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 § 103
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 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Sampath (US Pub. 20240354176) in view of Townsend et al. (US Pub. 20250028900).
Referring to claim 1, Sampath discloses A device, comprising: a processing system including a processor; and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations [fig. 2, computing system 400, processor 402, and memory 402], the operations comprising:
receiving…a sample input format specification and output format specification for transforming data [pars. 58, 61-63, 97, 110, and 111; an input prompt generated for an LLM specifies an input format and an output format for translating a plurality of event messages (e.g., “prompt”: {“<error message from event X>, <error message from event Y>, <error message from event Z>”, “completion”=“summary of consequences of event X, event Y and event Z in a human-readable notification message”})];
searching a repository for a tag and associated data [fig. 4; pars. 73, 91-94, 112, and 113; the notification processor determines whether an aggregation trigger has occurred based on priority labels and dependency relationships associated with the plurality of event messages, which entails retrieving the associated priority labels and dependency relationships from a dependency/priority data store of a storage memory; the associated priority labels and dependency relationships are included as input prompt context in the input prompt in addition to the plurality of event messages];
merging or updating the sample input format specification and the output format specification with the associated data responsive to finding the tag in the repository, thereby creating updated data [fig. 4; pars. 73, 91-94, 112, and 113; the input prompt is updated to include the input prompt context (e.g., “Event X is a high priority event, event Y is a medium priority event and event Z is a low priority event”. As a further non-limiting example, such text indication in machine-readable format may include: “prompt”: {“<error message from event X, “high priority”>, <error message from event Y, “medium priority”>, <error message from event Z, “low priority”>”,})];
providing the updated data as a prompt to a large language model [par. 123; the notification processor inputs the input prompt including the plurality of event messages and the input prompt context into the LLM];
receiving a response to the prompt from the large language model [par. 123; the LLM generates an aggregation notification message in response to the input prompt];
verifying that the response is satisfactory [par. 132; user response (or lack thereof) to the aggregation notification message provides feedback about the aggregation notification message]; and
storing a context comprising the tag, the updated data and the response in the repository [fig. 4; pars. 127 and 131; the aggregation notification message is stored in a notification datastore of a storage memory in association with the plurality of event messages, the aggregation trigger based on priority labels and dependency relationships associated with the plurality of event messages, customer information (e.g., user feedback), which is used to associate the aggregation notification message with a usability or desirability ranking].
Sampath does not appear to explicitly disclose that the sample input format specification and the output format specification is received from a user interface.
However, Townsend discloses that the sample input format specification and the output format specification is received from a user interface [fig. 3C; par. 69; a user provides instructions describing desired information to be extracted and desired formatting of the extracted information via new or updated prompts to an LLM].
It would have been obvious to one or ordinary skill in the art before the effective filing date of the claimed invention to modify the input prompt taught by Sampath so that the input prompt is provided by a user as taught by Townsend, with a reasonable expectation of success. The motivation for doing so incorporate user expertise to fine-tune the input prompt [Townsend, par. 69].
Referring to claim 2, Sampath discloses The device of claim 1, wherein the operations further comprise: generating embeddings from the sample input format specification and the output format specification; and creating the tag from the embeddings [pars. 55-58; note implementation details related to embeddings].
Referring to claim 3, Sampath discloses The device of claim 1, wherein the prompt provides few-shot training of the large language model [par. 62; the input prompt may be a few-shot prompt that includes multiple examples].
Referring to claim 4, Townsend discloses The device of claim 1, wherein the tag is provided through the user interface [fig. 3C; par. 69; note the providing of the prompts by the user].
Referring to claim 5, Sampath discloses The device of claim 1, wherein the operations further comprise generating embeddings for the tag, the updated data and the response and including the embeddings in the context [pars. 55-58; note implementation details related to embeddings].
Referring to claim 6, Townsend discloses The device of claim 1, wherein the operations further comprise comparing the output format specification provided through the user interface with an output format in the response to verify that the response is satisfactory [pars. 61 and 69; performance metrics are generated by comparing results provided by the LLM with a set of initial ground truth data created by the user until the user is satisfied with the performance metrics].
Referring to claim 7, Sampath discloses The device of claim 1, wherein the processing system comprises a plurality of processors operating in a distributed computing environment [par. 61; note the distributed arrangement].
Referring to claim 8, see at least the rejection for claim 1. Sampath further discloses A non-transitory, machine-readable medium, comprising executable instructions that, when executed by a processing system including a processor, facilitate performance of operations, the operations comprising the claimed steps [fig. 2, computing system 400, processor 402, and memory 402].
Referring to claim 9, see the rejection for claim 2.
Referring to claim 10, see the rejection for claim 3.
Referring to claim 11, see the rejection for claim 4.
Referring to claim 12, see the rejection for claim 5.
Referring to claim 13, see the rejection for claim 6.
Referring to claim 14, see the rejection for claim 7.
Referring to claim 15, see the rejection for claim 1, which incorporates the claimed method.
Referring to claim 16, see the rejection for claim 2.
Referring to claim 17, see the rejection for claim 3.
Referring to claim 18, see the rejection for claim 4.
Referring to claim 19, see the rejection for claim 5.
Referring to claim 20, see the rejection for claim 6.
Conclusion
The following prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Marwah et al. (US Pub. 20250007790) discloses in-context learning in an LLM in response to a received prompt.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to GRACE PARK whose telephone number is (571)270-7727. The examiner can normally be reached M-F 8AM-5PM.
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, TAMARA KYLE can be reached at (571)272-4241. 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.
/Grace Park/Primary Examiner, Art Unit 2144
Prosecution Insights