公开(公告)号：US10599769B2

公开(公告)日：2020-03-24

申请号：US16019021

申请日：2018-06-26

Applicant: Capital One Services, LLC

Inventor： Jon Austin Osbourne ,  Aaron Raymer ,  Megan Yetman ,  Venkat Yashwanth Gunapati

IPC: G06F17/27 ,  G06N5/04 ,  G10L19/083 ,  G06K9/62 ,  G06F16/35

Abstract: A method performed by a device may include identifying a plurality of samples of textual content; performing tokenization of the plurality of samples to generate a respective plurality of tokenized samples; performing embedding of the plurality of tokenized samples to generate a sample matrix; determining groupings of attributes of the sample matrix using a convolutional neural network; determining context relationships between the groupings of attributes using a bidirectional long short term memory (LSTM) technique; selecting predicted labels for the plurality of samples using a model, wherein the model selects, for a particular sample of the plurality of samples, a predicted label of the predicted labels from a plurality of labels based on respective scores of the particular sample with regard to the plurality of labels and based on a nonparametric paired comparison of the respective scores; and providing information identifying the predicted labels.

公开(公告)号：US20200175228A1

公开(公告)日：2020-06-04

申请号：US16784551

申请日：2020-02-07

Applicant: Capital One Services, LLC

Inventor： Jon Austin Osbourne ,  Aaron Raymer ,  Megan Yetman ,  Venkat Yashwanth Gunapati

IPC: G06F40/284 ,  G06N5/04 ,  G10L19/083 ,  G06K9/62 ,  G06F16/35

Abstract: A method performed by a device may include identifying a plurality of samples of textual content; performing tokenization of the plurality of samples to generate a respective plurality of tokenized samples; performing embedding of the plurality of tokenized samples to generate a sample matrix; determining groupings of attributes of the sample matrix using a convolutional neural network; determining context relationships between the groupings of attributes using a bidirectional long short term memory (LSTM) technique; selecting predicted labels for the plurality of samples using a model, wherein the model selects, for a particular sample of the plurality of samples, a predicted label of the predicted labels from a plurality of labels based on respective scores of the particular sample with regard to the plurality of labels and based on a nonparametric paired comparison of the respective scores; and providing information identifying the predicted labels.

公开(公告)号：US11379659B2

公开(公告)日：2022-07-05

申请号：US16784551

申请日：2020-02-07

Applicant: Capital One Services, LLC

Inventor： Jon Austin Osbourne ,  Aaron Raymer ,  Megan Yetman ,  Venkat Yashwanth Gunapati

IPC: G06F40/20 ,  G06N5/04 ,  G10L19/083 ,  G06K9/62 ,  G06F16/35 ,  G06F40/284

Abstract: A method performed by a device may include identifying a plurality of samples of textual content; performing tokenization of the plurality of samples to generate a respective plurality of tokenized samples; performing embedding of the plurality of tokenized samples to generate a sample matrix; determining groupings of attributes of the sample matrix using a convolutional neural network; determining context relationships between the groupings of attributes using a bidirectional long short term memory (LSTM) technique; selecting predicted labels for the plurality of samples using a model, wherein the model selects, for a particular sample of the plurality of samples, a predicted label of the predicted labels from a plurality of labels based on respective scores of the particular sample with regard to the plurality of labels and based on a nonparametric paired comparison of the respective scores; and providing information identifying the predicted labels.