公开(公告)号：US11899699B2

公开(公告)日：2024-02-13

申请号：US17347448

申请日：2021-06-14

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

Inventor： Kaichun Yao ,  Chuan Qin ,  Hengshu Zhu ,  Chao Ma ,  Jingshuai Zhang

IPC: G06F40/289 ,  G06F40/40 ,  G06F16/332 ,  G06F16/335 ,  G06F40/20

CPC classification number: G06F16/3329 ,  G06F16/335 ,  G06F40/20

Abstract: This application discloses a keyword generating method, an apparatus, a device and a storage medium, which relate to the field of natural language processing in the field of artificial intelligence. A specific implementation scheme includes: inputting a target text into a text processing model, obtaining a word sequence corresponding to the target text, and generating a semantic representation sequence corresponding to the word sequence; making prediction about each semantic representation vector in the semantic representation sequence respectively to obtain a prediction result; and if the prediction result indicates that a word corresponding to the semantic representation vector is capable of triggering a generation of a keyword, outputting the keyword based on the semantic representation vector and the prediction result. This method improves the accuracy of generating keywords.

公开(公告)号：US20230093528A1

公开(公告)日：2023-03-23

申请号：US18070775

申请日：2022-11-29

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

Inventor： Ying SUN ,  Hengshu Zhu ,  Chuan Qin ,  Fuzhen Zhuang ,  Hui Xiong

IPC: G06N3/04 ,  G06N3/08

Abstract: An interpretation method for a neural network model is provided. Input data and output data corresponding to the input data of a neural network model are acquired, in which the neural network model includes layers of networks connected sequentially, and each layer of network corresponds to a plurality of candidate concepts. A key inference path through which the output data is obtained by the neural network model based on the input data are acquired, in which the key inference path includes target concepts respectively used by the layers of networks when the input data is processed in the neural network model, in which the target concepts are selected from the plurality of candidate concepts. Interpretation information corresponding to the layers of networks is determined according to the target concepts corresponding to the layers of networks, respectively. The key inference path and the interpretation information are output.