Apparatus and method to facilitate an iterative, machine learning based traffic classification
AssigneeAT&T Intellectual Property I, L.P.
InventorsDonglin Hu, Zhengye Liu, Yali Liu, Jin Wang
Life of this patent
Estimating the term…
Abstract
Aspects of the subject disclosure may include, for example, applying a model to a first unlabeled traffic item to generate a classification of the first unlabeled traffic item as a first class of traffic items or a second class of traffic items, generating a first score that is representative of a first confidence of the classification, determining that the first score is greater than a first threshold, and responsive to determining that the first score is greater than the first threshold, refining the model in accordance with at least the classification, resulting in a modified model. Other embodiments are disclosed.
Claims20
A device, comprising:
- a processing system including a processor;
- and
- a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations, the operations comprising:
- obtaining a first unlabeled traffic item, wherein the first unlabeled traffic item is encrypted;
- applying a model to the first unlabeled traffic item, without decrypting the first unlabeled traffic item, to generate a first prediction regarding whether the first unlabeled traffic item is a video traffic item or a non-video traffic item;
- generating a first score that is representative of a first confidence of the first prediction;
- and
- responsive to a determination that the first score is less than a first threshold and greater than a second threshold, performing a first test on the first unlabeled traffic item, wherein the performing of the first test on the first unlabeled traffic item enhances the first score, resulting in a first enhanced first score.
A non-transitory machine-readable medium, comprising executable instructions that, when executed by a processing system including a processor, facilitate performance of operations, the operations comprising:
- obtaining a first unlabeled traffic item, wherein the first unlabeled traffic item is encrypted;
- applying a model to the first unlabeled traffic item, without decrypting the first unlabeled traffic item, to generate a first prediction regarding whether the first unlabeled traffic item is a video traffic item or a non-video traffic item;
- generating a first score that is representative of a first confidence of the first prediction;
- and
- based at least on a determination that the first score is less than a first threshold, performing a first test on the first unlabeled traffic item, wherein the performing of the first test on the first unlabeled traffic item enhances the first score, resulting in a first enhanced first score.
A method, comprising:
- applying, by a processing system including a processor, a model to a first unlabeled traffic item to generate a classification of the first unlabeled traffic item as a first class of traffic items or a second class of traffic items;
- generating, by the processing system, a first score that is representative of a first confidence of the classification;
- and
- responsive to a determination that the first score is less than a first threshold, performing, by the processing system, a first test on the first unlabeled traffic item, wherein the performing of the first test on the first unlabeled traffic item enhances the first score, resulting in a first enhanced first score.
Dependencies are inferred from the claim text.