLM to generate an output (0039 Using test data for an NLP processing task, like task 313, inferences may be made using the prompt; 46);
assessing the output data produced by each test prompt with respect to the corresponding label associated with input data with which the test prompt was passed through the further LLM (0039 Using test data for an NLP processing task, like task 313, inferences may be made using the prompt 311 and obtain for validation, as indicated at 353. These inferences may then be compared with the sample output 317 and ground truth labels for the test data to determine whether the prompt's claimed sample output 317 is achieved; 0046 Results 434 for candidate prompts may be collected; labeled or ground truth data for test data 435 is used to score the accuracy of the candidate prompt), and
selecting, based on the assessing, one or more of the candidate-prompt-templates for subsequent generation of prompts (0046: a test data sample output may be obtained for inclusion in a prompt recommendation; 0047: recommendation).
Zha teaches a prompt development and discovery system that uses machine learning (fig 2; 0033), where the system includes prompt ingestion and discovery.
Prompt ingestion focuses on receiving a prompt (submission) and corresponding information such as input data type and output data, performing testing and validation (fig 3 310, 311, 313, 315, 317; para 0038).
Prompt discovery receives requests, and corresponding information (description, sample input/output) for processing to obtain candidate prompts (fig 4; 0041-44).
Zha therefore teaches initial prompts with corresponding information (generating an initial prompt), and utilizing machine learning to generate candidate prompts (passing initial prompt …to generate candidate prompts), which reads on the limitations as currently recited.
Further elaborating on certain limitations, e.g. “initial prompt instructing”; “to generate a plurality of candidate prompt”, and tying them together, may help to advance prosecution and differentiate over cited prior art of record.
Therefore, the claims do not yet overcome the cited prior art and the rejections are maintained. The additional independent and dependent claims are rejected based on arguments presented above and art rejections below.
Claim Rejections - 35 USC § 102
5. 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 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.
6. 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.
(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.
7. Claims 1-9, 12, 17 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Zha et al (2024/0202458).
Regarding claim 1 Zha teaches A computer implemented method of generating validated prompt-templates for generating prompts for instructing large language models (LLMs) to perform specific tasks (Abstract: Prompt discovery is performed for identifying prompts to natural language processing machine learning models. A request to determine a prompt for a natural language processing task performed by a pre-trained natural language processing machine learning model may be received. A task classification for the natural language processing task may be determined and candidate prompts for the natural language processing prompt task collection selected. Respective prompt results for the candidate prompts are evaluated to generate a prompt recommendation for the natural language processing task.;
Figures 1, 4, 9, 11- computer system, processor;
0020: prompt; [0025] NLP ML model(s) 124 may be pre-trained or custom NLP ML models and may be based on various different ML model architectures (e.g., Generative Pre-trained Transformer (GPT)-based ML models), and frameworks (e.g., PyTorch, TensorFlow, etc.). These NLP Models may be trained to perform various NLP processing tasks, such as document or dialogue summarization, paraphrasing, structure to text, relation extraction and/or coreference resolution, among others), said method comprising the steps of:
generating an initial prompt instructing an LLM to produce a plurality of candidate prompt-templates for generating test prompts (figure 1; paragraphs 0038: prompt ingestion; prompt submission may include the prompt; may also include various other information for the prompt, such as NLP processing task; description; information that can be included in an entry for the prompt; sample output;
43: prompt and NLP ML candidate selection 420. Prompt and NLP ML candidate selection 420 may utilize an NLP task classification, as well as other information from discovery request(s) 400 to select candidate prompts), said initial prompt defining:
an input data type to be included with a prompt generated using a candidate prompt-template (38: processing task, task categories; 42: prompt task classification; 43: prompt and NLP ML candidate selection 420. Prompt and NLP ML candidate selection 420 may utilize an NLP task classification, as well as other information from discovery request(s) 400 to select candidate prompts), and
output data to be produced by an LLM that has processed a prompt generated using a candidate prompt-template (38: sample output; 41: the sample output may an example of expected results);
passing the initial prompt through an LLM to generate a plurality of candidate prompt-templates (fig 1; 0025; 0038: interactions to submit prompts for discovery, selection, and development through a machine learning service; 43: prompt and NLP ML candidate selection 420. Prompt and NLP ML candidate selection 420 may utilize an NLP task classification, as well as other information from discovery request(s) 400 to select candidate prompts);
generating a plurality of test prompts, each test prompt constructed from one of the candidate prompt-templates using input data from a set of pre-labelled input data comprising a plurality of items of input data and corresponding labels (fig 4 435 test data; 0039: prompt validation tests; performance evaluations; 0046: evaluate performance of the candidate prompts;
46: Test data 435 may be obtained. Test data 435 may be specified or identified as part of discovery request 410 (e.g., by identifying a file, storage location, or other path for accessing test data 435, or test data 435 may be sample input 413). In some embodiments, test data 435 may be maintained by machine learning service 210 for evaluating the identified NLP task. When the test data 435 is obtained, the candidate prompts 432 may be used to generate inferences using the candidate NLP ML model(s) 433 on the test data; labeled or ground truth data for test data 435 is used to score the accuracy of the candidate prompt),
passing each test prompt through a further LLM to generate an output (0039 Using test data for an NLP processing task, like task 313, inferences may be made using the prompt; 46);
assessing the output data produced by each test prompt with respect to the corresponding label associated with input data with which the test prompt was passed through the further LLM (0039 Using test data for an NLP processing task, like task 313, inferences may be made using the prompt 311 and obtain for validation, as indicated at 353. These inferences may then be compared with the sample output 317 and ground truth labels for the test data to determine whether the prompt's claimed sample output 317 is achieved; 0046 Results 434 for candidate prompts may be collected; labeled or ground truth data for test data 435 is used to score the accuracy of the candidate prompt), and
selecting, based on the assessing, one or more of the candidate-prompt-templates for subsequent generation of prompts (0046: a test data sample output may be obtained for inclusion in a prompt recommendation; 0047: recommendation).
Regarding claim 2 Zha teaches A computer implemented method according to claim 1, wherein the output data defined in the initial prompt comprises property data associated with a property of the input data defined in the initial prompt (fig 4 410; 40: description, task; 42: prompt task classification).
Regarding claim 3 Zha teaches A computer implemented method according to claim 2, wherein the initial prompt further defines a constraint instruction to be applied by each test prompt which constrains the generated property data generated by each test prompt (fig 4 410; 41: the sample output may an example of expected results (e.g., The most frequent sentiment of commenters on the post is [sentiment]”); 0038 sample output).
Regarding claim 4 Zha teaches A computer implemented method according to claim 3, wherein the constraint instruction specifies a plurality of predetermined properties of which the output data must comprise one (fig 4 410; 0038; 41: the sample output may an example of expected results (e.g., The most frequent sentiment of commenters on the post is [sentiment]”)).
Regarding claim 5 Zha teaches A computer implemented method according to claim 2, wherein the property is one of a qualitative property of the input data or a quantitative property of the input data (fig 4 410; 0040: description, task; 42: prompt task classification; 41: the sample output may an example of expected results (e.g., The most frequent sentiment of commenters on the post is [sentiment]”)).
Regarding claim 6 Zha teaches A computer implemented method according to claim 1, wherein the input data type defined by the initial prompt is text data (41: sample input may be sample document, file, or other text; 43).
Regarding claim 7 Zha teaches A computer implemented method according to claim 6, wherein the input data type defined by the initial prompt is unstructured text data from a received message (19-20; 42; 43: text summarization;
19: NLP ML models, for example, may be trained using training data sets of documents or other sets of natural language (e.g., human language) to perform various natural language processing tasks, including, but not limited to information extraction (e.g., named entity recognition, relation extraction, coreference resolution, events extraction and joint entity relation extraction), text classification (e.g., classification, sentiment, relation classification, topic classification, paraphrase identification, word sense disambiguation, and natural language inference), question answering (e.g., extractive QA and close-book QA), summarization (e.g., extractive summarization and abstractive summarization), generation (e.g., sentence completion and structure to text), among others. – making natural language decisions for unstructured text).
Regarding claim 8 Zha teaches A computer implemented method according to claim 2, wherein each label associated with each item of pre-labelled data specifies property data associated with a property of the item of pre-labelled data (43: NLP task classification, as well as other information from discovery request(s) ; prompts may be organized or identified with different prompt task collections 421. Each prompt task collection 421 may correspond to a task classification.
46: Test data 435 may be obtained. Test data 435 may be specified or identified as part of discovery request 410 (e.g., by identifying a file, storage location, or other path for accessing test data 435, or test data 435 may be sample input 413). In some embodiments, test data 435 may be maintained by machine learning service 210 for evaluating the identified NLP task. When the test data 435 is obtained, the candidate prompts 432 may be used to generate inferences using the candidate NLP ML model(s) 433 on the test data; labeled or ground truth data for test data 435 is used to score the accuracy of the candidate prompt).
Regarding claim 9 Zha teaches A computer implemented method according to claim 8, wherein the property data specified by each label associated with each item of pre-labelled data specifies one of a plurality of predetermined properties (43: NLP task classification, as well as other information from discovery request(s) ; prompts may be organized or identified with different prompt task collections 421. Each prompt task collection 421 may correspond to a task classification.
46: Test data 435 may be obtained. Test data 435 may be specified or identified as part of discovery request 410 (e.g., by identifying a file, storage location, or other path for accessing test data 435, or test data 435 may be sample input 413). In some embodiments, test data 435 may be maintained by machine learning service 210 for evaluating the identified NLP task. When the test data 435 is obtained, the candidate prompts 432 may be used to generate inferences using the candidate NLP ML model(s) 433 on the test data; labeled or ground truth data for test data 435 is used to score the accuracy of the candidate prompt).
Regarding claim 12 Zha teaches A system for generating validated prompt-templates for generating prompts for instructing large language models (LLMs) to perform specific tasks, said system comprising a prompt-template generation instruction module configured to generate an initial prompt instructing an LLM to produce a plurality of candidate prompt-templates for generating test prompts, said initial prompt defining:
an input data type to be included with a prompt generated using a candidate prompt-template, and output data to be produced by an LLM that has processed a prompt generated using a candidate prompt-template, said prompt-template generation instruction module configured to communicate the initial prompt to a first LLM system to generate a plurality of candidate prompt-templates, wherein
said system further comprises a test prompt generation module configured to generate a plurality of test prompts, each test prompt constructed from one of the candidate prompt-templates generated by the prompt-template generation instruction module using input data from a set of pre-labelled input data comprising a plurality of items of input data and corresponding labels, said test prompt generation module configured to communicate each test prompt through a further LLM system to generate an output, and
said system further comprising a prompt-template assessment unit configured to assess the output data produced by each test prompt with respect to the corresponding label associated with input data with which the test prompt was passed through the further LLM, and select, based on the assessing, one or more of the candidate-prompt-templates for subsequent generation of prompts.
Claim recites limitations similar to claim 1 and is rejected for similar rationale and reasoning
Regarding claim 17 Zha teaches A computer including a computer program providing instructions which when implemented on a computing device implements a method according to claim 1.
Claim recites limitations similar to claim 1 and is rejected for similar rationale and reasoning
Claim Rejections - 35 USC § 103
8. 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.
9. Claims 10-11, 13-15 are rejected under 35 U.S.C. 103 as being unpatentable over Zha et al (2024/0202458) in view of Zeng et al (2005/0234955).
Regarding claim 10 Zha does not specifically teach where Zeng teaches A computer implemented method according to claim 1, further comprising generating the set of pre-labelled input data by:
retrieving labelled data samples from a labelled data samples data store (18 labeled data);
retrieving unlabelled data from an unlabelled-data data store (18 unlabeled data);
labelling the unlabelled data using an AI process guided by the labelled data (18 unlabeled data is then labeled),
generating labelled data (18)
([0018] The following systems and methods for clustering based text classification (CBC) utilize both labeled and unlabeled data in semi-supervised learning operations. The systems and methods first cluster training data, which includes labeled and unlabeled data, with guidance of the labeled data. At least a portion of the unlabeled data is then labeled based on the obtained clusters to generate an expanded labeled dataset. In one implementation, discriminative classifiers are then trained with the expanded labeled dataset. In this manner, the systems and methods provide for semi-supervised learning treated as clustering aided by labeled data. Such labeled data may provide important information for latent class variables, assisting in the determination of parameters associated with clustering operations to affect final clustering results. By latent class variables we mean that the variables used to generate the data samples.), and
{storing the labelled data as pre-labelled input data for use in generating the test prompts}.
It would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate Zeng for an improved system to generate the pre-labelled (test) data for proper testing of the candidate prompts.
Zha already teaches labelled test data for use in testing candidate prompts based on specific natural language task classification, and one could look to Zeng to further generate the labelled data, and with Zha allowing for
storing the labelled data as pre-labelled input data for use in generating the test prompts.
Regarding claim 11 Zha does not specifically teach where Zeng teaches A computer implemented method according to claim 10, wherein the AI process is one of a semi-supervised learning process, an active learning process or a clustering process (0018: clustering; semi-supervised learning).
Rejected for similar rationale and reasoning as claim 10
Claims 13-15 recite limitations similar to claims 10-11 and are rejected for similar rationale and reasoning
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 SHAUN A ROBERTS whose telephone number is (571)270-7541. The examiner can normally be reached Monday-Friday 9-5 EST.
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, Andrew Flanders can be reached on 571-272-7516. 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.
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 or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/SHAUN ROBERTS/Primary Examiner, Art Unit 2655
Prosecution Insights