CN112418671A - Crowd-sourcing alliance establishment method based on disturbance particle swarm - Google Patents

Crowd-sourcing alliance establishment method based on disturbance particle swarm Download PDF

Info

Publication number
CN112418671A
CN112418671A CN202011325632.7A CN202011325632A CN112418671A CN 112418671 A CN112418671 A CN 112418671A CN 202011325632 A CN202011325632 A CN 202011325632A CN 112418671 A CN112418671 A CN 112418671A
Authority
CN
China
Prior art keywords
particle
alliance
crowd
sourcing
test
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
CN202011325632.7A
Other languages
Chinese (zh)
Inventor
张雷
李珂帆
张�杰
朱银龙
王崇骏
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.)
Nanjing University
Original Assignee
Nanjing 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 Nanjing University filed Critical Nanjing University
Priority to CN202011325632.7A priority Critical patent/CN112418671A/en
Publication of CN112418671A publication Critical patent/CN112418671A/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
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06311—Scheduling, planning or task assignment for a person or group
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/36—Preventing errors by testing or debugging software
    • G06F11/3668—Software testing
    • G06F11/3672—Test management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • 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
    • G06Q10/10—Office automation; Time management
    • G06Q10/101—Collaborative creation, e.g. joint development of products or services
    • 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
    • G06Q10/10—Office automation; Time management
    • G06Q10/103—Workflow collaboration or project management

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Theoretical Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Operations Research (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Computer Hardware Design (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Computing Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Game Theory and Decision Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a crowd-sourcing alliance establishing method based on disturbance particle swarm, which initializes the reward of crowd-sourcing workers according to a capability function and obtains characteristic data; obtaining a three-dimensional data set consisting of all characteristic data and capability functions, using the three-dimensional data set as initial position distribution of cluster optimization, using a PSO algorithm, after adding certain disturbance, enabling the initial position distribution of particles to be in a certain range, and initializing a public testing alliance; in the alliance optimization stage, calculating to obtain an optimal solution based on income according to the initialization data and a given ability function, and adjusting the ability function in the calculation process according to different characteristic data; in the alliance forming stage, each particle dynamically adjusts the flight speed of the particle by following the best position of the particle and the best position of the particle in the group, and finally, the optimal solution is found out through search iteration. The invention enables the individual profit to be maximized, thus saving costs as far as possible in the view of optimizing the allocation of personnel.

Description

Crowd-sourcing alliance establishment method based on disturbance particle swarm
Technical Field
The invention mainly relates to a crowd-sourcing alliance establishing method based on disturbance particle swarm, and belongs to the field of model algorithm design.
Background
Data volume sharply increases and diversity caused by a large number of user groups in an internet mode gradually arouses the rise of crowd-sourcing technology and other utilization crowd-sourcing resources, crowd-sourcing is used as one of research hotspots in crowd-sourcing collaborative computing, and task participants complete tasks and distribute benefits through collaborative cooperation in a voluntary mode through a task publishing mode. Software testing is an important component of software industry, is a technology developed for a long time and is mature, the field of software testing is changed in the big data era, a mass testing platform is gradually mainstream, compared with the traditional testing, the mass testing gathers testing experts distributed in various industries and having related resources in various fields, the testing experts can respond to the testing requirement of the mass testing platform at any time, and the full coverage of the industries, the time period, the equipment and the regions are realized on the software testing. But due to uncertainty in the tester's information and its self-benefit, it may result in a higher cost for the numerous testing tasks than expected or even in tasks that cannot be completed on a quality-by-quality basis as expected. Based on this background, the present document attempts to reduce the cost of paying testers by designing an optimization model for task allocation of the testers in the process of crowd test and designing a corresponding game mechanism on the basis of the model.
In order to save cost as much as possible on the premise of obtaining high-quality results, the most widely used in the existing many-test system is an iteration-summary model framework, a demand party submits test tasks to a many-test platform, the tasks are distributed to a plurality of test workers, and the platform obtains respective results of each worker and then carries out sorting and aggregation to generate answers.
The method is characterized in that a task allocation mechanism is designed by taking maximized cost benefits and cost saving as optimization targets and utilizing a greedy strategy, so that problems related to task allocation in a crowdsourcing process are solved, reliability updating is carried out on workers by utilizing historical information of the workers, the reliability mechanism is designed according to historical records and the completion quality of the current task, and the reliability mechanism is hooked with reward paid finally, so that the workers are encouraged to continuously complete the task with high quality, but a certain data basis is required to be established, and the problem of optimization of the initial task quality of a user is not well solved.
Disclosure of Invention
The purpose of the invention is as follows: the invention mainly solves the technical problems that on the basis of a mass test background such as software test, the minimized project cost is selected as a research target, the research is carried out aiming at task allocation, the task decomposition and the optimized division of labor of testers are aimed at, and the problems of potential interest amplification caused by human participation and the like are avoided. The invention provides a crowd-sourcing alliance establishing method based on disturbance particle swarm, which aims at optimizing and decomposing high-dimensional complex tasks, performs initial task allocation according to the capability of workers and adopts an optimization algorithm of optimization Particle Swarm (PSO) to obtain the optimal sequencing of the workers under each task.
The technical scheme is as follows: in order to achieve the purpose, the invention adopts the technical scheme that:
a crowd-sourcing alliance establishment method based on disturbance particle swarm comprises a data acquisition stage, a data acquisition stage and a data acquisition stage, wherein the data acquisition stage is used for initializing reward of crowd-sourcing workers according to a capability function and acquiring data of four characteristics of function test, performance test, compatibility test and safety test of objects in enough real application scenes; in the data preprocessing stage, a safety test and a performance test are synthesized to obtain a three-dimensional data set consisting of all characteristic data and capability functions, the three-dimensional data set is used as initial position distribution of cluster optimization, a PSO algorithm is used, after a certain disturbance is added, the initial position distribution of particles is in a certain range, and a public test alliance is initialized; in the alliance optimization stage, calculating to obtain an optimal solution based on income according to the initialization data and a given ability function, and adjusting the ability function in the calculation process according to different characteristic data; in the alliance forming stage, each particle dynamically adjusts the flight speed of the particle by following the individual best position of the particle and the global best position of the group, and finally finds an approximate optimal solution through search iteration, and the method specifically comprises the following steps:
step 1, data acquisition, namely initializing reward of a worker according to a capability function, and acquiring data of four characteristics of a function test, a performance test, a compatibility test and a safety test owned by an object in an application scene;
step 2, data preprocessing: synthesizing safety test and performance test characteristics to obtain a three-dimensional data set consisting of all characteristic data and capability functions, using the three-dimensional data set as initial position distribution of cluster optimization, using a PSO algorithm, after adding certain disturbance, distributing the initial positions of particles in a certain range, and initializing a public test alliance;
step 3, alliance optimization: based on the step 2, calculating to obtain an optimal solution based on the profit according to the initialization data and the given capability function, and adjusting the capability function in the calculation process according to different feature data;
and 4, forming a union, performing the operation in the step 3 in an iterative manner, dynamically adjusting the flight speed of each particle by following the best position of each particle per se and the best position of the group per se, and finally finding an approximate optimal solution through searching iteration.
Preferably: the data preprocessing method in the step 2 is as follows:
step 2a), defining a capability function:
Figure BDA0002794186950000021
wherein the content of the first and second substances,
Figure BDA0002794186950000022
the function of the capability is represented by,
Figure BDA0002794186950000023
representing the position vector, t representing the number of iterations,
Figure BDA0002794186950000024
representing a velocity of a location;
synthesizing safety test and performance test characteristic data to obtain a three-dimensional data set;
step 2b) adding disturbance to make the initial position of the particles distributed in a certain range and the initial velocity
Figure BDA0002794186950000025
Wherein the content of the first and second substances,
Figure BDA0002794186950000026
initial position
Figure BDA0002794186950000027
Wherein the content of the first and second substances,
Figure BDA0002794186950000028
the parameters satisfy:
Figure BDA0002794186950000031
wherein, KiThe number of the particles is shown as,
Figure BDA0002794186950000032
which is indicative of the velocity of the particles,
Figure BDA0002794186950000033
indicating the particle position.
Step 2c), initializing a public testing alliance, and defining the group scale m;
and 2d), calculating by using a PSO algorithm.
Preferably: and (3) a method for alliance optimization in the step 3:
step 3a), initializing the maximum number of iterations tmaxPrecision of algorithm ε, and parameter r1,r2,c1,c2,ωmax,ωminWherein the parameter r1,r2R is more than or equal to 01，r2≤1；
Step 3b), judging the PSO algorithm termination condition: if it is
Figure BDA0002794186950000034
If it is true, then outputObtaining a current position vector and an accuracy value, and finishing the algorithm;
step 3c), otherwise, judging that t is more than tmaxIf yes, outputting the current position vector and the precision value, and finishing the algorithm;
step 3d), if not, repeating the step 3b) and the step 3c) until the condition is met.
Preferably: and (4) a method for forming the alliance in the step 4:
step 4a), in the t +1 th iteration, the particle carries out the updating formula of the speed and the position:
Figure BDA0002794186950000035
wherein: r is1、r2Is [0,1 ]]Random weights in between, for preserving diversity of the population, c1、c2As a learning factor, Vi t+1Denotes the velocity of particle i at t +1 iterations, ω denotes the inertial weight, Pi bestRepresents the optimum position, G, of the particle i searched so farbestRepresenting the optimal position searched so far for the entire population,
Figure BDA0002794186950000036
represents the position of particle j at t iterations;
step 4b), in order to ensure that the iteration is optimized within a certain range, defining the inertia weight omega as follows:
Figure BDA0002794186950000037
wherein: omegamaxIs an initial weight, ωminTo final weight, tmaxIs the maximum iteration number, and t is the current iteration number;
step 4c), updating PbestjAnd Gbest, the updated representation is as follows:
Figure BDA0002794186950000041
Gbest＝argmin(f(Pbest1),f(Pbest2),...,f(Pbestm),)；
step 4d), updating
Figure BDA0002794186950000042
And
Figure BDA0002794186950000043
updating the inertial weight ω based on step 4b), and then
Figure BDA0002794186950000044
And
Figure BDA0002794186950000045
and (6) updating.
Compared with the prior art, the invention has the following beneficial effects:
the Particle Swarm Optimization (PSO) algorithm is designed aiming at the task allocation process, the task is analyzed, the self-supervision learning is carried out according to the capability function of the worker, the indexes of four test types are selected, and the results prove that the Particle Swarm Optimization (PSO) algorithm has good model convergence and can well save the mass test cost under the external disturbance through different mass test specifications and the comparison experiment with disturbance.
Drawings
FIG. 1 is an overall flow chart of the method of the present invention;
FIG. 2 is a flow chart of the present invention for establishing a crowd-sourcing alliance using a PSO-based algorithm.
Detailed Description
The present invention is further illustrated by the following description in conjunction with the accompanying drawings and the specific embodiments, it is to be understood that these examples are given solely for the purpose of illustration and are not intended as a definition of the limits of the invention, since various equivalent modifications will occur to those skilled in the art upon reading the present invention and fall within the limits of the appended claims.
A crowd-sourcing alliance establishment method based on perturbed particle swarm, as shown in fig. 1-2, comprising the following steps:
step 1, data acquisition, namely initializing reward of a worker according to a capability function and acquiring data of four characteristics of a function test, a performance test, a compatibility test and a safety test owned by an object in a sufficient real application scene.
Step 2, data preprocessing, namely synthesizing safety test and performance test characteristics to obtain a three-dimensional data set consisting of all characteristic data and capability functions, using the three-dimensional data set as initial position distribution of cluster optimization, and using a PSO algorithm to distribute the initial position of data in a certain range after adding certain disturbance;
the step 2 comprises the following steps:
step 2a) defining a capability function:
Figure BDA0002794186950000046
wherein the content of the first and second substances,
Figure BDA0002794186950000047
the function of the capability is represented by,
Figure BDA0002794186950000049
representing the position vector, t representing the number of iterations,
Figure BDA0002794186950000048
representing a velocity of a location;
synthesizing safety test and performance test characteristic data to obtain a three-dimensional data set;
step 2b) adding disturbance to make the initial position of the particles distributed in a certain range and the initial velocity
Figure BDA0002794186950000051
Wherein the content of the first and second substances,
Figure BDA0002794186950000052
initial position
Figure BDA0002794186950000053
Wherein the content of the first and second substances,
Figure BDA0002794186950000054
each parameter satisfies the following formula:
Figure BDA0002794186950000055
wherein, KiThe number of the particles is shown as,
Figure BDA0002794186950000056
which is indicative of the velocity of the particles,
Figure BDA0002794186950000057
indicating the particle position.
Step 2c), initializing a public testing alliance, and defining the group scale m;
and 2d) calculating by using a PSO algorithm.
Step 3, alliance optimization, based on the step 2, calculating and obtaining an optimal solution based on income according to the initialization data and a given ability function, and adjusting the ability function in the calculation process according to different feature data;
step 3 comprises the following steps:
step 3a) initializing the maximum number of iterations tmaxPrecision of algorithm ε, and parameter r1,r2,c1,c2,ωmax,ωmin0 wherein each parameter satisfies 0. ltoreq. r1，r2≤1；
And 3b) judging the PSO algorithm termination condition. If it is
Figure BDA0002794186950000058
If yes, outputting the current position vector and the precision value, and finishing the algorithm;
step 3c) otherwise, judging that t is more than tmaxIf yes, outputting the current position vector and the precision value, and finishing the algorithm;
if the step 3d) is not true, repeating the step 3b) and the step 3c) until the condition is met.
And 4, forming a union, performing the operation in the step 3 in an iterative manner, dynamically adjusting the flight speed of each particle by following the best position of each particle per se and the best position of the group per se, and finally finding an approximate optimal solution through searching iteration.
Step 4 comprises the following steps:
step 4a) in the t +1 th iteration, the particle carries out the update formula of the speed and the position:
Figure BDA0002794186950000061
wherein r is1、r2Is [0,1 ]]Random weights in between, for preserving diversity of the population, c1、c2As a learning factor, Vi t+1Denotes the velocity of particle i at t +1 iterations, ω denotes the inertial weight, Pi bestRepresents the optimum position, G, of the particle i searched so farbestRepresenting the optimal position searched so far for the entire population,
Figure BDA0002794186950000062
represents the position of particle j at t iterations;
step 4b) to ensure that the iteration is optimized within a certain range, ω is defined as follows:
Figure BDA0002794186950000063
wherein omegamaxIs an initial weight; omegaminIs the final weight; t is tmaxIs the maximum iteration number; t is the current iteration number;
step 4c) updating PbestjAnd Gbest, the updated representation is as follows:
Figure BDA0002794186950000064
Gbest＝argmin(f(Pbest1),f(Pbest2),...,f(Pbestm),)；
step 4d) update
Figure BDA0002794186950000065
And
Figure BDA0002794186950000066
updating the inertial weight ω based on step 4b), and then
Figure BDA0002794186950000067
And
Figure BDA0002794186950000068
and (6) updating.
A large number of data experiments prove that the iteration effect is obviously better after the scale is increased, the experimental result can almost reach the global optimum, the tie in local deadlock is avoided, and the effectiveness and the reliability of the Particle Swarm Optimization (PSO) algorithm are proved. After disturbance is added, the influence on the convergence result is small, the optimal solution is almost consistent and can be ignored, and the algorithm still has good adaptability under the disturbance.
In summary, the invention is based on a high-dimensional complex crowd-sourcing task, and adopts an optimization algorithm of a Particle Swarm Optimization (PSO) to obtain the optimal worker sequence under each task, so that the personal profit is maximized, and the cost is saved as far as possible in the aspect of optimizing the personnel allocation. The Particle Swarm Optimization (PSO) algorithm model has good convergence, and can well save the mass measurement cost under external disturbance.
The above description is only of the preferred embodiments of the present invention, and it should be noted that: it will be apparent to those skilled in the art that various modifications and adaptations can be made without departing from the principles of the invention and these are intended to be within the scope of the invention.

Claims (4)

1. A crowd-sourcing alliance establishment method based on disturbance particle swarm is characterized by comprising the following steps:
step 1, data acquisition, namely initializing reward of a worker according to a capability function, and acquiring data of four characteristics of a function test, a performance test, a compatibility test and a safety test owned by an object in an application scene;
step 2, data preprocessing: synthesizing safety test and performance test characteristics to obtain a three-dimensional data set consisting of all characteristic data and capability functions, using the three-dimensional data set as initial position distribution of cluster optimization, using a PSO algorithm, after adding certain disturbance, distributing the initial positions of particles in a certain range, and initializing a public test alliance;
step 3, alliance optimization: based on the step 2, calculating to obtain an optimal solution based on the profit according to the initialization data and the given capability function, and adjusting the capability function in the calculation process according to different feature data;
and 4, forming a union, performing the operation in the step 3 in an iterative manner, dynamically adjusting the flight speed of each particle by following the best position of each particle per se and the best position of the group per se, and finally finding an approximate optimal solution through searching iteration.
2. The crowd-sourcing alliance establishment method based on perturbed particle swarm of claim 1, wherein: the data preprocessing method in the step 2 is as follows:
step 2a), defining a capability function:
Figure FDA0002794186940000011
wherein the content of the first and second substances,
Figure FDA0002794186940000012
the function of the capability is represented by,
Figure FDA0002794186940000013
representing the position vector, t representing the number of iterations,
Figure FDA0002794186940000014
representing a velocity of a location;
synthesizing safety test and performance test characteristic data to obtain a three-dimensional data set;
step 2b) adding disturbance to make the initial position of the particles distributed in a certain range and the initial velocity
Figure FDA0002794186940000015
Wherein the content of the first and second substances,
Figure FDA0002794186940000016
initial position
Figure FDA0002794186940000017
Wherein the content of the first and second substances,
Figure FDA0002794186940000018
the parameters satisfy:
Figure FDA0002794186940000019
wherein, KiThe number of the particles is shown as,
Figure FDA00027941869400000110
which is indicative of the velocity of the particles,
Figure FDA00027941869400000111
the position of the particle is indicated by the indication,
step 2c), initializing a public testing alliance, and defining the group scale m;
and 2d), calculating by using a PSO algorithm.
3. The crowd-sourcing alliance establishment method based on perturbed particle swarm of claim 2, wherein: and (3) a method for alliance optimization in the step 3:
step 3a), initializing the maximum number of iterations tmaxPrecision of algorithm ε, and parameter r1,r2,c1,c2,ωmax,ωminWherein the parameter r1,r2R is more than or equal to 01，r2≤1；
Step 3b), judging the PSO algorithm termination condition: if it is
Figure FDA0002794186940000021
If yes, outputting the current position vector and the precision value, and finishing the algorithm;
step 3c), otherwise, judging that t is more than tmaxIf yes, outputting the current position vector and the precision value, and finishing the algorithm;
step 3d), if not, repeating the step 3b) and the step 3c) until the condition is met.
4. The crowd-sourcing alliance establishment method based on perturbed particle swarm of claim 3, wherein: and (4) a method for forming the alliance in the step 4:
step 4a), in the t +1 th iteration, the particle carries out the updating formula of the speed and the position:
Figure FDA0002794186940000022
wherein: r is1、r2Is [0,1 ]]Random weights in between, for preserving diversity of the population, c1、c2As a learning factor, Vi t+1Denotes the velocity of particle i at t +1 iterations, ω denotes the inertial weight, Pi bestRepresents the optimum position, G, of the particle i searched so farbestRepresenting the optimal position searched so far for the entire population,
Figure FDA0002794186940000023
represents the position of particle j at t iterations;
step 4b), in order to ensure that the iteration is optimized within a certain range, defining the inertia weight omega as follows:
Figure FDA0002794186940000024
wherein: omegamaxIs an initial weight, ωminTo final weight, tmaxIs the maximum iteration number, and t is the current iteration number;
step 4c), updating PbestjAnd Gbest, the updated representation is as follows:
Figure FDA0002794186940000025
Gbest＝argmin(f(Pbest1),f(Pbest2),...,f(Pbestm),)；
step 4d), updating
Figure FDA0002794186940000026
And
Figure FDA0002794186940000027
updating the inertial weight ω based on step 4b), and then
Figure FDA0002794186940000028
And
Figure FDA0002794186940000029
and (6) updating.
CN202011325632.7A 2020-11-24 2020-11-24 Crowd-sourcing alliance establishment method based on disturbance particle swarm Pending CN112418671A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011325632.7A CN112418671A (en) 2020-11-24 2020-11-24 Crowd-sourcing alliance establishment method based on disturbance particle swarm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011325632.7A CN112418671A (en) 2020-11-24 2020-11-24 Crowd-sourcing alliance establishment method based on disturbance particle swarm

Publications (1)

Publication Number Publication Date
CN112418671A true CN112418671A (en) 2021-02-26

Family

ID=74777442

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011325632.7A Pending CN112418671A (en) 2020-11-24 2020-11-24 Crowd-sourcing alliance establishment method based on disturbance particle swarm

Country Status (1)

Country Link
CN (1) CN112418671A (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101790251A (en) * 2010-01-13 2010-07-28 北京邮电大学 Wireless sensor node alliance generating method based on improved particle swarm optimization algorithm
US20110131076A1 (en) * 2009-12-01 2011-06-02 Thomson Reuters Global Resources Method and apparatus for risk mining
US20120316916A1 (en) * 2009-12-01 2012-12-13 Andrews Sarah L Methods and systems for generating corporate green score using social media sourced data and sentiment analysis
CN104036186A (en) * 2014-07-02 2014-09-10 浪潮电子信息产业股份有限公司 Anti-attack engine implementation method
CN106060851A (en) * 2016-06-30 2016-10-26 南京理工大学 Secure resource optimization method under congestion control in heterogeneous cloud wireless access network
CN108830372A (en) * 2018-06-08 2018-11-16 湖北工业大学 A kind of adaptive particle swarm optimization method of Traveling Salesman Problem
CN111091240A (en) * 2019-12-10 2020-05-01 河南省计量科学研究院 Public institution electric power energy efficiency monitoring system and service method

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110131076A1 (en) * 2009-12-01 2011-06-02 Thomson Reuters Global Resources Method and apparatus for risk mining
US20120316916A1 (en) * 2009-12-01 2012-12-13 Andrews Sarah L Methods and systems for generating corporate green score using social media sourced data and sentiment analysis
CN101790251A (en) * 2010-01-13 2010-07-28 北京邮电大学 Wireless sensor node alliance generating method based on improved particle swarm optimization algorithm
CN104036186A (en) * 2014-07-02 2014-09-10 浪潮电子信息产业股份有限公司 Anti-attack engine implementation method
CN106060851A (en) * 2016-06-30 2016-10-26 南京理工大学 Secure resource optimization method under congestion control in heterogeneous cloud wireless access network
CN108830372A (en) * 2018-06-08 2018-11-16 湖北工业大学 A kind of adaptive particle swarm optimization method of Traveling Salesman Problem
CN111091240A (en) * 2019-12-10 2020-05-01 河南省计量科学研究院 Public institution electric power energy efficiency monitoring system and service method

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
ZHOU, JG 等: "Short-Term Wind Power Forecasting: A New Hybrid Model Combined Extreme-Point Symmetric Mode Decomposition, Extreme Learning Machine and Particle Swarm Optimization", 《SUSTAINABILITY》, vol. 10, no. 09, 30 September 2018 (2018-09-30) *
吴成明 等: "基于TVAC-PSO算法的可重构微电网优化调度方案", 《电力科学与工程》, vol. 34, no. 10, 31 October 2018 (2018-10-31), pages 15 - 23 *
张帆: "多臂手术机器人效能优化研究及虚拟仿真系统构建", 《中国优秀硕士学位论文全文数据库（电子期刊）》信息科技辑, no. 02, 15 February 2017 (2017-02-15) *

Similar Documents

Publication Publication Date Title
CN106228185B (en) A kind of general image classifying and identifying system neural network based and method
CN108549233B (en) Unmanned aerial vehicle air combat maneuver game method with intuitive fuzzy information
CN105044662A (en) Fingerprint clustering multi-point joint indoor positioning method based on WIFI signal intensity
Slivinski et al. A hybrid particle–ensemble Kalman filter for Lagrangian data assimilation
CN108320293A (en) A kind of combination improves the quick point cloud boundary extractive technique of particle cluster algorithm
CN104112062B (en) The acquisition methods of wind-resources distribution based on interpolation method
WO2021196743A1 (en) Tropical cyclone intensity forecast information generation method and system
CN113206887A (en) Method for accelerating federal learning aiming at data and equipment isomerism under edge calculation
CN111415379A (en) Three-dimensional point cloud data registration method based on cuckoo optimization
CN109033543A (en) A kind of heterogeneous area's vegetation fraction estimation method, device and equipment of earth's surface
CN115420294A (en) Unmanned aerial vehicle path planning method and system based on improved artificial bee colony algorithm
CN113553755A (en) Power system state estimation method, device and equipment
Feng et al. Point cloud registration algorithm based on the grey wolf optimizer
CN110363219B (en) Method for identifying middle-stage target micro-motion form of trajectory based on convolutional neural network
Chen et al. SA-SinGAN: self-attention for single-image generation adversarial networks
CN112418671A (en) Crowd-sourcing alliance establishment method based on disturbance particle swarm
Zhang et al. Modeling of spatial distributions of farmland density and its temporal change using geographically weighted regression model
CN109489636B (en) Real-time acquisition system and acquisition method for surveying and mapping operation
CN117241215A (en) Wireless sensor network distributed node cooperative positioning method based on graph neural network
CN116017476A (en) Wireless sensor network coverage design method and device
CN114329855B (en) Sensor layout optimization and rapid deployment method of wireless vision sensing network
CN109493065A (en) A kind of fraudulent trading detection method of Behavior-based control incremental update
CN114841066A (en) Flying dust particle drift trajectory model and modeling method thereof
CN113821967A (en) Large sample training data generation method based on scattering center model
CN114185039A (en) Radar target one-dimensional range profile intelligent identification method

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