中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

32 records (took 0.019 seconds)

    SYSTEM AND METHOD FOR FRAUD DETECTION THROUGH NETWORK MONITORING
    11.
    发明申请
    SYSTEM AND METHOD FOR FRAUD DETECTION THROUGH NETWORK MONITORING 有权

    公开(公告)号：US20250113193A1

    公开(公告)日：2025-04-03

    申请号：US18477699

    申请日：2023-09-29

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Zhengyi Zhou ,  Guy Jacobson ,  Venson Shaw ,  Wen-Ling Hsu

    IPC: H04W12/122 ,  H04W12/79

    Abstract: Aspects of the subject disclosure may include, for example, a device, having a processing system including a processor; and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations of: collecting data traffic of one or more network devices of a user, wherein the data traffic is associated with multiple channels of interactions; building a channel-specific user signature and a cross-channel user signature of normal usage for the user based on the data traffic collected; detecting a change in a characteristic of the data traffic, wherein the change indicates fraudulent activity based on the channel-specific user signature and the cross-channel user signature; and issuing an alert of the fraudulent activity based on the change. Other embodiments are disclosed.

    DETECTING NETWORK ANOMALIES FOR ROBUST SEGMENTS OF NETWORK INFRASTRUCTURE ITEMS IN ACCORDANCE WITH SEGMENT FILTERS ASSOCIATED VIA FREQUENT ITEMSET MINING
    13.
    发明申请
    DETECTING NETWORK ANOMALIES FOR ROBUST SEGMENTS OF NETWORK INFRASTRUCTURE ITEMS IN ACCORDANCE WITH SEGMENT FILTERS ASSOCIATED VIA FREQUENT ITEMSET MINING 有权

    公开(公告)号：US20220311687A1

    公开(公告)日：2022-09-29

    申请号：US17660632

    申请日：2022-04-25

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Zhengyi Zhou ,  Deirdre Paul

    IPC: H04L43/08 ,  H04L41/0893 ,  H04L41/142 ,  H04L41/0816

    Abstract: A processing system may generate segments of network infrastructure items deployed in a communication network, each segment comprising network infrastructure items grouped in accordance with segment filters and a segment size sparsity threshold, and identify anomalous segments comprising at least a subset of the segments having anomalies of an anomaly type regarding a performance indicator. The processing system may next determine segments from the subset that are defined by sets of segment filter values that are different for less than a threshold number of segment filters, merge the segments from the subset that are different for less than the threshold number to create at least one aggregate segment, and generate a ranking of the subset having the anomalies of the anomaly type, wherein the ranking includes the at least one aggregate segment. The processing system may then perform at least one action in the communication network responsive to the ranking.

    SEPARATING INTENDED AND NON-INTENDED BROWSING TRAFFIC IN BROWSING HISTORY
    15.
    发明申请
    SEPARATING INTENDED AND NON-INTENDED BROWSING TRAFFIC IN BROWSING HISTORY 审中-公开

    公开(公告)号：US20200076906A1

    公开(公告)日：2020-03-05

    申请号：US16120748

    申请日：2018-09-04

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Zhengyi Zhou ,  Christopher Volinsky

    IPC: H04L29/08 ,  H04L29/06 ,  H04W12/08 ,  G06F17/30

    Abstract: Facilitating separation of intended and non-intended browsing traffic in browsing history advanced networks (e.g., 4G, 5G, and beyond) is provided herein. Operations of a system can comprise determining respective contradiction values for second-level domains of a group of second-level domains in observed browsing history traffic. The operations can also comprise separating intended network traffic from non-intended network traffic based on the respective contradiction values. The respective contradiction values can indicate levels of inconsistency between the observed browsing history traffic and a determined popularity ranking.

    TRANSFER KNOWLEDGE FROM AUXILIARY DATA FOR MORE INCLUSIVE MACHINE LEARNING MODELS
    16.
    发明公开
    TRANSFER KNOWLEDGE FROM AUXILIARY DATA FOR MORE INCLUSIVE MACHINE LEARNING MODELS 审中-公开

    公开(公告)号：US20240104422A1

    公开(公告)日：2024-03-28

    申请号：US17935747

    申请日：2022-09-27

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Zhengyi Zhou ,  Cheryl Brooks ,  Aritra Guha ,  Yaron Kanza ,  Balachander Krishnamurthy

    IPC: G06N20/00

    CPC classification number: G06N20/00

    Abstract: Transfer knowledge from auxiliary data for more inclusive machine learning models is provided. A method can include generating a common feature space comprising first data features, wherein the first data features are present in training data used to train a first machine learning model, and wherein the first data features are present in auxiliary data that are independent of the training data; generating a combined learned feature representation, the combined learned feature representation being representative of the first data features of the common feature space and second data features that are unique to the training data; and training a second machine learning model based on the combined learned feature representation.

    FACILITATING IDENTIFICATION OF BACKGROUND BROWSING TRAFFIC IN BROWSING HISTORY DATA IN ADVANCED NETWORKS
    19.
    发明申请
    FACILITATING IDENTIFICATION OF BACKGROUND BROWSING TRAFFIC IN BROWSING HISTORY DATA IN ADVANCED NETWORKS 有权

    公开(公告)号：US20220303227A1

    公开(公告)日：2022-09-22

    申请号：US17204746

    申请日：2021-03-17

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Zhengyi Zhou ,  Deirdre Paul ,  Christopher Volinsky

    IPC: H04L12/927 ,  H04L12/911 ,  H04W72/12

    Abstract: Facilitating identification of background browsing traffic in browsing history data in advanced networks (e.g., 5G, 6G, and beyond) is provided herein. Operations of a system can include, based on browsing history traffic observed with respect to a group of user equipment, constructing labeling functions for a group of domains associated with the browsing history traffic, producing a group of labels based on the labeling functions, and transforming the group of labels into a single consolidated label for a first domain. Further, the operations can include, based on a determination that a first numeric value of the single consolidated label is nearer to a first value than a second value, scheduling first traffic for the first domain prior to scheduling traffic for a second domain determined to include the second numeric value that is nearer the second value than the first value.

    Detecting network anomalies for robust segments of network infrastructure items in accordance with segment filters associated via frequent itemset mining
    20.
    发明授权
    Detecting network anomalies for robust segments of network infrastructure items in accordance with segment filters associated via frequent itemset mining 有权

    公开(公告)号：US11316764B1

    公开(公告)日：2022-04-26

    申请号：US17210109

    申请日：2021-03-23

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Zhengyi Zhou ,  Deirdre Paul

    IPC: G06F15/173 ,  H04L43/08 ,  H04L41/0893 ,  H04L41/142 ,  H04L41/0816

    Abstract: A processing system may generate segments of network infrastructure items deployed in a communication network, each segment comprising network infrastructure items grouped in accordance with segment filters and a segment size sparsity threshold, and identify anomalous segments comprising at least a subset of the segments having anomalies of an anomaly type regarding a performance indicator. The processing system may next determine segments from the subset that are defined by sets of segment filter values that are different for less than a threshold number of segment filters, merge the segments from the subset that are different for less than the threshold number to create at least one aggregate segment, and generate a ranking of the subset having the anomalies of the anomaly type, wherein the ranking includes the at least one aggregate segment. The processing system may then perform at least one action in the communication network responsive to the ranking.

Patent Agency Ranking