Title:
METHOD FOR INTELLIGENT DIALOGUE BASED ON MACHINE READING COMPREHENSION, DEVICE, AND TERMINAL
Document Type and Number:
WIPO Patent Application WO/2019/242297
Kind Code:
A1
Abstract:
A method for intelligent dialogue based on machine reading comprehension, a device, and a terminal, the method comprising: acquiring a question provided by a user as well as a text corresponding to the question (S101); segmenting and vectorizing the question and the text to obtain a question vector corresponding to each word in the question and a text vector corresponding to each word in the text (S102); inputting the question vector and the text vector into an attention model to obtain a first vector and a second vector, wherein the first vector is used for indicating the degree to which the question influences paying attention to any word in the text, and the second vector is used for indicating the degree to which the text influences generating a question (S103); determining an answer start point and an answer end point in the text according to the first vector and the second vector, and determining a section between the answer start point and the answer end point as the answer to the question (S104). By means of the method, various questions of a user may be flexibly answered without needing to configure "question-answer" pairs in advance, thereby overcoming the detect in the existing technology wherein continuous maintenance of a question library is required, and reducing the costs of updating data.
Inventors:
HE QI (CN)
Application Number:
PCT/CN2019/070350
Publication Date:
December 26, 2019
Filing Date:
January 04, 2019
Export Citation:
Assignee:
ONE CONNECT SMART TECH CO LTD SHENZHEN (CN)
International Classes:
G06F16/30; G06F16/40
Foreign References:
| CN107562792A | 2018-01-09 | |||
| CN108170816A | 2018-06-15 | |||
| CN106776562A | 2017-05-31 | |||
| CN109086303A | 2018-12-25 |
Other References:
RONG, GUANGHUI ET AL.: "Question Answer Matching Method Based on Deep Learning", JOURNAL OF COMPUTER APPLICATIONS, vol. 37, no. 10, 10 October 2017 (2017-10-10), ISSN: 1001-9081
LIU, FEILONG ET AL.: "Attention of Bilinear Function Based Bi-LSTM Model for Machine Reading Comprehension", COMPUTER SCIENCE, vol. 44, no. 6A, 30 June 2017 (2017-06-30), pages 92 - 96; 122, ISSN: 1002-137X
LIU, FEILONG ET AL.: "Attention of Bilinear Function Based Bi-LSTM Model for Machine Reading Comprehension", COMPUTER SCIENCE, vol. 44, no. 6A, 30 June 2017 (2017-06-30), pages 92 - 96; 122, ISSN: 1002-137X
Attorney, Agent or Firm:
LIFANG & PARTNERS LTD. (CN)
Download PDF: