Unlock instant, AI-driven research and patent intelligence for your innovation.

General sense reasoning-oriented generative man-machine conversation reply generation method

A technology of man-machine dialogue and common sense reasoning, applied in reasoning methods, knowledge expression, electronic digital data processing, etc., can solve problems such as rough generation, low diversity and similarity of reply information, and achieve the effect of improving reply quality

Active Publication Date: 2021-12-17
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] 1. The lack of understanding of the dialogue leads to the rough generation of similar and vague replies by the dialogue system, which makes the dialogue less accurate
[0006] 2. Lack of knowledge processing, it is difficult to obtain knowledge related to use, so that the diversity of reply information in the dialogue is low

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
  • General sense reasoning-oriented generative man-machine conversation reply generation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] A generative man-machine dialogue reply generation method oriented to commonsense reasoning, specifically comprising the following steps:

[0034] S1. Preprocessing the dialogue context text information data; the specific process is:

[0035]S11. Perform data cleaning processing on the dialogue context text information data, including word segmentation, case conversion, and full-width and half-width format conversion;

[0036] S12. Separating the context text information data after cleaning in S11 into sentences according to the speaker; specifically, mark [speaker1] before the sentence of speaker 1, and mark [speaker2] before the sentence of speaker 2;

[0037] S2. Using the encoding method of the multi-head self-attention mechanism, using the Transformer Encoder (encoder) to encode the dialogue context information data preprocessed in step S1, to obtain the context vector W context ;

[0038] S3. Perform knowledge reasoning on the dialogue context information data p...

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 a general sense reasoning-oriented generative man-machine conversation reply generation method, and belongs to the technical field of natural language processing. The knowledge entity is introduced through context search, the knowledge vector and the dialogue vector are decoded together to generate the reply, the reply adopts the existing knowledge and inference technology to judge the context, and the dialogue reply quality is effectively improved.

Description

technical field [0001] The invention belongs to the technical field of natural language processing, and in particular relates to a generative man-machine dialogue reply generation method oriented to common sense reasoning. Background technique [0002] Using natural language to communicate with machines has been one of the goals of computer science research for a long time. With the rapid development of modern artificial intelligence and deep learning technology, as well as the substantial increase in dialogue materials brought about by the popularity of the global Internet and mobile devices, research in the field of natural language processing and dialogue systems, which were previously difficult to progress due to diverse meanings and complex grammar also developed rapidly. [0003] Human-machine dialogue refers to a system that enables machines to interact with humans through human language. The generative dialogue system is a technology that is gradually available aft...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/332G06F16/33G06F16/36G06N5/02G06N5/04
CPCG06F16/3329G06F16/3334G06F16/3347G06F16/367G06N5/022G06N5/04Y02D10/00
Inventor 卢国明康昭陈爱国罗光春穆亚侨姚娴
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA