CN111967927A - Commercial purchasing method for calculating satisfaction degree through multiple criteria - Google Patents
Commercial purchasing method for calculating satisfaction degree through multiple criteria Download PDFInfo
- Publication number
- CN111967927A CN111967927A CN202010636005.9A CN202010636005A CN111967927A CN 111967927 A CN111967927 A CN 111967927A CN 202010636005 A CN202010636005 A CN 202010636005A CN 111967927 A CN111967927 A CN 111967927A
- Authority
- CN
- China
- Prior art keywords
- supplier
- price
- dimension
- suppliers
- score
- 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 30
- 239000013598 vector Substances 0.000 claims abstract description 61
- 239000011159 matrix material Substances 0.000 claims abstract description 23
- 238000012216 screening Methods 0.000 claims abstract description 4
- 238000004364 calculation method Methods 0.000 claims description 28
- 238000011156 evaluation Methods 0.000 claims description 22
- 230000000694 effects Effects 0.000 claims description 12
- 230000001186 cumulative effect Effects 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 8
- 238000011161 development Methods 0.000 description 5
- 238000013507 mapping Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000009466 transformation Effects 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0605—Supply or demand aggregation
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0609—Buyer or seller confidence or verification
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0611—Request for offers or quotes
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of industry internet information in the vertical field of manufacturing industry, and discloses a commercial purchasing method for calculating satisfaction based on multiple criteria, which comprises the following steps: s1, obtaining information vectors of all suppliers in all non-price dimensions, and obtaining original matrixes of all suppliers in all non-price dimensions; s2, extracting and obtaining a characteristic vector matrix of all suppliers under each non-price dimension through PCA; s3, calculating the scores of all suppliers under all non-price dimensions according to dimensions; s4, obtaining a plurality of different purchasing schemes, arranging the purchasing schemes in a descending order according to the total price, and calculating the price scores of all suppliers in the former M purchasing schemes; s5, calculating the comprehensive satisfaction of the buyer to each supplier; and S6, screening N purchasing schemes with the comprehensive satisfaction degree of the suppliers in the purchasing schemes larger than the satisfaction degree threshold value and lower price as the purchasing schemes recommended to the user. The invention obtains the purchasing scheme which is more in line with the cooperation habit of the client and has higher satisfaction degree through multiple criteria and user habits.
Description
Technical Field
The invention relates to a multi-criterion commercial purchasing method for calculating satisfaction, and belongs to the technical field of industry internet information in the vertical field of manufacturing industry.
Background
The 'Shandong province artificial intelligence industry development report' indicates that the greatest value of artificial intelligence is in combination with specific industries, the manufacturing industry, the Shandong province, the great province of the industry, the great thickness of the industry foundation, the perfect industry system and the wide artificial intelligence application scene. The intelligent manufacturing development is the necessary route for transformation and upgrade of the manufacturing industry. The development of intelligent manufacturing is restricted by pain points such as technology shortage, high purchasing cost, labor cost rising and the like. How to realize accurate matching of mass supply and demand information through an industrial internet platform breaks through the current situation of information asymmetry, reduces the transaction cost, accelerates market transaction circulation, and is a key point for promoting rapid development of intelligent manufacturing. With the rapid development of information technology, a business evaluation model based on one-to-many bilateral matching of multiple criteria is produced.
Commercial evaluation and supplier selection are important items in purchasing decisions. The core idea of the supplier scheme based on business evaluation in the invention is 'decentralized resource centralized use and centralized resource decentralized service'. Under the environment of platform collection, a large amount of purchasing demands can be concentrated, the effect of large amount and low price is achieved, and the price disadvantage of small amount of purchasing in small and medium-sized enterprises is solved.
In the prior art, commercial evaluation and supplier evaluation comprise two parts, namely an evaluation system and an evaluation method. For the supplier evaluation system, many scholars have set forth a large number of different evaluation criteria from different environments and perspectives. At present, the common supplier evaluation methods include a linear weight integral method, a statistical method, a cost estimation method, an analytic hierarchy process and a fuzzy analytic hierarchy process. However, the methods have the defects of being not objective enough, strong in subjectivity, inaccurate in evaluation and not in line with actual business habits.
Disclosure of Invention
In order to solve the problem that the business evaluation method in the prior art is not accurate and objective enough, the invention provides a multi-criterion business purchasing method for calculating satisfaction, and by comprehensively evaluating suppliers in a manufacturing platform, the purchasing scheme of a purchaser is optimized, so that the purchasing efficiency of the purchaser is improved, the purchasing cost of the purchaser is reduced, and the method plays a role in guiding an enterprise to optimize the purchasing scheme to a certain extent.
In order to solve the technical problems, the invention adopts the technical scheme that: a business procurement method for calculating satisfaction based on multiple criteria, comprising the steps of:
s1, taking the input time of a buyer as a node, a product to be purchased as a reference, and a supplier which is in front of the previous node and supplies the purchased product as an analysis object, acquiring information vectors of all suppliers in all non-price dimensions, and acquiring original matrixes of all suppliers in all non-price dimensions;
s2, extracting by PCA to obtain a characteristic vector matrix of all suppliers under each non-price dimension, and simultaneously obtaining an original characteristic vector representing original information under each non-price dimension;
s3, calculating the normalized inner product value between the feature vector of each supplier and the original feature vector under each non-price dimension in a dimensionality division mode, and taking the normalized inner product value as the score of the supplier under the non-price dimension;
s4, acquiring price sequence matrixes and inventory of all suppliers, solving the relation between the total price W and the total purchase quantity X based on dynamic planning, and acquiring a plurality of different purchase schemes; arranging different purchasing schemes in a descending order according to the total price, selecting the first M purchasing schemes after removing the purchasing schemes completely identical to the suppliers, and calculating the ratio of the total product supply quantity of each supplier in the first M purchasing schemes to the total supply quantity of the M schemes to serve as the price score of each supplier;
s5, obtaining the grading requirements of each dimensionality of the buyer, and calculating the comprehensive satisfaction degree of the buyer to each supplier;
and S6, screening out purchasing schemes of which the comprehensive satisfaction of the suppliers is greater than the threshold value of the comprehensive satisfaction, and selecting N purchasing schemes with lower prices as the purchasing schemes recommended to the user for the user to select.
The non-price dimensions include: integrity H, strength S, informatization T, liveness A and customer satisfaction C.
In step S2, the specific method for obtaining the eigenvector matrix of all suppliers under each non-price dimension by PCA extraction includes the following steps:
s201, calculating a decentralized matrix X under a first non-price dimension;
s202, calculating a covariance matrix
Solving an eigenvalue lambda and an orthogonalized unit eigenvector b of the covariance matrix;
s203, sorting the characteristic values in a descending order, lambda1≥λ2≥…≥λnCalculating the cumulative variance contribution rate, taking the minimum k value of which the cumulative variance contribution rate is greater than 90% as the number of the principal components, and extracting the principal components corresponding to the first k characteristic values to obtain a principal component space U; wherein 0<k<n and is a positive integer, and the cumulative variance contribution ratio is calculated by the formula:
s204, calculating to obtain a feature vector matrix B under a first non-price dimension, wherein the calculation formula is as follows: b ═ XU;
and S205, repeating the steps S201 to S204, and calculating to obtain the feature vector matrixes of all suppliers under all non-price dimensions.
In step S3, the integrity score of each supplier is calculated by the following formula:
wherein HiRepresenting the integrity score of the ith supplier, b0jValue of the jth component of the original feature vector representing the honest dimension, bijA value representing a jth component of an ith vendor in a trustworthiness dimension;
the calculation formula of the strength score of each supplier is as follows:
wherein S isiIndicating the strength score of the ith supplier, d0jValue of the jth component of the original feature vector representing the real dimension, dijA value representing the jth component of the ith supplier in the real dimension;
the calculation formula of the informatization scores of each supplier is as follows:
wherein E isiAn informationized score representing the ith supplier, e0jValue of the jth component of the original feature vector representing the informatization dimension, eijA value representing a jth component of an ith vendor in the informatization dimension;
the calculation formula of the activity score of each supplier is as follows:
wherein A isiIndicating the liveness score of the ith supplier, f0jValue of the j-th component of the original feature vector representing the liveness dimension, dijA value representing a jth component of an ith supplier in an activity dimension;
the calculation formula of the customer satisfaction score of each supplier is as follows:
wherein, CiRepresents the customer satisfaction score, q, of the ith supplier0jValue of jth component of original feature vector representing customer satisfaction dimension, qijA value representing the jth component of the ith vendor in the customer satisfaction dimension.
In step S4, the calculation formula of the price score of each supplier is:
wherein, PiRepresents the price score, x, of the ith supplierijIndicates the supply quantity, x, of the ith supplier in the jth procurement planmkRepresenting the supply of k suppliers in the mth procurement plan.
In step S5, the calculation process of the comprehensive satisfaction of the buyer with each supplier specifically includes the following steps:
s501, obtaining scores of buyers for all dimensions and requiring Score0＝[H0,S0,T0,A0,C0,P0]Where the buyer's Score is required for each dimension0The evaluation average value of all the dimensions of all the suppliers in the purchase history of the buyer on the platform is shown;
s502, calculating the scores of all suppliers in all non-price dimensions and the Euclidean distance values between the price scores and the score requirements of the buyers, and adding all the Euclidean distance values to obtain the sum of the distance values between all the suppliers and the buyers;
s503, calculating the comprehensive satisfaction of the buyer to each supplier, wherein the calculation formula is as follows:
wherein s isiIndicating the combined satisfaction of the buyer with the ith supplier, diRepresenting the sum of the distance values between the ith supplier and the buyer.
In step S501, the user who first purchases on the platform sets the initial value of the rating requirement for each dimension to: score0＝[0.6,0.6,0.6,0.6,0.6,0.6]。
The values of M and N are both 10, and the comprehensive satisfaction threshold is 70%.
Compared with the prior art, the invention has the following beneficial effects: the invention provides a multi-criterion commercial purchasing method for calculating satisfaction, which is based on score extraction of six dimensional elements, combines with a supplier scheme score based on a total price relation of dynamic planning, and realizes multi-criterion commercial evaluation based on a score vector; the collection mode of the platform has influence on the price sequence, and the possibility of reducing the cost is provided for the user; and obtaining a purchasing scheme which better accords with the cooperation habit of the client and has higher satisfaction degree through multiple criteria and user habits.
Drawings
Fig. 1 is a schematic flow chart of a proposed multi-criteria commercial purchasing method for calculating satisfaction according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to specific embodiments and accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention; all other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, the embodiment of the present invention provides a method for purchasing a business based on multi-criteria calculation satisfaction, which includes the following six steps.
And S1, taking the input time of the buyer as a node, taking the product to be purchased as a reference, taking the supplier which supplies the purchased product before the previous node as an analysis object, acquiring information vectors of all suppliers in all non-price dimensions, and acquiring the original matrix of all suppliers in all non-price dimensions.
In this embodiment, the original dimensions include a non-price dimension and a price dimension, where the non-price dimension includes integrity (H), strength (S), informatization (T), liveness (a), customer satisfaction (C), and the price dimensionDegree refers in particular to the price advantage sequence (P). The original information of each dimension is a vector composed of its sub-index elements, e.g. integrity H ═ (H)1,H2,…,Hm)TThe expression integrity H is composed of n components, and the like strength (S), informatization (T), liveness (A), customer satisfaction (C) and price advantage sequence (P) are composed of a plurality of components. The calculation time of the current user is taken as a node, the product which needs to be purchased by the current user is taken as a reference, the provider dimension information of the purchased product supplied before the previous node is taken as a latest training set of the PCA, and final-stage indexes of all dimensions of the provider supplied on the platform for the first time, such as the complaint rate and the return rate of the final-stage indexes, without corresponding final-stage quantitative indexes are set according to the optimal scores.
S2, extracting by PCA to obtain a characteristic vector matrix of all suppliers under each non-price dimension, and simultaneously obtaining an original characteristic vector representing original information under each non-price dimension;
in this embodiment, feature vectors are extracted by PCA, and principal components are obtained by using the PCA learning training set. And mapping the set to a principal component space, and extracting a dimension characteristic vector representing dimension original information. As in the dimension of integrity H, the raw information of each vendor is extracted by PCA as feature vectors:
where H is the original information matrix of the vendor integrity dimension, HmIs the original information vector of the mth supplier honest dimension, each supplier contains n indexes of honest dimension evaluation, hmnAn nth index value representing an mth supplier; b is a feature vector matrix of H extracted by PCA, BmIs the original information vector H of the mth suppliermFeature vectors extracted by PCA, bmkAnd k is the number automatically obtained after the variance contribution rate is set to be 90%, and is the number of characteristic elements of the characteristic vector of the integrity dimension extracted by PCA.
Taking the extraction of the eigenvector B by the honest dimension H as an example, the process of obtaining the eigenvector matrix of all suppliers under the honest dimension by PCA extraction is as follows: and extracting principal components from the integrity dimension original information H by using PCA, and mapping the integrity dimension original information H into a principal component space to obtain a feature vector B representing the original integrity dimension information H. The specific calculation steps are as follows:
s201, mean value removing, namely decentralization, namely subtracting the mean value corresponding to all indexes from each index. The average index value is:
represents the average value of the i-th index. The de-centered matrix X is then:
s202, calculating a covariance matrix:
and solving the eigenvalue lambda and the specially-orthogonalized unit eigenvector b.
S203, sorting the characteristic values in a descending order, lambda1≥λ2≥…≥λnIs more than or equal to 0. Calculating the cumulative variance contribution rate, taking the minimum k value of which the cumulative variance contribution rate is greater than 90% as the number of principal components, and extracting the principal components corresponding to the first k characteristic values to obtain a principal component space V; wherein 0<k<n and is a positive integer, and the cumulative variance contribution ratio is calculated by the formula:
wherein λ isiCorresponding unit feature vector biIs the main component FiWith respect to the coefficient of the original variable, the ith principal component F of the original variableiComprises the following steps: fi＝bi' X; variance contribution ratio of principal component, variance contribution ratio calculation of ith principal componentComprises the following steps:
wherein the number of the finally selected principal components, i.e., F1,F2,…,FkThe determination of k is determined by the variance cumulative contribution rate g (k). When the cumulative contribution rate is greater than 90%, it is considered that the information of the original variable is sufficiently reflected, and the corresponding k is the first k principal components extracted, i.e., the principal component space U.
S204, calculating to obtain a feature vector matrix B under a first non-price dimension, wherein the calculation formula is as follows: b ═ XU;
where X is m × n constituted by the original information, U is an n × k matrix constituted by k principal components, and B is an extracted m × k eigenvector matrix.
And S205, repeating the steps S201 to S204, and calculating to obtain the feature vector matrixes of all suppliers under all non-price dimensions.
In this embodiment, corresponding feature vectors may be extracted for non-price dimensions such as strength (S), informatization (T), liveness (a), customer satisfaction (C), and the like:
and S3, calculating the normalized inner product value between the feature vector of each supplier and the original feature vector under each non-price dimension by dimension, and taking the normalized inner product value as the score of the supplier under the non-price dimension.
In this embodiment, the score is calculated by normalizing the inner product. And mapping the optimal original information data of each dimension to the principal component space of each dimension to obtain the characteristic vector representing the optimal original information data. In this embodiment, the evaluation numbers of each index of each non-price dimension are shown in tables 1 to 5, wherein the evaluation of the integrity index is shown in table 1, and the highest score of the evaluation of each index (the final-stage index) is used as the best original information of integrity. In addition, the index setting of the invention can be set in other forms according to requirements, and is within the protection scope of the invention.
TABLE 1 sincerity parameter index
TABLE 2 force parameter index
TABLE 3 informationized parameter index
TABLE 4 liveness parameter index
TABLE 5 customer satisfaction parameter index
Best original information H to be honest0Mapping to principal component space to obtain original representation information H0Feature vector B of0＝(b01,b02,…,b0k) The integrity feature vector of supplier i and B0And uses it as the score of the supplier in the integrity dimension quotient, i.e. the integrity score SD (B) of the supplier i0,Bi) Expressed as:
wherein HiRepresenting the integrity score of the ith supplier, b0jValue of the jth component of the original feature vector representing the honest dimension, bijRepresenting the value of the jth component of the ith vendor in the honest dimension, SB representing the inner product operation;
in the same way, the normalized inner product scores between the feature vectors corresponding to the extraction of the strength (S), the informatization (T), the activity (A) and the customer satisfaction (C) and the feature vectors corresponding to the representation of the optimal original information data can be calculated, and the provider scores under each dimension are calculated according to the calculation formulas:
wherein S isiIndicating the strength score of the ith supplier, d0jValue of the jth component of the original feature vector representing the real dimension, dijA value representing the jth component of the ith supplier in the real dimension; t isiAn informationized score representing the ith supplier, e0jValue of the jth component of the original feature vector representing the informatization dimension, eijA value representing a jth component of an ith vendor in the informatization dimension; a. theiIndicating the liveness score of the ith supplier, f0jValue of the j-th component of the original feature vector representing the liveness dimension, dijA value representing a jth component of an ith supplier in an activity dimension; ciRepresents the customer satisfaction score, q, of the ith supplier0jValue of jth component of original feature vector representing customer satisfaction dimension, qijA value representing the jth component of the ith vendor in the customer satisfaction dimension.
In addition, in the embodiment of the invention, the scores of all the dimensions of all the suppliers are obtained by normalizing inner product values with the feature vectors of the best information of all the dimensions, and 0 < H is providedi,Si,Ti,Ai,Ci＜＜1。
S4, acquiring price sequence matrixes and inventory of all suppliers, solving the relation between the total price W and the total purchase quantity X based on dynamic planning, and acquiring a plurality of different purchase schemes; and (3) arranging the different purchasing schemes in a descending order according to the total price, selecting the first M purchasing schemes after removing the completely same purchasing schemes of the suppliers, and calculating the ratio of the total product supply quantity of each supplier in the first M purchasing schemes to the total supply quantity of the M schemes to serve as the price score of each supplier.
Each supplier has a separate price sequence matrix R and current inventory V representation consisting of:
where m denotes that the supplier has m gradient quotes, Rm1Lower limit of the m-th dose gradient, Rm2For prices within the corresponding gradient purchase amount, i.e. (R)m1-R(m-1)1) The execution price within the purchase amount is Rm2，Rm3Indicating whether there is collecting activity in the corresponding gradient purchase amount, 0 indicating no collecting activity, and 1 indicating collecting activity. Rm4Indicating the number of products capable of participating in the acquisition within the current corresponding gradient purchase amount, wherein the current acquisition product number contains the number of the previous gradient purchase amount. The collecting activity refers to a mode of initiating grouping purchase, multiple buyers participate together, and the purchasing amount is increased so as to reduce purchasing cost.
Solving the relation between the total price and the total amount based on dynamic planning, wherein the product demand of the buyer is X, and the demand vector provided by n suppliers is (X)1,x2,…,xn) The supply quantity of each supplier is considered to participate in the collecting part and the non-collecting part simultaneously, and the corresponding price is expressed as (y)1,y2,…,yn)，viIndicating the inventory of the product for the ith supplier. In designing a project, the acquisition part and the non-acquisition part are treated as different project situations. And calculating the final price W to obtain different purchasing schemes.
W＝y1+y2+…+yn；
The present embodiment scores suppliers based on a procurement plan. And (4) arranging different purchasing schemes in a descending order according to the total price, and selecting the first 10 purchasing schemes after removing the purchasing schemes completely identical with the suppliers. Counting the product purchasing amount of each supplier in 10 schemes, wherein the grade P of the supplier is the ratio of the total product supply amount of the supplier in 10 schemes to the total supply amount of the 10 schemes, and the grade of the ith supplier is Pi。
Wherein, PiRepresents the price score, x, of the ith supplierijIndicates the supply quantity, x, of the ith supplier in the jth procurement planmkRepresenting the supply of k suppliers in the mth procurement plan.
And S5, acquiring the grading requirements of each dimensionality of the buyer and calculating the comprehensive satisfaction degree of the buyer to each supplier.
Score grading the six dimensions of the supplier, and Score grading the various dimensions of the buyer0＝ [H0,S0,T0,A0,C0,P0]As input to calculate the overall satisfaction of the buyer with the n suppliers. Where the buyer's Score is required for each dimension0The evaluation is the average value of all the suppliers in all the dimensions in the purchase history of the buyer on the platform. Such as, for example,
wherein HiIs the integrity score of the buyer i in the history record of the buyer, and n represents n buyers in the purchasing history of the buyers. For a user who first purchases on the platform, i.e. no history, the scoring requirements for each dimension are initialized as follows: score0＝[0.6,0.6,0.6,0.6,0.6,0.6]. And further calculating the comprehensive satisfaction degree of the buyer to the n suppliers.
Specifically, the calculation process of the comprehensive satisfaction degree of the buyer to each supplier specifically comprises the following steps:
s501, obtaining scores of buyers for all dimensions and requiring Score0＝[H0,S0,T0,A0,C0,P0]In which H is0,S0,T0,A0,C0,P0Respectively representing the grading requirements of the buyer under six dimensions of sincerity, strength, informatization, liveness, customer satisfaction and price, and the grading requirement of the buyer to each dimension is Score0The evaluation average value of all the dimensions of all the suppliers in the purchase history of the buyer on the platform is shown; the user who first purchases on the platform, the grading requirement of each dimension is initially as follows: score0＝[0.6,0.6,0.6,0.6,0.6,0.6]。
S502, calculating the scores of all suppliers in all non-price dimensions and the Euclidean distance values between the price scores and the score requirements of the buyers, and adding all the Euclidean distance values to obtain the sum of the distance values between all the suppliers and the buyers;
specifically, the calculation formula between the euclidean distance values of the dimensions is:
wherein d ishi、dsi、dti、dai、dciAnd dpiRespectively representing the integrity H, the strength S, the informatization T, the activity A, the customer satisfaction C and the Euclidean distance value between a buyer and a supplier under the price P dimensionality; the calculation formula of the sum of the distance values between each supplier and each buyer is as follows:
di＝dhi+dsi+dti+dai+dci+dpi； (24)
wherein d isiRepresenting the sum of the total distance values of the buyer and the ith supplier. From diCan be known as d is more than or equal to-6i≤6。
S503, calculating the comprehensive satisfaction of the buyer to each supplier, wherein the calculation formula is as follows:
wherein s isiIndicating the combined satisfaction of the buyer with the ith supplier, diRepresenting the sum of the distance values between the ith supplier and the buyer.
And S6, screening out purchasing schemes of which the comprehensive satisfaction of the suppliers is greater than the threshold value of the comprehensive satisfaction, and selecting N purchasing schemes with lower prices as the purchasing schemes recommended to the user for the user to select.
Specifically, in this embodiment, the satisfaction evaluation of the buyer to the provider is taken as a reference, and the purchasing scheme with higher comprehensive satisfaction and lower purchasing price is selected in combination with the purchasing scheme. And sorting the suppliers according to the comprehensive satisfaction degree of the suppliers, and selecting the top 10 purchasing schemes with the comprehensive satisfaction degree of the suppliers being more than 70% and the lower purchasing price as the purchasing schemes recommended to the user for the user to select for the supplier list in the standard purchasing scheme.
In conclusion, the invention provides a multi-criterion commercial purchasing method for calculating satisfaction, which is based on score extraction of six dimensional elements, combines with a supplier scheme score based on a total sum relation of dynamic planning, and realizes multi-criterion commercial evaluation based on a score vector; the collection mode of the platform has influence on the price sequence, and the possibility of reducing the cost is provided for the user; and obtaining a purchasing scheme which better accords with the cooperation habit of the client and has higher comprehensive satisfaction through multiple criteria and user habits.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.
Claims (8)
1. A business procurement method for calculating satisfaction based on multiple criteria, comprising the steps of:
s1, taking the input time of a buyer as a node, a product to be purchased as a reference, and a supplier which is in front of the previous node and supplies the purchased product as an analysis object, acquiring information vectors of all suppliers in all non-price dimensions, and acquiring original matrixes of all suppliers in all non-price dimensions;
s2, extracting by PCA to obtain a characteristic vector matrix of all suppliers under each non-price dimension, and simultaneously obtaining an original characteristic vector representing original information under each non-price dimension;
s3, calculating the normalized inner product value between the feature vector of each supplier and the original feature vector under each non-price dimension in a dimensionality division mode, and taking the normalized inner product value as the score of the supplier under the non-price dimension;
s4, acquiring price sequence matrixes and inventory of all suppliers, solving the relation between the total price W and the total purchase quantity X based on dynamic planning, and acquiring a plurality of different purchase schemes; arranging different purchasing schemes in a descending order according to the total price, selecting the first M purchasing schemes after removing the purchasing schemes completely identical to the suppliers, and calculating the ratio of the total product supply quantity of each supplier in the first M purchasing schemes to the total supply quantity of the M schemes to serve as the price score of each supplier;
s5, obtaining the grading requirements of each dimensionality of the buyer, and calculating the comprehensive satisfaction degree of the buyer to each supplier;
and S6, screening out purchasing schemes of which the comprehensive satisfaction of the suppliers is greater than the threshold value of the comprehensive satisfaction, and selecting N purchasing schemes with lower prices as the purchasing schemes recommended to the user for the user to select.
2. The method of claim 1, wherein the non-price dimension comprises: integrity H, strength S, informatization T, liveness A and customer satisfaction C.
3. The method for purchasing commerce based on multi-criteria to calculate satisfaction according to claim 2, wherein the specific method for obtaining the feature vector matrix of all suppliers in each non-price dimension by PCA extraction in step S2 includes the following steps:
s201, calculating a decentralized matrix X under a first non-price dimension;
s202, calculating a covariance matrix
Solving eigenvalues lambda and orthogonality of covariance matricesTransforming unit feature vector b;
s203, sorting the characteristic values in a descending order, lambda1≥λ2≥…≥λnCalculating the cumulative variance contribution rate, taking the minimum k value of which the cumulative variance contribution rate is greater than 90% as the number of the principal components, and extracting the principal components corresponding to the first k characteristic values to obtain a principal component space U; wherein 0<k<n and is a positive integer, and the cumulative variance contribution ratio is calculated by the formula:
s204, calculating to obtain a feature vector matrix B under a first non-price dimension, wherein the calculation formula is as follows: b ═ XU;
and S205, repeating the steps S201 to S204, and calculating to obtain the feature vector matrixes of all suppliers under all non-price dimensions.
4. The method for purchasing commerce based on multi-criteria calculation of satisfaction according to claim 3, wherein in said step S3, the integrity score of each supplier is calculated by the formula:
wherein HiRepresenting the integrity score of the ith supplier, b0jValue of the jth component of the original feature vector representing the honest dimension, bijA value representing a jth component of an ith vendor in a trustworthiness dimension;
the calculation formula of the strength score of each supplier is as follows:
wherein S isiIndicating the strength score of the ith supplier, dojRepresenting a dimension of forceValue of jth component of original feature vector, dijA value representing the jth component of the ith supplier in the real dimension;
the calculation formula of the informatization scores of each supplier is as follows:
wherein, TiAn informationized score representing the ith supplier, e0jValue of the jth component of the original feature vector representing the informatization dimension, eijA value representing a jth component of an ith vendor in the informatization dimension;
the calculation formula of the activity score of each supplier is as follows:
wherein A isiIndicating the liveness score of the ith supplier, f0jValue of the j-th component of the original feature vector representing the liveness dimension, dijA value representing a jth component of an ith supplier in an activity dimension;
the calculation formula of the customer satisfaction score of each supplier is as follows:
wherein, CiRepresents the customer satisfaction score, q, of the ith supplier0jValue of jth component of original feature vector representing customer satisfaction dimension, qijA value representing the jth component of the ith vendor in the customer satisfaction dimension.
5. The method for purchasing commerce based on multi-criteria calculation of satisfaction according to claim 1, wherein in said step S4, the calculation formula of the price score of each supplier is:
wherein, PiRepresents the price score, x, of the ith supplierijIndicates the supply quantity, x, of the ith supplier in the jth procurement planmkRepresenting the supply of k suppliers in the mth procurement plan.
6. The method for purchasing commerce based on multiple criteria to calculate satisfaction degree of claim 2, wherein in step S5, the calculation process of the comprehensive satisfaction degree of the purchaser to each supplier specifically includes the following steps:
s501, obtaining scores of buyers for all dimensions and requiring Score0＝[H0,S0,T0,A0,C0,P0]Where the buyer's Score is required for each dimension0The evaluation average value of all the dimensions of all the suppliers in the purchase history of the buyer on the platform is shown;
s502, calculating the scores of all suppliers in all non-price dimensions and the Euclidean distance values between the price scores and the score requirements of the buyers, and adding all the Euclidean distance values to obtain the sum of the distance values between all the suppliers and the buyers;
s503, calculating the comprehensive satisfaction of the buyer to each supplier, wherein the calculation formula is as follows:
wherein s isiIndicating the combined satisfaction of the buyer with the ith supplier, diRepresenting the sum of the distance values between the ith supplier and the buyer.
7. The business adoption of claim 6 for calculating satisfaction based on multiple criteriaThe purchasing method is characterized in that, in step S501, a user who first purchases on a platform sets the initial value of the rating requirement of each dimension to: score0＝[0.6,0.6,0.6,0.6,0.6,0.6]。
8. The method of claim 1, wherein the values of M and N are both 10, and the threshold value of the overall satisfaction is 70%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010636005.9A CN111967927A (en) | 2020-07-03 | 2020-07-03 | Commercial purchasing method for calculating satisfaction degree through multiple criteria |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010636005.9A CN111967927A (en) | 2020-07-03 | 2020-07-03 | Commercial purchasing method for calculating satisfaction degree through multiple criteria |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111967927A true CN111967927A (en) | 2020-11-20 |
Family
ID=73362194
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010636005.9A Pending CN111967927A (en) | 2020-07-03 | 2020-07-03 | Commercial purchasing method for calculating satisfaction degree through multiple criteria |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111967927A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112465389A (en) * | 2020-12-12 | 2021-03-09 | 广东电力信息科技有限公司 | Word frequency-based similar provider recommendation method and device |
| CN115187107A (en) * | 2022-07-21 | 2022-10-14 | 深圳市企企通科技有限公司 | Intelligent allocation method and device for purchasing demand, computer equipment and storage medium |
| CN117391583A (en) * | 2023-10-23 | 2024-01-12 | 南京鑫智链科技信息有限公司 | Purchasing data management method and platform |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104766181A (en) * | 2015-04-28 | 2015-07-08 | 上海海事大学 | Chemical enterprise purchasing management decision support system based on GIS |
| CN106875137A (en) * | 2015-12-14 | 2017-06-20 | 何怀泽 | A kind of procurement decisions optimization method and system |
| CN106952052A (en) * | 2017-04-06 | 2017-07-14 | 东北林业大学 | Based on hybrid weight core principle component analysis enterprise supplier evaluation method |
| CN107491897A (en) * | 2017-08-31 | 2017-12-19 | 四川长虹电器股份有限公司 | The method of supplier's commodity evaluation |
| CN108470245A (en) * | 2018-03-13 | 2018-08-31 | 山东理工职业学院 | A kind of computer network system for enterprise purchasing management |
-
2020
- 2020-07-03 CN CN202010636005.9A patent/CN111967927A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104766181A (en) * | 2015-04-28 | 2015-07-08 | 上海海事大学 | Chemical enterprise purchasing management decision support system based on GIS |
| CN106875137A (en) * | 2015-12-14 | 2017-06-20 | 何怀泽 | A kind of procurement decisions optimization method and system |
| CN106952052A (en) * | 2017-04-06 | 2017-07-14 | 东北林业大学 | Based on hybrid weight core principle component analysis enterprise supplier evaluation method |
| CN107491897A (en) * | 2017-08-31 | 2017-12-19 | 四川长虹电器股份有限公司 | The method of supplier's commodity evaluation |
| CN108470245A (en) * | 2018-03-13 | 2018-08-31 | 山东理工职业学院 | A kind of computer network system for enterprise purchasing management |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112465389A (en) * | 2020-12-12 | 2021-03-09 | 广东电力信息科技有限公司 | Word frequency-based similar provider recommendation method and device |
| CN115187107A (en) * | 2022-07-21 | 2022-10-14 | 深圳市企企通科技有限公司 | Intelligent allocation method and device for purchasing demand, computer equipment and storage medium |
| CN115187107B (en) * | 2022-07-21 | 2024-05-10 | 深圳市企企通科技有限公司 | Intelligent purchasing demand distribution method and device, computer equipment and storage medium |
| CN117391583A (en) * | 2023-10-23 | 2024-01-12 | 南京鑫智链科技信息有限公司 | Purchasing data management method and platform |
| CN117391583B (en) * | 2023-10-23 | 2024-04-05 | 南京鑫智链科技信息有限公司 | Purchasing data management method and platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109063945B (en) | Value evaluation system-based 360-degree customer portrait construction method for electricity selling company | |
| CN111967927A (en) | Commercial purchasing method for calculating satisfaction degree through multiple criteria | |
| Şen et al. | Pre-selection of suppliers through an integrated fuzzy analytic hierarchy process and max-min methodology | |
| Hsu | Using a decision-making process to evaluate efficiency and operating performance for listed semiconductor companies | |
| KR100746107B1 (en) | Cross correlation tool for automated portfolio descriptive statistics | |
| CN101329683A (en) | Recommendation system and method | |
| CN111489180A (en) | Reference information generation method, system and device | |
| CN110826886A (en) | Electric power customer portrait construction method based on clustering algorithm and principal component analysis | |
| CN111192161A (en) | Electric power market trading object recommendation method and device | |
| CN111784109A (en) | Supplier selection method based on Bidagolas fuzzy set and VIKOR | |
| Xuefeng et al. | Predicting the final prices of online auction items | |
| Blois | The manufacturing/marketing orientation and its information needs | |
| CN111507782A (en) | User loss attribution focusing method and device, storage medium and electronic equipment | |
| CN111861679A (en) | Commodity recommendation method based on artificial intelligence | |
| CN114723535A (en) | Supply chain and knowledge graph-based item recommendation method, equipment and medium | |
| Chou et al. | The RFM Model Analysis for VIP Customer: A case study of golf clothing brand | |
| CN110020918B (en) | Recommendation information generation method and system | |
| CN112163781A (en) | Park electricity utilization group life cycle evaluation method based on multi-dimensional index clustering | |
| Sobhanallahi et al. | An aggregated supplier selection method based on QFD and TOPSIS (case study: A financial institution) | |
| Aghdaie | Data mining group decision-making with FAHP: An application in supplier evaluation and segmentation | |
| CN116012086A (en) | Commodity price estimating method, commodity price estimating device, electronic equipment and storage medium | |
| CN115344767A (en) | Supplier evaluation method based on network data | |
| Zheng | Application of silence customer segmentation in securities industry based on fuzzy cluster algorithm | |
| CN114418318A (en) | Generation method of priority queue of purchasing task | |
| CN111768139B (en) | Stock processing method, apparatus, device and storage medium |
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 |