At&t Intellectual Property I, LP

Warnermedia, LLC

Appavu Siva Prakasam

Ann Eileen Skudlark

Christopher Volinsky

Sanjeev Misra

Zhengyi Zhou

Deirdre Paul

Olivia Hong

Rakhi Seth-Forrest

Raif Rustamov

Lien K Tran

Prashanth Boddhireddy

Siva Kolachina

Nisha Shahul Hameed

Jenq-Chyuan Wang

Concepts and technologies disclosed herein are directed to increasing misspelling, typographical, and partial search tolerance for search terms. A system can obtain media content metadata associated with media content. The system can identify a plurality of names within the media content metadata and remove a plurality of stop words from the media content metadata. The system can determine a plurality of unigrams and a plurality of bigrams from the media content metadata. The system can determine a plurality of misspellings of the media content metadata. The system can compile the plurality of names, the plurality of stop words, the plurality of unigrams, the plurality of bigrams, and the plurality of misspellings as results. The system can determine a plurality of incorrect search strings based upon the results and can create a dictionary including the plurality of incorrect search strings mapped to a plurality of correct search strings.

Increasing misspelling, typographical, and partial search tolerance for search terms

Aspects of the subject disclosure may include, for example, a system or method that determines, based on consumption data and location information, groups of access portals, where the consumption data and the location information correspond to a time period in which the access portals are used to access a service using an account. The groups can be adjusted according to an intended benefit unit for the service and a sharing structure can be determined including benefit unit partitions for the account based on the adjusting. Factors can be determined, based on the benefit unit partitions, that are indicative of account sharing, as well as weights for the factors by applying a learning model to the consumption data. An intervention strategy can be selected from a group of intervention strategies according to the factors and the weights for the factors. Other embodiments are disclosed.

Method and apparatus to profile account credential sharing

Aspects of the subject disclosure may include, for example, a system or method that collects or otherwise accesses information indicating connection patterns such as IP addresses being utilized by communication devices for communication services over a time period, where the communication devices use a same credential of a single account for accessing the communication services. Hubs can be identified according to groups of the communication devices that exhibit a particular sharing pattern such as having used the one or more common IP addresses. A prediction or estimation that the single account is engaging in sharing activity can be made based on an analysis of the hubs, such as based on a number of the hubs. Other embodiments are disclosed.

Method and apparatus to monitor account credential sharing in communication services

Aspects of the subject disclosure may include, for example, identifying content consumption data associated with media content consumption at a customer device, and generating a content selection recommendation for the customer device. Some embodiments can include determining a habit-based content selection vector for the customer device. Various embodiments can include determining the habit-based content selection vector based on a habit profile for the customer device. Some embodiments can include adjusting a content selection vector for the customer device based on the habit-based content selection vector for the customer device. Various embodiments can include generating the content selection recommendation for the customer device based on the adjusted content selection vector. Other embodiments are disclosed.

Content recommendation techniques with reduced habit bias effects

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.

Method and apparatus for labeling data

Growing community of inventors

New Providence, NJ, United States of America

Appavu Siva Prakasam