Lien Thi Tran

US Patent:

20220277351, Sep 1, 2022

Filed:

May 20, 2022

Appl. No.:

17/749347

Inventors:

- Atlanta GA, US
Appavu Siva Prakasam - New Providence NJ, US
Ann Eileen Skudlark - San Ramon CA, US
Siva Kolachina - Plano TX, US
Nisha Shahul Hameed - Bellevue WA, US
Prashanth Boddhireddy - Plano TX, US
Lien Tran - Seattle WA, US

Assignee:

AT&T Intellectual Property I, L.P. - Atlanta GA

International Classification:

G06Q 30/02
G06F 16/35
G06F 16/93
G06F 40/295
G06N 5/04
G06Q 10/10
G06N 20/00

Abstract:

Aspects of the subject disclosure may include, for example, determining classes from a corpus based on topic modeling, data clustering and unsupervised learning. Labels are determined for each of the classes and trained models are generated for each of the classes by assignment of a plurality of textual documents to labels based on a highest number of matches. A raw textual document can be tokenized and stop words removed. A corresponding one of the trained models can be selected according to a class that is applicable to subject matter of the raw textual document. The processed document can be assigned to a target label based on a highest number of matches of words. Other embodiments are disclosed.

US Patent:

20220224768, Jul 14, 2022

Filed:

Apr 4, 2022

Appl. No.:

17/712975

Inventors:

- Atlanta GA, US
Eric Zavesky - Austin TX, US
Lien Tran - Seattle WA, US
David Crawford Gibbon - Lincroft NJ, US
Zhu Liu - Marlboro NJ, US

Assignee:

AT&T Intellectual Property I, L.P. - Atlanta GA

International Classification:

H04L 67/306
H04N 21/25
H04L 67/50
H04N 21/442

Abstract:

Aspects of the subject disclosure may include, for example, a method that includes obtaining metadata from media content and consumed by network subscribers; determining for each network subscriber a consumer context associated with the media content; and determining a media consumption pattern for each network subscriber based on the metadata and the consumer context, thereby generating a plurality of media consumption patterns. The method further includes aggregating the media consumption patterns; determining, based on the aggregated media consumption patterns, a media consumption trend for the network subscribers; and correlating the media consumption trend with a profile including a current activity for a network subscriber of the plurality of network subscribers, thereby generating a recommendation for the network subscriber regarding new media content not previously consumed by the network subscriber. The method also includes communicating the recommendation to the network subscriber. Other embodiments are disclosed.

US Patent:

20230085233, Mar 16, 2023

Filed:

Nov 22, 2022

Appl. No.:

17/991886

Inventors:

- Atlanta GA, US
Lien K. Tran - Seattle WA, US
Yu Jin - Madison NJ, US

Assignee:

AT&T Intellectual Property I, L.P. - Atlanta GA

International Classification:

H04L 51/212
H04L 9/40
H04W 4/14

Abstract:

A cloud based mobile internet protocol messaging spam defense. Short message service (SMS) messages are analyzed by a cloud based virtual machine to determine if should be considered potentially unwanted messages (e.g., spam). The cloud based virtual machine uses a user specific algorithm for determining if a message should be considered to be a potentially unwanted message. Messages that are determined to be potentially unwanted messages trigger a notification to be sent to a user device associated with the virtual machine. The notification requests confirmation from the user that the potentially unwanted message is an unwanted message. The user’s response to a request for confirmation is then used to update an unwanted message database associated with the user and the user device.

US Patent:

20210273898, Sep 2, 2021

Filed:

May 14, 2021

Appl. No.:

17/320271

Inventors:

- Atlanta GA, US
Lien K. Tran - Seattle WA, US
Yu Jin - Madison NJ, US

Assignee:

AT&T Intellectual Property I, L.P. - Atlanta GA

International Classification:

H04L 12/58
H04L 29/06
H04W 4/14

Abstract:

A cloud based mobile internet protocol messaging spam defense. Short message service (SMS) messages are analyzed by a cloud based virtual machine to determine if should be considered potentially unwanted messages (e.g., spam). The cloud based virtual machine uses a user specific algorithm for determining if a message should be considered to be a potentially unwanted message. Messages that are determined to be potentially unwanted messages trigger a notification to be sent to a user device associated with the virtual machine. The notification requests confirmation from the user that the potentially unwanted message is an unwanted message. The user's response to a request for confirmation is then used to update an unwanted message database associated with the user and the user device.