FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4229016850> ?p ?o ?g. }

• W4229016850 endingPage "11" @default.
• W4229016850 startingPage "1" @default.
• W4229016850 abstract "On the basis of the analysis of the evolution dynamics and the process of smart tourism service, this paper constructs the evolutionary game model of smart tourism service and reveals the evolution mechanism of smart tourism service based on the network platform. Based on the strategic main line of “advantages,” it proposes the design ideas and overall framework of the smart tourism service model based on the network platform, including the smart tourism information interactive service model, the element collaborative service model, and the value cocreation service model. The comparison of recommendation results shows that the recommendation error of the genetically improved generalized regression neural network algorithm is reduced, and the recommendation accuracy is better than that of the unimproved generalized regression neural network algorithm. In the recommendation scenario of click-through rate recommendation, the existing recommendation models are difficult to meet the functions of memory and generalization at the same time and cannot fully mine and combine low-level features, and the model parameters of the deep learning model are difficult to learn under the high-dimensional sparse data set of the recommendation system. To solve the problem of generalization, this paper proposes a deep CTR recommendation model based on the gradient boosting tree and factorization machine. It can fully mine low-level feature information and automatically realize low-level feature combination, which can better learn model parameters on high-dimensional sparse data sets, and the recommendation results are no longer overgeneralized. In this paper, simulation experiments are carried out on the data set, and the related recommendation models are compared. The experimental results show that the model proposed in this paper achieves better results in both the AUC (area under ROC curve) evaluation index and the cross-entropy evaluation index." @default.
• W4229016850 created "2022-05-08" @default.
• W4229016850 creator A5018329083 @default.
• W4229016850 date "2022-05-05" @default.
• W4229016850 modified "2023-09-27" @default.
• W4229016850 title "Implementation of Personalized Scenic Spot Recommendation Algorithm Based on Generalized Regression Neural Network for 5G Smart Tourism System" @default.
• W4229016850 cites W2748880077 @default.
• W4229016850 cites W2772907995 @default.
• W4229016850 cites W2780723616 @default.
• W4229016850 cites W2802138086 @default.
• W4229016850 cites W2890570516 @default.
• W4229016850 cites W2939270215 @default.
• W4229016850 cites W2942534105 @default.
• W4229016850 cites W2944425798 @default.
• W4229016850 cites W2970036099 @default.
• W4229016850 cites W2973030310 @default.
• W4229016850 cites W2981975915 @default.
• W4229016850 cites W3000235295 @default.
• W4229016850 cites W3026594440 @default.
• W4229016850 cites W3035574535 @default.
• W4229016850 cites W3093135286 @default.
• W4229016850 cites W3094267028 @default.
• W4229016850 cites W3136239617 @default.
• W4229016850 cites W3153685513 @default.
• W4229016850 cites W3162663167 @default.
• W4229016850 cites W3167165556 @default.
• W4229016850 cites W3176764349 @default.
• W4229016850 cites W3211945130 @default.
• W4229016850 cites W4210916485 @default.
• W4229016850 doi "https://doi.org/10.1155/2022/3704494" @default.
• W4229016850 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35571704" @default.
• W4229016850 hasPublicationYear "2022" @default.
• W4229016850 type Work @default.
• W4229016850 citedByCount "1" @default.
• W4229016850 countsByYear W42290168502022 @default.
• W4229016850 crossrefType "journal-article" @default.
• W4229016850 hasAuthorship W4229016850A5018329083 @default.
• W4229016850 hasBestOaLocation W42290168501 @default.
• W4229016850 hasConcept C119857082 @default.
• W4229016850 hasConcept C124101348 @default.
• W4229016850 hasConcept C134306372 @default.
• W4229016850 hasConcept C136264566 @default.
• W4229016850 hasConcept C138885662 @default.
• W4229016850 hasConcept C154945302 @default.
• W4229016850 hasConcept C162324750 @default.
• W4229016850 hasConcept C177148314 @default.
• W4229016850 hasConcept C21569690 @default.
• W4229016850 hasConcept C2776401178 @default.
• W4229016850 hasConcept C2780378061 @default.
• W4229016850 hasConcept C33923547 @default.
• W4229016850 hasConcept C41008148 @default.
• W4229016850 hasConcept C41895202 @default.
• W4229016850 hasConcept C50644808 @default.
• W4229016850 hasConcept C557471498 @default.
• W4229016850 hasConceptScore W4229016850C119857082 @default.
• W4229016850 hasConceptScore W4229016850C124101348 @default.
• W4229016850 hasConceptScore W4229016850C134306372 @default.
• W4229016850 hasConceptScore W4229016850C136264566 @default.
• W4229016850 hasConceptScore W4229016850C138885662 @default.
• W4229016850 hasConceptScore W4229016850C154945302 @default.
• W4229016850 hasConceptScore W4229016850C162324750 @default.
• W4229016850 hasConceptScore W4229016850C177148314 @default.
• W4229016850 hasConceptScore W4229016850C21569690 @default.
• W4229016850 hasConceptScore W4229016850C2776401178 @default.
• W4229016850 hasConceptScore W4229016850C2780378061 @default.
• W4229016850 hasConceptScore W4229016850C33923547 @default.
• W4229016850 hasConceptScore W4229016850C41008148 @default.
• W4229016850 hasConceptScore W4229016850C41895202 @default.
• W4229016850 hasConceptScore W4229016850C50644808 @default.
• W4229016850 hasConceptScore W4229016850C557471498 @default.
• W4229016850 hasLocation W42290168501 @default.
• W4229016850 hasLocation W42290168502 @default.
• W4229016850 hasLocation W42290168503 @default.
• W4229016850 hasOpenAccess W4229016850 @default.
• W4229016850 hasPrimaryLocation W42290168501 @default.
• W4229016850 hasRelatedWork W1773619406 @default.
• W4229016850 hasRelatedWork W2075040002 @default.
• W4229016850 hasRelatedWork W2126026531 @default.
• W4229016850 hasRelatedWork W2348159088 @default.
• W4229016850 hasRelatedWork W2356507104 @default.
• W4229016850 hasRelatedWork W2377968345 @default.
• W4229016850 hasRelatedWork W2402445420 @default.
• W4229016850 hasRelatedWork W2514833639 @default.
• W4229016850 hasRelatedWork W2573253449 @default.
• W4229016850 hasRelatedWork W2974025129 @default.
• W4229016850 hasVolume "2022" @default.
• W4229016850 isParatext "false" @default.
• W4229016850 isRetracted "false" @default.
• W4229016850 workType "article" @default.