公开(公告)号：US12014546B2

公开(公告)日：2024-06-18

申请号：US17456375

申请日：2021-11-23

Applicant: INSTITUTE FOR INFORMATION INDUSTRY

Inventor： Chu-Chun Huang ,  Yen-Heng Tsao ,  Ping-I Chen

IPC: G06V20/40 ,  G06F16/74 ,  G06F16/783 ,  G06F40/30 ,  G06V40/16 ,  G06V40/20

CPC classification number: G06V20/46 ,  G06F16/743 ,  G06F16/7844 ,  G06F40/30 ,  G06V40/164 ,  G06V40/176 ,  G06V40/20

Abstract: A multimodal method for detecting video includes following step of: receiving a message to be detected to obtain a multimodal association result, which message to be detected corresponds to a video to be detected; generating a plurality of detecting conditions according to multimodal association result; searching a plurality of videos in a video detection database to obtain a target video in videos according to detecting conditions, which each of videos includes a plurality of video paragraphs respectively, which each of video paragraphs includes a piece of multimodal related data respectively; comparing detecting conditions and piece of multimodal related data of video paragraphs to obtain a matching video paragraph and using video corresponding to matching video paragraph as the target video; and outputting the target video and the video to be detected to a display device for display.

公开(公告)号：US20230135866A1

公开(公告)日：2023-05-04

申请号：US17456375

申请日：2021-11-23

Applicant: INSTITUTE FOR INFORMATION INDUSTRY

Inventor： Chu-Chun Huang ,  Yen-Heng Tsao ,  Ping-I Chen

IPC: G06V20/40 ,  G06F16/783 ,  G06F16/74 ,  G06V40/16 ,  G06V40/20 ,  G06F40/30

Abstract: A multimodal method for detecting video includes following step of: receiving a message to be detected to obtain a multimodal association result, which message to be detected corresponds to a video to be detected; generating a plurality of detecting conditions according to multimodal association result; searching a plurality of videos in a video detection database to obtain a target video in videos according to detecting conditions, which each of videos includes a plurality of video paragraphs respectively, which each of video paragraphs includes a piece of multimodal related data respectively; comparing detecting conditions and piece of multimodal related data of video paragraphs to obtain a matching video paragraph and using video corresponding to matching video paragraph as the target video; and outputting the target video and the video to be detected to a display device for display.

公开(公告)号：US11386305B2

公开(公告)日：2022-07-12

申请号：US17106171

申请日：2020-11-29

Applicant: INSTITUTE FOR INFORMATION INDUSTRY

Inventor： Chu-Chun Huang ,  Yu-Chuan Yang ,  Yen-Heng Tsao ,  Tzu-Ying Chen ,  Po-Hsien Chiang ,  Fu-Jheng Jheng

IPC: G06K9/00 ,  G06K9/62 ,  G06F40/284

Abstract: A device and a method for detecting a purpose of an article are provided. The device is configured to divide the article into a plurality of sentences and input the sentences to a feature identification model to generate a contextualized word vector corresponding to each of the sentences. The device further inputs the representation to a specific purpose detecting model to generate a distributed representation similarity of the article. When the distributed representation similarity of the article is greater than a threshold, the device determines that the article conforms to a specific purpose.

公开(公告)号：US20190139064A1

公开(公告)日：2019-05-09

申请号：US15831406

申请日：2017-12-05

Applicant: INSTITUTE FOR INFORMATION INDUSTRY

Inventor： Ping-I Chen ,  Tai-Ta Kuo ,  Yen-Heng Tsao ,  Fu-Jheng Jheng ,  Yu-Chuan Yang

IPC: G06Q30/02 ,  G06F17/30

Abstract: An inference system for data relation, method and system for generating marketing target groups are disclosed herein. The method includes the following operations: inputting a product name; determining a first group type of the product name from a specified data source according to the product name and finding a first interesting field and at least one first interesting data in the first interesting field corresponding to the first group type; establishing a customer persona model, wherein the customer persona model contains second group types, each of second group types has a second interesting field and at least one second interesting data in the second interesting field corresponding to the second group type; comparing the at least one second interesting data of the second group type of the customer persona model with the at least one first interesting data, and screening at least one marketing target group.