中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

7 records (took 0.014 seconds)

    Aggregating results from named entity recognition services
    1.
    发明授权
    Aggregating results from named entity recognition services 有权

    公开(公告)号：US10762117B2

    公开(公告)日：2020-09-01

    申请号：US15635098

    申请日：2017-06-27

    Applicant: SAP SE

    Inventor： Katja Pfeifer ,  Johannes Meinecke

    IPC: G06F16/33 ,  G06F16/338 ,  G06F40/295

    Abstract: An aggregation service aggregates extraction results from diverse named entity recognition (“NER”) services, which can help improve the quality of extracted information. In some cases, the aggregation service considers differences in entity type classifications when aggregating extraction results from different NER services. The aggregation service can also consider performance characteristics (e.g., error rates) for the different NER services. For example, the aggregation service receives extraction results generated for a document corpus according to an entity type schema for each of multiple different NER services, then aggregates the extraction results based at least in part on relations between entity types for the NER services. For a given annotation area, the computing system can identify hypotheses and rank the hypotheses according to an aggregation approach. For some types of aggregation approach, the computing system uses weight values, error path values and/or other performance characteristics determined during training for the NER services.

    AGGREGATING RESULTS FROM NAMED ENTITY RECOGNITION SERVICES
    3.
    发明申请
    AGGREGATING RESULTS FROM NAMED ENTITY RECOGNITION SERVICES 审中-公开

    公开(公告)号：US20170293682A1

    公开(公告)日：2017-10-12

    申请号：US15635098

    申请日：2017-06-27

    Applicant: SAP SE

    Inventor： Katja Pfeifer ,  Johannes Meinecke

    IPC: G06F17/30

    Abstract: An aggregation service aggregates extraction results from diverse named entity recognition (“NER”) services, which can help improve the quality of extracted information. In some cases, the aggregation service considers differences in entity type classifications when aggregating extraction results from different NER services. The aggregation service can also consider performance characteristics (e.g., error rates) for the different NER services. For example, the aggregation service receives extraction results generated for a document corpus according to an entity type schema for each of multiple different NER services, then aggregates the extraction results based at least in part on relations between entity types for the NER services. For a given annotation area, the computing system can identify hypotheses and rank the hypotheses according to an aggregation approach. For some types of aggregation approach, the computing system uses weight values, error path values and/or other performance characteristics determined during training for the NER services.

    Automatic extension of a partially-editable dataset copy
    5.
    发明授权
    Automatic extension of a partially-editable dataset copy 有权

    公开(公告)号：US12282472B1

    公开(公告)日：2025-04-22

    申请号：US18598195

    申请日：2024-03-07

    Applicant: SAP SE

    Inventor： Jan Rittinger ,  Johannes Meinecke ,  Gregor Hackenbroich ,  Richard Pilz ,  Katja Pfeifer ,  Tom Spiegler ,  Franz Josef Grueneberger

    IPC: G06F16/23

    Abstract: The present disclosure involves systems, software, and computer implemented methods for automatically extending a partially-editable dataset copy. One example method includes identifying, for a data set, extension filter criteria that extends a current filter that defines an editable portion of the data set. An extended filter is automatically generated for the data set based on the extension filter criteria and the current filter. Additional data is copied into the partially-editable copy of the data set based on the extended filter and the current filter to generate an updated partially-editable copy of the data set. The current filter is replaced with the extended filter to create a new current filter. An updated exposed view is generated using the new current filter that exposes the updated partially-editable copy of the data set and an updated non-editable portion of the data set.

Patent Agency Ranking