Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.
Enhance README_ZH.md with detailed templates for various domains including medicine, TCM, industry, history, biology, legal, literature, news, agriculture, and food. Each section now includes specific template names, underlying primitives, descriptions, and typical application scenarios to improve clarity and usability.
yifanfeng97ed6e18580e67
diff --git a/hyperextract/templates/README.md b/hyperextract/templates/README.mdindex 98723c5..fea8e28 100644--- a/hyperextract/templates/README.md+++ b/hyperextract/templates/README.md@@ -98,69 +98,298 @@ Optimized for complex financial relationships, market sentiment, and temporal ev### 3. `medicine` (Medicine)Focuses on causality, standardized terminology (UMLS mappings), and precise relationships.-* **Medical Textbooks & Monographs**: Systematized knowledge of anatomy, pathology, and treatment protocols (e.g., "Principles of Neural Science").-* **Clinical Practice Guidelines**: Standardized procedures for treating diseases, defining "Symptom -> Diagnosis -> Treatment" decision trees.-* **Discharge Summaries**: Narrative records of a patient's hospital stay, including admission reason, hospital course, and discharge instructions.-* **Pathology Reports**: Microscopic descriptions of tissue samples, detailing tumor grades, invasion depths, and histological features.-* **Drug Package Inserts**: Legal documents listing indications, contraindications, dosage, and adverse reactions.++* **Medical Textbooks & Monographs**: Systematized knowledge of anatomy, pathology, and treatment protocols.++| Template Name | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`PathologyHypergraph`** | `AutoHypergraph` | **Pathology Mechanism**. Models complex "Gene + Env + Trigger -> Disease" logic. | Research, clinical knowledge base |+| **`MedicalConceptNet`** | `AutoGraph` | **Medical Concept Net**. Extracts terminology and semantic relations (Is-A, Defined-As). | Taxonomy building, semantic search |+| **`PharmacologyGraph`** | `AutoGraph` | **Pharmacology Action**. Maps interactions between drugs, receptors, and physiological responses. | Drug mechanism analysis |+| **`AnatomyHierarchy`** | `AutoGraph` | **Anatomy Tree**. Builds hierarchical positions (Part-Of) and connectivity. | Anatomy atlases, surgical planning |+| **`SymptomDifferential`** | `AutoSet` | **Differential Table**. Summarizes symptoms and their corresponding differentiator diseases. | Diagnostic support, education |++* **Clinical Practice Guidelines**: Standardized procedures for treating diseases, defining decision trees.++| Template Name | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`TreatmentRegimenMap`** | `AutoHypergraph` | **Therapy Regimen**. Extracts multi-modal treatments comprising Drugs, Therapy, and Lifestyle. | Oncology protocols, chronic care |+| **`ClinicalPathway`** | `AutoGraph` | **Decision Pathway**. Extracts "If-Then-Else" structures for clinical decision trees. | Pathway management, standardization |+| **`LevelOfEvidence`** | `AutoList` | **Evidence Grading**. Extracts recommendations with associated Grade/Level of Evidence. | Clinical QA, research citations |++* **Discharge Summaries**: Narrative records of a patient's hospital stay.++| Template Name | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`SurgicalEventGraph`** | `AutoHypergraph` | **Surgical Event**. Models surgery as a complex event involving {Surgeon, Site, Procedure, Tools}. | Quality control, performance audit |+| **`HospitalCourseTimeline`** | `AutoTemporalGraph` | **Hospital Timeline**. Chronologically extracts admission, tests, procedures, and outcomes. | Case review, dispute tracing |+| **`DischargeInstruction`** | `AutoModel` | **Discharge Summary**. Extracts medications, follow-ups, and rehabilitation guidance. | Patient follow-up, management |++* **Pathology Reports**: Microscopic descriptions of tissue samples.++| Template Name | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`TumorStagingItem`** | `AutoModel` | **TNM Staging**. Extracts Tumor size (T), Node (N), Metastasis (M), and Stage. | Tumor registry, prognosis |+| **`MicroscopicFeatureSet`** | `AutoSet` | **Biomarker Registry**. Extracts immunohistochemistry (IHC) results and mutations. | Targeted therapy, research screening |++* **Drug Package Inserts**: Legal documents listing indications, contraindications, and interactions.++| Template Name | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`ComplexInteractionNet`** | `AutoHypergraph` | **Conditional Interaction**. Models high-order "Drug A + B + condition -> Reaction" logic. | CDSS, clinical safety |+| **`ContraindicationList`** | `AutoList` | **Contraindications**. Explicitly lists absolute contraindications (Pregnancy, etc.). | Prescription blocking |+| **`AdverseReactionStats`** | `AutoList` | **Adverse Reaction Stats**. Extracts reactions by system with frequency descriptions. | Pharmacovigilance |### 4. `tcm` (Traditional Chinese Medicine)Specialized for the unique logic of syndrome differentiation (`Bian Zheng`) and herbal compatibility.+* **Medical Case Records (Yi An)**: Clinical records from famous practitioners detailing symptoms, pattern differentiation logic, and the reasoning behind prescribed formulas.++| Template | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`SyndromeReasoningGraph`** | `AutoHypergraph` | **Reasoning Logic Graph**. Models the chain of `{Symptoms} -> Syndrome -> Principle -> {Formula}`. | Mining clinical experience, inheritance of TCM experts |+| **`PrescriptionModification`** | `AutoGraph` | **Formula Modification Logic**. Extracts additions/subtractions to a base formula based on specific symptoms. | Analysis of clinical medication rules |+| **`PulseTongueRecord`** | `AutoList` | **Pulse & Tongue Features**. Structured extraction of tongue body/coating and pulse characteristics. | Objectification of TCM diagnosis |+* **Herbal Compendiums (Ben Cao)**: Encyclopedic entries for single herbs describing their nature (Qi), flavor, meridian tropism, and functions.++| Template | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`HerbPropertyModel`** | `AutoModel` | **Herb Properties**. Extracts the Four Natures, Five Flavors, Meridian Tropism, and Toxicity. | TCM Basic Database Construction |+| **`CompatibilityNet`** | `AutoGraph` | **Compatibility Network**. Extracts "Seven Emotions" (Reinforcement, Counteraction, Incompatibility, etc.). | Contraindication warning, formula network analysis |+| **`ProcessingMethod`** | `AutoList` | **Processing Methods (Pao Zhi)**. Lists different processing methods (e.g., Honey-fried) and their effects. | TCM processing standards |+* **Prescription Formularies (Fang Zhu)**: Documents defining herbal formulas, including the role of each ingredient (Monarch, Minister, Assistant, Envoy).++| Template | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`FormulaComposition`** | `AutoHypergraph` | **Structural Composition**. Models the formula as a hierarchy of roles: `{Monarch, Minister, Assistant, Envoy}`. | Formula structure analysis |+| **`FunctionIndicationMap`** | `AutoGraph` | **Function-Indication Map**. Links Formula -> Functions -> Indicated Syndromes/Symptoms. | Formula recommendation systems |+* **Meridian & Acupoint Treatises**: Texts defining the anatomical location of acupoints and their specific therapeutic effects.+| Template | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`AcupointLocationMap`** | `AutoGraph` | **Acupoint Spatial Map**. Extracts relative locations based on anatomical landmarks (e.g., "2 cun lateral to navel"). | Acupuncture teaching, Acupoint Atlases |+| **`MeridianFlowGraph`** | `AutoGraph` | **Meridian Flow Graph**. Extracts the pathway and flow sequence of the twelve meridians. | Meridian theory education |+### 5. `industry` (Industry)Focuses on unstructured operational data in manufacturing, energy, and power sectors.+* **Maintenance Logs & Work Orders**: Field records of equipment failures, repair actions taken, and parts replaced. often containing jargon and abbreviations.++| Template | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`FailureKnowledgeHypergraph`** | `AutoHypergraph` | **Failure Hypergraph**. Models `{Structure, RootCause, Component, Solution}` multi-dimensional relations. | Diagnostic expert systems |+| **`MaintenaceOperationMap`** | `AutoHypergraph` | **Maintenance Operation Map**. Models the operation as a complex event: `{Operator, Tool, Object, Duration}`. | SOP standardization, Man-hour analysis |+| **`PartReplacementList`** | `AutoList` | **Spare Parts List**. Extracts replaced part numbers, quantities, and reasons. | Inventory prediction |+* **HSE Incident Reports**: Investigations into safety incidents, detailing the sequence of events, root causes, and corrective actions.++| Template | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`IncidentCausalityMap`** | `AutoHypergraph` | **Incident Causality**. Models the coupling of `{Hazard, Trigger, Violation, Consequence}`. | Risk prevention, Accident simulation |+| **`SafetyTimeline`** | `AutoTemporalGraph` | **Incident Timeline**. Reconstructs the sequence of alarms, actions, and responses. | Accident review, Drill planning |+* **Shift Handover Logs**: Summaries written by operators regarding equipment status changes, anomalies, and ongoing issues.++| Template | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`OpenIssueRegistry`** | `AutoSet` | **Open Issue Registry**. Deduplicated list of unresolved hazards or pending tasks. | Handover management |+| **`AbnormalParameterList`** | `AutoList` | **Abnormal Parameters**. Extracts mentions of abnormal values or alarms (e.g., "High Temp on T-101"). | Trend analysis |+* **Technical Specifications / Datasheets**: Semi-structured text describing equipment parameters, design standards, and performance curves.+| Template | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`SystemCompatibilityGraph`** | `AutoHypergraph` | **Compatibility Hypergraph**. Extracts `{Device, Condition, Constraint}` relationships for different environments. | Selection assistance, Design compliance |+| **`SpecParameterTable`** | `AutoModel` | **Key Specs Table**. Extracts rated power, material classes, and dimensional tolerances. | Digital asset delivery |+### 6. `history` (History)-Heavily focused on long-span timelines and social networks.-* **Historical Monographs**: Academic books analyzing specific eras, events, or figures with rich causal analysis and citations.-* **Chronicles & Annals**: Year-by-year records of events, focusing on temporal sequencing and regime changes.-* **Oral History Transcripts**: First-person narratives, often non-linear and focused on personal experiences within historical events.-* **Archival Correspondence**: Personal exchanges revealing social networks, hidden intents, and dates of specific interactions.+Focuses on long-span timelines and social network reconstruction.++* **Historical Monographs**: Academic books analyzing specific periods, events, or figures with causal depth.++| Template | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`HistoricalKnowledgeGraph`** | `AutoGraph` | **General History Graph**. Extracts basic relationships (Kinship, Minister-Ruler) and causality. | Historical Social Network Analysis |+| **`MultiParticipantEventMap`** | `AutoHypergraph` | **Multi-Participant Event Map**. Models events as hyperedges connecting all participants (e.g., "Feast at Hong Gate"). | Complex event reconstruction |++* **Chronicles**: Strictly chronological records focusing on temporal evolution.++| Template | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`ChronologicalEventChain`** | `AutoTemporalGraph` | **Event Chain**. Extracts atomic events with precise timestamps. | Timeline generation |+| **`HistoricalContextGraph`** | `AutoGraph` | **Historical Context Graph**. Extracts static relationships (kinship, alliances) underlying the events. | Background mining |+| **`PoliticalStruggleHypergraph`** | `AutoHypergraph` | **Political Struggle Hypergraph**. Models `{Attacker, Defender, Planner, Traitor}` in battles or coups. | Faction analysis, Battle review |++* **Oral History**: First-person memoirs containing non-linear narratives and personal details.++| Template | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`PersonalTrajectoryHypergraph`** | `AutoHypergraph` | **Personal Trajectory Hypergraph**. Models life stages as hyperedges: `{Period, Location, Peers, Experience}`. | Biography writing, Life course research |+| **`NarrativeRelationGraph`** | `AutoGraph` | **Narrative Relation Graph**. Extracts interpersonal interactions and evaluations from the narrator's perspective. | Oral history social network analysis |+| **`MemoryFlashbackList`** | `AutoList` | **Memory Flashbacks**. Extracts specific anecdotes, feelings, or side descriptions of historical moments. | Historical detail supplementation |++* **Archival Correspondence**: Letters between historical figures revealing hidden social networks.++| Template | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`EpistolaryKnowledgeGraph`** | `AutoGraph` | **Epistolary Content Graph**. Extracts entities and relations mentioned *within* the letter text, rather than just sender/receiver metadata. | Historical material mining |### 7. `biology` (Biology)Goes beyond genomics to include proteomics, metabolism, and ecology.+* **Biological Monographs**: Specialized books detailing species taxonomy, evolutionary history, or complex biological systems.-* **Protein Structure Summaries (PDB Headers)**: Descriptions of protein crystal structures, ligand binding sites, and post-translational modifications.++| Template | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`SpeciesInteractionWeb`** | `AutoGraph` | **Species Interaction Network**. Extracts predation, parasitism, competition, and symbiosis relations. | Food web analysis, Ecosystem modeling |+| **`TaxonomicTree`** | `AutoGraph` | **Taxonomic Tree**. Builds hierarchical relationships (Kingdom -> Phylum -> ... -> Species). | Biological taxonomy database |++* **Protein Structure Summaries**: Descriptions of protein crystal structures, ligand binding sites, and post-translational modifications.++| Template | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`ProteinComplexMap`** | `AutoHypergraph` | **Protein Complex Hypergraph**. Models multi-subunit assemblies: `{SubunitA, SubunitB, Cofactor}` forming one functional complex. | Complex databases, Structural research |+| **`BindingSiteModel`** | `AutoModel` | **Binding Site Profile**. Extracts active site residues, binding pocket chemistry, and functional annotations. | Drug design, Mutation analysis |+* **Metabolic Pathway Descriptions**: Texts explaining biochemical cascades, detailing enzymes, substrates, products, and regulation mechanisms.-* **Ecological Survey Reports**: Documents recording species distribution, abundance, and habitat characteristics in specific geographic areas.-* **Taxonomic Descriptions**: Detailed physical characterizations of organisms used for classification and identification.++| Template | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`BiochemicalReactionHypergraph`** | `AutoHypergraph` | **Reaction Hypergraph**. Precisely models multi-input/output reactions: `{Enzyme + SubstrateA + SubstrateB -> ProductC + ProductD}`. | Pathway mapping, Metabolic engineering |+| **`RegulatoryNetwork`** | `AutoGraph` | **Gene Regulatory Network**. Extracts transcription factor -> promoter -> gene expression relationships (activation, inhibition, cooperation). | Gene regulation analysis, Systems biology |++* **Ecological Surveys**: Detailed physical characterizations and systematic relationships of organisms, as well as species distribution and habitat characteristics from field surveys.++| Template | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`PhylogeneticRelationGraph`** | `AutoGraph` | **Phylogenetic Relations**. Extracts evolutionary relationships, divergence distances, and branching patterns. | Molecular systematics, Evolutionary tree building |+| **`BiodiversityRegistry`** | `AutoSet` | **Species Registry**. Deduplicates and consolidates observed species and population information from survey reports. | Biodiversity assessment, Conservation prioritization |### 8. `legal` (Legal)Handles precise logical conditions, obligations, and citations.+* **Legal Treatises / Commentaries**: Scholarly books analyzing legal principles, statutes, and case law logic.++| Template | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`LegalConceptOntology`** | `AutoGraph` | **Legal Concept Ontology**. Extracts definitions, hierarchical relationships (Is-A), and statutory interpretations from academic texts. | Legal research, Educational systems |+| **`CaseLawCitationNet`** | `AutoGraph` | **Citation Network**. Maps how cases cite, distinguish, or overrule previous precedents. | Precedent analysis, Legal history map |+* **Master Service Agreements (MSA)**: Contracts defining long-term business relationships, liability limits, and intellectual property rights.++| Template | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`ContractObligationHypergraph`** | `AutoHypergraph` | **Obligation Hypergraph**. Models complex conditional obligations: `{Party, Duty, Trigger Condition, Exception, Penalty}`. | Contract review, Compliance automation |+| **`DefinedTermRegistry`** | `AutoSet` | **Defined Terms Registry**. Deduplicates definitions of capitalized terms (e.g., "Confidential Information") across the document. | Contract consistency check |+| **`LiabilityClauseList`** | `AutoList` | **Liability Clauses**. Extracts specific clauses regarding indemnification, limitations of liability, and warranties. | Risk assessment, Deal comparison |+* **Court Judgments**: Final rulings by judges, containing fact-finding sections, legal reasoning, and citations of precedents.++| Template | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`CaseFactTimeline`** | `AutoTemporalGraph` | **Fact Timeline**. Reconstructs the chronological sequence of events leading to the dispute from the "Findings of Fact" section. | Case analysis, Evidence marshalling |+| **`AdjudicationLogic`** | `AutoHypergraph` | **Reasoning Hypergraph**. Models the judicial logic: `{Proven Fact + Applicable Law -> Legal Conclusion}`. | Judgment prediction, Legal reasoning Support |+| **`LitigationParticipantMap`** | `AutoGraph` | **Participant Map**. Maps relationships between plaintiffs, defendants, counsel, and witnesses. | Conflict of interest check |+* **Regulatory Compliance Filings**: Detailed reports submitted to government bodies regarding data privacy, anti-money laundering, or environmental impact.+| Template | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`ComplianceRequirementList`** | `AutoList` | **Requirement Checklist**. Extracts specific affirmative duties or negative covenants mandated by the filing. | Regulatory gap analysis |+| **`BeneficialOwnershipGraph`** | `AutoGraph` | **Ownership Structure**. Traces complex corporate ownership layers to identify Ultimate Beneficial Owners (UBO). | AML/KYC screening, Sanctions check |+### 9. `literature` (Literature & Fiction)Focuses on narrative structure, character interactions, and world-building.+* **Screenplays / Scripts**: Highly structured texts (Scene Heading, Action, Dialogue) ideal for extracting character interaction graphs.-* **Character Bibles**: Internal documents describing character backstories, personality traits, and relationships.++| Template | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`SceneEventHypergraph`** | `AutoHypergraph` | **Scene Event Hypergraph**. Models a scene as a hyperedge connecting `{Characters, Location, Props, Key Actions}`. | Scene complexity analysis, Shooting schedule planning |+| **`CharacterArcTimeline`** | `AutoTemporalGraph` | **Character Arc Timeline**. Tracks a character's location, emotional state, or key actions chronologically through the script. | Character development analysis, Continuity check |++* **Novels**: Texts with complex plots, numerous characters, and interwoven relationships.++| Template | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`ComplexCharacterRelation`** | `AutoHypergraph` | **Complex Character Relation**. Models multi-party social structures (e.g., Love Triangles, Alliances, Factions) beyond simple pairwise links. | Ensemble analysis, Fan wiki consistency |+| **`StoryEntityGraph`** | `AutoGraph` | **Story Entity Graph**. Focuses on key items, locations, and their ownership/location, distinct from character relations. | World-building database, Licensed game adaptation |+| **`NarrativeEventChain`** | `AutoTemporalGraph` | **Narrative Event Chain**. Extracts key plot points strictly following the story's internal timeline. | Synopsis generation, Timeline reconstruction |+* **Literary Criticism**: Analytical texts exploring themes, motifs, and intertextuality.-### 10. `travel` (Travel)-Focuses on spatial relationships and temporal sequences.-* **Travel Itineraries**: Sequential plans including times, locations (POIs), transport modes, and accommodation.-* **Destination Guides**: Comprehensive descriptions of places, including top logical relations (Next To, Inside) and cultural tips.+| Template | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`MotifAssociationNet`** | `AutoGraph` | **Motif Association Net**. Links recurring symbols and motifs (nodes are all "Motifs") based on co-occurrence. | Systematic text analysis, Semiotics |+| **`CritiqueArgumentHypergraph`** | `AutoHypergraph` | **Argument Hypergraph**. Models complex argumentation: `{Evidence1, Evidence2, Quoted Text} -> Core Thesis`. | Academic paper analysis, Thesis extraction |+| **`NarrativeStructureTree`** | `AutoGraph` | **Narrative Structure Tree**. Maps the hierarchical structure of the narrative (e.g., Frame Story -> Main Plot -> Subplot). | Narratology, Structure analysis |++### 10. `news` (News & Journalism)+Focuses on the "5Ws" (Who, What, Where, When, Why), event causality, and viewpoint analysis.++* **Investigative Journalism**: Long-form reporting revealing complex societal relationships or hidden truths.++| Template | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`InvestigativeContextGraph`** | `AutoGraph` | **Investigation Context Graph**. Extracts baseline static relationships (employment, kinship, location) between all entities mentioned in the report. | Entity mapping, Stakeholder identification |+| **`ComplexRelationNet`** | `AutoHypergraph` | **Complex Relationship Network**. Models multi-party social connections (e.g., family ties, political alliances, business partnerships) involving three or more entities. | Political analysis, feature stories |+| **`KeyEventSequence`** | `AutoTemporalGraph` | **Investigative Timeline**. Traces the chronological sequence of critical events discovered during an investigation. | Retrospective reports, backgrounders |-### 11. `news` (News)-Focuses on the "5Ws" (Who, What, Where, When, Why) and causality.-* **Investigative Features**: Long-form reporting revealing complex causal chains and multi-party stakeholder relationships.* **Breaking News Wires**: Short, factual updates focusing on immediate events and entities.-### 12. `agriculture` (Agriculture)-* **Agricultural Manuals**: Technical guides on crop management, planting standards, and pest control techniques.-* **Crop Scouting Reports**: Observations of crop growth stages, pest identification, and disease severity.-* **Soil Analysis Reports**: Textual descriptions of soil chemical properties and corresponding fertilizer recommendations.+| Template | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`NewsEntityGraph`** | `AutoGraph` | **Core Entity Graph**. Quickly extracts key subjects (who) and their direct actions (what) or relations. | News feeds, entity linking |+| **`NewsSummaryModel`** | `AutoModel` | **Structured Summary**. Standardized extraction of 5W1H elements (Who, What, When, Where, Why, How). | News aggregation, Ticker generation |+| **`LiveUpdateTimeline`** | `AutoTemporalGraph` | **Live Event Timeline**. Extracts minute-by-minute updates of an unfolding situation (e.g., press conferences, emergencies). | Live blog summary, Crisis monitoring |++* **Policy Analysis & Editorials**: Analytical pieces focusing on opinions, arguments, and future impacts.++| Template | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`ViewpointStructure`** | `AutoHypergraph` | **Argument Structure**. Models the logical structure of an editorial: `{Claim, Premises/Evidence, Conclusion}`. | Opinion mining, editorial analysis |+| **`ImpactChain`** | `AutoGraph` | **Policy Impact Chain**. Extracts causal chains predicting how a policy or event affects specific groups or sectors. | Policy reviews, trend analysis |++### 11. `agriculture` (Agriculture)+Focuses on crop lifecycle management, field monitoring, and soil health data.++* **Agricultural Manuals**: Technical guides on crop planting standards, field management practices, and pest/disease control techniques.++| Template | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`CropGrowthCycle`** | `AutoTemporalGraph` | **Crop Growth Cycle Timeline**. Extracts key farming operations and environmental conditions required at each growth stage (seeding, tillering, maturation, etc.). | Planting calendar generation, Task scheduling |+| **`PestControlHypergraph`** | `AutoHypergraph` | **Pest Control Logic**. Models complex intervention rules: `{Crop, Growth Stage, Adverse Factor} -> {Target Disease/Pest, Recommended Agent, Dosage, Safe Interval}`. | Smart crop protection systems, Pesticide recommendation |++* **Crop Scouting Reports**: Field observation records of crop growth stages and pest/disease conditions.++| Template | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`FieldObservationList`** | `AutoList` | **Field Observation Log**. Structured extraction of scouting records: `{Field ID, Crop, Growth Stage, Observed Issue (Weed/Pest), Severity, Recommendation}`. | Scouting digitization, Pest/disease early warning |++* **Soil Analysis Reports**: Reports describing soil chemical composition and corresponding fertilization recommendations.++| Template | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`SoilNutrientModel`** | `AutoModel` | **Soil Nutrient Profile**. Extracts core physicochemical indicators (pH, Organic Matter, N-P-K, micronutrients). | Soil-testing-based fertilizer prescription, Soil fertility grading |+| **`AmendmentPlan`** | `AutoGraph` | **Soil Amendment Plan**. Maps the logic: `{Test Result -> Limiting Factor -> Amendment Method -> Target Outcome}`. | Precision agriculture prescription generation |++### 12. `food` (Food)+Focuses on recipe standardization, ingredient pairing logic, and food review data.-### 13. `food` (Food)-* **Standardized Recipes**: Step-by-step instructions including ingredients, preparation methods, and critical control points.-* **Menu Engineering Reports**: Analysis of dishes involving flavor profiles, ingredients, and customer preferences.+* **Standardized Recipes**: Structured texts containing ingredient lists, cooking steps, and critical control points.++| Template Name | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`RecipeCollection`** | `AutoSet` | **Recipe Catalog**. Deduplicates and extracts all unique dish entities and basic classifications from text. | Menu digitization, dish index construction |+| **`StandardRecipeCard`** | `AutoModel` | **Standard Recipe Card**. Extracts complete ingredient list, step-by-step instructions, and key TIPS for a single dish. | Kitchen SOP cards, cooking instruction |+| **`IngredientCompositionHypergraph`** | `AutoHypergraph` | **Ingredient Pairing Hypergraph**. Models the complex combination of `{Dish, Main Ingredient, Accessory, Seasoning}`. | Cost calculation, allergen management, R&D |++* **Food Reviews**: Detailed evaluation records by professional food critics or R&D teams.++| Template Name | Primitive | Description | Typical Use Case |+| :--- | :--- | :--- | :--- |+| **`DishReviewSummary`** | `AutoList` | **Dish Review Summary**. Extracts core review points, recommendation level, and price perception by dish. | Structured exploration notes, must-try lists |+| **`SensoryEvaluationGraph`** | `AutoGraph` | **Sensory Evaluation Graph**. Extracts `{Dish} -[has feature]-> {Taste/Texture} -[attributed to]-> {Ingredient/Technique}` evaluation logic. | Flavor attribution analysis, R&D feedback |diff --git a/hyperextract/templates/README_ZH.md b/hyperextract/templates/README_ZH.mdindex e66e5a6..3c2ed10 100644--- a/hyperextract/templates/README_ZH.md+++ b/hyperextract/templates/README_ZH.md@@ -98,70 +98,299 @@### 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。-* **医学教科书与专著**:系统性阐述解剖、病理、药理及治疗原则的专业书籍(如《神经科学原理》)。-* **临床诊疗指南 (Clinical Guidelines)**:权威机构发布的标准化文档,定义了“症状-诊断-治疗-预后”的决策路径。-* **出院小结 (Discharge Summaries)**:患者住院全过程的叙述性记录,包含入院主诉、诊疗经过及出院医嘱。-* **病理报告 (Pathology Reports)**:对组织样本的微观描述,包含肿瘤分级、侵润深度及细胞学特征。-* **药品说明书 (Package Inserts)**:法律规定的药品文档,包含适应症、禁忌症、不良反应及药物相互作用。++* **医学教科书与专著**:系统性阐述解剖、病理、药理及治疗原则的专业书籍。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`PathologyHypergraph`** | `AutoHypergraph` | **多因素病理机制图**。建模“基因+环境+诱因 -> 疾病”的复杂致病逻辑。 | 疾病原理研究、知识库构建 |+| **`MedicalConceptNet`** | `AutoGraph` | **医学概念网络**。提取医学术语及其关联属性(如:属于、定义为)。 | 术语标准化、语义搜索 |+| **`PharmacologyGraph`** | `AutoGraph` | **药理机制图**。提取药物、受体、靶点及生理反应之间的相互作用路径。 | 药理逻辑梳理、新药研发 |+| **`AnatomyHierarchy`** | `AutoGraph` | **解剖层级树**。构建解剖位置的包含 (Part-Of) 和毗邻 (Connected-To) 关系。 | 解剖学图谱、手术导航基础 |+| **`SymptomDifferential`** | `AutoSet` | **鉴别诊断表**。汇总症状与其对应的鉴别疾病列表,形成症状-疾病映射。 | CDSS 辅助诊断、教学系统 |++* **临床诊疗指南 (Clinical Guidelines)**:权威机构发布的标准化文档,定义了决策路径。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`TreatmentRegimenMap`** | `AutoHypergraph` | **综合治疗方案图**。提取由“药物组合+理疗+生活干预”构成的多因素治疗方案。 | 肿瘤化疗方案、慢病管理 |+| **`ClinicalPathway`** | `AutoGraph` | **临床路径图**。提取“If 症状A Then 检查B Else 治疗C”的决策树结构。 | 临床路径管理、诊疗规范化 |+| **`LevelOfEvidence`** | `AutoList` | **证据评级表**。提取指南中的具体推荐意见及其对应的证据等级。 | 设计临床质控方案、科研引用 |++* **出院小结 (Discharge Summaries)**:患者住院全过程的叙述性记录。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`SurgicalEventGraph`** | `AutoHypergraph` | **手术事件超图**。将手术建模为 {医生, 部位, 术式, 器械} 共同参与的复杂事件。 | 手术质控、绩效评估 |+| **`HospitalCourseTimeline`** | `AutoTemporalGraph` | **住院病程时间轴**。严格按时间顺序提取入院、检查、治疗、转归等节点。 | 病历质控、医疗纠纷溯源 |+| **`DischargeInstruction`** | `AutoModel` | **出院医嘱摘要**。提取出院带药、复诊计划及康复建议的结构化信息。 | 患者随访、慢病续方 |++* **病理报告 (Pathology Reports)**:对组织样本的微观描述。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`TumorStagingItem`** | `AutoModel` | **TNM 分期表**。提取肿瘤大小(T)、淋巴结(N)、转移(M)及分期结果。 | 肿瘤登记、预后评估 |+| **`MicroscopicFeatureSet`** | `AutoSet` | **微观特征集**。提取免疫组化指标(如 HER2+, Ki67)及基因突变状态。 | 靶向药匹配、科研入组筛选 |++* **药品说明书 (Package Inserts)**:法律规定的药品文档,包含适应症、禁忌症等内容。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`ComplexInteractionNet`** | `AutoHypergraph` | **条件性相互作用网**。建模“药A+药B+特定体质 -> 不良反应”的高阶依赖。 | 合理用药系统 (高级版) |+| **`ContraindicationList`** | `AutoList` | **禁忌症清单**。提取绝对禁忌(如孕妇、严重肾衰竭等)的明确列表。 | 处方拦截、用药安全监测 |+| **`AdverseReactionStats`** | `AutoList` | **不良反应统计**。提取各系统的不良反应表现及其发生率描述。 | 药物警戒、安全性评价 |### 4. `tcm` (中医中药)针对中医特有的辨证论治逻辑和药性理论进行优化。+* **名医医案 (Medical Case Records)**:记录“望闻问切”症状、辨证分析(理)、治法(法)及处方(方药)的临床实录。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`SyndromeReasoningGraph`** | `AutoHypergraph` | **辨证论治逻辑图**。建模 `{症状群} -> 证型 -> 治则 -> {处方}` 的完整推理链条。 | 医案数据挖掘、名老中医经验传承 |+| **`PrescriptionModification`** | `AutoGraph` | **处方加减逻辑**。提取基于特定症状对基础方剂进行的药物加减(如“随证加减”)。 | 临证用药规律分析 |+| **`PulseTongueRecord`** | `AutoList` | **舌脉特征提取**。结构化提取舌象(质、苔)与脉象描述,用于统计分析。 | 中医诊断客观化研究 |+* **本草典籍 (Herbal Compendiums)**:描述单味药的四气五味、归经、功效主治及配伍禁忌的文本。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`HerbPropertyModel`** | `AutoModel` | **药物性味归经**。提取单味药的四气五味、归经、毒性及推荐剂量。 | 中药基础数据库构建 |+| **`CompatibilityNet`** | `AutoGraph` | **七情配伍网络**。提取药物间的相须、相使、相畏、相杀、十八反十九畏关系。 | 配伍禁忌预警、方剂组网分析 |+| **`ProcessingMethod`** | `AutoList` | **炮制方法列表**。提取药物的不同炮制方法(如蜜炙、酒炒)及其对药效的影响。 | 中药炮制规范、饮片管理 |+* **方剂规范 (Prescription Formularies)**:记载方剂组成的文档,包含君臣佐使的配伍结构及煎服法。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`FormulaComposition`** | `AutoHypergraph` | **君臣佐使结构图**。将方剂建模为 `{君药, 臣药, 佐药, 使药}` 的层级化超边结构。 | 方剂结构解析、组方规律研究 |+| **`FunctionIndicationMap`** | `AutoGraph` | **主治功效映射**。关联 方剂 -> 功能(如清热解毒) -> 主治证候。 | 方剂推荐系统 |+* **经络腧穴专著 (Meridian Treatises)**:描述穴位解剖定位、归经及其特定主治功能的文本。+| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`AcupointLocationMap`** | `AutoGraph` | **腧穴空间定位**。基于人体解剖标志提取穴位的相对位置关系(如“脐旁2寸”)。 | 针灸教学可视化、穴位图谱 |+| **`MeridianFlowGraph`** | `AutoGraph` | **经络流注图**。提取十二经脉的循行路线及经气流注次序。 | 经络理论教学 |+### 5. `industry` (工业)专注于电力、制造、能源等行业的运维数据与非结构化日志分析。+* **维修日志与工单 (Maintenance Logs)**:现场人员记录的设备故障现象、维修措施及备件更换情况,常包含大量行业术语。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`FailureKnowledgeHypergraph`** | `AutoHypergraph` | **故障知识超图**。建模 `{故障现象, 根因, 涉及部件, 解决方案}` 多维关联,解决单一因果无法覆盖复杂故障的问题。 | 故障诊断专家系统、维修知识库 |+| **`MaintenaceOperationMap`** | `AutoHypergraph` | **维修作业图**。将维修作业视为一个复杂事件,关联 `{操作人, 使用工具, 操作对象, 动作耗时}`。 | 维修动作标准化、工时定额分析 |+| **`PartReplacementList`** | `AutoList` | **备件消耗清单**。结构化提取更换的具体零件型号、数量及更换原因。 | 备件库存预测、供应链优化 |+* **HSE安全事故报告 (Incident Reports)**:对生产事故的调查报告,包含事件时间线、根本原因分析 (RCA) 及整改措施。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`IncidentCausalityMap`** | `AutoHypergraph` | **事故因果链超图**。建模 `{隐患, 触发条件, 违章行为, 事故后果}` 的多因素耦合关系。 | 安全风险双重预防机制、事故推演 |+| **`SafetyTimeline`** | `AutoTemporalGraph` | **事故时序图**。还原事故发生前后的关键操作、报警与响应序列。 | 事故复盘、应急预案演练 |+* **交接班记录 (Shift Handover)**:运行人员记录的设备状态变化、异常参数及遗留问题。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`OpenIssueRegistry`** | `AutoSet` | **遗留问题登记**。去重汇总当前未解决的隐患、待办事项及挂牌情况。 | 交接班管理、隐患排查闭环 |+| **`AbnormalParameterList`** | `AutoList` | **异常参数记录**。提取交接班中重点提及的数值异常或状态报警(如“T-101温度偏高”)。 | 运行状态趋势分析 |+* **技术规格书 (Technical Specifications)**:描述设备额定参数、材质标准及性能曲线的半结构化文本。+| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`SystemCompatibilityGraph`** | `AutoHypergraph` | **系统兼容性超图**。提取设备与不同环境、介质、电压等级之间的 `{设备, 适用工况, 限制条件}` 对应关系。 | 选型辅助、设计合规性检查 |+| **`SpecParameterTable`** | `AutoModel` | **核心规格表**。提取额定功率、材质、尺寸精度等关键技术指标。 | 主要设备台账构建、数字化交付 |+### 6. `history` (历史)专注于长跨度的时间线梳理及人物社会网络构建。-* **历史专著**:对特定断代、事件或人物进行深度因果分析与考证的学术书籍。++* **历史专著 (Historical Monographs)**:对特定断代、事件或人物进行深度因果分析与考证的学术书籍。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`HistoricalKnowledgeGraph`** | `AutoGraph` | **通用历史图谱**。提取基础的人物关系(亲属、君臣、敌友)及事件因果。 | 历史人物关系网构建 |+| **`MultiParticipantEventMap`** | `AutoHypergraph` | **多方事件超图**。将历史事件建模为连接多个参与者的超边(如“鸿门宴”连接项羽、刘邦等)。 | 复杂历史事件还原、群像分析 |+* **编年史 (Chronicles)**:按严格时间顺序记录的历史事件,侧重于时序演变。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`ChronologicalEventChain`** | `AutoTemporalGraph` | **编年事件链**。提取带精确时间戳的原子事件,严格还原时间线。 | 历史大事年表生成 |+| **`HistoricalContextGraph`** | `AutoGraph` | **历史背景关联图**。提取事件背后的人物关系、地缘政治等静态关联。 | 历史事件背景挖掘 |+| **`PoliticalStruggleHypergraph`** | `AutoHypergraph` | **政治博弈超图**。针对战役或政争,提取 `{攻方, 守方, 策划者, 变节者}` 的复杂互动。 | 战役复盘、派系斗争分析 |+* **口述历史 (Oral History)**:亲历者的第一人称回忆录,包含非线性叙事及个人视角细节。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`PersonalTrajectoryHypergraph`** | `AutoHypergraph` | **个人轨迹超图**。以人生阶段为超边,关联 `{时期, 地点, 同行人物, 核心经历}`。 | 人物传记编撰、生命历程研究 |+| **`NarrativeRelationGraph`** | `AutoGraph` | **叙事关系图**。提取口述者主观视角下的人物互动与评价关系。 | 口述史社会网络分析 |+| **`MemoryFlashbackList`** | `AutoList` | **回忆片段清单**。提取口述中提到的具体轶事、感悟或对特定历史时刻的侧面描写。 | 历史细节补充、情感分析 |+* **档案馆藏信札 (Archival Correspondence)**:历史人物间的往来书信,揭示隐秘的社交网络和事件细节。+| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`EpistolaryKnowledgeGraph`** | `AutoGraph` | **信札内容图谱**。提取信件正文中提到的人物、事件及其相互关系,而非仅仅是发信和收信关系。 | 史料挖掘、事件考证 |+### 7. `biology` (生物科学)从单一的基因组扩展到蛋白质组学、代谢通路及生态学。-* **生物学专著**:详述物种分类、进化历史或复杂生物系统机制的学术书籍。++* **生物学专著 (Biological Monographs)**:详述物种分类、进化历史或复杂生物系统机制的学术书籍。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`SpeciesInteractionWeb`** | `AutoGraph` | **物种相互作用网**。提取捕食、寄生、竞争、互利共生等关系。 | 食物网构建、生态关系分析 |+| **`TaxonomicTree`** | `AutoGraph` | **分类学树**。提取界门纲目科属种的层级包含关系。 | 生物分类学数据库 |+* **蛋白质结构摘要 (Protein Structure Summaries)**:描述蛋白质晶体结构、配体结合位点及修饰位点的文本。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`ProteinComplexMap`** | `AutoHypergraph` | **蛋白质复合物超图**。建模 `{亚基A, 亚基B, 辅因子}` 共同组成功能复合物的多亚基结构。 | 蛋白质复合物数据库、结构研究 |+| **`BindingSiteModel`** | `AutoModel` | **关键位点模型**。提取活性位点、结合位点的残基编号、化学性质及功能注解。 | 药物设计、位点突变分析 |+* **代谢通路描述 (Metabolic Pathways)**:解释生物化学反应级联的文本,涉及酶、底物、产物及调控机制。-* **生态调查报告 (Ecological Surveys)**:记录特定区域内物种分布、种群数量及生境特征的考察文档。-* **分类学描述 (Taxonomic Descriptions)**:对物种形态特征、鉴别要点及系统发育关系的详细记录。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`BiochemicalReactionHypergraph`** | `AutoHypergraph` | **生化反应超图**。精准建模 `{酶 + 底物A + 底物B -> 产物C + 产物D}` 的多输入多输出反应。 | 代谢通路图谱、代谢工程 |+| **`RegulatoryNetwork`** | `AutoGraph` | **基因调控网络**。提取转录因子、启动子及其对基因表达的促进、抑制、协同作用。 | 基因调控分析、系统生物学 |++* **生态调查 ( Ecological Surveys)**:对物种形态特征、鉴别要点及系统发育关系的详细记录,以及特定区域内物种分布与生境特征的考察。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`PhylogeneticRelationGraph`** | `AutoGraph` | **系统发育关系图**。提取物种间的亲缘关系、演化距离及分支点。 | 分子系统学、进化树构建 |+| **`BiodiversityRegistry`** | `AutoSet` | **物种名录**。去重汇总调查报告中观测到的所有物种及其种群数量信息。 | 物种清单制作、保护优先级评估 |### 8. `legal` (法律)专注于提取权利义务逻辑、条件约束及法律事实。+* **法学专著与评注**:对法律原则、法条逻辑及判例法进行深度学理解析的书籍。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`LegalConceptOntology`** | `AutoGraph` | **法律概念本体**。提取法律术语的定义、上下位关系及法理阐释。 | 法律检索增强、法学教育 |+| **`CaseLawCitationNet`** | `AutoGraph` | **判例引用网络**。映射案件之间的引用、区分(Distinguish)或推翻(Overrule)关系。 | 判例法研究、类案检索 |+* **主服务协议 (MSA)**:定义长期商业合作框架的合同,包含责任限制、知识产权归属及违约条款。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`ContractObligationHypergraph`** | `AutoHypergraph` | **合同义务超图**。建模复杂的条件性义务:`{主体, 义务, 触发条件, 例外情形, 违约责任}`。 | 同时履行抗辩权分析、合同审查 |+| **`DefinedTermRegistry`** | `AutoSet` | **术语定义表**。去重并汇总合同中定义的所有专有名词(如“机密信息”、“不可抗力”)。 | 术语一致性检查、合同摘要 |+| **`LiabilityClauseList`** | `AutoList` | **责任条款清单**。提取关于赔偿、责任限制、保证及免责声明的具体条款。 | 合同风险评估、法务审核 |+* **法院判决书 (Judgments)**:法官对案件的最终裁定,包含事实认定、法律推理及判例引用。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`CaseFactTimeline`** | `AutoTemporalGraph` | **案件事实时序图**。从“经审理查明”部分还原导致纠纷的按时间顺序排列的事实链条。 | 案情复盘、证据链梳理 |+| **`AdjudicationLogic`** | `AutoHypergraph` | **裁判逻辑超图**。建模法官的推理过程:`{认定事实 + 适用法律 -> 裁判结论}`。 | 类案推送、判决预测辅助 |+| **`LitigationParticipantMap`** | `AutoGraph` | **诉讼参与人图谱**。提取原告、被告、第三人、代理律师及证人之间的关系。 | 利益冲突检索、关联案件分析 |+* **合规申报文件 (Compliance Filings)**:企业提交给监管机构的关于数据合规、反洗钱或环境影响的详细陈述。+| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`ComplianceRequirementList`** | `AutoList` | **合规要求清单**。提取文件中承诺遵守的具体义务或整改措施。 | 合规差距分析、监管应对 |+| **`BeneficialOwnershipGraph`** | `AutoGraph` | **受益所有权图谱**。穿透多层股权结构,识别最终受益人 (UBO) 和控制人。 | 反洗钱 (AML)、制裁筛查 |+### 9. `literature` (文学与影视)专注于叙事结构分析、角色互动及世界观设定。+* **影视剧本 (Screenplays)**:格式严格的文本(场景头、动作、对白),适合提取角色互动图谱。-* **角色设定集 (Character Bibles)**:描述角色背景故事、性格特征及人际关系的内部文档。-* **文学评论 (Literary Criticism)**:对作品主题、隐喻及互文性关系的深度剖析。-### 10. `travel` (旅游)-专注于地理空间关系及路线规划。-* **旅行行程单 (Itineraries)**:包含时间、地点 (POI)、交通及住宿安排的序列化文本。-* **目的地指南 (Destination Guides)**:对地点的综合介绍,包含方位关系(位于、毗邻)及文化贴士。+| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`SceneEventHypergraph`** | `AutoHypergraph` | **场景事件超图**。将一场戏建模为连接 `{出场角色, 场景地点, 关键道具, 核心动作}` 的超边。 | 剧本统筹、场次复杂度分析 |+| **`CharacterArcTimeline`** | `AutoTemporalGraph` | **角色弧光时序图**。按剧本时间线提取角色在不同场次中的位置、情绪状态或关键行为。 | 人物成长路径分析、连戏检查 |-### 11. `news` (新闻)-专注于新闻要素 (5W1H) 及事件因果链提取。-* **深度调查报道 (Investigative Features)**:揭示复杂事件背后利益链条及多方博弈关系的长文。-* **突发新闻电讯 (Breaking News)**:短小精悍、注重时效性和事实要素的实时消息。+* **长篇小说 (Novels)**:情节复杂、人物众多且关系交织的文本。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`ComplexCharacterRelation`** | `AutoHypergraph` | **复杂人物关系网**。超越两两关系,提取涉及多方的社会结构(如三角恋、结盟、家族派系)。 | 人物群像分析、粉丝维基构建 |+| **`StoryEntityGraph`** | `AutoGraph` | **故事实体图谱**。专注于提取关键物品、地点及其归属或位置关系,与人物关系分离。 | 世界观设定整理、RPG 游戏改编 |+| **`NarrativeEventChain`** | `AutoTemporalGraph` | **叙事事件链**。按故事内部时间线提取关键情节转折点 (Plot Points)。 | 故事梗概生成、时间线梳理 |++* **文学评论 (Literary Criticism)**:对作品主题、意象及结构的深度剖析。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`MotifAssociationNet`** | `AutoGraph` | **意象关联网络**。提取文本中反复出现的符号、意象之间的关联,节点类型统一为“意象”。 | 文本细读辅助、符号学分析 |+| **`CritiqueArgumentHypergraph`** | `AutoHypergraph` | **评论论证超图**。建模复杂的论证逻辑:`{论据1, 论据2, 引用文本} -> 核心观点`。 | 学术论文分析、观点提炼 |+| **`NarrativeStructureTree`** | `AutoGraph` | **叙事结构树**。构建作品的结构层级(如主线、支线、插叙部分)。 | 叙事学研究、结构拆解 |++### 10. `news` (新闻传媒)+专注于新闻要素 (5W1H)、事件因果链及观点分析。++* **深度调查报道 (Investigative Journalism)**:揭示复杂社会关系或深层真相的长篇报道。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`InvestigativeContextGraph`** | `AutoGraph` | **调查背景图谱**。提取报道中涉及的所有人物、机构、地点及其表层的静态关系(如任职、亲属、所在地)。 | 实体关系梳理、利益相关方识别 |+| **`ComplexRelationNet`** | `AutoHypergraph` | **复杂关系网络**。建模涉及多方(三人及以上)的社会关联(如家族、政治盟友、商业伙伴),而非简单的点对点关系。 | 人物特稿、政商关系分析 |+| **`KeyEventSequence`** | `AutoTemporalGraph` | **调查事件脉络**。按时间顺序还原调查中揭露的关键事件节点,梳理前因后果。 | 深度回顾、历史遗留问题揭秘 |++* **突发新闻与电讯 (Breaking News & Wire Stories)**:注重时效性和核心事实的短消息。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`NewsEntityGraph`** | `AutoGraph` | **新闻实体图谱**。快速提取快讯中的核心主体(Who)及其直接动作(Action)或状态。 | 即时新闻流、实体链接 |+| **`NewsSummaryModel`** | `AutoModel` | **结构化摘要**。标准化提取 5W1H 要素(Who, What, When, Where, Why, How)。 | 新闻聚合、自动简报 |+| **`LiveUpdateTimeline`** | `AutoTemporalGraph` | **实时动态时间轴**。针对正在发生的事件(如由于发布会、突发事态),提取分钟级更新。 | 直播贴整理、实时监控 |++* **政策解读与社论 (Policy Analysis & Editorials)**:侧重观点、论证逻辑及未来影响分析的文章。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`ViewpointStructure`** | `AutoHypergraph` | **观点逻辑结构**。建模文章的论证逻辑:`{核心观点, 支撑论据, 背景引用}`。 | 社论分析、舆情观点聚类 |+| **`ImpactChain`** | `AutoGraph` | **影响推演链**。提取“政策/事件 -> 影响群体 -> 预期后果”的因果预测链条。 | 宏观政策解读、行业影响评估 |++### 11. `agriculture` (农业)+专注于作物全生命周期管理、田间监测及土壤健康数据。++* **农业技术手册 (Agricultural Manuals)**:关于作物种植规范、田间管理标准及病虫害防治技术的指导书。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`CropGrowthCycle`** | `AutoTemporalGraph` | **作物生长周期图**。以时间为轴,提取作物各生长阶段(播种、分蘖、成熟等)对应的关键农事操作与环境要求。 | 种植日历生成、农事任务规划 |+| **`PestControlHypergraph`** | `AutoHypergraph` | **病虫害防治超图**。建模复杂的防治逻辑:`{作物, 阶段, 不良诱因} -> {防治对象(病/虫), 推荐药剂, 剂量, 安全间隔期}`。 | 智能植保系统、农药推荐 |-### 12. `agriculture` (农业)-* **农业技术手册**:关于作物种植规范、田间管理标准及病虫害防治技术的指导书。* **巡田报告 (Crop Scouting Reports)**:对作物生长阶段及病虫害情况的实地观察记录。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`FieldObservationList`** | `AutoList` | **田间观测清单**。结构化提取每一次巡田的核心记录:`{地块编号, 作物, 生长阶段, 观测问题(杂草/虫害), 严重等级, 建议措施}`。 | 巡田日志数字化、病虫害预警 |+* **土壤分析报告 (Soil Analysis)**:描述土壤化学成分及对应施肥建议的文本。-### 13. `food` (美食餐饮)+| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`SoilNutrientModel`** | `AutoModel` | **土壤养分模型**。提取核心理化指标(pH、有机质、N-P-K含量、微量元素)。 | 测土配方施肥、地力等级评价 |+| **`AmendmentPlan`** | `AutoGraph` | **改良方案图**。提取 `{检测结果 -> 限制因子 -> 改良措施 -> 预期目标}` 的逻辑链条。 | 精准农业处方生成 |++### 12. `food` (美食餐饮)+专注于食谱标准化、食材配伍逻辑及美食评价数据。+* **标准化食谱 (Standardized Recipes)**:包含配料表、烹饪步骤及关键控制点的结构化文本。-* **菜单工程分析 (Menu Engineering)**:结合菜品描述与销售数据的分析文档。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`RecipeCollection`** | `AutoSet` | **菜谱名录**。去重提取文本中出现的所有独立菜品实体及基本分类。 | 菜单数字化、菜品库索引构建 |+| **`StandardRecipeCard`** | `AutoModel` | **单品标准食谱**。针对单个菜品提取完整的配料表、步骤说明及关键TIPS。 | 后厨 SOP 卡片、烹饪教学 |+| **`IngredientCompositionHypergraph`** | `AutoHypergraph` | **食材配伍超图**。建模菜品与其 `{主料, 辅料, 调味品}` 的复杂组合关系。 | 成本核算、过敏原管理、新菜研发 |++* **美食评论与感官评价 (Food Reviews & Sensory Evaluation)**:专业食评人或研发团队对菜品的详细评价记录。++| 模板名称 | 底层原语 | 描述 | 典型应用场景 |+| :--- | :--- | :--- | :--- |+| **`DishReviewSummary`** | `AutoList` | **食评摘要清单**。按菜品提取核心评价点、推荐等级及价格感知。 | 探店笔记结构化、必吃榜单生成 |+| **`SensoryEvaluationGraph`** | `AutoGraph` | **感官评价图谱**。提取 `{菜品} -[具有特征]-> {口感/味道} -[归因于]-> {食材/技法}` 的评价逻辑。 | 风味归因分析、新品研发反馈 |