公开(公告)号：US20230072116A1

公开(公告)日：2023-03-09

申请号：US18049782

申请日：2022-10-26

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

Inventor： Hao CHEN ,  Runmei ZHAO ,  Jizhou HUANG

IPC: G06F16/9537 ,  G06F16/9535 ,  G06Q30/02

Abstract: A method and an apparatus for recommending a travel mode, an electronic device; and a storage medium are provided. An implementation is: receiving a request from a user for querying a first point of interest; analyzing a travel type of the user based on the request; obtaining an alternative travel mode based on the travel type in combination with user information; calculating a travel cost corresponding to the alternative travel mode; and recommending at least one travel mode for the user according to the travel cost.

公开(公告)号：US20230049839A1

公开(公告)日：2023-02-16

申请号：US17974409

申请日：2022-10-26

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

Inventor： Hao CHEN ,  Runmei ZHAO ,  Jizhou HUANG

IPC: G06F16/33 ,  G06F40/205

Abstract: The present disclosure provides a question answering method and apparatus for query information. The method may include: receiving query information input by a user, and analyzing a query target comprised in the query information; recalling candidate answers from a pre-generated knowledge graph based on the query target, where the knowledge graph is constructed based on inherent data in a map database and dynamic data of historical users, and the dynamic data includes at least one of comment data, search data, or spatiotemporal big data; and returning, in response to that there is a target answer whose matching degree with the query target exceeds a preset threshold in the candidate answers, the target answer to the user.

公开(公告)号：US20220172310A1

公开(公告)日：2022-06-02

申请号：US17651788

申请日：2022-02-18

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

Inventor： An ZHUO ,  Yu CHEN ,  Huan LIU ,  Shuai LI ,  Jia WANG ,  Chunfeng LI ,  Wei YANG ,  Hao CHEN ,  Shu ZHANG

IPC: G06Q50/16 ,  G06Q30/06 ,  G06N5/02

Abstract: Provided is a house-renting recommendation method. The method includes: receiving a destination and a house-renting requirement input by a current user; where the house-renting requirement includes at least a commuting time and a house-renting expense; inputting, into a pre-trained recommendation model, the destination and the house-renting requirement input by the current user; outputting, through the recommendation model, a search result for the current user based on a pre-constructed house-renting knowledge graph; and recommending, in response to the search result for the current user comprising information about at least one candidate housing resource, the information about the at least one candidate housing resource to the current user.