:Q Chat Overview

Key Benefits

• Retrieve data through natural language Q&A, reducing manual query effort.

• Identify root causes of data anomalies and fluctuations to simplify decision-making.

  • Anomaly detection:

    Detect unusual data points in reports or files. Q Chat automatically drills down to find anomaly sources, such as specific customers contributing to a monthly profit deviation.

  • Fluctuation attribution:

    Compare metrics across time periods. Q Chat analyzes change drivers from multiple perspectives and shows each factor's contribution, helping you pinpoint issues and take action.

  • Customized contextual insights:

    Build custom workflows on Dify or Model Studio to create a custom agent, then connect it to Q Chat for business-specific insights.

• Supports complex, multi-step conversational queries.

Use Cases

Q Chat accelerates data retrieval through natural language, detects anomalies, and attributes metric fluctuations across time periods. This supports data-driven decisions in business analysis, performance reviews, and troubleshooting.

Use Case 1: Business management

• Scenario: Use AI+BI to improve business management efficiency and identify profit growth opportunities.

• Comparison: The following table compares the traditional approach with the Q Chat approach.

  Traditional approach (before)

  Intelligent approach (after)

  Manual sales analysis. Performance reporting: A manual process requiring dozens of people to review reports nightly. Lacks standardized and ad-hoc analysis tools. Users can only filter a single report, leading to inefficient weekly summaries. Sales issue review: Relies on meetings for multi-dimensional analysis of customers, orders, and product categories. Data interpretation depends on individual skill, often missing insights and preventing knowledge sharing. Market trend tracking: Relies on experience. Field visit notes and performance data are siloed. Target achievement depends on manual supervision with no closed-loop monitoring.

  AI-assisted business management for efficient, accurate, and on-demand decision-making. Interactive queries: Conduct intelligent sales reviews. Retrieve performance data through conversation and receive AI-powered suggestions. Interactive summaries: Perform intelligent sales quality checks. Create custom client analysis models that uncover opportunities and risks from visit records. Periodic reports: Make intelligent business decisions. Use agent-based intent classification for daily report attribution and auto-planning for weekly analysis.

• Summary: AI-powered insights summarize sales management progress, making performance growth trackable, manageable, and predictable:

  • More efficient: Self-service data queries and progress summaries increase daily operational efficiency by 80% and reduce unnecessary debates by 50%.

  • Easier to manage: Frees managers from navigating hundreds of reports, letting them focus on customer management and performance targets.

Use Case 2: Supply chain management

• Scenario: Use AI+BI to improve operational analysis and identify supply chain optimization opportunities.

• Comparison: The following table compares the traditional approach with the Q Chat approach.

  Traditional approach (before)

  Intelligent approach (after)

  Manual analysis and discussion. Analysis of 100+ supply chain dimension combinations: A manual process. Fixed reports meet less than 20% of needs, and the manual data retrieval cycle (weekly report generation) is costly. Identifying order delay causes: Relies on meetings. With nearly 100 dimension combinations, manually pinpointing key factors is difficult. Manual analysis is inaccurate and inefficient. Handling similar issues: Relies on asking others. Staff cannot quickly find business terminology, slowing onboarding and creating information silos.

  AI-assisted supply chain management for conversational responses, efficient root cause analysis, and subsequent action. Insight: Track performance through conversational queries. For example, ask "What is the order fulfillment performance in each region?" and drill into the chart to find root causes. Diagnosis: Analyze anomalies with automatic attribution. For example, ask "What is the primary reason for failing to meet the fulfillment rate target in the Northeast region this week?" Action: Retrieve related knowledge from a centralized AI-powered platform, ensuring consistent information access across the organization.

• Summary: AI-powered attribution identifies supply chain fulfillment issues, making the operational chain diagnosable, extensible, and reliable:

  • More efficient: Automated information retrieval and Q&A increase daily operational efficiency by 80% and reduce unnecessary manual work by 30%.

  • Easier to manage: Staff focus on fulfillment and inventory control by quickly identifying issues, reducing operational costs.

Features

The Q Chat interface on PC and mobile supports dataset preview and selection, typed or voice queries, multi-turn conversations, and a conversation list for history.

• Diverse data sources

  Query a selected dataset or an uploaded data file.

  

• Convenient query methods

  Type questions directly, use quick queries, or voice input.

  

• Flexible large model selection

  Choose a built-in or custom large model for interpretation and reasoning.

  

• Data insights and fluctuation attribution

  Compare metric fluctuations across different time periods. Q Chat analyzes the causes of these changes from multiple perspectives and shows each factor's contribution, helping you pinpoint issues and decide on actionable steps.

  

• Predictive data trends

  Forecast future trends based on historical data.

  

• Traceable conversation history

  View your conversations from the last 30 days.

  

• Multi-device compatibility

  Use Q Chat on your phone or tablet.

Workflow

The following table outlines the Q Chat workflow.