CN118172113A - Vendor classification rating method, device, equipment and medium - Google Patents
Vendor classification rating method, device, equipment and medium Download PDFInfo
- Publication number
- CN118172113A CN118172113A CN202410344771.6A CN202410344771A CN118172113A CN 118172113 A CN118172113 A CN 118172113A CN 202410344771 A CN202410344771 A CN 202410344771A CN 118172113 A CN118172113 A CN 118172113A
- Authority
- CN
- China
- Prior art keywords
- weight
- link
- suppliers
- calculating
- supplier
- 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
- 238000000034 method Methods 0.000 title claims abstract description 80
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 40
- 238000005457 optimization Methods 0.000 claims abstract description 16
- 238000013077 scoring method Methods 0.000 claims abstract description 14
- 238000004590 computer program Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 11
- 238000009826 distribution Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 5
- 238000007619 statistical method Methods 0.000 claims description 2
- 238000011156 evaluation Methods 0.000 abstract description 5
- 238000010801 machine learning Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 4
- 241000272168 Laridae Species 0.000 description 2
- 238000011869 Shapiro-Wilk test Methods 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 101100029838 Mus musculus Pinx1 gene Proteins 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013278 delphi method Methods 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012856 packing Methods 0.000 description 1
- 230000002028 premature Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000013107 unsupervised machine learning method Methods 0.000 description 1
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention belongs to the technical field of classification evaluation of suppliers, and particularly discloses a classification rating method, a classification rating device, classification rating equipment and classification rating media of suppliers; the method comprises the steps of respectively calculating provider data by using an entropy weight method and an expert scoring method to obtain a first weight and a second weight and calculating a comprehensive weight; calculating link scores and provider scores of the providers based on the first weights; clustering suppliers by a DBSCAN clustering algorithm improved based on a seagull optimization algorithm, and each link score and the supplier score of the suppliers, and classifying and grading the suppliers based on the clustering result and the comprehensive weight to obtain a classification and grading result; the objective method and the subjective method are combined to determine the weight of each flow link so as to avoid the limitation of subjective judgment; the suppliers are rated by adopting a clustering machine learning method, and the suppliers are objectively rated and classified.
Description
Technical Field
The invention belongs to the technical field of classification evaluation of suppliers, and particularly relates to a classification rating method, device, equipment and medium for suppliers.
Background
With the increasing complexity of the global supply chain and the close partnership between businesses, vendor ratings become a critical regulatory issue. Traditional vendor rating methods often rely on subjective judgment and limited metrics, and cannot comprehensively and objectively evaluate the comprehensive capacity and risk level of the vendor.
The conventional vendor rating method has the following problems: first, relying entirely on subjective judgment is susceptible to subjective bias and experience limitations of the evaluator, and the rating result may lack objectivity and consistency. Second, conventional methods typically consider only a few metrics, such as financial status and delivery accuracy, and cannot fully reflect the comprehensive capacity and risk level of the provider. In addition, the rating results of conventional methods are often discrete and difficult to effectively categorize and compare to suppliers.
Disclosure of Invention
The invention aims to provide a vendor classification rating method, device, equipment and medium, which are used for solving the problems that the traditional vendor classification rating method lacks objectivity and consistency, the rating result is discrete, and the vendors are difficult to effectively classify and compare.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
in a first aspect of the present invention, there is provided a vendor classification rating method, comprising:
Respectively calculating the provider data by using an entropy weight method and an expert scoring method to obtain a first weight and a second weight; calculating based on the first weight and the second weight to obtain comprehensive weight;
Calculating link scores and provider scores of the providers based on the first weights;
And clustering the suppliers by a DBSCAN clustering algorithm improved based on a seagull optimization algorithm, and each link score and the supplier score of the suppliers, and classifying and grading the suppliers based on the clustering result and the comprehensive weight to obtain a classification grading result.
Further, during the provider data acquisition, whether the provider is overdue or not is judged by carrying out reasonable interval estimation and reasonable interval of overall use on each flow link of the provider, and the method is specific:
Carrying out normal test by means of a Charpy-Weirk test, verifying whether the array of each link is subjected to normal distribution, and if the array of each link is reasonable data, obtaining reasonable time length of each link by means of data modeling; the specific calculation formula is as follows:
In the method, in the process of the invention, The mean value of the samples is sigma, the total standard deviation is sigma, Z α/2 is the quantile of a standard normal distribution random variable, and n is the sample capacity.
Further, the calculating of the first weight includes:
based on the obtained vendor data, a first weight W 1 is calculated by an entropy weight method:
n suppliers, m links, and given a feature matrix a of n×m:
Wherein A is a multi-link feature matrix corresponding to multiple suppliers; x nm is the data of the mth link of the nth supplier;
Data normalization:
Wherein x ij' is the normalized data of the j link of the i-th supplier; x ij is the data of the j link of the i-th supplier;
calculating the proportion of the ith supplier in the jth link:
Wherein P ij is the proportion of the ith supplier in the jth link;
Calculating the entropy value of the j link of the i provider:
wherein e ij is the entropy value of the j link of the i-th supplier; k is a first parameter, k >0; e j is more than or equal to 0;
calculating a difference coefficient of the jth link of the ith supplier:
gij＝1-eij(j＝1,2,…,m)
Wherein g ij is the difference coefficient of the j link of the i-th supplier;
Calculating the weight of the j link of the i provider:
Obtaining a first weight calculated by an entropy weight method
Wherein W 1 is a first weight calculated by an entropy weight method; w ij is the weight of the jth link of the ith vendor.
Further, the calculating of the second weight includes:
And selecting an expert in each aspect of the enterprise through an expert scoring method, adopting a form of independently filling a table to select weights, sorting and statistically analyzing the weights selected by the expert, determining each factor, checking and correcting the weights of each index by using a mathematical statistical method, and calculating to obtain a second weight W 2.
Further, the calculation of the comprehensive weight is as follows:
W＝W1+W2
wherein W is the comprehensive weight.
Further, the calculating the link scores and the provider scores of the providers based on the first weights specifically includes:
sij＝tijWij
Where S ij is the score of the jth link of the ith supplier, t ij is the period used by the jth link of the ith supplier, W ij is the weight of the jth link of the ith supplier, and S i is the total score of the ith supplier.
Further, the classifying and grading the suppliers based on the clustering result and the comprehensive weight, and the obtaining the classifying and grading result specifically includes:
After clustering, classifying the suppliers into a plurality of classes, calculating the scores of the suppliers in each class according to the comprehensive weight, and grading the suppliers according to the scores, wherein the grading method comprises the following steps: a layer difference method, a buckling method or an RFM model.
In a second aspect of the present invention, there is provided a vendor classification rating apparatus comprising:
The weight calculation module is used for respectively calculating the provider data by using an entropy weight method and an expert scoring method to obtain a first weight and a second weight; calculating based on the first weight and the second weight to obtain comprehensive weight;
a score calculating module for calculating each link score and the provider score of the provider based on the first weight;
And the classification rating result obtaining module is used for clustering the suppliers by a DBSCAN clustering algorithm improved based on a seagull optimization algorithm, each link score of the suppliers and the supplier score, and classifying and rating the suppliers based on the clustering result and the comprehensive weight to obtain a classification rating result.
In a third aspect of the invention, an electronic device is provided comprising a processor and a memory, the processor being adapted to execute a computer program stored in the memory to implement a vendor classification rating method as claimed in any one of the preceding claims.
In a fourth aspect of the present invention, there is provided a computer readable storage medium storing at least one instruction which when executed by a processor implements a vendor classification rating method as claimed in any one of the preceding claims.
The beneficial effects of the invention are as follows:
1. The method comprises the steps of respectively calculating provider data by using an entropy weight method and an expert scoring method to obtain a first weight and a second weight and calculating a comprehensive weight; calculating link scores and provider scores of the providers based on the first weights; clustering suppliers by a DBSCAN clustering algorithm improved based on a seagull optimization algorithm, and each link score and the supplier score of the suppliers, and classifying and grading the suppliers based on the clustering result and the comprehensive weight to obtain a classification and grading result; the objective method and the subjective method are combined to determine the weight of each flow link so as to avoid the limitation of subjective judgment; the suppliers are rated by adopting a clustering machine learning method, and the suppliers are objectively rated and classified.
2. The DBSCAN algorithm is less influenced by abnormal values, the clustering effect is better, and the robustness is stronger; the parameters of the DBSCAN algorithm are adjusted through a seagull optimization algorithm, the most suitable parameter value is automatically and rapidly found in the running process, and the intelligence and reliability of the algorithm and the accuracy of the result are improved; by adopting various provider order scoring and grading methods, the grading is more reasonable, and the selectivity to management staff is more.
3. The method adopts a subjective and objective combination mode to calculate the weight of each supplier performance link; after the weight of each supplier performance link is obtained, the suppliers are clustered by using a DBSCAN clustering algorithm, DBSCAN parameters are optimized by using a seagull optimization algorithm, the optimal parameters of the DBSCAN algorithm are rapidly obtained, and the clustering rationality and accuracy are improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:
FIG. 1 is a flow chart of a vendor classification rating method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a DBSCAN algorithm modified based on a seagull optimization algorithm according to the embodiment of the invention;
FIG. 3 is a block diagram illustrating a vendor classification rating apparatus according to an embodiment of the present invention;
Fig. 4 is a block diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The application will be described in detail below with reference to the drawings in connection with embodiments. It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other.
The following detailed description is exemplary and is intended to provide further details of the application. Unless defined otherwise, all technical terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments in accordance with the application.
Example 1
As shown in fig. 1, a vendor classification rating method includes:
S1: acquiring provider data;
judging whether the supplier is overdue or not by carrying out reasonable interval estimation and reasonable interval of overall time consumption on each flow link of the supplier, and specifically:
and (3) reasonably estimating the use time of the supplier performance links, carrying out a normalization test through a Shapiro-Wilk test (Shapiro-Wilk test), verifying whether the array of each link obeys the normalization distribution, and obtaining reasonable time length of each link through data modeling if the array of each link is reasonable data. The specific calculation formula is as follows:
In the method, in the process of the invention, The mean value of the samples is sigma, the total standard deviation is sigma, Z α/2 is the quantile of a standard normal distribution random variable, and n is the sample capacity.
S2: respectively calculating the provider data by using an entropy weight method and an expert scoring method to obtain a first weight W 1 and a second weight W 2;
Specific:
S21: calculating the weight of each flow link of different suppliers by an entropy weight method based on the acquired supplier data;
According to the explanation of the basic principle of the information theory, the information is a measure of the order degree of the system, and the entropy is a measure of the disorder degree of the system; according to the definition of the information entropy, for a certain index, the degree of dispersion of the certain index can be judged by using the entropy value, the smaller the information entropy value is, the larger the degree of dispersion of the index is, the larger the influence (i.e. weight) of the index on the comprehensive evaluation is, and if the values of the certain index are all equal, the index does not play a role in the comprehensive evaluation. Therefore, the weight of each flow link can be calculated by utilizing the information entropy tool, and a basis is provided for multi-index comprehensive evaluation. The specific flow is as follows:
(1) There are n rows of records, m variables (n suppliers, m links), given an n x m feature matrix a of:
Wherein A is a multi-link feature matrix corresponding to multiple suppliers; x nm is the data of the mth link of the nth supplier;
(2) Data normalization:
Wherein x ij' is the data of the kth link of the ith supplier after normalization; x ij is the data of the kth link of the ith supplier;
(3) Calculating the proportion of the ith supplier in the jth link:
Wherein P ij is the proportion of the ith supplier in the jth link;
(4) Calculating the entropy value of the j link of the i provider:
wherein e ij is the entropy value of the j link of the i-th supplier; k is a first parameter, k >0; e j is more than or equal to 0;
(5) Calculating a difference coefficient of the jth link of the ith supplier:
gij＝1-eij(j＝1,2,…,m)
Wherein g ij is the difference coefficient of the j link of the i-th supplier;
(6) Calculating the weight of the jth link of the ith provider
Through the steps, the first weight calculated by the entropy weight method is obtained
Wherein W 1 is a first weight calculated by an entropy weight method; w ij is the weight of the jth link of the ith vendor.
S22: calculating the weight of each flow link by an expert scoring method based on the acquired provider data;
The expert scoring method is a scientific and reasonable method, according to the basic principle of the Delphi method, the experts in all aspects of the enterprise are selected, the weights are selected by adopting independent form filling, then the weights selected by the experts are sorted and statistically analyzed, and finally the weights of all the factors and all the indexes are determined. The intelligence and the opinion of each expert are collected, and the inspection and the correction are carried out by using a mathematical statistics method, so that the weight W 2 (4 multiplied by 6) calculated by the expert scoring method is finally obtained.
S3: calculating to obtain a comprehensive weight W based on the first weight W 1 and the second weight W 2; calculating link scores and provider scores of the providers based on the first weights W 1;
the influence degree of each link on the whole performance can be obtained by calculating the comprehensive weight;
the comprehensive weight is as follows:
W＝W1+W2
wherein W is the comprehensive weight.
Calculating the concrete score of each link of each provider, knowing the running state of the provider in the link, and acquiring the characteristics of each link of each provider;
The calculation method is as follows:
sij＝tijWij
Where S ij is the score of the jth link of the ith supplier, t ij is the period used by the jth link of the ith supplier, W ij is the weight of the jth link of the ith supplier, and S i is the total score of the ith supplier.
S4: and clustering the suppliers by a DBSCAN clustering algorithm improved based on a seagull optimization algorithm, and each link score and the supplier score of the suppliers, and classifying and grading the suppliers based on the clustering result and the comprehensive weight to obtain a classification grading result.
DBSCAN (Density-Based Spatial Clustering of Applications with Noise) is a Density-based spatial clustering algorithm. Belonging to an unsupervised machine learning method.
If the clustering structure can be obtained through the compactness of sample distribution, the density-based clustering algorithm clusters by taking the density of sample points displayed on the spatial distribution as a standard, namely, once the density of the samples in one area is larger than a given threshold value, the density of the samples is classified into clusters close to the density.
The algorithm expresses the data distribution compactness by using two key parameter radiuses Eps and a density threshold MinPts, and marks scattered points which are higher in data density than other parts and communicated with each other and present density packing in the data set D as the same class. The DBSCAN algorithm can effectively separate clusters from noise points under the condition that no tag data exists and the number of data sample categories is unknown, and has a good recognition effect on data samples including non-convex data sets.
The DBSCAN algorithm measures the similarity between each sample in the sample space in terms of the distance Dist (p, q) between the object points p and q. The smaller the value of Dist (p, q), the more similar the representative objects p and q.
The Euclidean metric formula is used to measure the distance between data objects:
Wherein Dist (p, q) is the distance between the object points p and q; x= (x 1,x2,…,xn) is the coordinates of the point object p, and y= (y 1,y2,…,yn) is the coordinates of the point object q.
Eps neighborhood: a circular region with a radius of Eps around a given object p, i.e. an Eps neighborhood of p
NEps(p)＝{q∈D|Dist(p,q)≤Eps}
Where N Eps (p) represents the set of all objects in dataset D that are not more than Eps apart from object p.
Core object: if the Eps neighborhood of the object p contains no less than the number of MinPts, the object p is called as a core object, namely:
|NEps|≥MinPts
the density is direct: in the data set D, if p is a core object and the object is within the radius Eps neighborhood of q object p, then it can be considered that the object q is directly from the density of when the object p starts.
The density can be achieved: for the object chain p 1,p2,…,pj,…,pn, if p 1 = p and p n＝q,pi are satisfied as p i+1 is directly directed to the Eps and MinPts densities, then p is reachable from q to the Eps and MinPts densities.
Density connection: if object O ε D is present, such that object p and object q are both reachable from O with respect to the Eps and MinPts densities, then p and q are connected in density.
Cluster and noise: taking any point p from the data set D, searching all points which meet the conditions of Eps and MinPts and have reachable densities in the D from p, wherein the points form a class, and an object which does not belong to any class is marked as a noise point.
The gull optimization algorithm (Seagull Optimization Algorithm, SOA) principle includes:
(1) Migration process
① Avoiding mutual collision between seagulls
Cs＝A·Ps(X)
Wherein, a=f c-(X·(fc/Mq));X＝0,1,2,…,Mq;Cs is a new seagull position, P s is a current seagull position, and X is the number of iterative updating times to the current position; a is the movement parameter of seagulls; f c plays a role in controlling the change of the movement parameters; q is the number of iterative updates; m q is the maximum number of iterations.
② Approaching the current optimal seagull
Wherein M s is the direction of the current seagull to the current optimal seagull; b is a random variable; r epsilon [0,1] is a random number; p best (X) is the current optimal seagull position.
③ Location update
Ds＝|Cs+Ms|
Wherein D s is the distance between the current seagull and the optimal seagull.
(2) Attack procedure
Wherein r is the flight radius of the seagull in the descending process; k is a random value within [0,2 pi ]; u, v are constant variables of spiral flight; e is the base of natural logarithm; p s+1 (X) is the updated optimal gull position.
S41: clustering suppliers by a DBSCAN clustering algorithm improved based on a seagull optimization algorithm, and each link score and supplier score of the suppliers to obtain a clustering result;
As shown in fig. 2, two key parameters of the DBSCAN algorithm are radius Eps and density threshold MinPts, eps being the range in which data items are counted, minPts being the number of data items within a certain range. Each provider has m links, which can be considered to have m features, each feature having a corresponding score. In the specific design process of the clustering algorithm, two parameters of the radius Eps and the density threshold MinPts have certain difficulty, and a large number of experiments are needed to determine the most reasonable parameter values. And optimizing the two key parameters by adopting a seagull optimization algorithm.
(1) Decoding and encoding
The solution vector adopts a two-dimensional coding mode:
X＝(x1,x2)
Wherein x 1 represents the value of radius Eps, the value range is [ lEps, uEps ]; x 2 represents the value of the density threshold MinPts, ranging from [ lPts, uPts ]. The value range is set according to the requirement.
(2) Initial solution set generation
To ensure the disorder and randomness of the initial solution set, thereby avoiding the premature algorithm, generating the initial solution by using the cube chaos
x0∈rand(0,1)
x′n＝x′n-1*(1-x′n-1)
xn＝(ubn-lbn)*x′n+lbn
Where x 0 is a random number in the range of [0,1], x' n is a chaos factor of an nth decision variable, x n is a randomly generated nth decision variable, ub n is an upper limit of the value of the nth decision variable, and lb n is a lower limit of the value of the nth decision variable.
(3) Fitness function
The fitness function adopts a contour coefficient calculation mode, and the contour coefficient is a common method for evaluating the cluster effect. The profile coefficient comprises two parts, namely a cohesive degree and a separation degree, wherein the cohesive degree is the tightness degree of a sample point and elements in a cluster; the degree of separation is the degree of tightness between a sample point and an element outside a cluster, and the calculation formula is as follows:
wherein a (i) represents the class cohesive degree of the sample point, and the calculation formula is that
Where j represents other sample points in the same cluster as sample i, the smaller a (i) the tighter the class; the calculation of B (i) is substantially the same as that of a (i), except that B (i) is a point of traversing other clusters, so B (i) has multiple candidate values b= { B 1(i),b2(i),…,bm (i) }, B (i) =minb. According to the above description, the contour coefficient S epsilon [ -1,1], and the larger the value of S, the better the clustering effect.
The fitness value of the individual i of the t th generation of seagull is
f(Xi(t))＝S(i)
Wherein f (X i (t)) is the fitness value of the individual i of the t th generation of seagull;
after clustering, suppliers are divided into a plurality of classes, and the suppliers in each class have similar scores.
S42: classifying and grading the clustering results according to the comprehensive weights to obtain classification and grading results;
After clustering, the suppliers may be separated into several classes, scores for the suppliers in each class are calculated according to the composite weights, and the suppliers are rated according to the scores. The rating method may include the following three types:
(1) Layer difference method, also called interval method: dividing the target value into a plurality of sections by taking the target value as a reference, and setting a corresponding score for each section; after the actual value is checked, judging which interval is in, and obtaining the score of the index.
(2) The buckling method comprises the following steps: the score is only reduced and not added for the index; the target value is a reference completion value above which no score is added and below which scores are all withheld according to a certain rule.
(3) RFM model: important tools and means for measuring customer value and customer profit creation capability; among the numerous analysis modes of Customer Relationship Management (CRM), RFM models are widely mentioned; the value status of a customer is described in terms of 3 points of the amount of consumption by the recent purchase behavior of the customer, the overall frequency of purchases.
Example 2
As shown in fig. 3, based on the same inventive concept as the above embodiment, the present invention also provides a vendor classification rating apparatus, comprising:
The weight calculation module is used for respectively calculating the provider data by using an entropy weight method and an expert scoring method to obtain a first weight and a second weight; calculating based on the first weight and the second weight to obtain comprehensive weight;
a score calculating module for calculating each link score and the provider score of the provider based on the first weight;
And the classification rating result obtaining module is used for clustering the suppliers by a DBSCAN clustering algorithm improved based on a seagull optimization algorithm, each link score of the suppliers and the supplier score, and classifying and rating the suppliers based on the clustering result and the comprehensive weight to obtain a classification rating result.
Example 3
As shown in fig. 4, the present invention also provides an electronic device 100 for implementing a vendor classification rating method;
the electronic device 100 comprises a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on the at least one processor 102, and at least one communication bus 104.
Memory 101 may be used to store a computer program 103 and processor 102 implements a vendor classification rating method step of embodiment 1 by running or executing the computer program stored in memory 101 and invoking data stored in memory 101.
The memory 101 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (such as audio data) created according to the use of the electronic device 100, and the like. In addition, memory 101 may include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart memory card (SMART MEDIA CARD, SMC), secure Digital (SD) card, flash memory card (FLASH CARD), at least one disk storage device, flash memory device, or other non-volatile solid-state storage device.
The at least one Processor 102 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. The processor 102 may be a microprocessor or the processor 102 may be any conventional processor or the like, the processor 102 being a control center of the electronic device 100, the various interfaces and lines being utilized to connect various portions of the overall electronic device 100.
Memory 101 in electronic device 100 stores a plurality of instructions to implement a vendor classification rating method, processor 102 may execute the plurality of instructions to implement:
Respectively calculating the provider data by using an entropy weight method and an expert scoring method to obtain a first weight and a second weight; calculating based on the first weight and the second weight to obtain comprehensive weight;
Calculating link scores and provider scores of the providers based on the first weights;
And clustering the suppliers by a DBSCAN clustering algorithm improved based on a seagull optimization algorithm, and each link score and the supplier score of the suppliers, and classifying and grading the suppliers based on the clustering result and the comprehensive weight to obtain a classification grading result.
Example 4
The modules/units integrated with the electronic device 100 may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as a stand alone product. Based on such understanding, the present invention may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the steps of each method embodiment described above may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, executable files or in some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, and a Read-Only Memory (ROM).
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In the description of the present specification, the descriptions of the terms "one embodiment," "example," "specific example," and the like, mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is intended to be covered by the claims.
Claims (10)
1. A vendor classification rating method, comprising:
Respectively calculating the provider data by using an entropy weight method and an expert scoring method to obtain a first weight and a second weight; calculating based on the first weight and the second weight to obtain comprehensive weight;
Calculating link scores and provider scores of the providers based on the first weights;
And clustering the suppliers by a DBSCAN clustering algorithm improved based on a seagull optimization algorithm, and each link score and the supplier score of the suppliers, and classifying and grading the suppliers based on the clustering result and the comprehensive weight to obtain a classification grading result.
2. The method for classifying and rating suppliers according to claim 1, wherein when the supplier data is obtained, whether the suppliers are overdue or not is judged by carrying out reasonable interval estimation and reasonable interval of overall use on each flow link of the suppliers, specifically:
Carrying out normal test by means of a Charpy-Weirk test, verifying whether the array of each link is subjected to normal distribution, and if the array of each link is reasonable data, obtaining reasonable time length of each link by means of data modeling; the specific calculation formula is as follows:
In the method, in the process of the invention, The mean value of the samples is sigma, the total standard deviation is sigma, Z α/2 is the quantile of a standard normal distribution random variable, and n is the sample capacity.
3. The vendor classification rating method of claim 1, wherein the calculating of the first weight comprises:
based on the obtained vendor data, a first weight W 1 is calculated by an entropy weight method:
n suppliers, m links, and given a feature matrix a of n×m:
Wherein A is a multi-link feature matrix corresponding to multiple suppliers; x nm is the data of the mth link of the nth supplier;
Data normalization:
Wherein x il' is the normalized data of the j link of the i-th supplier; x ij is the data of the j link of the i-th supplier;
calculating the proportion of the ith supplier in the jth link:
Wherein P ij is the proportion of the ith supplier in the jth link;
Calculating the entropy value of the j link of the i provider:
wherein e ij is the entropy value of the j link of the i-th supplier; k is a first parameter, k >0; e j is more than or equal to 0;
calculating a difference coefficient of the jth link of the ith supplier:
gij＝1-eij(j＝1,2,…,m)
Wherein g ij is the difference coefficient of the j link of the i-th supplier;
Calculating the weight of the j link of the i provider:
Obtaining a first weight calculated by an entropy weight method
Wherein W 1 is a first weight calculated by an entropy weight method; w ij is the weight of the jth link of the ith vendor.
4. A vendor classification rating method according to claim 3, wherein the calculating of the second weight comprises:
And selecting an expert in each aspect of the enterprise through an expert scoring method, adopting a form of independently filling a table to select weights, sorting and statistically analyzing the weights selected by the expert, determining each factor, checking and correcting the weights of each index by using a mathematical statistical method, and calculating to obtain a second weight W 2.
5. The vendor classification rating method of claim 4, wherein the calculation of the integrated weight is:
W＝W1+W2
wherein W is the comprehensive weight.
6. The vendor classification rating method according to claim 5, wherein the calculating the link scores and the vendor scores of the vendors based on the first weights is specifically as follows:
sij＝tijWij
Where S ij is the score of the jth link of the ith supplier, t ij is the period used by the jth link of the ith supplier, W ij is the weight of the jth link of the ith supplier, and S i is the total score of the ith supplier.
7. The method for classifying and rating suppliers according to claim 6, wherein the classifying and rating suppliers based on the clustering result and the comprehensive weight, the obtaining the classifying and rating result specifically comprises:
After clustering, classifying the suppliers into a plurality of classes, calculating the scores of the suppliers in each class according to the comprehensive weight, and grading the suppliers according to the scores, wherein the grading method comprises the following steps: a layer difference method, a buckling method or an RFM model.
8. A vendor classification rating apparatus, comprising:
The weight calculation module is used for respectively calculating the provider data by using an entropy weight method and an expert scoring method to obtain a first weight and a second weight; calculating based on the first weight and the second weight to obtain comprehensive weight;
a score calculating module for calculating each link score and the provider score of the provider based on the first weight;
And the classification rating result obtaining module is used for clustering the suppliers by a DBSCAN clustering algorithm improved based on a seagull optimization algorithm, each link score of the suppliers and the supplier score, and classifying and rating the suppliers based on the clustering result and the comprehensive weight to obtain a classification rating result.
9. An electronic device comprising a processor and a memory, the processor being configured to execute a computer program stored in the memory to implement a vendor classification rating method as claimed in any one of claims 1 to 7.
10. A computer readable storage medium storing at least one instruction which when executed by a processor implements a vendor classification rating method according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410344771.6A CN118172113A (en) | 2024-03-25 | 2024-03-25 | Vendor classification rating method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410344771.6A CN118172113A (en) | 2024-03-25 | 2024-03-25 | Vendor classification rating method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118172113A true CN118172113A (en) | 2024-06-11 |
Family
ID=91348357
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410344771.6A Pending CN118172113A (en) | 2024-03-25 | 2024-03-25 | Vendor classification rating method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118172113A (en) |
-
2024
- 2024-03-25 CN CN202410344771.6A patent/CN118172113A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Pang et al. | ELECTRE I Decision Model of Reliability Design Scheme for Computer Numerical Control Machine. | |
| CN109919489B (en) | Enterprise asset management system and GA-BP-based enterprise equipment life prediction method | |
| CN107168995B (en) | Data processing method and server | |
| CN112241494B (en) | Key information pushing method and device based on user behavior data | |
| CN109345050A (en) | A kind of quantization transaction prediction technique, device and equipment | |
| CN107392217B (en) | Computer-implemented information processing method and device | |
| CN111309577B (en) | Spark-oriented batch application execution time prediction model construction method | |
| CN115081515A (en) | Energy efficiency evaluation model construction method and device, terminal and storage medium | |
| CN113837266B (en) | Software defect prediction method based on feature extraction and Stacking ensemble learning | |
| CN112598405B (en) | Business project data management method and system based on big data | |
| CN117056761A (en) | Customer subdivision method based on X-DBSCAN algorithm | |
| CN118172113A (en) | Vendor classification rating method, device, equipment and medium | |
| CN113393023B (en) | Mold quality evaluation method, apparatus, device and storage medium | |
| CN111026661B (en) | Comprehensive testing method and system for software usability | |
| CN107291722B (en) | Descriptor classification method and device | |
| KR102289396B1 (en) | Application of reinforcement learning for the advancement of forecasting item demand of repair parts of military equipment | |
| CN114298579A (en) | Active power distribution network fault risk early warning method and system based on data mining | |
| Azzalini et al. | Data Quality and Data Ethics: Towards a Trade-off Evaluation. | |
| CN117539520B (en) | Firmware self-adaptive upgrading method, system and equipment | |
| CN118036920A (en) | Supplier competition type matching method and system based on photovoltaic demand | |
| CN115730254B (en) | Method and device for expanding modeling sample data label | |
| Faran et al. | Combination of RFM’s (Recency Frequency Monetary) Method and Agglomerative Ward’s Method for Donors Segmentation | |
| Le et al. | Application of isotonic regression in predicting business risk scores | |
| CN118297193A (en) | Voting-based civil aviation customer satisfaction prediction algorithm | |
| CN114445122A (en) | User loss rate prediction method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |