公开(公告)号：US20250036707A1

公开(公告)日：2025-01-30

申请号：US18771988

申请日：2024-07-12

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Man LIU ,  Cheng LV ,  Rendan PAN ,  Xinji ZHONG

IPC: G06F16/957 ,  G06F3/0481 ,  G06F3/0484 ,  G06F16/9538

Abstract: The disclosure relates to a content processing method and apparatus, a device, and a storage medium. The method includes: showing a target content page to display a multimedia content; determining a content consumption intention on the multimedia content based on browsing information corresponding to the target content page; determining target summary information that adapted to the content consumption intention, where the target summary information is generated at least based on the multimedia content; in response to the content consumption intention being a shallow consumption intention, the target summary information is first summary information; and in response to the content consumption intention being a deep consumption intention, the target summary information is second summary information with a larger information content; and displaying the target summary information on the target content page.

公开(公告)号：US20250103824A1

公开(公告)日：2025-03-27

申请号：US18783342

申请日：2024-07-24

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Aonan TAN ,  Huayong DING ,  Jun LI ,  Rendan PAN ,  Cheng LV

IPC: G06F40/35 ,  G06F3/0482 ,  G06F40/289

Abstract: A method for question-and-answer processing, an electronic device and a storage medium are provided. The method includes: receiving a content of a first to-be-processed question that is inputted; acquiring at least two first answer results of the content of the first to-be-processed question, where the at least two first answer results are generated based on at least two target generative models matched with the content of the first to-be-processed question respectively, the at least two target generative models are capable of answering the first to-be-processed question, and generative models of different types are trained based on different occupational scenes; and displaying the at least two first answer results.