CN105069044A - Simulated indirect dependency based novel process model mining method - Google Patents

Simulated indirect dependency based novel process model mining method Download PDF

Info

Publication number
CN105069044A
CN105069044A CN201510437577.3A CN201510437577A CN105069044A CN 105069044 A CN105069044 A CN 105069044A CN 201510437577 A CN201510437577 A CN 201510437577A CN 105069044 A CN105069044 A CN 105069044A
Authority
CN
China
Prior art keywords
model
sequence
indirect
intending
mining
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201510437577.3A
Other languages
Chinese (zh)
Inventor
方贤文
化佩
刘祥伟
方欢
殷志祥
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Anhui University of Science and Technology
Original Assignee
Anhui University of Science and Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Anhui University of Science and Technology filed Critical Anhui University of Science and Technology
Priority to CN201510437577.3A priority Critical patent/CN105069044A/en
Publication of CN105069044A publication Critical patent/CN105069044A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2455—Query execution
    • G06F16/24568—Data stream processing; Continuous queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2465—Query processing support for facilitating data mining operations in structured databases

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Fuzzy Systems (AREA)
  • Software Systems (AREA)
  • Probability & Statistics with Applications (AREA)
  • Mathematical Physics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

A simulated indirect dependency based novel process model mining method relates to event log preprocessing, initial model creation and regulation as well as mining of a model having indirect dependency, and belongs to the field of process mining. Most existing process mining methods only consider a direct dependency relation between tasks and neglect an indirect dependency relation between the tasks. The invention proposes the simulated indirect dependency based process mining method which is based on a behavior profile of an event log and mainly aims to mine out the process model having the indirect dependency based on a simulated indirect dependency relation. A plurality of candidate models can be generated in a mining process and an optimal model is selected out by calculating the fitness and the behavior suitability. According to the method, a cross order is subdivided into a parallel cross order and a cyclic cross order, so that parallel tasks and cyclic tasks can be effectively mined out. In addition, a definition of the simulated indirect dependency is formalized, so that a task pair having the simulated indirect dependency relation can be quickly found out in the mining process.

Description

Based on the new method that the process model intending indirectly relying on excavates
Technical field
The invention belongs to process model mining field, relate to a kind of new method that process model excavates, comprising the task and a kind of process model method for digging based on intending indirectly relying on finding and have and intend indirect dependence, being specially adapted to the excavation containing the process model indirectly relied on.
Background technology
Along with the development of infotech, infosystem is more and more important in BPM, due to the event log quantity sharp increase of infosystem record, makes this Auto-Modelling Technology of process model mining become the focus of research.Process model mining is intended to excavate process model from the event log of infosystem record, thus helps people to improve or rebuild operation flow.
Various process model method for digging occurs in succession in recent years, but most method for digging only considers the direct dependence between task and have ignored indirect dependence.This concept of indirect dependence is proposed at first by professor vanderAalst, and the method that in existing process model mining method, more satisfactory excavation contains the process model indirectly relied on is α ++algorithm, although the method can excavate the process model containing indirectly relying on, does not analyze from the angle of process state.
The present invention proposes the new method excavated based on the process model intending indirectly relying on, and intersection sequence is subdivided into parallel sequence and the recycling cross sequence of intersecting, extends the relation of event log behavior profile, carry out analysis modeling from the angle of process state.The present invention is the form of Definition intending indirectly relying in addition, makes can find out rapidly in mining process to have to intend indirect dependence activity pair, and then adjusts model, finally excavates the process model containing indirectly relying on.
Summary of the invention
The present invention is in order to enrich existing process model mining technology, propose a kind of new method excavated based on the process model intending indirectly relying on, initial model is set up based on the behavior profile of daily record, adjustment model is carried out according to calculating adaptability and behavior appropriateness Incremental Log, then find out have the activity of intending indirect dependence to and model is adjusted, finally carry out Model Selection, obtain optimization model.
In the process excavated, first, from infosystem, extract event log, remove incomplete logged sequence and merge daily record to improve model quality and to reduce workload; Then set up behavior profile relation table according to direct strict sequence, indirect strict sequence, parallel intersection sequence, recycling cross sequence, exclusive sequence, build initial model; And then be that model is adjusted, evaluation criterion be set according to adaptability and behavior appropriateness, in undesirable situation, use Incremental Log adjustment model; Finally find out have the activity of intending indirect dependence to and adjustment model, select optimization model according to evaluation criterion.
The indirect dependence of plan that the present invention proposes is defined as: establish the event log in Petri nets model PM=(S, T, F, C, s, e), σ i=t 1t 2t nfor the logged sequence in event log L, then movable transition are to (a, b) ∈ (T l× T l) (not consider in every bar logged sequence all common activity occurred to) have and intend indirect dependence, be designated as a ∝ b, and if only if:
P ( a , b ) = Σ i = 1 k n i r ( b , σ i ) Σ i = 1 k n 1 R ( a → i d b , σ i ) = 1
Wherein k is the different event track number of given execution journal, n irepresent the process instance number comprised in the i-th class event trace, r (b, σ i) be used for judging that whether activity transition b is at σ imiddle appearance, if b is at σ imiddle appearance, then r (b, σ i)=1, if do not occur, r (b, σ i)=0; R (a → idb, σ i) be used for judging whether a and b occurs with indirect strict order relation, if so, then R (a → idb, σ i)=1, if not, then R (a → idb, σ i)=0.
Advantage of the present invention is the concept using the order relation based on weak order relation to improve daily record behavior profile, and these order relations comprise: direct strict sequence, indirect strict sequence, parallel sequence, recycling cross sequence, the exclusive sequence of intersecting.In addition, propose the concept intending indirectly relying on, and the form of Definition intending indirectly relying on, and then indirectly rely on adjustment model based on plan, improve the quality of model, and effectively can excavate a part containing the process model indirectly relied on.
Accompanying drawing explanation
Fig. 1 is structural drawing of the invention process.
Fig. 2 is the block diagram of structure initial model of the present invention.
Fig. 3 is that searching of the present invention has the right block diagram of the indirect dependence activity of plan.
Fig. 4 is the block diagram based on intending indirectly relying on adjustment model of the present invention.
Embodiment
The present invention proposes the new method excavated based on the process model intending indirectly relying on.
Below in conjunction with accompanying drawing, the present invention is further illustrated.
Fig. 1 is the structural drawing of the whole implementation process of the present invention.As shown in the figure, it mainly comprises four parts, is pre-service event log respectively, sets up initial model, adjustment initial model and indirectly rely on adjustment model based on plan and preferentially select final mask.
Fig. 2 is the block diagram of structure initial model of the present invention.As shown in the figure, first, five kinds of order relations (direct strict sequence, indirect strict sequence, parallel sequence, recycling cross sequence, the exclusive sequence of intersecting) based on weak order relation set up behavior profile relation table, then corresponding according to behavior profile basic structure determination flow relation, constructs initial model.
Fig. 3 is that searching of the present invention has the right block diagram of the indirect dependence activity of plan.As shown in the figure, first for arbitrary movable to (a, b) ∈ (T l× T l) (not consider in every bar logged sequence all common activity occurred to), judge whether b occurs in certain logged sequence, draw the value of r, judgement activity is to (a again, b) whether occur with indirect strict order relation in certain logged sequence, draw the value of R, and then P (a is calculated, b) whether 1 is equaled, until all activities are complete to inquiry, record and make the activity of P (a, b)=1 right, namely these activities to being that to have the activity intending indirect dependence right.
Fig. 4 is the block diagram based on intending indirectly relying on adjustment model of the present invention.As shown in the figure, find out all have intend indirect dependence activity to rear, initial model after using Incremental Log adjustment is adjusted further, make to have intend indirect dependence two activities between have a storehouse directly they to be connected, to ensure the dependence between them.Like this, in the model after adjustment, have intend indirect dependence activity transition to also having indirect dependence, therefore, indirectly rely on based on intending the process model can excavated containing indirectly relying on.

Claims (3)

1. excavate new method based on the process model intending indirectly relying on, comprise pre-service event log, set up initial model, adjust initial model and indirectly rely on adjustment model based on plan and preferentially select final mask.It is characterized in that: from infosystem, extract event log, remove incomplete logged sequence and merge daily record, improve model quality and decrease workload; Set up behavior profile relation table according to direct strict sequence, indirect strict sequence, parallel intersection sequence, recycling cross sequence, exclusive sequence, build initial model, can effectively excavate parallel task and cycle task; Find out according to the formal definitions intending indirectly relying on have the activity of intending indirect dependence to and adjustment model, select optimization model according to evaluation criterion, finally can excavate the process model containing dependence indirectly.
2. the foundation of initial model according to claim 1, it is characterized in that: set up behavior profile relation table according to direct strict sequence, indirect strict sequence, parallel intersection sequence, recycling cross sequence, exclusive sequence, the behavior of event log is analyzed, then corresponding according to behavior profile basic structure determination flow relation, builds initial model.
3. according to claim 1 based on intending indirect dependence adjustment model and preferentially selecting final mask, it is characterized in that: the definition quantification intending indirect dependence, make searching process simplification; Find out the activity transition that have and intend indirect dependence to rear, adjustment model make to have intend indirect dependence two transition between have a storehouse directly they to be connected, to ensure the dependence between them; Evaluation criterion being set based on adaptability and behavior appropriateness, if meet, then selecting the model based on intending indirectly relying on after adjustment, if do not meet, then the model of Selection utilization Incremental Log adjustment.
CN201510437577.3A 2015-07-22 2015-07-22 Simulated indirect dependency based novel process model mining method Pending CN105069044A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510437577.3A CN105069044A (en) 2015-07-22 2015-07-22 Simulated indirect dependency based novel process model mining method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510437577.3A CN105069044A (en) 2015-07-22 2015-07-22 Simulated indirect dependency based novel process model mining method

Publications (1)

Publication Number Publication Date
CN105069044A true CN105069044A (en) 2015-11-18

Family

ID=54498416

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510437577.3A Pending CN105069044A (en) 2015-07-22 2015-07-22 Simulated indirect dependency based novel process model mining method

Country Status (1)

Country Link
CN (1) CN105069044A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108984774A (en) * 2018-07-24 2018-12-11 安徽理工大学 A kind of behavior block process model mining method based on subsequent relationship
CN112261006A (en) * 2020-09-27 2021-01-22 中孚安全技术有限公司 Mining method, terminal and storage medium for discovering dependency relationship among threat behaviors
CN115525693A (en) * 2022-09-20 2022-12-27 山东理工大学 Incremental event log-oriented process model mining method and system

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6038538A (en) * 1997-09-15 2000-03-14 International Business Machines Corporation Generating process models from workflow logs
CN102880684A (en) * 2012-09-13 2013-01-16 杭州电子科技大学 Workflow modeling method based on log record mining and combination verification
CN103559588A (en) * 2013-11-15 2014-02-05 安徽理工大学 Log mining method based on Petri network behavior profile
CN103778051A (en) * 2014-01-09 2014-05-07 安徽理工大学 Business process increment mining method based on L* algorithm
CN104133857A (en) * 2014-07-14 2014-11-05 安徽理工大学 New method for digging business process model on the basis of configuration constraint

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6038538A (en) * 1997-09-15 2000-03-14 International Business Machines Corporation Generating process models from workflow logs
CN102880684A (en) * 2012-09-13 2013-01-16 杭州电子科技大学 Workflow modeling method based on log record mining and combination verification
CN103559588A (en) * 2013-11-15 2014-02-05 安徽理工大学 Log mining method based on Petri network behavior profile
CN103778051A (en) * 2014-01-09 2014-05-07 安徽理工大学 Business process increment mining method based on L* algorithm
CN104133857A (en) * 2014-07-14 2014-11-05 安徽理工大学 New method for digging business process model on the basis of configuration constraint

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
ROZINAT A 等: "Conformance checking of processes based on monitoring real behavior", 《INFORMATION SYSTEMS》 *
WEN L 等: "Detecting Implicit Dependencies Between Tasks from Event Logs", 《LECTURE NOTES IN COMPUTER SCIENCE》 *
王俊杰: "基于事件日志的业务流程模型的变化分析", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *
闻立杰: "基于工作流网的过程挖掘算法研究", 《中国博士学位论文全文数据库 信息科技辑》 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108984774A (en) * 2018-07-24 2018-12-11 安徽理工大学 A kind of behavior block process model mining method based on subsequent relationship
CN112261006A (en) * 2020-09-27 2021-01-22 中孚安全技术有限公司 Mining method, terminal and storage medium for discovering dependency relationship among threat behaviors
CN112261006B (en) * 2020-09-27 2022-07-19 中孚安全技术有限公司 Mining method, terminal and storage medium for discovering dependency relationship among threat behaviors
CN115525693A (en) * 2022-09-20 2022-12-27 山东理工大学 Incremental event log-oriented process model mining method and system
CN115525693B (en) * 2022-09-20 2024-02-06 山东理工大学 Incremental event log-oriented process model mining method and system

Similar Documents

Publication Publication Date Title
CN103559588A (en) Log mining method based on Petri network behavior profile
CN103020494B (en) Copyright ownership detecting method using Program code programming mode copyright ownership detecting model
CN105069044A (en) Simulated indirect dependency based novel process model mining method
CN103778051A (en) Business process increment mining method based on L* algorithm
CN105095473A (en) Method and system for analyzing discrepant data
CN104133857A (en) New method for digging business process model on the basis of configuration constraint
Kovalevs’ka et al. The formation of the finite-element model of the system “undermined massif–support of stope”
Aksarayli et al. Process optimization with simulation modeling in a manufacturing system
CN103714093A (en) Method and device for mining key pages of website
CN112036609B (en) Dynamic prediction method for water inflow of coal mine working face based on multi-order power system model
CN103236085A (en) Method for automatically establishing FLAC3D (fast Lagrangian analysis of continua in 3 dimensions) complicated three-dimensional geologic body models
CN107194021A (en) The figure adjustment of box beam configuration and real time evaluating method
CN109752064A (en) A kind of automation method for drafting for the mine remnants water level isopleth that accuracy is high
CN106599511B (en) Method for optimizing coal mining method of thin coal seam longwall fully mechanized coal mining face
CN102708224A (en) Functional design-based method for automatically analyzing system structure
SA521421641B1 (en) Data Structure for Fast Invasion Percolation Modeling Software
Yoo et al. Systems Engineering based Live Fire Test of Weapon Systems
CN112241594A (en) Rapid optimization method for side slope exploration drilling arrangement scheme
CN104182528A (en) Partial-sequence pattern based educational information course association pattern discovery method and system
Wang et al. Practical semiautomatic stope design and cutoff grade calculation method.
CN113837440B (en) Blasting effect prediction method and device, electronic equipment and medium
Wellmann et al. Probabilistic machine learning for improved decision-making with 3-D geological models
Xiao et al. An improved bidirectional generative adversarial network model for multivariate estimation of correlated and imbalanced tunnel construction parameters
CN108573043A (en) Business procedure deadlock and the method for digging for lacking timing error
Skone Distribution combustion compressor drivers

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20151118

WD01 Invention patent application deemed withdrawn after publication