Demo untuk flow yang tadi: CatDict browser, CategoryAlgo, manual learning loop, dan save-algo-results. Fokus pada classification engine, bukan GL posting.
$result = CategoryAlgo::categorize($tx);
if ($result['confidence_score'] < 70) {
$result['needs_review'] = true;
}
save_algo_result($tx['id'], [
'algo_category' => $result['final_category'],
'algo_confidence' => $result['confidence_score'],
'algo_match_type' => $result['match_type'],
'algo_reason' => $result['explanation'],
'algo_needs_review' => $result['needs_review'] ? 1 : 0,
]);
if (!empty($manual_category)) {
catdictSaveManualCategory(
$tx['description'],
(float)$tx['debit'],
(float)$tx['credit'],
$manual_category,
$tx['source_sheet'] ?? ''
);
}Description, debit, credit, and source sheet arrive from recompile-mbb.
Match rule, fallback, or review path based on confidence.
Manual category corrections improve the next run.
Basic Package
Special SME traction programme by AINNA.
Limited starter website offer. AI usage, hosting, maintenance and custom integrations depend on the confirmed scope.
View SME Offer →
Ask about AINNA pages, services and articles.
AINNA sources only · up to 5 lines · 20 questions/hour
No section data available yet.
Sites with documented sections will appear here.
We value your privacy
We use browser storage to remember your choice. Optional analytics runs only after you allow it; your choice is recorded with an anonymous ID. Privacy Policy