公开(公告)号：US20220084077A1

公开(公告)日：2022-03-17

申请号：US17532989

申请日：2021-11-22

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Donghai Bian ,  Yehan Zheng ,  Weihua Peng ,  Yu Luo

IPC: G06Q30/02

Abstract: Exemplary embodiments of the present disclosure provide a method and apparatus for automatically generating an advertisement, a device, a computer-readable storage medium, and a computer program product. The method for automatically generating an advertisement includes: obtaining, based on a field to which an object of the advertisement belongs, multimedia content reflecting attributes of the object, wherein the multimedia content comprises one of text content, image content, video content, and audio content; generating, based on the field and the attributes, text information describing the object; and combining the multimedia content and the text information to generate the advertisement.

公开(公告)号：US20230199277A1

公开(公告)日：2023-06-22

申请号：US18084953

申请日：2022-12-20

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Donghai Bian ,  Yuwei Wu ,  Guangzhi Sheng ,  Yehan Zheng ,  Weihua Peng ,  Weijian Xu

IPC: H04N21/845 ,  G06V20/40

CPC classification number: H04N21/8456 ,  G06V20/46

Abstract: Provided are a video generation method, an electronic device, and a non-transitory computer-readable storage medium. The implementation scheme is as follows: a place path of at least two target events is planned in an electronic map according to occurrence places of the at least two target events and occurrence time of the at least two target events, where the at least two target events have a same theme; video sub-segments of the at least two target events are respectively determined to obtain at least two video sub-segments; and a target video is generated according to the at least two video sub-segments and the place path.

公开(公告)号：US20230117255A1

公开(公告)日：2023-04-20

申请号：US18084444

申请日：2022-12-19

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Donghai BIAN ,  Yuwei Wu ,  Guangzhi Sheng ,  Yehan Zheng ,  Weihua Peng ,  Weijian Xu

IPC: G06V20/40 ,  G06V10/77 ,  G06V10/82 ,  G06T7/246 ,  G06T7/215

Abstract: A method for processing video data includes: acquiring a target segment of video data to be extracted; acquiring theme information to be extracted; and determining an association degree between the target segment and the theme information based on segment information of the video data and a relationship between the target segment and the video data.

公开(公告)号：US20230133981A1

公开(公告)日：2023-05-04

申请号：US18086556

申请日：2022-12-21

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Donghai BIAN ,  Yuwei Wu ,  Guangzhi Sheng ,  Yehan Zheng ,  Weihua Peng ,  Weijian Xu

IPC: G06V10/771 ,  G06V10/74

Abstract: A method of training an image generation model, and a method of generating an image. A specific implementation solution includes: acquiring a first image sample and a first text sample matched with the first image sample; performing an enhancement on at least one type of sample in the first image sample and the first text sample according to a predetermined knowledge graph, so as to obtain at least one type of sample in a second image sample obtained by the enhancement and a second text sample obtained by the enhancement; and training the image generation model according to a training set selected from a first training set, a second training set or a third training set, until the image generation model converges.