Improve title to better capture activity

This commit is contained in:
Nicolas Mowen 2026-03-09 17:33:07 -06:00
parent 9cbd80d981
commit df6a9ca45c

View File

@ -112,7 +112,7 @@ When forming your description:
Your response MUST be a flat JSON object with: Your response MUST be a flat JSON object with:
- `scene` (string): A narrative description of what happens across the sequence from start to finish, in chronological order. Start by describing how the sequence begins, then describe the progression of events. **Describe all significant movements and actions in the order they occur.** For example, if a vehicle arrives and then a person exits, describe both actions sequentially. **Only describe actions you can actually observe happening in the frames provided.** Do not infer or assume actions that aren't visible (e.g., if you see someone walking but never see them sit, don't say they sat down). Include setting, detected objects, and their observable actions. Avoid speculation or filling in assumed behaviors. Your description should align with and support the threat level you assign. - `scene` (string): A narrative description of what happens across the sequence from start to finish, in chronological order. Start by describing how the sequence begins, then describe the progression of events. **Describe all significant movements and actions in the order they occur.** For example, if a vehicle arrives and then a person exits, describe both actions sequentially. **Only describe actions you can actually observe happening in the frames provided.** Do not infer or assume actions that aren't visible (e.g., if you see someone walking but never see them sit, don't say they sat down). Include setting, detected objects, and their observable actions. Avoid speculation or filling in assumed behaviors. Your description should align with and support the threat level you assign.
- `title` (string): A concise, grammatically complete title in the format "[Subject] [action verb] [context]" that matches your scene description. Use names from "Objects in Scene" when you visually observe them. - `title` (string): A short title that characterizes **what took place and where**. Interpret the overall purpose or outcome of the activity from the full sequence do not simply compress the scene description into fewer words. Include the relevant location (zone, area, or entry point). Always include subject names from "Objects in Scene" do not replace named subjects with generic terms. Do not include editorial qualifiers like "routine" or "suspicious" just describe what happened. Keep it under 10 words.
- `shortSummary` (string): A brief 2-sentence summary of the scene, suitable for notifications. Should capture the key activity and context without full detail. This should be a condensed version of the scene description above. - `shortSummary` (string): A brief 2-sentence summary of the scene, suitable for notifications. Should capture the key activity and context without full detail. This should be a condensed version of the scene description above.
- `confidence` (float): 0-1 confidence in your analysis. Higher confidence when objects/actions are clearly visible and context is unambiguous. Lower confidence when the sequence is unclear, objects are partially obscured, or context is ambiguous. - `confidence` (float): 0-1 confidence in your analysis. Higher confidence when objects/actions are clearly visible and context is unambiguous. Lower confidence when the sequence is unclear, objects are partially obscured, or context is ambiguous.
- `potential_threat_level` (integer): 0, 1, or 2 as defined in "Normal Activity Patterns for This Property" above. Your threat level must be consistent with your scene description and the guidance above. - `potential_threat_level` (integer): 0, 1, or 2 as defined in "Normal Activity Patterns for This Property" above. Your threat level must be consistent with your scene description and the guidance above.