Q Chat allows users to retrieve data directly through natural language interaction. This conversational query feature makes data analysis accessible to everyone and introduces a new way of consuming data.
Q Chat is a value-added module that requires a separate purchase.
This feature is currently available only in the Hong Kong (China) and Malaysia sites. Support for other sites will be available soon.
Q Chat is supported only in the Premium and Professional Editions. It is not supported in the Personal Edition.
To embed Q Chat into your business systems, you must purchase the Ticket Enhanced Embedding module. This module is supported only in the Professional Edition or higher.
Core advantages
Efficiently retrieve data through Q&A to simplify the data retrieval process.
Gain insights into the key drivers of data anomalies and fluctuations to simplify decision-making.
Anomaly detection:
Detect abnormal data from reports or data files. Automatically drill down to find the source of the anomaly in more granular objects. For example, you can identify specific customers who are causing monthly profit anomalies.
Fluctuation attribution:
Compare metric fluctuations over different periods and analyze the causes of these fluctuations from various perspectives. This feature shows the contribution of different factors to locate root causes and identify actionable steps.
Custom scenario-based insights:
You can build custom workflows using the built-in Dify/Alibaba Cloud Model Studio platform. You can then integrate the resulting custom Agents with Q Chat to enable scenario-specific insights.
Supports complex query scenarios, such as multi-step queries.
Scenarios
Q Chat uses natural language to quickly retrieve data. This improves data retrieval efficiency and reduces the manual workload. It automatically detects data anomalies to pinpoint root causes. By comparing metrics across different periods, Q Chat also performs fluctuation attribution analysis. It breaks down the contribution of each dimension to identify the reasons for fluctuations and provides actionable insights. This makes it ideal for frequent data-driven decisions, such as business analysis, performance reviews, and troubleshooting.
Scenario 1: Business management
Scenario description: Use AI+BI to improve business management efficiency and identify opportunities for profit growth.
Solution comparison: The following table compares the traditional data analysis method with Q Chat in this scenario.
Traditional method (Before)
Intelligent method (After)
Heavy reliance on manual sales analysis.
Sales report analysis: Manual process. Dozens of people gather every night to review sales reports. They lack tools for both fixed-question and flexible review analysis. They can only view and repeatedly filter a single report, leading to inefficient weekly business summaries.
Sales issue review: Relies on meetings. Multi-dimensional data analysis of customers, sales reports, and product categories depends on individual skills. Key management points are often missed, and it is difficult to learn from the sales experience of others.
Market trend tracking: Relies on experience. Sales notes from deals and performance data cannot be used together. Sales target achievement depends entirely on manual supervision, lacking a closed-loop monitoring system from goal setting to action execution.
AI-assisted business management for efficient and accurate decision-making anytime, anywhere.
Interactive query: Smart sales review. Quickly retrieve performance data through conversation. Get further suggestions from the AI large model.
Interactive summary: Smart sales quality inspection. Use the AI large model to customize customer analysis models. Uncover opportunities and threats from sales visit records.
Periodic reporting: Smart business decision-making. Supports conversational daily report attribution using Agent intent classification. Supports weekly business analysis based on the Agent's automatic planning capabilities.
Summary: AI-powered insights provide a comprehensive summary of sales management progress, making performance growth trackable, manageable, and predictable:
More efficient: Self-service data queries and progress summaries improve the efficiency of daily business operations by 80% and reduce unnecessary discussions and disputes by 50%.
Easier to manage: It frees sales and business management personnel from reviewing hundreds of reports. The business can focus more on tasks such as customer management and performance achievement, driving business growth.
Scenario 2: Supply chain management
Scenario description: Use AI+BI to improve operational analysis efficiency and identify opportunities for supply chain improvement.
Solution comparison: The following table compares the traditional data analysis method with Q Chat in this scenario.
Traditional method (Before)
Intelligent method (After)
Tedious manual analysis and discussion.
Analysis of over 100 dimension combinations in the supply chain: Manual process. Business analysis requires drilling down into many dimensions (fixed reports have a low satisfaction rate of <20%). Analysis times are flexible (fixed reports only provide weekly or monthly data). Manual data retrieval has long cycles and high costs (reports are generated weekly).
Identifying reasons for order delays: Relies on meetings. Lacks multi-dimensional analysis of target variances (with nearly 100 dimension combinations for drill-down, manual analysis struggles to locate core factors). Relies on "manual" analysis, which is inaccurate and inefficient.
Handling similar issues: Relies on asking others. Staff cannot quickly look up and learn business terms (relying on offline documents and training). Business personnel have a slow learning curve and high training costs. Information is not synchronized.
AI-assisted supply chain management for Q&A responses, efficient cause identification, and action planning.
Insight: Intelligently locate performance achievement through scenario-based queries and conversational "data consumption". For example, directly ask, "What is the order fulfillment performance in each major region?" and use the chart returned by the AI to discover the specific reasons.
Diagnosis: Intelligently analyze abnormal nodes and their causes with the AI assistant's smart analysis and automatic attribution. Directly ask, "What are the core reasons for the Northeast region's failure to meet its fulfillment rate target this week?"
Action: Intelligently retrieve related knowledge. An AI knowledge platform provides unified maintenance and efficient querying. Enterprise personnel can use this platform to quickly acquire knowledge and synchronize information.
Summary: AI-powered attribution efficiently pinpoints supply chain fulfillment issues, making the entire operational link diagnosable, scalable, and trustworthy:
More efficient: Automated information retrieval and Q&A improve the efficiency of daily business operations by 80% and reduce unnecessary manual work by 30%.
Easier to manage: It allows business personnel to focus more on fulfillment, inventory control, and other tasks by identifying issues, which leads to reduced operational costs.
Features
From the Q Chat interface on your PC or mobile device, you can preview and select datasets, ask questions in the input box, use saved searches, engage in multi-turn conversations, and view historical Q Chat conversations in the conversation list.
Multiple data sources
You can query data from selected datasets and uploaded data files.
Convenient query methods
You can ask questions by typing them directly or use more efficient methods such as saved searches and speech input.
Multiple large model options
You can select the system's built-in large model or a custom large model for interpretation and inference.
Data insights and fluctuation attribution
Q Chat compares metric fluctuations over different periods and analyzes the causes from various perspectives. It shows the contribution of different factors to locate root causes and identify actionable steps.
Predictable data trends
You can predict future trends over a period based on historical data.
Traceable conversation history
You can view conversations from the last 30 days.
Multi-device compatibility
You can query data on mobile phones and tablets.
Workflow
The workflow for using Q Chat and its related reference documents is as follows.
Step | Procedure | Description |
1 | Preparation | Before using Q Chat, configure the dataset for querying. For more information, see Prepare data. |
2 | Flexible configuration and management |
|
3 | Initiate a query | After completing the preparation, authorized users can perform data Q&A in the Q Chat interface. This includes the following operations:
For more information, see Initiate a query. |
4 | Query operations | While using Q Chat, the system records user query behaviors and selects a list of use cases to track from the query records. For more information, see Query operations. |
5 | System integration | When using Quick BI Professional Edition, you can use the Ticket Q Chat embedding solution. This solution provides one-stop security control for multiple scenarios, such as linking, access, and querying. It helps you integrate with enterprise business systems at a low cost and efficiently build data products with your own brand characteristics. For more information, see Embed intelligent Q Chat. |