-
公开(公告)号：US11922333B2
公开(公告)日：2024-03-05
申请号：US17744847
申请日：2022-05-16
Inventor： Sungbum Park , Suehyun Chang , Geun Jin Ahn
Abstract: A search method using an artificial intelligence based information retrieval model and a method for training the artificial intelligence based information retrieval model used for the method are provided.
In the method, even if there is no labeled data and only a corpus exists, the artificial intelligence based information retrieval model can be trained using the weak-supervision methodology. Search can be performed by dividing documents into passages having short lengths. Compared to an information retrieval model based on unsupervised learning, improved search results are provided.-
2.发明申请公开(公告)号：US20250021594A1
公开(公告)日：2025-01-16
申请号：US18901236
申请日：2024-09-30
Inventor： Sung-Bum PARK , Suehyun CHANG
IPC: G06F16/383 , G06F16/338
Abstract: A method is presented for enhancing search results by segmenting documents into smaller passages and utilizing those passages as the search unit. This method integrates the passage rankings from two search models to produce a new document ranking and arranges the documents accordingly. The ranking of document is also rearranged based on the proportion of passages taken from the same document versus the total number of passages in that document. The final search ranking system combines document-level and passage-level search rankings to rank documents. This method ensures that when conducting a passage search, the search results consider the general relevance of the entire document, which leads to better performance compared to searching only by document-level or passage-level searches.
-
3.发明申请公开(公告)号：US20250021593A1
公开(公告)日：2025-01-16
申请号：US18901220
申请日：2024-09-30
Inventor： Sung-Bum PARK , Suehyun CHANG
IPC: G06F16/383 , G06F16/338
Abstract: A method is presented for enhancing search results by segmenting documents into smaller passages and utilizing those passages as the search unit. This method integrates the passage rankings from two search models to produce a new document ranking and arranges the documents accordingly. The ranking of document is also rearranged based on the proportion of passages taken from the same document versus the total number of passages in that document. The final search ranking system combines document-level and passage-level search rankings to rank documents. This method ensures that when conducting a passage search, the search results consider the general relevance of the entire document, which leads to better performance compared to searching only by document-level or passage-level searches.
-
4.发明公开公开(公告)号：US20240168988A1
公开(公告)日：2024-05-23
申请号：US18527499
申请日：2023-12-04
Inventor： Sung-Bum PARK , Suehyun CHANG
IPC: G06F16/383 , G06F16/338
CPC classification number: G06F16/383 , G06F16/338
Abstract: A method is presented for enhancing search results by segmenting documents into smaller passages and utilizing those passages as the search unit. This method integrates the passage rankings from two search models to produce a new document ranking and arranges the documents accordingly. The ranking of document is also rearranged based on the proportion of passages taken from the same document versus the total number of passages in that document. The final search ranking system combines document-level and passage-level search rankings to rank documents.
This method ensures that when conducting a passage search, the search results consider the general relevance of the entire document, which leads to better performance compared to searching only by document-level or passage-level searches.
-
-
-
Search Results
4
records
(took 0.01 seconds)
