Data processing: database and file management or data structures – Database design – Data structure types
Reexamination Certificate
2001-06-08
2004-01-06
Amsbury, Wayne (Department: 2171)
Data processing: database and file management or data structures
Database design
Data structure types
C706S045000
Reexamination Certificate
active
06675164
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of Endeavor
The present invention relates to data mining and more particularly to parallel object-oriented data mining.
2. State of Technology
U.S. Pat. No. 5,692,107 for a method for generating predictive models in a computer system by Simoudis et al, patented Nov. 25, 1997 provides the following information, “Accurate forecasting relies heavily upon the ability to analyze large amounts of data. This task is extremely difficult because of the sheer quantity of data involved and the complexity of the analyses that should be performed. The problem is exacerbated by the fact that the data often resides in multiple databases, each database having different internal file structures. Rarely is the relevant information explicitly stored in the databases. Rather, the important information exists only in the hidden relationships among items in the databases. Recently, artificial intelligence techniques have been employed to assist users in discovering these relationships and, in some cases, in automatically discovering the relationships. Data mining is a process that uses specific techniques to find patterns in data, allowing a user to conduct a relatively broad search of large databases for relevant information that may not be explicitly stored in the databases. Typically, a user initially specifies a search phrase or strategy and the system then extracts patterns and relations corresponding to that strategy from the stored data. These extracted patterns and relations can be: (1) used by the user, or data analyst, to form a prediction model; (2) used to refine an existing model; and/or (3) organized into a summary of the target database. Such a search system permits searching across multiple databases. There are two existing forms of data mining: top-down; and bottom-up. Both forms are separately available on existing systems. Top-down systems are also referred to as “pattern validation,” “verification-driven data mining” and “confirmatory analysis.” This is a type of analysis that allows an analyst to express a piece of knowledge, validate or validate that knowledge, and obtain the reasons for the validation or invalidation. The validation step in a top-down analysis requires that data refuting the knowledge as well as data supporting the knowledge be considered. Bottom-up systems are also referred to as “data exploration.” Bottom-up systems discover knowledge, generally in the form of patterns, in data. Existing systems rely on the specific interface associated with each database, which further limits a user's ability to dynamically interact with the system to create sets of rules and hypotheses than can be applied across several databases, each having separate structures. For large data problems, a single interface and single data mining technique significantly inhibits a user's ability to identify all appropriate patterns and relations. The goal of performing such data mining is to generate a reliable predictive model that can be applied to data sets. Furthermore, existing systems require the user to collect and appropriately configure the relevant data, frequently from multiple and diverse data sources. Little or no guidance or support for this task is produced. Thus, there remains a need for a system that permits a user to create a reliable predictive model using data mining across multiple and diverse databases.”
U.S. Pat. No. 5,758,147 for efficient information collection method for parallel data mining by Chen et al, patented May 26, 1998 provides the following information, “The importance of database mining is growing at a rapid pace. Progress in bar-code technology has made it possible for retail organizations to collect and store massive amounts of sales data. Catalog companies can also collect sales data from the orders they receive. A record in such data typically consists of the transaction date, the items bought in that transaction, and possibly the customer-id if such a transaction is made via the use of a credit card or customer card. Analysis of past transaction data can provide very valuable information on customer buying behavior, and thus improve the quality of business decisions such as: what to put on sale; which merchandise should be placed on shelves together; and how to customize marketing programs; to name a few. It is, however, essential to collect a sufficient amount of sales data before any meaningful conclusions can be drawn therefrom. It is therefore important to devise efficient methods of communicating and mining the ‘gold’ in these often enormous volumes of partitioned data. The most important data mining problem is mining association rules. By mining association rules it is meant that given a database of sales transactions, the process of identifying all associations among items such that the presence of some items in a transaction will imply the presence of other items in the same transaction. It is known that mining association rules can be decomposed into two subproblems. First, all sets of items (itemsets) that are contained in a sufficient number of transactions above a minimum (support) threshold are identified. These itemsets are referred to as large itemsets. Once all large itemsets are obtained, the desired association rules can be generated therefrom in a straightforward manner. Database mining in general requires progressive knowledge collection and analysis based on a very large transaction database. When the transaction database is partitioned across a large number of nodes in a parallel database environment, the volume of inter-node data transmissions required for reaching global decisions can be prohibitive, thus significantly compromising the benefits normally accruing from parallelization. It is therefore important to devise efficient methods for mining association rules in a parallel database environment.”
U.S. Pat. No. 5,787,425 for an object-oriented data mining framework mechanism by Joseph Phillip Bigus, patented Jul. 28, 1998 provides the following description, “The development of the EDVAC computer system of 1948 is often cited as the beginning of the computer era. Since that time, computer systems have evolved into extremely sophisticated devices, capable of storing and processing vast amounts of data. As the amount of data stored on computer systems has increased, the ability to interpret and understand the information implicit in that data has diminished. In the past, data was stored in flat files, then hierarchical and network data based systems, and now in relational or object oriented databases. The primary method for analyzing that data has been to form well structured queries, for example using SQL (Structured Query Language), and then to perform simple aggregations or hypothesis testing against that data. Recently, a new technique called data mining has been developed, which allows a user to search large databases and to discover hidden patterns in that data. Data mining is thus the efficient discovery of valuable, non-obvious information from a large collection of data and centers on the automated discovery of new facts and underlying relationships in the data. The term “data mining” comes from the idea that the raw material is the business data, and the data mining algorithm is the excavator, shifting through the vast quantities of raw data looking for the valuable nuggets of business information. Because data can be stored in such a wide variety of formats and because the data values can have such a wide variety of meanings, data mining applications have in the past been written to perform specific data mining operations, and there has been little or no reuse of code between application programs. Thus, each data mining application is written from scratch, making the development process long and expensive. Although the nuggets of business information that a data mining application discovers can be quite valuable, they are of little use if they are expensive and untimely discovered. Returning to the mining analogy, even if gold is selling for $900 per ounce, nobody i
Cantu-Paz Erick
Kamath Chandrika
Amsbury Wayne
Scott Eddie E.
The Regents of the University of California
Thompson Alan H.
LandOfFree
Parallel object-oriented data mining system does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Parallel object-oriented data mining system, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Parallel object-oriented data mining system will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3243407