What this category's data looks like
Undergraduate program revision involves three types of materials: program plans, course syllabi, and credit structure tables. Sources are academic affairs system exports and departmental submissions, with update cadence advancing along with revision batches. Program plans contain program names, total credits, course modules, and signature fields; course syllabi contain course names, credit hours, assessment methods, and authors; credit structure tables contain credits, proportions, and dates for each module. When these three types of materials enter the vector model and indexing function, they respectively assume the roles of terminology source, contextual cross-reference, and field verification: program plans provide the terminology baseline for programs and modules, course syllabi provide course translated names and expression variants, and credit structure tables provide quantity and date fields. Multilingual materials and terminology processing require the same terminology to be consistent throughout the entire document, translated names to be traceable back to the original text, and material fields and signatures to be aligned item by item.
Configuration and implementation checks
This step is executed by the indexing service and vector database, outputting vectors and index status (whether recall is possible, whether data in the same group is merged). The "unified terminology table and comparison draft" is then completed by subsequent AI nodes, code nodes, or manual work (retrieval and citation trimming only take supporting materials).
| Object | Check | Verification action |
|---|---|---|
| Program plan | Program name, total credits, course modules, and signature fields are written consistently across the three types of materials, and translated names can be traced back to the original text | Open the data row corresponding to the program plan, check whether the index field contains multiple vector identifiers, and perform a retrieval to see whether the same group is merged |
| Course syllabus | Course name, credit hours, assessment method, and author fields match the program plan and credit structure table, and dates do not conflict | In the knowledge base settings, check that the index model is consistent with the vector model actually used, and view the values of defaultToken and maxToken |
| Credit structure table | Credits, proportions, and dates for each module are consistent with the program plan and course syllabus, versions are synchronized, and no signatures or receipts are missing | View the data scope covered by the rebuild task, and confirm that after changing the model, rebuild is triggered only for data that has already been indexed |
| Data row | Multiple vector identifiers for one piece of data are all present, and the status is indexed or a rebuild task record exists | Open a data row to check the index field, confirm that multiple vector identifiers are complete, and that the original data can be traced back |
Three common errors
- Symptom: duplicate entries appear in retrieval results. Inspect the following: the same group of original data corresponds to multiple vectors, and when merging, they are not merged by the highest score, resulting in the same group of data not being merged.
- Symptom: the name, quantity, and date of the same record do not match between the program plan and the credit structure table. Inspect the following: versions are not synchronized, and the two materials were revised separately without unified write-back.
- Symptom: the course syllabus lacks a signature or receipt, and the author cannot be confirmed before external release. Inspect the following: the material circulation step did not collect all signed documents.
How to verify the setup
Acceptance for this function: sample one data row and check the index field to confirm that multiple vector identifiers are complete and the status is indexed or a rebuild task record exists; then perform a retrieval to see whether the same group of data is merged and whether the vector score takes the highest score.
Business test: sample three terms to check whether their writing is consistent throughout the document, and verify whether the translated names can be traced back to the original text.
- In the knowledge base settings, check that the index model is consistent with the vector model actually used by the knowledge base, and record the values of
defaultTokenandmaxToken. - View the data scope covered by the rebuild task, confirm that after changing the model, rebuild is triggered only for data that has already been indexed, and open a data row to check the index field.