AWS Context Ontology Accelerator（COA）で日本語のオントロジーを構築してみた - 多言語検索等のサポート

CONTAINS(LCASE(?label), "検索語")     -- 格納済みラベルが検索語を含むか

# v0.2.1: packages/context-manager/src/coa_serve/query_utils.py
_ENTITY_RE = re.compile(r"\b[a-zA-Z0-9](?:[a-zA-Z0-9-]*[a-zA-Z0-9])?\b")

# v0.2.1: packages/context-manager/src/coa_serve/tier3/graph_traverser.py
_SAFE_ENTITY_RE = re.compile(r"^[a-z0-9][a-z0-9_-]{0,63}$")

CONTAINS("質問文の連続領域", LCASE(STR(?label)))   -- 質問文が格納済みラベルを含むか

% git -C coa show v0.2.1:packages/context-manager/src/coa_serve/query_utils.py > scripts/query_utils_v021.py
% coa/.venv/bin/python scripts/compare_tokenizer.py

lang  question                                       v0.2.1 entities        v0.2.2 terms / containers
--------------------------------------------------------------------------------------------------------
ja    商品分類ごとの在庫数量を教えてください            []   terms=['商品分類', '在庫数'] containers=1
ja    配送ステータスが遅延している注文はいくつありますか  []   terms=['配送', 'ステータス', '遅延', '注文'] containers=1
ja    顧客区分別の売上合計を出してください              []   terms=['顧客区分別', '売上合計'] containers=1
zh    每个商品分类的库存数量是多少                      []   terms=['每个商品分类的库存数量是多少'] containers=1
ko    상품분류별 재고수량을 알려주세요                   []   terms=['상품분류별', '재고수량을', '알려주세요'] containers=3
th    จำนวนสินค้าคงคลังของแต่ละหมวดหมู่สินค้าคือเท่าใด  []   terms=['จำนวนสินค้าคงคลัง...'] containers=1
en    How many products are in stock per product category
                              ['products', 'stock', 'per', 'product', 'category']
                              terms=['products', 'stock', 'per', 'product', 'category'] containers=0

keyword        v0.2.1     v0.2.2
----------------------------------------
商品分類           DROP       keep
在庫数            DROP       keep
顧客区分           DROP       keep
products       keep       keep
stock-level    keep       keep
Straße         DROP       keep
재고수량           DROP       keep
库存数量           DROP       keep

% git clone https://github.com/aws/context-ontology-accelerator.git coa
% cd coa && git checkout v0.2.2
% git describe --tags
v0.2.2

% for c in node npm pnpm uv java python3 aws git docker; do printf '%-8s: ' "$c"; $c --version 2>&1 | head -1; done
node    : v22.23.2
npm     : 10.9.8
pnpm    : 10.30.3
uv      : uv 0.8.14 (Homebrew 2025-08-28)
java    : openjdk 25.0.2 2026-01-20
python3 : Python 3.12.7
aws     : aws-cli/2.36.29 Python/3.14.6 Darwin/25.6.0 exe/arm64
git     : git version 2.53.0
docker  : docker version 5.6.0

# packages/ontology-engine/src/coa_ontology/inducer/strategies/table_to_ontology.py
g.add((table_cls, RDFS.label, Literal(table.name)))
...
g.add((prop_uri, RDFS.label, Literal(col.name)))

glue.create_table(DatabaseName="coa_ja_probe", TableInput={
    "Name": "商品マスタ",
    "StorageDescriptor": {"Columns": [{"Name": "商品コード", "Type": "string"},
                                      {"Name": "商品名", "Type": "string"},
                                      {"Name": "商品分類", "Type": "string"}], ...},
    ...})

create_table OK   : 商品マスタ
create_table OK   : products_ja_cols

SELECT "商品名", "商品分類" FROM "coa_ja_probe"."商品マスタ" LIMIT 5

商品名           | 商品分類
ワイヤレスマウス   | 周辺機器
USB-Cハブ       | 周辺機器

SELECT "配送ステータス", count(*) AS 件数 FROM "coa_blog_ja"."受注明細" GROUP BY "配送ステータス"

InvalidRequestException: line 1:31: mismatched input '件'. Expecting: <identifier>

SELECT "配送ステータス", count(*) AS "件数", sum("受注金額") AS "受注金額合計"
FROM "coa_blog_ja"."受注明細" GROUP BY "配送ステータス" ORDER BY 2 DESC

配送ステータス | 件数 | 受注金額合計
配達完了     | 33  | 4526160
出荷済      | 22  | 4066120
出荷準備中    | 13  | 2625860
受注済      | 7   | 742440
遅延       | 5   | 381280

商品名                  | 商品分類 | 在庫数量
ワイヤレスマウス           | 周辺機器 | 0
書画カメラ               | 映像機器 | 7
USB 電源アダプタ          | 電源機器 | 12
昇降デスク               | 什器   | 18
4K ウェブカメラ           | 映像機器 | 22
ネットワークスイッチ 8ポート  | 通信機器 | 29
電子ホワイトボード          | 什器   | 42

% aws ssm put-parameter --name /coa/config --type String --overwrite \
  --value '{"initialAdminEmail":"xxxxx@example.com"}'

% aws s3 cp "s3://coa-dev-ontology-artifacts-123456789012/proposals/$NS/$PID/latest/ontology.ttl" -

ind:entity_ a owl:DatatypeProperty ;
    rdfs:label "受注日",
        "受注番号",
        "受注金額",
        "商品コード",
        "数量",
        "配送ステータス",
        "顧客コード" ;
    rdfs:comment "受注した個数",
        "受注を登録した日",
        "受注明細の主キー。O + 4桁の連番",
        ... ;
    rdfs:domain ind:Entity ;
    rdfs:range xsd:integer,
        xsd:string .

ind:Entity a owl:Class ;
    rdfs:label "受注明細" .

ind:Entity_b121102e a owl:Class ;
    rdfs:label "顧客マスタ" .

ind:Entity_fd703afe a owl:Class ;
    rdfs:label "商品マスタ" .

# packages/ontology-engine/src/coa_ontology/inducer/strategies/table_to_ontology.py
def _to_pascal(s: str) -> str:
    return "".join(w.capitalize() for w in re.split(r"[\s_\-]+", re.sub(r"[^a-zA-Z0-9\s_\-]", "", s)) if w)

column '商品コード'   -> _to_camel=''  property local = 'entity_'
column '商品名'      -> _to_camel=''  property local = 'entity_'
column '在庫数量'     -> _to_camel=''  property local = 'entity_'
column 'product_code' -> _to_camel='productCode'  property local = 'entity_productCode'

"context_preview": "Table: 受注明細 | Columns: 受注日:integer (受注した個数)
                    Table: 顧客マスタ | Columns: 登録日:string (与信限度額と請求サイクルの区分...)
                    Table: 商品マスタ | Columns: 取扱開始日:integer (商品の名称)"

% python3 scripts/create_glue_tables_ascii.py
created table: coa_blog_ja_ascii.商品マスタ (6 columns)
created table: coa_blog_ja_ascii.顧客マスタ (5 columns)
created table: coa_blog_ja_ascii.受注明細 (7 columns)

% python3 scripts/run_query.py "配送ステータスが遅延している受注は何件ありますか"
tier      : 2.0
confidence: {"score": 0.9, "rationale": "LLM-generated SQL from ontology retrieval"}
rowCount  : 1
rows      : [{"order_count": "5"}]

queryUsed:
SELECT COUNT(*) AS order_count
FROM "受注明細"
WHERE delivery_status = '遅延'

--- トレース ---
  routing.select             success        0ms  {"gating": "source_composition", "hasStructuredSource": true, "hasUnstructuredSource": false, "skipped": ["tier3_vector_search"]}
  t1.metric_match            miss         123ms  {"query_length": 24}
  query.embed                success      223ms [bedrock]  {"dimensions": 1024}
  t2.sql.generate            success     3362ms [bedrock]  {"confidence": 1.0, "tables": ["受注明細", "商品マスタ", "顧客マスタ"]}
  t2.sql.authorize           allow         71ms [cedar]
  t2.sql.firewall            success       71ms [sql-firewall]
  t2.sql.execute             error        120ms  {"error": "InvalidRequestException", "message": "... line 2:6: mismatched input '", "shot": 1}
  t2.sql.generate            success     1827ms [bedrock]  {"confidence": 0.9, "correction_shot": 2}
  t2.sql.authorize           allow          1ms [cedar]
  t2.sql.firewall            success        1ms [sql-firewall]
  t2.sql.execute             success     1789ms  {"rowCount": 1, "shot": 2, "engine": "athena"}

% python3 scripts/run_query.py "商品分類ごとの在庫数量の合計を教えてください"
rows : [{"product_category": "通信機器", "total_stock_quantity": "470"},
        {"product_category": "映像機器", "total_stock_quantity": "310"},
        {"product_category": "什器",   "total_stock_quantity": "230"},
        {"product_category": "電源機器", "total_stock_quantity": "222"},
        {"product_category": "記憶装置", "total_stock_quantity": "195"},
        {"product_category": "周辺機器", "total_stock_quantity": "192"},
        {"product_category": "音響機器", "total_stock_quantity": "120"}]

% python3 scripts/run_query.py "顧客区分別の受注金額の合計を多い順に教えてください"
rows : [{"customer_segment": "官公庁",   "total_order_amount": "4451960"},
        {"customer_segment": "教育機関",  "total_order_amount": "2864980"},
        {"customer_segment": "個人事業主", "total_order_amount": "2179420"},
        {"customer_segment": "法人小口",  "total_order_amount": "1992460"},
        {"customer_segment": "法人大口",  "total_order_amount": "853040"}]

queryUsed:
SELECT c.customer_segment, COALESCE(SUM(o.order_amount), 0) AS total_order_amount
FROM "受注明細" o
JOIN "顧客マスタ" c ON o.customer_code = c.customer_code
GROUP BY c.customer_segment
ORDER BY total_order_amount DESC

% python3 scripts/run_query_direct.py "顧客区分別の受注金額の合計を多い順に教えてください" --strategy ontop
tier: 2.0 | confidence: {"score": 0.8, "rationale": "NL-to-SPARQL translation"}

queryUsed:
SELECT V5."customer_segment1m3" AS "customer_segment1m3", SUM(V5."order_amount1m17") AS "sum1"
FROM (SELECT DISTINCT ... FROM "受注明細" AS V1, "受注明細" AS V2, "顧客マスタ" AS V3 WHERE ...) AS V5
GROUP BY V5."customer_segment1m3" ORDER BY SUM(V5."order_amount1m17") DESC

--- トレース ---
  t2.vkg.context             success      149ms [tbox-builder]     "3 classes, 18 properties"
  t2.vkg.translate           success     5184ms [bedrock]          "confidence=0.85"
  t2.vkg.validate            success       50ms [sparql-validator] "passed"
  t2.vkg.compile             success      255ms [ontop]            {"dialect": "trino", "tables": ["受注明細", "顧客マスタ"]}
  t2.vkg.execute             success     1857ms [sql-engine]       {"row_count": 5}

% python3 scripts/run_query.py "発注点を下回っている商品を教えてください"
tier      : 2.0
confidence: {"score": 0.4, "rationale": "LLM-generated SQL from ontology retrieval"}
rowCount  : 1
rows      : [{"product_code": "P001", "product_name": "ワイヤレスマウス", "stock_quantity": "0"}]

queryUsed:
SELECT DISTINCT product_code, product_name, stock_quantity
FROM "商品マスタ"
WHERE stock_quantity <= 0

% curl -sS -X POST "$API/namespaces/$NS/sources" -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" -d '{
    "sourceType": "DOCUMENTS",
    "documentSource": {"name": "ja-business-docs",
      "sourceBucketArn": "arn:aws:s3:::coa-blog-ja-123456789012-us-east-1",
      "s3Prefixes": ["docs/"]}}'

16:36:40Z  REGISTERED
16:36:57Z  SCANNING
16:37:48Z  SCANNING_ENTITY_EXTRACTION
16:43:42Z  COMPLETED

% python3 scripts/run_query_direct.py "発注点の定義と、商品分類ごとのしきい値を教えてください" --tier 3 --mode agentic
tier: 3.0 | confidence: {"score": 0.85, "rationale": "Agentic synthesis"}

## 発注点の定義

データグロッサリー(data-glossary-ja.txt)によると、「発注点」は以下のように定義されています。
- 発注点とは、在庫を補充するための在庫数量のしきい値である
- 発注点は商品分類によって異なる値が設定される

## 商品分類ごとのしきい値

| 商品分類 | 発注点 |
|---|---|
| 什器 | 50個未満で発注点(什器は嵩張るため個別に設定) |
| その他すべての商品分類 | 30個未満で発注点 |

{"topic": "青葉オフィスサプライ販売業務ポリシーの配送ステータス定義",
 "statements": ["受注済 is the state immediately after registering an order",
                "受注明細の配送ステータス is a classification system"]}
{"topic": "Product Classification and Inventory Management Policies",
 "statements": ["Fixtures have large volume, therefore the reorder point is set when inventory quantity falls below 50 units.",
                "All other product classifications have an inventory reorder point of 30 units."]}

HTTP 504
{"message": "Endpoint request timed out"}

% python3 scripts/sparql_ab.py artifacts/ontology_ascii.ttl "受注明細表の配送状況を集計してください"

## 質問: 受注明細表の配送状況を集計してください
  v0.2.1 FILTER      : （検索語ゼロ件のため SPARQL を発行せず終了）
  v0.2.1 ヒット       : 0 件 []
  v0.2.2 順方向のみ      : 0 件 []
    FILTER: CONTAINS(LCASE(?label), "受注明細表") || CONTAINS(LCASE(?label), "配送状況") || CONTAINS(LCASE(?label), "集計")
  v0.2.2 逆方向のみ      : 1 件 ['受注明細']
    FILTER: (STRLEN(STR(?label)) >= 2 && CONTAINS("受注明細表の配送状況を集計してください", LCASE(STR(?label))))
  v0.2.2 実装（双方向）    : 1 件 ['受注明細']

## 質問: 受注明細ごとの金額を教えてください
  v0.2.2 順方向のみ      : 1 件 ['受注明細']
  v0.2.2 逆方向のみ      : 1 件 ['受注明細']

## 質問: 請統計受注明細表的配送狀況
  v0.2.1 ヒット       : 0 件 []
  v0.2.2 順方向のみ      : 0 件 []
    FILTER: CONTAINS(LCASE(?label), "請統計受注明細表的配送狀況")
  v0.2.2 逆方向のみ      : 1 件 ['受注明細']
  v0.2.2 実装（双方向）    : 1 件 ['受注明細']

full_context = await self._try_full_namespace_context(namespace, mapped)
if full_context is not None:
    classes, properties = full_context
elif ontology_hits:
    classes, properties = await self._fetch_ontology_context(ontology_hits, namespace, mapped)
elif query:
    # Fallback: use query entities to fetch context
    classes, properties = await self._fetch_by_entities(query, namespace, mapped)

# packages/context-manager/src/coa_serve/tier1/metric_resolver.py
def _name_pattern(name: str) -> re.Pattern:
    escaped = re.escape(name).replace("_", r"[\s_]")
    return re.compile(rf"\b{escaped}\b")

メトリクス名       質問                                   マッチ
--------------------------------------------------------------
売上合計         売上合計は？                               miss
売上合計         顧客区分別の売上合計を教えてください                   miss
在庫数量         商品分類ごとの在庫数量を教えてください                  miss
total_sales  show me the total sales by customer segment HIT
total_sales  what is the total sales?                    HIT

# 残差トークンの抽出（v0.2.2）
_RESIDUAL_TOKEN_RE = re.compile(r"[a-z0-9_%$\uac00-\ud7a3]+")

% GET /namespaces/{ns}/sources/{sid}/tables
HTTP 200 ['coa_blog_ja_ascii.顧客マスタ', 'coa_blog_ja_ascii.商品マスタ', 'coa_blog_ja_ascii.受注明細']

% GET /namespaces/{ns}/sources/{sid}/tables/coa_blog_ja_ascii.%E5%95%86%E5%93%81%E3%83%9E%E3%82%B9%E3%82%BF
HTTP 404: {"error": "Table coa_blog_ja_ascii.%E5%95%86%E5%93%81%E3%83%9E%E3%82%B9%E3%82%BF not found"}

# packages/sources/src/coa_sources/api/sources_handler.py
table_id = path_params.get("tableId", "")