# Usage Analytics

## How to View

Navigate to "<mark style="color:blue;">AI Assistant</mark>" in the left sidebar, then select "<mark style="color:blue;">Usage Analytics</mark>" to view the AI assistant's conversation processing dashboard.

* Word Count
* Conversation Count
* Message Count
* Average Messages per Conversation
* User Satisfaction Rate
* Time Filter (by date, month, day, hour)

Through these metrics, you can understand the AI assistant's usage from multiple perspectives.

<figure><img src="https://1360999650-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F6v6TNkkOQVfRYfcNirHL%2Fuploads%2Fgit-blob-74ea759830879a00950ca0141d74db1afb6e9973%2F%E6%88%AA%E5%9C%96%202025-04-25%20%E4%B8%AD%E5%8D%8812.13.48.png?alt=media" alt=""><figcaption></figcaption></figure>

## Detailed Statistics Explanation

### 1. Words Count

**Calculation Method:**

* **Text Word Count**: Calculates the character count of 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)

**Statistical Scope:** Includes user input messages and AI assistant reply messages, supports daily and monthly time granularity statistics

***

### 2. Conversations Count

**Calculation Method:**

* Counter increments by +1 each time a new conversation is created
* When the first message in a conversation is created, it triggers a conversation statistics update

**Update Timing:** When a user starts a new conversation (first message)

**Statistical Scope:** Supports hourly, daily, and monthly time granularity statistics

***

### 3. Messages Count

**Calculation Method:**

* Counter increments by +1 each time a new message is created
* Includes user input messages and AI assistant reply messages

**Update Timing:** Triggers statistics update upon creation of each message

**Statistical Scope:** Supports hourly, daily, and monthly time granularity statistics

***

### 4. Average Messages per Conversation

**Calculation Formula:**

```
Average Messages per Conversation = Messages Count ÷ Conversations Count (displays 0 if Conversations Count is 0)
```

**Meaning:**

* Represents the average number of messages per conversation
* Reflects the interaction depth between users and the AI assistant
* Higher values indicate deeper conversations and more frequent interactions

**Statistical Scope:** Supports hourly, daily, and monthly time granularity statistics

***

### 5. User Satisfaction Rate

**Calculation Formula:**

```
User Satisfaction Rate = Number of Likes ÷ Total Feedback Count (displays 0 if Total Feedback Count is 0)
Total Feedback Count = Number of Likes + Number of Dislikes
```

**Meaning:**

* Represents the proportion of positive feedback (like rate)
* Value range: 0% \~ 100%
* Higher values indicate greater user satisfaction with AI assistant responses

**Feedback Mechanism:**

* Users can give "likes" or "dislikes" to AI assistant responses
* Supports real-time statistics updates

**Update Timing:** When users provide feedback (create, update, delete)

**Statistical Scope:** Supports hourly, daily, and monthly time granularity statistics

***

## Statistics Update Mechanism

**Real-time Updates:** When relevant events occur (new messages, new conversations, feedback changes), statistics updates are triggered immediately

**Time Granularity Support:**

* **Hourly**: Suitable for real-time monitoring
* **Daily**: Suitable for daily report analysis
* **Monthly**: Suitable for monthly reports and trend analysis

## Application Scenario: Usage Effectiveness Evaluation

Observing the trend changes in "User Satisfaction Rate" and interaction count can evaluate whether the AI assistant's response quality meets expectations, serving as a basis for optimization.