| I&T Solution |
Lift and Escalator Reportable Incidents extraction and analysis system
(REF: S-0771) |
| Matched I&T Wish |
|
| Trial Project |
|
| Solution Feature |
- The system will apply orientation, brightness and contrast visual tuning on the images whenever necessary to improve the OCR performance.
- The system will provide an OCR and NLP function, supporting Traditional and Simplified Chinese and English in both typed or handwritten form, to recognize texts filled in predefined form fields in scanned images and output digital texts filled in corresponding fields.
- The system will apply NLP techniques to extract information from texts in sentence and paragraph form into predefined fields with predefined categories. The output could be further analyzed with text categorization to output categorical results.
- This system (the “Revision System”) allows users to review and manually revise the output of the AI System through a user-friendly graphical interface.
- Users will be able to export the analysis of data from a predefined time-range into a summary report, including both data visualization and descriptive reports in PDF format.
|
| Trial Application and Expected Outcome |
- EMSD to share actual report documents for AI model training.
- Separate testing datasets for testing the accuracy of trained AI model on extraction results.
|
| Additional Solution Information |
Solution Introduction - Analysis of Lift and Escalator Reportable Incidents.pdf
|
| Info on I&T Solution Provider |
| Solution Provider | : | Datax Limited | | Address | : | Unit 708, Data Technology Hub, 5 Chun Cheong Street, Tseung Kwan O, Hong Kong | | Contact Person | : | Aric Fung |
| Position | : | Account Director | | Tel | : | 9143 8473 | | Email | : |
aric.fung@datax.io | | Webpage | : | https://datax.io |
|
