Metalearning-based strategy game behavior prediction method and predictor

The invention relates to a behavior prediction method and predictor of a strategy game based on meta-learning in the technical field of strategy games. The method comprises the steps of obtaining a network attack and defense game data set, dividing the data set into a new task used for testing the e...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: LI PENG, YUAN WEILIN, GU XUEQIANG, CHEN SHAOFEI, LU LINA, SU JIONGMING, CHEN JIAXING, ZOU MINGWO, HU ZHENZHEN
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator LI PENG
YUAN WEILIN
GU XUEQIANG
CHEN SHAOFEI
LU LINA
SU JIONGMING
CHEN JIAXING
ZOU MINGWO
HU ZHENZHEN
description The invention relates to a behavior prediction method and predictor of a strategy game based on meta-learning in the technical field of strategy games. The method comprises the steps of obtaining a network attack and defense game data set, dividing the data set into a new task used for testing the effect of a trained behavior prediction model and a training sample used for meta-learning, and training the constructed behavior prediction model based on a deep neural network by adopting a meta-learning method, and the trained behavior prediction model is used to predict the strategic behavior of the attacker in the network attack and defense game in the new task. According to the method, a task classification method of unsupervised learning and a meta-learning method of an expert mixed architecture are adopted, the prediction precision and prediction speed of strategic behaviors of attackers in a network attack and defense game can be obviously improved in a scene with a small network attack and defense game dat
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN114866356A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN114866356A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN114866356A3</originalsourceid><addsrcrecordid>eNrjZPD0TS1JzElNLMrLzEvXTUosTk1RKC4pSixJTa9USE_MTVVISs1ILMvML1IoKEpNyUwuyczPU8hNLcnIT1FIzEuBieYX8TCwpiXmFKfyQmluBkU31xBnD93Ugvz41OKCxOTUvNSSeGc_Q0MTCzMzY1MzR2Ni1AAAHTw1MQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Metalearning-based strategy game behavior prediction method and predictor</title><source>esp@cenet</source><creator>LI PENG ; YUAN WEILIN ; GU XUEQIANG ; CHEN SHAOFEI ; LU LINA ; SU JIONGMING ; CHEN JIAXING ; ZOU MINGWO ; HU ZHENZHEN</creator><creatorcontrib>LI PENG ; YUAN WEILIN ; GU XUEQIANG ; CHEN SHAOFEI ; LU LINA ; SU JIONGMING ; CHEN JIAXING ; ZOU MINGWO ; HU ZHENZHEN</creatorcontrib><description>The invention relates to a behavior prediction method and predictor of a strategy game based on meta-learning in the technical field of strategy games. The method comprises the steps of obtaining a network attack and defense game data set, dividing the data set into a new task used for testing the effect of a trained behavior prediction model and a training sample used for meta-learning, and training the constructed behavior prediction model based on a deep neural network by adopting a meta-learning method, and the trained behavior prediction model is used to predict the strategic behavior of the attacker in the network attack and defense game in the new task. According to the method, a task classification method of unsupervised learning and a meta-learning method of an expert mixed architecture are adopted, the prediction precision and prediction speed of strategic behaviors of attackers in a network attack and defense game can be obviously improved in a scene with a small network attack and defense game dat</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC COMMUNICATION TECHNIQUE ; ELECTRICITY ; PHYSICS ; TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION</subject><creationdate>2022</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20220805&amp;DB=EPODOC&amp;CC=CN&amp;NR=114866356A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20220805&amp;DB=EPODOC&amp;CC=CN&amp;NR=114866356A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>LI PENG</creatorcontrib><creatorcontrib>YUAN WEILIN</creatorcontrib><creatorcontrib>GU XUEQIANG</creatorcontrib><creatorcontrib>CHEN SHAOFEI</creatorcontrib><creatorcontrib>LU LINA</creatorcontrib><creatorcontrib>SU JIONGMING</creatorcontrib><creatorcontrib>CHEN JIAXING</creatorcontrib><creatorcontrib>ZOU MINGWO</creatorcontrib><creatorcontrib>HU ZHENZHEN</creatorcontrib><title>Metalearning-based strategy game behavior prediction method and predictor</title><description>The invention relates to a behavior prediction method and predictor of a strategy game based on meta-learning in the technical field of strategy games. The method comprises the steps of obtaining a network attack and defense game data set, dividing the data set into a new task used for testing the effect of a trained behavior prediction model and a training sample used for meta-learning, and training the constructed behavior prediction model based on a deep neural network by adopting a meta-learning method, and the trained behavior prediction model is used to predict the strategic behavior of the attacker in the network attack and defense game in the new task. According to the method, a task classification method of unsupervised learning and a meta-learning method of an expert mixed architecture are adopted, the prediction precision and prediction speed of strategic behaviors of attackers in a network attack and defense game can be obviously improved in a scene with a small network attack and defense game dat</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC COMMUNICATION TECHNIQUE</subject><subject>ELECTRICITY</subject><subject>PHYSICS</subject><subject>TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZPD0TS1JzElNLMrLzEvXTUosTk1RKC4pSixJTa9USE_MTVVISs1ILMvML1IoKEpNyUwuyczPU8hNLcnIT1FIzEuBieYX8TCwpiXmFKfyQmluBkU31xBnD93Ugvz41OKCxOTUvNSSeGc_Q0MTCzMzY1MzR2Ni1AAAHTw1MQ</recordid><startdate>20220805</startdate><enddate>20220805</enddate><creator>LI PENG</creator><creator>YUAN WEILIN</creator><creator>GU XUEQIANG</creator><creator>CHEN SHAOFEI</creator><creator>LU LINA</creator><creator>SU JIONGMING</creator><creator>CHEN JIAXING</creator><creator>ZOU MINGWO</creator><creator>HU ZHENZHEN</creator><scope>EVB</scope></search><sort><creationdate>20220805</creationdate><title>Metalearning-based strategy game behavior prediction method and predictor</title><author>LI PENG ; YUAN WEILIN ; GU XUEQIANG ; CHEN SHAOFEI ; LU LINA ; SU JIONGMING ; CHEN JIAXING ; ZOU MINGWO ; HU ZHENZHEN</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN114866356A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2022</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC COMMUNICATION TECHNIQUE</topic><topic>ELECTRICITY</topic><topic>PHYSICS</topic><topic>TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION</topic><toplevel>online_resources</toplevel><creatorcontrib>LI PENG</creatorcontrib><creatorcontrib>YUAN WEILIN</creatorcontrib><creatorcontrib>GU XUEQIANG</creatorcontrib><creatorcontrib>CHEN SHAOFEI</creatorcontrib><creatorcontrib>LU LINA</creatorcontrib><creatorcontrib>SU JIONGMING</creatorcontrib><creatorcontrib>CHEN JIAXING</creatorcontrib><creatorcontrib>ZOU MINGWO</creatorcontrib><creatorcontrib>HU ZHENZHEN</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>LI PENG</au><au>YUAN WEILIN</au><au>GU XUEQIANG</au><au>CHEN SHAOFEI</au><au>LU LINA</au><au>SU JIONGMING</au><au>CHEN JIAXING</au><au>ZOU MINGWO</au><au>HU ZHENZHEN</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Metalearning-based strategy game behavior prediction method and predictor</title><date>2022-08-05</date><risdate>2022</risdate><abstract>The invention relates to a behavior prediction method and predictor of a strategy game based on meta-learning in the technical field of strategy games. The method comprises the steps of obtaining a network attack and defense game data set, dividing the data set into a new task used for testing the effect of a trained behavior prediction model and a training sample used for meta-learning, and training the constructed behavior prediction model based on a deep neural network by adopting a meta-learning method, and the trained behavior prediction model is used to predict the strategic behavior of the attacker in the network attack and defense game in the new task. According to the method, a task classification method of unsupervised learning and a meta-learning method of an expert mixed architecture are adopted, the prediction precision and prediction speed of strategic behaviors of attackers in a network attack and defense game can be obviously improved in a scene with a small network attack and defense game dat</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN114866356A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC COMMUNICATION TECHNIQUE
ELECTRICITY
PHYSICS
TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION
title Metalearning-based strategy game behavior prediction method and predictor
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-01T11%3A56%3A09IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=LI%20PENG&rft.date=2022-08-05&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN114866356A%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true