What is Entityidentification

EntityIdentification is an MCP server designed to determine whether two sets of data originate from the same entity.

Use cases

Use cases include comparing customer records from different databases to identify duplicates, verifying identity in financial transactions, and ensuring data consistency across systems.

How to use

To use EntityIdentification, install the necessary dependencies using pip, and then utilize its functions to normalize text, compare values, and evaluate JSON objects for similarity.

Key features

Key features include text normalization, value comparison (both exact and semantic), JSON traversal for key-value comparison, and integration of a language model for assessing semantic similarity.

Where to use

EntityIdentification can be used in various fields such as data integration, fraud detection, customer relationship management, and any domain requiring entity resolution.

EntityIdentification

Identify whether two sets of data are from the same entity. 识别两组数据是否来自同一主体

This is a MCP (Model Context Protocol) server. 这是一个支持MCP协议的服务器。

Data Comparison Tool

This tool provides a comprehensive way to compare two sets of data, evaluating both exact and semantic equality of their values. It leverages text normalization and a language model to determine if the data originates from the same entity.

Features

• Text Normalization: Converts text to lowercase, removes punctuation, and normalizes whitespace.
• Value Comparison: Compares values directly and semantically (ignoring order for lists).
• JSON Traversal: Iterates through each key in the JSON objects and compares corresponding values.
• Language Model Integration: Uses a generative language model to assess semantic similarity and provide a final judgment on whether the data comes from the same entity.

Installation

To use this tool, ensure you have the necessary dependencies installed. You can install them using pip:

pip install genai

Usage

Functions

1. normalize_text(text):

   • Normalizes the input text by converting it to lowercase, removing punctuation, and normalizing whitespace.

2. compare_values(val1, val2):

   • Compares two values both exactly and semantically.
   • If the values are lists, it ignores the order of elements for semantic comparison.

3. compare_json(json1, json2):

   • Compares two JSON objects key by key.
   • Uses compare_values to evaluate each key’s values.
   • Integrates a language model to assess semantic similarity and provides a final judgment.

Example

import json
import genai
import re

# Define your JSON objects
json1 = {
    "name": "John Doe",
    "address": "123 Main St, Anytown, USA",
    "hobbies": ["reading", "hiking", "coding"]
}

json2 = {
    "name": "john doe",
    "address": "123 Main Street, Anytown, USA",
    "hobbies": ["coding", "hiking", "reading"]
}

# Compare the JSON objects
comparison_results = compare_json(json1, json2)

# Generate final matching result
model1 = genai.GenerativeModel("gemini-2.0-flash-thinking-exp")
result_matching = model1.generate_content("综合这些信息，你认为可以判断两个数据来自同一主体吗？"+json.dumps(comparison_results, ensure_ascii=False, indent=4))
print(result_matching.text)

Contributing

Contributions are welcome! Please open an issue or submit a pull request.

License

This project is licensed under the MIT License. See the LICENSE file for details.

Contact

If you have any questions or suggestions, please contact me:

• Email: [email protected]
• GitHub: [email protected]。

Wechat