US6094645A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Finding collective baskets and inference rules for internet or intranet mining for large data bases
Assignee: International Business Machines Corp
•
Filing: 1997-11-21
•
Granted: 2000-07-25
•
Expires: 2017-11-21
Abstract
Abstract A computer method of online mining of inference rules in a large database comprising a preprocessing stage and an online rule generation stage. The pre-processing stage includes first finding itemsets that possess a minimum computed collective strength K1, and second, pruning the itemsets with inference strength below a predetermined inference strength, K2. The online rule generation stage utilizes the itemsets organized into an adjacency lattice to generate inference rules with inference strength K2.
Inventors
- 👤 Charu Chandra Aggarwal
- 👤 Philip Shi-lung Yu
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-01 09:02
CPC Classifications
G; G06; G06F; G06F16/00; G06F16/20; G06F16/25; G06F16/252; G06F16/24; G06F16/90; G06F16/95; G06F16/958; G06F16/972; Y; Y10; Y10S; Y10S707/00; Y10S707/99931; Y10S707/99933; Y10S707/99936
Claims Analysis
Total Claims: 10
Claim 1
Independent Claim
186 words
A computer program device readable by a machine tangibly embodying a program of instructions executable by the machine to perform method steps for generating inference rules that identify transaction patterns describing consumer transaction tendencies from transaction data stored in one or more databases, the method steps comprising: a) generating a plurality of strongly collective baskets whose collective strength is at least equal to a defined collective strength value; and b) generating inference rules for those collective baskets whose inference strength is greater than a defined inference strength value, the generated inference rules describing patterns of transaction tendencies; wherein step of generating inference rules further comprises: a) partitioning said collective baskets into a plurality of associated partition pairs, (P,Q), wherein each partition pair consists of a unique division of items from said collective basket; for each partition pair; i) calculating an inference strength; ii) determining whether said calculated inference strength is at least equal to said user-defined inference strength value; and iii) generating an inference rule of the form, P implies Q, whenever said calculated inference strength is at least equal to said user-defined inference strength value.
Claim 2
Dependent Claim
186 words
A computer program device readable by a machine tangibly embodying a program of instructions executable by the machine to perform method steps for generating inference rules that identify transaction patterns describing consumer transaction tendencies from transaction data stored in one or more databases, the method steps comprising: a) generating a plurality of strongly collective baskets whose collective strength is at least equal to a defined collective strength value; and b) generating inference rules for those collective baskets whose inference strength is greater than a defined inference strength value, the generated inference rules describing patterns of transaction tendencies; wherein step of generating inference rules further comprises: a) partitioning said collective baskets into a plurality of associated partition pairs, (P,Q), wherein each partition pair consists of a unique division of items from said collective basket; for each partition pair; i) calculating an inference strength; ii) determining whether said calculated inference strength is at least equal to said user-defined inference strength value; and iii) generating an inference rule of the form, P implies Q, whenever said calculated inference strength is at least equal to said user-defined inference strength value.
Claim 3
Dependent Claim
88 words
The computer program device of claim 1, further comprising the steps of: calculating said inference strength of said inference rule as a ratio, where f(P) and f(-Q) are multiplied in a numerator of said ratio, and f(P) represents the fraction of transactions which contain the itemset P, and f(-Q) is the fraction of transactions which do not contain the itemset Q completely, and f(P,-Q) represents a denominator of said ratio, defined as the fraction of transactions which contain itemset P, and do not contain the itemset Q completely.
Claim 4
Dependent Claim
153 words
A computer program device readable by a machine tangibly embodying a program of instructions executable by the machine to perform method steps for generating inference rules that identify transaction patterns describing consumer transaction tendencies from transaction data stored in one or more databases, the method steps comprising: a) generating a plurality of strongly collective baskets whose collective strength is at least equal to a defined collective strength value; and b) generating inference rules for those collective baskets whose inference strength is greater than a defined inference strength value, the generated inference rules describing patterns of transaction tendencies; wherein said step of generating a plurality of strongly collective baskets whose collective strength is at least equal to a defined collective strength value, further comprises the step of pruning the strongly collective basket when at least one subset of the basket does not have a collective strength at least equal to the collective strength value.
Claim 5
Dependent Claim
153 words
A computer program device readable by a machine tangibly embodying a program of instructions executable by the machine to perform method steps for generating inference rules that identify transaction patterns describing consumer transaction tendencies from transaction data stored in one or more databases, the method steps comprising: a) generating a plurality of strongly collective baskets whose collective strength is at least equal to a defined collective strength value; and b) generating inference rules for those collective baskets whose inference strength is greater than a defined inference strength value, the generated inference rules describing patterns of transaction tendencies; wherein said step of generating a plurality of strongly collective baskets whose collective strength is at least equal to a defined collective strength value, further comprises the step of pruning the strongly collective basket when at least one subset of the basket does not have a collective strength at least equal to the collective strength value.
Claim 6
Dependent Claim
168 words
A computerized method for generating inference rules that identify transaction pattern describing consumer transaction tendencies from transaction data stored in one or more databases, the method steps comprising: a) generating a plurality of strongly collective baskets whose collective strength is at least equal to a defined collective strength value; and b) generating inference rules for those collective baskets whose inference strength is greater than a defined inference strength value, the generated inference rule describing patterns of transaction tendencies; wherein the step of generating inference rules further comprises: a) partitioning said collective baskets into a plurality of associated partition pairs, (P,Q), wherein each partition pair consists of a unique division of items from said collective basket; for each partition pair; i) calculating an inference strength; ii) determining whether said calculated inference strength is at least equal to said user-defined inference strength value; and iii) generating an inference rule of the form, P implies Q, whenever said calculated inference strength is at least equal to said user-defined inference strength value.
Claim 7
Dependent Claim
168 words
A computerized method for generating inference rules that identify transaction pattern describing consumer transaction tendencies from transaction data stored in one or more databases, the method steps comprising: a) generating a plurality of strongly collective baskets whose collective strength is at least equal to a defined collective strength value; and b) generating inference rules for those collective baskets whose inference strength is greater than a defined inference strength value, the generated inference rule describing patterns of transaction tendencies; wherein the step of generating inference rules further comprises: a) partitioning said collective baskets into a plurality of associated partition pairs, (P,Q), wherein each partition pair consists of a unique division of items from said collective basket; for each partition pair; i) calculating an inference strength; ii) determining whether said calculated inference strength is at least equal to said user-defined inference strength value; and iii) generating an inference rule of the form, P implies Q, whenever said calculated inference strength is at least equal to said user-defined inference strength value.
Claim 8
Dependent Claim
86 words
The method of claim 4, further comprising the steps of: calculating said inference strength of said inference rule as a ratio, where f(P) and f(-Q) are multiplied in a numerator of said ratio, and f(P) represents the fraction of transactions which contain the itemset P, and f(-Q) is the fraction of transactions which do not contain the itemset Q completely, and f(P,-Q) represents a denominator of said ratio, defined as the fraction of transactions which contain itemset P, and do not contain the itemset Q completely.
Claim 9
Dependent Claim
134 words
A computerized method for generating inference rules that identify transaction patterns describing consumer transaction tendencies from transaction data stored in one or more databases, the method steps comprising: a) generating a plurality of strongly collective baskets whose collective strength is at least equal to a defined collective strength value; and b) generating inference rules for those collective baskets whose inference strength is greater than a defined inference strength value, the generated inference rules describing patterns of transaction tendencies; wherein said step of generating a plurality of strongly collective baskets whose collective strength is at least equal to a defined collective strength value, further comprises the step of pruning the strongly collective basket when at least one subset of the basket does not have a collective strength at least equal to the collective strength value.
Claim 10
Dependent Claim
134 words
A computerized method for generating inference rules that identify transaction patterns describing consumer transaction tendencies from transaction data stored in one or more databases, the method steps comprising: a) generating a plurality of strongly collective baskets whose collective strength is at least equal to a defined collective strength value; and b) generating inference rules for those collective baskets whose inference strength is greater than a defined inference strength value, the generated inference rules describing patterns of transaction tendencies; wherein said step of generating a plurality of strongly collective baskets whose collective strength is at least equal to a defined collective strength value, further comprises the step of pruning the strongly collective basket when at least one subset of the basket does not have a collective strength at least equal to the collective strength value.
References Cited (Backward Citations)
US5819266A
Cited
US5842200A
Cited
US5615341A
Cited
US5668988A
Cited
US5742811A
Cited
US5983222A
Cited
US5905973A
Cited
US5920855A
Cited
US5943667A
Cited
US5884305A
Cited
US6003029A
Cited
US5946683A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2003-07-25 | 2004-01-24 | 2004-07-25 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2007-07-25 | 2008-01-24 | 2008-07-25 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2011-07-25 | 2012-01-24 | 2012-07-25 | $7700.00 | Window Closed / Lapsed |