-
公开(公告)号：US20250086448A1
公开(公告)日：2025-03-13
申请号：US18367020
申请日：2023-09-12
Applicant: Adobe Inc.
Inventor： Tanay ANAND , Siddarth RAMESH , Shripad Vilasrao DESHMUKH , Jayakumar SUBRAMANIAN
IPC: G06N3/08 , G06N3/0475
Abstract: Systems and methods provide a generative recommendation model that leverages verbalizations generated from sequential data. In accordance with some aspects, sequential data for a trajectory comprising a plurality of steps is accessed, in which the sequential data comprises a tuple for each step of the trajectory. Verbalized sequential data is generated from the sequential data, in which the verbalized sequential data for each step of the trajectory comprises one or more natural language sentences generated from the tuple for the step. A generative model is trained on the verbalized sequential data to provide a trained generative model that generates a recommended action given a prompt specifying a current state.
-
公开(公告)号：US20250124620A1
公开(公告)日：2025-04-17
申请号：US18380059
申请日：2023-10-13
Applicant: Adobe Inc.
Inventor： Tarun ARORA , Tanay ANAND , Siddarth RAMESH , Shripad DESHMUKH , Pranjal PRASOON , Piyush DEWNANI , Md anis ALAM , Jayakumar SUBRAMANIAN , Gaurav SATIJA , Diwakar Reddy YERRAGUNTA , Deepthi AMIRTHAGADESWARAN , Balaji KRISHNAMURTHY , Avinash KATIYAR
Abstract: Various disclosed embodiments are directed to deriving, via a language model, a summary of data by converting or encoding table data into one or more natural language sentences, which are then used as input to the language model for generating the summary. One or more embodiments are additionally or alternatively directed to deriving, via a language model, a response to a user question or command via a chat interface by providing the language model with the generated summary as input. In this way, for example, the language model can use the summary as a prompt or other target context for providing a response.
