MATCHFAI: Sistema de recomendação híbrido de músicas usando inteligência artificial generativa e agentes inteligentes, 2024
| dc.contributor.advisor | Silva, Fábio Santos da | |
| dc.contributor.advisor-lattes | http://lattes.cnpq.br/5711873110376600 | |
| dc.contributor.author | Boadana, Ronald Carvalho | |
| dc.contributor.author-lattes | http://lattes.cnpq.br/7886307507641530 | |
| dc.contributor.referee1 | Silva, Fábio Santos da | |
| dc.contributor.referee2 | Figueiredo, Carlos Mauricio Serodio | |
| dc.contributor.referee3 | Melo, Tiago Eugenio de | |
| dc.date.accessioned | 2025-08-29T19:43:17Z | |
| dc.date.issued | 2025-09-05 | |
| dc.description.abstract | This work explores the use of Large Language Models (LLMs) in a hybrid music recommendation system, combined with artificial intelligence agents, presenting a new approach to music recommendation. The proposed architecture includes various agents to perform hybrid filtering, combining content-based and collaborative filtering, along with other support agents. Several LLMs, such as Gemini, LLaMA, and Mixtral, are employed as recommendation engines. The final results show that the Gemini 1.5 Pro model achieved the best performance among the evaluated models, based on data obtained from user testing. | |
| dc.description.resumo | Este trabalho explora o uso de grandes modelos de linguagem (large language models, em inglês - LLMs) um sistema de recomendação de músicas híbrido, juntamente com agentes de inteligência artificial, apresentando uma nova abordagem para recomendação musical. A proposta inclui uma arquitetura que utiliza diversos agentes para realizar uma filtragem híbrida, combinando filtragem baseada em conteúdo e colaborativa, além de outros agentes de suporte. Diversos LLMs, como Gemini, LLaMA e Mixtral, são empregados como motores de recomendação. Os resultados finais demonstram que o modelo Gemini 1.5 Pro apresentou o melhor desempenho entre os modelos avaliados, conforme os dados obtidos por meio de testes realizados com os usuários. | |
| dc.identifier.citation | BOADANA, Ronald Carvalho. MATCHFAI: Sistema de recomendação híbrido de músicas usando inteligência artificial generativa e agentes inteligentes, Manaus, 2024. 127 f. TCC- (Graduação em Engenharia da Computação) – Universidade do Estado do Amazonas. Escola Superior de Tecnologia. | |
| dc.identifier.uri | https://ri.uea.edu.br/handle/riuea/7827 | |
| dc.publisher | Universidade do Estado do Amazonas | |
| dc.publisher.initials | UEA | |
| dc.relation.references | ACHARYA, A.; SINGH, B.; ONOE, N. Llm based generation of item-description for recommendation system. RecSys ’23: Proceedings of the 17th ACM Conference on Recommender Systems, 2023. ANACONDA. Anaconda | The Operating System for AI. 2024. <https://www.anaconda.com/>. Acesso em: 24/11/2024. APPLE. Apple Music - Apple (BR). 2024. <https://www.apple.com/br/apple-music/>.Acesso em: 05/05/2024. AWS. Amazon EC2 tipos de instâncias - AWS. 2023. <https://aws.amazon.com/pt/ec2/instance-types/>. Acesso em: 13/07/2024. BROWN, S. The C4 model for visualising software architecture. 2024. <https://c4model.com/>. Acesso em: 07/05/2024. CHEN, H. et al. Chatgpt’s one-year anniversary: are open-source large language models catching up? arXiv preprint arXiv:2311.16989, 2023. CREWAI. crewAI - Platform for Multi AI Agents Systems. 2024. <https://www.crewai.com/>.Acesso em: 13/07/2024. CREWAI. crewAI Agents - crewAI. 2024. <https://docs.crewai.com/core-concepts/Agents/#what-is-an-agent>. Acesso em: 13/07/2024. CREWAI. crewAI Tasks - crewAI. 2024. <https://docs.crewai.com/core-concepts/Tasks/>.Acesso em: 13/07/2024. CRFM, S. Stanford CRFM. 2023. <https://crfm.stanford.edu/2023/03/13/alpaca.html>.Acesso em: 07/05/2024. DAI s. et al. Uncovering chatgpt’s capabilities in recommender systems. RecSys ’23: Proceedings of the 17th ACM Conference on Recommender Systems, 2023. DEEZER. Deezer | Ouvir musica online | Aplicativo para escutar musica. 2024.<https://www.deezer.com/br/>. Acesso em: 05/05/2024. DJANGO. The web framework for perfectionists with deadlines | Django. 2024. <https://www.djangoproject.com/>. Acesso em: 24/11/2024. ELAHI, M. et al. Hybrid recommendation by incorporating the sentiment of product reviews. Informatics and Computer Science Intelligent Systems Applications An International Journal, 2023. FIGMA. Figma: a ferramenta de design de interface colaborativa. 2024. <https://www.figma.com/pt-br/>. Acesso em: 25/11/2024. GOLDBERG, Y. Neural network methods for natural language processing. [S.l.]: Synthesis Lectures on Human Language Technologies, 2017. GOOGLE. Gemini - Google DeepMind. 2024. <https://deepmind.google/technologies/gemini/#introduction>. Acesso em: 07/05/2024. GOURLEY, D. et al. HTTP: The Definitive Guide. 1st. ed. [S.l.]: O’Reilly Media, 2002. HUA, W. et al. Tutorial on large language models for recommendation. RecSys ’23: Proceedings of the 17th ACM Conference on Recommender Systems, 2023. INGELMO, V. et al. C4 model in a software engineering subject to ease the comprehension of uml and the software. In: 2020 IEEE Global Engineering Education Conference (EDUCON).[S.l.: s.n.], 2020. p. 919–924. JANNACH, D.; ZANKER, M.; FELFERNIG, A. Recommender Systems: An Introduction.1st. ed. [S.l.]: Cambridge University Press, 2010. JIANG, A. Q. et al. Mistral 7B. arXiv, 2023. JIN, B.; SAHIN, S.; SHEVAT, A. Designing Web APIs: Building APIs that Developers Love.[S.l.]: O’Reilly Media, 2018. JJ, G.; JON, S. API Design Patterns. [S.l.]: Manning Publications Co., 2021. KUROSE, K. R. J. Redes de computadores e a Internet: uma abordagem top-down. 6th. ed. [S.l.]: Pearson Education do Brasil, 2013. LANGCHAIN. Defining Custom Tools - LangChain. 2024. <https://python.langchain.com/v0.1/docs/modules/tools/custom tools/>. Acesso em: 13/07/2024. LANGCHAIN. Defining Custom Tools | Langchain. 2024. <https://python.langchain.com/v0.1/docs/modules/tools/custom tools/>. Acesso em: 20/11/2024. LANGCHAIN. GoogleAI - LangChain. 2024. <https://python.langchain.com/v0.2/docs/integrations/llms/google ai/>. Acesso em: 13/07/2024. LANGCHAIN. Groq - LangChain. 2024. <https://python.langchain.com/v0.2/docs/integrations/chat/groq/>. Acesso em: 13/07/2024. LAST.FM. Página Inicial | Last.fm. 2024. <https://www.last.fm/pt/home>. Acesso em:05/05/2024. MCDONALD, D.; PAPADOPOULOS, R.; BENNINGFIELD, L. Reducing llm hallucination using knowledge distillation: A case study with mistral large and mmlu benchmark. Authorea Preprints, Authorea, 2024. META. Meta Llama. 2024. <https://llama.meta.com/>. Acesso em: 07/05/2024. META. Meta Llama 3. 2024. <https://llama.meta.com/llama3/>. Acesso em: 15/07/2024. MISTRAL. Mistral AI | Frontier AI in your hands. 2024. <https://mistral.ai/>. Acesso em: 07/05/2024. MONGODB. Modelagem de dados | Manual do MongoDB v8.0. 2024. <https://www.mongodb.com/pt-br/docs/manual/data-modeling/#std-label-manual-data-modeling-intro>.Acesso em: 21/11/2024. MONGODB. MongoDB: a plataforma de dados para desenvolvedores | MongoDB. 2024.<https://www.mongodb.com/pt-br>. Acesso em: 17/11/2024. NPM. node-cron - npm. 2024. <https://www.npmjs.com/package/node-cron>. Acesso em:25/11/2024. OPENAI. GPT3 powers the next generation of apps | OpenAI. 2024. <https://openai.com/index/gpt-3-apps>. Acesso em: 07/05/2024. PANDAS. pandas - Python Data Analysis Library. 2024. <https://pandas.pydata.org/>.Acesso em: 13/07/2024. PEEPERKORN, M. et al. Is Temperature the Creativity Parameter of Large Language Models? 2024. Disponível em: <https://arxiv.org/abs/2405.00492>. POTDAR, A. M. et al. Performance evaluation of docker container and virtual machine. Procedia Computer Science, Elsevier, v. 171, p. 1419–1428, 2020. RUAN, J. et al. TPTU: Large language model-based AI agents for task planning and tool usage. arXiv, 2023. RUSSELL, J.; NORVIG, P. Artificial Intelligence - A Modern Approach. 4th. ed. [S.l.]: GEN LTC, 2022. SHARMA, L.; GERA, A. A survey of recommendation system: Research challenges. International Journal of Engineering Trends and Technology (IJETT), v. 4, n. 5, p. 1989–1992, 2013. SPOTIFY. Entenda as recomendações no Spotify. 2024. <https://www.spotify.com/br-pt/safetyandprivacy/understanding-recommendations>. Acesso em: 05/05/2024. SPOTIFY. Spotify Web Player. 2024. <https://open.spotify.com/intl-pt>. Acesso em:05/05/2024. TEAM, G. et al. Gemini: A Family of Highly Capable Multimodal Models. 2024. Disponível em: <https://arxiv.org/abs/2312.11805>. TEAM, G. et al. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. 2024. Dispon´ıvel em: <https://arxiv.org/abs/2403.05530>. TIDAL. TIDAL - High Fidelity Music Streaming. 2024. <https://tidal.com/>. Acesso em: 05/05/2024. TOUVRON, H. et al. LLaMA: Open and efficient foundation language models. arXiv, 2023. WEIHS, C. et al. Music Data Analysis: Foundations and Applications. 1st. ed. [S.l.]: CRC Press, 2017. WU, D. Music personalized recommendation system based on hybrid filtration. In: 2019 International Conference on Intelligent Transportation, Big Data & Smart City (ICITBS).[S.l.]: IEEE, 2019. WU, L. et al. A survey on evaluation of large language models. ACM Transactions on Intelligent Systems and Technology, 2024. ZHAO, Z. et al. Recommender systems in the era of large language models (LLMs). IEEE Trans. Knowl. Data Eng., Institute of Electrical and Electronics Engineers (IEEE), p. 1–20, 2024. | |
| dc.rights | Attribution-NonCommercial-NoDerivs 3.0 United States | en |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/3.0/us/ | |
| dc.subject | Large Language Models | |
| dc.subject | Agentes Inteligentes. | |
| dc.subject | Inteligência Artificial | |
| dc.subject | Sistemas de Recomendação | |
| dc.title | MATCHFAI: Sistema de recomendação híbrido de músicas usando inteligência artificial generativa e agentes inteligentes, 2024 | |
| dc.type | Trabalho de Conclusão de Curso |
Arquivos
Pacote original
1 - 1 de 1
Carregando...
- Nome:
- Inteligencia_Artificial_Linguagens_Sistema_Recomendação.pdf
- Tamanho:
- 3.33 MB
- Formato:
- Adobe Portable Document Format