公开(公告)号：US11210824B2

公开(公告)日：2021-12-28

申请号：US16880503

申请日：2020-05-21

Applicant: AT&T intellectual Property I, L.P.

Inventor： Changchuan Yin

IPC: G06T11/20 ,  G06F40/126 ,  G06T11/00

Abstract: Aspects of the subject disclosure may include, for example, a method of transforming, by a processing system comprising a processor, text comprising a series of characters into a graphic representation, wherein the graphic representation comprises a series of dots arranged in a two-dimensional pattern, wherein the two-dimensional pattern comprises two dots per character, and wherein each dot in the series of dots is one unit away from a preceding dot; and plotting, by the processing system, the series of dots on a two-dimensional graph, thereby creating a unique encoded image of the text. Other embodiments are disclosed.

公开(公告)号：US12008448B2

公开(公告)日：2024-06-11

申请号：US18183120

申请日：2023-03-13

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Changchuan Yin

IPC: G06F40/103 ,  G06N20/00

CPC classification number: G06N20/00 ,  G06F40/103

Abstract: A processing system including at least one processor may obtain a machine learning model, serialize the machine learning model into a serialized format, and embed a delimiter indicator into a documentation file comprising information regarding the use of the machine learning model, where the delimiter indicator is in a file position that is after an end-of-file indicator of the documentation file. The processing system may further embed the machine learning model in the serialized format into the documentation file in a file position that is after the delimiter indicator. The processing system may then store the documentation file with the delimiter indicator and the machine learning model in the serialized format that are embedded.

公开(公告)号：US20210027190A1

公开(公告)日：2021-01-28

申请号：US16519914

申请日：2019-07-23

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Changchuan Yin

IPC: G06N20/00 ,  G06F17/21

Abstract: A processing system including at least one processor may obtain a machine learning model, serialize the machine learning model into a serialized format, and embed a delimiter indicator into a documentation file comprising information regarding the use of the machine learning model, where the delimiter indicator is in a file position that is after an end-of-file indicator of the documentation file. The processing system may further embed the machine learning model in the serialized format into the documentation file in a file position that is after the delimiter indicator. The processing system may then store the documentation file with the delimiter indicator and the machine learning model in the serialized format that are embedded.

公开(公告)号：US20230067842A1

公开(公告)日：2023-03-02

申请号：US17463950

申请日：2021-09-01

Applicant: AT&T Intellectual Property I, L.P. ,  AT&T Mobility II LLC

Inventor： Changchuan Yin ,  Sachin Lohe

IPC: H04L12/26 ,  H04W24/10 ,  H04W24/08

Abstract: A processing system including at least one processor may generate a plurality of subsequences of a time series data set, convert the plurality of subsequences to a plurality of frequency domain point sets, compute pairwise distances of the plurality of frequency domain point sets, project the plurality of frequency domain point sets into a lower dimensional space in accordance with the pairwise distances, where the projecting maps each of plurality of frequency domain point sets to a node of a plurality of nodes in the lower dimensional space, and generate a notification of at least one isolated node of the plurality of nodes, where the at least one isolated node represents at least one anomaly in the time series data set.

公开(公告)号：US20220139011A1

公开(公告)日：2022-05-05

申请号：US17529837

申请日：2021-11-18

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Changchuan Yin

IPC: G06T11/20 ,  G06F40/126 ,  G06T11/00

Abstract: Aspects of the subject disclosure may include, for example, a method of transforming, by a processing system comprising a processor, text comprising a series of characters into a graphic representation, wherein the graphic representation comprises a series of dots arranged in a two-dimensional pattern, wherein the two-dimensional pattern comprises four dots per character, and wherein each dot in the series of dots is one unit away from a preceding dot; and plotting, by the processing system, the series of dots on a two-dimensional graph, thereby creating a unique encoded image of the text. Other embodiments are disclosed.

公开(公告)号：US20210248318A1

公开(公告)日：2021-08-12

申请号：US17241361

申请日：2021-04-27

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Changchuan Yin

IPC: G06F40/284 ,  G06F40/242

Abstract: Text can be encoded into DNA sequences. Each word from a document or other text sample can be encoded in a DNA sequence or DNA sequences and the DNA sequences can be stored for later retrieval. The DNA sequences can be stored digitally, or actual DNA molecules containing the sequences can be synthesized and stored. In one example, the encoding technique makes use of a polynomial function to transform words based on the Latin alphabet into k-mer DNA sequences of length k. Because the whole bits required for the DNA sequences are smaller than the actual strings of words, storing documents using DNA sequences may compress the documents relative to storing the same documents using other techniques. In at least one example, the mapping between words and DNA sequences is one-to-one and the collision ratio for the encoding is low.

公开(公告)号：US20230222389A1

公开(公告)日：2023-07-13

申请号：US18183120

申请日：2023-03-13

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Changchuan Yin

IPC: G06N20/00 ,  G06F40/103

CPC classification number: G06N20/00 ,  G06F40/103

Abstract: A processing system including at least one processor may obtain a machine learning model, serialize the machine learning model into a serialized format, and embed a delimiter indicator into a documentation file comprising information regarding the use of the machine learning model, where the delimiter indicator is in a file position that is after an end-of-file indicator of the documentation file. The processing system may further embed the machine learning model in the serialized format into the documentation file in a file position that is after the delimiter indicator. The processing system may then store the documentation file with the delimiter indicator and the machine learning model in the serialized format that are embedded.

公开(公告)号：US20220358290A1

公开(公告)日：2022-11-10

申请号：US17740773

申请日：2022-05-10

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Changchuan Yin

IPC: G06F40/284 ,  G06F40/242

Abstract: Text can be encoded into DNA sequences. Each word from a document or other text sample can be encoded in a DNA sequence or DNA sequences and the DNA sequences can be stored for later retrieval. The DNA sequences can be stored digitally, or actual DNA molecules containing the sequences can be synthesized and stored. In one example, the encoding technique makes use of a polynomial function to transform words based on the Latin alphabet into k-mer DNA sequences of length k. Because the whole bits required for the DNA sequences are smaller than the actual strings of words, storing documents using DNA sequences may compress the documents relative to storing the same documents using other techniques. In at least one example, the mapping between words and DNA sequences is one-to-one and the collision ratio for the encoding is low.

公开(公告)号：US20220327278A1

公开(公告)日：2022-10-13

申请号：US17225041

申请日：2021-04-07

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Changchuan Yin ,  Sachin Lohe

IPC: G06F40/126 ,  G06F40/123

Abstract: An example method is provided for encoding text for language processing. The method may be executed by a processing system, and the method includes receiving text comprising a plurality of alphanumeric characters or symbols and converting the text into a numerical vector comprising a plurality of numerical values, by mapping each alphanumeric character or symbol of the text to a vertex coordinate of one of a plurality of vertices of a hypercube, wherein a number of the plurality of vertices is equal to or greater than a number of the plurality of alphanumeric characters or symbols, wherein the numerical vector consumes less space in memory than the text. An amount of time consumed by language processing of the numerical vector may be less than an amount of time consumed by language processing of the text.

公开(公告)号：US11675965B2

公开(公告)日：2023-06-13

申请号：US17225041

申请日：2021-04-07

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Changchuan Yin ,  Sachin Lohe

IPC: G06F40/126 ,  G06F40/123

CPC classification number: G06F40/126 ,  G06F40/123

Abstract: An example method is provided for encoding text for language processing. The method may be executed by a processing system, and the method includes receiving text comprising a plurality of alphanumeric characters or symbols and converting the text into a numerical vector comprising a plurality of numerical values, by mapping each alphanumeric character or symbol of the text to a vertex coordinate of one of a plurality of vertices of a hypercube, wherein a number of the plurality of vertices is equal to or greater than a number of the plurality of alphanumeric characters or symbols, wherein the numerical vector consumes less space in memory than the text. An amount of time consumed by language processing of the numerical vector may be less than an amount of time consumed by language processing of the text.