Skip to content

Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.

feat: 更新 README 文档,增强金融领域模板描述,增加财报电话会议及金融新闻相关模板

yuxizhec8c60adebb7d
diff --git a/hyperextract/templates/README.md b/hyperextract/templates/README.md
index a704e49..b1894e4 100644
--- a/hyperextract/templates/README.md
+++ b/hyperextract/templates/README.md
@@ -9,7 +9,7 @@ This library is organized by **Domain**, ensuring that the extraction logic matc
| Domain | Description | Key Focus |
| :--- | :--- | :--- |
| **`general`** | General Purpose | Arbitrary Text, Encyclopedias, Biographies |
-| **`finance`** | Finance & Investment | Reports, Filings, Transcripts |
+| **`finance`** | Finance & Investment | Reports, Filings, Transcripts, Earnings Calls, Market News |
| **`medicine`** | Medicine & Health | Clinical Records, Guidelines, Drug Info |
| **`tcm`** | Traditional Chinese Medicine | Case Records, Herbology, Acupuncture |
| **`industry`** | Industry | Maintenance, Safety, Operations |
@@ -63,6 +63,16 @@ The default choice for unstructured text that doesn't fit a specific industry.
### 2. `finance` (Finance)
Optimized for complex financial relationships, market sentiment, and temporal events.
+* **SEC Filings (10-K / 10-Q / 8-K)**: Standardized regulatory filings containing financial statements, management discussion, risk factors, and material event disclosures with complex document structures (tables, narratives, exhibits). *(Ref: [Financial Report Chunking for RAG, Yepes et al. 2024](https://arxiv.org/abs/2402.05131))*
+
+| Template Name | Primitive | Description | Typical Use Case |
+| :--- | :--- | :--- | :--- |
+| **`FilingFinancialSnapshot`** | `AutoModel` | **Financial Data Extraction**. Extracts key figures from income statements, balance sheets, and cash flow statements embedded in filings. | Fundamental screening, financial database population |
+| **`MDANarrativeGraph`** | `AutoGraph` | **MD&A Causal Map**. Extracts causal relationships from Management Discussion & Analysis (e.g., "Supply chain disruption -> Revenue decline -> Margin compression"). | Narrative analytics, driver attribution |
+| **`FilingRiskFactorSet`** | `AutoSet` | **Risk Factor Registry**. Deduplicates and catalogs all risk factors disclosed across Item 1A, tracking additions and removals between filing periods. | Risk evolution monitoring, cross-company risk comparison |
+| **`MaterialEventTimeline`** | `AutoTemporalGraph` | **8-K Event Timeline**. Chronologically extracts material events (executive changes, M&A announcements, restatements) from current reports. | Event-driven analysis, regulatory monitoring |
+| **`SegmentPerformanceList`** | `AutoList` | **Segment Breakdown**. Extracts revenue, operating income, and key metrics by business segment or geographic region. | Segment-level valuation, geographic exposure analysis |
+
* **Equity Research Reports**: Detailed analysis by analysts containing ratings, target prices, and investment logic.
| Template Name | Primitive | Description | Typical Use Case |
@@ -81,13 +91,23 @@ Optimized for complex financial relationships, market sentiment, and temporal ev
| **`ProceedsUsage`** | `AutoList` | **Fund Usage**. Details project names, allocated amounts, and estimated timelines for proceeds. | Post-IPO monitoring |
| **`CompanyHistoryTimeline`** | `AutoTemporalGraph` | **Corporate Milestones**. Chronological extraction of founding, funding rounds, and major pivots. | Due diligence, history mapping |
-* **M&A Due Diligence Reports**: Documents detailing legal risks, business synergies, and financial health of target companies.
+* **Earnings Call Transcripts**: Quarterly conference calls where management presents financial results and answers analyst questions, containing forward-looking guidance and sentiment signals. *(Ref: [HybridRAG, Sarmah et al. 2024](https://arxiv.org/abs/2408.04948))*
+
+| Template Name | Primitive | Description | Typical Use Case |
+| :--- | :--- | :--- | :--- |
+| **`EarningsCallSummary`** | `AutoModel` | **Call Overview**. Extracts reported metrics (Revenue, EPS), management guidance, and overall call tone (positive/cautious/negative). | Quarterly review dashboards, consensus tracking |
+| **`ManagementGuidanceList`** | `AutoList` | **Forward Guidance**. Extracts forward-looking statements: projected figures, strategic priorities, and qualitative outlook. | Guidance tracking, expectation management |
+| **`AnalystQAGraph`** | `AutoGraph` | **Q&A Interaction Map**. Maps analyst questions to management responses, capturing concerns raised and commitments made. | Analyst focus analysis, commitment tracking |
+| **`CallSentimentHypergraph`** | `AutoHypergraph` | **Topic-Sentiment Analysis**. Models multi-dimensional sentiment: `{Topic (Revenue/Margin/Guidance), Speaker, Sentiment, Driving Factor}` across the call. | Sentiment-driven trading signals, tone shift detection |
+
+* **Financial News & Market Commentary**: News articles, analyst commentaries, and social media posts conveying market sentiment, event impact, and forward-looking opinions about financial instruments or markets. *(Ref: [Survey of LLMs for Financial Applications, Nie et al. 2024](https://arxiv.org/abs/2406.11903))*
| Template Name | Primitive | Description | Typical Use Case |
| :--- | :--- | :--- | :--- |
-| **`SynergyMap`** | `AutoGraph` | **Synergy Network**. Analyzes complementary relationships between Acquirer and Target. | Value creation assessment |
-| **`LegalRiskRegistry`** | `AutoSet` | **Legal Encumbrances**. Deduplicates and lists pending litigations, compliance gaps, and IP disputes. | Risk clearing, valuation haircut |
-| **`KeyPersonnelProfile`** | `AutoModel` | **Management Profiles**. Extracts backgrounds, non-competes, and retention plans of target leadership. | Human capital assessment |
+| **`MarketSentimentModel`** | `AutoModel` | **Sentiment Snapshot**. Extracts sentiment polarity (Bullish/Bearish/Neutral), mentioned entities (tickers, sectors), and expected price impact. | Real-time sentiment feeds, trading signal generation |
+| **`FinancialEventCausalGraph`** | `AutoGraph` | **Event Impact Graph**. Maps financial events to affected entities and downstream market reactions (e.g., "Fed rate hike -> Bank sector rally -> Bond yield rise"). | Event-driven strategy, macro impact analysis |
+| **`MultiSourceSentimentHypergraph`** | `AutoHypergraph` | **Cross-Source Sentiment Fusion**. Integrates sentiment signals from multiple sources: `{News Article, Social Media Post, Analyst Note} -> Aggregated Sentiment -> Affected Entity`. | Ensemble sentiment scoring, fake signal filtering |
+| **`MarketNarrativeTimeline`** | `AutoTemporalGraph` | **Narrative Evolution Timeline**. Tracks how market narratives and dominant themes evolve over time (e.g., shift from "inflation fear" to "soft landing hope"). | Thematic investing, regime detection |
### 3. `medicine` (Medicine)
Focuses on causality, standardized terminology (UMLS mappings), and precise relationships.
diff --git a/hyperextract/templates/README_ZH.md b/hyperextract/templates/README_ZH.md
index 594aed3..0084a56 100644
--- a/hyperextract/templates/README_ZH.md
+++ b/hyperextract/templates/README_ZH.md
@@ -9,7 +9,7 @@
| 领域代码 | 领域名称 | 核心关注点 |
| :--- | :--- | :--- |
| **`general`** | 通用/百科 | 任意文本、百科全书、人物传记 |
-| **`finance`** | 金融投资 | 研报、公告、会议纪要 |
+| **`finance`** | 金融投资 | 财报、研报、会议纪要、金融资讯 |
| **`medicine`** | 医疗健康 | 临床指南、病历、药品文档 |
| **`tcm`** | 中医中药 | 医案、本草、方剂、经络 |
| **`industry`** | 工业 | 运维日志、安全报告、技术规格 |
@@ -63,6 +63,16 @@
### 2. `finance` (金融)
专注于提取复杂的交易关系、市场观点及时间敏感事件。
+* **SEC财报 (10-K / 10-Q / 8-K)**:提交给监管机构的标准化财务申报文件,涵盖财务报表、管理层讨论与分析 (MD&A)、风险因素及重大事件披露,具有复杂的文档结构(表格、叙述文本、附件)。
+
+| 模板名称 | 底层原语 | 描述 | 典型应用场景 |
+| :--- | :--- | :--- | :--- |
+| **`FilingFinancialSnapshot`** | `AutoModel` | **财务数据快照**。从申报文件中嵌入的利润表、资产负债表及现金流量表中提取关键财务数据。 | 基本面筛选、财务数据库构建 |
+| **`MDANarrativeGraph`** | `AutoGraph` | **MD&A 因果图谱**。从管理层讨论与分析部分提取因果关系(如"供应链中断 -> 营收下降 -> 利润率压缩")。 | 叙事分析、业绩驱动因素归因 |
+| **`FilingRiskFactorSet`** | `AutoSet` | **风险因素登记册**。去重汇总 Item 1A 中披露的所有风险因素,跟踪各报告期的新增与删除变化。 | 风险演变监控、跨公司风险对标 |
+| **`MaterialEventTimeline`** | `AutoTemporalGraph` | **重大事件时间轴**。按时间顺序提取 8-K 当期报告中的重大事件(高管变动、并购公告、财务重述等)。 | 事件驱动分析、合规监控 |
+| **`SegmentPerformanceList`** | `AutoList` | **分部业绩明细**。按业务分部或地理区域提取营收、经营利润等关键指标。 | 分部估值、区域风险敞口分析 |
+
* **股票研究报告 (Equity Research)**:分析师撰写的深度报告,包含评级、目标价及投资逻辑相关内容。
| 模板名称 | 底层原语 | 描述 | 典型应用场景 |
@@ -81,13 +91,23 @@
| **`ProceedsUsage`** | `AutoList` | **募资投向**。详细提取募投项目的名称、计划金额分配及预计时间表。 | 投后管理、资金使用合规 |
| **`CompanyHistoryTimeline`** | `AutoTemporalGraph` | **公司大事记**。按时间轴提取公司成立以来的融资、并购、管理层变更等里程碑。 | 投研尽调、企业图鉴 |
-* **并购尽职调查报告 (Due Diligence)**:详述目标公司的法律风险、业务协同效应及财务健康状况。
+* **财报电话会议 (Earnings Call Transcripts)**:管理层按季度发布的业绩说明会实录,包含财务数据解读、前瞻性指引及分析师问答,蕴含丰富的情感信号与预期信息。 *(参考: [HybridRAG, Sarmah et al. 2024](https://arxiv.org/abs/2408.04948))*
+
+| 模板名称 | 底层原语 | 描述 | 典型应用场景 |
+| :--- | :--- | :--- | :--- |
+| **`EarningsCallSummary`** | `AutoModel` | **电话会议概览**。提取核心披露指标(营收、EPS)、管理层指引及整体会议基调(积极/审慎/消极)。 | 季度回顾看板、一致性预期跟踪 |
+| **`ManagementGuidanceList`** | `AutoList` | **前瞻性指引**。提取管理层的前瞻性声明:预期数据、战略优先级及定性展望。 | 业绩指引跟踪、预期差分析 |
+| **`AnalystQAGraph`** | `AutoGraph` | **问答互动图谱**。映射分析师提问与管理层回答的对应关系,捕捉被关注的焦点问题及管理层承诺。 | 分析师关注点分析、承诺追踪 |
+| **`CallSentimentHypergraph`** | `AutoHypergraph` | **话题-情感分析超图**。建模多维情感信号:`{话题(营收/利润率/指引), 发言人, 情感倾向, 驱动因素}` 的复杂关联。 | 情感驱动交易信号、基调变化检测 |
+
+* **金融新闻与市场评论 (Financial News & Market Commentary)**:传递市场情绪、事件影响及前瞻性观点的新闻报道、分析师评论及社交媒体帖子。 *(参考: [Survey of LLMs for Financial Applications, Nie et al. 2024](https://arxiv.org/abs/2406.11903))*
| 模板名称 | 底层原语 | 描述 | 典型应用场景 |
| :--- | :--- | :--- | :--- |
-| **`SynergyMap`** | `AutoGraph` | **协同效应网络**。分析并购双方在业务板块、技术或市场上的互补关系。 | 并购价值评估、反垄断分析 |
-| **`LegalRiskRegistry`** | `AutoSet` | **法律风险登记册**。去重汇总所有未决诉讼、合规漏洞及知识产权争议记录。 | 风险排查、估值打折计算 |
-| **`KeyPersonnelProfile`** | `AutoModel` | **核心团队画像**。提取目标公司关键管理人员的背景、竞业条款及留任计划。 | 组织尽调、人才保留计划 |
+| **`MarketSentimentModel`** | `AutoModel` | **情绪快照**。提取情感极性(看涨/看跌/中性)、涉及实体(股票代码、板块)及预期价格影响方向。 | 实时情绪数据流、交易信号生成 |
+| **`FinancialEventCausalGraph`** | `AutoGraph` | **事件影响图谱**。映射金融事件到受影响实体及下游市场反应的因果链(如"美联储加息 -> 银行板块上涨 -> 债券收益率上升")。 | 事件驱动策略、宏观影响分析 |
+| **`MultiSourceSentimentHypergraph`** | `AutoHypergraph` | **多源情绪融合超图**。融合多渠道情绪信号:`{新闻报道, 社交媒体, 分析师研报} -> 聚合情绪 -> 受影响实体` 的多因素模型。 | 集成情绪评分、虚假信号过滤 |
+| **`MarketNarrativeTimeline`** | `AutoTemporalGraph` | **市场叙事演变轴**。追踪市场主流叙事与主题如何随时间演变(如从"通胀恐慌"转向"软着陆预期")。 | 主题投资、市场状态识别 |
### 3. `medicine` (医学)
专注于疾病诊疗逻辑、标准化术语映射及因果关系提取。