CN114219381A - Spatial decomposition enhancement-based multi-valence value chain collaborative evaluation system and method - Google Patents
Spatial decomposition enhancement-based multi-valence value chain collaborative evaluation system and method Download PDFInfo
- Publication number
- CN114219381A CN114219381A CN202210165301.4A CN202210165301A CN114219381A CN 114219381 A CN114219381 A CN 114219381A CN 202210165301 A CN202210165301 A CN 202210165301A CN 114219381 A CN114219381 A CN 114219381A
- Authority
- CN
- China
- Prior art keywords
- evaluation
- evaluator
- enhancement
- evaluated
- sub
- 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
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 188
- 238000000354 decomposition reaction Methods 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims abstract description 29
- 239000013598 vector Substances 0.000 claims abstract description 103
- 230000000295 complement effect Effects 0.000 claims abstract description 18
- 238000013077 scoring method Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 7
- 229920001577 copolymer Polymers 0.000 claims description 3
- 239000006185 dispersion Substances 0.000 claims description 2
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000011158 quantitative evaluation Methods 0.000 description 3
- 101100379081 Emericella variicolor andC gene Proteins 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012946 outsourcing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
- G06F17/12—Simultaneous equations, e.g. systems of linear equations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/17—Function evaluation by approximation methods, e.g. inter- or extrapolation, smoothing, least mean square method
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Software Systems (AREA)
- Development Economics (AREA)
- Databases & Information Systems (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Algebra (AREA)
- Tourism & Hospitality (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Complex Calculations (AREA)
Abstract
The invention discloses a spatial decomposition enhancement-based multi-value chain collaborative evaluation system and method, which aim at scenes in which an evaluated person participates in evaluation of a plurality of evaluation systems in sequence and are in accordance with the situation of information asymmetryn‑The sub-linear space and its orthogonal complement space formed by the weight vectors in 1 evaluation systemnThe weight vector of each evaluation system is projected to a sub-linear space and an orthogonal complement space, the projection of the sub-linear space of a base pair formed by the maximum linear irrelevance group of the weight vector is utilized to carry out linear decomposition, the enhancement times are quantitatively calculated, and the enhancement times are compared beforen‑The winner in 1 evaluation is enhanced, so that the restoration of the hidden information is partially realized, and the first evaluation is improvednObjectivity of the sub-evaluation and overall level of the winner.
Description
Technical Field
The invention relates to the technical field of multi-target decision, in particular to a data intelligent method for optimizing another multi-index weighted evaluation based on spatial decomposition enhanced multivalence value chain collaborative evaluation by utilizing a plurality of existing multi-index weighted evaluation results.
Background
The application of multi-target decision and multi-index evaluation methods such as a comprehensive scoring method is very common; obviously, for the same type of object (evaluated object), different evaluators have similar but different evaluation systems due to different requirements, and the evaluation systems show the same evaluation index and different weights; for example: a plurality of automobile assembly factories evaluate a plurality of indexes of cooperation experience, product birth, quality method, outsourcing, production and customer care of suppliers, but the evaluation weights are different;
although a plurality of evaluation systems are different, the same object is evaluated after all, so that the evaluation results have stronger positive correlation; after some evaluators make evaluations, subsequent evaluators can optimize their own evaluation work by means of the evaluation results, but the current literature lacks a quantitative method for the evaluation work;
in some special cases, such as the case of information asymmetry, the evaluation result of referring to others is particularly important; such as: when in useAQualified suppliers in the industry chain of branded automobilesE 1、BQualified suppliers in the industry chain of branded automobilesE 2Namely isABrand automobile is alsoBQualified suppliers in the industry chain of branded automobilesE 3General suppliers ofE 4Participate inCFor protection when evaluating qualified suppliers of branded automobilesA、BThe purpose of industrial chain business confidentiality,E 1、E 2、E 3is not directed toCThe branded car provides comprehensive information, resulting inCTo pairE 1、E 2、E 3The evaluation of (a) was low; at this time, ifCThe evaluator takes into accountE 1、E 2、E 3Has been thatAOrBAnd some enhancement (multiplication by an enhancement factor greater than 1) is performed on the evaluation score of the qualified supplier to restore the true ability of the qualified supplierCPair ofE 1、E 2、E 3Objective evaluation of (2);
however, to achieve such enhancement of evaluation, the following problems are encountered: firstlyCIs not aware ofE 1、E 2、E 3In thatA、BScoring specific indexes in the evaluation process; ②A、BThere is a difference in the evaluation system of (1), for exampleE 1、E 2The ordering differs between the two evaluations and it is therefore difficult to determine for these evaluations that the results should beHow to comprehensively consider; ③ ofE 4Although notA、BBut may not participate at allA、BIs simply evaluated for a qualified supplier whose ability is not necessarily poorE 1、E 2、E 3Enhancement is not scientific; and fourthly, the enhancement coefficient lacks of a scientific calculation method.
Disclosure of Invention
The invention provides a spatial decomposition enhancement-based system and a spatial decomposition enhancement-based method for collaborative evaluation of a multivalence value chain, which aim to solve the technical problems that: the technical problem that the evaluation of an evaluator is not objective in the prior art is solved.
In view of the above problems of the prior art, according to one aspect of the present disclosure, the following technical solutions are adopted in the present invention:
a spatial decomposition enhancement-based collaborative evaluation method for a multivalent value chain comprises the following steps:
s1, successively participating the evaluated person from 0 to 0n-1 scenario of evaluation by evaluation system, the firstnEvaluators of sub-evaluationK n Before acquisitionnAll evaluators in 1 evaluationK i Set evaluation weight vectorw i =(w i1,w i2,…,w im )（i=1,2,…,n-1) and obtaining a set of evaluated winner of the evaluated personE i （i=1,2,…,n-1）；
S2. evaluatorK n Setting evaluation weight, collecting participationnEvaluators of sub-evaluationK n Selected set of evaluatorsE n To the evaluatorK n The provided information is scored by the evaluation to obtain a plurality of information about each evaluated objectE nk （kScore vector of =1,2, …);
s3. evaluatorK n By usingn1 evaluation of the sub-linear space and its orthogonal complement space formed by the weight vectors in the systemnWeight vector linear null of secondary evaluation systemProjecting the inter-and orthogonal complementary spaces, and performing linear decomposition on the projection of the sub-linear space by using a basis consisting of the maximum linear irrelevance groups of the weight vectors to separate the similar part and the difference part of each evaluation system;
s4. evaluatorK n Before passingnSet of winners in 1 evaluation and topn-evaluation system weight vector in 1 evaluation, quantitative calculation of enhancement factor, beforen-enhancing the component of the score vector of the winner in 1 evaluation to realize the restoration of the hidden information and improve the first evaluationnObjectivity of the secondary evaluation and overall level of the winner;
s5, according to the evaluation weight, calculating the total score of each evaluated person according to the weighting of the score vector, and selecting the secondnWinner of secondary evaluation.
In order to better realize the invention, the further technical scheme is as follows:
further, the step S2 includes:
s21, the firstnAn evaluatorK n Setting an evaluation weight vector for the evaluation systemw n =(w n1,w n2,…,w nm )；
S22. the firstnAn evaluatorK n According to collectionsE n The person to be evaluated in (1)E nk To the evaluatorK n The provided information, for each indexq j Is scored for performance ofv kj （k=1,2,…,s；j=1,2,…,m) To obtainsAn individual vectorv k =(v k1, v k2,…, v km )（k=1,2,…,s）。
Further, the step S3 includes:
s31. evaluatorK n At vector setw 1,w 2,…,w n-1Any one of a large, linearly independent set of great facesz 1,z 2,…,z t }（tIs a copolymer of (1),n-1]integer over interval), calculate a weight vectorw n At vector setz 1,z 2,…,z t Stretched sub-linear spaceL 1Projection ontow (1)；
S32. evaluatorK n Calculating a weight vectorw n In linear space of sub-lineL 1Of orthogonal complementL 2Projection ontow (2)=w n -w (1)；
S33. evaluatorK n Computingw (1)At vector setz 1,z 2,…,z t The linearity of the symbol indicatesw (1)=
；
S34. evaluatorK n Computing collectionsE n Each of the evaluated persons in theE nk Vertical score ofV k (2)=w (2)·v k （k=1,2,…,s）。
Further, the step S4 includes:
s41. evaluatorK n Paired vector groupz 1,z 2,…,z t All vectors of } arez i The enhancement factor is calculated as followsλ i （i=1,2,…,t）：
If it isE=E n ∩E i Is an empty collection, orE n =EThen, thenλ i = 1; otherwise:
（1）K n calculating the winning numberC i =C i = 
Wherein a functionδ(x) Representing a Boolean variablexAn indicative function of, i.e.δ(x)= 
The same below)；
（2）K n Computing collectionsE n Each of the evaluated persons in theE nk Parallel score ofV k (1)=(α i z i )·v k (k=1,2,…,s)；
(3) EvaluatorsK n Calculating real variablesλEquation (2)C(λ)-C i Numerical solution of =0λ i Wherein a functionC(λ)= 
S42. evaluatorK n Computing collectionsE n Each of the evaluated persons in theE nk Enhanced score ofS k =
（k=1,2,…,s) And selecting several evaluated persons with highest enhancement score as the evaluatorsK n The winner of (1).
Further, in the step S41, the evaluatorK n Calculating real variablesλIn the equation solution of (1), a Bolzano-Cauchy first theorem and a binary search method are used for solving.
Further, in the step S41, the evaluatorK n In the equation solution for calculating the real variable λ, if a plurality of solutions are encountered, one of the solutions is arbitrarily selected.
Further, in the step S41, the evaluatorK n Equation for calculating real variable lambdaIn the solution method, ifC(λ)-C i （i=1,2,…,n-1) the dispersion of the value ranges results in no solution, and interpolation is used to approximate the solution.
Further, in the step S2, the score is given by an expert score method or an index score method.
Further, the evaluator is a buyer, and the evaluated person is a supplier;
or the evaluator is a contracting party and the evaluated person is a contractor;
or the evaluator is an integrator and the evaluated is a manufacturer.
The invention can also be:
a spatial decomposition enhancement based collaborative evaluation system for a chain of multivalent values, comprising:
the acquisition module is used for acquiring the successive participation of the evaluated person from 0 to 0n-Weight vector in 1 evaluation systemw i =(w i1,w i2,…,w im ) And according to said weight vectorw i =(w i1,w i2,…,w im ) Constructed winner set E i （i=1,2,…,n-1）；
A data receiving module for receiving the evaluated objectE nk To the evaluatorK n The information provided;
a scoring module for scoring according to the evaluated personE nk To the evaluatorK n The provided information and the set evaluation weight are evaluated for each evaluated objectE nk The index performance of (2) is scored, and a related score vector is obtained;
spatial decomposition module for evaluatorK n By usingn1 evaluation of the sub-linear space and its orthogonal complement space formed by the weight vectors in the systemnThe weight vector of the secondary evaluation system is projected to the sub-linear space and the orthogonal complement space, and the maximum linear independent texture of the weight vector is utilizedPerforming linear decomposition on the projection of the formed base pair linear space to separate the similar part and the different part of each evaluation system;
enhanced evaluation module fornEvaluators of sub-evaluationK n Before passingnWinner and before in-1 evaluationn-evaluation system weight vector in 1 evaluation, quantitative calculation of enhancement factor, beforenEnhancing the winner in the 1 evaluation to realize the restoration of the hidden information, and improving the first evaluation by using the computed enhanced score as the final evaluation basisnObjectivity of the sub-evaluation and overall level of the winner.
Compared with the prior art, the invention has the following beneficial effects:
the invention relates to a spatial decomposition enhancement-based polyvalent value chain collaborative evaluation system and method, wherein an evaluation system containing multiple sets of differentiation indexes is skillfully established, and the evaluation system is based on the previous evaluation systemn1 evaluation of the sub-linear space and its orthogonal complement space formed by the weight vectors in the systemnThe weight vector of the secondary evaluation system is projected to the sub-linear space and the orthogonal complement space, and the projection of the sub-linear space is linearly decomposed by utilizing the projection of the basic pair formed by the maximum linear irrelevant group of the weight vector, so that not only are the similar part and the difference part of each evaluation system separated, but also conditions are created for the restoration of the evaluation system under the condition of information asymmetry; at this time, thenThe evaluator of the secondary evaluation only needs to know whether the evaluated person is in the pastnWin (pass) in 1 evaluation, and beforenThe enhancement factor can be quantitatively calculated by the evaluation system weight vector in 1 evaluationλ i （i=1,2,…,n-1), in front ofn-1 winner in evaluation is enhanced, so that the restoration of the hidden information is partially realized, and the first time is improvednObjectivity of the sub-evaluation and overall level of the winner.
Drawings
For a clearer explanation of the embodiments or technical solutions in the prior art of the present application, the drawings used in the description of the embodiments or prior art will be briefly described below, it is obvious that the drawings in the following description are only references to some embodiments in the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a diagram illustrating a spatial decomposition of weight vectors according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a spatial decomposition enhancement-based collaborative evaluation system for a polyvalent value chain according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to examples, but the embodiments of the present invention are not limited thereto.
Referring to fig. 1, a spatial decomposition enhancement-based collaborative evaluation method for a polyvalent value chain includes:
s1, successively participating the evaluated person from 0 to 0n-1 scenario of evaluation by evaluation system, the firstnEvaluators of sub-evaluationK n Before acquisitionnAll evaluators in 1 evaluationK i Set evaluation weight vectorw i =(w i1,w i2,…,w im )（i=1,2,…,n-1) and obtaining a set of evaluated winner of the evaluated personE i （i=1,2,…,n-1）；
Wherein the weight vector is evaluatedw i =(w i1,w i2,…,w im ) （i=1,2,…,n-1) can be evaluated by an evaluatorK i According to the preference degree of the user to different indexes.
And the evaluatorK i Can be set as required according to the requirementsK i Number of winners: (i=1,2,…,n-1）。
The above index scoring method may be an expert scoring method or other quantitative evaluation method.
S2. evaluatorK n Setting evaluation weight, collecting participationnSet of evaluated subjects of sub-evaluationE n To the evaluatorK n The provided information is scored by the evaluation to obtain a plurality of information about each evaluated objectE nk （kScore vector of =1,2, …);
the specific operation process can comprise the following preferable scheme:
s21, the firstnAn evaluatorK n Setting an evaluation weight vector for the evaluation systemw n =(w n1,w n2,…,w nm )；
S22. the firstnAn evaluatorK n According to collectionsE n The person to be evaluated in (1)E nk To the evaluatorK n The provided information, for each indexq j Is scored for performance ofv kj （k=1,2,…,s；j=1,2,…,m) To obtainsAn individual vectorv k =(v k1, v k2,…, v km )（k=1,2,…,s）。
The scoring method may be performed by an expert scoring method or an index scoring method, but the present invention is not limited thereto.
S3. evaluatorK n By usingn1 evaluation of the sub-linear space and its orthogonal complement space formed by the weight vectors in the systemnThe weight vectors of the secondary evaluation system are projected to a sub-linear space and an orthogonal complement space, and the projection of the sub-linear space is linearly decomposed by using a basis pair composed of the maximum linear irrelevance groups of the weight vectors, so that similar parts and different parts of each evaluation system are separated.
Among them, in the step S3, the following scheme may be particularly preferable:
s31. evaluatorK n At vector setw 1,w 2,…,w n-1Any one of a large, linearly independent set of great facesz 1,z 2,…,z t }（tIs a copolymer of (1),n-1]integer over interval), calculate a weight vectorw n At vector setz 1,z 2,…,z t Stretched sub-linear spaceL 1Projection ontow (1)；
S32. evaluatorK n Calculating a weight vectorw n In linear space of sub-lineL 1Of orthogonal complementL 2Projection ontow (2)=w n -w (1)；
S33. evaluatorK n Computingw (1)At vector setz 1,z 2,…,z t The linearity of the symbol indicatesw (1)=
；
S34. evaluatorK n Computing collectionsE n Each of the evaluated persons in theE nk Vertical score ofV k (2)=w (2)·v k （k=1,2,…,s）（x·yEach representing two vectorsx、yThe inner product of (1) is the same as below).
S4. evaluatorK n Before passingnSet of winners in 1 evaluation and topn-evaluation system weight vector in 1 evaluation, quantitative calculation of enhancement factor, beforen-enhancing the component of the score vector of the winner in 1 evaluation to realize the restoration of the hidden information and improve the first evaluationnObjectivity of the secondary evaluation and overall level of the winner;
in the step S4, the following preferred schemes may be adopted:
s41. evaluatorK n Paired vector groupz 1,z 2,…,z t All vectors of } arez i The enhancement is calculated as followsFactor(s)λ i （i=1,2,…,t）：
If it isE=E n ∩E i Is an empty collection, orE n =EThen, thenλ i = 1; otherwise:
（1）K n calculating the winning numberC i = 
；(function ofδ(x) All represent Boolean variablesxAn indicative function of, i.e.δ(x)=
The same applies below).
（2）K n Computing collectionsE n Each of the evaluated persons in theE nk Parallel score ofV k (1)=(α i z i )·v k (k=1,2,…,s)；
(3) EvaluatorsK n Calculating real variablesλEquation (2)C(λ)-C i Numerical solution of =0λ i Wherein a functionC(λ)=
Due to the fact thatλWhen it is large enoughC(λ)-C i Is not less than 0 andC(-λ)-C i less than or equal to 0, so that the equation must have a solution according to the first theorem (theorem of zero existence) of Bolzano-Cauchy, and the solution can be carried out by adopting algorithms such as a binary search method and the like; search interval of the bisection methodλ (1),λ (2)]When the length is reduced to 0.01, ifP(λ (1))=P(λ (2)) Then getλ i =λ (1)(ii) a Otherwise, obtaining by interpolationλ i =
Obtaining an approximate solution by adopting an interpolation method; if multiple solutions are encountered, one is arbitrarily selected.
S42. evaluatorK n Computing collectionsE n Each of the evaluated persons in theE nk Enhanced score ofS k =
（k=1,2,…,s) And selecting several evaluated persons with highest enhancement score as the evaluatorsK n The winner of (1). Here, the number of the first and second electrodes,K n according to the requirements, set as requiredK n The number of winners; if there is a case where a plurality of evaluators have the same enhancement score,K n the evaluators having the same enhancement score may be ranked according to preference or other criteria.
As shown in fig. 2, a spatial decomposition-based enhanced collaborative evaluation system for a polyvalent value chain includes:
the acquisition module is used for acquiring the successive participation of the evaluated person from 0 to 0n-Weight vector in 1 evaluation systemw i =(w i1,w i2,…,w im ) And a winner set constructed according to the weight vector E i （i=1,2,…,n-1）；
A data receiving module for receiving the evaluated objectE nk To the evaluatorK n The information provided;
a scoring module for scoring according to the evaluated personE nk To the evaluatorK n The provided information and the set evaluation weight are evaluated for each evaluated objectE nk The index performance of (2) is scored, and a related score vector is obtained;
spatial decomposition module for evaluatingAK n By usingn1 evaluation of the sub-linear space and its orthogonal complement space formed by the weight vectors in the systemnThe weight vectors of the secondary evaluation system are projected to a sub-linear space and an orthogonal complement space, and the projection of the sub-linear space is linearly decomposed by using a basis pair formed by the maximum linear irrelevance groups of the weight vectors, so that the similar part and the difference part of each evaluation system are separated;
enhanced evaluation module fornEvaluators of sub-evaluationK n Before passingnWinner and before in-1 evaluationn-evaluation system weight vector in 1 evaluation, quantitative calculation of enhancement factor, beforenEnhancing the winner in the 1 evaluation to realize the restoration of the hidden information, and improving the first evaluation by using the computed enhanced score as the final evaluation basisnObjectivity of the sub-evaluation and overall level of the winner.
The system and the method for the collaborative evaluation of the multivalent value chain based on the spatial decomposition enhancement can be applied to the enterprise supply link (qualified supplier evaluation), the manufacturing link (operation undertaking unit/team selection), the marketing link (propaganda channel, sales channel selection) and the management link (department/staff evaluation), and particularly the collaborative optimization among a plurality of value chains (industrial chains); meanwhile, the method can also be used in various application fields related to multi-target decision or multi-index evaluation, so that the existing multi-index weighted evaluation result is utilized to optimize the other multi-index weighted evaluation;
the following is an example of the automotive industry chain field to further illustrate the invention:
for a simulation scenario of a multi-industry chain comprising 5 automotive industry chains, in each case with an automobile factoryK 1、K 2、K 3、K 4Candidate skylight providers have been evaluated for 4 industry chains of core enterprises and a number of qualified providers have been selected; another in car factoryK 5Selecting 10 qualified suppliers from 30 candidate skylight suppliers for the industry chain of the core enterprise; the method of the invention is an automobile factoryK 5Providing selective qualifying offeringsThe quotient optimization method comprises the following steps:
(1) for the index containing 20 indexesq 1,q 2,…,q 20Evaluation System of (1), 4 evaluatorsK i （i=1,2,3, 4) setting evaluation weight vectorw i =(w i1,w i2,…,w i,20) To submitK i Multiple evaluated persons are subjected to index scoring and weighting, and several persons with highest score are selected according to weighted comprehensive scoreK i The winner, constituteK i Set of winnersE i （i=1,2,3, 4); here, the number of the first and second electrodes,K i setting evaluation weight vector according to preference and requirementw i =(w i1,w i2,…,w i,20) And as requiredK i The number of winners and the index scoring method can be an expert scoring method or other quantitative evaluation methods;
(2) for the participants evaluatingK 5Set of 30 evaluated subjectsE 5={E 5,1, E 5,2,…, E 5,30}，K 5Is selected according to the following stepsK 5The winner:
（2.1）K 5setting an evaluation weight vector for the same evaluation system in the step (1) according to own preferencew 5=(w 5,1,w 5,2,…,w 5,20)；
（2.2）K 5According toE 5Each of the evaluated persons in theE k5To the direction ofK 5The provided information, pairE k5Each indexq j Is scored for performance ofv kj （k=1,2,…,30；j=1,2, …, 20), resulting in 30 vectorsv k =（v k1, v k2,…, v k20）（k=1,2, …, 30); here, the index scoring method may be an expert scoring method or other quantitative evaluation method;
（2.3）K 5obtain all evaluatorsK i Evaluating weight vectorsw i （i=1,2,3,4）；
（2.4）K 5At vector setw 1,w 2, w 3,w 4Any one of a large, linearly independent set of great facesz 1, …,z t }（t4) or less), calculatingw 5At vector setz 1,…,z t Stretched sub-linear spaceL 1Projection ontow (1)(ii) a Here, the maximum linearity independent group can be calculated by the following method: arranging the column vectors into a matrix, carrying out elementary transformation to form a step shape, and forming a maximum linear independent group by the column vectors before transformation corresponding to the column where the first non-zero element of all non-zero rows is located; the projection of the vector on a sub-linear space formed by the linearly independent vectors can be calculated by a least square method;
（2.5）K 5computingw 5In thatL 1Of orthogonal complementL 2Projection ontow (2)=w 5-w (1)；
（2.6）K 5Computingw (1)At vector setz 1,z 2,…,z t The linearity of the symbol indicatesw (1)=
(ii) a Here, the linear expression can be obtained by solving the system of linear equations. Due to the fact thatL 1Being a set of linearly independent vectorsz 1,z 2,…,z t A sub-linear space formed byz 1,z 2,…,z t Is composed ofL 1A group of radicals ofw (1)∈L 1Therefore, the linear equation system has a unique solution and can be solved by an elementary variation method.
（2.7）K 5Calculating a set of evaluated personsE 5Each element ofE k5Vertical score ofV k (2)=w (2)·v k （k=1,2,…,30）；
（2.8）K 5Paired vector groupz 1,…,z t All vectors of } arez i The enhancement factor is calculated as followsλ i （i=1,…,t）：
(2.8.1) ifE=E 5∩E i Is an empty collection, orE 5=EThen, thenλ i =1；
(2.8.2) otherwise:
（2.8.2.1）K 5calculating the winning numberC i =
Function ofδ(x) All represent Boolean variablesxAn indicative function of, i.e.δ(x)=
）；
（2.8.2.2）K 5Calculating a set of evaluated personsE 5Each element ofE k5Parallel score ofV k (1)=(α i z i )·v k (k=1,2,…,30)；
（2.8.2.3）K 5Calculating real variablesλEquation (2)C(λ)-C i Numerical solution of =0λ i Wherein a functionC(λ)=
；
Specifically, the following description is provided: due to the fact thatλWhen it is large enoughC(λ)-C i Is not less than 0 andC(-λ)-C i the value is less than or equal to 0, so that the algorithm such as Bolzano-Cauchy first theorem (theorem exists at zero point) and a binary search method is utilized to solve; search interval of the bisection methodλ (1),λ (2)]When the length is reduced to 0.01, ifP(λ (1))=P(λ (2)) Then getλ i =λ (1)(ii) a Otherwise, obtaining by interpolationλ i = 
(ii) a If a plurality of solutions are encountered, one of the solutions is arbitrarily selected;
（2.9）K 5calculating a set of evaluated personsE 5Each element ofE k5Enhanced score ofS k = 
（k=1,2, …, 30), and several evaluated persons having the highest enhancement score among them are selected as the evaluated personsK 5The winner; here, the number of the first and second electrodes,K 5according to the requirements, set as requiredK 5The number of winners; if there is a case where a plurality of evaluators have the same enhancement score,K 5the evaluators having the same enhancement score may be ranked according to preference or other criteria.
In conclusion, under the condition that the information is asymmetric, the method of the invention is as beforen1 evaluation of the sub-linear space and its orthogonal complement space formed by the weight vectors in the systemnThe weight vector of the secondary evaluation system is projected to the sub-linear space and the orthogonal complement space, and the projection of the sub-linear space is linearly decomposed by utilizing the projection of the basic pair formed by the maximum linear irrelevant group of the weight vector, so that not only are the similar part and the difference part of each evaluation system separated, but also conditions are created for the restoration of the evaluation system under the condition of information asymmetry; at this time, thenThe evaluator of the secondary evaluation only needs to know whether the evaluated person is in the pastnWin (pass) in 1 evaluation, and beforenThe enhancement factor can be quantitatively calculated by the evaluation system weight vector in 1 evaluationλ i （i=1,2,…,n-1), in front ofn-1 winner in evaluation is enhanced, so that the restoration of the hidden information is partially realized, and the first time is improvednObjectivity of the sub-evaluation and overall level of the winner.
The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
Reference throughout this specification to "one embodiment," "another embodiment," "an embodiment," or the like, means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment described generally in this application. The appearances of the same phrase in various places in the specification are not necessarily all referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with any embodiment, it is submitted that it is within the scope of the invention to effect such feature, structure, or characteristic in connection with other embodiments.
Although the invention has been described herein with reference to a number of illustrative embodiments thereof, it should be understood that numerous other modifications and embodiments can be devised by those skilled in the art that will fall within the spirit and scope of the principles of this disclosure. More specifically, various variations and modifications are possible in the component parts and/or arrangements of the subject combination arrangement within the scope of the disclosure and claims of this application. In addition to variations and modifications in the component parts and/or arrangements, other uses will also be apparent to those skilled in the art.
Claims (10)
1. A spatial decomposition enhancement-based collaborative evaluation method for a multivalent value chain is characterized by comprising the following steps:
s1, evaluating the existence of a quiltThe participants successively participate in the period from 0 ton-1 scenario of evaluation by evaluation system, the firstnEvaluators of sub-evaluationK n Before acquisitionnAll evaluators in 1 evaluationK i Set evaluation weight vectorw i =(w i1,w i2,…,w im )（i=1,2,…,n-1) and obtaining a set of evaluated winner of the evaluated personE i （i=1,2,…,n-1）；
S2. evaluatorK n Setting evaluation weight, collecting participationnSet of evaluated subjects of sub-evaluationE n To the evaluatorK n The provided information is scored by the evaluation to obtain a plurality of information about each evaluated objectE nk （kScore vector of =1,2, …);
s3. evaluatorK n By usingn1 evaluation of the sub-linear space and its orthogonal complement space formed by the weight vectors in the systemnThe weight vectors of the secondary evaluation system are projected to a sub-linear space and an orthogonal complement space, and the projection of the sub-linear space is linearly decomposed by using a basis pair formed by the maximum linear irrelevance groups of the weight vectors, so that the similar part and the difference part of each evaluation system are separated;
s4. evaluatorK n Before passingnSet of winners in 1 evaluation and topn-evaluation system weight vector in 1 evaluation, quantitative calculation of enhancement factor, beforen-enhancing the component of the score vector of the winner in 1 evaluation to realize the restoration of the hidden information and improve the first evaluationnObjectivity of the secondary evaluation and overall level of the winner;
s5, according to the evaluation weight, calculating the total score of each evaluated person according to the weighting of the score vector, and selecting the secondnWinner of secondary evaluation.
2. The spatial decomposition enhancement-based collaborative evaluation method for a multivalent value chain according to claim 1, wherein the step S2 includes:
s21, the firstnAn evaluatorK n Setting an evaluation weight vector for the evaluation systemw n =(w n1,w n2,…,w nm )；
S22. the firstnAn evaluatorK n According to collectionsE n The person to be evaluated in (1)E nk To the evaluatorK n The provided information, for each indexq j Is scored for performance ofv kj （k=1,2,…,s；j=1,2,…,m) To obtainsAn individual vectorv k =(v k1, v k2,…, v km )（k=1,2,…,s）。
3. The spatial decomposition enhancement-based collaborative evaluation method for a multivalent value chain according to claim 2, wherein the step S3 includes:
s31. evaluatorK n At vector setw 1,w 2,…,w n-1Any one of a large, linearly independent set of great facesz 1,z 2,…,z t }（tIs a copolymer of (1),n-1]integer over interval), calculate a weight vectorw n At vector setz 1,z 2,…,z t Stretched sub-linear spaceL 1Projection ontow (1)Therein-w 1,w 2,…,w n-1The weight vector set of the previous n evaluations is obtained;
s32. evaluatorK n Calculating a weight vectorw n In linear space of sub-lineL 1Of orthogonal complementL 2Projection ontow (2)=w n -w (1)；
S33. evaluatorK n Computingw (1)At vector setz 1,z 2,…,z t The linearity of the symbol indicatesw (1)=
Wherein
Decomposition coefficients that are vectors;
s34. evaluatorK n Computing collectionsE n Each of the evaluated persons in theE nk Vertical score ofV k (2)=w (2)·v k （k=1,2,…,s）。
4. The spatial decomposition enhancement-based collaborative evaluation method for a multivalent value chain according to claim 3, wherein the step S4 includes:
s41. evaluatorK n Paired vector groupz 1,z 2,…,z t All vectors of } arez i The enhancement factor is calculated as followsλ i （i=1,2,…,t）：
If it isE=E n ∩E i Is an empty collection, orE n =EThen, thenλ i = 1; otherwise:
（1）K n calculating the winning numberC i =
Wherein a functionδ(x) Representing a Boolean variablexAn indicative function of, i.e.δ(x)=
The same applies below);
（2）K n computing collectionsE n Each of the evaluated persons in theE nk Parallel score ofV k (1)=(α i z i )·v k (k=1,2,…,s) Whereinα i Decomposition coefficients that are vectors;
(3) evaluatorsK n Calculating real variablesλEquation (2)C(λ)-C i Numerical solution of =0λ i Wherein a functionC(λ)=
；
S42. evaluatorK n Computing collectionsE n Each of the evaluated persons in theE nk Enhanced score ofS k =
（k=1,2,…,s) And selecting several evaluated persons with highest enhancement score as the evaluatorsK n The winner of (1).
5. The spatial decomposition enhancement-based collaborative evaluation method for multi-valent value chain according to claim 4, wherein in step S41, the evaluatorK n Calculating real variablesλIn the equation solution of (1), a Bolzano-Cauchy first theorem and a binary search method are used for solving.
6. The spatial decomposition enhancement-based collaborative evaluation method for multi-valent value chain according to claim 4, wherein in step S41, the evaluatorK n In the equation solution for calculating the real variable λ, if a plurality of solutions are encountered, one of the solutions is arbitrarily selected.
7. Root of herbaceous plantThe spatial decomposition enhancement-based collaborative evaluation method for multi-valent value chain according to claim 4, wherein in step S41, the evaluatorK n In the solution of the equation for calculating the real variable λ, ifC(λ)-C i （i=1,2,…,n-1) the dispersion of the value ranges results in no solution, and interpolation is used to approximate the solution.
8. The spatial decomposition enhancement-based collaborative evaluation method for the multivalent value chain according to claim 1, wherein in the step S2, the score is performed by an expert scoring method or an index scoring method.
9. The spatial decomposition enhancement-based collaborative evaluation method for the polyvalent value chain according to any one of claims 1 to 8, wherein the evaluator is a buyer and the evaluators are suppliers;
or the evaluator is a contracting party and the evaluated person is a contractor;
or the evaluator is an integrator and the evaluated is a manufacturer.
10. A spatial decomposition enhancement-based collaborative evaluation system for a polyvalent value chain is characterized by comprising the following steps:
a data acquisition module for acquiring the successive participation of the evaluated person from 0 to 0n-Weight vector in 1 evaluation systemw i =(w i1,w i2,…,w im ) And according to said weight vectorw i =(w i1,w i2,…,w im ) Constructed winner set E i （i=1,2,…,n-1）；
A data receiving module for receiving the evaluated objectE nk To the evaluatorK n The information provided;
a scoring module for scoring according to the evaluated personE nk To the evaluatorK n The provided information and the set evaluation weight are evaluated for each evaluated objectE nk The index performance of (2) is scored, and a related score vector is obtained;
spatial decomposition module for evaluatorK n By usingn1 evaluation of the sub-linear space and its orthogonal complement space formed by the weight vectors in the systemnThe weight vectors of the secondary evaluation system are projected to a sub-linear space and an orthogonal complement space, and the projection of the sub-linear space is linearly decomposed by using a basis pair formed by the maximum linear irrelevance groups of the weight vectors, so that the similar part and the difference part of each evaluation system are separated;
enhanced evaluation module fornEvaluators of sub-evaluationK n Before passingnWinner and before in-1 evaluationn-evaluation system weight vector in 1 evaluation, quantitative calculation of enhancement factor, beforenEnhancing the winner in the 1 evaluation to realize the restoration of the hidden information, and improving the first evaluation by using the computed enhanced score as the final evaluation basisnObjectivity of the sub-evaluation and overall level of the winner.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210165301.4A CN114219381A (en) | 2022-02-23 | 2022-02-23 | Spatial decomposition enhancement-based multi-valence value chain collaborative evaluation system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210165301.4A CN114219381A (en) | 2022-02-23 | 2022-02-23 | Spatial decomposition enhancement-based multi-valence value chain collaborative evaluation system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114219381A true CN114219381A (en) | 2022-03-22 |
Family
ID=80709329
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210165301.4A Pending CN114219381A (en) | 2022-02-23 | 2022-02-23 | Spatial decomposition enhancement-based multi-valence value chain collaborative evaluation system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114219381A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115242250A (en) * | 2022-09-21 | 2022-10-25 | 成都工业学院 | Encoding and decoding method for single-full mapping of multi-value chain data element allocation |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107610061A (en) * | 2017-08-30 | 2018-01-19 | 西安理工大学 | A kind of guarantor's edge point cloud hole repair method based on two-dimensional projection |
| US20190138597A1 (en) * | 2017-07-28 | 2019-05-09 | Nia Marcia Maria Dowell | Computational linguistic analysis of learners' discourse in computer-mediated group learning environments |
-
2022
- 2022-02-23 CN CN202210165301.4A patent/CN114219381A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190138597A1 (en) * | 2017-07-28 | 2019-05-09 | Nia Marcia Maria Dowell | Computational linguistic analysis of learners' discourse in computer-mediated group learning environments |
| CN107610061A (en) * | 2017-08-30 | 2018-01-19 | 西安理工大学 | A kind of guarantor's edge point cloud hole repair method based on two-dimensional projection |
Non-Patent Citations (2)
| Title |
|---|
| 李乐等: "基于线性投影结构的非负矩阵分解", 《自动化学报》 * |
| 金菊良等: "基于投影寻踪权重优化的水资源承载力评价模型", 《水资源保护》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115242250A (en) * | 2022-09-21 | 2022-10-25 | 成都工业学院 | Encoding and decoding method for single-full mapping of multi-value chain data element allocation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Romney et al. | Predicting clustering from semantic structure | |
| Foxman et al. | Adolescents' influence in family purchase decisions: A socialization perspective | |
| Trost et al. | Technical training and earnings: a polychotomous choice model with selectivity | |
| CN108960304B (en) | Deep learning detection method for network transaction fraud behaviors | |
| Zahrotun | Implementation of data mining technique for customer relationship management (CRM) on online shop tokodiapers. com with fuzzy c-means clustering | |
| CN112381179A (en) | Heterogeneous graph classification method based on double-layer attention mechanism | |
| CN114219381A (en) | Spatial decomposition enhancement-based multi-valence value chain collaborative evaluation system and method | |
| Makhijani et al. | Parametric models for intransitivity in pairwise rankings | |
| CN114580525A (en) | Gesture action classification method for data containing missing | |
| CN112529415A (en) | Article scoring method based on combined multi-receptive-field-map neural network | |
| Asgarnezhad et al. | An Effective Algorithm to Improve Recommender Systems using Evolutionary Computation Algorithms and Neural Network | |
| CN114187261A (en) | Non-reference stereo image quality evaluation method based on multi-dimensional attention mechanism | |
| Kung et al. | A fuzzy MCDM method to select the best company based on financial report analysis | |
| CN111931023B (en) | Community structure identification method and device based on network embedding | |
| Zahavl et al. | Issues and problems in applying neural computing to target marketing | |
| Mojaddady et al. | Stock market prediction using twin Gaussian process regression | |
| CN110264364B (en) | Recommendation method for investor | |
| CN117094859A (en) | Learning path recommendation method and system combining graph neural network and multi-layer perceptron | |
| KR102183083B1 (en) | Method and apparatus for calculating two-way recommended scores based on data of purchase | |
| Kang et al. | RETRACTED: A hybrid model to develop aesthetic product design of customer satisfaction | |
| CN114912774A (en) | Multi-value chain cooperative orthogonal decomposition and parallel data enhancement intelligent method | |
| Bhargav et al. | Market basket analysis using artificial neural network | |
| CN107449964A (en) | A kind of Generalized Multivariate singular spectrum analysis method for being used for mode reconstruction and prediction | |
| Kim et al. | A New Perspective for Neural Networks: Application to a Marketing Management Problem. | |
| WO1992017853A2 (en) | Direct data base analysis, forecasting and diagnosis 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 |