AUTOMATICALLY GENERATING EXECUTION SEQUENCES FOR WORKFLOWS

Patent №

US 9,952,899

Granted

2018-04-24

Filed 2014

Owner

GOOGLE INC.

AI components

5

ml · nlp · kr · planning · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

14511027

The present disclosure relates to automatically generating execution sequences from workflow definitions. One example method includes receiving a workflow definition including a plurality of operations, each of the plurality of operations including input attributes each associated with an input value and output attributes each associated with an output value; determining an execution sequence for the workflow defining relationships between the plurality of operations, the determining based at least in part on the one or more input attributes and associated input values, and the output attributes and associated output values for each operation, and at least in part on one or more semantic rules defining dependencies of each of the plurality of operations; and generating a directed acyclic graph representing the execution sequence including nodes each representing an operation from the plurality of operations, and vertices each representing a relationship between the plurality of operations defined by the execution sequence.

AI classification

Planning1.00
Knowledge representation1.00
AI hardware0.99
Natural language0.87
Machine learning0.53
Evolutionary computation0.03
Vision0.01
Speech0.00

Ownership

GOOGLE INC.

assignment · 340640623

Assignors

NOVAES, MARCOS

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC