Implementasi Teknologi Cloud AI Google pada Sistem Informasi Konsultasi Karir Berbasis Website
DOI:
https://doi.org/10.29407/qbc82t90Keywords:
Chatbot, Fresh Graduate, Generative AI, Hybrid System, PHPAbstract
Lulusan baru (fresh graduate) sering menghadapi kecemasan dan kebingungan dalam menentukan arah karir, namun akses terhadap konselor karir profesional seringkali terbatas biaya dan waktu. Penelitian ini bertujuan merancang aplikasi chatbot konsultasi karir yang dapat memberikan respon cepat dan personal. Metode yang digunakan adalah pendekatan Hybrid, menggabungkan metode Rule Based untuk pertanyaan umum yang solusinya sudah pasti, dan Generative AI menggunakan Google Gemini API untuk pertanyaan yang membutuhkan analisis konteks lebih dalam. Aplikasi dibangun menggunakan bahasa pemrograman PHP Native dan database MySQL, dengan integrasi API model Gemini-2.5-flash. Hasil pengujian fungsional (Black Box Testing) menunjukkan sistem berjalan 100% valid sesuai skenario perancangan. Evaluasi kinerja menunjukkan keunggulan arsitektur hybrid, di mana solusi statis (Rule Based) memiliki rata-rata waktu respon <1 detik, sedangkan respon dinamis (Generative AI) membutuhkan waktu 3-5 detik. Pendekatan ini terbukti efisien dalam meminimalisir penggunaan token API dan latensi sistem, sekaligus menjaga fleksibilitas jawaban. Sistem ini diharapkan menjadi solusi alternatif bimbingan karir yang mudah diakses dan responsif.
Downloads
References
[1] S. H. Fazira, A. Handayani, dan F. W. Lestari, "Faktor Penyebab Quarter Life Crisis Pada Dewasa Awal," Jurnal Pendidikan dan Konseling (JPDK), vol. 5, no. 2, hal. 2227–2234, 2023.
[2] Badan Pusat Statistik, "Keadaan Ketenagakerjaan Indonesia Februari 2024," BPS, Jakarta, Berita Resmi Statistik No. 27/05/Th. XXVII, 2024.
[3] R. Y. Wardani, H. Hermanto, dan M. A. Arosyid, ""Merchan-Chat Bot": Teman Virtual AI Berbasis Android," Prosiding Seminar Nasional Teknologi dan Sains (STAINS), vol. 2, hal. 225-230, 2023.
[4] S. K. Ojha, A. Kumar, T. Bhole, dan S. Naaz, "Rule based AI chatbot," International Journal of Innovative Research in Technology (IJIRT), vol. 11, no. 5, hal. 639-646, 2024.
[5] Google DeepMind, "Gemini: A Family of Highly Capable Multimodal Models," Google DeepMind Technical Report, 2023. [Online]. Tersedia: https://arxiv.org/abs/2312.11805.
[6] M. Z. N. Al-Imran, "Penerapan Metode Hybrid Pada Chatbot Layanan Akademik," Jurnal Teknologi Informasi, vol. 7, no. 2, hal. 101-110, 2022.
[7] The PHP Group, "PHP: cURL - Manual," 2024. [Online]. Tersedia: https://www.php.net/manual/en/book.curl.php. [Diakses: 17-Des-2025].
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Aldestra Bagus Wardana
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
