# 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="/files/B36vxFMQZjOOgeNrAkJb" 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.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.maiagent.ai/maiagent-user-guide/maiagent-user-guide-en/track/usage.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.