CN115511233A - Supply chain process reproduction method and system based on process mining - Google Patents

Supply chain process reproduction method and system based on process mining Download PDF

Info

Publication number
CN115511233A
CN115511233A CN202110690372.1A CN202110690372A CN115511233A CN 115511233 A CN115511233 A CN 115511233A CN 202110690372 A CN202110690372 A CN 202110690372A CN 115511233 A CN115511233 A CN 115511233A
Authority
CN
China
Prior art keywords
node
supply chain
flow
nodes
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
CN202110690372.1A
Other languages
Chinese (zh)
Inventor
胡永焕
孙阳盛
陈之浩
李俊颖
董力
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.)
State Grid Shanghai Electric Power Co Ltd
Original Assignee
State Grid Shanghai Electric Power Co Ltd
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 State Grid Shanghai Electric Power Co Ltd filed Critical State Grid Shanghai Electric Power Co Ltd
Priority to CN202110690372.1A priority Critical patent/CN115511233A/en
Publication of CN115511233A publication Critical patent/CN115511233A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0633—Workflow analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Strategic Management (AREA)
  • Quality & Reliability (AREA)
  • Theoretical Computer Science (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Development Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Educational Administration (AREA)
  • Game Theory and Decision Science (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to a supply chain process reappearing method and a supply chain process reappearing system based on process mining, wherein the method comprises the steps of obtaining service log information of a supply chain system; extracting process nodes from the service log information and constructing a process set; deducing the ordering relation of the process nodes through an alpha algorithm based on the process set, and bringing the frequency into the consideration range of the alpha algorithm; constructing a process network according to the sequencing relation of the process nodes; and outputting the flow of the supply chain according to the flow network. Compared with the prior art, the method is based on a big data algorithm, automatically monitors the 'blockage point' of the operation time of the supply chain process, finds the 'blind point' of the supply chain process in accordance with the monitoring, shows the real process trend of the process, shows the execution duration of each link of the process, predicts the execution risk of the supply chain process, and assists the aim of lean management of the power grid material through a digital means, thereby continuously enhancing the response capability and reliability of the material, realizing the execution risk of the data feedback service, and practically ensuring the supply of the project material.

Description

Supply chain process reproduction method and system based on process mining
Technical Field
The invention relates to the technical field of power supply chain management, in particular to a supply chain process reproduction method and a supply chain process reproduction system based on process mining.
Background
The supply chain business in the power industry has the characteristics of more process link differences, more business collaborative interaction and long business change process. At present, the power supply chain still follows flow sectional type management, the homogenization management and control condition is serious, redundant interaction links are multiple, the interaction links are easy to become bottleneck links, the material supply timeliness is influenced, the information transmission timeliness is poor, and the flow execution efficiency is low.
Disclosure of Invention
The invention aims to provide a supply chain flow reproduction method and a supply chain flow reproduction system based on flow mining, aiming at overcoming the defects that the prior art still follows flow sectional management at the present stage, the homogenization management and control situation is serious, redundant interaction links are more, the interaction links are easy to become bottleneck links, the material supply timeliness is influenced, the information transmission timeliness is poor, and the flow execution efficiency is low.
The purpose of the invention can be realized by the following technical scheme:
a supply chain process reproduction method based on process mining comprises the following steps:
a1: acquiring service log information of a supply chain system;
a2: extracting process nodes from the service log information to construct a process set;
a3: deducing the ordering relation of the process nodes through an alpha algorithm based on the process set;
a4: constructing a process network according to the sequencing relation of the process nodes;
a5: and outputting the flow of the supply chain according to the flow network.
Further, the deducing the ordering relationship of the flow nodes by the α algorithm specifically includes the following steps:
s1: four sequences exist to define flow nodes:
direct pointing: x > y if and only if node x flows directly to node y in some instances;
indirect pointing: x → y if and only if x > y and y > x are absent;
parallel juxtaposition: x | | y if and only if x > y and y > x;
not relevant: x # y is if and only if x > y is absent and y > x is absent;
s2: extracting all process information from the log W and storing the process information in a set T;
s3: finding all relative flow sets (a, B) that satisfy the condition:
by some predetermined path t A e.A should be connected to all t B ∈B；
Figure BDA0003126450440000021
And is provided with
Figure BDA0003126450440000022
a→b；
Figure BDA0003126450440000023
a2 ∈ A: a1# a2 and
Figure BDA0003126450440000024
b2∈B:b1#b2；
s4: in the process sets (a, B) obtained in step S3, only the largest set is retained;
s5: for each pair (A, B), using a path P (A，B) Connecting all the nodes of A with all the nodes of B, and then connecting the input and output positions in the circulation process;
s6: finally, the starting point i of the process is determined W ∈T I And end point o W ∈T O And connecting with the middle section of the process to obtain a process network.
Further, the calculation expression of step S2 is:
Figure BDA0003126450440000027
Figure BDA0003126450440000028
Figure BDA0003126450440000029
in the formula, T W A set T is stored for extracting the process information from the log W, T is a node in the set T, sigma is a node in the log W, T I For the set of all flow starts, T O Is the set of all flow ends.
Further, the calculation expression of step S3 is:
Figure BDA0003126450440000025
in the formula, X W For all the relative flow sets (A, B) found, a is the node in set A, B is the node in set B, a1 is the first node in set A, a2 is the second node in set A, B1 is the first node in set B, B2 is the second node in set B, a1# W a2 is node a1 is not related to node a2, b1# W b2 is node b1 and is not related to node b 2.
Further, the calculation expression of step S4 is:
Figure BDA0003126450440000026
in the formula, Y W Is the largest set reserved from the flow sets (a, B).
Further, the calculation expression of step S5 is:
P W ＝{P (A，B) |(A，B)∈Y W }∪{I W ，O W }
in the formula, P W For using a path P (A，B) All nodes of A and all nodes of BPath after points are connected, I W As input (starting point), O W Is the output (end point). .
Further, the calculation expression of step S6 is:
F W ＝{(a，P (A，B) )|(A，B)∈Y W ∧a∈A}∪
(P (A，B) ，b)|(A，B)∈Y W ∧b∈B}∪{(i W ，t)|t∈T I }∪{(t，o W )|t∈T O }
in the formula, F W For the acquired process network, i W As a starting point of the flow, o W Is the end point of the process.
Further, the deducing the ordering relationship of the process nodes by the α algorithm further includes adjusting the process network according to the frequency that the node a points to the node B directly, and the high calculation expression of the process is as follows:
Figure BDA0003126450440000031
wherein, | a >, in W b | denotes a > in W W Number of occurrences of b, a > W b is that the node a points to the node b directly, b > W a is the node b pointing directly to the node a,
Figure BDA0003126450440000032
the probability of pointing indirectly to b for a.
Further, the supply chain process reproduction method further comprises the step of displaying the process network through a flow chart.
The invention also provides a supply chain process reproduction system based on process mining, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor calls the computer program to execute the steps of the method.
Compared with the prior art, the invention has the following advantages:
the flow mining is an efficient flow analysis method, objective flow information can be obtained by analyzing data of a system by utilizing the unique innovation capability of the flow mining, and hidden business problems are found, so that an enterprise is helped to realize business flow reconstruction, and the influence of the flow mining on the business flow reconstruction and the innovation mode of the enterprise is reflected in the following aspects:
(1) And (3) identifying an accurate service flow: the process mining utilizes a process node identification technology to analyze a process event log and automatically generate an objective process model, so that the deviation and one-sidedness of a process analysis result caused by a traditional process management method such as business interview are avoided, the time and cost required for knowing the current process are greatly reduced, and an enterprise is helped to concentrate all processes.
(2) Visual business process analysis: the process mining visualizes the complete business process through the process chart, enterprises can simply and directly check whether the process event is consistent with the standard process model, and the enterprises can be helped to discover bottlenecks, deviations and potential risks in the business process from the aspects of organization or time and the like by highlighting the characteristics of abnormal cases.
(3) Self-evolution of the business model: different from a static model provided by a traditional process analysis method, the process mining provides a dynamic system which can continuously receive and process newly added service data, and automatically adjusts the existing model by utilizing the data to realize automatic evolution, so that an enterprise can check the change of the service process in real time in the process mining result.
Drawings
Fig. 1 is a schematic flow chart of a supply chain process reproduction method based on process mining according to an embodiment of the present invention;
FIG. 2 is a flowchart of an embodiment of the present invention with 6 nodes;
FIG. 3 is a graph comparing the results of the short-loop time alpha algorithm with the length of 1 and the actual situation in the embodiment of the present invention;
fig. 4 is a graph comparing the results of the short-loop time alpha algorithm with the length of 2 in the embodiment of the present invention with the actual situation.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
The method adopts a process mining technology as a bridge between data mining and business process management, extracts key information from event logs of each business system in the material supply chain through big data acquisition and convergence technologies, automatically identifies and associates through a big data algorithm to realize the simulation and the reconstruction of the business process of the material supply chain, carries out deep mining on data from multiple dimensions by utilizing abundant indexes and legend analysis and finally generates key data insights, accurately positions business pain points and realizes the improvement of modern intelligent supply chain process compliance, efficiency and efficiency.
In order to meet the service requirements and operation requirements of a supply chain operation platform and realize data communication and panoramic controllability of all service nodes, a process mining tool is firstly communicated with all service systems and captures data of different types, so that the process mining tool can realize the purposes of plan submission, purchase approval, bid inviting and bid bidding and bid winning results of equipment, the process mining tool is used for gathering the data of the whole process from the investment production, supervision and manufacture, spot inspection, installation and debugging, payment settlement of the equipment, and the operation, capital transfer, overhaul, scrapping and the like of the equipment; meanwhile, the data is analyzed and processed by utilizing the built-in high-performance data cleaning and data modeling functions to form a standard, accurate and intelligent operation analysis model, so that data support is provided for decision making; and finally, establishing and applying a flow mining algorithm model, performing correlation analysis and fusion utilization on data resources, providing a real, reliable and real-time information source for a management layer, objectively and completely depicting business activities, service objects and mechanism efficiency, rapidly finding flow deviation, material supply chain abnormity and risks in a mode of 'point + line + plane' full-dimensional monitoring, consistency check and the like, and realizing flow panoramic monitoring and risk real-time perception from the aspects of flow compliance, resources, efficiency and the like. In order to more intuitively embody the flow problem and to summarize the flow overall, the tool generates an exquisite chart, a coordinate graph, a dashboard and a report in a short time through a visual legend analysis component according to the personalized requirements of users. The simple and convenient dragging type operation report form making function supports a user to define view, layout, shape and color, various scenes meeting the business requirements of the user are built, the user is assisted to carry out business process analysis from multiple dimensions such as material categories, project units and the like, key data insight is generated, and business pain points are accurately positioned.
The process performance index of the process mining tool can visually reflect the operation efficiency of each service node and the cooperation condition among all departments in the supply chain, an assistant manager can quickly locate abnormal process links and inefficient service behaviors, and targeted optimization suggestions of the supply chain are completed through schemes of simplifying process redundancy links, coordinating and optimizing among departments and the like, so that the purposes of quality improvement and efficiency improvement are achieved.
The present embodiment provides a supply chain process recurrence method based on process mining, and the implementation means thereof is described in detail below.
1. Introduction of core function
Through the construction of a supply chain process mining tool, the log mining and analysis of a supply chain information system are carried out, the potential risk of supply is early warned practically, the actual execution path of the process is simulated, the problems of timeliness, compliance and the like of the process are found, the purposes of simpler process, more convenient operation, smoother cooperation, more efficient service, more intercommunication and comprehensive perception of information, more compatible functions and more flexible configuration are achieved, and a valuable reference suggestion is provided for the optimization and automation of the supply chain service through practical data. Wherein the tool comprises the following core functions:
1.1 flow direction simulation
Based on the existing business data processing and modeling through a big data algorithm, the process mining tool restores each actual business process to a user through a unique process analysis component, and defines the process with the most cases as a standard main process. Meanwhile, the execution path and difference of each flow are simulated through animation by means of the flow components, and abnormal flows are quickly identified.
1.2 root cause induction of abnormal process
The process mining tool mines the compute engine through an advanced process. For an abnormal flow with too long output time and node backups, a corresponding machine learning algorithm is adopted to develop root cause analysis, a corresponding problem label is attached to the abnormal flow, scientific, complete, comprehensive and accurate flow problem label library management is constructed according to an actual root cause verification result, business personnel are assisted to find the crux of the problem of flow organization, and a fundamental solution is found.
1.3, visual flow statistical indexes
The flow performance indexes of the flow mining tool can visually reflect the operation efficiency of each service node and the cooperation condition among departments of the supply chain, an assistant manager can quickly locate abnormal flow links and low-efficiency service behaviors, and local targeted optimization of the supply chain is realized by simplifying schemes such as flow redundancy links, cooperation and optimization among departments and the like. The visual legend analysis component can generate exquisite charts, coordinate graphs, instrument panels and reports in a short time according to the personalized requirements of users. The simple drag-and-drop operation report form making function supports a user to define view, layout, shape and color, builds various scenes meeting the business requirements of the user, assists the user to analyze business processes from multiple dimensions such as material categories, project units and the like, generates key data insights and accurately positions business pain points.
2. Data source and preprocessing techniques
Data of supply chain process analysis mainly comes from supply chain ERP and related systems such as planning, tender, contract, performance, warehousing and the like. In order to meet the service needs and operation needs of a supply chain operation platform, the process mining tool supports adaptation to various source system database types and provides various data connection schemes for implementation.
The process mining platform processes data by using data cleaning and data modeling functions to form a standardized and structured bottom layer analysis model, and data quality and accuracy play an important role in later-stage calculation results, so that data abnormal values need to be eliminated through data cleaning. And finally, generating a reliable and real business flow direction by using the data resource correlation analysis and fusion utilization of the big data algorithm model, and objectively and completely depicting business activities.
3. Core algorithm model
The process mining algorithm is a tool for extracting relevant service node information, generating relevant insights and realizing service process reappearance from an event log generated by a company service system, is a heuristic mining algorithm based on a statistical alpha algorithm, is used for ensuring the accuracy of the process mining algorithm, accelerating model calculation operation events and avoiding the problem that the accuracy of a final service process model is influenced by overhigh fitting degree, and reduces the operation time of the algorithm and ensures the efficiency of the algorithm while ensuring the higher accuracy and proper fitting degree of the algorithm.
As shown in fig. 1, the α algorithm construction process mining model is mainly divided into the following five steps:
a1: connecting a data source and reading service log information of the system;
a2: acquiring a task set of a process node;
a3: inferring ordering relationships (kernels);
a4: constructing a flow network based on the inferred ordering relationship;
a5: outputting the result on an analysis page of the system;
in the α algorithm, there are four different sequence relationships directly at nodes: →, |, #;
direct pointing: x > y if and only if node x flows directly to node y in some instances
Indirect pointing: x → y if and only if x > y and y > x are absent
Parallel juxtaposition: x | | y if and only if x > y and y > x
Not relevant: x # y if and only if x > y is absent and y > x is absent
From four different sequence relationships, the α algorithm is defined as follows:
all the flow information is extracted from the log W and stored in the set T,
Figure BDA0003126450440000071
let T I Is the set of all flow starts, T O Is the set of all the flow ends and,
Figure BDA0003126450440000072
Figure BDA0003126450440000073
in the formula, T W A set T is stored for extracting the flow information from the log W, T is a node in the set T, sigma is a node in the log W, T I For the set of all flow starts, T O Is the set of all flow ends.
Finding all relative flow sets (a, B) satisfies:
by some predetermined path t A e.A should be connected to all t B ∈B；
Figure BDA0003126450440000074
And is provided with
Figure BDA0003126450440000075
a→b；
Figure BDA0003126450440000076
a2 ∈ A: a1# a2 and
Figure BDA0003126450440000077
b2∈B:b1#b2；
Figure BDA0003126450440000078
in the formula, X W For all the relative flow sets (A, B) found, a is the node in set A, B is the node in set B, a1 is the first node in set A, a2 is the second node in set A, B1 is the first node in set B, B2 is the second node in set B, a1# W a2 is node a1 is not related to node a2, b1# W b2 is node b1 and node b2 are not related.
When all such sets are found, eventually only the largest set is retained,
Figure BDA0003126450440000081
in the formula, Y W Is the largest set reserved from the flow sets (a, B).
For each pair (A, B), one path P is used (A，B) All nodes of a are connected with all nodes of B. The positions of the inputs and outputs during the circulation are then correctly connected,
P W ＝{P (A，B) |(A，B)∈Y W }∪{I W ，O W }
in the formula, P W To use a path P (A，B) Path connecting all nodes of A with all nodes of B, I W As input (starting point), O W Is the output (end point).
Finally, starting point i of the process is determined W ∈T I And end point o W ∈T O Connected with the middle section of the process.
F W ＝{(a，P (A，B) )|(A，B)∈Y W ∧a∈A}∪
(P (A，B) ，b)|(A，B)∈Y W ∧b∈B}∪{(i W ，t)|t∈T I }∪{(t，o W )|t∈T O }
In the formula, F W For the acquired process network, i W As a starting point of the flow, o W Is the end point of the flow.
Example (c): when the flows corresponding to three cases in the log data of a flow (a, B, C, D, E, F) having 6 nodes are as follows: [ ABCD, ACBD, EF ]
The relationship between the process nodes can be preliminarily judged as follows:
A→B A→C B→D C→D E→F B||C C||B
executing the log data in the alpha algorithm may result in a flow chart as shown in fig. 2:
however, there are limitations to using the α algorithm, for example, the α algorithm cannot find such a flow when facing a short loop with a length of 1, such as for the following logs [ AC, ABC, ABBC, ABBBC ], the α algorithm may be in error when the flow algorithm is reproduced, as shown in fig. 3.
In the face of a cycle of length 2 such as [ ABD, ABCBD, ABCCBD ], in which case the α algorithm would consider B | | C due to B > C and C > B, as shown in FIG. 4;
in order to solve the limitation of the α algorithm, a heuristic mining method based on the α algorithm is used in the embodiment.
In order to obtain an accurate flow model, a representative sample set of case logs is required. The noise and incomplete behavior that occurs in the case samples in the normal case causes the accuracy of the model to decrease.
Noise case logs contain rare and uncommon behavior and do not represent typical behavior of a flow.
Incompleteness the case log contains too few events to find some of the underlying control flow structures.
The heuristic mining method is actually an improvement on the basis of an alpha algorithm, the main optimization is to take the frequency of an event into consideration, and the judgment method of the heuristic mining algorithm on the frequency is as follows:
let W be the event log on T and a, b ∈ T:
X W ＝|a＞ W b | represents a > in W W Number of occurrences of b:
Figure BDA0003126450440000091
wherein, | a >, in W b | represents a > in W W Number of occurrences of b, a > W b is that the node a points to the node b directly, b > W a is the node b pointing directly to the node a,
Figure BDA0003126450440000092
the probability of a pointing indirectly to b.
The higher the frequency when node A points directly to node B
Figure BDA0003126450440000093
The larger, the data for noise and imperfections
Figure BDA0003126450440000094
Will be significantly less than normal, is
Figure BDA0003126450440000095
And setting a threshold, and removing the node incidence relation smaller than the threshold to finish the noise reduction operation, thereby improving the accuracy of the process mining model.
The present embodiment also provides a supply chain process reproduction system based on process mining, which includes a memory and a processor, where the memory stores a computer program, and the processor calls the computer program to execute the steps of the supply chain process reproduction method based on process mining as described above.
The foregoing detailed description of the preferred embodiments of the invention has been presented. It should be understood that numerous modifications and variations can be devised by those skilled in the art in light of the above teachings. Therefore, the technical solutions available to those skilled in the art through logic analysis, reasoning and limited experiments based on the prior art according to the concept of the present invention should be within the scope of protection defined by the claims.

Claims (10)

1. A supply chain process reproduction method based on process mining is characterized by comprising the following steps:
a1: acquiring service log information of a supply chain system;
a2: extracting process nodes from the service log information to construct a process set;
a3: deducing the ordering relation of the process nodes through an alpha algorithm based on the process set;
a4: constructing a process network according to the sequencing relationship of the process nodes;
a5: and outputting the flow of the supply chain according to the flow network.
2. The method for supply chain process recurrence based on process mining as claimed in claim 1, wherein the step of inferring the ordering relationship of the process nodes by α algorithm specifically comprises the steps of:
s1: four sequences exist to define flow nodes:
direct pointing: x > y if and only if node x flows directly to node y in some instances;
indirect pointing: x → y if and only if x > y and y > x are absent;
parallel juxtaposition: x | | y if and only if x > y and y > x;
not relevant: x # y is absent and only if x > y is absent and y > x is absent;
s2: extracting all flow information from the log W and storing the flow information into a set T;
s3: finding all relative flow sets (a, B) that satisfy the condition:
by some predetermined path t A e.A should be connected to all t B ∈B；
Figure FDA0003126450430000013
And is
Figure FDA0003126450430000014
a→b；
Figure FDA0003126450430000015
a2 ∈ A: a1# a2 and
Figure FDA0003126450430000016
b2∈B:b1#b2；
s4: in the process sets (a, B) obtained in step S3, only the largest set is retained;
s5: for each pair (A, B), using a path P (A，B) Connecting all the nodes of A with all the nodes of B, and then connecting the input and output positions in the circulation process;
s6: finally, the starting point i of the process is determined W ∈T I And end point o W ∈T O And connecting with the middle section of the process to obtain a process network.
3. The method for supply chain process recurrence based on process mining as claimed in claim 2, wherein the computational expression of step S2 is:
Figure FDA0003126450430000011
Figure FDA0003126450430000012
Figure FDA0003126450430000021
in the formula, T W A set T is stored for extracting the flow information from the log W, T is a node in the set T, and sigma is a dayNode in log W, T I For the set of all flow starts, T O Is the set of all flow ends.
4. The method for supply chain process recurrence based on process mining as claimed in claim 3, wherein the computational expression of step S3 is:
Figure FDA0003126450430000022
in the formula, X W For all the relative flow sets (A, B) found, a is the node in set A, B is the node in set B, a1 is the first node in set A, a2 is the second node in set A, B1 is the first node in set B, B2 is the second node in set B, a1# W a2 is node a1 is not related to node a2, b1# W b2 is node b1 and is not related to node b 2.
5. The method for supply chain process recurrence based on process mining as claimed in claim 4, wherein the computational expression of step S4 is:
Figure FDA0003126450430000023
in the formula, Y W Is the largest set reserved from the flow sets (a, B).
6. The method for supply chain process recurrence based on process mining as claimed in claim 5, wherein the computational expression of step S5 is:
P W ＝{P (A，B) |(A，B)∈Y W }∪{I W ，O W }
in the formula, P W To use a path P (A，B) Path connecting all nodes of A with all nodes of B, I W As input (starting point), O W Is output (terminated)A dot).
7. The method for supply chain process recurrence based on process mining as claimed in claim 6, wherein the computational expression of step S6 is:
F W ＝{(a，P (A，B) )|(A，B)∈Y W ∧a∈A}∪
(P (A，B) ，b)|(A，B)∈Y W ∧b∈B}∪{(i W ，t)|t∈T I }∪{(t，o W )|t∈T O }
in the formula, F W For the acquired process network, i W As a starting point of the flow, o W Is the end point of the process.
8. The method of claim 7, wherein the inferring the ordering relationships of the process nodes by the α algorithm further comprises tuning the process network according to the frequency of the node A pointing directly to the node B, and the process is represented by the following calculation expressions:
X W ＝|a＞ W b|
Figure FDA0003126450430000031
wherein, | a >, is W b | represents a > in W W Number of occurrences of b, a > W b is that the node a points to the node b directly, b > W a is the node b pointing directly to the node a,
Figure FDA0003126450430000032
b is the probability that a points indirectly to b.
9. The method of claim 1, wherein the method further comprises displaying the flow network via a flow chart.
10. A supply chain process reproduction system based on process mining, comprising a memory and a processor, wherein the memory stores a computer program, and the processor calls the computer program to execute the steps of the method according to any one of claims 1 to 9.
CN202110690372.1A 2021-06-22 2021-06-22 Supply chain process reproduction method and system based on process mining Pending CN115511233A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110690372.1A CN115511233A (en) 2021-06-22 2021-06-22 Supply chain process reproduction method and system based on process mining

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110690372.1A CN115511233A (en) 2021-06-22 2021-06-22 Supply chain process reproduction method and system based on process mining

Publications (1)

Publication Number Publication Date
CN115511233A true CN115511233A (en) 2022-12-23

Family

ID=84499705

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110690372.1A Pending CN115511233A (en) 2021-06-22 2021-06-22 Supply chain process reproduction method and system based on process mining

Country Status (1)

Country Link
CN (1) CN115511233A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116258350A (en) * 2023-05-15 2023-06-13 烟台岸基网络科技有限公司 Sea container transportation monitoring method
CN116934067A (en) * 2023-09-19 2023-10-24 广州信安数据有限公司 Flow mining method, storage medium and equipment based on full-link monitoring data
CN117891857A (en) * 2024-03-13 2024-04-16 广东工业大学 Data mining method and system based on big data

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116258350A (en) * 2023-05-15 2023-06-13 烟台岸基网络科技有限公司 Sea container transportation monitoring method
CN116258350B (en) * 2023-05-15 2023-08-11 烟台岸基网络科技有限公司 Sea container transportation monitoring method
CN116934067A (en) * 2023-09-19 2023-10-24 广州信安数据有限公司 Flow mining method, storage medium and equipment based on full-link monitoring data
CN117891857A (en) * 2024-03-13 2024-04-16 广东工业大学 Data mining method and system based on big data
CN117891857B (en) * 2024-03-13 2024-05-24 广东工业大学 Data mining method and system based on big data

Similar Documents

Publication Publication Date Title
CN112394922B (en) Decision configuration method, business decision method and decision engine system
CN115511233A (en) Supply chain process reproduction method and system based on process mining
US7234131B1 (en) Peer review evaluation tool
US8930833B2 (en) Method and apparatus to present an integrated process modeler
JP2002149868A (en) Method for predicting time of future service event of product
John et al. Towards an AI‐driven business development framework: A multi‐case study
CN114546365B (en) Flow visualization modeling method, server, computer system and medium
CN112861492A (en) Method and device for linkage calculation between internal tables of report table and electronic equipment
Lyu et al. A data-driven approach for identifying possible manufacturing processes and production parameters that cause product defects: A thin-film filter company case study
CN108399284B (en) Big data transaction model analysis and restoration method based on deviation reduction
CN112102099B (en) Policy data processing method and device, electronic equipment and storage medium
CN212460603U (en) Robot management system based on material contract management
CN112488425A (en) Prediction method for bank business process task template optimization
CN114004712B (en) Service value chain construction method based on event log
Dzhusupova et al. Challenges in developing and deploying AI in the engineering, procurement and construction industry
Wei et al. Visual diagnostics of parallel performance in training large-scale dnn models
CN112395343B (en) DSG-based field change data acquisition and extraction method
Song et al. Risk evaluation of information technology outsourcing project: An integrated approach considering risk interactions and hierarchies
CN115454826A (en) Regression testing method, device, electronic equipment and storage medium
CN112000309B (en) Data acquisition method and system
Canitz Machine Learning in Supply Chain Planning--When Art & Science Converge.
Hesham et al. Enhanced Framework for Big Data Requirement Elicitation
CN115392805B (en) Transaction type contract compliance risk diagnosis method and system
Son A Process Mining Based Approach to Complex Manufacturing Process Flow Analysis: A Case Study
CN116720973A (en) Digital financial management method and system based on RPA

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication