{"schema_version":"2.0.0","product_id":"supplier-catalog-extractor","title":{"en":"Supplier Catalog Extractor","zh-TW":"供應商型錄擷取"},"product_type":"Smart Tools Decision Product","suite":"supplier-intelligence","status":"SPECIFICATION_AVAILABLE;PROPOSED:catalog-extraction","version":"0.1.0","updated_at":"2026-10-08","primary_intent":{"en":"Turn a supplier catalog into traceable records for the next sourcing decision.","zh-TW":"把供應商型錄轉成可追溯紀錄，支援下一個採購決策。"},"capability_id":"cap:automation","inputs":["authorized_source_document","source_version","target_fields","optional_change_review_packet"],"outputs":["proposed_catalog_review_bundle","field_provenance","unresolved_conflicts","reviewed_handoff"],"deployment":["specification:available","local-or-hosted-adapter:proposed"],"capabilities":[{"id":"bilingual_specification","status":"AVAILABLE"},{"id":"official_integration_research","status":"AVAILABLE"},{"id":"tracked_handoff_links","status":"AVAILABLE"},{"id":"document_extraction","status":"PROPOSED"},{"id":"supplier_entity_resolution","status":"PROPOSED"},{"id":"reviewed_graph_write","status":"PLANNED"}],"sections":[{"number":1,"id":"achieve","title":{"en":"What are you trying to achieve?","zh-TW":"你想完成什麼？"},"paragraphs":[{"en":"Turn a supplier catalog into records you can trace back to the exact source, review, and pass to a sourcing decision. Start with the changed document, not a guessed company match.","zh-TW":"把供應商型錄轉成能回到確切來源、可查核並交給採購決策的紀錄。從變更文件開始，不以相似公司名猜測身份。"}],"items":[]},{"number":2,"id":"intents","title":{"en":"User intents","zh-TW":"使用者意圖"},"paragraphs":[{"en":"Primary intent: prepare versioned supplier, model and specification candidates. Secondary intents: review changed fields, locate missing units and compare catalog revisions. This is not supplier qualification, a binding quotation, or proof of origin.","zh-TW":"主要意圖：準備有版本的供應商、型號與規格候選紀錄。其次是查核變更欄位、找出缺漏單位與比較型錄版本。這不是供應商資格認定、正式報價或產地證明。"}],"items":[]},{"number":3,"id":"inputs","title":{"en":"Inputs","zh-TW":"輸入"},"paragraphs":[{"en":"The proposed adapter accepts an authorized PDF, HTML snapshot or existing extraction output, together with a document identifier, capture time when known, version and target fields. A Website Change Monitor review packet can identify which source and fields need attention. This page does not upload or fetch documents.","zh-TW":"規劃中的適配器接收已授權 PDF、HTML 快照或既有擷取結果，連同文件識別碼、已知擷取時間、版本及目標欄位。網站變更查核資料可指出待處理的來源與欄位。本頁不會上傳或抓取文件。"}],"items":[]},{"number":4,"id":"outputs","title":{"en":"Outputs","zh-TW":"輸出"},"paragraphs":[{"en":"The proposed output is a review bundle: candidate model records, raw field text, normalized values when justified, original units, source locations, unresolved conflicts and a revision relationship. Extraction confidence and human review state are separate. A missing value stays missing.","zh-TW":"規劃輸出是查核資料包：候選型號紀錄、原始欄位文字、有依據才轉換的值、原單位、來源位置、未解衝突及版本關係。擷取信心與人工查核狀態分開；缺漏值維持缺漏。"}],"items":[]},{"number":5,"id":"works","title":{"en":"How it works","zh-TW":"如何運作"},"paragraphs":[{"en":"Choose an existing extraction engine for the document type. Preserve its output and source coordinates; map fields to the catalog schema; flag uncertain entities and units; ask a reviewer to accept or reject candidates. Only reviewed records may enter a future capability graph. These execution steps are proposed.","zh-TW":"依文件類型選用現成擷取引擎，保留原輸出與來源座標，再映射到型錄欄位，標示不確定實體與單位，由查核者接受或拒絕候選值。只有經查核紀錄可進入未來能力圖譜；以上執行步驟仍為規劃。"}],"items":[]},{"number":6,"id":"example","title":{"en":"Example workflow","zh-TW":"流程範例"},"paragraphs":[{"en":"Illustrative case: a fictional AX-12 revision changes payload from 5 kg to 7 kg. Keep both excerpts and document versions, associate each value with its page or element, and flag the change for review. Do not conclude that a specific mission can carry 7 kg or merge AX-12 with another supplier model.","zh-TW":"示意案例：虛構 AX-12 的改版將載重從 5 kg 改為 7 kg。保留兩份摘錄與文件版本，讓各數值對應頁碼或元素，並標示待查核。不能推論某次任務可承載 7 kg，也不能併入另一家同名型號。"}],"items":[]},{"number":7,"id":"stack","title":{"en":"Integration Stack","zh-TW":"整合組合"},"paragraphs":[{"en":"Integrate document conversion and web extraction where they already exist. Benchmark a managed layout service against the same labeled catalog set. Keep source evidence separate from the recommended execution stack; no provider is connected to Smart Tools in this release.","zh-TW":"文件轉換與網頁擷取採現成能力；用相同標註型錄比較託管版面服務。來源證據與建議執行組合分開；本版尚未接通任何供應商服務。"}],"items":[]},{"number":8,"id":"matrix","title":{"en":"Build / Integrate / Benchmark Matrix","zh-TW":"自建／整合／參考矩陣"},"paragraphs":[{"en":"Compare local document processing, document partitioning, managed layout analysis and web product extraction. These options solve different input problems. Selection depends on document layout, language, deployment constraints and measured field quality; there is no universal accuracy ranking here.","zh-TW":"比較本機文件處理、文件分割、託管版面分析與網頁產品擷取，各自處理不同輸入問題。選擇取決於版面、語言、部署條件與實測欄位品質；此處不提供通用準確率排名。"}],"items":[]},{"number":9,"id":"owns","title":{"en":"What Smart Tools owns","zh-TW":"Smart Tools 掌握的部分"},"paragraphs":[{"en":"Why Smart Tools exists: a parsed table still does not say which supplier and model it belongs to, which revision applies, what is uncertain, or how it affects a buyer requirement. Smart Tools should own the reviewed relationship between those facts and the next decision, rather than a replacement OCR engine.","zh-TW":"Why Smart Tools exists：解析出的表格仍未回答供應商與型號身份、適用版本、未知條件，以及如何影響買方需求。Smart Tools 應掌握這些資料經查核後與下一個決策的關係，而不是另做 OCR 引擎。"}],"items":[]},{"number":10,"id":"fit","title":{"en":"Works best when","zh-TW":"何時適合"},"paragraphs":[{"en":"Start with a small, authorized catalog set that has recognizable model identifiers and reviewable source pages. Define required fields and a reviewer before choosing an adapter. A useful pilot includes clean tables, merged cells, scanned pages and conflicting revisions.","zh-TW":"從小量、已授權、型號可辨識且來源頁可查核的型錄開始。先指定必要欄位與查核者，再選適配器。試點應涵蓋清楚表格、合併儲存格、掃描頁與版本衝突。"}],"items":[]},{"number":11,"id":"anti-fit","title":{"en":"Not suitable when","zh-TW":"何時不適合"},"paragraphs":[{"en":"Not suitable for inferring absent certifications, assuming a distributor is the manufacturer, guessing units, merging similar model names, or silently publishing confidential drawings. Use the original source when the document cannot support a reliable field location.","zh-TW":"不適合推定未列認證、把經銷商視為製造商、猜測單位、合併相似型號，或無聲公開機密圖面。文件無法支持可信欄位位置時，回到原始來源查核。"}],"items":[]},{"number":12,"id":"architecture","title":{"en":"Technical architecture","zh-TW":"技術架構"},"paragraphs":[{"en":"Proposed architecture: controlled intake → document/version fingerprint → selected extraction adapter → immutable raw output → field mapping → conflict and entity review → approved export. Keep parsing workers separate from the website. Record provider and model versions so a rerun can be compared.","zh-TW":"規劃架構：受控接收 → 文件／版本指紋 → 選定擷取適配器 → 保留原始輸出 → 欄位映射 → 衝突與實體查核 → 核准匯出。解析工作節點與網站分開；記錄供應商及模型版本以比較重跑結果。"}],"items":[]},{"number":13,"id":"interfaces","title":{"en":"API / SDK / OSS options","zh-TW":"API／SDK／開源選項"},"paragraphs":[{"en":"Docling, Unstructured and Diffbot are integration candidates; Azure Document Intelligence provides a managed-layout comparison. The downloadable contract defines candidate fields and review states, not a working Smart Tools extraction endpoint. No credentials or paid calls are required to read this specification.","zh-TW":"Docling、Unstructured 與 Diffbot 是整合候選；Azure Document Intelligence 提供託管版面比較。可下載契約定義候選欄位與查核狀態，不代表已有 Smart Tools 擷取端點。閱讀規格不需要憑證或付費呼叫。"}],"items":[]},{"number":14,"id":"privacy","title":{"en":"Data / privacy / deployment","zh-TW":"資料／隱私／部署"},"paragraphs":[{"en":"Keep confidential catalogs private by default. Before execution, choose local or hosted processing, retention, reviewer access and deletion behavior for that document. The current page receives no catalog content; anonymous page/link events exclude documents, excerpts, source URLs and API keys.","zh-TW":"機密型錄預設私密。執行前應逐文件決定本機或雲端處理、保存期限、查核權限及刪除方式。本頁不接收型錄內容；匿名頁面／連結事件不包含文件、摘錄、來源網址或 API 金鑰。"}],"items":[]},{"number":15,"id":"use-cases","title":{"en":"Industrial use cases","zh-TW":"產業用途"},"paragraphs":[{"en":"Manufacturing: preserve part/model codes, dimensions, units and catalog revisions. UAV: distinguish a vehicle, payload and configuration rather than inheriting a whole-company claim. Composites: record a stated material or test method without treating an equipment list as a measured material result.","zh-TW":"製造業保留料號／型號、尺寸、單位與型錄改版；UAV 區分載具、酬載與配置，不繼承整家公司的主張；複材記錄明示材料或試驗方法，不把設備清單視為材料實測結果。"}],"items":[]},{"number":16,"id":"internal-links","title":{"en":"Internal links","zh-TW":"語意內部連結"},"paragraphs":[{"en":"Previous: review a meaningful source change with Website Change Monitor. Next: hand reviewed candidates to Supplier Capability Matcher; it remains planned. RFQ Requirement Parser is a separate planned input path for buyer requirements. Use the workflow map to inspect availability before continuing.","zh-TW":"上一步是 Website Change Monitor 的來源變更查核；下一步把已查核候選紀錄交給 Supplier Capability Matcher，後者仍在規劃。RFQ Requirement Parser 是買方需求的另一條規劃輸入。繼續前先在流程圖確認狀態。"}],"items":[]},{"number":17,"id":"network","title":{"en":"Cross-site routing","zh-TW":"跨站分流"},"paragraphs":[{"en":"Sites provides company and source context; BE PASSIVE provides original catalog access and a contextual requirement route. The BYTE source gallery is an existing engineering experience, not a live demonstration of this extractor. A dedicated extraction Demo and cross-site completion measurement remain unavailable.","zh-TW":"Sites 提供公司與來源脈絡；BE PASSIVE 提供原型錄及有上下文的需求入口。BYTE 來源圖庫是既有工程體驗，不是本擷取器的實機示範。專用擷取 Demo 與跨站完成量測尚未提供。"}],"items":[]},{"number":18,"id":"references","title":{"en":"External evidence / references","zh-TW":"外部證據／參考"},"paragraphs":[{"en":"The references below are official documentation reviewed on 2026-10-08. They establish documented provider capabilities, not integration tests, tenant entitlement or measured accuracy on this catalog set. Each external reference keeps its direct URL and a stable tracking ID.","zh-TW":"下列為 2026-10-08 查閱的官方文件。它們支持供應商已記載的能力，不代表整合測試、租戶使用權或本型錄集合的實測準確率。每個外部參考保留直接網址與穩定追蹤識別碼。"}],"items":[]},{"number":19,"id":"seo","title":{"en":"SEO","zh-TW":"搜尋意圖"},"paragraphs":[{"en":"Search intent: evaluate supplier catalog extraction and field-level provenance before implementation. English and Traditional Chinese pages have reciprocal language links and distinct canonical URLs. Original company sources remain their own pages; this specification does not replace them.","zh-TW":"搜尋意圖是實作前評估供應商型錄擷取及逐欄來源。英文與繁體中文頁互相連結並有各自 canonical；原公司來源仍維持獨立頁面，不由本規格取代。"}],"items":[]},{"number":20,"id":"structured-data","title":{"en":"Structured data","zh-TW":"機器可讀資料"},"paragraphs":[{"en":"This page is a TechArticle with official citations and breadcrumb data. The JSON spec exposes the product status, proposed contract, integration comparison, related routes and acceptance gates. It does not advertise a working SoftwareApplication or fabricated ratings, prices or extraction results.","zh-TW":"本頁以 TechArticle 提供官方引用與導覽資料；JSON 規格公開產品狀態、規劃契約、整合比較、相關路徑與驗收條件。不宣稱已有可執行軟體，也不編造評分、價格或擷取成果。"}],"items":[]},{"number":21,"id":"tracking","title":{"en":"Analytics / tracking","zh-TW":"追蹤與成效"},"paragraphs":[{"en":"Available measurement covers specification views, downloads, official references and next-step clicks. Execution, extraction quality, useful-result feedback and RFQ completion are unavailable until the corresponding functionality is connected. A reference click is not a successful extraction or inquiry.","zh-TW":"目前量測規格瀏覽、下載、官方參考與下一步點擊。執行、擷取品質、有用結果回饋及 RFQ 完成，須等相應功能接通才提供。參考連結點擊不等於擷取或詢價成功。"}],"items":[]},{"number":22,"id":"mvp","title":{"en":"MVP","zh-TW":"最小版本"},"paragraphs":[{"en":"This release delivers the bilingual product specification, proposed field contract, integration research and semantic handoff links. Next implementation slice: select one adapter and review ten authorized catalog pages against a labeled field set. Do not start several provider connectors at once.","zh-TW":"本版交付雙語產品規格、規劃欄位契約、整合研究及語意交接連結。下一個實作增量是選定一個適配器，以十頁已授權型錄比對已標註欄位；不一次開發多個供應商連接器。"}],"items":[]},{"number":23,"id":"acceptance","title":{"en":"Acceptance criteria","zh-TW":"驗收條件"},"paragraphs":[{"en":"Execution acceptance gates: every accepted field has a source locator; missing values and zero remain distinct; units are preserved; duplicate models and contradictory versions remain separate until reviewed. Test rotated scans, merged tables, malformed output, timeouts, duplicate callbacks and access-controlled deletion. Publish measured coverage and unresolved cases, not an unsupported accuracy target.","zh-TW":"執行驗收：每個接受欄位有來源位置；缺漏與零值分開；保留單位；重複型號與矛盾版本在查核前不合併。測試旋轉掃描、合併表格、錯誤輸出、逾時、重複 callback 與授權刪除。公布實測涵蓋率及未解案例，不設定無依據準確率。"}],"items":[]},{"number":24,"id":"graph","title":{"en":"Product graph position","zh-TW":"產品圖譜位置"},"paragraphs":[{"en":"Supplier Intelligence: monitor → catalog candidates → capability matching. Manufacturing Source-to-Quote can reuse the reviewed catalog with a separate buyer requirement. Shared product nodes retain one identity across suites; this page adds one specification, not another set of product counts.","zh-TW":"供應商情報流程：監看 → 型錄候選紀錄 → 能力匹配。製造來源到報價可搭配獨立買方需求重用查核型錄。跨流程共用節點保留同一身份；本頁增加一份規格，不另增重複產品數。"}],"items":[]},{"number":25,"id":"next","title":{"en":"Next related product","zh-TW":"下一個產品"},"paragraphs":[{"en":"Continue to Supplier Capability Matcher only after supplier/model identity, required field provenance and buyer requirements are available. If those inputs are missing, return to the source or prepare the RFQ input. The next product remains explicitly planned.","zh-TW":"只有供應商／型號身份、必要欄位來源及買方需求都具備，才進入 Supplier Capability Matcher。缺少輸入時，返回來源或準備 RFQ 輸入。下一個產品維持明確的規劃狀態。"}],"items":[]}],"research":[{"product":"Docling","role":"INTEGRATE","source_id":"docling","url":"https://docling-project.github.io/docling/","covered_capabilities":{"en":"Document conversion, table structure and JSON export; local execution is documented.","zh-TW":"文件轉換、表格結構及 JSON 匯出；文件記載本機執行能力。"},"integration_level":{"en":"Python library / CLI; select and pin the execution configuration.","zh-TW":"Python 函式庫／CLI；需選定並固定執行設定。"},"smart_tools_implication":{"en":"Candidate for an initial local PDF adapter.","zh-TW":"首個本機 PDF 適配器候選。"},"limitation":{"en":"Document parsing does not resolve a supplier identity or verify a catalog claim.","zh-TW":"文件解析不會認定供應商身份或證實型錄主張。"},"last_verified":"2026-10-08","smart_tools_connector_status":"PROPOSED","integration_test":"not-run"},{"product":"Unstructured","role":"INTEGRATE","source_id":"unstructured","url":"https://docs.unstructured.io/open-source/core-functionality/partitioning","covered_capabilities":{"en":"Partition documents into typed elements; PDF table extraction has strategy-specific options.","zh-TW":"將文件拆成具類型元素；PDF 表格擷取需選擇對應策略。"},"integration_level":{"en":"Open-source partition functions; keep element metadata with the output.","zh-TW":"開源 partition 函式；保留輸出元素的中繼資料。"},"smart_tools_implication":{"en":"Alternative when an existing document pipeline already uses its elements.","zh-TW":"既有文件流程已使用該元素格式時的替代候選。"},"limitation":{"en":"Page breaks and table behavior depend on format and strategy; verify on the chosen inputs.","zh-TW":"頁面分隔與表格行為依格式和策略而異，需以選定輸入核對。"},"last_verified":"2026-10-08","smart_tools_connector_status":"PROPOSED","integration_test":"not-run"},{"product":"Azure Document Intelligence","role":"BENCHMARK","source_id":"azure-layout","url":"https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/prebuilt/layout?view=doc-intel-4.0.0","covered_capabilities":{"en":"Layout analysis returns document text, tables and source-region information.","zh-TW":"版面分析回傳文件文字、表格及來源區域資訊。"},"integration_level":{"en":"Managed layout API; resource access and document handling require project review.","zh-TW":"託管版面 API；需核對資源權限與文件處理條件。"},"smart_tools_implication":{"en":"Compare managed output against the same labeled pages before selecting deployment.","zh-TW":"選定部署前，以相同標註頁面比較託管輸出。"},"limitation":{"en":"A recognized table is not a verified supplier/model record.","zh-TW":"辨識出的表格不等於已確認供應商／型號紀錄。"},"last_verified":"2026-10-08","smart_tools_connector_status":"PROPOSED","integration_test":"not-run"},{"product":"Diffbot Product API","role":"INTEGRATE","source_id":"diffbot-product","url":"https://www.diffbot.com/docs/extract/product","covered_capabilities":{"en":"Extract product identifiers, specifications and other data from commerce product pages.","zh-TW":"從商務產品頁擷取產品識別碼、規格與其他資料。"},"integration_level":{"en":"Hosted Product API; HTML/plain-text submission is documented.","zh-TW":"託管 Product API；文件記載 HTML／純文字提交介面。"},"smart_tools_implication":{"en":"Candidate for suitable web product pages rather than scanned engineering catalogs.","zh-TW":"適用網頁產品的候選，而非掃描工程型錄的通用替代品。"},"limitation":{"en":"Scope and field availability must be tested on the actual supplier pages.","zh-TW":"需以實際供應商頁面測試適用範圍與欄位可得性。"},"last_verified":"2026-10-08","smart_tools_connector_status":"PROPOSED","integration_test":"not-run"}],"sources":[{"evidence_id":"EV-SCE-DOCLING","link_id":"ref-sce-docling","title":"Docling official documentation","source_url":"https://docling-project.github.io/docling/","source_type":"official-documentation","level":"P1","retrieved_at":"2026-10-08","claim_supported":{"en":"Document conversion, table structure and JSON export; local execution is documented.","zh-TW":"文件轉換、表格結構及 JSON 匯出；文件記載本機執行能力。"},"verification":"official-source-reviewed","confidence":"source-supported;not-an-integration-test"},{"evidence_id":"EV-SCE-UNSTRUCTURED","link_id":"ref-sce-unstructured","title":"Unstructured official documentation","source_url":"https://docs.unstructured.io/open-source/core-functionality/partitioning","source_type":"official-documentation","level":"P1","retrieved_at":"2026-10-08","claim_supported":{"en":"Partition documents into typed elements; PDF table extraction has strategy-specific options.","zh-TW":"將文件拆成具類型元素；PDF 表格擷取需選擇對應策略。"},"verification":"official-source-reviewed","confidence":"source-supported;not-an-integration-test"},{"evidence_id":"EV-SCE-AZURE-LAYOUT","link_id":"ref-sce-azure-layout","title":"Azure Document Intelligence official documentation","source_url":"https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/prebuilt/layout?view=doc-intel-4.0.0","source_type":"official-documentation","level":"P1","retrieved_at":"2026-10-08","claim_supported":{"en":"Layout analysis returns document text, tables and source-region information.","zh-TW":"版面分析回傳文件文字、表格及來源區域資訊。"},"verification":"official-source-reviewed","confidence":"source-supported;not-an-integration-test"},{"evidence_id":"EV-SCE-DIFFBOT-PRODUCT","link_id":"ref-sce-diffbot-product","title":"Diffbot Product API official documentation","source_url":"https://www.diffbot.com/docs/extract/product","source_type":"official-documentation","level":"P1","retrieved_at":"2026-10-08","claim_supported":{"en":"Extract product identifiers, specifications and other data from commerce product pages.","zh-TW":"從商務產品頁擷取產品識別碼、規格與其他資料。"},"verification":"official-source-reviewed","confidence":"source-supported;not-an-integration-test"}],"links":[{"link_id":"product-sce-upstream","relation":"upstream","property":"industrial_ai","href":"/industrial-ai/automation","localize":true,"label":{"en":"Understand industrial automation","zh-TW":"理解產業自動化"},"reason":{"en":"Choose the task before the extraction engine.","zh-TW":"先選任務，再選擷取引擎。"},"status":"AVAILABLE"},{"link_id":"product-sce-previous","relation":"previous","property":"product","href":"/product/website-change-monitor","localize":true,"label":{"en":"Review the source change first","zh-TW":"先查核來源變更"},"reason":{"en":"Carry the changed document and fields into a catalog review.","zh-TW":"把變更文件與欄位帶入型錄查核。"},"status":"AVAILABLE"},{"link_id":"product-sce-next","relation":"next","property":"product","href":"/products/workflows#supplier-capability-matcher","localize":true,"label":{"en":"Inspect the capability-matching handoff","zh-TW":"查看能力匹配交接"},"reason":{"en":"Matcher execution remains planned; source and buyer inputs are required.","zh-TW":"匹配執行仍為規劃，須先具備來源與買方輸入。"},"status":"PLANNED"},{"link_id":"product-sce-alternative","relation":"alternative","property":"product","href":"/products/workflows#rfq-requirement-parser","localize":true,"label":{"en":"Start from buyer requirements instead","zh-TW":"改從買方需求開始"},"reason":{"en":"A planned input route for RFQ documents rather than supplier catalogs.","zh-TW":"面向 RFQ 文件的規劃輸入，而非供應商型錄。"},"status":"PLANNED"},{"link_id":"product-sce-company-evidence","relation":"evidence","property":"sites","href":"https://sites.smart-tools.ai","localize":false,"label":{"en":"Explore the company evidence network","zh-TW":"探索公司證據網路"},"reason":{"en":"Locate company context before accepting an entity match.","zh-TW":"接受實體對應前先找到公司脈絡。"},"status":"AVAILABLE"},{"link_id":"product-sce-source","relation":"evidence","property":"be_passive","href":"https://be-passive.com/sites/byte/library.html","localize":false,"label":{"en":"Open the original BYTE catalog library","zh-TW":"開啟 BYTE 原始型錄"},"reason":{"en":"Inspect source documents independently of the proposed extractor.","zh-TW":"獨立於規劃擷取器查閱原始文件。"},"status":"AVAILABLE"},{"link_id":"product-sce-commercial","relation":"commercial","property":"be_passive","href":"https://be-passive.com/sites/missions/oem/en?audience=buyers&industry=tooling-precision-manufacturing&content_id=supplier-catalog-extractor#inquiry","localize":false,"label":{"en":"Discuss a component requirement","zh-TW":"討論零件需求"},"reason":{"en":"Carry the product context into an existing requirement route; no inquiry is submitted by this link.","zh-TW":"把產品脈絡帶入既有需求入口；點擊不會自動提交詢價。"},"status":"AVAILABLE"},{"link_id":"product-sce-experience","relation":"experience","property":"be_passive","href":"https://be-passive.com/sites/byte/source-gallery.html#cad-source-comparison","localize":false,"label":{"en":"Explore the existing engineering source gallery","zh-TW":"探索既有工程來源圖庫"},"reason":{"en":"View an existing source experience; it is not an extraction demonstration.","zh-TW":"查看既有來源體驗，不代表擷取功能示範。"},"status":"AVAILABLE"}],"intents":[{"id":"supplier-specification","label":{"en":"Catalog field provenance","zh-TW":"型錄欄位來源"}}],"market_reality":[{"title":{"en":"Already solved","zh-TW":"已有成熟能力"},"body":{"en":"Document parsing and web product extraction have existing tools. Their output still needs review in the context of a specific supplier and requirement.","zh-TW":"文件解析與網頁產品擷取已有現成工具；輸出仍須依特定供應商與需求查核。"}},{"title":{"en":"Smart Tools opportunity","zh-TW":"Smart Tools 的機會"},"body":{"en":"Own versioned provenance, uncertainty and a reviewed decision handoff. Measure this contribution separately from parser accuracy.","zh-TW":"掌握版本化來源、未知條件與經查核的決策交接，並與解析準確率分開量測。"}}],"do_not_build":{"en":"Do not rebuild general OCR, PDF layout analysis, commodity web crawling or a provider-specific product parser. Add the supplier/model review and decision contract around an existing engine.","zh-TW":"不重做通用 OCR、PDF 版面分析、一般爬站或供應商已有的產品解析；在現成引擎外加入供應商／型號查核與決策契約。"},"implementation_delta":[{"area":{"en":"Product specification and bilingual page","zh-TW":"产品規格與雙語頁"},"status":"AVAILABLE"},{"area":{"en":"Provider adapter and catalog execution","zh-TW":"供應商適配器與型錄執行"},"status":"PROPOSED"},{"area":{"en":"Private review storage and reviewer authorization","zh-TW":"私密查核保存與權限"},"status":"PROPOSED"},{"area":{"en":"Supplier capability matching and graph writes","zh-TW":"供應商能力匹配與圖譜寫入"},"status":"PLANNED"},{"area":{"en":"Dedicated extraction Demo and RFQ outcome","zh-TW":"專用擷取 Demo 與 RFQ 結果"},"status":"NOT_CONNECTED"}],"seo":{"en":{"title":"Supplier Catalog Extractor — Traceable Field Specification | Smart Tools","description":"Evaluate catalog extraction with field-level provenance, document versions, review states and existing integration options. Product specification; extraction is not enabled."},"zh-TW":{"title":"供應商型錄擷取｜逐欄來源與交接規格 | Smart Tools","description":"評估型錄擷取的逐欄來源、文件版本、查核狀態與現成整合選項。提供完整產品規格；擷取服務尚未啟用。"}},"keywords":{"primary":"supplier catalog extraction","secondary":["catalog field provenance","supplier product data","PDF catalog extraction"],"intent":"evaluate-and-specify"},"adapter_contract":{"status":"PROPOSED;no-public-endpoint","source":{"document_id":"required","sha256":"computed-from-source-by-adapter","version":"explicit-or-unknown","captured_at":"known-or-null","access":"private-by-default"},"candidate_record":{"supplier_id":"unverified-until-reviewed","model_raw":"exact-source-text","fields":[{"name":"target-field","raw_text":"exact-excerpt","value":"parsed-value-or-null","unit":"source-unit-or-null","locator":{"page":"known-or-null","element_id":"known-or-null","bbox":"known-or-null"},"extraction_confidence":"provider-value-or-null","review_state":"needs-review"}]},"failure_states":["unsupported-format","encrypted-document","missing-source-locator","ambiguous-model","conflicting-version","unknown-unit","provider-timeout","quota-exhausted","malformed-output"],"acceptance":["every-accepted-field-has-source-locator","no-silent-unit-or-entity-inference","retry-does-not-duplicate-version","review-gates-graph-write"]},"kpis":["specification-view","specification-download","official-reference-click","next-step-click"],"unavailable_kpis":["extraction-quality","useful-result-rate","rfq-completion"],"analytics_status":"metadata-only;no-execution-results","network_route_review":"existing-source-routes-reviewed;no-receiving-site-submission","integrates":[{"product":"Docling","role":"INTEGRATE","source_id":"docling","url":"https://docling-project.github.io/docling/","covered_capabilities":{"en":"Document conversion, table structure and JSON export; local execution is documented.","zh-TW":"文件轉換、表格結構及 JSON 匯出；文件記載本機執行能力。"},"integration_level":{"en":"Python library / CLI; select and pin the execution configuration.","zh-TW":"Python 函式庫／CLI；需選定並固定執行設定。"},"smart_tools_implication":{"en":"Candidate for an initial local PDF adapter.","zh-TW":"首個本機 PDF 適配器候選。"},"limitation":{"en":"Document parsing does not resolve a supplier identity or verify a catalog claim.","zh-TW":"文件解析不會認定供應商身份或證實型錄主張。"},"last_verified":"2026-10-08","smart_tools_connector_status":"PROPOSED","integration_test":"not-run"},{"product":"Unstructured","role":"INTEGRATE","source_id":"unstructured","url":"https://docs.unstructured.io/open-source/core-functionality/partitioning","covered_capabilities":{"en":"Partition documents into typed elements; PDF table extraction has strategy-specific options.","zh-TW":"將文件拆成具類型元素；PDF 表格擷取需選擇對應策略。"},"integration_level":{"en":"Open-source partition functions; keep element metadata with the output.","zh-TW":"開源 partition 函式；保留輸出元素的中繼資料。"},"smart_tools_implication":{"en":"Alternative when an existing document pipeline already uses its elements.","zh-TW":"既有文件流程已使用該元素格式時的替代候選。"},"limitation":{"en":"Page breaks and table behavior depend on format and strategy; verify on the chosen inputs.","zh-TW":"頁面分隔與表格行為依格式和策略而異，需以選定輸入核對。"},"last_verified":"2026-10-08","smart_tools_connector_status":"PROPOSED","integration_test":"not-run"},{"product":"Diffbot Product API","role":"INTEGRATE","source_id":"diffbot-product","url":"https://www.diffbot.com/docs/extract/product","covered_capabilities":{"en":"Extract product identifiers, specifications and other data from commerce product pages.","zh-TW":"從商務產品頁擷取產品識別碼、規格與其他資料。"},"integration_level":{"en":"Hosted Product API; HTML/plain-text submission is documented.","zh-TW":"託管 Product API；文件記載 HTML／純文字提交介面。"},"smart_tools_implication":{"en":"Candidate for suitable web product pages rather than scanned engineering catalogs.","zh-TW":"適用網頁產品的候選，而非掃描工程型錄的通用替代品。"},"limitation":{"en":"Scope and field availability must be tested on the actual supplier pages.","zh-TW":"需以實際供應商頁面測試適用範圍與欄位可得性。"},"last_verified":"2026-10-08","smart_tools_connector_status":"PROPOSED","integration_test":"not-run"}],"benchmarks":[{"product":"Azure Document Intelligence","role":"BENCHMARK","source_id":"azure-layout","url":"https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/prebuilt/layout?view=doc-intel-4.0.0","covered_capabilities":{"en":"Layout analysis returns document text, tables and source-region information.","zh-TW":"版面分析回傳文件文字、表格及來源區域資訊。"},"integration_level":{"en":"Managed layout API; resource access and document handling require project review.","zh-TW":"託管版面 API；需核對資源權限與文件處理條件。"},"smart_tools_implication":{"en":"Compare managed output against the same labeled pages before selecting deployment.","zh-TW":"選定部署前，以相同標註頁面比較託管輸出。"},"limitation":{"en":"A recognized table is not a verified supplier/model record.","zh-TW":"辨識出的表格不等於已確認供應商／型號紀錄。"},"last_verified":"2026-10-08","smart_tools_connector_status":"PROPOSED","integration_test":"not-run"}],"evidence_sources":[{"evidence_id":"EV-SCE-DOCLING","link_id":"ref-sce-docling","title":"Docling official documentation","source_url":"https://docling-project.github.io/docling/","source_type":"official-documentation","level":"P1","retrieved_at":"2026-10-08","claim_supported":{"en":"Document conversion, table structure and JSON export; local execution is documented.","zh-TW":"文件轉換、表格結構及 JSON 匯出；文件記載本機執行能力。"},"verification":"official-source-reviewed","confidence":"source-supported;not-an-integration-test"},{"evidence_id":"EV-SCE-UNSTRUCTURED","link_id":"ref-sce-unstructured","title":"Unstructured official documentation","source_url":"https://docs.unstructured.io/open-source/core-functionality/partitioning","source_type":"official-documentation","level":"P1","retrieved_at":"2026-10-08","claim_supported":{"en":"Partition documents into typed elements; PDF table extraction has strategy-specific options.","zh-TW":"將文件拆成具類型元素；PDF 表格擷取需選擇對應策略。"},"verification":"official-source-reviewed","confidence":"source-supported;not-an-integration-test"},{"evidence_id":"EV-SCE-AZURE-LAYOUT","link_id":"ref-sce-azure-layout","title":"Azure Document Intelligence official documentation","source_url":"https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/prebuilt/layout?view=doc-intel-4.0.0","source_type":"official-documentation","level":"P1","retrieved_at":"2026-10-08","claim_supported":{"en":"Layout analysis returns document text, tables and source-region information.","zh-TW":"版面分析回傳文件文字、表格及來源區域資訊。"},"verification":"official-source-reviewed","confidence":"source-supported;not-an-integration-test"},{"evidence_id":"EV-SCE-DIFFBOT-PRODUCT","link_id":"ref-sce-diffbot-product","title":"Diffbot Product API official documentation","source_url":"https://www.diffbot.com/docs/extract/product","source_type":"official-documentation","level":"P1","retrieved_at":"2026-10-08","claim_supported":{"en":"Extract product identifiers, specifications and other data from commerce product pages.","zh-TW":"從商務產品頁擷取產品識別碼、規格與其他資料。"},"verification":"official-source-reviewed","confidence":"source-supported;not-an-integration-test"}],"related_products":[{"link_id":"product-sce-previous","relation":"previous","property":"product","href":"/product/website-change-monitor","localize":true,"label":{"en":"Review the source change first","zh-TW":"先查核來源變更"},"reason":{"en":"Carry the changed document and fields into a catalog review.","zh-TW":"把變更文件與欄位帶入型錄查核。"},"status":"AVAILABLE"},{"link_id":"product-sce-next","relation":"next","property":"product","href":"/products/workflows#supplier-capability-matcher","localize":true,"label":{"en":"Inspect the capability-matching handoff","zh-TW":"查看能力匹配交接"},"reason":{"en":"Matcher execution remains planned; source and buyer inputs are required.","zh-TW":"匹配執行仍為規劃，須先具備來源與買方輸入。"},"status":"PLANNED"},{"link_id":"product-sce-alternative","relation":"alternative","property":"product","href":"/products/workflows#rfq-requirement-parser","localize":true,"label":{"en":"Start from buyer requirements instead","zh-TW":"改從買方需求開始"},"reason":{"en":"A planned input route for RFQ documents rather than supplier catalogs.","zh-TW":"面向 RFQ 文件的規劃輸入，而非供應商型錄。"},"status":"PLANNED"}],"related_companies":[],"related_missions":[],"traffic_status":"not-measured-in-this-release","integration_test":"not-run-for-third-party-providers","seo_package":{"en":{"title":"Supplier Catalog Extractor — Traceable Field Specification | Smart Tools","description":"Evaluate catalog extraction with field-level provenance, document versions, review states and existing integration options. Product specification; extraction is not enabled."},"zh-TW":{"title":"供應商型錄擷取｜逐欄來源與交接規格 | Smart Tools","description":"評估型錄擷取的逐欄來源、文件版本、查核狀態與現成整合選項。提供完整產品規格；擷取服務尚未啟用。"},"indexable":true,"sitemap_group":"industrial-ai-workflows","lastmod_source":"meaningful-content-change","lastmod":"2026-10-08","language_variants":["en","zh-TW"],"hreflang":{"en":"https://smart-tools.ai/product/supplier-catalog-extractor","zh-TW":"https://smart-tools.ai/zh-tw/product/supplier-catalog-extractor","x-default":"https://smart-tools.ai/product/supplier-catalog-extractor"}}}