feat: 添加线索引擎、NLQ、场景检测、前端界面等核心功能模块

2026-06-16 08:15:15 +08:00
parent 7b1e2b10a8
commit 48340f6011
62 changed files with 6772 additions and 65 deletions
@@ -0,0 +1,237 @@
+"""R15 适配器：员工内部舞弊与资源滥用。
+
+源明细：SrcEmployeeOperation / SrcInternalMsisdn / SrcPointsTransaction
+映射到：Entity(EMPLOYEE, MSISDN) + 关系(OPERATES) + MetricEvent
+"""
+
+from __future__ import annotations
+
+import uuid
+
+from sqlalchemy.orm import Session
+
+from app.datahub.graph_repo import add_relationship, upsert_entity
+from app.datahub.models import MetricEvent
+from app.datahub.ontology import EntityType, RelationshipType
+from app.datahub.staging import (
+    SrcEmployeeOperation,
+    SrcInternalMsisdn,
+    SrcPointsTransaction,
+)
+from app.ingest.base import BaseAdapter, IngestResult
+from app.ingest.registry import register_adapter
+
+
+@register_adapter
+class EmployeeOperationAdapter(BaseAdapter):
+    """SrcEmployeeOperation → Entity(EMPLOYEE) + 关系(OPERATES) + MetricEvent。"""
+
+    source_system = "BSS"
+    staging_table = "src_employee_operation"
+
+    def ingest(
+        self,
+        session: Session,
+        data_version_id: uuid.UUID | None = None,
+        batch_size: int = 1000,
+    ) -> IngestResult:
+        result = IngestResult()
+        query = session.query(SrcEmployeeOperation)
+        if data_version_id:
+            query = query.filter(SrcEmployeeOperation.data_version_id == data_version_id)
+        rows = query.limit(batch_size).all()
+
+        for row in rows:
+            try:
+                # 员工实体
+                emp_entity = upsert_entity(
+                    session,
+                    entity_type=EntityType.EMPLOYEE,
+                    business_key=row.employee_key,
+                    display_name=row.employee_name,
+                    attributes={
+                        "position": row.position,
+                        "department": row.department,
+                        "role_permissions": row.role_permissions,
+                    },
+                    data_version_id=data_version_id,
+                )
+                result.entities.append(emp_entity)
+
+                # 操作目标 → OPERATES 关系（如操作对象是号码或账户）
+                if row.operation_target:
+                    # 尝试识别操作目标类型（简单启发式：以1开头长度11为号码，否则为账户）
+                    target_key = row.operation_target.strip()
+                    if target_key.isdigit() and len(target_key) == 11:
+                        target_entity = upsert_entity(
+                            session,
+                            entity_type=EntityType.MSISDN,
+                            business_key=target_key,
+                            data_version_id=data_version_id,
+                        )
+                        rel = add_relationship(
+                            session, RelationshipType.OPERATES, emp_entity, target_entity,
+                            attributes={"operation_type": row.operation_type},
+                            data_version_id=data_version_id,
+                        )
+                        result.relationships.append(rel)
+
+                # 操作日志事件
+                if row.operation_time:
+                    event = MetricEvent(
+                        event_time=row.operation_time,
+                        subject_type="employee",
+                        subject_key=row.employee_key,
+                        metric_name="operation_log",
+                        metric_value=1.0,
+                        attributes={
+                            "operation_type": row.operation_type,
+                            "operation_target": row.operation_target,
+                            "position": row.position,
+                            "department": row.department,
+                        },
+                        data_version_id=data_version_id,
+                    )
+                    session.add(event)
+                    result.metric_events.append(event)
+
+                result.row_count += 1
+            except Exception:
+                result.error_count += 1
+
+        return result
+
+
+@register_adapter
+class InternalMsisdnAdapter(BaseAdapter):
+    """SrcInternalMsisdn → Entity(MSISDN, EMPLOYEE) + 关系(OPERATES) + MetricEvent。"""
+
+    source_system = "BSS"
+    staging_table = "src_internal_msisdn"
+
+    def ingest(
+        self,
+        session: Session,
+        data_version_id: uuid.UUID | None = None,
+        batch_size: int = 1000,
+    ) -> IngestResult:
+        result = IngestResult()
+        query = session.query(SrcInternalMsisdn)
+        if data_version_id:
+            query = query.filter(SrcInternalMsisdn.data_version_id == data_version_id)
+        rows = query.limit(batch_size).all()
+
+        for row in rows:
+            try:
+                # 内部号码实体
+                msisdn_entity = upsert_entity(
+                    session,
+                    entity_type=EntityType.MSISDN,
+                    business_key=row.msisdn,
+                    display_name=row.msisdn,
+                    attributes={"purpose": row.purpose, "internal": True},
+                    data_version_id=data_version_id,
+                )
+                result.entities.append(msisdn_entity)
+
+                # 分配员工 → OPERATES 关系
+                if row.assigned_employee:
+                    emp_entity = upsert_entity(
+                        session,
+                        entity_type=EntityType.EMPLOYEE,
+                        business_key=row.assigned_employee,
+                        data_version_id=data_version_id,
+                    )
+                    rel = add_relationship(
+                        session, RelationshipType.OPERATES, emp_entity, msisdn_entity,
+                        attributes={"purpose": row.purpose},
+                        data_version_id=data_version_id,
+                    )
+                    result.relationships.append(rel)
+
+                # 内部号用量事件
+                import datetime as dt
+
+                try:
+                    event_time = dt.datetime.strptime(
+                        row.report_month, "%Y-%m"
+                    ).replace(tzinfo=dt.timezone.utc) if row.report_month else dt.datetime.now(dt.timezone.utc)
+                except ValueError:
+                    event_time = dt.datetime.now(dt.timezone.utc)
+
+                event = MetricEvent(
+                    event_time=event_time,
+                    subject_type="msisdn",
+                    subject_key=row.msisdn,
+                    metric_name="internal_usage",
+                    metric_value=row.traffic_mb,
+                    attributes={
+                        "voice_min": row.voice_min,
+                        "revenue_attributed": row.revenue_attributed,
+                        "assigned_employee": row.assigned_employee,
+                        "purpose": row.purpose,
+                    },
+                    data_version_id=data_version_id,
+                )
+                session.add(event)
+                result.metric_events.append(event)
+                result.row_count += 1
+            except Exception:
+                result.error_count += 1
+
+        return result
+
+
+@register_adapter
+class PointsTransactionAdapter(BaseAdapter):
+    """SrcPointsTransaction → MetricEvent（积分发放/兑换时序）。"""
+
+    source_system = "BSS"
+    staging_table = "src_points_transaction"
+
+    def ingest(
+        self,
+        session: Session,
+        data_version_id: uuid.UUID | None = None,
+        batch_size: int = 1000,
+    ) -> IngestResult:
+        result = IngestResult()
+        query = session.query(SrcPointsTransaction)
+        if data_version_id:
+            query = query.filter(SrcPointsTransaction.data_version_id == data_version_id)
+        rows = query.limit(batch_size).all()
+
+        for row in rows:
+            try:
+                # 确保操作人实体存在
+                upsert_entity(
+                    session,
+                    entity_type=EntityType.EMPLOYEE,
+                    business_key=row.operator_key,
+                    data_version_id=data_version_id,
+                )
+
+                # 积分事件
+                if row.transaction_time:
+                    event = MetricEvent(
+                        event_time=row.transaction_time,
+                        subject_type="employee",
+                        subject_key=row.operator_key,
+                        metric_name="points_transaction",
+                        metric_value=row.points_amount,
+                        attributes={
+                            "transaction_no": row.transaction_no,
+                            "target_account": row.target_account,
+                            "transaction_type": row.transaction_type,
+                            "cash_value": row.cash_value,
+                        },
+                        data_version_id=data_version_id,
+                    )
+                    session.add(event)
+                    result.metric_events.append(event)
+
+                result.row_count += 1
+            except Exception:
+                result.error_count += 1
+
+        return result