公开(公告)号：US20220208317A1

公开(公告)日：2022-06-30

申请号：US17136036

申请日：2020-12-29

Applicant: Industrial Technology Research Institute

Inventor： Cheng-Yi Yang ,  Cheng-Liang Lin ,  Hsing-Chen Lin

IPC: G16H10/60 ,  G16H30/20 ,  G06F16/583

Abstract: An image content extraction method and an image content extraction device are disclosed. The method includes the following. An image file is obtained; the image file is analyzed to obtain distribution information of at least one grid in an image frame corresponding to the image file; template information is determined according to the distribution information of the at least one grid; text information is extracted from the image file according to the template information; and integration information related to a medical record of a user is generated according to the text information.

公开(公告)号：US20140201768A1

公开(公告)日：2014-07-17

申请号：US13956379

申请日：2013-08-01

Applicant: Industrial Technology Research Institute

Inventor： Tun-Hao You ,  Cheng-Liang Lin ,  Jin-Chin Chung

IPC: H04N21/442

CPC classification number: H04N21/24 ,  H04N21/2407 ,  H04N21/44213 ,  H04N21/6582 ,  H04N21/812

Abstract: A method for recording and analyzing audience information of an audio/video program is provided. The method includes receiving at least one user information from at least one online social service, at least one audio/video capture information from at least one terminal device associated with the at least one user information, and at least one social behavior information related to the at least one audio/video capture information from the at least one online social service. The method includes establishing a relationship between the at least one user information, the at least one audio/video capture information, and the at least one social behavior information, and recording the relationship and the foregoing information into an audience information database. The method includes when receiving a querying command, generating a querying result of qualitative rating according to at least one reference information acquired from the audience information database in accordance with the querying command.

Abstract translation: 提供了一种用于记录和分析音频/视频节目的观众信息的方法。 所述方法包括从至少一个在线社交服务接收至少一个用户信息，至少一个来自与所述至少一个用户信息相关联的终端设备的音频/视频捕获信息，以及至少一个与所述至少一个用户信息有关的社交行为信息 来自至少一个在线社交服务的至少一个音频/视频捕获信息。 所述方法包括建立所述至少一个用户信息，所述至少一个音频/视频捕获信息和所述至少一个社交行为信息之间的关系，以及将所述关系和所述信息记录到观众信息数据库中。 该方法包括当接收到查询命令时，根据查询命令，根据从观众信息数据库获得的至少一个参考信息，产生定性评级的查询结果。

公开(公告)号：US10572929B2

公开(公告)日：2020-02-25

申请号：US15853866

申请日：2017-12-25

Applicant: Industrial Technology Research Institute

Inventor： Cheng-Liang Lin ,  Jie-Sin Li ,  En-Tzu Wang ,  Jyun-Tang Huang ,  Tsung-Wen Tso

IPC: G06Q30/00 ,  G06Q30/06 ,  G06Q30/02 ,  G06F17/18 ,  G06N5/04 ,  G06F16/2457

Abstract: A decision factors analyzing device and a decision factors analyzing device for analyzing a plurality of decision factors which cause a product of a product type to be purchased are provided. The method includes identifying a plurality of product sequences corresponding to the product type from a plurality of browse history data and a plurality of purchase history data corresponding to a plurality of consumers of a consumer database, wherein each of the product sequences includes a unpurchased product and a purchased product; obtaining a feature sequence according to the produce sequences and a plurality of product information; training a regression model corresponding to the product type according to K decision factors of the feature sequence to obtain an optimized regression model, and obtaining K decision values respectively corresponding to the K decision factors according to the optimized regression model to generate a decision factor sequence corresponding to the product type.

公开(公告)号：US20190164213A1

公开(公告)日：2019-05-30

申请号：US15853866

申请日：2017-12-25

Applicant: Industrial Technology Research Institute

Inventor： Cheng-Liang Lin ,  Jie-Sin Li ,  En-Tzu Wang ,  Jyun-Tang Huang ,  Tsung-Wen Tso

IPC: G06Q30/06 ,  G06Q30/02 ,  G06F17/30 ,  G06N5/04 ,  G06F17/18

Abstract: A decision factors analyzing device and a decision factors analyzing device for analyzing a plurality of decision factors which cause a product of a product type to be purchased are provided. The method includes identifying a plurality of product sequences corresponding to the product type from a plurality of browse history data and a plurality of purchase history data corresponding to a plurality of consumers of a consumer database, wherein each of the product sequences includes a unpurchased product and a purchased product; obtaining a feature sequence according to the produce sequences and a plurality of product information; training a regression model corresponding to the product type according to K decision factors of the feature sequence to obtain an optimized regression model, and obtaining K decision values respectively corresponding to the K decision factors according to the optimized regression model to generate a decision factor sequence corresponding to the product type.