Usage Analytics
Provides backend monitoring data to understand user information.
How to View
Go to "AI Assistant" in the left menu and select "Usage Analytics" to view the AI Assistant conversation dashboard.
Word count
Conversation count
Message count
Average messages per conversation
User satisfaction
Time filters (by date, month, day, hour)
These metrics allow you to understand AI Assistant usage from multiple perspectives.
Detailed Metric Descriptions
1. Word Count (Words Count)
Calculation Method:
Text word count: Counts the number of characters in message content
Image cost: Each image is calculated based on the configured image word cost
Total word count = Message content word count + (Number of images × Image word cost)
Scope: Includes both user input messages and AI Assistant reply messages. Supports daily and monthly granularity.
2. Conversation Count (Conversations Count)
Calculation Method:
Each time a new conversation is created, the counter increments by 1
When the first message in a conversation is created, it triggers a conversation statistics update
Update Trigger: When a user starts a new conversation (first message)
Scope: Supports hourly, daily, and monthly granularity.
3. Message Count (Messages Count)
Calculation Method:
Each time a new message is created, the counter increments by 1
Includes both user input messages and AI Assistant reply messages
Update Trigger: Each message creation triggers a statistics update
Scope: Supports hourly, daily, and monthly granularity.
4. Average Messages per Conversation (Average Messages per Conversation)
Formula:
Description:
Represents the average number of messages per conversation
Reflects the depth of interaction between users and the AI Assistant
Higher values indicate deeper and more frequent interactions
Scope: Supports hourly, daily, and monthly granularity.
5. User Satisfaction (User Satisfaction Rate)
Formula:
Description:
Represents the percentage of positive feedback (like rate)
Value range: 0% to 100%
Higher values indicate greater user satisfaction with AI Assistant responses
Feedback Mechanism:
Users can give a "like" or "dislike" to AI Assistant responses
Statistics are updated in real time
Update Trigger: When users provide feedback (create, update, or delete)
Scope: Supports hourly, daily, and monthly granularity.
Statistics Update Mechanism
Real-time updates: Statistics are immediately updated when relevant events occur (new message, new conversation, feedback change)
Time granularity support:
Hourly: Suitable for real-time monitoring
Daily: Suitable for daily report analysis
Monthly: Suitable for monthly reports and trend analysis
Use Case: Effectiveness Assessment
Observe trends in "User Satisfaction" and interaction counts to evaluate whether the AI Assistant's response quality meets expectations, serving as a basis for optimization.
Last updated
Was this helpful?