Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Alliance Grants

University of Calgary

$25,000.00

Topology Understanding by Large Language Models on Simplified Maps

EF 2023-24

Résumé
The proposed international collaboration project aims to improve the topological understanding on a simplified map, which help develop a Multimodal Large Language Model (MLLM) agent as to identify and interpret Point Of Interest (POI) through visual and textual information and generate text for a routes between locations. Leveraging their natural language processing, contextual analysis, data integration, and personalization capabilities, the project seeks to interpret user queries effectively, consider contextual factors, integrate diverse data sources, and tailor recommendations to individual preferences. By processing geospatial information, generating natural language descriptions, and continuously improving through user feedback and new data, the project aims to deliver more relevant, accurate, and user-friendly location recommendations, ultimately contributing to improved map understanding and enriched user experiences. This project will involve computer vision, natural language processing (NLP), and possibly graph neural networks to understand and reason about the spatial relationships encoded within these maps. The Catalyst grant will initiate collaboration on this project among the University of Calgary, University of Minnesota, and University of California, Davis in United States. It will enable preliminary study of the understanding topology relationships from maps for LLMs to be conducted by HQPs and PIs in three universities. The proposed project could benefit Canada and the USA in multiple ways. It aims to enhance location recommendations and map understanding, benefiting residents and travelers through personalized suggestions for places to visit, dine, shop, or explore. This could improve navigation experiences and increase satisfaction. Businesses in tourism, hospitality, and retail may gain from targeted recommendations, boosting foot traffic, engagement, and revenue. Furthermore, leveraging geospatial data could aid urban planning, transportation optimization, and disaster response, fostering more efficient and resilient communities.
Programme
Alliance Grants
Bénéficiaire
Emplacement
Alberta, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
592368-2023
Name nom
Wang, Xin X
Department département
Geomatics Engineering
Organization id
11
Institution établissement
University of Calgary
Province en
Alberta
Province fr
Alberta
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2023
Competition year année de concours
2023
Award amount
25000
Program id
ALLRP
Program name en
Alliance Grants
Program name fr
Subventions Alliance
Group en
RESEARCH PARTNERSHIPS
Group fr
PARTENARIATS DE RECHERCHE
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
1207
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Information, computer and communication technologies
Area of application fr
Technologie de l'information, des ordinateurs et des réseaux de communications
Research subject code
2800
Research subject group en
Artificial intelligence
Research subject group fr
Artificial intelligence (computer vision, use2603)
Research subject en
Intelligence artificielle
Research subject fr
Intelligence artificielle (vision artificielle, utiliser 2603)
Application title
Topology Understanding by Large Language Models on Simplified Maps
Keyword
Large Language Model; Spatial relationships; Topology
Application summary
The proposed international collaboration project aims to improve the topological understanding on a simplified map, which help develop a Multimodal Large Language Model (MLLM) agent as to identify and interpret Point Of Interest (POI) through visual and textual information and generate text for a routes between locations. Leveraging their natural language processing, contextual analysis, data integration, and personalization capabilities, the project seeks to interpret user queries effectively, consider contextual factors, integrate diverse data sources, and tailor recommendations to individual preferences. By processing geospatial information, generating natural language descriptions, and continuously improving through user feedback and new data, the project aims to deliver more relevant, accurate, and user-friendly location recommendations, ultimately contributing to improved map understanding and enriched user experiences. This project will involve computer vision, natural language processing (NLP), and possibly graph neural networks to understand and reason about the spatial relationships encoded within these maps. The Catalyst grant will initiate collaboration on this project among the University of Calgary, University of Minnesota, and University of California, Davis in United States. It will enable preliminary study of the understanding topology relationships from maps for LLMs to be conducted by HQPs and PIs in three universities. The proposed project could benefit Canada and the USA in multiple ways. It aims to enhance location recommendations and map understanding, benefiting residents and travelers through personalized suggestions for places to visit, dine, shop, or explore. This could improve navigation experiences and increase satisfaction. Businesses in tourism, hospitality, and retail may gain from targeted recommendations, boosting foot traffic, engagement, and revenue. Furthermore, leveraging geospatial data could aid urban planning, transportation optimization, and disaster response, fostering more efficient and resilient communities.