17599973. SYSTEM AND METHOD FOR MODIFYING KNOWLEDGE GRAPH FOR PROVIDING SERVICE simplified abstract (SAMSUNG ELECTRONICS CO., LTD.)

From WikiPatents
Jump to navigation Jump to search

SYSTEM AND METHOD FOR MODIFYING KNOWLEDGE GRAPH FOR PROVIDING SERVICE

Organization Name

SAMSUNG ELECTRONICS CO., LTD.

Inventor(s)

Wonjong Choi of Suwon-si (KR)

Soofeel Kim of Suwon-si (KR)

Yewon Park of Suwon-si (KR)

Jina Ham of Suwon-si (KR)

SYSTEM AND METHOD FOR MODIFYING KNOWLEDGE GRAPH FOR PROVIDING SERVICE - A simplified explanation of the abstract

This abstract first appeared for US patent application 17599973 titled 'SYSTEM AND METHOD FOR MODIFYING KNOWLEDGE GRAPH FOR PROVIDING SERVICE

Simplified Explanation

The patent application describes a system and method for modifying a knowledge graph to provide a service. Here are the key points:

  • The system interprets text related to a user's inquiry using natural language understanding (NLU) models.
  • It identifies the user's intention and the corresponding service.
  • A detailed knowledge graph related to the identified service is obtained.
  • The system identifies constraints based on the user's intention and selects a common knowledge graph related to those constraints.
  • A specific knowledge triple related to the constraint is extracted from the selected common knowledge graph.
  • The detailed knowledge graph is modified based on the extracted knowledge triple.

Potential Applications

This technology has potential applications in various fields, including:

  • Virtual assistants: The system can be used to enhance virtual assistants' ability to understand user queries and provide accurate and relevant information.
  • Customer support: It can be utilized to improve customer support systems by quickly identifying the user's intention and providing relevant solutions.
  • Knowledge management: The technology can assist in organizing and updating knowledge graphs, making them more comprehensive and adaptable.

Problems Solved

The system addresses several problems in knowledge graph modification and service provision:

  • Improved understanding: By utilizing NLU models, the system can better interpret user queries and understand their intentions, leading to more accurate service identification.
  • Constraint handling: The system can identify constraints based on user intentions and modify the knowledge graph accordingly, ensuring that the provided service meets the user's requirements.
  • Efficient knowledge graph modification: By extracting specific knowledge triples from common knowledge graphs, the system can efficiently modify the detailed knowledge graph, saving time and resources.

Benefits

The technology offers several benefits:

  • Enhanced user experience: By accurately identifying user intentions and modifying the knowledge graph accordingly, the system can provide more relevant and personalized services, improving the overall user experience.
  • Time and resource efficiency: The system's ability to extract specific knowledge triples from common knowledge graphs allows for efficient modification of the detailed knowledge graph, saving time and resources.
  • Improved service accuracy: By utilizing NLU models and considering user constraints, the system can provide more accurate and tailored services, increasing customer satisfaction.


Original Abstract Submitted

Provided is a system and method of modifying a knowledge graph for providing a service. A method, performed by a server, of modifying a knowledge graph for providing a service includes obtaining text related to an inquiry of a user; identifying a service related to an intention of the user by interpreting the text using at least one natural language understanding (NLU) model; obtaining a detailed knowledge graph related to the identified service; identifying at least one parameter indicating a constraint based on the intention of the user, based on a result of the interpreting; selecting a common knowledge graph related to a parameter representing the constraint from among a plurality of common knowledge graphs related to the identified service; extracting a first knowledge triple related to the parameter from the selected common knowledge graph; and modifying the detailed knowledge graph based on the extracted first knowledge triple.