Skip to main content

Monitoring Management

The entry point for log monitoring is as follows:

Agent Monitoring​

The Data Center provides comprehensive statistics and analysis on the usage of intelligent agents and user conversation content, helping users better understand the effectiveness and operational status of AI, and optimize management and decision-making.

The Data Center supports data statistics by agent dimension, system API dimension, and time dimension.

agent Analysis​

This section focuses on quantitative analysis of the usage of each AI agent, including:

  • Number of users in conversation: The number of unique users who have interacted with the agent.
  • Number of conversations: The total number of interactions between users and the agent, measuring usage activity.
  • Token consumption: Measures the resource consumption of model calls during agent operation.
  • agent usage ranking: Ranks all agents by usage frequency to identify high-frequency agents.
  • Token consumption ranking: Counts the Token usage of each agent to assist in resource optimization and cost control.

Conversation Analysis​

This section delves into the content of conversations between users and agents, gaining insights into user needs and interaction patterns, including:

  • High-frequency word analysis: Extracts keywords from user conversations to identify hot topics and demand trends.
  • Conversation logs: View historical conversation details for quality review, issue troubleshooting, and content auditing.

💡 Tip: Conversation count statistics and agent usage ranking are updated once a day; other information such as conversation logs is updated in real time.

Notification Management​

Notification management is used to count and view various notification messages received by all users in the system. Through this function, administrators can track the delivery of notifications, understand whether users have read them, and whether the notification content has been effectively communicated.

For example: When a user provides feedback on an answer from an agent during a conversation, the system will send a feedback notification to that user. Such notifications will be recorded and displayed in notification management.

Function Description​

On the notification management page, you can view the following information:

  • Recipient: The user account or username that received the notification
  • Notification status: Whether the notification has been read (read / unread)
  • Send time: The specific time the system sent the notification
  • Notification content: Detailed information of the notification, supports viewing original prompts, feedback results, etc.
  • Notification category: The category to which the notification belongs, such as feedback notification, system notification, task reminder, etc.

💡 Tip: Supports filtering notifications by time dimension

Admin Logs​

Admin logs are log files or database records that record administrator activities and operations in the system. They are typically used to monitor, audit, and analyze administrator behavior in the system to ensure system security, compliance, and performance.

Information Provided by Admin Logs​

Admin logs can provide the following key information:

  • Account information
    Records the administrator account information that performed the operation, helping to track which user performed a specific operation.

  • IP address
    Records the IP address when the administrator logs in or performs operations, which helps determine the source of the operation.

  • Client information
    Records the type of client used by the administrator (such as browser, operating system, etc.), helping to understand the administrator's operating environment.

  • Operation content
    Detailed records of the specific operations performed by the administrator, such as login, configuration modification, file deletion, etc.

  • Operation time
    Records the specific time the operation occurred, which helps with time series analysis and troubleshooting.

Functions of Admin Logs​

  • Security monitoring: Admin logs help detect unauthorized access or suspicious activity, enhancing system security.
  • Compliance auditing: Log records provide evidence for compliance requirements, ensuring that administrator operations comply with company or industry regulations.
  • Issue troubleshooting: The time and operation information recorded in admin logs help trace and quickly resolve issues when they occur.

Operation Logs​

Operation logs record key user actions on the platform and include the following information fields:

  • Username: The name of the user performing the operation
  • User ID: The unique identifier of the corresponding user
  • Operation type: Such as create, update, delete, view, etc.
  • Resource type: The category of the object being operated on, such as agent, knowledge base, conversation record, etc.
  • Resource unique identifier: The ID or name of the specific resource being operated on
  • Action description: The specific operation action, such as "add feedback", "delete file", "edit agent configuration", etc.

For example: When user A provides feedback on an agent's Q&A, the system will record an "add feedback" operation log, indicating that the user performed a specific action on a certain resource at a certain time.

Functions of Operation Logs​

  • Behavior tracking: Clearly reconstruct every user operation, making it easy to understand and analyze user behavior paths
  • Issue troubleshooting: When the system encounters an exception or the result is not as expected, the cause can be quickly located through operation logs
  • Permission auditing: Helps verify whether users are operating within their authorized scope, improving security
  • Compliance traceability: Meets regulatory compliance requirements and provides evidence for security audits
  • Operational analysis: Analyzes user usage frequency and active operation modules, providing references for product optimization

Operation logs are usually immutable and are important data assets generated at the system level. They can be used in conjunction with modules such as notification management and permission management.

File Logs​

File logs are a log system that records user file operation behaviors in the system. They detail various operations users perform on files, such as upload, download, modify, delete, etc. File logs are crucial for maintaining system security, audit compliance, and tracking user behavior.

Information Provided by File Logs​

File logs can provide the following key information:

  • Account record
    Records the user account information that performed the operation, helping to track which user performed a specific operation.

  • IP address
    Records the IP address when the user logs in or performs operations, which helps determine the source of the operation.

  • Client information
    Records the type of client used by the user (such as browser, operating system, etc.), helping to understand the user's operating environment.

  • Operation content
    Detailed records of the specific operations performed by the user, such as file upload, download, modification, deletion, etc.

  • Operation time
    Records the specific time the operation occurred, which helps with time series analysis and troubleshooting.

  • File information
    Records information about the files involved in the operation, such as file name, file path, file space, etc.

Functions of File Logs​

  • Security monitoring: File logs help detect illegal operations or unauthorized access, enhancing system security.
  • Compliance auditing: File logs provide evidence for compliance checks, ensuring that file operations comply with regulations.
  • Behavior tracking: By recording user operations, file changes can be traced and responsible persons identified.
  • Issue troubleshooting: The time and operation information recorded in file logs help analyze and resolve system issues related to file operations.

Billing Details​

In the SERVICEME system, you can view billing details for Token usage. The line chart at the top of the interface displays the changes in Token-related values at different points in time, providing an intuitive view of usage trends. The table below records in detail the Token consumption and corresponding costs of various models within a specific time period, and lists related usage types and other information, making it easy to clearly understand the billing situation for each Token usage.

Information Provided on the Billing Details Page​

On the billing details interface, you can view the following information:

  • Model group: Displays the group category to which the model belongs.

  • Model set: Indicates the name of the set to which the model belongs.

  • Model: Displays the name of the specific model used.

  • Channel: Identifies the channel through which the model runs.

  • API Key name: Shows the API key name used to access the model.

  • Input Token: Records the number of Tokens input into the model.

  • Input token (cache hit): Shows the number of Tokens input when the cache is hit.

  • Output token: Displays the number of Tokens consumed by the model's output results.

  • Token cost: Lists the cost incurred by using Tokens.

  • Time: Records the specific time the model operation occurred.

  • Operation: Provides executable operation options such as viewing log details.

Functions of Billing Details​

  • Real-time monitoring of Token consumption: Through billing details, administrators can view the Token consumption of models in real time and judge usage trends based on the line chart.
  • Cost tracking: Facilitates tracking the cost of each operation, helping administrators control costs.
  • Log viewing: Through the log details viewing function provided in the operation column, users can gain an in-depth understanding of the specific content of each model operation, helping with troubleshooting.