Recommendation Algorithm Based on Knowledge Graph to Propagate User Preference

Yang, Zhisheng; Cheng, Jinyong

doi:10.2991/ijcis.d.210503.001

Cited by 14 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Knowledge graphs helped the model learn the needs and interests of consumers to provide personalized experience to them. According to the test results, this new method can provide better recommendations of movies, books or music [ 8 ]. Liang and Yin found that there is a poor balance of recommended resources and low trustworthiness of recommended content in traditional sports network multimedia teaching platform system.…”

Section: Literature Reviewmentioning

confidence: 99%

Application of KL distance-based intelligent recommendation method to fund recommendation for users with investment behavior in Asia Region

Chiou-Wei,

Lee

2024

Heliyon

View full text Add to dashboard Cite

Section: Literature Reviewmentioning

confidence: 99%

Application of KL distance-based intelligent recommendation method to fund recommendation for users with investment behavior in Asia Region

Chiou-Wei,

Lee

2024

Heliyon

View full text Add to dashboard Cite

“…It is assumed, there are a total of five pieces of music in the database, the candidate item sets obtained from scanning will contain five items. Moreover, the support of each item is computed [12]:…”

Section: A Music Recommendation Algorithm Based On Associationmentioning

confidence: 99%

Personalized Music Recommendation Based on Interest and Emotion: A Comparison of Multiple Algorithms

Yan¹

2023

IJACSA

View full text Add to dashboard Cite

Recommendation algorithms can greatly improve the efficiency of information retrieval for users. This article briefly introduced recommendation algorithms based on association rules and algorithms based on interest and emotion analysis. After crawling music and comment data from the NetEase Cloud platform, a simulation experiment was conducted. Firstly, the performance of the Back-Propagation Neural Network (BPNN) in the interest and emotion-based algorithm for recommending music was tested, and then the impact of the proportion of emotion weight between comments and music on the emotion analysis-based algorithm was tested. Finally, the three recommendation algorithms based on association rules, user ratings, and interest and emotion analysis were compared. The results showed that when the BPNN used the dominant interest and emotion and secondary interest and emotion as judgment criteria, the accuracy of interest and emotion recognition for music and comments was higher. When the proportion of interest and emotion weight between comments and music was 6:4, the interest and emotion analysis-based recommendation algorithm had the highest accuracy. The interest and emotion-based recommendation algorithm had higher recommendation accuracy than the association rule-based and user rating-based algorithms, and could provide users with more personalized and emotional music recommendations.

show abstract

“…The RippleNet model uses the user's historical preferences as a seed set and iteratively calculates the interest set of the first k neighborhood through the meta-paths in the knowledge graph to achieve the simulation of the user's interest propagation. The inputs to the model are user u and item v output is the predicted probability of that user clicking on item v [30].…”

Section: Step2 Calculate the Initial Similarity Between Clustersmentioning

confidence: 99%

Research and Practice of Digital Training Model Based on Artificial Intelligence Technology

Duan

2023

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

There are fatal defects in both the simulation practical training model and the actual combat practical training model. This paper firstly takes artificial intelligence technology as the basis for the construction of digital wisdom training classrooms and constructs the artificial intelligence digital wisdom training model. Secondly, it combines multi-factor reasoning and integrated clustering ideas to portray the vocational ability portrait of the learner group in the model and realizes the recommendation of students’ personalized training teaching resources with the learner’s portrait. Finally, the effectiveness is verified through the application practice of the digital training model for AI in higher vocational colleges. The results show that the use of multi-factor reasoning and integrated clustering can realize the accurate portrayal of the learner portrait of the digital intelligent training students and the difference between the loss value of the training and validation of the personalized recommendation model based on the learner portrait is about 0.01, and the average time consumed is about 1.05s. The digital training model supported by artificial intelligence technology can help students establish higher-order scientific thinking, promote students’ mastery of skills, and fully compensate for the shortcomings of the existing practical training model.

show abstract

Recommendation Algorithm Based on Knowledge Graph to Propagate User Preference

Cited by 14 publications

References 26 publications

Application of KL distance-based intelligent recommendation method to fund recommendation for users with investment behavior in Asia Region

Application of KL distance-based intelligent recommendation method to fund recommendation for users with investment behavior in Asia Region

Personalized Music Recommendation Based on Interest and Emotion: A Comparison of Multiple Algorithms

Research and Practice of Digital Training Model Based on Artificial Intelligence Technology

Contact Info

Product

Resources

About