What this category's data looks like
This category's data looks like this: Social evaluation of vocational skill level certification involves materials such as evaluation implementation plans, candidate registration forms, and assessor dispatch forms; the sources are evaluation institutions and test sites, updated by batch. The implementation plan contains the occupation name, level, assessment method, and date; the registration form contains the candidate's identity, declared occupation, and signature; the dispatch form contains the assessor's name, task, and receipt. When materials enter parsing and chunking, the implementation plan provides terminology sources and process fields, the registration form provides personnel and declaration fields, and the dispatch form provides assessment and signature fields; together, the three support field alignment for the unified terminology table and the comparison draft.
Configuration and implementation checks
Configuration and implementation checks: This step is executed by parsing and training tasks (server-side tasks), outputting data rows and index status (parsed, indexing, indexed). The "unified terminology table and comparison draft" is then completed by retrieval and subsequent processing.
| Object | Check | Verification action |
|---|---|---|
| Evaluation implementation plan | The occupation name, level, assessment method, date, and signature fields must be aligned item by item with the registration form and dispatch form | Check that the occupation name and level in the plan are written consistently in the registration form and dispatch form, that dates and signatures are complete, and confirm that the parsing and chunking parameters chunkSize, chunkSplitter, and trainingType records are consistent |
| Candidate registration form | The candidate's identity, declared occupation, level, and signature receipt must correspond to the implementation plan and dispatch form | Extract three terms, check whether their spelling is consistent throughout the document, and check the number of people and dates in the registration form and dispatch form, confirming that the data row status is parsed, indexing, or indexed |
| Assessor dispatch form | The assessor's name, task, date, and receipt must correspond to the implementation plan and registration form | Check the assessor names, quantities, and dates in the dispatch form and registration form, inspect for missing signatures or receipts, and confirm that the trainingType and chunkSize settings are consistent |
| Data rows and index status | Is in one of the three states parsed, indexing, or indexed and is consistent with the interface display | Open the data row to check the status, confirm that data pending indexing does not participate in recall, that changing the model only rebuilds indexed data, and check chunkSplitter and trainingType |
Three common errors
- Symptom: The name, quantity, and date of the same record do not match between the implementation plan and the registration form. Cause: During multilingual materials and terminology processing, fields were not aligned and versions were not synchronized.
- Symptom: The dispatch form lacks a signature or receipt, and the materials cannot be released externally. Cause: Signature fields were not included in parsing and chunking verification, and receipts were not updated with the version.
- Symptom: Newly uploaded materials cannot be found. Cause: Successful parsing does not equal retrieval hits; the data row is in parsed or indexing and has not completed indexing.
How to verify the setup
How to verify the setup: Acceptance for this feature: upload one material, observe the data row status transitions and the coverage scope of the rebuild task, check that the three states parsed, indexing, and indexed are consistent with the interface, confirm that the rebuild only covers data that has completed indexing, and check the chunkSize, chunkSplitter, and trainingType records
Business test: extract three terms and check whether their spelling is consistent throughout the document
- Separately check the file records and data rows, confirm that file and data row identifiers are distinguishable, and check the
chunkSize,chunkSplitter, andtrainingTypefields - View the data rows covered by the rebuild task, confirm that it only covers data that has completed indexing, and that the initial training covers data pending indexing and data being indexed