What this category's data looks like
Vocational college program setup filing materials are mainly composed of the program setup filing form as the main document, with talent demand justification and faculty and equipment lists as attachments. They are often submitted in aggregate by the academic affairs or planning department by academic year or application batch, and the sources include on-campus submissions, industry research, and receipts from competent authorities. The three types of materials are field-intensive: program name, code, program length, enrollment scale, justification date, number of faculty, number of equipment sets, and signature and seal positions, and the same record must keep names, quantities, and dates consistent across multiple materials. After entering the parsing and chunking stage, the filing form carries the main structure, the justification materials carry supporting paragraphs, and the faculty and equipment lists carry tabular fields, each being split into retrievable data rows for subsequent retrieval and version comparison.
Configuration and implementation checks
This step is executed by the parsing and training task (server-side task), which outputs data rows and index status (parsed, indexing, indexed). The "version ledger and change records" are then completed by retrieval and subsequent processing.
| Object | Check | Verification action |
|---|---|---|
| Program setup filing form | Fields, dates, and signatures must be consistent with the attachments | Check the program name, code, program length, enrollment scale, and signature and seal positions, and compare the same-named program and dates in the talent demand justification |
| Talent demand justification | The justification date and program name must align with the filing form | Check whether the program name and research date in the justification conclusion are consistent with the filing form, and check whether signatures or receipts are complete |
| Faculty and equipment list | Quantities and number of sets must correspond to the fields in the filing form | Check whether the number of faculty, number of equipment sets, and dates match the filing form and justification materials, and check for missing signatures or receipts |
| Data row | Is in one of the three states and consistent with the interface display | Open the data row to check the status, and confirm that chunkSize, chunkSplitter, and trainingType match the parsing and chunking results |
Three common errors
- Symptom: newly uploaded filing materials cannot be found. Cause: the data row is still in parsed or indexing, and data pending indexing is naturally isolated at the retrieval layer and is not recalled.
- Symptom: the same program name does not match between the filing form and the justification materials. Cause: the two materials are parsed and stored separately, fields are not compared across documents for consistency, and versions are not synchronized.
- Symptom: empty data rows remain after training fails. Cause: successful parsing does not mean retrieval will definitely hit; failed data is not edited or deleted in time, and the index status does not transition to indexed.
How to verify the setup
This feature's acceptance: upload one material, observe the data row status transitions and the coverage scope of the rebuild task, and confirm that after parsing and chunking is completed it is immediately stored and bound to a unique data identifier, that the status transitions through parsed, indexing, and indexed, and that changing the model only rebuilds data that has already completed indexing.
Business test: change one piece of content and see whether the version number and references are updated synchronously.
- Open the data row to check whether the status is consistent with the interface display, separately check the identity identifiers of the file record and the data row, and confirm that the identities of the file record and the data row are distinguishable from each other.
- View the data rows covered by the rebuild task, and confirm that only data that has already completed indexing is covered, while data pending indexing and data being indexed do not participate in the rebuild.