Research on the Construction and Application of Earthquake Emergency Information Knowledge Graph Based on Large Language Models

To address the challenges of semantic parsing of multi-source heterogeneous information and the delayed emergency response decisions caused by insufficient relational reasoning capabilities in earthquake emergency management, this study proposes a domain knowledge extraction method for earthquakes b...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE access Ročník 13; s. 127742 - 127757
Hlavní autoři:	Zhou, Wentao, Huang, Meng, Liu, Shuai, You, Qiao, Meng, Fanxin
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Piscataway IEEE 2025 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Accuracy Attention Bi-GAT Cognition Correlation Data mining Disasters Earthquake construction Earthquakes Emergency management Emergency response Emergency services Feature extraction Knowledge Knowledge graphs Knowledge representation Large language models Matching Neo4j NLP PCCA Prompt engineering Semantics TPES-LLM
ISSN:	2169-3536, 2169-3536
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	To address the challenges of semantic parsing of multi-source heterogeneous information and the delayed emergency response decisions caused by insufficient relational reasoning capabilities in earthquake emergency management, this study proposes a domain knowledge extraction method for earthquakes based on a large language model combined with a three-level prompt engineering system (TPES-LLM) of "instruction fine-tuning - demand awareness - case matching. "The method deploys a local large language model using LangChain +QWEN2.5-7B, integrates earthquake domain knowledge through LoRa fine-tuning based on earthquake experts' classifications and industry standards, and injects seismic knowledge into the model. The multi-head attention mechanism weights are optimized based on the co-occurrence frequency of historical earthquake entities, and demand-aware knowledge identifies key textual features that significantly impact knowledge extraction. Training is performed on 36 known earthquake disaster events to learn the association patterns of entities, relationships, and events hidden within the earthquake case data for case matching. This method significantly enhances the accuracy of entity recognition and the efficiency of relation extraction for complex disaster-related texts. Additionally, a bidirectional graph attention network (Bi-GAT) is designed to enable bidirectional propagation and dynamic aggregation of node features. The path confidence constraint algorithm (PCCA) is used to achieve deep semantic associations of earthquake disaster elements. Based on the Neo4j graph database, an earthquake emergency knowledge graph is constructed. Experimental results from real earthquake events such as the 2022 Luding 6.8-magnitude earthquake, the 2024 Jishishan 6.2-magnitude earthquake, and the 2025 Dingri 6.8-magnitude earthquake show that the accuracy of intelligent Q&A retrieval for the earthquake emergency knowledge graph reaches 89.62%, 87.28%, and 90.23%, respectively. The earthquake emergency knowledge graph based on large language models constructed in this study provides intelligent decision support for earthquake emergencies, with significant application value.
AbstractList	To address the challenges of semantic parsing of multi-source heterogeneous information and the delayed emergency response decisions caused by insufficient relational reasoning capabilities in earthquake emergency management, this study proposes a domain knowledge extraction method for earthquakes based on a large language model combined with a three-level prompt engineering system (TPES-LLM) of "instruction fine-tuning - demand awareness - case matching. "The method deploys a local large language model using LangChain +QWEN2.5-7B, integrates earthquake domain knowledge through LoRa fine-tuning based on earthquake experts' classifications and industry standards, and injects seismic knowledge into the model. The multi-head attention mechanism weights are optimized based on the co-occurrence frequency of historical earthquake entities, and demand-aware knowledge identifies key textual features that significantly impact knowledge extraction. Training is performed on 36 known earthquake disaster events to learn the association patterns of entities, relationships, and events hidden within the earthquake case data for case matching. This method significantly enhances the accuracy of entity recognition and the efficiency of relation extraction for complex disaster-related texts. Additionally, a bidirectional graph attention network (Bi-GAT) is designed to enable bidirectional propagation and dynamic aggregation of node features. The path confidence constraint algorithm (PCCA) is used to achieve deep semantic associations of earthquake disaster elements. Based on the Neo4j graph database, an earthquake emergency knowledge graph is constructed. Experimental results from real earthquake events such as the 2022 Luding 6.8-magnitude earthquake, the 2024 Jishishan 6.2-magnitude earthquake, and the 2025 Dingri 6.8-magnitude earthquake show that the accuracy of intelligent Q&A retrieval for the earthquake emergency knowledge graph reaches 89.62%, 87.28%, and 90.23%, respectively. The earthquake emergency knowledge graph based on large language models constructed in this study provides intelligent decision support for earthquake emergencies, with significant application value.
Author	Huang, Meng Liu, Shuai Zhou, Wentao You, Qiao Meng, Fanxin
Author_xml	– sequence: 1 givenname: Wentao orcidid: 0009-0006-3179-5178 surname: Zhou fullname: Zhou, Wentao organization: Institute of Disaster Prevention, Langfang, China – sequence: 2 givenname: Meng orcidid: 0009-0000-9107-9102 surname: Huang fullname: Huang, Meng email: hm@cidp.edu.cn organization: Institute of Disaster Prevention, Langfang, China – sequence: 3 givenname: Shuai surname: Liu fullname: Liu, Shuai organization: Institute of Disaster Prevention, Langfang, China – sequence: 4 givenname: Qiao orcidid: 0009-0003-2576-4832 surname: You fullname: You, Qiao organization: Institute of Disaster Prevention, Langfang, China – sequence: 5 givenname: Fanxin surname: Meng fullname: Meng, Fanxin organization: Sichuan Disaster Reduction Center, Chengdu, China
BookMark	eNpNUU1vEzEUXKEiUUp_ARwscU7qz419DKu0RA1ConC2vPZzsmFjb-1doZ746zjdCvDBfm80M-9Z87a6CDFAVb0neEkIVjfrptk8PCwppmLJhKzZCr-qLimp1YIJVl_8V7-prnM-4nJkgcTqsvr9DTKYZA8oBjQeADUx5DFNduwKYIJD62HoO2ue--jRxqTx8DiZn4A2J0h7CPYJbYOP6TRz7kP81YPbA7pLZjigTyaDO7vvTGGXO-wnU4ov0UGf31WvvekzXL-8V9WP28335vNi9_Vu26x3C8tqMi5AchASO8zAYUzbWoJUQjjZMumJopxygRkzvECuZcoK3PKVt7yl1HJM2VW1nX1dNEc9pO5k0pOOptPPQEx7XT7W2R60crX3lqoaLONMecWtASwNgC2TnSpeH2evIcXHCfKoj3FKoayvGeV1WUxiUlhsZtkUc07g_04lWJ-D03Nw-hycfgmuqD7Mqg4A_ikIXolaMPYH8EuW6w
CODEN	IAECCG
Cites_doi	10.1109/PRAI55851.2022.9904215 10.1016/j.jag.2025.104423 10.1016/j.scs.2023.105113 10.1016/j.neucom.2021.10.101 10.1016/j.aei.2023.101900 10.18653/v1/2022.emnlp-main.759 10.1007/s10694-024-01544-6 10.3390/su10103429 10.1007/s00521-020-05057-5 10.1016/j.neucom.2022.02.002 10.1016/j.neucom.2024.127571 10.1145/3604931 10.1093/gji/ggae436 10.1016/j.knosys.2023.111323 10.1016/j.inffus.2020.03.014 10.1109/TNNLS.2021.3070843 10.1145/3544548.3581402 10.1016/j.eswa.2019.112948 10.3233/sw-180333
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
DBID	97E ESBDL RIA RIE AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D DOA
DOI	10.1109/ACCESS.2025.3586370
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE Xplore Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts METADEX Technology Research Database Materials Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef Materials Research Database Engineered Materials Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace METADEX Computer and Information Systems Abstracts Professional
DatabaseTitleList	Materials Research Database
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	2169-3536
EndPage	127757
ExternalDocumentID	oai_doaj_org_article_9d6ffc296ec3439f94cae08aeec02bd9 10_1109_ACCESS_2025_3586370 11075653
Genre	orig-research
GrantInformation_xml	– fundername: Sichuan Province Key Research and Development Project “Construction and Demonstration of Earthquake Emergency Response Assistance System Based on Digital Twin Technology” grantid: 2023YFS0437 – fundername: Science and Technology Innovation Program for Postgraduate Students in Institute of Disaster Prevention (IDP) subsidized by the Fundamental Research Funds for the Central Universities grantid: ZY20250324
GroupedDBID	0R~ 4.4 5VS 6IK 97E AAJGR ABAZT ABVLG ACGFS ADBBV AGSQL ALMA_UNASSIGNED_HOLDINGS BCNDV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD ESBDL GROUPED_DOAJ IPLJI JAVBF KQ8 M43 M~E O9- OCL OK1 RIA RIE RNS AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c361t-e84e580d03ed002b68e8955d8b38f1924245033a45d8db39c50b47fc4b22c4023
IEDL.DBID	RIE
ISICitedReferencesCount	0
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001544669800042&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2169-3536
IngestDate	Fri Oct 03 12:53:13 EDT 2025 Sat Nov 01 14:30:29 EDT 2025 Sat Nov 29 07:40:42 EST 2025 Wed Aug 27 02:13:13 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Language	English
License	https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c361t-e84e580d03ed002b68e8955d8b38f1924245033a45d8db39c50b47fc4b22c4023
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0009-0006-3179-5178 0009-0000-9107-9102 0009-0003-2576-4832
OpenAccessLink	https://ieeexplore.ieee.org/document/11075653
PQID	3246895801
PQPubID	4845423
PageCount	16
ParticipantIDs	ieee_primary_11075653 crossref_primary_10_1109_ACCESS_2025_3586370 proquest_journals_3246895801 doaj_primary_oai_doaj_org_article_9d6ffc296ec3439f94cae08aeec02bd9
PublicationCentury	2000
PublicationDate	20250000 2025-00-00 20250101 2025-01-01
PublicationDateYYYYMMDD	2025-01-01
PublicationDate_xml	– year: 2025 text: 20250000
PublicationDecade	2020
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE access
PublicationTitleAbbrev	Access
PublicationYear	2025
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	Hu (ref26); 1 Guiyang (ref12) 2024; 2024 Zheng (ref40) 2025 ref14 Razeghi (ref22) 2022 ref31 Minglun (ref37) 2025; 2025 ref30 ref10 ref2 ref1 ref16 Fengying (ref17) 2022; 35 Hu (ref25) 2021 Huang (ref13) 2024; 43 Zhongjiang (ref41) 2024; 45 Jing (ref34) 2022; 48 Jingru (ref23) 2020; 4 Weidong (ref27) 2025; 2025 Yulan (ref18) 2025; 48 ref42 Zhang (ref33) 2024; 18 ref21 Fei (ref24); 35 ref43 Nie (ref20) 2002 Zhang (ref11) 2023; 17 ref28 Minghua (ref35) 2024; 64 Bai (ref19) 2010; 33 ref29 ref8 ref7 Yang (ref32) 2025; 45 Feng (ref36) 2024; 18 Bin (ref38) 2025; 45 ref9 Jianjia (ref15) 2025; 2025 ref4 ref3 ref6 ref5 Yang (ref39) 2025; 42
References_xml	– ident: ref10 doi: 10.1109/PRAI55851.2022.9904215 – ident: ref14 doi: 10.1016/j.jag.2025.104423 – ident: ref6 doi: 10.1016/j.scs.2023.105113 – volume: 45 start-page: 1865 issue: 6 year: 2024 ident: ref41 article-title: Long-tail noise detection in knowledge graphs based on confidence publication-title: Comput. Eng. Design – ident: ref42 doi: 10.1016/j.neucom.2021.10.101 – start-page: 105 issue: 3 year: 2002 ident: ref20 article-title: Construction of a basic database for earthquake emergency response publication-title: Earthquake – ident: ref7 doi: 10.1016/j.aei.2023.101900 – volume: 35 start-page: 15460 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref24 article-title: Lasuie: Unifying information extraction with latent adaptive structure-aware generative language model – volume: 2024 start-page: 1 year: 2024 ident: ref12 article-title: Research on knowledge injection methods for large language models aimed at process specification texts publication-title: Comput. Sci. Exploration – volume: 43 start-page: 46 issue: 4 year: 2024 ident: ref13 article-title: Research on rainstorm disaster chain mining and prediction based on knowledge graph publication-title: Frontiers Eng. Manage. Technol. – ident: ref21 doi: 10.18653/v1/2022.emnlp-main.759 – volume: 48 start-page: 2556 issue: 12 year: 2022 ident: ref34 article-title: Named entity recognition in nuclear power domain based on ELMo-GCN publication-title: J. Beihang Univ. – ident: ref4 doi: 10.1007/s10694-024-01544-6 – ident: ref1 doi: 10.3390/su10103429 – volume: 45 start-page: 785 issue: 3 year: 2025 ident: ref32 article-title: Construction of a digital twin water conservancy knowledge graph integrating large language models and prompt learning publication-title: Comput. Appl. – volume: 2025 start-page: 1 year: 2025 ident: ref37 article-title: GAGAT: A global perception knowledge graph reasoning model based on graph attention network publication-title: Data Anal. Knowl. Discovery – volume: 42 start-page: 82 issue: 1 year: 2025 ident: ref39 article-title: Knowledge graph completion method based on improved graph convolutional neural network publication-title: Comput. Appl. Softw. – ident: ref8 doi: 10.1007/s00521-020-05057-5 – volume: 4 start-page: 33 issue: 10 year: 2020 ident: ref23 article-title: A BiLSTM-CRF model for protected health information in Chinese publication-title: Data Anal. Knowl. Discovery – volume: 1 start-page: 1 issue: 2 volume-title: Proc. ICLR ident: ref26 article-title: LoRA: Low-rank adaptation of large language models – ident: ref28 doi: 10.1016/j.neucom.2022.02.002 – volume: 45 start-page: 12 issue: 4 year: 2025 ident: ref38 article-title: Dual graph attention recommendation model integrating social relationships and knowledge graph publication-title: Mod. Inf. – ident: ref3 doi: 10.1016/j.neucom.2024.127571 – volume: 2025 start-page: 1 year: 2025 ident: ref27 article-title: Research on the construction method of Northeast Anti-Japanese allied red figures knowledge graph based on large models and LoRA publication-title: Inf. Theory Pract. – ident: ref9 doi: 10.1145/3604931 – volume: 18 start-page: 1637 issue: 6 year: 2024 ident: ref36 article-title: Construction and application of a water engineering scheduling knowledge graph based on large language models publication-title: Comput. Sci. Explor. – ident: ref43 doi: 10.1093/gji/ggae436 – ident: ref5 doi: 10.1016/j.knosys.2023.111323 – volume: 35 start-page: 1025 issue: 11 year: 2022 ident: ref17 article-title: Knowledge graph multi-hop reasoning model integrating semantic information publication-title: Pattern Recognit. Artif. Intell. – volume: 17 start-page: 2377 issue: 10 year: 2023 ident: ref11 article-title: Research on question answering systems integrating large language models and knowledge graphs publication-title: Comput. Sci. Explor. – volume: 48 start-page: 51 issue: 2 year: 2025 ident: ref18 article-title: Graph attention network representation learning algorithm based on adaptive differentiated graph convolution publication-title: Mod. Electron. Technol. – volume: 18 start-page: 2656 issue: 10 year: 2024 ident: ref33 article-title: Research on knowledge graph construction and application based on large language models publication-title: Comput. Sci. Explor. – year: 2022 ident: ref22 article-title: Impact of pretraining term frequencies on few-shot reasoning publication-title: arXiv:2202.07206 – start-page: 1 year: 2025 ident: ref40 article-title: Intelligent planning method of distribution network based on knowledge graph and graph convolutional neural network publication-title: Comput. Eng. – ident: ref2 doi: 10.1016/j.inffus.2020.03.014 – ident: ref29 doi: 10.1109/TNNLS.2021.3070843 – year: 2021 ident: ref25 article-title: LoRA: Low-rank adaptation of large language models publication-title: arXiv:2106.09685 – volume: 33 start-page: 111 issue: 1 year: 2010 ident: ref19 article-title: Preliminary study on classification of field information in earthquake emergency response publication-title: Seismological Res. – ident: ref30 doi: 10.1145/3544548.3581402 – volume: 64 start-page: 1228 issue: 8 year: 2024 ident: ref35 article-title: Automatic construction and retrieval technology of knowledge graph in the field of electronic information based on large models publication-title: Telecommun. Technol. – ident: ref16 doi: 10.1016/j.eswa.2019.112948 – volume: 2025 start-page: 1 year: 2025 ident: ref15 article-title: Research on the construction and application of knowledge graphs for typical emergency scenarios publication-title: J. Saf. Environ. – ident: ref31 doi: 10.3233/sw-180333
SSID	ssj0000816957
Score	2.3343444
Snippet	To address the challenges of semantic parsing of multi-source heterogeneous information and the delayed emergency response decisions caused by insufficient...
SourceID	doaj proquest crossref ieee
SourceType	Open Website Aggregation Database Index Database Publisher
StartPage	127742
SubjectTerms	Accuracy Attention Bi-GAT Cognition Correlation Data mining Disasters Earthquake construction Earthquakes Emergency management Emergency response Emergency services Feature extraction Knowledge Knowledge graphs Knowledge representation Large language models Matching Neo4j NLP PCCA Prompt engineering Semantics TPES-LLM
SummonAdditionalLinks	– databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV07SwQxEA4iFlqITzxfpLB0NbtJNkl5HqeCIhYKdiFPFGVPPbX1rzvJ7uqBhY3NFmFJNpnZmfmSzDcIHdQmsLIMojAAdQpWRVbYQH3BjJAqltyakBOFL8XVlby7U9czpb7SnbCWHrhduGPl6xhdpergKDjPqJgzgUjowpHK-py6R4SaAVPZBsuyVlx0NEMlUcfD0QhmBICw4keUy5qm8sQzrigz9nclVn7Z5exsTlfQchcl4mH7datoLjRraGmGO3AdffZ35vCkwRDF4VR6syeDxabxePhzNo0nEY9hrvcv7-Yx4HGfc4m7bKT8zkW_vYbPEos1PgEH51Pvl-m2ODzbnU2cyqc9TTfQ7en4ZnRedNUUCkfr8q0IkgUuiSc0eDCDtpZBKs69tFTGBMMqlo40DYMmb6lynFgmomO2qhygTLqJ5ptJE7YQpoREURoepRfMgM0TzBtPE1SyIN5ygA77hdXPLWmGzmCDKN3KQSc56E4OA3SSFv_71cR4nRtAD3SnB_ovPRigjSS6n_EA10KwSgdot5el7n7PqYYosobJg3fe_o-xd9Bimk-7M7OL5kHYYQ8tuI-3h-nrftbML44N6BA priority: 102 providerName: Directory of Open Access Journals
Title	Research on the Construction and Application of Earthquake Emergency Information Knowledge Graph Based on Large Language Models
URI	https://ieeexplore.ieee.org/document/11075653 https://www.proquest.com/docview/3246895801 https://doaj.org/article/9d6ffc296ec3439f94cae08aeec02bd9
Volume	13
WOSCitedRecordID	wos001544669800042&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: DOA dateStart: 20130101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: M~E dateStart: 20130101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PbxUhECa28aAHbbXG11_h4NFtdxdY4Pj68qpJa-NBk94IC0M0mn3qaz3af70zLNs2MR68kA1hdyHfAPMNzAxjbzoPsmlAVx6pTiXbJKseRKyk18amRvUesqPwub64MJeX9mNxVs--MACQL5_BET3ms_y4CtdkKjsmroIKiNhgG1p3o7PWnUGFMkhYpUtkoaa2x_PFAgeBHLBVR0KZTlBG4ge7Tw7SX7Kq_LUU5_3l9Pl_9myLPSuKJJ-PyG-zRzC8YE8fhBd8yW6ma3V8NXBU9Dhl55zixXI_RD6_P77mq8SXKEdffl77b8CXk1smLw5Luc3ZZIHj7yjQNT_BPTDS18_pQjmWo_GTU4a17-sd9vl0-WnxvioJF6oguuaqAiNBmTrWAiKulH1nwFiloumFScTUWkmnnl5iVeyFDarupU5B9m0bkIiKV2xzWA3wmnFR10k3XiUTtfS4LGoZfRTEpnqUgGbG3k5AuB9jXA2X-Uht3YibI9xcwW3GTgisu6YUFDtXIAquzDFnY5dSaG0HQaCelawMHmqD0hZwMNHO2A4hd_-_AtqM7U_YuzKD1w4VzQ4Hjxv47j9e22NPqIujPWafbSJ-cMAeh99XX9e_DjO5x_LDn-VhFtRbq6TmGw
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Nb9QwEB1BQQIOfBaxUMAHjqR1Yjuxj9vVlqIuKw5F6s1y7LFAoCywLVf-OmPHaSshDlyiKHISW2_smTf2zAC8aR3KusauckR1KtlEWfUoQiVdp02sVe8wBwqvuvVan52ZjyVYPcfCIGI-fIb76Tbv5YeNv0iusoPEVcgAETfhlpKy4WO41qVLJdWQMKoruYVqbg7miwUNg1hgo_aF0q1INYmv6Z-cpr_UVflrMc4a5ujBf_btIdwvpiSbj9g_ghs4PIZ71xIMPoHf08E6thkYmXos1eecMsYyNwQ2v9rAZpvIliRJn39cuK_IllNgJishS7nNyeSDY-9Sqmt2SFowpK-v0pFyuo7uT5ZqrH3b7sKno-Xp4rgqJRcqL9r6vEItUWkeuMBAa2XfatRGqaB7oWPiao1M-55O0qPQC-MV72UXveybxhMVFU9hZ9gM-AyY4Dx2tVNRh046Whg7GVwQiU_1JAP1DN5OQNjvY2YNmxkJN3bEzSbcbMFtBocJrMumKS12fkAo2DLLrAltjL4xLXpBllY00jvkmuTN02CCmcFuQu7qfwW0GexN2Nsyh7eWTM2WBk8q_Pk_XnsNd45PP6zs6v365AXcTd0dvTN7sENY4ku47X-df9n-fJUF9Q_uNec8
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Research+on+the+Construction+and+Application+of+Earthquake+Emergency+Information+Knowledge+Graph+Based+on+Large+Language+Models&rft.jtitle=IEEE+access&rft.au=Zhou%2C+Wentao&rft.au=Huang%2C+Meng&rft.au=Liu%2C+Shuai&rft.au=You%2C+Qiao&rft.date=2025&rft.pub=IEEE&rft.eissn=2169-3536&rft.volume=13&rft.spage=127742&rft.epage=127757&rft_id=info:doi/10.1109%2FACCESS.2025.3586370&rft.externalDocID=11075653
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2169-3536&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2169-3536&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2169-3536&client=summon