公开(公告)号：US11692293B2

公开(公告)日：2023-07-04

申请号：US16497778

申请日：2019-04-16

Applicant: LG ELECTRONICS INC.

Inventor： Jaehong Kim ,  Heeyeon Choi

IPC: D06F33/32 ,  D06F34/18 ,  D06F34/28 ,  G06F3/16 ,  G06N3/008 ,  G06F18/214 ,  G06V10/82

CPC classification number: D06F33/32 ,  D06F34/18 ,  D06F34/28 ,  G06F3/16 ,  G06F18/2148 ,  G06N3/008 ,  G06V10/82

Abstract: Disclosed is an artificial intelligence (AI)-based laundry treatment apparatus comprising: a washing module; a camera to acquire an image of laundry; a memory for storing therein a laundry recognition model, wherein the model is trained using a machine learning or deep learning algorithm, wherein the model is configured to recognize laundry information about the laundry; and a processor configured to apply image data from the acquired image to the laundry recognition model to acquire the laundry information.

公开(公告)号：US20220343098A1

公开(公告)日：2022-10-27

申请号：US17348532

申请日：2021-06-15

Applicant: LG ELECTRONICS INC.

Inventor： Jaehong Kim ,  Hangil Jeong ,  Hyoeun Kim ,  Heeyeon Choi ,  Kamin Lee ,  Hyejeong Jeon

IPC: G06K9/00 ,  H04N7/18 ,  G06K9/62 ,  G06F3/14 ,  G06F16/245 ,  G06N3/04 ,  G06N3/08

Abstract: According to an embodiment of the present disclosure, a refrigerator may include a storage compartment, an outer door, one or more cameras provided in the outer door, a global DB configured to store a plurality of default food identification items and a plurality of default product names respectively corresponding to the plurality of default food identification items, and a local DB configured to store edited product names and a food identification item corresponding to the edited product names, and a processor configured to photograph an internal image of the storage compartment through the one or more cameras, obtain a food identification item from the photographed internal image, determine whether the obtained food identification item is stored in the local DB, and when the food identification item is not stored in the local DB, determine whether the obtained food identification item is stored in the global DB.

公开(公告)号：US11521093B2

公开(公告)日：2022-12-06

申请号：US16541740

申请日：2019-08-15

Applicant: LG ELECTRONICS INC.

Inventor： Jaehong Kim ,  Heeyeon Choi

IPC: G06N5/04 ,  G06K19/07 ,  G06N3/08 ,  G06N3/04

Abstract: Disclosed is an artificial intelligence apparatus that includes: a sensing unit that includes a gyroscope sensor and an acceleration sensor; an output unit that outputs information; and a processor that acquires a resultant value output from a deep learning model by inputting data acquired from the gyroscope sensor and the acceleration sensor into the deep learning model, performs self-diagnosis when the resultant value shows a shock requiring self-diagnosis, and controls the output unit to output a result of the self diagnosis, in which the deep learning model is a neural network having an adjusted weight by being trained using whether a shock is a shock requiring the self-diagnosis as a resultant value and sensing values of the gyroscope sensor and the acceleration sensor as input values.

公开(公告)号：US11113532B2

公开(公告)日：2021-09-07

申请号：US16493700

申请日：2019-04-16

Applicant: LG ELECTRONICS INC.

Inventor： Jaehong Kim ,  Heeyeon Choi

IPC: G06K9/00 ,  G06K9/62 ,  G06N20/00 ,  G06N3/04 ,  G06N3/08

Abstract: Disclosed herein is an artificial intelligence apparatus for recognizing at least one object, comprising: a memory configured to store a plurality of recognition models for generating identification information corresponding to the object from image data; and a processor configured to: obtain image data for the object, generate first identification information corresponding to the object from the image data using a default recognition model composed of at least one or more of the plurality of recognition models, measure a confidence level for the first identification information, obtain the first identification information as a recognition result of the object if the confidence level is equal to or greater than a first reference value, and obtain second identification information corresponding to the object from the image data as a recognition result of the object using a compound recognition model composed of at least one or more of the plurality of recognition models if the measured confidence level is less than the first reference value, wherein the default recognition model is a model defined by first weights for the plurality of recognition models, and wherein the compound recognition model is a model defined by second weights for the plurality of recognition models.

公开(公告)号：US11776544B2

公开(公告)日：2023-10-03

申请号：US17747944

申请日：2022-05-18

Applicant: LG ELECTRONICS INC.

Inventor： Jaehong Kim ,  Hyoeun Kim ,  Hangil Jeong ,  Heeyeon Choi

IPC: G10L15/22 ,  G06N3/08 ,  G10L15/26 ,  G10L25/30

CPC classification number: G10L15/22 ,  G06N3/08 ,  G10L15/26 ,  G10L25/30 ,  G10L2015/225

Abstract: An embodiment of the present invention provides an artificial intelligence (AI) apparatus for recognizing a speech of a user, the artificial intelligence apparatus includes a memory to store a speech recognition model and a processor to obtain a speech signal for a user speech, to convert the speech signal into a text using the speech recognition model, to measure a confidence level for the conversion, to perform a control operation corresponding to the converted text if the measured confidence level is greater than or equal to a reference value, and to provide feedback for the conversion if the measured confidence level is less than the reference value.

公开(公告)号：US11653805B2

公开(公告)日：2023-05-23

申请号：US16575628

申请日：2019-09-19

Applicant: LG ELECTRONICS INC.

Inventor： Jaehong Kim ,  Hyoeun Kim ,  Heeyeon Choi

IPC: A47L9/28

CPC classification number: A47L9/2831 ,  A47L9/2826 ,  G05D2201/0215

Abstract: A robot cleaner for performing cleaning using artificial intelligence includes a suction unit configured to suction dust, a driving unit to drive the robot cleaner, a memory configured to store a compensation model for inferring optimal suction output and driving output for cleaning environment information for learning, and a processor configured to acquire cleaning environment information, determine a suction output value and a driving speed of the robot cleaner from the acquired cleaning environment information using the compensation model, control the suction unit to suction the dust with the determined suction output value, and control the driving unit to drive the robot cleaner at the determined driving speed.

公开(公告)号：US20220277746A1

公开(公告)日：2022-09-01

申请号：US17747944

申请日：2022-05-18

Applicant: LG ELECTRONICS INC.

Inventor： Jaehong Kim ,  Hyoeun Kim ,  Hangil Jeong ,  Heeyeon Choi

IPC: G10L15/22 ,  G06N3/08 ,  G10L15/26 ,  G10L25/30

Abstract: An embodiment of the present invention provides an artificial intelligence (AI) apparatus for recognizing a speech of a user, the artificial intelligence apparatus includes a memory to store a speech recognition model and a processor to obtain a speech signal for a user speech, to convert the speech signal into a text using the speech recognition model, to measure a confidence level for the conversion, to perform a control operation corresponding to the converted text if the measured confidence level is greater than or equal to a reference value, and to provide feedback for the conversion if the measured confidence level is less than the reference value.

公开(公告)号：US11211079B2

公开(公告)日：2021-12-28

申请号：US16657137

申请日：2019-10-18

Applicant: LG ELECTRONICS INC.

Inventor： Jongwoo Han ,  Jaehong Kim ,  Hyoeun Kim ,  Taeho Lee ,  Hangil Jeong ,  Heeyeon Choi

IPC: G10L21/0208 ,  G10L17/02 ,  G10L17/18 ,  G10L17/04 ,  G10L15/02

Abstract: An AI device is provided. The AI device includes a memory to store data, a voice acquisition interface to acquire a voice signal, and a processor to perform preprocessing for the voice signal based on a parameter, to provide the preprocessed voice signal to a voice recognition model, to acquire a voice recognition result, to store a characteristic of the preprocessed voice signal in the memory, and to change the parameter using a distribution of characteristics of voice signals accumulated in the memory.

公开(公告)号：US12046030B2

公开(公告)日：2024-07-23

申请号：US17348532

申请日：2021-06-15

Applicant: LG ELECTRONICS INC.

Inventor： Jaehong Kim ,  Hangil Jeong ,  Hyoeun Kim ,  Heeyeon Choi ,  Kamin Lee ,  Hyejeong Jeon

IPC: G06V20/00 ,  G06F3/14 ,  G06F16/245 ,  G06F18/214 ,  G06F18/22 ,  G06N3/04 ,  G06N3/08 ,  H04N7/18 ,  G06V20/68

CPC classification number: G06V20/00 ,  G06F3/14 ,  G06F16/245 ,  G06F18/214 ,  G06F18/22 ,  G06N3/04 ,  G06N3/08 ,  H04N7/188 ,  G06V20/68

Abstract: According to an embodiment of the present disclosure, a refrigerator may include a storage compartment, an outer door, one or more cameras provided in the outer door, a global DB configured to store a plurality of default food identification items and a plurality of default product names respectively corresponding to the plurality of default food identification items, and a local DB configured to store edited product names and a food identification item corresponding to the edited product names, and a processor configured to photograph an internal image of the storage compartment through the one or more cameras, obtain a food identification item from the photographed internal image, determine whether the obtained food identification item is stored in the local DB, and when the food identification item is not stored in the local DB, determine whether the obtained food identification item is stored in the global DB.

公开(公告)号：US11593588B2

公开(公告)日：2023-02-28

申请号：US16593928

申请日：2019-10-04

Applicant: LG Electronics Inc.

Inventor： Jaehong Kim ,  Hyoeun Kim ,  Hyejeong Jeon ,  Heeyeon Choi

IPC: G06Q30/00 ,  G06K9/62 ,  G06N20/00 ,  G06N5/04 ,  G06N3/08

Abstract: An artificial intelligence apparatus for generating training data includes a memory configured to store a target artificial intelligence model, and a processor configured to receive sensor data, determine whether the received sensor data is irrelevant to a learning of the target artificial intelligence model, determine whether the received sensor data is useful for the learning if the received sensor data is determined to be relevant to the learning, extract a label from the received sensor data by using a label extractor if the received sensor data is determined to be useful for the learning, determine a confidence level of the extracted label, and generate training data including the received sensor data and the extracted label if the determined confidence level exceeds a first reference value.