Feedback type dialogue intention obtaining method based on trigger rule

An acquisition method and trigger technology, applied in neural learning methods, motion accessories, biological neural network models, etc., can solve the problems of NPC feedback dialogue styles are scarce, and achieve the effect of increasing freshness and avoiding repeated and ineffective feedback.

Pending Publication Date: 2021-11-02
SUN YAT SEN UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

As the number of NPCs in the game increases, this development method will bring about an exponential growth in the preset writin

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
  • Feedback type dialogue intention obtaining method based on trigger rule
  • Feedback type dialogue intention obtaining method based on trigger rule
  • Feedback type dialogue intention obtaining method based on trigger rule

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The accompanying drawings are for illustrative purposes only and cannot be construed as limiting the patent;

[0045] In order to better illustrate this embodiment, some parts in the drawings will be omitted, enlarged or reduced, and do not represent the size of the actual product;

[0046] It is understood by those skilled in the art that certain known structures and descriptions thereof may be omitted in the drawings.

[0047] The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0048] Such as Figure 2-3 As shown, this application provides a trigger-based rule-based feedback dialogue intent acquisition method, which mainly includes five steps: data set construction, model construction, asynchronous model training, and system dialogue generation:

[0049] S1: Dataset construction.

[0050] 1) Construction of game background knowledge map

[0051] In the game, the triggered...

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 provides a feedback dialogue intention obtaining method based on a trigger rule, which uses Node2Vec to carry out graph embedded coding on an environment background condition in a game, and when dialogue generation is carried out for an NPC, an environment knowledge feature vector K corresponding to the current environment background condition can be applied as one of input which is taken into consideration. An output dialogue according to the analyzed feedback intention label is generated in combination with a trigger rule. Therefore, the game NPC and the game environment can be more closely connected; on the basis of a Seq2Seq structure, an environment knowledge feature vector K and a player input semantic vector Hin are integrated to obtain an output semantic vector Hout, and the output semantic vector Hout is decoded into an output statement Uout of NPC. The dialogue generation mode can prevent the NPC from generating repeated and invalid feedback to the player, and the feeling of freshness obtained when the player makes contact with the NPC is increased.

Description

technical field [0001] The present invention relates to the fields of knowledge graph embedding and natural language processing, and more specifically, to a trigger-based rule-based feedback dialogue intent acquisition method. Background technique [0002] The rapid development of Internet technology has promoted the transformation of products in many industries, and the computer game industry is one of the most profoundly affected industries. Due to the maturity of various related technologies, the means of enriching the player's sensory experience such as images, sound effects, and plots of computer games have been developed to the extreme. However, in recent years, the improvement speed of these related technologies has also tended to be slow, and the existing technological development in all aspects tends to be in a bottleneck period. At this time, the computer game industry urgently needs new technologies as a powerful means to improve game experience and enhance game ...

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): G06F16/332G06F16/33G06F16/36G06F40/30A63F13/60G06N3/08
CPCG06F16/3329G06F16/3344G06F16/367G06F40/30A63F13/60G06N3/084Y02D10/00
Inventor 万海陈灏罗炜麟曾娟黄佳莉
Owner SUN YAT SEN UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap