店址选址分析 Skill

智能化零售店铺选址分析工具，帮助用户基于数据做出科学的选址决策。

Core Capabilities

1. Multi-dimensional Analysis
• Foot traffic analysis
• Population density assessment
• Commercial facility scoring
• Transportation convenience
• Competition environment evaluation
• Delivery order analysis

1. Smart Scoring System
• Automatically adjusts weights based on store type
• Supports 7 store types: bubble tea shops, coffee shops, toy stores, bakeries, restaurants, clothing stores, convenience stores
• Each store type has customized evaluation criteria

1. Visual Reports
• Generates professional HTML reports
• Includes bar charts and radar charts
• Detailed data cards and recommendation analysis
• Outputs structured JSON data

Workflow

When a user requests location analysis:

1. Collect Requirements
• Store type: What kind of store to open
• Target area: Specific location or region

1. Data Analysis

Execute location_analyzer.py to evaluate:

• Population and demographics
• Business environment
• Traffic and foot flow
• Delivery and consumption patterns

1. Generate Report

Use generate_report.py to create:

• HTML visualization report using report_template_simple.html
• JSON structured data
• Comprehensive recommendations

Using the Scripts

Location Analyzer (location_analyzer.py)

Core analysis engine that calculates location scores.

Key Classes:

• LocationData: Data model for location information
• LocationAnalyzer: Scoring engine with store-type-specific weights
• AnalysisResult: Output containing scores, advantages, risks, and recommendations

Usage Pattern:

import sys
sys.path.insert(0, skill_dir)  # Add skill directory to path

from location_analyzer import LocationAnalyzer, LocationData

# Create analyzer for specific store type
analyzer = LocationAnalyzer("咖啡店")

# Prepare location data
location_data = LocationData(
    name="Location Name",
    address="Full Address",
    population_density=10000.0,
    daily_traffic=20000,
    households=1500,
    avg_income=15.0,
    commercial_score=80.0,
    traffic_score=85.0,
    competition_density=10,
    delivery_orders=1000,
    avg_delivery_price=28.0,
    nearby_facilities=["Facility 1", "Facility 2"],
    target_audience_match=0.8
)

# Calculate score
score, result = analyzer.calculate_score(location_data)

Report Generator (generate_report.py)

Generates HTML and JSON reports from analysis results.

Key Classes:

• ReportGenerator: Handles report generation with HTML templates

Usage Pattern:

from generate_report import ReportGenerator

# Create generator
generator = ReportGenerator(analyzer)

# Generate HTML report (uses report_template_simple.html)
html_path = generator.generate_html_report(
    results=[result],
    district="District Name",
    output_path="/path/to/output/report.html"
)

# Generate JSON report
json_report = analyzer.generate_report_json(results, "District Name")

HTML Templates

• report_template_simple.html: Primary template for report generation (recommended)
• report_template.html: Alternative template with additional features

The report generator automatically uses the simple template unless specified otherwise.

Store Type Weights

Different store types use different evaluation weights:

Coffee Shops / Bubble Tea Shops:

• Foot traffic: 40%
• Young demographic: 25%
• Commercial facilities: 15%
• Competition: 20%

Toy Stores:

• Family households: 35%
• Child population density: 40%
• School/kindergarten proximity: 15%
• Commercial facilities: 10%

Bakeries:

• Foot traffic: 25%
• Residential density: 30%
• Transportation convenience: 20%
• Competition: 25%

Restaurants:

• Foot traffic: 30%
• Parking convenience: 20%
• Commercial facilities: 25%
• Delivery orders: 25%

Clothing Stores:

• Foot traffic: 35%
• Young female demographic: 25%
• Commercial prosperity: 25%
• Competition: 15%

Convenience Stores:

• Residential density: 40%
• Transportation convenience: 25%
• Foot traffic: 20%
• Competition: 15%

Data Considerations

When real data is unavailable:

• Generate reasonable simulated data based on location type
• Clearly mark data as simulated in reports
• Adjust estimates based on:
• Location type (commercial district / residential area / transportation hub)
• Regional characteristics
• Store type requirements

Location Type Examples

Commercial Districts (e.g., Financial District):

• High foot traffic (40,000+ daily)
• Few households (0-500)
• High income levels (20,000+ yuan/year)
• Excellent commercial facilities (95+ score)
• High competition (30+ competitors)

Residential Areas (e.g., Community Districts):

• Moderate foot traffic (10,000-15,000 daily)
• Many households (2,000-3,000)
• Middle income levels (10,000-15,000 yuan/year)
• Moderate commercial facilities (60-70 score)
• Low competition (5-10 competitors)

Transportation Hubs (e.g., Train Stations):

• Very high foot traffic (30,000-50,000 daily)
• Few households (500-1,000)
• Mixed income levels (15,000+ yuan/year)
• Good commercial facilities (80-90 score)
• Moderate-high competition (10-20 competitors)

Output Files

Always save output files to the user's output directory:

• HTML reports: 选址分析报告_{location}_{store_type}.html
• JSON data: 选址分析数据_{location}_{store_type}.json

After generating reports, use declare_artifact to register the HTML report as a final deliverable.

Important Notes

1. Data Source Transparency: Always indicate whether data is real or simulated
2. Comprehensive Analysis: Consider all dimensions before making recommendations
3. Balanced Scoring: Use appropriate weights for the specific store type
4. Risk Awareness: Clearly identify potential risks and challenges
5. Actionable Recommendations: Provide specific, implementable advice

Files in This Skill

All files are in the same directory:

• SKILL.md - This file
• location_analyzer.py - Core analysis engine
• generate_report.py - Report generator
• report_template_simple.html - Primary HTML template (recommended)
• report_template.html - Alternative HTML template