What Data This Category Entails
Core data for this category comes from the enterprise registration full-process electronic system, the national enterprise credit information publicity system, the electronic business license system, and the residence information database. The update frequency is daily.
Documents processed daily include establishment registration applications, articles of association, shareholder resolutions, residence certificates, business licenses, food business license applications, and more. Document structures cover fields such as main entity identity information, residence address, shareholder contribution information, and license type. Some documents exist as structured tables or scanned copies. Support for multi-format parsing and field extraction is required.
Constraints Imposed on Workflow Orchestration
Data sources for this category are scattered and updated daily. Workflows must support connecting to multiple system data sources and syncing the latest data.
Document types are diverse, including structured tables and scanned copies. Workflows must support multi-format file parsing and image recognition capabilities.
Core verification links take extended time. Workflows must split nodes and set reasonable timeout thresholds.
Errors may lead to outcomes such as registration rejection or false registration. Workflows must configure verification and correction trigger nodes to ensure business compliance.
Configuration Specifications
Reference only; verify against the target FastGPT release and deployment documentation.
| Config Item | Recommended Value | Basis for This Value |
|---|---|---|
| Node timeout time | 600 seconds | The average time spent on the market entity registration verification form link does not exceed 10 minutes. Timeout will cause workflow interruption |
| Excel file parsing rules | Maximum 10000 rows per single parse, map core fields of establishment registration applications and shareholder resolutions | Excel documents in this category are mostly registration application materials submitted by enterprises. Extraction of specified business fields is required |
| Image recognition trigger mode | Automatic recognition mode, recognition resolution of 300 DPI | Automatic information extraction from scanned copies such as business licenses and residence certificates is required. No manual trigger is needed |
variables parameter configuration | Bind application number and application type parameters in the URL | External incoming business parameters must be synchronized to the workflow to match corresponding knowledge bases and verification rules |
| Multiple knowledge base binding | Bind up to 3 associated knowledge bases, automatically switch according to application type in variables | This category covers multiple scenarios including establishment, change, and food business license. Corresponding different business knowledge bases are required |
| Trigger node binding | Bind window submission event according to nodeId | Must match the offline submission process of market supervision windows to automatically start the workflow |
Three Common Configuration Mistakes
- Workflow execution fails to read uploaded Excel files, and returns empty fields. The cause is that field mapping rules for Excel parsing nodes are not configured, so core business fields from establishment registration applications and shareholder resolutions cannot be extracted.
- Workflow cannot obtain the application number parameter from the current URL, and the corresponding field in
variablesis empty. The cause is that the URL parameter extraction node is not configured in the workflow, and URL parameters are not bound to business variables. - The image recognition node does not automatically complete information extraction from business license scanned copies, and requires manual triggering. The cause is that automatic recognition trigger mode is not enabled, and only manual upload trigger logic is configured.
How to Confirm Proper Configuration
- Upload a test Excel-format establishment registration application, and verify whether core fields such as residence address and shareholder information can be correctly extracted.
- Construct a test URL containing an application number, trigger the workflow, and verify whether URL parameters can be correctly extracted and bound to
variablesvariables. - Upload a business license scanned copy, and verify whether the recognition node can be automatically triggered and information such as the unified social credit code can be extracted.
- Switch the application type parameter, and verify whether the corresponding bound knowledge base can be automatically matched and called.
The values given are common starting points and should be measured against the reader's own samples.
Question material comes from public community discussions. Configuration values are common starting points and should be measured against your own samples. Verified on 2026-09-28.