CN110990460A - Data mining method for dynamic service resources - Google Patents

Data mining method for dynamic service resources Download PDF

Info

Publication number
CN110990460A
CN110990460A CN201911226646.0A CN201911226646A CN110990460A CN 110990460 A CN110990460 A CN 110990460A CN 201911226646 A CN201911226646 A CN 201911226646A CN 110990460 A CN110990460 A CN 110990460A
Authority
CN
China
Prior art keywords
value
individual
attribute
field
array
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
CN201911226646.0A
Other languages
Chinese (zh)
Inventor
苑明海
孙超
顾文斌
蔡仙仙
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.)
Changzhou Campus of Hohai University
Original Assignee
Changzhou Campus of Hohai University
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 Changzhou Campus of Hohai University filed Critical Changzhou Campus of Hohai University
Priority to CN201911226646.0A priority Critical patent/CN110990460A/en
Publication of CN110990460A publication Critical patent/CN110990460A/en
Pending legal-status Critical Current

Links

Images

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
    • G06F16/2458—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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/12—Computing arrangements based on biological models using genetic models
    • G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Biophysics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Probability & Statistics with Applications (AREA)
  • Fuzzy Systems (AREA)
  • Physiology (AREA)
  • Genetics & Genomics (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention discloses a data mining method for dynamic service resources, and belongs to the technical field of data mining. The method comprises the following steps: selecting characteristic information of the dynamic service resources as fields, and setting a plurality of attributes of each field and corresponding attribute values of the attributes; encoding the attribute of each field; and mining the association relation among the fields of the dynamic service resources by adopting a genetic algorithm. The method and the system can dig out the potential relation between the characteristic information of the dynamic service resources and provide valuable data information for enterprises.

Description

Data mining method for dynamic service resources
Technical Field
The invention relates to the technical field of industrial operation data mining, in particular to a data mining method for dynamic service resources.
Background
With the rapid development of modern network technology, the challenge of knowledge economy and the trend of global informatization wave, the traditional manufacturing industry is developing towards the direction of things integration, intellectualization, integration and synergy, and the sharing and cooperation of information resources become the main melody of the modern manufacturing industry. In the face of massive data information of enterprise manufacturing resources, necessary data mining and corresponding analysis processing need to be carried out on the massive data information, so that the information rule of the enterprise manufacturing resources is analyzed and explored, valuable data information is provided for the enterprise, and the enterprise is guided to make correct technical and operational decisions, so that the operation efficiency of the manufacturing enterprise is improved, and benefit maximization is obtained.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a data mining method for dynamic service resources, which is used for mining potential relation among characteristic information of the dynamic service resources and providing valuable data information for enterprises.
In order to solve the technical problem, the invention provides a data mining method of dynamic service resources, which is characterized by comprising the following steps:
selecting characteristic information of the dynamic service resources as fields, and setting a plurality of attributes of each field and corresponding attribute values of the attributes;
encoding the attribute of each field;
and mining the association relation among the fields of the dynamic service resources by adopting a genetic algorithm.
Further, the encoding the attribute of each field includes:
and encoding the attribute of each field by adopting a real number encoding mode.
Further, the encoding the attribute of each field in a real number encoding manner includes:
each field corresponds to an attribute value array, and a label array is additionally arranged behind each field attribute value array; the attribute value array of each field and the corresponding label array form a group, the first array value of the ith group is a certain attribute value of the field i, the value range of the second array value is {0,1,2}, and the value indicates whether the corresponding attribute value array is in the association rule of data mining or not; where i ∈ {1, 2., M }, where M is the number of fields.
Further, the mining of the association relationship between the fields of the dynamic service resource by using the genetic algorithm includes:
1) initialization: randomly generating an initial population C, and setting the population scale and the iteration times;
2) setting a fitness function;
3) genetic manipulation: selection operations, crossover operations, and mutation operations;
4) simulating annealing operation;
5) judging whether the iteration algebra reaches a preset value; if not, repeating the step 3); and if the preset value is reached, acquiring the association relation among the fields of the dynamic service resources.
Further, the selecting operation includes:
selecting individuals by roulette method, wherein the size of the group is M (50-150), and the size of the individual CjHas a fitness value of F (C)j) Then the individual CjThe probability of being selected is:
Figure BDA0002302416340000021
certain improvement is carried out on a selection operator:
searching and classifying individuals with the same attribute, and defining j (j is 1,2, …, n) th class, wherein n represents the individual CjThe number of (c), then the individual concentrations:
Figure BDA0002302416340000031
in the formula: gamma rayjRepresents the number of j-th classes;
individual concentration probability: because of Σ ρIndividual concentration×P Probability of individual concentration1 ≡ 1, i.e.
Figure BDA0002302416340000032
So as to obtain the individual concentration probability
Figure BDA0002302416340000033
Individual selection probability:
Figure BDA0002302416340000034
α is the selection weight coefficient.
Further, the interleaving operation includes:
adapting the cross probability dynamically, with adaptationThe degree changes to adjust the changes automatically; adaptive cross probability PcComprises the following steps:
Figure BDA0002302416340000035
in the formula: pc1,Pc2E.g. random number of (0.2, 1); f is the greater fitness value of the two crossed individuals; fmaxThe maximum fitness value in the current population;
Figure BDA0002302416340000036
and the average fitness value of the current population.
Further, the mutation operation comprises:
adopting self-adaptive variation probability; adaptive mutation probability PmComprises the following steps:
Figure BDA0002302416340000037
in the formula: pm1,Pm2Epsilon (0.0005,0.1) is a random number; f' is the fitness value of the individual to be mutated; fmaxThe maximum fitness value in the current population;
Figure BDA0002302416340000038
and the average fitness value of the current population.
Further, the simulated annealing operation comprises:
judging the fitness value of the new individual subjected to genetic operation, and replacing the new individual subjected to genetic operation if the fitness value is greater than the fitness of the original individual; if the fitness value of the original individual is lower, a new individual is received by adopting the Metropolis criterion of simulated annealing.
Compared with the prior art, the invention has the beneficial effects that: the invention relates to a data mining method of dynamic service resources, which is used for mining potential relation among fields (characteristic information) of the dynamic service resources, providing more scientific and efficient management for the dynamic service resources and guiding enterprises to make correct technology and operation decisions so as to improve the operation efficiency of manufacturing enterprises and obtain maximum benefits.
Drawings
FIG. 1 is a schematic flow diagram of the process of the present invention;
fig. 2 is a line diagram corresponding to the machine tool attribute mapping result in the embodiment.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
The invention relates to a data mining method of dynamic service resources, which aims at the dynamic service resources owned by enterprises and solves the incidence relation between dynamic service resource data by using a genetic algorithm. Referring to fig. 1, the following process is included:
step 1: and (5) initializing.
Analyzing the dynamic service resources, selecting the characteristic information of the dynamic service resources as fields, recording the number of the fields as M, setting a plurality of attributes and corresponding attribute values of each field, randomly generating an initial population C, setting the population scale and the iteration times, and defining as follows: c ═ C1,C2,C3,…,CmIn which C ismRepresents the m-th individual in the population C, and m is the number of individuals in the population C (for example, the value is 100).
Step 2: and adopting real number array coding.
When encoding an individual (i.e. a dynamic service resource), the present invention needs to set fields and attribute values of the dynamic service resource, where the correspondence between the fields and the attribute values is shown in table 1, O, S, T indicates the number of attribute values of each field. The value of the field M is determined according to the information type of the dynamic service resource and is not a unique value. For example, when the dynamic service resources of the employees are set, the fields comprise ages, academic calendars and the like, and then the ages are continuously subdivided into three age attributes of 20-30, 30-45 and 45-60, wherein the attribute values are 1,2 and 3 respectively; the study calendar is divided into five attributes of junior high school, major, basic, major and above, and the attribute values are 1,2,3,4 and 5 respectively.
TABLE 1 field vs. Attribute value
Figure BDA0002302416340000051
In order to convert the content of the attribute value into data of a numerical type, individuals in the population are encoded according to a real number encoding mode, the encoding length is 2M, and every two arrays form a group from beginning to end, and the total number of the groups is M.
And adding a label array behind each array for representing the field attribute value, wherein the array is used for judging whether the previous field attribute value array is in the rule or not. The first array value of the ith group is a certain attribute value of the field i, the value is a random value in an attribute value range, the value range of the second array value is {0,1,2}, and the value indicates whether the first attribute value array is in the association rule of data mining or not; where i ∈ {1, 2.,. M }.
In the embodiment of the invention, an array Z [2M ] is adopted to represent the codes, Z [ i ] represents the attribute value genes of the field i, Z [ i +1] represents whether the field i is in the association rules, is not in the association rules, has a value of 0, is in the front piece, has a value of 1, is in the back piece, and has a value of 2, wherein i belongs to {1, 2.., M }, and then the individual codes of the database are shown in Table 2. O, S, T indicates the number of attribute values for each field.
TABLE 2 Individual codes
Array of elements Z[1] Z[2] Z[3] Z[4] ... Z[2M-1] Z[2M]
Encoding 1～ O 0,1,2 1～ S 0,1,2 ... 1～ T 0,1,2
And step 3: and setting a fitness function.
In genetic algorithms, it is generally required that the fitness value is non-negative, and the larger the value, the better. Since the support describes the importance of the data, which is proportional to the association rule, the fitness function f (x) is:
Figure BDA0002302416340000061
in the formula: supportminiRepresenting the minimum support degree set by the user; support (x) is the support degree of the association rule, x refers to an individual, and the greater the support degree, the more important the association rule.
The dynamic resource data mining method provided by the invention is used for mining the association relation between the fields, so that the setting of the fitness function is related to the association support degree of the field set.
And 4, carrying out genetic manipulation.
Firstly, selecting operation, the patent introduces the concept of individual concentration on the basis of the traditional roulette selecting method to jointly complete the selecting operation; secondly, performing cross operation, namely performing single cross operation based on real number coding, and performing a judgment standard of the cross operation by using an improved self-adaptive formula; finally, mutation operation; and in the variation link, uniform variation operation is selected, and an improved self-adaptive formula is utilized to carry out the judgment standard of the variation operation.
Step 4.1: selecting individuals by rouletteLet the size of the population be M (50. ltoreq. M. ltoreq.150), and the individual CjHas a fitness value of F (C)j) Then the individual CjThe probability of being selected is:
Figure BDA0002302416340000062
the roulette-based method cannot guarantee that individuals with high fitness values will be selected certainly, and can cause the phenomenon of 'precocity', so that certain improvements are made to the selection operator:
searching and classifying individuals with the same attribute, and defining j (j is 1,2, …, n) th class, wherein n represents the individual CjThe number of (c), then the individual concentrations:
Figure BDA0002302416340000063
in the formula: gamma rayjIndicating the number of jth classes.
Individual concentration probability: because of Σ ρIndividual concentration×P Probability of individual concentration1 ≡ 1, i.e.
Figure BDA0002302416340000064
So as to obtain the individual concentration probability
Figure BDA0002302416340000071
Individual selection probability:
Figure BDA0002302416340000072
wherein α (0 < α < 1) is the selection weight coefficient.
Step 4.2: because the coding method of the real number array is adopted, a single intersection mode can be selected. In order to effectively prevent the occurrence of the phenomenon of premature convergence in the genetic algorithm, the crossover operator is improved to a certain extent, and the self-adaptive dynamic adjustment of the crossover probability is adopted to automatically adjust the change along with the change of the fitness. Adaptive cross probability PcComprises the following steps:
Figure BDA0002302416340000073
in the formula: pc1,Pc2E.g. random number of (0.2, 1);f is the greater fitness value of the two crossed individuals; fmaxThe maximum fitness value in the current population;
Figure BDA0002302416340000074
and the average fitness value of the current population.
Step 4.3: because a real number value coding method is adopted, uniform variation is selected. Also to prevent the occurrence of "precocity", adaptive mutation probabilities are employed. Adaptive mutation probability PmComprises the following steps:
Figure BDA0002302416340000075
in the formula: pm1,Pm2Epsilon (0.0005,0.1) is a random number; f' is the fitness value of the individual to be mutated; fmaxThe maximum fitness value in the current population;
Figure BDA0002302416340000076
and the average fitness value of the current population.
And 5: and simulating an annealing operation. Judging the fitness value of the new individual subjected to genetic operation, and replacing the new individual subjected to genetic operation if the fitness value is greater than the fitness of the original individual; if the fitness value of the original individual is lower, a new individual is received by adopting the Metropolis criterion of simulated annealing.
Generating a new individual after crossing and mutation operations, and replacing the new individual if the fitness value of the new individual is larger than that of the initial individual; otherwise, new individuals are received using Metropolis's criteria for simulated annealing. Thus, the diversity of the population is maintained, and the optimal solution of the genetic algorithm is obtained with a certain probability PnReceiving a new individual:
Figure BDA0002302416340000081
in the formula: ζ is a positive number less than 1; confidenceiConfidence for parent class; confidencei+1A confidence that is a subclass; t is temperature, and T gradually decreases with the increase of the iteration number.
Step six: and after the termination condition is met, decoding the attribute values of the fields obtained by the optimal solution, and mining the associated data information among the dynamic service resources according to the attribute values.
Example 1:
in order to realize the application of the improved genetic algorithm, a machine tool service data table in a certain company dynamic service resource platform is sorted, the genetic algorithm is used for solving the relation between machine tool dynamic service resources, fields defined by a machine tool have grades, regions, time and the like, different fields have different attributes, which indicate the dynamic service resources, the genetic algorithm has uncertainty, the genetic algorithm finds out individuals with high support degree through a fitness function, potential association relations between the fields are found out through decoding, for example, a certain type of machine tool is extremely needed in a certain season and the data mining is carried out.
In this embodiment, a part of attributes are selected for analysis and processing, and a new machine tool service data record table is established, as shown in table 3.
TABLE 3 machine tool service data record table
Figure BDA0002302416340000082
Figure BDA0002302416340000091
From the above record table, the resulting fields and their relationships with attributes are shown in table 4.
TABLE 4 machine tool service attribute mapping coding table
Figure BDA0002302416340000092
Figure BDA0002302416340000101
As can be seen from table 4, the fields in table 3 have been converted into numerical values to represent the mapping results of the database (the database is obtained according to the order, contains the information in table 4, and the values in each row refer to the code values in table 4 to obtain the machine tool attributes.) as shown in table 5.
Table 5 attribute value mapping result table
Figure BDA0002302416340000102
Figure BDA0002302416340000111
As shown in fig. 2, the line graph corresponding to the attribute mapping result is obtained by accumulating numerical values of the rows in table 6 corresponding to the 6 attribute code values in fig. 2.
As can be seen from fig. 2, each attribute mapping value tends to develop steadily and regularly in a certain section, and has an important reference meaning for performing association rule data mining.
The expression shows that the operation of the genetic algorithm is facilitated by converting each attribute value into the operation of the array through real array coding, so that the effective and rapid mining of the resource service data association rule is facilitated. The array and attribute correspondence is shown in table 6.
Table 6 corresponding relation table of array and attribute field
Figure BDA0002302416340000121
Setting parameters: code length 6 (6 arrays according to table 6), population size 100, minimum support 0.1, minimum confidence 0.5, minimum interest 1, random number Pc1＝0.9、0.2≤Pc2＜0.9、Pm1＝0.1、0.001≤Pm2And less than 0.1, the termination algebra represents a parameter of a constraint algorithm termination condition, and the output after the iteration is finished is not an optimal solution but a set of association rules meeting a given threshold value.
According to the improved genetic algorithm, data mining of association rules is performed on machine tool data information, the obtained result is represented in a triple F (Support, Confidence, Interest) form, and partial results are shown in table 7.
TABLE 7 mined partial association rules
Figure BDA0002302416340000122
Figure BDA0002302416340000131
The above mined partial association rules are interpreted, and the results are as follows:
rule < 1 >: 212031112210 (support: 0.18; confidence: 0.74; interest: 1.07)
Namely < machine grade: middle-high grade; date: quarter 3; the type of the enterprise: large-scale; user areas: area of south China >
Regular meaning: medium and high-grade machine tools provide services mainly to large enterprises in south china in 3 rd quarter.
Rule < 2 >: 212110212220 (support: 0.16; confidence: 0.54; interest: 1.54)
Namely < machine grade: middle-high grade; type of machine tool: a special machine tool; the type of the enterprise: medium size; user areas: area of south China >
Regular meaning: the enterprises which need the medium-high grade special machine tools are mainly medium-sized enterprises in south China.
Rule < 3 >: 204131113022 (support: 0.15; confidence: 0.50; interest: 1.09)
Namely < machine type: a machining center; date: quarter 3; the type of the enterprise: large-scale; additional services: training >
Regular meaning: major enterprises that require machining center services and require additional services for training are on the market in quarter 3.
Rule < 4 >: 103131113022 (support degree: 0.14; confidence degree: 0.88; interest degree: 1.02)
Namely < machine type: a numerical control machine tool; date: quarter 3; the type of the enterprise: large-scale: additional services: training >
Regular meaning: major enterprises requiring numerical control machine tool services in the 3 rd season.
Rule < 5 >: 302031112121 (support: 0.18; confidence: 0.56; interest: 1.17)
Namely < date: quarter 3; the type of the enterprise: large-scale; user areas: the south of China; additional services: training >
Regular meaning: major enterprises in south china are required for machine training services in the 3 rd quarter.
Rule < 6 >: 212031112232 (support: 0.17; confidence: 0.73; interest: 1.65)
Namely < machine grade: middle-high grade; date: quarter 3; the type of the enterprise: large-scale; user areas: the south of China; additional services: maintenance >
Regular meaning: major enterprises in south china are required to service medium and high grade machine tools and provide additional services for maintenance in quarter 3.
The rules mined from above know that: the improved genetic algorithm can effectively realize data mining of association rules, potential relations among machine tool grades, machine tool types, dates, enterprise types, user areas and additional services can be known through the rules (the potential relations are frequent periods of machine tool service requirements in 3 rd quarter, users served by middle-high-grade numerical control machines and machining centers are mostly large enterprises in south China, and the additional training service requirements are provided at the same time), and a certain basis is provided for service management and decision making of a cloud manufacturing service platform. Meanwhile, the following steps are known: the 3 rd quarter is a frequent period of machine tool service demands, and users served by medium-high-grade numerical control machines and machining centers are mostly large enterprises in south China, and meanwhile, extra training service needs are provided. Therefore, the rule mining can help enterprises to make corresponding countermeasures in corresponding time periods, and optimal demand service is provided for users.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.

Claims (8)

1. A data mining method of dynamic service resources is characterized by comprising the following steps:
selecting characteristic information of the dynamic service resources as fields, and setting a plurality of attributes of each field and corresponding attribute values of the attributes;
encoding the attribute of each field;
and mining the association relation among the fields of the dynamic service resources by adopting a genetic algorithm.
2. The method of claim 1, wherein the encoding the attributes of each field comprises:
and encoding the attribute of each field by adopting a real number encoding mode.
3. The method as claimed in claim 2, wherein said encoding the attribute of each field by real number coding comprises:
each field corresponds to an attribute value array, and a label array is additionally arranged behind each field attribute value array; the attribute value array of each field and the corresponding label array form a group, the first array value of the ith group is a certain attribute value of the field i, the value range of the second array value is {0,1,2}, and the value indicates whether the corresponding attribute value array is in the association rule of data mining or not; where i ∈ {1, 2., M }, where M is the number of fields.
4. The method as claimed in claim 1, wherein said mining the association relationship between fields of the dynamic service resource by using the genetic algorithm comprises:
1) initialization: randomly generating an initial population, and setting the population scale and the iteration times;
2) setting a fitness function;
3) genetic manipulation: selection operations, crossover operations, and mutation operations;
4) simulating annealing operation;
5) judging whether the iteration algebra reaches a preset value; if not, repeating the step 3); and if so, outputting the association relationship among the fields of the dynamic service resources.
5. The method of claim 4, wherein the selecting operation comprises:
selecting individuals by roulette method, wherein the size of the group is M (50-150), and the size of the individual CjHas a fitness value of F (C)j) Then the individual CjThe probability of being selected is:
Figure FDA0002302416330000021
and (3) improving a selection operator:
searching and classifying individuals with the same attribute, and defining the individuals as the jth class, then the individual concentration:
Figure FDA0002302416330000022
in the formula: gamma rayjRepresenting the number of j-th classes, wherein M is the number of fields;
individual concentration probability: because of the fact that
Figure FDA0002302416330000023
n represents an individual CjSo as to find the individual concentration probability
Figure FDA0002302416330000024
Individual selection probability:
Figure FDA0002302416330000025
α is the selection weight coefficient.
6. The method of claim 4, wherein the interleaving comprises:
adopting a mode of self-adapting dynamic adjustment of the cross probability, and self-adapting the cross probability PcComprises the following steps:
Figure FDA0002302416330000026
in the formula: pc1,Pc2E.g. random number of (0.2, 1); f is the greater fitness value of the two crossed individuals; fmaxThe maximum fitness value in the current population;
Figure FDA0002302416330000031
and the average fitness value of the current population.
7. The method of claim 4, wherein the mutation operation comprises:
adopting self-adaptive variation probability; adaptive mutation probability PmComprises the following steps:
Figure FDA0002302416330000032
in the formula: pm1,Pm2Epsilon (0.0005,0.1) is a random number; f' is the fitness value of the individual to be mutated; fmaxThe maximum fitness value in the current population;
Figure FDA0002302416330000033
and the average fitness value of the current population.
8. The method of claim 4, wherein the simulated annealing operation comprises:
judging the fitness value of the new individual subjected to genetic operation, and replacing the new individual subjected to genetic operation if the fitness value is greater than the fitness of the original individual; if the fitness value of the original individual is lower, a new individual is received by adopting the Metropolis criterion of simulated annealing.
CN201911226646.0A 2019-12-04 2019-12-04 Data mining method for dynamic service resources Pending CN110990460A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911226646.0A CN110990460A (en) 2019-12-04 2019-12-04 Data mining method for dynamic service resources

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911226646.0A CN110990460A (en) 2019-12-04 2019-12-04 Data mining method for dynamic service resources

Publications (1)

Publication Number Publication Date
CN110990460A true CN110990460A (en) 2020-04-10

Family

ID=70089902

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911226646.0A Pending CN110990460A (en) 2019-12-04 2019-12-04 Data mining method for dynamic service resources

Country Status (1)

Country Link
CN (1) CN110990460A (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130308570A1 (en) * 2012-05-17 2013-11-21 Beijing University Of Posts And Telecommunications Method for joint optimization of schedule and resource allocation based on the genetic algorithm
CN105426966A (en) * 2015-12-14 2016-03-23 河海大学常州校区 Association rule digging method based on improved genetic algorithm
CN109918418A (en) * 2019-03-06 2019-06-21 桂林理工大学 A kind of improvement method for digging of the correlation rule based on genetic algorithm

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130308570A1 (en) * 2012-05-17 2013-11-21 Beijing University Of Posts And Telecommunications Method for joint optimization of schedule and resource allocation based on the genetic algorithm
CN105426966A (en) * 2015-12-14 2016-03-23 河海大学常州校区 Association rule digging method based on improved genetic algorithm
CN109918418A (en) * 2019-03-06 2019-06-21 桂林理工大学 A kind of improvement method for digging of the correlation rule based on genetic algorithm

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
高怀金: "基于遗传算法的Web使用挖掘研究", 《电脑知识与技术》 *

Similar Documents

Publication Publication Date Title
CN107169628B (en) Power distribution network reliability assessment method based on big data mutual information attribute reduction
CN101271572B (en) Image segmentation method based on immunity clone selection clustering
CN111832101A (en) Construction method of cement strength prediction model and cement strength prediction method
CN111897733A (en) Fuzzy test method and device based on minimum set coverage
CN111582325B (en) Multi-order feature combination method based on automatic feature coding
CN111950910B (en) Airport guarantee vehicle task scheduling method based on DBSCAN-GA
CN108564117A (en) A kind of poor student&#39;s auxiliary identification based on SVM
CN110471274A (en) Based on the machine components process line dispatching method for improving unified particle swarm algorithm
CN113901728B (en) Computer second-class assembly line balance optimization method based on migration genetic algorithm
CN116128544A (en) Active auditing method and system for electric power marketing abnormal business data
CN111984514B (en) Log anomaly detection method based on Prophet-bLSTM-DTW
CN110990460A (en) Data mining method for dynamic service resources
Ilich et al. Modeling of employment structural transformations
Wang et al. Multiobjective order acceptance and scheduling on unrelated parallel machines with machine eligibility constraints
Nermend et al. Modeling users’ preferences in the Decision Support System
CN115687788A (en) Intelligent business opportunity recommendation method and system
CN111915077B (en) Machine learning-based thermal state prediction method and system for coal blending and coking
CN114064794A (en) Business expansion file mining and analyzing method based on big data technology
CN110298538B (en) Intelligent workshop combined scheduling control method
Ray et al. Modeling and forecasting of hybrid rice yield using a grey model improved by the genetic algorithm.
CN107516133A (en) A kind of mixing attributive character large data sets clustering algorithm based on CSA
Zheldak et al. THE ALGORITHM OF ARTIFICIAL IMMUNE SYSTEM SIMULATION WITH SAATY SELECTION OPERATOR AND ONE-DIMENSIONAL LOCAL SEARCH.
Setiyani et al. 3D Neighborhood Relationships of Cellular Genetic Algorithms for the Tour Guide Assignment Problem
Ke et al. Asset risk diversity and portfolio optimization with genetic algorithm
CN115293801A (en) Internet click rate prediction method based on recall-sorting idea

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20200410

RJ01 Rejection of invention patent application after publication