-
Patent Agency Ranking
公开(公告)号：US20210182887A1
公开(公告)日：2021-06-17
申请号：US17182161
申请日：2021-02-22
Applicant: AT&T Intellectual Property I, L.P.
Inventor： Prashanth Boddhireddy , Kyubyul Hwang , Siva Kolachina , Vijayendra Kousik Garikapati
Abstract: A processing system may obtain a feature set for segmenting households comprising subscribers of a telecommunication network into segments, the households including reporting households for which an information value regarding a feature of interest is available, and non-reporting households for which an information value regarding the feature of interest is not available. The processing system may then assign the households to segments, each segment associated with a set of information values for features of the feature set, and where for each segment, households assigned to the segment have information values that are the same for each of the features of the feature set. The processing system may also link each non-reporting household in a segment to a reporting household in the segment. The processing system may then reconfigure the telecommunication network in accordance with information values for the at least one feature of interest for the plurality of households.
-
公开(公告)号：US20220277351A1
公开(公告)日：2022-09-01
申请号：US17749347
申请日：2022-05-20
Applicant: AT&T Intellectual Property I, L.P.
Inventor： Sanjeev Misra , Appavu Siva Prakasam , Ann Eileen Skudlark , Siva Kolachina , Nisha Shahul Hameed , Prashanth Boddhireddy , Lien Tran , Jenq-Chyuan Wang
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.
-
公开(公告)号：US20210182912A1
公开(公告)日：2021-06-17
申请号：US16866798
申请日：2020-05-05
Applicant: AT&T Intellectual Property I, L.P. , Xandr Inc.
Inventor： Sanjeev Misra , Appavu Siva Prakasam , Ann Eileen Skudlark , Siva Kolachina , Nisha Shahul Hameed , Prashanth Boddhireddy , Lien Tran , Jenq-Chyuan Wang
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.
-
公开(公告)号：US11386463B2
公开(公告)日：2022-07-12
申请号：US16866798
申请日：2020-05-05
Applicant: AT&T Intellectual Property I, L.P.
Inventor： Sanjeev Misra , Appavu Siva Prakasam , Ann Eileen Skudlark , Siva Kolachina , Nisha Shahul Hameed , Prashanth Boddhireddy , Lien Tran , Jenq-Chyuan Wang
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.
-
公开(公告)号：US10929862B2
公开(公告)日：2021-02-23
申请号：US16179799
申请日：2018-11-02
Applicant: AT&T Intellectual Property I, L.P.
Inventor： Prashanth Boddhireddy , Kyubyul Hwang , Siva Kolachina , Vijayendra Kousik Garikapati
Abstract: A processing system may obtain a feature set for segmenting households comprising subscribers of a telecommunication network into segments, the households including reporting households for which an information value regarding a feature of interest is available, and non-reporting households for which an information value regarding the feature of interest is not available. The processing system may then assign the households to segments, each segment associated with a set of information values for features of the feature set, and where for each segment, households assigned to the segment have information values that are the same for each of the features of the feature set. The processing system may also link each non-reporting household in a segment to a reporting household in the segment. The processing system may then reconfigure the telecommunication network in accordance with information values for the at least one feature of interest for the plurality of households.
-
-
-
-
Search Results
5
records
(took 0.015 seconds)
