Deep reinforcement learning-based multi-step question answering systems
US11573991B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Nov 26, 2019 |
| Grant date | Feb 7, 2023 |
| Priority date | — |
| Expiry date | Jun 21, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V20/10
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method includes receiving a user query and performing, using at least one processor, multiple rounds of an answer generation process. Each round of the answer generation process includes selecting one of multiple functions to be performed based on an input state. The input state for each round includes an embedding of the user query in a feature space. The input state for at least one round also includes an embedding of information to be used to identify an answer to the user query in the feature space. Each round of the answer generation process also includes performing the selected function. The multiple functions include (i) an answer generation function that produces the answer to the user query and (ii) at least one additional function that updates the input state for a current round for use during a subsequent round. In addition, the method includes providing the answer to the user.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.