CN112668871B - Method for dynamically distributing special weights in multi-round group decision - Google Patents
Method for dynamically distributing special weights in multi-round group decision Download PDFInfo
- Publication number
- CN112668871B CN112668871B CN202011562835.8A CN202011562835A CN112668871B CN 112668871 B CN112668871 B CN 112668871B CN 202011562835 A CN202011562835 A CN 202011562835A CN 112668871 B CN112668871 B CN 112668871B
- Authority
- CN
- China
- Prior art keywords
- calculating
- expert
- quality
- decision data
- round
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 17
- 238000004364 calculation method Methods 0.000 claims abstract description 12
- 230000003542 behavioural effect Effects 0.000 claims abstract description 4
- 238000011156 evaluation Methods 0.000 claims description 4
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a dynamic distribution method of special weights in multi-round group decisions, which comprises five steps of collecting expert decision data, calculating decision data quality, calculating behavior evolution quality, calculating expert weights and calculating group decision results. The quality of the decision data is calculated by quantitatively analyzing the uncertainty and the inconsistency of the decision data; the behavior evolution quality is obtained through calculation by quantitatively analyzing uncertainty and expected evolution characteristics of expert in decision data of the t-th round and the t-1 th round; calculating according to the decision data quality and the behavior evolution quality to obtain expert weights; and calculating by adopting a weighted average algorithm of the cloud model to obtain a group decision result. According to the method, the cloud model is used for representing the expert's decision data, so that the simplicity of quantitatively calculating the quality of the decision data and the quality of behavioral evolution is enhanced, the rationality of expert weight distribution is improved, and the achievement of group consensus is promoted.
Description
Technical Field
The invention belongs to the field of group decision, and particularly relates to a method for dynamically distributing special weights in multiple rounds of group decision.
Background
Group intelligence is an effective tool to deal with many complex real-world problems, and human beings rely on social groups such as committees, teams of experts, task groups, etc. to make many important decisions. It is difficult for a single decision maker to consider aspects of complex problems, and by many people collaborating and sharing knowledge, group decision uses "group wisdom" to deal with increasingly complex real problems. Currently, population decision-making techniques are widely used. In order to obtain stable and reliable group decision results, a multi-round iterative feedback process is generally adopted to improve group consensus.
In group decisions, different experts involved in the decision are typically assigned weights of different sizes. The size of the expert weights is mainly determined by the quality of their decision information. In order to reasonably determine expert weights and facilitate group consensus achievement, the expert weights should be dynamically allocated while taking into account decision data quality and behavioral evolution characteristics of the expert. In view of the above, a method for dynamically distributing expert weights in multi-round group decision is provided, and a dynamic distribution algorithm of the expert weights is established by quantitatively calculating decision data quality and behavior evolution quality.
Disclosure of Invention
The purpose of the invention is that: in order to reasonably determine expert weights in multiple rounds of group decisions and promote group consensus, a dynamic expert weight allocation method is provided.
In order to achieve the technical purpose, the invention adopts the following technical scheme:
the method for dynamically distributing the special weights in the multi-round group decision comprises five steps of collecting expert decision data, calculating decision data quality, calculating behavior evolution quality, calculating expert weights and calculating group decision results, wherein the specific implementation modes of the steps are as follows:
step 1, collecting expert decision data:
at the t-th round, collecting decision data represented by expert i by cloud model
Without loss of generality, if the universe is 0-10, then the decision data satisfiesAnd->
Step 2, calculating decision data quality:
calculating decision data quality, including uncertainty, of expert i at round tAnd inconsistency +.>
Step 3, calculating behavior evolution quality:
calculating behavior evolution quality of expert i in t-th roundEta is a weight factor and 0<η<1；
wherein ,
group decision result calculated for round t-1 +.>Is a desired value of (2);
step 4, calculating expert weights:
the weight of the computing expert i at the t-th round is
Wherein alpha, beta and gamma are uncertaintyInconsistent degree->Behavioral evolution quality->Weight factor of 0<α<1、0<β<1、0<γ<1 and α+β+γ=1;
step 5, calculating a group decision result:
calculating group decision result of the t-th round by adopting weighted average algorithm of cloud model
Wherein the weighted average algorithm of the cloud model is as follows
By adopting the technical scheme, the invention can obtain the following beneficial effects:
1. according to the method for dynamically distributing the expert weights in the multi-round group decision, the expert weights are dynamically distributed by considering the decision data quality and the behavior evolution characteristics of the expert, so that the rationality of expert weight distribution is improved, and the group consensus is promoted;
2. according to the method for dynamically distributing the special weights in the multi-round group decision, the cloud model is used for representing the decision data of the special, so that the simplicity of quantitatively calculating the quality of the decision data and the quality of behavior evolution is enhanced.
The foregoing description is only an overview of the present invention, and is intended to be implemented in accordance with the teachings of the present invention, as well as the preferred embodiments thereof, together with the following detailed description of the invention, given by way of illustration only, together with the accompanying drawings.
Drawings
FIG. 1 is a flow chart of a method for dynamically assigning weights for a specificity in multiple rounds of group decisions according to the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, the following technical scheme of the present invention will be further described with reference to the accompanying drawings and examples.
The embodiment applies the method for dynamically distributing the special weights in the multi-round group decision to a certain evaluation problem, and comprises the following steps:
step 1, collecting expert decision data: the decision data expressed by the cloud model of 10 experts are collected in the 1 st round and the 2 nd round, and are shown in the 2 nd columns of the table 1 and the table 2 respectively;
table 1 round 1 decision data and calculation results
Table 2 round 2 decision data and calculation results
Step 2, calculating decision data quality: calculating decision data quality, including uncertainty, of each expert at round 1 and round 2And inconsistency +.>Wherein t=2, p=10;
the calculation results of the 1 st round are shown in columns 3 and 4 of table 1, and the calculation results of the 2 nd round are shown in columns 3 and 4 of table 2;
step 3, calculating behavior evolution quality: calculating the behavior evolution quality of each expert in the 1 st round and the 2 nd roundIn this example, η=0.5;
wherein ,
the calculation results of round 1 are shown in column 5 of table 1, and the calculation results of round 2 are shown in column 5 of table 2;
step 4, calculating expert weights: calculating the weight of each expert in round 1 and round 2
In this embodiment, t=2, p=10, and α=0.2, β=0.4, γ=0.4;
the calculation results of round 1 are shown in column 6 of table 1, and the calculation results of round 2 are shown in column 6 of table 2;
step 5, calculating a group decision result: the group decision results of the 1 st round and the 2 nd round are calculated by adopting a weighted average algorithm of a cloud model and are respectively
So far, expert weight dynamic allocation in multiple rounds of group decision is completed through the 5 steps, and group decision results of each round are obtained through calculation.
In conclusion, the dynamic distribution of expert weights in multi-round group decisions is realized by quantitatively calculating the decision data quality and the behavior evolution quality. The method can be applied to expert weight distribution based on multi-round group decision in different fields, such as complex system evaluation based on expert group, talent evaluation, project review and the like.
The above embodiments are only illustrative of the method steps of the present invention and their core ideas, and are not intended to limit the present invention. Modifications and variations may be made to the above-described embodiments by those skilled in the art without departing from the spirit and scope of the invention. Accordingly, it is intended that all equivalent modifications and variations of the invention be covered by the claims of this invention, which are within the skill of those skilled in the art, can be made without departing from the spirit and scope of the invention disclosed herein.
Claims (1)
1. The method for dynamically distributing the weights of the experts in the multi-round group decision is applied to complex system evaluation based on the experts group and is characterized by comprising the following steps:
step 1, collecting expert decision data: collecting decision data represented by each expert by adopting a cloud model (Ex, en, he), wherein the decision data satisfies that Ex is more than or equal to 0 and less than or equal to 10 and 3 (En+3He) is more than or equal to 10 without losing generality and assuming that the universe is 0-10;
step 2, calculating decision data quality: quantitatively calculating uncertainty and inconsistency of decision data;
expert i decision data at round tUncertainty of->And inconsistency +.>The calculation method of (1) is as follows:
step 3, calculating behavior evolution quality: quantitatively calculating behavior evolution quality according to uncertainty of decision data and expected evolution characteristics;
the calculation method of the behavior evolution quality of the expert i in the t-th round is as followsEta is a weight factor and 0<η<1；
wherein ,
group decision result calculated for round t-1 +.>Is a desired value of (2);
step 4, calculating expert weights: calculating expert weights according to the decision data quality and the behavior evolution quality;
expert i weights at round t as
Wherein alpha, beta and gamma are uncertaintyInconsistent degree->Behavioral evolution quality->Weight factor of 0<α<1、0<β<1、0<γ<1 and α+β+γ=1;
step 5, calculating a group decision result: and calculating a group decision result by adopting a weighted average algorithm of the cloud model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011562835.8A CN112668871B (en) | 2020-12-25 | 2020-12-25 | Method for dynamically distributing special weights in multi-round group decision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011562835.8A CN112668871B (en) | 2020-12-25 | 2020-12-25 | Method for dynamically distributing special weights in multi-round group decision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112668871A CN112668871A (en) | 2021-04-16 |
| CN112668871B true CN112668871B (en) | 2023-10-13 |
Family
ID=75409108
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011562835.8A Active CN112668871B (en) | 2020-12-25 | 2020-12-25 | Method for dynamically distributing special weights in multi-round group decision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112668871B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113316177B (en) * | 2021-06-01 | 2022-03-25 | 山东大学 | An intelligent group decision-making communication system and decision-making communication method |
| CN113361200A (en) * | 2021-06-09 | 2021-09-07 | 河南农业大学 | Information uncertainty grey group decision method based on group consensus |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105138838A (en) * | 2015-08-21 | 2015-12-09 | 浙江工业大学 | Index weight distribution method based on AHP and expert sorting empowerment |
| WO2017046530A1 (en) * | 2015-09-18 | 2017-03-23 | Safran Aircraft Engines | Decision aid system and method for the maintenance of a machine with learning of a decision model supervised by expert opinion |
| CN109670202A (en) * | 2018-11-15 | 2019-04-23 | 中国人民解放军空军工程大学 | A kind of Simulation Credibility Evaluation method based on cloud model |
| CN111046926A (en) * | 2019-11-26 | 2020-04-21 | 山东浪潮人工智能研究院有限公司 | An ensemble learning method for computer vision image classification |
-
2020
- 2020-12-25 CN CN202011562835.8A patent/CN112668871B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105138838A (en) * | 2015-08-21 | 2015-12-09 | 浙江工业大学 | Index weight distribution method based on AHP and expert sorting empowerment |
| WO2017046530A1 (en) * | 2015-09-18 | 2017-03-23 | Safran Aircraft Engines | Decision aid system and method for the maintenance of a machine with learning of a decision model supervised by expert opinion |
| CN109670202A (en) * | 2018-11-15 | 2019-04-23 | 中国人民解放军空军工程大学 | A kind of Simulation Credibility Evaluation method based on cloud model |
| CN111046926A (en) * | 2019-11-26 | 2020-04-21 | 山东浪潮人工智能研究院有限公司 | An ensemble learning method for computer vision image classification |
Non-Patent Citations (2)
| Title |
|---|
| 基于双层专家权重确定的风险型大群体决策;耿秀丽;肖子涵;孙绍荣;;控制与决策(05);全文 * |
| 群决策专家权重自适应算法研究;王俊英;李德华;;计算机应用研究(02);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112668871A (en) | 2021-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Pousinho et al. | Short-term electricity prices forecasting in a competitive market by a hybrid PSO–ANFIS approach | |
| Sun et al. | A hybrid co-evolutionary cultural algorithm based on particle swarm optimization for solving global optimization problems | |
| CN112668871B (en) | Method for dynamically distributing special weights in multi-round group decision | |
| CN104516785B (en) | A kind of cloud computing resources dispatch system and method | |
| CN114385376B (en) | Client selection method for federal learning of lower edge side of heterogeneous data | |
| CN107045785B (en) | A Method of Short-term Traffic Flow Prediction Based on Gray ELM Neural Network | |
| WO2024087512A1 (en) | Graph neural network compression method and apparatus, and electronic device and storage medium | |
| CN113657718B (en) | Multi-robot dynamic alliance task allocation method and related device | |
| Mashwani et al. | Ameliorated Ensemble Strategy-Based Evolutionary Algorithm with Dynamic Resources Allocations. | |
| CN107025228A (en) | A kind of method for recommending problem and equipment | |
| CN104467999A (en) | Spectrum sensing algorithm based on quantum leapfrog | |
| CN113886460A (en) | Low-bandwidth distributed deep learning methods | |
| Duarte et al. | A new strategy to evaluate the attractiveness in a dynamic island model | |
| Al-Zarrad et al. | A New Model to Improve Project Time-Cost Trade-Off | |
| CN118070926B (en) | Multi-task federation learning method based on client resource self-adaption | |
| CN108427773B (en) | A Distributed Knowledge Graph Embedding Method | |
| CN107357858A (en) | A kind of network reconstruction method based on geographical position | |
| Kustiyahningsih et al. | Integration interval type-2 FAHP-FTOPSIS group decision-making problems for salt farmer recommendation | |
| CN112514352A (en) | Method, device, system, storage medium and terminal for updating scheduling rule | |
| CN104700374A (en) | Scene Image Denoising Method Based on Type-2 Fuzzy Logic System | |
| CN107423811A (en) | The streamflow change attribution recognition methods combined based on BP artificial neural networks and Scene Simulation | |
| WO2021059527A1 (en) | Learning device, learning method, and recording medium | |
| CN116880540A (en) | Heterogeneous unmanned aerial vehicle group task allocation method based on alliance game formation | |
| CN111415265A (en) | Social relationship data generation method of generative confrontation network | |
| Tan et al. | A fast and stable forecasting model to forecast power load |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |