Domains π
Blurbs π€
Comments: looks good. Thereβs a lot here technically so I need to work out what features are shared amongst all of these and which ones are unique/ need to be built. Then we prioritise build against what clients we want/ have access to
@Corey Parkinson Okay! Will put it on the website and we can edit as we go⦠let me know if there is anything you ABSOLUTELY DO NOT want to be shared. But at this point in time I think we put it up there, and take down when needed.
Starting transfer of the script now. Format has all been designed and implemented.
Okay- nice one!
Tech:
Models:
-Decoding video to a select number of frames which can be ingested by our CNN model
-Created a CNN model to identify key malicious content (certain % of skin, children, negative gestures)
-API
Portal
-
Results Page
- A table with all videos/images and their Priority
- Priority is based on the level of severity which can be set by cleints
- Filter by priority and also the different malicious content e.g filter swearing/nudity etc
- Dashboard view
- Number of flagged videos in past 30 days / 7 days
- Pie chart of malicious content breakdown
- Total number of videos processed.
- Number of flagged malicious videos.
- Percentage of videos flagged.
- Real-time Monitoring:
- Live feed of videos being processed.
- Highlight flagged videos for quick attention.
- Severity Level:
- Categorise malicious content by severity (e.g., low, medium, high).
- Visual indicators for severity levels.
- Geographical Distribution:
- Map showing the geographical distribution of flagged videos.
-
Analytics Page
- Trend Analysis:
- Historical data on the frequency of malicious content over time.
- Identify patterns or spikes in malicious content.
- Content Types:
- Breakdown of malicious content by types (e.g., violent, explicit, hate speech).
- Analysis of the most prevalent types of malicious content.
- User Patterns:
- Identify users who frequently upload malicious content.
- Analyze user behavior patterns leading to malicious content.
- Efficiency Metrics:
- False positive/negative rates.
- Time taken to process and flag malicious content.
- Geographical Insights:
- Analyse regional variations in malicious content.
- Identify hotspots or regions with higher instances.
-
API Config Page