Back to results
US 12,762,547 B2Granted
Data acquisition method and apparatus for analyzing cryptocurrency transaction
AssigneeS2W Inc.
InventorsSang Duk Suh, Changhoon Yoon, Seung Hyeon Lee
Life of this patent
Estimating the term…
Abstract
The present disclosure relates to a method and apparatus for acquiring learning data to generate a machine learning model for detecting a scam account of cryptocurrency. The method comprises receiving a report related to a scam address from a first database having information about a reported scam address stored therein, acquiring a first scam address and a first description related to the first scam address from the report, extracting a plurality of first keywords related to the first scam address from the first description using natural language processing, and storing the first scam address in a second database.
Claims8
A learning data acquisition method for acquiring learning data to generate a machine learning model for detecting a scam account of cryptocurrency in a learning data acquisition apparatus, the method comprising:
- receiving a report related to a scam address included in a first database having information about a reported scam address stored therein from a service provider for providing information related to scam addresses of cryptocurrency;
- acquiring a first scam address and a first description related to the first scam address from the report, wherein the first scam address is an address determined as a cryptocurrency address used for scam by the service provider;
- extracting a plurality of first keywords related to the first scam address from the first description using natural language processing, wherein the extracting of the plurality of first keywords includes removing characters unnecessary for analysis from the first description, including numbers, URLs, and stop words, and based on a number of words remaining in the first description after the unnecessary characters being removed from the first description being equal to or greater than a predetermined number, without limiting a length of each of the words remaining in the first description, using the words of remaining in the first description as the plurality of first keywords related to the first scam address, and wherein, based on the number of remaining words in the first description being less than the predetermined number, the first description is not used for obtaining keywords related to the first scam address;
- storing the first scam address in a second database;
- receiving text information from a publicly accessible website not provided by the service provider for providing information related to scam addresses of cryptocurrency;
- analyzing, by a hardware processor of the learning data acquisition apparatus, the received text information and extracting, by the hardware processor, main text information including a cryptocurrency address from the text information;
- extracting, by the hardware processor, a plurality of second keywords from the main text information using natural language processing;
- acquiring, by the hardware processor, a scam information detection model which is a machine learning model for determining whether a cryptocurrency address is used by a scammer based on keywords related to an address of cryptocurrency;
- determining, by the hardware processor, whether or not the cryptocurrency address included in the main text information is a scam address by applying the plurality of second keywords to the scam information detection model, wherein the determining of whether or not the cryptocurrency address included in the main text information is the scam address comprises (i) deriving a frequency with which each of the plurality of second keywords extracted from the main text information appears in the main text information, and (ii) applying the plurality of second keywords extracted from the main text information and the frequency to the scam information detection model;
- acquiring, by the hardware processor, when the cryptocurrency address included in the main text information is a scam address, the cryptocurrency address included in the main text information as a second scam address;
- and
- storing the second scam address in the second database,
- wherein the step of acquiring the scam information detection model comprises:
- acquiring words related to a benign cryptocurrency address from a website determined as including the benign cryptocurrency address, the words related to the benign cryptocurrency address being keywords for explaining the benign cryptocurrency address, wherein the website determined as including the benign cryptocurrency address is different from the publicly accessible website and is not provided by the service provider for providing information related to scam addresses of cryptocurrency,
- acquiring a first frequency with which each of the words related to the benign cryptocurrency address appears on the website determined as including the benign cryptocurrency address,
- acquiring a second frequency with which each of the plurality of first keywords related to the first scam address appears in the first description related to the first scam address, and
- acquiring the scam information detection model by machine learning of (i) the words related to the benign cryptocurrency address labeled as benign, (ii) the first frequency, (iii) the second frequency, and (iv) the plurality of first keywords labeled as scam.
14 more elements
A learning data acquisition apparatus for acquiring learning data to generate a machine learning model for detecting a scam account of cryptocurrency, including a hardware processor and a memory, wherein, according to commands stored in the memory, the hardware processor executes:
- receiving a report related to a scam address included in a first database having information about a reported scam address stored therein from a service provider for providing information related to scam addresses of cryptocurrency;
- acquiring a first scam address and a first description related to the first scam address from the report, wherein the first scam address is an address determined as a cryptocurrency address used for scam by the service provider;
- extracting a plurality of first keywords related to the first scam address from the first description using natural language processing, wherein the extracting of the plurality of first keywords includes removing characters unnecessary for analysis from the first description, including numbers, URLs, and stop words, and based on a number of words remaining in the first description after the unnecessary characters being removed from the first description being equal to or greater than a predetermined number, without limiting a length of each of the words remaining in the first description, using the words remaining in the first description as the plurality of first keywords related to the first scam address, and wherein, based on the number of remaining words in the first description being less than the predetermined number, the first description is not used for obtaining keywords related to the first scam address;
- storing the first scam address in a second database;
- receiving text information from a publicly accessible website not provided by the service provider for providing information related to scam addresses of cryptocurrency;
- analyzing the received text information and extracting main text information including a cryptocurrency address from the text information;
- extracting a plurality of second keywords from the main text information using natural language processing;
- acquiring a scam information detection model which is a machine learning model for determining whether a cryptocurrency address is used by a scammer based on keywords related to an address of cryptocurrency;
- determining whether or not the cryptocurrency address included in the main text information is a scam address by applying the plurality of second keywords to the scam information detection model, wherein the determining of whether or not the cryptocurrency address included in the main text information is the scam address comprises (i) deriving a frequency with which each of the plurality of second keywords extracted from the main text information appears in the main text information, and (ii) applying the plurality of second keywords extracted from the main text information and the frequency to the scam information detection model;
- acquiring, when the cryptocurrency address included in the main text information is a scam address, the cryptocurrency address included in the main text information as a second scam address;
- and
- storing the second scam address in the second database,
- wherein the acquiring of the scam information detection model comprises:
- acquiring words related to a benign cryptocurrency address from a website determined as including the benign cryptocurrency address, the words related to the benign cryptocurrency address being keywords for explaining the benign cryptocurrency address,
- wherein the website determined as including the benign cryptocurrency address is different from the publicly accessible website and is not provided by the service provider for providing information related to scam addresses of cryptocurrency,
- acquiring a first frequency with which each of the words related to the benign cryptocurrency address appears on the website determined as including the benign cryptocurrency address,
- acquiring a second frequency with which each of the plurality of first keywords related to the first scam address appears in the first description related to the first scam address, and
- acquiring the scam information detection model by machine learning of (i) the words related to the benign cryptocurrency address labeled as benign, (ii) the first frequency, (iii) the second frequency, and (iv) the plurality of first keywords labeled as scam.
15 more elements
Dependencies are inferred from the claim text.