| Row ID | Full name in Chinese/中文全名 | Full name in English/英文全名 | Gender/性別 | Current Year of Study/目前就讀的年級 |
|---|---|---|---|---|
| 1 | 張芷琪 | Zhang Tsz Ki | Female/女性 | Grade 9 (Secondary 3)/中學九年級（中三） |
| 2 | 戴箏 | Dai Zheng | Female/女性 | Grade 9 (Secondary 3)/中學九年級（中三） |
| 3 | 鄭安生 | Cheng Anson | Female/女性 | Grade 8 (Secondary 2)/中學八年級（中二） |
In today’s society, many young individuals may feel the impulse to experiment with drugs for various reasons, including peer pressure, the desire to fit in, or a need for relaxation. As secondary students ourselves, we have come to realise the many temptations that draw us to taking an unhealthy path.
Perhaps many of us already understand the consequences: the detrimental impact on our health, the strain it puts between interpersonal relationships, the loss of interest in academic and worldly pursuits. However, the knowledge of drugs alone is already a wide topic by itself; not all of us have the necessary knowledge to distinguish and identify harmful substances. So what could be a portable, private and reliable tool us teenagers can rely on?
VBesties consists of three 3D virtual friends, for you to carry and speak to anytime, anywhere. Combining AI with gameplay, our 3D characters act as students, complete with uniforms and distinctive speaking styles. Users simply need to converse to the VBesties as if it is a normal occasion. They are friendly and supportive, always ready to help you tackle your questions.
With Unity as a primary interface, we fed LLMs with databases related to drug knowledge and its prevention. These are done in both question-and-answer pairs and plain texts, ensuring accurate responses. The user’s words will be transferred via speech-to-text function, prompting the LLM to generate a response. Speech-to-text is achieved through Oration, where voice recognition is transcripted. The response will be then spoken via text-to-speech function by the virtual friends. To give a more natural environment for user experience, each 3D character’s AI model will also interact with each other. Each 3D character is uniquely rendered with Vroid. Adobe Mixamo is also used for animating these characters so users will feel more at ease when interacting. Components from Hugging Face are also used to facilitate emotion recognition and stress detection, which can respond to the user’s needs efficiently.
Knowledge of drugs and its prevention is often acquired through books or lectures delivered in school: which is sometimes not engaging enough for the teenagers to fully understand. Our solution, however, builds an interactive environment and graphic details which will appeal to teens.
Privacy is also valued among teens: if we have any issues relating to drug usage, we are often advised to seek counselors. Teens often dislike this, however, leading them not to have enough professional support. While AI is not enough a substitute for professional support, it still at least resolves some questions the teens might have: thereby lowering the risks. Its portability and convenience will also be one of the reasons.
We have also invited students to fill in questionnaires before and after the making of our prototype. 58.8% were very satisfied with how VBesties turned out, with another 32.4% benign satisfied, noting how it educated them more on the scientific side of drug usage, and stopped any temptation that might have curdled up inside them. This proves promising: not only is VBesties uncomplicated to implement, its initial draft also proves that it has a lot of potential to eventually solve the issue at hand.
Personal Information Collection Statement (PICS)/收集個人資料聲明:
1. The personal data collected in this form will be used for activity-organizing, record keeping and reporting only. The collected personal data will be purged within 6 years after the event.
2. Please note that it is obligatory to provide the personal data required.
3. Your personal data collected will be kept by the LTTC and will not be transferred to outside parties.
4. You have the right to request access to and correction of information held by us about you. If you wish to access or correct your personal data, please contact our staff at lttc@eduhk.hk.
5. The University’s Privacy Policy Statement can be access at https://www.eduhk.hk/en/privacy-policy.
- I have read and agree to the competition rules and privacy policy/我已閱讀並同意比賽規則和隱私權政策。