Data processing apparatus and method for merging and processing deterministic knowledge and non-deterministic knowledge

Patent metadata

Field	Value
Publication number	US-11144833-B2
Application number	US-201715692070-A
Country	US
Kind code	B2
Filing date	Aug 31, 2017
Priority date	Nov 23, 2016
Publication date	Oct 12, 2021
Grant date	Oct 12, 2021

Abstract

Provided are a data processing apparatus and method for merging and processing deterministic knowledge and non-deterministic knowledge. The data processing apparatus and method may efficiently process various real-time and large-scale data to convert the data into knowledge by merging and processing non-deterministic knowledge and also deterministic knowledge perceived by an expert. Thus, it is possible to adaptively operate in accordance with a dynamically changing application service environment by converting a conversion rule for converting collected data generated from an application service system into semantic data, a context awareness rule for perceiving context information from given information, and a user query for searching for knowledge information into knowledge and gradually augmenting the knowledge information in accordance with an application service environment.

First claim

What is claimed is:

1. A data processing apparatus for merging and processing deterministic and non-deterministic knowledge, the data processing apparatus interoperating with a specific application service system to process knowledge information of a corresponding application service environment, the data processing apparatus comprising:
a knowledge base unit configured to store the knowledge information, the knowledge information including a conversion rule for converting collected data generated by the application service system into a predetermined type of knowledge;
a machine learning unit configured to perform machine learning on the converted knowledge stored in the knowledge base unit on a data type basis and extract extensive conversion rule information according to the type of collected data;
a data conversion unit configured to input data type information regarding collected data generated in the specific application service environment and the conversion rule of the knowledge base unit to the machine learning unit, augment the conversion rule of the knowledge base unit by reflecting the extensive conversion rule information extracted by the machine learning unit, and convert the collected data generated in the specific application service environment into knowledge information on the basis of the conversion rule of the knowledge base unit; and
a context awareness unit configured to receive context information, service information, and rule generation information from the application service system, generate context awareness rules for context awareness, extract complete rule information for an incomplete rule among generated context awareness through the machine learning unit, generate a complete context awareness by reflecting the extracted complete rule information, and provide context information or service information derived by applying the context awareness rule to the application service system.

2. The data processing apparatus of claim 1 , wherein the data conversion unit converts the collected data into semantic data.

3. The data processing apparatus of claim 1 , further comprising a query unit configured to search the knowledge base unit according to a user query delivered from the application service system, determine whether the user query has a predetermined structured format, and convert the user query into the structured format through the machine learning unit when the user query does not have the structured format, wherein:
the knowledge base unit further stores knowledge information regarding the user query;
the machine learning unit performs learning on the basis of the knowledge information regarding the user query stored in the knowledge base unit to extract complete query information for converting the user query into the structured format; and
the query unit converts the user query into the structured format on the basis of the complete query information.

4. The data processing apparatus of claim 1 ,
wherein the knowledge base unit further includes knowledge information regarding the context awareness rule; and
the machine learning unit performs machine learning on the knowledge information regarding the context awareness rule to extract the complete rule information.

5. The data processing apparatus of claim 4 , further comprising an inference unit configured to infer the context information or service information from the collected data on the basis of an inference rule including the context awareness rule.

6. A data processing method for merging and processing deterministic knowledge and non-deterministic knowledge, the data processing method for interoperating with a specific application service system to process knowledge information of a corresponding application service environment, the data processing method comprising:
storing knowledge information regarding a conversion rule for converting data generated by the application service system into a predetermined type of knowledge; and
converting collected data generated in the application service environment into the predetermined type of data on the basis of the conversion rule of the knowledge information, wherein the converting comprises:
performing machine learning on the conversion rule on the basis of data types of the collected data generated in the application service system to extract extensive conversion rule information according to the type of collected data; and
augmenting the knowledge information regarding the conversion rule by reflecting the extensive conversion rule information corresponding to the type of collected data to a conversion rule expander through the performed machine learning.

Assignees

• Electronics & Telecommunications Res Inst

Inventors

• Kwon Soon Hyun
• Kim Eun Joo
• Park Hong Kyu
• Kang Hyun Joong
• Kim Kwi Hoon
• Kim Young Min
• Kim Hyun Jae
• Bae Ji Hoon
• Oh Se Won
• Yu Jae Hak
• Lee Yeon Hee
• Lee Ho Sung
• Kim Nae Soo
• Kim Sun Jin
• Pyo Cheol Sig

Classifications

• G06N5/013 Primary

  Automatic theorem proving · CPC title

• G06N5/04 Primary

  Inference or reasoning models · CPC title

• G06Q10/06

  Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling · CPC title

• G06F8/36

  Software reuse · CPC title

• G06F8/10

  Requirements analysis; Specification techniques · CPC title