-
公开(公告)号：US20230066143A1
公开(公告)日：2023-03-02
申请号：US17464534
申请日：2021-09-01
Applicant: Oracle International Corporation
Inventor： Liviu Sebastian Matei , Filip Trojan , Marc Michiel Bron , Andrew Kenneth Hind , Yingzhao Zhou , Maria-Monica Petrica , Rajesh Ashwinbhai Shah
Abstract: A document may be received as part of a request to identify similar documents in a collection of documents. However, the received document and the documents in the collection may have different schemas or formats. To provide semantic context to the search and allow similarity scores to be generated between different document types, a configuration may be accessed that defines how to generate queries from one schema into another schema. The configuration may map queries between different fields in both schemas. Results of the multiple queries can be combined to generate a weighted combination for each document that can be used as a similarity score between different document types.
-
公开(公告)号：US20220366298A1
公开(公告)日：2022-11-17
申请号：US17320534
申请日：2021-05-14
Applicant: Oracle International Corporation
Inventor： Alberto Polleri , Lukás Drápal , Filip Trojan , Karel Vaculik
Abstract: Techniques are disclosed for revising training data used for training a machine learning model to exclude categories that are associated with an insufficient number of data items in the training data set. The system then merges any data items associated with a removed category into a parent category in a hierarchy of classifications. The revised training data set, which includes the recategorized data items and lacks the removed categories, is then used to train a machine learning model in a way that avoids recognizing the removed categories.
-
公开(公告)号：US12265561B2
公开(公告)日：2025-04-01
申请号：US17898173
申请日：2022-08-29
Applicant: Oracle International Corporation
Inventor： Liviu-Sebastian Matei , Filip Trojan
IPC: G06F16/33 , G06F16/332 , G06F16/334
Abstract: A document repository may be searched for documents that are similar to a source document. Multiple queries may be generated based on a type of the source document, and the results may be combined in a unified response. User behavior may then be monitored, and implicit and explicit feedback may be gathered to evaluate the performance of the search. The gathered feedback may indicate how relevant each of the result documents are in comparison to the original source document. This feedback may then be used to adjust search parameters for the source document type, such that the performance of subsequent searches may be improved. A model may also be trained to classify implicit feedback using explicit feedback received from users.
-
公开(公告)号：US20230068342A1
公开(公告)日：2023-03-02
申请号：US17898173
申请日：2022-08-29
Applicant: Oracle International Corporation
Inventor： Liviu-Sebastian Matei , Filip Trojan
IPC: G06F16/332 , G06F16/33
Abstract: A document repository may be searched for documents that are similar to a source document. Multiple queries may be generated based on a type of the source document, and the results may be combined in a unified response. User behavior may then be monitored, and implicit and explicit feedback may be gathered to evaluate the performance of the search. The gathered feedback may indicate how relevant each of the result documents are in comparison to the original source document. This feedback may then be used to adjust search parameters for the source document type, such that the performance of subsequent searches may be improved. A model may also be trained to classify implicit feedback using explicit feedback received from users.
-
-
-
Search Results
4
records
(took 0.016 seconds)
