Files
X-Financial/document/development/agent plan/02_semantic_ontology.md

363 lines
5.3 KiB
Markdown
Raw Normal View History

# 语义本体协议设计
## 1. 定位
语义本体协议是用户问题、定时任务、规则中心、MCP、数据库查询和 Agent 之间的统一中间层。
它解决的问题是:
- 用户到底在问哪个业务域?
- 这属于什么场景?
- 用户想做什么?
- 问题中涉及哪些对象?
- 有没有时间、金额、状态、部门等过滤条件?
- 是否涉及风险?
- 下一步应该查知识库、查数据库、跑规则、调 MCP还是追问
## 2. 第一版核心字段
第一版建议只强制落 8 个字段。
```json
{
"domain": "",
"scenario": "",
"intent": "",
"entities": [],
"time_range": {},
"constraints": {},
"risk_signals": [],
"next_step": ""
}
```
### 2.1 domain
一级业务域。
建议枚举:
```text
reimbursement
accounts_receivable
accounts_payable
general_finance
system_operation
```
含义:
- `reimbursement`:报销、差旅、发票、补件。
- `accounts_receivable`:应收账款、客户开票、收款、账龄。
- `accounts_payable`:应付账款、供应商发票、付款、对账。
- `general_finance`:通用财务知识、制度、统计。
- `system_operation`系统巡检、任务运行、规则维护、MCP 健康检查。
### 2.2 scenario
细分场景。
报销:
```text
travel_reimbursement
daily_expense
invoice_validation
attachment_review
policy_overrun
reimbursement_audit
```
应收:
```text
customer_invoice
collection_followup
receivable_aging
payment_matching
bad_debt_risk
contract_receivable
```
应付:
```text
vendor_invoice
payment_request
payable_aging
vendor_reconciliation
invoice_matching
cash_outflow_forecast
```
系统运营:
```text
daily_risk_scan
daily_finance_statistics
knowledge_accumulation
mcp_health_check
rule_quality_review
```
### 2.3 intent
用户或任务的意图。
建议枚举:
```text
query
explain
create
validate
summarize
reconcile
monitor
predict
remind
generate
optimize
```
### 2.4 entities
识别出的业务对象。
统一结构:
```json
{
"type": "invoice",
"value": "INV-202605001",
"normalized_value": "INV-202605001",
"role": "target",
"confidence": 0.92
}
```
常见实体:
```text
employee
department
customer
vendor
invoice
contract
reimbursement_request
payment_order
receipt
bank_transaction
cost_center
project
policy
approval_node
rule
task
```
### 2.5 time_range
统一描述时间。
```json
{
"raw": "上个月",
"start": "2026-04-01",
"end": "2026-04-30",
"granularity": "month"
}
```
Hermes 定时任务也使用同一字段。
例如每日风险巡检:
```json
{
"raw": "昨日",
"start": "2026-05-09",
"end": "2026-05-09",
"granularity": "day"
}
```
### 2.6 constraints
查询、判断或执行条件。
```json
{
"status": "overdue",
"aging_days": ">30",
"amount": {
"operator": ">",
"value": 50000,
"currency": "CNY"
},
"department": "销售部",
"risk_level": ["medium", "high"]
}
```
### 2.7 risk_signals
风险信号。
建议枚举:
```text
duplicate_invoice
missing_attachment
policy_overrun
over_budget
overdue_receivable
bad_debt_risk
vendor_payment_risk
payment_mismatch
contract_mismatch
cashflow_pressure
mcp_unavailable
rule_quality_issue
```
### 2.8 next_step
下一步动作。
建议枚举:
```text
answer
ask_clarification
query_database
run_rule
call_mcp
search_knowledge
create_draft
create_task
generate_report
notify_user
escalate_to_human
```
## 3. 扩展字段
后续可以增加:
```json
{
"schema_version": "1.1",
"confidence": 0.86,
"ambiguity": [],
"missing_slots": [],
"required_capabilities": [],
"normalized_query": "",
"permission_scope": {},
"audit_tags": []
}
```
扩展原则:
- 先不要把所有字段都做成数据库列。
- 语义结果建议存 JSONB。
- 使用 `schema_version` 管理版本。
- Orchestrator 只依赖稳定字段。
- 新字段以可选方式加入,不影响老任务。
## 4. 示例
### 4.1 用户查询应收账龄
用户问:
```text
上个月哪些客户应收逾期超过 30 天?
```
解析:
```json
{
"domain": "accounts_receivable",
"scenario": "receivable_aging",
"intent": "query",
"entities": [
{
"type": "customer",
"value": "客户",
"role": "group_by"
}
],
"time_range": {
"raw": "上个月",
"start": "2026-04-01",
"end": "2026-04-30",
"granularity": "month"
},
"constraints": {
"aging_days": ">30",
"status": "overdue"
},
"risk_signals": ["overdue_receivable"],
"next_step": "query_database"
}
```
### 4.2 用户解释发票拦截
用户问:
```text
这张发票为什么报销被拦截?
```
解析:
```json
{
"domain": "reimbursement",
"scenario": "invoice_validation",
"intent": "explain",
"entities": [
{
"type": "invoice",
"value": "这张发票",
"role": "target"
}
],
"time_range": {},
"constraints": {},
"risk_signals": ["unknown"],
"next_step": "run_rule"
}
```
### 4.3 Hermes 每日风险巡检
任务配置:
```json
{
"domain": "reimbursement",
"scenario": "daily_risk_scan",
"intent": "monitor",
"entities": [],
"time_range": {
"raw": "昨日"
},
"constraints": {
"risk_level": ["medium", "high"]
},
"risk_signals": [
"duplicate_invoice",
"missing_attachment",
"policy_overrun"
],
"next_step": "run_rule"
}
```