公开(公告)号：US11157698B2

公开(公告)日：2021-10-26

申请号：US16176783

申请日：2018-10-31

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

Inventor： Jizhou Huang ,  Yaming Sun ,  Wei Zhang ,  Haifeng Wang

IPC: G06F40/00 ,  G06F40/295 ,  G06F16/951 ,  G06K9/00 ,  G06K9/62 ,  G06N7/00 ,  G06F40/30 ,  G06F40/268 ,  G06F40/242

Abstract: The present disclosure provides a method of training a descriptive text generating model, and a method and apparatus for generating a descriptive text, wherein the method of training a descriptive text generating model comprises: obtaining training data, the training data comprising: a notional word, a first descriptive text and a second descriptive text of the notional word, wherein the second descriptive text is a concise expression of the first descriptive text; regarding the notional word and the first descriptive text of the notional word as input of a seq2seq model, regarding the second descriptive text of the notional word as output of the seq2sequ model, and training the seq2seq model to obtain a descriptive text generating model. The descriptive text generating model according to the present disclosure can implement generation of a concise descriptive text with respect to the notional word in a deep understanding manner.

公开(公告)号：US10896188B2

公开(公告)日：2021-01-19

申请号：US16278651

申请日：2019-02-18

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

Inventor： Jizhou Huang ,  Wei Zhang ,  Yaming Sun ,  Haifeng Wang

IPC: G06F16/2457 ,  G06F16/248 ,  G06N3/04 ,  G06N3/08

Abstract: The present disclosure provides a method and apparatus for determining search results, a device and a computer storage medium, wherein the method comprises: obtaining a current query, a historical query sequence of the current query and candidate search results of the current query; inputting the current query, the historical query sequence of the current query and candidate search results of the current query into a search result-sorting model, scoring the candidate search results according to the search result-sorting model, and determining search results corresponding to the current query; wherein the scores rendered by the search result-sorting model for the candidate search results are determined according to a similarity degree between an integrated vector representation of the current query and the historical query sequence of the current query and vector representations of the candidate search results. The present disclosure can provide the user with search results which more accurately reflect the user's demands.