17491816. LINGUISTIC TRANSFORMATION BASED RELATIONSHIP DISCOVERY FOR TRANSACTION VALIDATION simplified abstract (International Business Machines Corporation)
LINGUISTIC TRANSFORMATION BASED RELATIONSHIP DISCOVERY FOR TRANSACTION VALIDATION
Organization Name
International Business Machines Corporation
Inventor(s)
Mukundan Sundararajan of Bangalore (IN)
LINGUISTIC TRANSFORMATION BASED RELATIONSHIP DISCOVERY FOR TRANSACTION VALIDATION - A simplified explanation of the abstract
This abstract first appeared for US patent application 17491816 titled 'LINGUISTIC TRANSFORMATION BASED RELATIONSHIP DISCOVERY FOR TRANSACTION VALIDATION
Simplified Explanation
The patent application describes a method for analyzing transaction data using a graph model and part of speech analysis. Here are the key points:
- A graph is created to represent relationships between transaction elements.
- Nodes in the graph represent transaction elements, and edges represent relationships between them.
- Some nodes are tagged with a part of speech tag using a part of speech analysis model.
- An alternative part of speech tag is generated for tagged nodes.
- Tagged nodes with alternative part of speech tags are grouped into word groups.
- The word groups are validated against a grammar of a natural language.
- If a word group conforms to the grammar, additional nodes representing the word group are added to the graph.
- The modified graph is then used to validate transactions in the transaction data.
Potential applications of this technology:
- Fraud detection: The graph model can help identify suspicious relationships between transaction elements, leading to better fraud detection.
- Customer behavior analysis: By analyzing the relationships between transaction elements, patterns in customer behavior can be identified and used for targeted marketing or personalized recommendations.
- Risk assessment: The graph model can be used to assess the risk associated with certain transaction elements or relationships, helping businesses make informed decisions.
Problems solved by this technology:
- Complex relationship analysis: The graph model allows for a more comprehensive analysis of relationships between transaction elements, which can be difficult to capture using traditional methods.
- Language understanding: The part of speech analysis and grammar validation help ensure that the analysis is accurate and aligned with the natural language used in the transaction data.
Benefits of this technology:
- Improved accuracy: By incorporating part of speech analysis and grammar validation, the method provides more accurate analysis and validation of transaction data.
- Enhanced insights: The graph model enables a deeper understanding of relationships and patterns within transaction data, leading to valuable insights for businesses.
- Efficient analysis: The method allows for efficient analysis of large volumes of transaction data, enabling real-time or near-real-time validation and decision-making.
Original Abstract Submitted
From transaction data, a graph modeling a set of relationships between transaction elements is constructed, a node of the graph representing a transaction element, an edge of the graph representing a relationship between two transaction elements. Using a part of speech analysis model, a subset of the nodes is tagged with a corresponding first part of speech tag. An alternative part of speech tag is generated for a tagged node. A set of tagged nodes is grouped into a word group including at least one tagged node having an alternative part of speech tag. The word group is validated against a grammar of a natural language. Responsive to the validating determining that the word group conforms to the grammar, a set of additional nodes representing the word group is added to the graph. Using the modified graph, a transaction in the transaction data is validated.
