CN114757730A - Supplier recommendation method based on intelligent supply chain platform - Google Patents

Supplier recommendation method based on intelligent supply chain platform Download PDF

Info

Publication number
CN114757730A
CN114757730A CN202210297364.5A CN202210297364A CN114757730A CN 114757730 A CN114757730 A CN 114757730A CN 202210297364 A CN202210297364 A CN 202210297364A CN 114757730 A CN114757730 A CN 114757730A
Authority
CN
China
Prior art keywords
index
supplier
indexes
evaluation system
weight
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210297364.5A
Other languages
Chinese (zh)
Inventor
刘霞凤
郭永江
郝鹏
杨海春
韩龙
李洪雷
王聪
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Liantong Shandong Industry Internet Co ltd
Original Assignee
Liantong Shandong Industry Internet Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Liantong Shandong Industry Internet Co ltd filed Critical Liantong Shandong Industry Internet Co ltd
Priority to CN202210297364.5A priority Critical patent/CN114757730A/en
Publication of CN114757730A publication Critical patent/CN114757730A/en
Pending legal-status Critical Current

Links

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]
    • G06Q30/0609—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]
    • G06Q30/0631—Item recommendations

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 computer application, and particularly relates to a supplier recommendation method based on an intelligent supply chain platform. The method divides the traditional supplier evaluation system into a dominant evaluation system and a recessive evaluation system for the first time, gives new weight assignment according to the characteristics of the dominant evaluation system and the recessive evaluation system, and ensures the stability of the weight by using a combined assignment method of subjective assignment and objective assignment, thereby ensuring the accuracy of a recommendation result.

Description

Supplier recommendation method based on intelligent supply chain platform
Technical Field
The invention belongs to the technical field of computer application, and particularly relates to a supplier recommendation method based on an intelligent supply chain platform.
Background
Currently, both the world and China are in a key phase of great development, great change and great adjustment. From the world, a new round of scientific and technological revolution and industry transformation and inoculation are raised, the contradiction between resource element configuration and the contradiction between industry structures related to old kinetic energy are more prominent, and the world economic pattern is in deep adjustment. From the country, the economic development of China enters a new era, and the basic characteristic is that the economy is shifted from a high-speed growth stage to a high-quality development stage. Driven by the dual purposes of technological innovation and system innovation, the original economic pattern is changing, intelligent manufacturing, internet plus, big data, cloud computing, digital economy, shared economy and the like related to new kinetic energy are rapidly developed, and more support is provided for high-quality development. In a new round of economic structure change and new and old kinetic energy conversion, traditional enterprises face significant challenges and opportunities, especially industrial and manufacturing enterprises. The industry and the manufacturing industry are both the national pillar industry and are the key targets of the economic optimization and the industrial revolution, so that how industrial and manufacturing enterprises adapt to the development trend to carry out self-transformation upgrading is particularly necessary.
Most of the Chinese manufacturers still use the traditional method to carry out purchasing work. The traditional enterprise purchasing has a set of inherent flow, and after the purchasing requirement is proposed, the purchasing department can summarize various requirements and search for proper products and suppliers. Then, a relatively long bid inviting process is carried out, and the purchasing process can be completed through ordering and receiving.
In addition, material purchasing of a plurality of companies is usually mastered in one department or the hands of a plurality of people or even one person at present, a powerful supervision and restriction mechanism is lacked, the purchasing department is usually used as a single functional department and carries out work relatively independently, and the whole effective information communication is lacked in the purchasing process. Once a certain link fails in understanding and communicating information, repeated purchase and overstock of materials can be caused.
The following is summarized as follows: the method has the advantages that the enterprise market information is not flexible, the inventory risk is large, the purchasing period is long, the purchasing link is difficult to monitor, benefit is driven, the operation is performed in a dark box, and the corruption hotbed is realized; the production department is disjointed from the purchasing department, which causes large inventory and occupies a large amount of mobile capital. The condition that the normal operation of production and operation activities of enterprises is influenced due to insufficient supply and demand can also occur, the cost is high, and the economic benefit of the enterprises is influenced.
Therefore, new technologies such as cloud computing and big data are combined with enterprise purchasing, and the intelligent supply chain platform which is used for getting through all links of the supply chain in an online shopping mall mode is a new choice of the existing enterprise, so that the purchasing cost can be effectively reduced, the purchasing efficiency is improved, the whole process is more transparent and more standard, and a powerful support is provided for transformation and upgrading of the whole enterprise. How to combine with user preferences and more accurately recommend supply and demand to users is a problem which needs to be solved by the intelligent supply chain platform at present.
Disclosure of Invention
Aiming at the recommendation problem of suppliers in the intelligent supply chain platform, the invention provides the supplier recommendation method based on the intelligent supply chain platform, which is reasonable in design, simple in method and capable of effectively improving recommendation efficiency.
In order to achieve the above object, the present invention provides a supplier recommendation method based on an intelligent supply chain platform, including the following steps:
a. firstly, constructing a supplier evaluation system, and dividing the evaluation system into an explicit evaluation system and an implicit evaluation system according to the product quality provided by a supplier and the company environment of the supplier, wherein the explicit evaluation system and the implicit evaluation system are three-level rating indexes, and the three-level rating index is a primary index, a secondary index branched by the primary index and a tertiary index branched by the secondary index;
b. index quantization is carried out on the three-level indexes by adopting an index quantization method, and normalization processing is carried out on the quantized indexes;
c. determining the weight of the three-level index from the subjective direction and the objective direction by adopting an analytic hierarchy process and an entropy weight method, then, taking the distance index as a composite weight, and obtaining the final three-level index weight after normalization;
d. if the user has historical search data, determining the superposed three-level indexes of different suppliers of the searched similar products as recommendation indexes according to the historical search data of the user, and if the user does not have the historical search data, determining the superposed three-level indexes of the different suppliers of the similar products as recommendation indexes according to the habit of other users of the similar products for selecting suppliers;
e. according to the formula:
RT＝λ(ωx1a1+ωx2a2+.....+ωxnan)+(1-λ)(ωy1b1+ωy2b2+.....+ωynbn)
calculating the recommended values of suppliers, and recommending to users according to the recommended values in a sequence, wherein lambda is the proportion of the recommended indexes of the explicit evaluation system in the recommended indexes in all the recommended indexes, and omega isxnIs a recommendation index a in an explicit evaluation systemnWeight value of anIs a recommended index in an explicit evaluation system, omegaynRecommending index b in a recessive evaluation systemnWeight value of (b)nIs a recommended index in a recessive evaluation system.
Preferably, the explicit evaluation system includes three primary indexes, i.e., a product quality index for evaluating product quality, a product price index for evaluating product price, and a delivery condition index for evaluating product distribution information.
Preferably, the implicit evaluation system comprises three primary indexes of a supplier company environment index for evaluating the information of the supplier company, a supplier ecological development index for evaluating the management operation condition of the supplier and a supplier company service index for evaluating the service capability of the supplier company.
Preferably, in the step b, the normalization processing method includes:
b1, constructing a multi-index multi-supplier decision matrix,
the supplier evaluation system has m suppliers, i indexes, and the jth supplier (j is 1,2,.., m) has a jth index (v is 1,2,.., i) value of ZvjThen, the multi-index multi-supplier decision matrix is:
Figure BDA0003562096310000031
b2, let gjvNormalizing the processed value, Z, for the v index of the j suppliervjIs the value of the v index of the j supplier, m is the number of suppliers, and the normalized value is:
Figure BDA0003562096310000032
preferably, in the step c, according to the formula:
Figure BDA0003562096310000033
calculating the composite weight rho of the three-level index vvWherein, deltavIs the weight of a tertiary index v, gamma, obtained by an analytic hierarchy processvThe weight of the three-level index v is obtained by adopting an entropy weight method.
Preferably, in the step c, according to the formula:
Figure BDA0003562096310000041
calculating a normalized value of the complex weight, wherein muvIs the final weight value, rho, of the three-level index vvI is the composite weight of the three-level index v, and i is the number of the three-level indexes.
Compared with the prior art, the invention has the advantages and positive effects that,
1. the invention provides a supplier recommendation method based on an intelligent supply chain platform, which is characterized in that a traditional supplier evaluation system is divided into a dominant evaluation system and a recessive evaluation system for the first time, new weight assignment is given according to the characteristics of the dominant evaluation system and the recessive evaluation system, and the stability of weight is ensured by utilizing a combination assignment method of subjective assignment and objective assignment, so that the accuracy of a recommendation result is ensured.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, the present invention will be further described with reference to the following examples. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and thus the present invention is not limited to the specific embodiments of the present disclosure.
In embodiment 1, this embodiment provides a method for recommending suppliers based on an intelligent supply chain platform, which aims to improve the accuracy of suppliers with respect to users and reduce the problem of excessive data when users search for suppliers, and for this reason, the method for recommending suppliers based on an intelligent supply chain platform according to this embodiment first constructs a supplier evaluation system, and only better understanding and management of suppliers can make corresponding recommendations according to the needs of users, and the supplier evaluation system is an important way for suppliers to understand and manage, and is different from the conventional supplier evaluation system that integrates all supplier indexes together, in this embodiment, the evaluation system is classified into an explicit evaluation system and an implicit evaluation system according to the product quality provided by suppliers and the company environment of suppliers, because in the platform constructed supplier evaluation system, the evaluation system is formed mainly by adopting an expert scoring mode, and since experts cannot represent all users, the recommendation accuracy is poor when recommending, for example, one user is more concerned about the information such as the popularity of a supplier of a product, personnel and the like, but not about the quality, and the experts are more concerned about the quality of the product, so that the evaluation index of the user is low on the contrary, and the user is difficult to recommend to the supplier meeting the intention of the user. For this reason, in the present embodiment, the situation of the supplier itself is assigned to the implicit evaluation hierarchy, and the related situation of the product is assigned to the explicit evaluation hierarchy.
In order to ensure the accuracy of the weight, in this embodiment, the explicit evaluation system and the implicit evaluation system are three-level rating indexes, and a first-level index, a second-level index branched by the first-level index, and a third-level index branched by the second-level index are compared with a tree in terms of the three-level rating.
The explicit evaluation system comprises product quality indexes for evaluating the product quality, wherein the product quality indexes are mainly based on the product quality, for example, for a steel plate, the first-level quality indexes are surface quality, process performance, mechanical property, surface quality and the like, the second-level indexes of the surface quality are surface defects, reflectivity and the like, the third-level indexes of the surface defects are roller marks, scratches, pockmarks and the like, therefore, the product quality indexes are technical indexes related to products, the product price indexes for evaluating the product price comprise first-level indexes of postage price, product price and the like, the postage price indexes comprise second-level price indexes of land transportation, air transportation and sea transportation, and the second-level price indexes comprise third-level price indexes of different times; the product delivery condition indexes used for evaluating the product logistics information comprise on-time delivery and inaccurate delivery, and the on-time delivery has the indexes of packaging quality, damage rate and the like.
The recessive evaluation system comprises three first-level indexes of a supplier company environment index for evaluating the information of the supplier company, a supplier ecological development index for evaluating the management operation condition of the supplier and a supplier company service index for evaluating the service capability of the supplier, wherein the supplier company environment index comprises two-level indexes of human resources, enterprise system, credit, financial status and the like, the financial status comprises three-level indexes of asset load rate, snap rate, capital operation capability, net asset earning rate and the like, the supplier ecological development index comprises two-level indexes of enterprise information management capability, enterprise production management capability and the like, the enterprise information management capability comprises three-level indexes of management information system construction level, information sharing integration capability and the like, the supplier company service index comprises two-level indexes of technical innovation capability, service operation and maintenance capability, environment protection capability and the like, the technical innovation capability has three-level indexes such as new product development rate, technical intensity and the like, in the indexes, the embodiment is only simply exemplified, different products and developers have different indexes, of course, the indexes can be continuously added according to the supply condition, and the indexes are distributed to a corresponding explicit evaluation system or a implicit evaluation system based on the functions of the indexes.
Determining an explicit evaluation system and a implicit evaluation system, then, performing index quantization on three-level indexes by adopting an index quantization method, and performing normalization processing on the quantized indexes, wherein the index quantization is to quantitatively score the indexes of different indexes in an expert scoring manner, and since the scores of different products are different, the quantized indexes need to be normalized for accurate calculation.
In this embodiment, the normalization processing method includes:
firstly, constructing a multi-index multi-supplier decision matrix:
suppose that the supplier evaluation system has m suppliers, i indexes, j-th supplier (j ═ 1,2,., m)
Has a value Z for the v-th index (v-1, 2, i)vjThen, the multi-index multi-supplier decision matrix is:
Figure BDA0003562096310000061
then, let gjvNormalize the processed value, Z, for the jth index of the jth vendorvjIs the value of the v index of the j supplier, m is the number of suppliers, and the normalized value is:
Figure BDA0003562096310000062
the normalization processing is beneficial to ensuring that the difference of the calculation results is small.
Then, adoptDetermining the weight delta of the three-level index from the subjective and objective directions by using the analytic hierarchy process and the entropy weight methodvAnd gammavCurrently, the commonly used subjective weighting methods include: a least squares method, a binomial coefficient method, an expert survey method (Delphi method), a pairwise comparison method, an analytic hierarchy process (AHP method), and the like. The subjective weighting method has the advantages that the knowledge and engineering experience of experts are fully utilized, the experts can make common sense empirical judgment on actual decision problems, and the determined target weights are almost the same as the actual conditions; the method has the disadvantages that the calculation result has strong subjective randomness, does not have objective theory and has limitation in practical application. The currently commonly used objective weighting methods include: a feature vector method, a dispersion method, an entropy weight method, a mean square error method, a principal component analysis method, a multi-objective programming method, a correlation coefficient method, a variation coefficient method and the like. The objective weighting method has the advantages that the intention of people is not transferred, the weight is calculated according to objective data of a target, the method has strong dialectical property, meanwhile, the objective weighting method does not increase the burden of a decision-making analyst, the method has scientific mathematical theory basis as support, and the big data analysis is convenient to carry out; the method has the disadvantages that enough sample data and an actual problem library are required to be used as supports, the difficulty of collecting the sample data is increased, the attention degree of a decision maker to different targets cannot be reflected, and the situation that the determined index weight is greatly deviated from the subjective intention of decision making or the actual situation can occur.
Therefore, in consideration of the problems of the analytic hierarchy process and the entropy weight process, in this embodiment, the distance index is used as the composite weight, and the final three-level index weight is obtained after normalization, and the specific operations are as follows:
according to the formula:
Figure BDA0003562096310000071
calculating the composite weight rho of the three-level index vvWherein, deltavIs the weight of a tertiary index v, gamma, obtained by an analytic hierarchy processvThe weight of the three-level index v obtained by the entropy weight method is adopted.
Preferably, in the step c, according to the formula:
Figure BDA0003562096310000072
calculating a normalized value of the complex weight, wherein muvIs the final weight value of the three-level index v, rhovI is the composite weight of the three-level index v, and i is the number of the three-level indexes.
Therefore, after normalization processing is carried out by using the composite weight, the obtained weight can be more accurate.
After the weight is determined, the condition that the user selects the suppliers needs to be judged, namely, if the user has historical search data, the superposed three-level indexes of different suppliers of the searched similar products are determined as recommendation indexes according to the historical search data of the user, because the superposed three-level indexes are some indexes which are more interesting to the user, the recommendation can be accurately carried out through the indexes, and if the user does not have the historical search data, the superposed three-level indexes of different suppliers of the similar products in the habit of selecting the suppliers of other users of the similar products are determined as the recommendation indexes.
Finally, according to the formula:
RT＝λ(ωx1a1+ωx2a2+.....+ωxnan)+(1-λ)(ωy1b1+ωy2b2+.....+ωynbn)
calculating the recommended value of a supplier, and recommending the user according to the recommended value in a sorting manner, wherein lambda is the proportion of the recommended indexes of the explicit evaluation system in all the recommended indexes, and lambda is the reason for dividing the evaluation indexes into the explicit evaluation indexes and the implicit evaluation indexes in the embodiment, and assigning the recommended indexes again according to the search habits of the user, wherein 20 recommended indexes of one user are assumed, and if only one index in the explicit evaluation system exists, lambda is 1/20, i.e., the user has less requirements on quality, so that 1-lambda gives more weight to the implicit evaluation indexes, and the recommendation accuracy is higher.
In the above formula, ω isxnIs a recommended index a in a dominant evaluation systemnWeight value of anIs a recommended index in an explicit evaluation system, omegaynRecommending index b in a recessive evaluation systemnWeight value of (b)nIs a recommended index in a recessive evaluation system.
By the method provided by the embodiment, the contradiction between experts and users is solved, and the experts are more personalized and attentive, so that the recommendation accuracy is improved.
The above description is only a preferred embodiment of the present invention, and not intended to limit the present invention in other forms, and any person skilled in the art may apply the above modifications or changes to the equivalent embodiments with equivalent changes, without departing from the technical spirit of the present invention, and any simple modification, equivalent change and change made to the above embodiments according to the technical spirit of the present invention still belong to the protection scope of the technical spirit of the present invention.

Claims (6)

1. A supplier recommendation method based on an intelligent supply chain platform is characterized by comprising the following steps:
a. firstly, constructing a supplier evaluation system, and dividing the evaluation system into an explicit evaluation system and an implicit evaluation system according to the product quality provided by a supplier and the company environment of the supplier, wherein the explicit evaluation system and the implicit evaluation system are three-level rating indexes, and the three-level rating index is a primary index, a secondary index branched by the primary index and a tertiary index branched by the secondary index;
b. index quantization is carried out on the three-level indexes by adopting an index quantization method, and normalization processing is carried out on the quantized indexes;
c. determining the weight of a three-level index from subjective and objective directions by adopting an analytic hierarchy process and an entropy weight process, then, taking a distance index as a composite weight, and normalizing to obtain the final three-level index weight;
d. if the user has historical search data, determining the superposed three-level indexes of different suppliers of the searched similar products as recommendation indexes according to the historical search data of the user, and if the user does not have the historical search data, determining the superposed three-level indexes of different suppliers of the similar products as recommendation indexes according to habits of other users of the similar products in selecting suppliers;
e. according to the formula:
RT＝λ(ωx1a1+ωx2a2+.....+ωxnan)+(1-λ)(ωy1b1+ωy2b2+.....+ωynbn)
calculating the recommended values of suppliers, and recommending to users according to the recommended values in a sequence, wherein lambda is the proportion of the recommended indexes of the explicit evaluation system in the recommended indexes in all the recommended indexes, and omega isxnIs a recommendation index a in an explicit evaluation systemnWeight value of (a)nAs a recommendation index in a dominant evaluation system, ωynRecommending index b in a recessive evaluation systemnWeight value of (b)nIs a recommended index in a recessive evaluation system.
2. The intelligent supply chain platform-based supplier recommendation method according to claim 1, wherein the explicit evaluation system comprises three primary indexes of a product quality index for evaluating product quality, a product price index for evaluating product price, and a product delivery condition index for evaluating product logistics information.
3. The intelligent supply chain platform-based supplier recommendation method of claim 2, wherein the implicit evaluation system comprises three primary indexes of a supplier company environment index for evaluating the information of the supplier company, a supplier ecological development index for evaluating the management operation condition of the supplier and a supplier company service index for evaluating the service capability of the supplier.
4. The intelligent supply chain platform-based supplier recommendation method according to claim 1, wherein in the step b, the normalization processing method is:
b1, constructing a multi-index multi-supplier decision matrix,
the supplier evaluation system has m suppliers, i indexes, and the jth supplier (j is 1,2,.., m) has a jth index (v is 1,2,.., i) value of ZvjThen, the multi-index multi-supplier decision matrix is:
Figure FDA0003562096300000021
b2, let gjvNormalize the processed value, Z, for the jth index of the jth vendorvjIs the value of the v index of the j supplier, m is the number of suppliers, and the normalized value is:
Figure FDA0003562096300000022
5. the intelligent supply chain platform based supplier recommendation method according to claim 1, wherein in the step c, according to the formula:
Figure FDA0003562096300000023
calculating the composite weight rho of the three-level index vvWherein, deltavIs the weight of the tertiary index v, gamma, obtained by an analytic hierarchy processvThe weight of the three-level index v obtained by the entropy weight method is adopted.
6. The intelligent supply chain platform based supplier recommendation method according to claim 6, wherein in the step c, according to the formula:
Figure FDA0003562096300000024
calculating a normalized value of the complex weight, wherein muvIs the final weight value of the three-level index v, rhovI is the composite weight of the three-level index v, and i is the number of the three-level indexes.
CN202210297364.5A 2022-03-24 2022-03-24 Supplier recommendation method based on intelligent supply chain platform Pending CN114757730A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210297364.5A CN114757730A (en) 2022-03-24 2022-03-24 Supplier recommendation method based on intelligent supply chain platform

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210297364.5A CN114757730A (en) 2022-03-24 2022-03-24 Supplier recommendation method based on intelligent supply chain platform

Publications (1)

Publication Number Publication Date
CN114757730A true CN114757730A (en) 2022-07-15

Family

ID=82326418

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210297364.5A Pending CN114757730A (en) 2022-03-24 2022-03-24 Supplier recommendation method based on intelligent supply chain platform

Country Status (1)

Country Link
CN (1) CN114757730A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117474426A (en) * 2023-12-27 2024-01-30 四川丝路易购科技有限公司 Block chain-based trade supply chain recommendation method and device

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108241932A (en) * 2018-01-24 2018-07-03 国网山东省电力公司泰安供电公司 A kind of method for building up of electricity provider evaluation model
CN110619444A (en) * 2018-06-19 2019-12-27 顺丰科技有限公司 Service outsourcing supplier set evaluation method and application
CN112686482A (en) * 2019-10-17 2021-04-20 株式会社日立制作所 Supplier evaluation device and supplier evaluation method
CN113537728A (en) * 2021-06-24 2021-10-22 上海阿法析地数据科技有限公司 Intelligent recommendation system and recommendation method based on business recruitment in industrial park

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108241932A (en) * 2018-01-24 2018-07-03 国网山东省电力公司泰安供电公司 A kind of method for building up of electricity provider evaluation model
CN110619444A (en) * 2018-06-19 2019-12-27 顺丰科技有限公司 Service outsourcing supplier set evaluation method and application
CN112686482A (en) * 2019-10-17 2021-04-20 株式会社日立制作所 Supplier evaluation device and supplier evaluation method
CN113537728A (en) * 2021-06-24 2021-10-22 上海阿法析地数据科技有限公司 Intelligent recommendation system and recommendation method based on business recruitment in industrial park

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117474426A (en) * 2023-12-27 2024-01-30 四川丝路易购科技有限公司 Block chain-based trade supply chain recommendation method and device
CN117474426B (en) * 2023-12-27 2024-04-26 四川丝路易购科技有限公司 Block chain-based trade supply chain recommendation method and device

Similar Documents

Publication Publication Date Title
Govindan et al. An integrated decision making model for the selection of sustainable forward and reverse logistic providers
Liao et al. Integrated FAHP, ARAS-F and MSGP methods for green supplier evaluation and selection
Karasan et al. Prioritization of production strategies of a manufacturing plant by using an integrated intuitionistic fuzzy AHP & TOPSIS approach
Li et al. A fuzzy inhomogenous multiattribute group decision making approach to solve outsourcing provider selection problems
Karami et al. Supplier selection and evaluation in the garment supply chain: An integrated DEA–PCA–VIKOR approach
Chatterjee et al. Supplier selection in Telecom supply chain management: a Fuzzy-Rasch based COPRAS-G method
Liu et al. A supplier evaluation model based on customer demand in blockchain tracing anti-counterfeiting platform project management
CN109754191A (en) A kind of intelligent supply chain management platform of the one-stop sale of medium-sized and small enterprises
Khanmohammadi et al. Drawing a strategy canvas using the fuzzy best–worst method
CN111242471A (en) Index system for selecting selling enterprises in supply chain with farmer cooperative as leading factor
Yaghin et al. Order allocation and procurement transport planning in apparel supply chain: A utility-based possibilistic-flexible programming approach
Tavana et al. An integrated and comprehensive fuzzy multicriteria model for supplier selection in digital supply chains
Lau et al. A hybrid multi-criteria decision model for supporting customer-focused profitability analysis
Yao et al. Evaluation of informatization performance of construction industrialization EPC enterprises in China
Qi et al. An artificial-intelligence-enabled sustainable supply chain model for B2C E-commerce business in the international trade
CN114757730A (en) Supplier recommendation method based on intelligent supply chain platform
Wright Supply chain strategies of manufacturers in Romania
Li et al. Optimization and system implementation of fuzzy integrated algorithm model for logistics supply chain under supply and demand uncertainty background
CN110310012A (en) Data analysing method, device, equipment and computer readable storage medium
Zhang Modular configuration of service elements based on the improved K‐means algorithm
CN115344767A (en) Supplier evaluation method based on network data
KR101853555B1 (en) SW Market Information Service System
Fang et al. Data mining technology and its Application In CRM of Commercial Banks
Wang An exploration of sustainable customer value and the procedure of the intelligent digital content analysis platform for big data using dynamic decision making
Bian Evaluation of WeMedia ads marketing based on the demand of internet economy

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