公开(公告)号：US20230316689A1

公开(公告)日：2023-10-05

申请号：US18331539

申请日：2023-06-08

申请人： URBANBASE INC.

发明人： Dae Hee YUN

IPC分类号： G06T19/20

CPC分类号： G06T19/20 ,  G06T2210/04 ,  G06T2219/2012 ,  G06T2219/2024

摘要： According to one embodiment of the present invention, an object recommendation method performed by an object recommendation device may comprise: a step of acquiring big data composed of information on a user using an interior design service, identification information of an interior design object placed by the user, and object information including styles of an object; a step of determining styles of an existing object placed in a virtual space by a first user using the interior design service; an operation of adding up a placement count of each style for the styles of the existing object; and a step of, in a case in which information with respect to a predetermined object to be newly placed in the virtual space of the first user is requested, adjusting a recommendation ratio of each style on the basis of the placement count of each style and recommending the predetermined object.

公开(公告)号：US20230222829A1

公开(公告)日：2023-07-13

申请号：US18156853

申请日：2023-01-19

申请人： URBANBASE INC.

发明人： Dae Hee YUN ,  Yun Ah BAEK

IPC分类号： G06V30/422 ,  G06V30/19 ,  G06V10/82

CPC分类号： G06V30/422 ,  G06V30/19173 ,  G06V10/82

摘要： According to one embodiment of the present invention, a symbol analysis device included in a facility floor plan can perform the operations of: acquiring a plurality of facility floor plans; detecting a rectangle included in each of the plurality of facility floor plans and an arc connected to the rectangle; specifying a window area and a door area on the basis of the rectangle and the arc; labeling pixels of the specified window area as the class of a window, and labeling pixels of the specified door area as the class of a door; and inputting the plurality of facility floor plans and data labeled in pixel units into a neural network model designed on the basis of a predetermined image segmentation algorithm, so as to learn the weight of the neural network model that derives the correlation between positions of the labeled pixels and the classes of windows and doors included in the plurality of facility floor plans, and thus a neural network model that determines the position and the class of windows and doors included in a facility floor plan is generated on the basis of the correlation.

公开(公告)号：US20230154050A1

公开(公告)日：2023-05-18

申请号：US18156743

申请日：2023-01-19

申请人： URBANBASE INC.

发明人： Dae Hee YUN

IPC分类号： G06T7/90 ,  G06Q30/0601

CPC分类号： G06T7/90 ,  G06Q30/0631 ,  G06T2207/10024

摘要： A spatial image analysis-based color scheme recommendation apparatus according to an embodiment of the present invention comprises a processor, wherein the processor may perform: an operation of receiving an input of a spatial image; an operation of determining types of colors constituting the spatial image and a ratio of respective types of colors used in the spatial image; an operation of selecting a first color that is a part of the colors constituting the spatial image in an increasing order of the ratio of colors used in the spatial image; an operation of determining an element value in which each of the first colors is located on a predetermined color image scale using soft and dynamic as elements; an operation of calculating a combined color scheme element value by applying a weight to the element value of each first color using, as a weight, a ratio of each first color used in the spatial image; and an operation of recommending a color scheme group including a color scheme element value in a color image scale, as a color scheme suitable for the spatial image.

公开(公告)号：US10803659B2

公开(公告)日：2020-10-13

申请号：US16718842

申请日：2019-12-18

申请人： URBANBASE INC.

发明人： Jinwoo Ha ,  Kyoungwoo Lee ,  Deockjoong Kim

IPC分类号： G06T17/10 ,  G06T17/00 ,  G06T15/50 ,  G06T19/20

摘要： The present disclosure relates to an automatic three-dimensional solid modeling method and program based on a two-dimensional drawing, including at least: acquiring a drawing image; generating a figure by extracting line segments in the drawing image; identifying sub-areas within the figure and identifying spatial types of the sub-areas; and generating a three-dimensional space model by applying height information corresponding to the spatial types of the sub-areas. The present disclosure is convenient in that there is no need to visit the real three-dimensional space in order to implement the corresponding space on a computer, and can remarkably reduce the time required to implement the three-dimensional space.

公开(公告)号：US20230351473A1

公开(公告)日：2023-11-02

申请号：US18350060

申请日：2023-07-11

申请人： URBANBASE INC.

发明人： Yun Ah BAEK ,  Dae Hee YUN

IPC分类号： G06Q30/0601 ,  G06F40/268 ,  G06F40/216

CPC分类号： G06Q30/0631 ,  G06F40/268 ,  G06F40/216

摘要： A method for providing a style analysis model according to one embodiment of the present invention may comprise: obtaining a training document including text data written by a user and determining a first text included in the training document; determining a predetermined number of second texts from among the first text of the training document; generating a first feature vector configured on the basis of the number of times each second text is included in training documents written by each user; generating, for each class, a second feature vector on the basis of the number of times each style-specific text is included in all the obtained training documents; labeling the first feature vector with a class of a second feature vector that is most similar to the first feature vector; and generating and training a machine learning-based neural network model that derives a correlation between the first feature vector and the class labeled in the first feature vector.

公开(公告)号：US20230351107A1

公开(公告)日：2023-11-02

申请号：US18350363

申请日：2023-07-11

申请人： URBANBASE INC.

发明人： Yun Ah BAEK ,  Dae Hee YUN

IPC分类号： G06F40/268 ,  G06F40/242

CPC分类号： G06F40/268 ,  G06F40/242

摘要： A method for providing a style analysis model according to an embodiment of the present invention may comprise the operations of: acquiring a document written by a first user from an SNS used by the first user of an interior decoration service; determining a first text included in the document; determining a predetermined number of second texts in the first text of the document; generating a first feature vector configured on the basis of a frequency by which each of the second texts is included in the document; determining the style of the first user by inputting the first feature vector into a machine learning-based neural network model in which a correlation is pre-learned to derive a class specifying an interior decoration style for a predetermined feature vector; and recommending object information to which metadata of the style is mapped, on the basis of the determined style, when the first user requests information on a predetermined object provided by the interior decoration service.

公开(公告)号：US20220366675A1

公开(公告)日：2022-11-17

申请号：US17870525

申请日：2022-07-21

申请人： Urbanbase, Inc.

发明人： Yun Ah Baek ,  Daehee YUN

IPC分类号： G06V10/774 ,  G06V10/764 ,  G06V10/82

摘要： Disclosed is a data augmentation-based preference analysis model learning apparatus including one or more processors, wherein the operation performed by the processor includes acquiring a plurality of space images and labeling a class specifying style information corresponding to each of the plurality of space images or acquiring the plurality of space images to which the class is labeled and generating learning data, generating a second space image by changing pixel information included in a first space image within a predetermined range among the plurality of space images and augmenting the learning data, and labeling a class labeled to the first space image, to the second space image.

公开(公告)号：US20220358752A1

公开(公告)日：2022-11-10

申请号：US17870330

申请日：2022-07-21

申请人： Urbanbase, Inc.

发明人： Yun Ah Baek ,  Daehee Yun

IPC分类号： G06V10/774 ,  G06V20/70 ,  G06V10/764 ,  G06V10/82

摘要： Disclosed is a data augmentation-based space analysis model learning apparatus including one or more processors, wherein the operation performed by the processor includes acquiring a plurality of space images and labeling a class specifying space information corresponding to each of the plurality of space images or acquiring the plurality of space images to which the class is labeled and generating learning data, generating a second space image by changing some or all of pixel information included in a first space image among the plurality of space images and augmenting the learning data, labeling a class labeled to the first space image, to the second space image, and learning a weight of a model designed based on a predetermined image classification algorithm, for deriving a correlation between a space image included in the learning data and a class labeled to each of the space images.

公开(公告)号：US20220358411A1

公开(公告)日：2022-11-10

申请号：US17870519

申请日：2022-07-21

申请人： Urbanbase, Inc.

发明人： Yun Ah BAEK ,  Daehee YUN

IPC分类号： G06N20/00

摘要： Disclosed is a data augmentation-based object analysis model learning apparatus including one or more processors, wherein the operation performed by the processor includes acquiring a first space image including a first object image and generating a second space image by changing pixel information included in the first space image, specifying a bounding box in a region including the first object image in the first space image and labeling a first class specifying the first object image in the bounding box, and primarily learning a weight of a model designed based on a predetermined object detection algorithm, for deriving a correlation between the first object image in the bounding box and the first class, by inputting the first space image to the model, specifying an object image included in a space image based on the correlation.

公开(公告)号：US20200126293A1

公开(公告)日：2020-04-23

申请号：US16718842

申请日：2019-12-18

申请人： URBANBASE INC.

发明人： Jinwoo HA ,  Kyoungwoo LEE ,  Deockjoong KIM

IPC分类号： G06T17/10 ,  G06T19/20 ,  G06T15/50 ,  G06T17/00

摘要： The present disclosure relates to an automatic three-dimensional solid modeling method and program based on a two-dimensional drawing, including at least: acquiring a drawing image; generating a figure by extracting line segments in the drawing image; identifying sub-areas within the figure and identifying spatial types of the sub-areas; and generating a three-dimensional space model by applying height information corresponding to the spatial types of the sub-areas. The present disclosure is convenient in that there is no need to visit the real three-dimensional space in order to implement the corresponding space on a computer, and can remarkably reduce the time required to implement the three-dimensional space.