Unsupervised generation of rules for an adapter grammar

    公开(公告)号:US11586812B2

    公开(公告)日:2023-02-21

    申请号:US16671047

    申请日:2019-10-31

    Abstract: One embodiment of the invention provides a method for entity extraction, comprising determining a set of part-of-speech (POS) tags based on one or more documents, determining a concept in the one or more documents based on the set of POS tags, and extracting one or more phrases from the one or more documents based on the concept. The method further comprises generating a first set of rules corresponding to the concept based on the one or more phrases, generating a second set of rules specific to a domain based on the first set of rules, and learning, via an adapter grammar, a structure of one or more named entities in the one or more documents based on the second set of rules.

    Query recommendation to locate an application programming interface

    公开(公告)号:US11500914B2

    公开(公告)日:2022-11-15

    申请号:US16122552

    申请日:2018-09-05

    Abstract: Systems, computer-implemented methods, and computer program products to facilitate query recommendation are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise an ontology component that can generate an ontology based on unstructured data of a description of an application programming interface. The computer executable components can further comprise a reasoner component that can identify one or more terms of the ontology that correspond semantically to a term of a query.

    UNSUPERVISED GENERATION OF RULES FOR AN ADAPTER GRAMMAR

    公开(公告)号:US20210133284A1

    公开(公告)日:2021-05-06

    申请号:US16671047

    申请日:2019-10-31

    Abstract: One embodiment of the invention provides a method for entity extraction, comprising determining a set of part-of-speech (POS) tags based on one or more documents, determining a concept in the one or more documents based on the set of POS tags, and extracting one or more phrases from the one or more documents based on the concept. The method further comprises generating a first set of rules corresponding to the concept based on the one or more phrases, generating a second set of rules specific to a domain based on the first set of rules, and learning, via an adapter grammar, a structure of one or more named entities in the one or more documents based on the second set of rules.

    Intelligent self-service delivery advisor

    公开(公告)号:US10380558B2

    公开(公告)日:2019-08-13

    申请号:US15806601

    申请日:2017-11-08

    Abstract: The present invention provides a method, system, and computer program product of an intelligent self-service delivery advisor. In an embodiment, the present invention includes, in response to receiving computer system service data, identifying, by a second computer system, a computer system service category among a plurality of computer system categories, identifying, by the second computer system, one or more computer system service tasks, based on the computer system service data and the computer system service category, selecting, by the second computer system, a catalog among a plurality of catalogs, based on the one or more computer system service tasks and the computer system service data, generating, by the second computer system, one or more suggestions based on the catalog and the one or more computer system service tasks; and displaying, displaying by the second computer system, the one or more suggestion on a display logically coupled to the computer system.

    USER/GROUP SERVICING BASED ON DEEP NETWORK ANALYSIS

    公开(公告)号:US20190019222A1

    公开(公告)日:2019-01-17

    申请号:US15859617

    申请日:2017-12-31

    Abstract: Content is selectively provided to users of mobile devices within a venue including an on-site wireless network. User authorization requests and/or user account registration data are transmitted to the on-site wireless network from mobile devices within the venue. Attributes such as user interests and professions, which comprise inferred user profiles, are obtained using the network traffic data. Identities of mobile devices are established based on a combination including two or more of network identifiers, mobile device signatures, and browser signatures. The inferred user profiles are correlated with the mobile device identities. The inferred user profiles are aggregated into user profile groups and then matched with a content provider's intended target profiles. Content is transmitted to the mobile devices corresponding to the intended target profiles and based on correlation of the inferred user profiles with identities of the devices. Inferred user profiles may be verified using social and/or geographical data.

Patent Agency Ranking