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 .
Response to Arguments
Applicant's arguments filed 4/28/2026 have been fully considered but they are not persuasive.
The applicant contends Anthony et al does not disclose the recited limitation “the categorical question including given categories and decoy categories”.
The examiner disagrees. The recited limitation merely indicates the categorical question includes information such as given categories and decoy categories, but does not specify how such information is included. For example, are all decoy categories listed in the categorical question or merely a general term inclusively addressing all decoy categories such as unknown? By definition, the term “include” is defined as “to take in or comprise as a part of a whole or group”. This indicates any method or manner in which both given categories and decoy categories are included in the categorical question is sufficient to meet the recited limitations. Due to the breath of the recited limitation, the limitation is interpreted as merely an overall addressment of any category that is not indicated as a given category would indicate inclusion of decoy categories. Anthony et al discloses such one method where the first prompt (categorical question) includes given categories (acceptable response to acceptable categories) and a general or fallback response to any category not indicated as a given category such as “an answer to the prompt is unknown”.
Paragraph 56 discloses “The first prompt may include acceptable responses such as acceptable categories of model types, product types, power capability, etc. …. The first prompt may include a required response. For example, the first response may indicate a required response to surface if an answer to the prompt is unknown (e.g., “I'm sorry, I'm unable to answer your query,” etc.).”
The highlighted portions of the paragraph are emphasized. The paragraph discloses the first prompt may include acceptable response for acceptable categories. When the category is unknown, specifically “if answer to the prompt is unknown”, the first prompt includes a required response (see highlights). This indicates decoy categories are categories that where the response or answer to the prompt is unknown such as answers or responses not within the acceptable categories or any response that is considered unknown or within categories not matching the listed categories as acceptable. By including a response for when the answer or response to the prompt is unknown, the decoy categories are included in the categorical question.
Note: The applicant’s remarks includes “Anthony’s approach of instructing the LLM to respond “Unknown” when categorization fails is fundamentally different from presenting decoy categories as selectable options within the prompt.” The recited limitation merely recites inclusion of given and decoy categories, but does not require the manner in which to include such categories is “presenting decoy categories as selectable options within the prompt.” As indicated above, there is more than 1 way in which decoy categories and given categories are included in the categorical question. Due to the breath of the claimed language, Anthony et al discloses one such method or manner. Please see the response above.
The applicant contends the dependent claims are therefore allowable for the same reason as their respective independent claims.
The examiner disagrees. Please see the rebuttal to the independent claims above and office action below.
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.
Claim(s) 1-5,8-14,17-19 is/are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Anthony et al (US Publication No.: 20250005224).
Claim 1, Anthony et al discloses
A processor configured to execute a software application (Fig. 10, label 1002 as the processor or processing system, label 1004 as software application. Fig. 1, label 107 as the software application. Paragraph 101) to:
Populate a large language model (LLM) prompt template (Fig. 2, label 203 populates a prompt template or generates a prompt for an LLM, label 205. Fig. 5, label 503,505 shows examples of prompt (filled prompt template).) yielding a populated LLM prompt including a categorical question for an LLM to perform a categorization task (Fig. 5, label 503 includes the user request or query (categorical question for LLM to perform categorization task) of categorizing the type of model that the user is attempting to build.), the categorical question including given categories and decoy categories (Fig. 5, label 503 includes given categorizes such as fan, conveyor, pump, etc. and decoy categories are any categories not listed in the given categories, which results in a required response indicating the category is unknown. (paragraph 67,56) Paragraph 69 discloses an invalid response is when the response does not include an acceptable model type category, which indicates decoy categories are categories that are not found in the acceptable model type categories or given categories.);
Provide the populated LLM prompt as input to the LLM (fig. 5, label 103,503, Fig. 2, label 205);
Receive a text response (Fig. 5, label response, Fig. 2, label 225. Paragraph 68 discloses a response is generated by the LLM may include the requested category and/or a required response.) from the LLM based on processing the populated LLM prompt as input (Fig. 2, label 225 is output by label LLM as a result of processing the prompt, label 223. Fig. 5, label 503 as the prompt, 103 as the LLM or model, response as the output from the LLM resulting from processing the prompt.), the text response of the LLM including a categorical answer indicating one of the given categories or one of the decoy categories (Paragraph 68 discloses a response generated by the LLM resulting from processing 503 includes category and/or a required response (decoy category). An example is shown in Fig. 5, label 507.); and
A memory to store data used by the processor (Fig. 10, label 1005,1003,1002).
Claim 2, Anthony et al discloses
Perform a category-specific operation based on any one of the given categories being selected by the LLM (Fig. 6 shows the continuation of LLM processing with prompt generation, wherein a category-specific operation is generation of a model, label 603,605,607, specific to the category as determined from process the prompt 503. The category specific operation is generation of a model in the category and summarization of the generated model.); and
Not perform a category-specific operation based on any one of the decoy categories being selected by the LLM (Paragraph 50 discloses when the response to prompt 503 or first prompt is unknown, label 225, and the response is determined as invalid, then an input 229 is generated to include an answer of “unknown”. Paragraph 70 discloses a response to label 503 and/or 505 is transmitted to application 107, where 107 displays the response such as personalized message including the response to prompt 503 and/or 505. This indicates a category specific operation such as generating a model in a category as shown in Fig. 6 is not be performed.).
Claim 3, Anthony et al discloses inclusion of the decoy categories in the populated LLM prompt causes the LLM to avoid spuriously selecting one of the given categories (Such limitation is an intended result of including decoy categories in the prompt. Paragraph 56,67 discloses the prompt includes decoy categories of any categories that would result in unknown with required message. Paragraph 69 discloses an invalid response is when the response does not include an acceptable model type category, which indicates decoy categories are categories that are not found in the acceptable model type categories or given categories, which is indicated in the prompt model.).
Claim 4, Anthony et al discloses
The given categories are categories that are supported by the software application (Paragraph 67 discloses the prompt include acceptable categories or given categories that are supported by the software application to generate a model as shown in Fig. 6. Fig. 1, label 107 as the software application.); and
The decoy categories are categories that are unsupported by the software application (Paragraph 67 discloses the prompt includes a required response when categorization is not found as one of the acceptable categories (paragraph 69 indicates valid response is when the LLM can categorize the request into an acceptable category, which indicates any categories not listed as acceptable is considered a decoy category. When the LLM outputs the required response, this indicates the category is unknown or decoy category is selected and subsequent actions to generate a response to a user request would not be supported by the software application such as generating a model according to the category as determined by the LLM (Fig. 6).).
Claim 5, Anthony et al discloses the software application is configured to respond indicating that a request is unsupported based on any one of the decoy categories being included in the text response of the LLM (Paragraph 56 discloses a required response can be asking the user for additional information for the unknown category, indicating the request or input to the prompt generator in Fig. 2, label 203 is unsupported based on any one of the decoy categories being included in the text response, Fig. 2, output from label 205.).
Claim 8, Anthony et al discloses the given categories are supported Application Programming Interfaces (APIs) (Fig. 2, label 205, Fig. 6 shows actions supported by APIs in order to generate following actions as a result of given categories listed as categories in the prompt shown in Fig. 5, label 503); and the decoy categories (Paragraphs 56,67,69 discloses categories that are supported, which are listed in the prompt. Any categories not listed in the prompt are unsupported or decoy categories.) are unsupported APIs (Paragraph 56 discloses when the LLM shown in Fig. 2 outputs a required response indicating the category is unknown, a request for additional information can be issued via the user interface shown in Fig. 2, label 213 which indicates unknown categories are not supported by APIs.).
Claim 9, Anthony et al discloses the categorical answer (Fig. 5, label response 505,507) indicates one of the given categories of a given API of the supported APIs (Fig. 5, label 507 indicates one of the given categories of a given API of the supported APIs (data model generation with LLM and prompt correlation shown in Fig. 6).); and the software application is configured to call the given API (Fig. 6, label 603 as the prompt issued to the LLM to generate a data model with response at label 607.).
Claim 10 recites similar limitations as recited in claim 1 and is rejected on the same grounds as claim 1.
Claim 11 recites similar limitations as recited in claim 2 and is rejected on the same grounds as claim 2.
Claim 12 recites similar limitations as recited in claim 3 and is rejected on the same grounds as claim 3.
Claim 13 recites similar limitations as recited in claim 4 and is rejected on the same grounds as claim 4.
Claim 14 recites similar limitations as recited in claim 5 and is rejected on the same grounds as claim 5.
Claim 17 recites similar limitations as recited in claim 8 and is rejected on the same grounds as claim 8.
Claim 18 recites similar limitations as recited in claim 9 and is rejected on the same grounds as claim 9.
Claim 19 recites similar limitations as recited in claim 1 and is rejected on the same grounds as claim 1.
Allowable Subject Matter
Claims 6-7,15-16 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
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 LINDA WONG whose telephone number is (571)272-6044. The examiner can normally be reached 9-5.
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 C Flanders can be reached at 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. 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.
/LINDA WONG/Primary Examiner, Art Unit 2655
Prosecution Insights