SMART DOCUMENT MIGRATION AND ENTITY DETECTION

    公开(公告)号:US20210374276A1

    公开(公告)日:2021-12-02

    申请号:US16924467

    申请日:2020-07-09

    Applicant: SAP SE

    Abstract: Systems and methods include extraction of a plurality of clauses from each of a plurality of electronic documents, determination, for each of the plurality of clauses and using a machine-learned algorithm, an associated clause type, identification of one or more data privacy protection entities present within each of one or more of the plurality of clauses, determination, for each of the one or more of the plurality of clauses, of a weighted frequency for each of the one or more data privacy protection entities present within the clause based on a type of the data privacy protection entity, determination of a weighted frequency associated with each of the plurality of electronic documents based on the determined weighted frequency for each of the one or more data privacy protection entities present within clauses of the plurality of electronic documents, and storage of an identifier of each of the plurality of electronic documents in association with a respective determined weighted frequency.

    DATA SECURITY IN LARGE LANGUAGE MODELS

    公开(公告)号:US20250094619A1

    公开(公告)日:2025-03-20

    申请号:US18467167

    申请日:2023-09-14

    Applicant: SAP SE

    Abstract: Certain aspects of the disclosure concern a computer-implemented method for improved data security in large language models. The method includes receiving a prompt query entered through a user interface, extracting a plurality of named entities from the prompt query and classifying the plurality of named entities into respective entity classes, tagging the plurality of named entities to be security compliant or security noncompliant based on the respective entity classes, and responsive to finding that one or more named entities are tagged to be security noncompliant, generating an alert on the user interface.

    Smart document migration and entity detection

    公开(公告)号:US11599666B2

    公开(公告)日:2023-03-07

    申请号:US16924467

    申请日:2020-07-09

    Applicant: SAP SE

    Abstract: Systems and methods include extraction of a plurality of clauses from each of a plurality of electronic documents, determination, for each of the plurality of clauses and using a machine-learned algorithm, an associated clause type, identification of one or more data privacy protection entities present within each of one or more of the plurality of clauses, determination, for each of the one or more of the plurality of clauses, of a weighted frequency for each of the one or more data privacy protection entities present within the clause based on a type of the data privacy protection entity, determination of a weighted frequency associated with each of the plurality of electronic documents based on the determined weighted frequency for each of the one or more data privacy protection entities present within clauses of the plurality of electronic documents, and storage of an identifier of each of the plurality of electronic documents in association with a respective determined weighted frequency.

    Providing Odata service based on service operation execution flow

    公开(公告)号:US10313421B2

    公开(公告)日:2019-06-04

    申请号:US15345841

    申请日:2016-11-08

    Applicant: SAP SE

    Abstract: A method and system for providing an OData service based on a service operation execution flow is described. Initially a data source metadata is converted to an entity data model. Based on the entity data model, the service operation execution flow is generated that displays a process for executing a service operation. Next, one or more runtime configuration data are received to edit the generated service operation execution flow. The edited service operation execution flow defines a communication between a data source and a client requesting execution of the service operation. Finally, based on the edited service operation execution flow and the entity data model the Odata service is published to process a client request for executing the service operation.

    Generating predictive models to reconfigure electronic devices

    公开(公告)号:US10268961B2

    公开(公告)日:2019-04-23

    申请号:US14950031

    申请日:2015-11-24

    Applicant: SAP SE

    Abstract: Various embodiments of systems and methods for generating predictive models are described herein. A computer system deployed in a distributed may receive configuration data from multiple electronic devices. The system may select a set of configuration data with respect to a device category and a subcategory to generate a prediction model. The predictive model includes hypothesis, an average deviation and information pertaining to optimal configuration data for the given subcategory and the device category. The computer system may also receive monitoring requests from electronic devices and retrieve appropriate predictive model with respect to the device category and subcategory. The system may reconfigure the electronic device based on the retrieve predictive model.

    GENERATING PREDICTIVE MODELS TO RECONFIGURE ELECTRONIC DEVICES

    公开(公告)号:US20170147928A1

    公开(公告)日:2017-05-25

    申请号:US14950031

    申请日:2015-11-24

    Applicant: SAP SE

    CPC classification number: G06N5/04 G06F9/44505 G06F9/448 G06F11/30 G06N99/005

    Abstract: Various embodiments of systems and methods for generating predictive models are described herein. A computer system deployed in a distributed may receive configuration data from multiple electronic devices. The system may select a set of configuration data with respect to a device category and a subcategory to generate a prediction model. The predictive model includes hypothesis, an average deviation and information pertaining to optimal configuration data for the given subcategory and the device category. The computer system may also receive monitoring requests from electronic devices and retrieve appropriate predictive model with respect to the device category and subcategory. The system may reconfigure the electronic device based on the retrieve predictive model.

Patent Agency Ranking