What this category's data looks like
This category's data covers three types of materials: program plans, course syllabi, and credit structure tables. The sources are departments and academic affairs offices, and the update cadence advances with revision batches. The field characteristics are course names, credit counts, course start dates, and signature fields. The program plan provides the overall framework and credit requirements, the course syllabus details each course's objectives and content, and the credit structure table summarizes the credit distribution of each module. In multilingual materials and terminology processing, the three types of materials each play a different role: the program plan provides definitions of terms, the course syllabus provides the usage context of terms, and the credit structure table verifies the consistency of names and quantities. After the materials enter the document parsing and chunking function, they first form retrievable data rows, and then support the production of the unified terminology glossary and the comparison draft.
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 "unified terminology glossary and comparison draft" is then completed by retrieval and subsequent processing. After parsing is complete, the parsed chunks are immediately persisted as visible data rows and bound to a unique data identifier. The index transitions through three states. Data pending indexing does not participate in recall. Changing the model only rebuilds data that has completed indexing.
| Object | Check | Verification action |
|---|---|---|
| Program plan | Whether the course names, credit counts, course start dates, and signature fields are consistent across the three types of materials | Check the course names, credit counts, dates, and signatures in the program plan and course syllabus, and confirm that the same record is written consistently |
| Course syllabus | Whether the translated term names can refer back to the source text, and whether the names and quantities match the program plan | Compare the course syllabus with the program plan, and check item by item the correspondence between translated term names and the source text as well as the consistency of quantities |
| Credit structure table | Whether the credit counts and dates are consistent with the program plan and course syllabus, and whether the versions are synchronized | Compare the credit counts and dates in the credit structure table with the program plan and course syllabus, and check version synchronization and signature receipts |
| Data row | Whether it is in one of the three states parsed, indexing, indexed and is consistent with the interface display | Open the data row to check the status, confirm that chunkSize, chunkSplitter, trainingType, and the rebuild scope only cover indexed data |
Three common errors
- Symptom: The name and credit count of the same course do not match between the program plan and the course syllabus. Cause: The versions of the two materials are not synchronized; after revision, only one is updated while the other still uses the old record.
- Symptom: The course start date in the credit structure table is inconsistent with that in the program plan. Cause: The materials are maintained in different batches, and the date fields have not been uniformly written back and cross-checked.
- Symptom: The course syllabus lacks a signature or receipt, and the terminology glossary cannot confirm the effective version. Cause: The signature field was not collected synchronously with the revision process, and no completeness check was performed before release.
How to verify the setup
Acceptance for this feature: Upload one material, observe the status transitions of the data rows and the coverage scope of the rebuild task, and confirm that the states are parsed, indexing, and indexed, that the rebuild only covers indexed data, and that the initial training covers data pending indexing and data being indexed.
Business test: Sample three terms and check whether their usage is consistent throughout the entire document, confirming that the same term is consistent throughout and that the translated name can refer back to the source text.
- Open the data row to check the status, confirm that it is in one of parsed, indexing, or indexed and is consistent with the interface display, and separately check the identity identifiers of the file record and the data row.
- View the data rows covered by the rebuild task, confirm that it only covers indexed data, and check whether the values of
chunkSize,chunkSplitter, andtrainingTypematch the current materials.