Intelligent question-answering method and device

An intelligent question answering and questioning technology, applied in the computer field, can solve problems such as low accuracy and inability to effectively use contextual information retrieval.

Pending Publication Date: 2020-10-23
TAIKANG LIFE INSURANCE CO LTD +1
View PDF9 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Unable to effectively use contextual information for retrieval, the accuracy of information retrieval is not high in multi-round dialogue scenarios

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Intelligent question-answering method and device
  • Intelligent question-answering method and device
  • Intelligent question-answering method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] Exemplary embodiments of the present invention are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present invention to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

[0037] figure 1 is a schematic diagram of the main steps of the intelligent question answering method according to an embodiment of the present invention.

[0038] An embodiment of the present invention first uses the language model to vectorize the dialogue records in the dialogue process to obtain the corresponding semantic feature vectors, and then uses the attention m...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an intelligent question-answering method and device, and relates to the technical field of computers. A specific embodiment of the intelligent question-answering method comprises the steps of generating a semantic feature vector set according to a dialogue record in a current dialogue process of a first user and a customer service, the semantic feature vector set comprisinga semantic feature vector of the dialogue record in the current dialogue process; performing semantic aggregation on the semantic feature vector set to obtain a first aggregated semantic vector representing the real intention and semantics of the current question of the first user; and searching a semantic vector matched with the first aggregated semantic vector from a knowledge base storing question and answer information, and outputting an answer to the current question according to the searched semantic vector. According to the embodiment, the context information can be effectively utilized for retrieval, and the accuracy of information retrieval in a multi-round dialogue scene is improved.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to an intelligent question answering method and device. Background technique [0002] In recent years, intelligent question answering technology has developed rapidly, mainly due to the rapid development of deep learning technology and its deep integration with natural language processing technology. Existing intelligent question answering systems are usually based on information retrieval or sequence generation. In commercial applications, due to the uncontrollability of sequence generation, more information retrieval models are used. In addition, in order to achieve specific business goals, a rule-based approach is usually adopted in dialogue state control, sacrificing the openness of the dialogue system in exchange for dominance of the dialogue process (state). In addition to deep learning, intelligent dialogue systems also widely use knowledge graph technology to deal with fa...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F16/332G06F16/35G06F40/30
CPCG06F16/3329G06F16/35G06F40/30
Inventor 闫永泽陈利琴刘设伟
Owner TAIKANG LIFE INSURANCE CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products