|
|
--- |
|
|
language: |
|
|
- vi |
|
|
- en |
|
|
tags: |
|
|
- sentence-transformers |
|
|
- text-embeddings |
|
|
- taxi-pricing |
|
|
- vietnamese |
|
|
license: apache-2.0 |
|
|
datasets: |
|
|
- custom-taxi-data |
|
|
model-index: |
|
|
- name: ETO-TAXI Pricing Model |
|
|
results: [ ] |
|
|
--- |
|
|
|
|
|
# ETO520 Pricing Model |
|
|
|
|
|
## Model Description |
|
|
|
|
|
Model is trained on [ETO-TAXI Pricing Model and Route Dataset](https://github.com/tkvclub01/eto-api) |
|
|
|
|
|
## Developed by |
|
|
|
|
|
**Công Ty CP DV VT My Sơn** |
|
|
Author: THÀNH TÂN |
|
|
Email: [email protected] |
|
|
Website: https://675.vn |
|
|
|
|
|
## Intended Uses & Limitations |
|
|
|
|
|
This model is intended for: |
|
|
|
|
|
- Extracting location information from Vietnamese text |
|
|
- Calculating similarity between locations |
|
|
- Pricing estimation for taxi services |
|
|
|
|
|
## How to Use |
|
|
|
|
|
python |
|
|
`from sentence_transformers import SentenceTransformer |
|
|
Load the model |
|
|
model = SentenceTransformer("icoquangninh/eto-taxi-model") |
|
|
Generate embeddings |
|
|
embeddings = model.encode(["Nhà hàng ABC", "Khách sạn XYZ"]) |
|
|
Calculate similarity |
|
|
from sklearn.metrics.pairwise import cosine_similarity similarity = cosine_similarity([embeddings[0]], [embeddings[1]])` |
|
|
|
|
|
## Training Data |
|
|
|
|
|
The model was trained on Vietnamese taxi booking data to understand location names and pricing contexts. |
|
|
|
|
|
## Evaluation Results |
|
|
|
|
|
The model achieves good performance on Vietnamese text understanding tasks related to taxi services. |
|
|
|
|
|
## Intended Uses & Limitations |
|
|
|
|
|
This model is intended for: |
|
|
|
|
|
- Extracting location information from Vietnamese text |
|
|
- Calculating similarity between locations |
|
|
- Pricing estimation for taxi services |
|
|
|
|
|
Limitations: |
|
|
|
|
|
- Model is specifically trained for Vietnamese language |
|
|
- Performance may vary for locations outside Vietnam |
|
|
- Pricing estimations are based on historical data patterns |
|
|
|
|
|
## Training Data |
|
|
|
|
|
The model was trained on Vietnamese taxi booking data to understand location names and pricing contexts. The training data includes: |
|
|
|
|
|
- Vietnamese location names and addresses |
|
|
- Taxi route information |
|
|
- Pricing data for various distances |
|
|
|
|
|
## Evaluation Results |
|
|
|
|
|
The model achieves good performance on Vietnamese text understanding tasks related to taxi services with high accuracy in location name recognition and similarity calculation. |
|
|
|
|
|
## Applications |
|
|
|
|
|
This model can be used for: |
|
|
|
|
|
1. Location-based search in taxi booking applications |
|
|
2. Route optimization and pricing calculation |
|
|
3. Similar location recommendation |
|
|
4. Customer service automation for taxi companies |
|
|
|
