Semantic layer-based marketing queries first define business indicators such as sales and cancellation rates, and then link natural language questions to approved indicators and data ranges. The focus is on reducing the problem of the same term having different meanings in different systems.
What data do you connect?
| data area | Description | Indicators to Link |
|---|---|---|
| ecommerce · Order · Payment | Inflow into our own mall, order and payment information | Order amount, order conversion and campaign inflow |
| OSM · Order Fulfillment | Order processing information, including shipment, delivery, installation, cancellation, and return | Fulfillment status, cancellation/return reflected sales |
| CTI · Customer consultation | Consultation classification and inquiries/inconveniences | Customer response regarding delivery inquiries and campaigns |
Name and ledger scope are the distinctions used in this case description. The data structure and calculation standards of the actual system are determined for each implementation environment.
Through what process are questions answered?
- Interpret the period, target, and indicator in the question and check again for ambiguous terms.
- Check calculation formulas, join relationships, and permission scopes in the semantic layer.
- Aggregates with the accepted data and returns the baseline and metric definition.
Sample question: “Please show us sales and delivery inquiries reflecting cancellations and returns from last week’s special exhibition.” This is a descriptive question and does not represent actual customer data or performance figures.
How do you verify accuracy and authority?
We compare the results with the correct questions and calculation formulas agreed upon at work, and test methods for accessing data outside of authority, exposing personal information, and handling ambiguous questions. It is important to indicate when the data is updated and when the results are based to account for differences in aggregation.
How are the roles of GLT and partners divided?
| area | Role in collaboration |
|---|---|
| GLT Korea | Definition of business rules and indicators between order, logistics fulfillment, and consultation, domain schema/linkage requirements, and review of result consistency |
| AI technology partners | Design and implementation of AI model, agent, and platform, and model evaluation and operation technology |
| Customer company/operating organization | Data use rights, business review, application approval and operating policy |
The table above divides the areas of collaboration, and the actual scope of performance and output for each project is confirmed according to the contract and division of work.
Disclosure and scope of explanation
Introduction to Serendex Public ProjectIntroduces a case of natural language marketing index inquiry that connects ecommerce, OSM, and CTI data of a global home appliance manufacturer with the Cube semantic layer.
This article explains the application structure based on the published examples and the domain perspective of GLT. Each customer's contract period, inspection results, and quantitative performance are provided separately from the technical description on this page.