公开(公告)号：US20250139447A1

公开(公告)日：2025-05-01

申请号：US18496496

申请日：2023-10-27

Applicant: Intuit, Inc.

Inventor： Sudhir AGARWAL ,  Esmé MANANDISE ,  Anu SREEPATHY

IPC: G06N3/09 ,  G06F9/54

Abstract: Certain aspects of the disclosure provide techniques for prompt processing. A method generally includes generating a representation of a prompt using a large language model (LLM), the representation comprising semantic features of the prompt, wherein the prompt requests a state change from an initial state to a desired goal state; generating a task description based on using the representation and a domain description; generating an execution plan for the task description, the execution plan comprising a sequence of steps used to transform the initial state to the desired goal state; executing the sequence of steps; and generating a natural language response to the prompt after completing the execution of the sequence of steps, wherein the natural language response is based on the information obtained or the desired goal state.

公开(公告)号：US20220012663A1

公开(公告)日：2022-01-13

申请号：US16922187

申请日：2020-07-07

Applicant: INTUIT INC.

Inventor： Sudhir AGARWAL ,  Roland Allen SANFORD, II

IPC: G06Q10/06 ,  G06Q30/00 ,  G06Q10/04 ,  G06N5/04

Abstract: Certain aspects of the present disclosure provide techniques for hierarchical optimization including: receiving a request to optimize a primary objective; determining a set of stages to optimize the primary objective; for each respective stage of the set of stages: determining an objective function; when the respective stage is the first stage to be processed: determining values of a set of variable inputs to the respective stage and an output of the objective function; when the respective stage is not the first stage: updating a set of fixed inputs to the respective stage by including the variable inputs to one or more previously processed stages and their corresponding values to the set of fixed inputs to the respective stage; determining values of the set of variable inputs to the respective stage and output of the objective function for the respective stage; providing a final output for display on a display device.

公开(公告)号：US20250165726A1

公开(公告)日：2025-05-22

申请号：US18954409

申请日：2024-11-20

Applicant: Intuit Inc.

Inventor： Anu SREEPATHY ,  Sudhir AGARWAL

IPC: G06F40/49 ,  G06F40/35

Abstract: Certain aspects of the disclosure provide techniques for translating a user request (e.g., posed in natural language) into a structured input using intermediate representations, to resolve the user request as a planning problem. A method generally includes generating a first intermediate representation of a first user request using a large language model (LLM), wherein the first intermediate representation comprises one or more first facts and/or one or more rules in a declarative language; generating a first materialized representation of the first user request based on the first intermediate representation and a domain description using a logic reasoner, wherein the first materialized representation comprises one or more second facts in the declarative language, and wherein the one or more second facts comprise a subset of the one or more first facts and one or more inferred facts; and generating a task description based on the first materialized representation.

公开(公告)号：US20250139367A1

公开(公告)日：2025-05-01

申请号：US18495641

申请日：2023-10-26

Applicant: Intuit, Inc.

Inventor： Esmé MANANDISE ,  Anu SREEPATHY ,  Sudhir AGARWAL

IPC: G06F40/284 ,  G06F40/211 ,  G06F40/226

Abstract: Certain aspects of the disclosure provide techniques for translating a prompt into a structured input to resolve the natural langue query as a planning problem. A method generally includes identifying and classifying tokens in a prompt using a large language model (LLM); extracting from a domain description in a planning domain definition language (PDDL): object types used to categorize objects; and predicates identifying relationships between the objects that may be true or false; categorizing at least one token in the prompt as one or more of the objects, one or more of the object types, or one or more of the predicates based on the classification of the at least one token determined by the LLM; and generating a task description in the PDDL based on the categorization, the task description comprising a translation of the prompt into a structured input for a planner.