RECALIBRATING RESOURCE PROFILES FOR NETWORK SLICES IN A 5G OR OTHER NEXT GENERATION WIRELESS NETWORK

    公开(公告)号:US20230114909A1

    公开(公告)日:2023-04-13

    申请号:US18064839

    申请日:2022-12-12

    Abstract: The technologies described herein are generally directed to facilitating the allocation, scheduling, and management of network slice resources. According to some embodiments, a system can facilitate performance of operations. The operations can include, based on a request for a network service type that was received from a user device, allocating a network slice of a network to the user device, with the network slice being previously assigned a capacity of a resource of the network in accordance with a resource profile. Further, operations include monitoring performance of the network slice, resulting in monitored slice performance compared to a performance requirement of the network service type. Another operation includes, based on the monitored slice performance, facilitating recalibration of the resource profile in accordance with a condition associated with the network service type, resulting in a modification of the capacity of the resource assigned to the network slice.

    Bias scoring of machine learning project data

    公开(公告)号:US11620542B2

    公开(公告)日:2023-04-04

    申请号:US16704965

    申请日:2019-12-05

    Abstract: Aspects of the subject disclosure may include, for example, system and apparatus that enable operations that may include receiving, by a processing system, project data defining a proposed machine learning (ML) project of an entity and storing the project data in a project database with other project data for other projects. The operations may further include extracting extracted features of the proposed project and, based on the extracted features, determining a clustering assignment for the proposed project. Determining the clustering assignment may comprise comparing information about the proposed project including the extracted features with information about the other projects and assigning the proposed project to a cluster including one or more projects having similar bias characteristics as the proposed project. The operations may further include determining a risk of potential bias for the proposed project and, based on the risk of bias, recommending a corrective action to reduce the risk of bias. Machine learning models may be used for project clustering and bias score determination and may be readily updated as new ML projects are evaluated. Other embodiments are disclosed.

    Intelligent Continuous Authentication for Digital Rights Management

    公开(公告)号:US20230103240A1

    公开(公告)日:2023-03-30

    申请号:US18074595

    申请日:2022-12-05

    Abstract: The concepts and technologies disclosed herein are directed to intelligent continuous authentication (“ICA”) for digital rights management (“DRM”). A user device can receive a notification that a media content playback device has requested playback of a media file that is protected by an ICA engine (“ICAE”) instance. The user device can request a unique code from the media content playback device. The user device can provide the unique code to an ICAE central management system associated with a media content provider that provides media content encompassed in the media file. The user device can determine, based upon a result provided by the ICAE central management system, whether the unique code is valid or invalid. The user device can instruct the ICAE instance to enable or disable the media file based upon whether the unique code is valid or invalid.

    AUTOMATIC DISCOVERY OF MACHINE LEARNING MODEL FEATURES

    公开(公告)号:US20230099502A1

    公开(公告)日:2023-03-30

    申请号:US17486770

    申请日:2021-09-27

    Abstract: A method performed by a processing system including at least one processor includes monitoring interactions of a human user with a platform for building machine learning models, where the human user is using the platform to build a new machine learning model, detecting, within the interactions, an event that triggers a suggestion feature, performing a search of a data source for existing data from existing machine learning models which can be reused to build the new machine learning model, using information about the event, presenting a suggestion to the human user to reuse a portion of the existing data discovered in the search in the new machine learning model, receiving a user feedback in response to the suggestion, and generating an updated suggestion in response to the user feedback.

    Dynamic cyclic extension for fast access to subscriber terminals (G.Fast)

    公开(公告)号:US11616673B2

    公开(公告)日:2023-03-28

    申请号:US17201156

    申请日:2021-03-15

    Abstract: Concepts and technologies for dynamic cyclic extension (“CE”) for Fast Access to Subscriber Terminals (“G.Fast”) are described. According to one aspect described herein, a system can synchronize a G.Fast modem with the default CE value, measure an upstream signal attenuation of a G.Fast cable in a G.Fast circuit to obtain an upstream signal attenuation value, determine a new CE value based upon the upstream signal attenuation value, and determine if the new CE value is not equal to a default CE value. In response to determining that the new CE value is not equal to the default CE value, the system can update and apply a CE value for the G.Fast cable in the G.Fast circuit to the new CE value. If, however, the new CE value is equal to the default CE value, the system can instead apply the default CE value.

Patent Agency Ranking