We build the Public-Document Automation System and sell it to institutional clients as an API, billed as an annual service fee plus call volume.
我們自研「公開資料自動化處理系統」，以應用程式介面（API）方式銷售予機構客戶，按年度服務費及調用量計費。
Research and analysis departments handle a large volume of public documents and data every day — listed-company announcements, periodic reports, industry statistics, public news. The formats are scattered and the volume is large. The work still depends on people reading and sorting by hand: slow, and expensive in headcount.
We build the Public-Document Automation System and open it to institutional clients as an application programming interface (API), callable directly from the client's own systems.
The system is exposed as an application programming interface (API) and called directly by the client's own systems, with no one in the middle moving files by hand. Below is the shape of a single call.
POST /v1/documents:extract
Content-Type: application/json
{
"source": "exchange_filing",
"document": { "uri": "<upload id or url>" },
"fields": [
"issuer", "period", "metrics", "events"
],
"summary": true,
"output_language": "zh-Hant"
}200 OK
{
"document_id": "<id>",
"source": "exchange_filing",
"fields": {
"issuer": { "value": "<text>", "page": "<int>" },
"period": { "value": "<date>", "page": "<int>" },
"metrics": [
{
"name": "<text>", "value": "<number>",
"unit": "<text>", "page": "<int>"
}
],
"events": [
{
"type": "<text>", "date": "<date>",
"page": "<int>"
}
]
},
"summary": {
"text": "<text>", "language": "zh-Hant"
},
"usage": { "pages": "<int>", "calls": 1 }
}The request and response below illustrate the data structure only. They are not an interface specification.
One primary interface service, plus two delivery and maintenance lines built around it.
Our value chain has three links, with purchases and sales matched one to one. Cost comes mainly from upstream compute and model interfaces; revenue comes from downstream API service and project delivery.
The algorithms produced by our own data-processing workflow, field definitions and structuring methods, and the processed output they generate, are our own intellectual property. The cloud providers acquire no rights by supplying the underlying resources.
Our clients are the research and operations departments of institutions. The purchasing decision is normally made by the client's information technology department or research department; the engagement is technology outsourcing.
Our business involves no physical goods, and there is no warehousing, logistics or shipping. The system, the processed output and the support are all delivered remotely.
To avoid any misunderstanding, we set out the boundaries of our business.
機構的研究與分析部門，日常須處理大量公開文檔與數據 —— 上市公司公告、定期報告、行業統計、公開新聞等。這些資料格式零散、數量龐大，長期依賴人工閱讀與手工整理，耗時且人力成本高。
本公司自研「公開資料自動化處理系統」，並以應用程式介面（API）方式向機構客戶開放，供客戶系統直接調用。
系統以應用程式介面（API）方式開放，由客戶的系統直接調用，不需要人再進來做一次搬運。下面是一次調用的結構示意。
POST /v1/documents:extract
Content-Type: application/json
{
"source": "exchange_filing",
"document": { "uri": "<upload id or url>" },
"fields": [
"issuer", "period", "metrics", "events"
],
"summary": true,
"output_language": "zh-Hant"
}200 OK
{
"document_id": "<id>",
"source": "exchange_filing",
"fields": {
"issuer": { "value": "<text>", "page": "<int>" },
"period": { "value": "<date>", "page": "<int>" },
"metrics": [
{
"name": "<text>", "value": "<number>",
"unit": "<text>", "page": "<int>"
}
],
"events": [
{
"type": "<text>", "date": "<date>",
"page": "<int>"
}
]
},
"summary": {
"text": "<text>", "language": "zh-Hant"
},
"usage": { "pages": "<int>", "calls": 1 }
}以下請求與返回僅用於說明數據結構，不構成正式接口規格。
一條主力的接口服務，加上兩條圍繞它的交付與維護業務。
本公司的價值鏈由三個環節構成，採購與銷售一一對應。成本主要來自上游算力與模型介面採購，收入來自下游 API 服務與項目交付。
以自研的數據處理流程、字段定義與結構化算法所產生的算法及加工成果，均為本公司自有知識產權；雲服務商不因提供底層資源而取得任何權利。
本公司的客戶為機構的研究與營運部門。採購決策通常由客戶的資訊科技部門或研究部門作出，性質屬於技術服務外包。
本公司業務不涉及任何實物貨品，沒有倉儲、物流與運輸安排。系統、處理成果與技術支持，全部以遠程方式交付。
為免誤解，本公司特此明確說明其業務邊界。