What this category's data looks like
In the course selection, scheduling, and classroom resource allocation category, materials include course offering plans, scheduling tables, course selection rules, multilingual reference drafts, and unified terminology glossaries. Course offering plans contain course codes, course names, credits, offering semesters, and signature fields; scheduling tables contain classroom numbers, week numbers, period numbers, start and end dates, and signatures; course selection rules contain selection rounds, capacities, priorities, and receipts. Multilingual materials come from academic affairs system exports, departmental submissions, and translated drafts, with an update cadence that rolls by semester and selection round, and the glossary is supplemented as new course names and classroom types are added. When entering the vector model and indexing function, course offering plans and scheduling tables serve as source data rows, while glossaries and reference drafts serve as multilingual supporting materials; each generates vector identifiers and is written into index fields for subsequent retrieval and citation trimming.
Configuration and implementation checks
This step is executed by the indexing service and vector database, outputting vectors and index status (whether recall is possible and whether data in the same group is merged). The unified terminology glossary and reference drafts are then completed by subsequent AI nodes, code nodes, or manual work (retrieval and citation trimming only take supporting materials).
| Object | Check | Verification action |
|---|---|---|
| Unified terminology glossary and reference drafts | The same term is consistent throughout, translated names can refer back to the source text, and course names and classroom types are written consistently in course offering plans, scheduling tables, and course selection rules | Sample three terms and check whether their wording is consistent throughout, and verify the back-reference relationship between the reference drafts and the source text |
| Course offering plans | Course codes, course names, credits, offering semesters, dates, and signatures are complete, and the same record has consistent names, quantities, and dates across multiple materials | Check fields and signatures row by row, and compare the same record in scheduling tables and course selection rules |
| Scheduling tables | Classroom numbers, week numbers, period numbers, start and end dates, and signatures are complete, and the version is synchronized with the course offering plan | Check classroom numbers and week/period numbers, and inspect version numbers and receipts |
| Course selection rules | Selection rounds, capacities, priorities, and receipts are complete, and the same record's names, quantities, and dates match the scheduling table | Check rounds and capacities, and inspect receipts and signatures |
Three common errors
- Symptom: the name, credits, or dates of the same course do not match between the course offering plan and the scheduling table. Inspect the following: multilingual materials have not unified terminology, and versions are not synchronized.
- Symptom: the scheduling table lacks signatures or receipts, and the capacity quantities in the course selection rules and scheduling table are inconsistent. Inspect the following: the material circulation step has no receipt, and versions are not synchronized.
- Symptom: a data row has content but cannot be retrieved, or duplicate entries appear in retrieval results. Inspect the following: the index field does not record all vector identifiers, and data in the same group is not merged.
How to verify the setup
This function's acceptance: sample one data row and inspect the index field to confirm that multiple vector identifiers are all present and the status is indexed; then retrieve once to see whether data in the same group is merged and whether the vector score takes the highest score, and verify the coverage scope of the rebuild task record.
Business test: sample three terms and check whether their wording is consistent throughout, whether translated names can refer back to the source text, and whether the same record's names, quantities, and dates match across course offering plans, scheduling tables, and course selection rules.
- In the knowledge base settings, verify that the indexing model is consistent with the vector model actually used by the knowledge base, verify the values of
limit, confirm that the number of citations is recorded by array length, and check citation text tokens separately. - Open a data row and verify the index field to confirm that multiple vector identifiers for one data item are all present; after changing models, check the rebuild task record to confirm that it is triggered only for data that has already been indexed.