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 with respect to the 35 U.S.C. 112 rejections are persuasive. Applicant’s amendments have overcome the issues raised under 35 U.S.C. 112. Accordingly, the 35 U.S.C. 112 rejections are withdrawn.
Applicant’s arguments with respect to the prior art rejections have been fully considered, but they are not persuasive.
Applicant argues that Miller does not disclose analyzing a model response to determine missing information and generating an additional prompt that includes the missing information as part of an iterative prompt-enrichment loop for the same plan-generation instance.
However, Miller discloses acquiring new skills during the plan generation instance. For example, Miller discloses “the planning stage can be guided by feedback from users or other AI components or systems” (paragraph [0053]). Thus, when the planner encounters a scenario where a complete solution plan cannot be realized (paragraph [0066]), the user “may provide an ad hoc explanation to guide the AI in developing a skill” by “list[ing] basic steps to complete the task” (paragraph [0067]). Additionally, Miller discloses a step of determining whether the user accepts the proposed solution plan, where the user may send additional prompts to “refine, update or replace the user prompt, goal and/or solution plan” (paragraph [0092]).
Thus, Miller clearly anticipates generating additional prompts that include missing information as part of an iterative prompt-enrichment loop for the same plan-generation instance. The prior art rejections are therefore maintained.
Claim Rejections - 35 USC § 102
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) 1-2, 4-17 and 19-20 is/are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Miller et al. (U.S. Patent Application Pub. No. 2024/0289545, hereinafter “Miller”).
In regard to claim 1, Miller discloses one or more non-transitory computer-readable media storing computer-executable instructions (paragraph [0164]) that upon execution cause one or more processors to perform acts comprising:
receiving a text-based request to perform a knowledge worker task for an organization from a computing device (Fig. 4B, step 410B; a text-based user prompt requesting help in performing a task is received, paragraph [0087]; where the plan is applied for organizations in various domains, paragraphs [0109-0110]);
retrieving at least contextual data that are relevant to the text-based request from a knowledge base (Fig. 5A, step 520, registered functions that correspond to the skills and resources for a particular domain are identified; paragraph [0113]; and relevant functions for plan creation are identified, Fig. 5B, step 531, paragraph [0118]);
generating a text-based prompt that at least includes text information included in the text-based request and the contextual data that are relevant to the text-based request (Fig. 5A, step 530 and Fig. 5B, step 533, plan prompts including the user prompt and list of registered functions are used to build plan prompts for an LLM, paragraphs [0114] and [0120]); and
sending the text-based prompt to a language model (LM) to prompt the LM to generate a new plan of action for performing the knowledge worker task (Fig. 5A, step 540, the plan prompts are sent to the LLM to identify a solution plan for the goal, paragraph [0115]);
determining whether a response from the LM indicates that the LM is able to process the text-based prompt into the new plan of action (the planner determines a solution plan cannot be realized, paragraph [0066]);
executing the new plan of action to perform the knowledge worker task for the organization when the LM is able to process the text-based prompt into the new plan of action (if the plan can be realized, it is executed, paragraph [0093]); and when the LM is unable to process the text-based prompt into the new plan of action:
analyzing the response from the LM to determine additional information that is to be obtained from at least one of a human user or the knowledge base in order for the LM to process the text-based prompt into the new plan of action (a prompt asking the user to learn a new skill is generated, paragraph [0067]);
obtaining the additional information from at least one of a corresponding computing device of the human user or the knowledge base (the user provides an ad hoc explanation on how to accomplish the task, paragraph [0067]; the feedback guiding the planner while generating the plan, paragraphs [0053] and [0092]); and
generating an additional text-based prompt that includes the additional information to prompt the LM to generate the new plan of action (additional prompts are generated to refine, update or replace the solution plan, paragraph [0092]).
In regard to claim 2, Miller discloses the retrieving includes further retrieving one or more existing plans of action that are relevant to the text-based request from the knowledge base, and wherein the generating includes generating the text-based prompt that includes the text information included in the text-based request, the one or more existing plans of action that are relevant to the text-based request, and the contextual data that are relevant to the text-based request (plans that are semantically similar to previously executed plans are reused and provided to the LLM when generating a new plan, paragraphs [0065] and [0088-0089]).
In regard to claim 4, Miller discloses the contextual data that is relevant to the text-based request includes plan formatting instructions for formatting the one or more existing plans of action or one or more subcomponents of the one or more existing plans of action into the next plan of action (additional prompts guide the selection of plan components, including information regarding stylistic choices, paragraphs [0087] and [0089]).
In regard to claim 5, Miller discloses the text- based request is inputted by a human user at the computing device or automatically generated based on a detection of a condition (see Fig. 1, the user 102 provides an initial prompt via computing device 110, paragraphs [0040-0042]).
In regard to claim 6, Miller disclose when the LM is unable to process the text-based prompt into the new plan of action, the additional text-based prompt further includes the text information included in the text- based request and the contextual data that are relevant to the text-based request (the updated prompt refines the original prompt an includes API calls and/or relevant functions, paragraph [0092]).
In regard to claim 7, Miller discloses the acts further comprise, when the LM is unable to process the text-based prompt into the new plan of action (when a complete solution plan cannot be realized, paragraph [0066]):
analyzing the response from the LM to determine additional information that is to be obtained from a user in order for the LM to process the text-based prompt into the new plan of action (in response, a prompt to the user asking to learn a new skill is generated, paragraph [0067]);
obtaining the additional information from a corresponding computing device of the human user (the user provides information on how to complete a task, paragraph [0067]); and
generating an additional text-based prompt that includes the additional information to prompt the LM to generate the new plan of action (the additional information is saved so that the plan creation component can leverage the skill in the future, paragraph [0067]).
In regard to claim 8, Miller discloses the additional information is provided to the computing device by the human user (the user provides information on how to complete a task, paragraph [0067]).
In regard to claim 10, Miller discloses the contextual data includes at least one of a positive example that comprises a first previous plan of action that successfully fulfilled a first previous text-based request, and a negative example that comprises a second previous plan of action that unsuccessfully fulfilled a second previous text- based request (positive and negative examples of previous plans are used when a semantically similar request is received, paragraph [0065]).
In regard to claim 11, Miller discloses the plan of action includes a plurality of programmatic objects (executable code, paragraph [0038]).
In regard to claim 12, Miller discloses the text- based request or the plan of action includes text in at least one of a natural language form or machine language form (a natural language string, paragraph [0087]).
In regard to claim 13, Miller discloses a computer-implemented method, comprising:
receiving a text-based request to perform a knowledge worker task for an organization from a computing device (Fig. 4B, step 410B; a text-based user prompt requesting help in performing a task is received, paragraph [0087]; where the plan is applied for organizations in various domains, paragraphs [0109-0110]);
retrieving one or more existing plans of action and contextual data that are relevant to the text-based request from a knowledge base (Fig. 5A, step 520, registered functions that correspond to the skills and resources for a particular domain are identified; paragraph [0113]; and relevant functions for plan creation are identified, Fig. 5B, step 531, paragraph [0118]; additionally, plans that are semantically similar to previously executed plans are reused and provided to the LLM when generating a new plan, paragraphs [0065] and [0088-0089]);
generating a text-based prompt that at least includes text information included in the text-based request, the one or more existing plans of action that are relevant to the text-based request, and the contextual data that are relevant to the text-based request (Fig. 5A, step 530 and Fig. 5B, step 533, plan prompts including the user prompt and list of registered functions are used to build plan prompts for an LLM, paragraphs [0114] and [0120]); and
sending the text-based prompt to a language model (LM) to prompt the LM to generate a new plan of action for performing the knowledge worker task (Fig. 5A, step 540, the plan prompts are sent to the LLM to identify a solution plan for the goal, paragraph [0115]);
determining whether a response from the LM indicates that the LM is able to process the text-based prompt into the new plan of action (the planner determines a solution plan cannot be realized, paragraph [0066]);
executing the new plan of action to perform the knowledge worker task for the organization when the LM is able to process the text-based prompt into the new plan of action (if the plan can be realized, it is executed, paragraph [0093]); and when the LM is unable to process the text-based prompt into the new plan of action:
analyzing the response from the LM to determine additional information that is to be obtained from at least one of a human user or the knowledge base in order for the LM to process the text-based prompt into the new plan of action (a prompt asking the user to learn a new skill is generated, paragraph [0067]);
obtaining the additional information from at least one of a corresponding computing device of the human user or the knowledge base (the user provides an ad hoc explanation on how to accomplish the task, paragraph [0067]; the feedback guiding the planner while generating the plan, paragraphs [0053] and [0092]); and
generating an additional text-based prompt that includes the additional information to prompt the LM to generate the new plan of action (additional prompts are generated to refine, update or replace the solution plan, paragraph [0092]).
In regard to claim 14, Miller discloses when the LM is unable to process the text-based prompt into the new plan of action, the additional text-based prompt further includes the text information included in the text- based request, the one or more existing plans of action that are relevant to the text-based request, and the contextual data that are relevant to the text-based request (the updated prompt refines the original prompt an includes API calls and/or relevant functions, paragraph [0092]).
In regard to claim 15, Miller discloses the acts further comprise, when the LM is unable to process the text-based prompt into the new plan of action (when a complete solution plan cannot be realized, paragraph [0066]):
analyzing the response from the LM to determine additional information that is to be obtained from a user in order for the LM to process the text-based prompt into the new plan of action (in response, a prompt to the user asking to learn a new skill is generated, paragraph [0067]);
obtaining the additional information from a corresponding computing device of the human user (the user provides information on how to complete a task, paragraph [0067]); and
generating an additional text-based prompt that includes the additional information to prompt the LM to generate the new plan of action (the additional information is saved so that the plan creation component can leverage the skill in the future, paragraph [0067]).
In regard to claim 17, Miller discloses the contextual data includes at least one of a positive example that comprises a first previous plan of action that successfully fulfilled a first previous text-based request, and a negative example that comprises a second previous plan of action that unsuccessfully fulfilled a second previous text- based request (positive and negative examples of previous plans are used when a semantically similar request is received, paragraph [0065]).
In regard to claim 19, Miller discloses the contextual data that is relevant to the text-based request includes plan formatting instructions for formatting the one or more existing plans of action or one or more subcomponents of the one or more existing plans of action into the next plan of action (additional prompts guide the selection of plan components, including information regarding stylistic choices, paragraphs [0087] and [0089]).
In regard to claim 20, Miller discloses a system (Fig. 7, 700), comprising:
one or more processors (processing units 702); and
memory including a plurality of computer-executable components that are executable by the one or more processors to perform a plurality of actions (memory 704), the plurality of actions comprising:
receiving a text-based request to perform a knowledge worker task for an organization from a computing device (Fig. 4B, step 410B; a text-based user prompt requesting help in performing a task is received, paragraph [0087]; where the plan is applied for organizations in various domains, paragraphs [0109-0110]);
retrieving one or more existing plans of action that are relevant to the text-based request from a knowledge base (plans that are semantically similar to previously executed plans are reused and provided to the LLM when generating a new plan, paragraphs [0065] and [0088-0089]).
generating a text-based prompt that at least includes text information included in the text-based request, the one or more existing plans of action that are relevant to the text-based request, and the contextual data that are relevant to the text-based request (Fig. 5A, step 530 and Fig. 5B, step 533, plan prompts including the user prompt, prior plans, and list of registered functions are used to build plan prompts for an LLM, paragraphs [0114] and [0120]); and
sending the text-based prompt to a language model (LM) to prompt the LM to generate a new plan of action for performing the knowledge worker task (Fig. 5A, step 540, the plan prompts are sent to the LLM to identify a solution plan for the goal, paragraph [0115]).
determining whether a response from the LM indicates that the LM is able to process the text-based prompt into the new plan of action (the planner determines a solution plan cannot be realized, paragraph [0066]);
executing the new plan of action to perform the knowledge worker task for the organization when the LM is able to process the text-based prompt into the new plan of action (if the plan can be realized, it is executed, paragraph [0093]); and when the LM is unable to process the text-based prompt into the new plan of action:
analyzing the response from the LM to determine additional information that is to be obtained from at least one of a human user or the knowledge base in order for the LM to process the text-based prompt into the new plan of action (a prompt asking the user to learn a new skill is generated, paragraph [0067]);
obtaining the additional information from at least one of a corresponding computing device of the human user or the knowledge base (the user provides an ad hoc explanation on how to accomplish the task, paragraph [0067]; the feedback guiding the planner while generating the plan, paragraphs [0053] and [0092]); and
generating an additional text-based prompt that includes the additional information to prompt the LM to generate the new plan of action (additional prompts are generated to refine, update or replace the solution plan, paragraph [0092]).
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.
Claim(s) 3 and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Miller, in view of Basson et al. (U.S. Patent Application Pub. No. 2016/0162538, hereinafter “Basson”).
In regard to claims 3 and 18, Miller discloses the retrieving includes determining that the text-based request matches elements within a specific organizational domain (paragraphs [0109-0110]), and wherein the retrieving includes retrieving the one or more existing plan from the knowledge base when the one or more existing plans of actions matches the elements (prior plans utilized for semantically related prior plans, paragraphs [0065] and [0088-0089]).
However, Miller does not expressly disclose matching a node of one or more nodes in a classification hierarchy of the organization.
Basson discloses a classification hierarchy for an organization (business) comprising a plurality of domain nodes (see Fig. 1, domain hierarchy 100, comprising nodes 110-130), wherein a text-based request (query) is matched with a node of one or more nodes in a classification hierarchy of the organization (query terms are matched to one or more existing business plans stored in models for the various nodes of the hierarchy, paragraphs [0039-0040] and [0052-0053]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to retrieve the one or more existing plans of action by determining that the text-based request matched a node of one or more nodes in a classification hierarchy of the organization, because it would allow a domain specific plan to be retrieved while requiring little to no information about the domain specific element of the organization, as suggested by Basson (paragraph [0012]).
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 BRIAN LOUIS ALBERTALLI whose telephone number is (571)272-7616. The examiner can normally be reached M-F 8AM-3PM, 4PM-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, Bhavesh Mehta can be reached at 571-272-7453. 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.
BLA 5/1/26
/BRIAN L ALBERTALLI/Primary Examiner, Art Unit 2656
Prosecution Insights