E-commerce platform supplier management method and system based on big data analysis

Abstract

The invention provides an e-commerce platform supplier management method and system based on big data analysis, and the method comprises the steps: carrying out the attribute analysis of each supplier in a to-be-evaluated and analyzed supplier set, and endowing each supplier with a corresponding attribute tag, so as to obtain a first supplier set; forming a plurality of virtual supply chains according to the first supplier set; sequentially carrying out demand matching on each virtual supply chain to determine key business demands of the e-commerce platform user on each link of the supply chain; creating a supplier evaluation index database, and obtaining a supply chain collaborative optimization result corresponding to each virtual supply chain according to the supplier evaluation index database; and taking the virtual supply chain corresponding to the supply chain collaborative optimization result with the highest score as the current available supply chain. According to the method, comprehensive analysis is carried out from multiple supply chain total utility demand dimensions, comprehensive analysis of supplier evaluation is realized, the method is more practical, and improvement of objective reliability of analysis results is facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of supplier evaluation, and in particular, to an e-commerce platform supplier management method and system based on big data analysis. Background Art

[0002] As a new business model, e-commerce has rapidly integrated with the real economy. The emergence of e-commerce platforms has brought great convenience to people's lives. Informatization and networking have injected new vitality into e-commerce platforms and become an important force in leading economic and social development. E-commerce has also developed from the earliest traditional e-commerce to various market segments. These market segments are no longer limited to industries such as clothing and food, but also include industries such as aviation, medicine, agricultural assistance, and fresh food. In the process of e-commerce transactions, suppliers play a key role in upstream transactions.

[0003] With the development of the market economy, competition between e-commerce companies and suppliers has become increasingly fierce. Competition between e-commerce companies has gradually evolved into competition in the supply chain. The level of management of suppliers by e-commerce companies directly affects whether the entire supply chain can win in the market competition.

[0004] Suppliers refer to the channel providers who provide the required materials and products to manufacturers or sellers, so that they can produce specific goods or provide services. Of course, suppliers can exist in various forms of companies or individuals. In the entire supply chain, suppliers, as the starting point, have input functions and play an important role. Their performance will in turn affect the performance of the entire supply chain. Therefore, the research on supplier selection and evaluation is of great significance to improving the potential competitiveness of enterprises and the efficiency of the entire supply chain. Suppliers play an important role in the entire supply chain. They can serve as both the starting point of materials and the end point of information flow. The evaluation of suppliers combined with segmented e-commerce platforms is a direction worthy of research, which has important research significance for promoting the development of e-commerce platforms.

[0005] Research on traditional management technologies such as supplier selection and evaluation has aroused discussion and widespread attention from experts, and has achieved certain results. However, the rapid development of e-commerce has brought greater challenges to supplier selection and evaluation. In the e-commerce environment based on information technology, enterprises and researchers have gradually realized that the research value of supplier selection evaluation is crucial. However, traditional supplier evaluation methods mainly rely on historical data and limited and fixed overall evaluation indicators for judgment. They lack real-time data support and appropriate dynamic evaluation indicators, making it difficult to accurately and objectively evaluate the tasks and performance of each supplier in the supply chain within a certain operating cycle. Summary of the invention

[0006] According to the technical problems raised above, a method and system for managing suppliers on an e-commerce platform based on big data analysis is provided. The present invention determines an evaluation system based on the key business requirements that each supplier needs to undertake in each link of the current supply chain, and uses the best supply chain collaborative optimization results among multiple potential supply chain organizational structures as the currently available supply chain, thereby performing a comprehensive analysis from multiple demand dimensions, and realizing a comprehensive and comprehensive analysis of supplier evaluation.

[0007] The technical means adopted by the present invention are as follows:

[0008] An e-commerce platform supplier management method based on big data analysis, comprising:

[0009] S1. Integrate various types of suppliers into a set of suppliers to be evaluated and analyzed, perform attribute analysis on each supplier and assign attribute labels to each supplier to obtain a first set of suppliers;

[0010] S2, forming multiple virtual supply chains according to the first supplier set obtained in S1;

[0011] S3, matching the needs of each virtual supply chain in S2 in turn, and determining the business needs of e-commerce platform users in each link of the supply chain;

[0012] S4. Create a supplier evaluation index database, and obtain the supply chain collaborative optimization result corresponding to each virtual supply chain based on the supplier evaluation index database, wherein the supplier evaluation index database is used to provide a supplier evaluation index system for various types of key business requirements;

[0013] S5. The virtual supply chain corresponding to the supply chain collaborative optimization result with the highest score is used as the currently available supply chain to implement supplier management.

[0014] Furthermore, the specific implementation steps of S1 include:

[0015] S11. Analyze the attributes of each supplier in the supplier set to be evaluated and analyzed, and determine the role attributes of each supplier in each link of the supply chain;

[0016] S12, counting the number of suppliers belonging to each type of role attribute, and determining whether the number of suppliers belonging to each type of role attribute is 1;

[0017] If the number of suppliers is 1, the supplier is identified as a first-level contribution supplier, and a first attribute label is assigned to the supplier, wherein the first attribute label includes at least a role attribute and a first-level contribution attribute;

[0018] If the number of suppliers is not 1, the supplier is identified as a secondary contribution supplier and a second attribute label is assigned to the supplier, wherein the second attribute label includes at least a role attribute and a secondary contribution attribute;

[0019] S13. Form a first supplier set according to the attribute tag category, wherein the first supplier set includes a first-level contributing supplier sub-set and a second-level contributing supplier sub-set.

[0020] Furthermore, the step S2 specifically includes:

[0021] Based on the first supplier set, in accordance with the role attributes required by each link in the supply chain, each supplier in the first-level contribution supplier subset is preferentially configured. After the configuration is completed, each supplier in the second-level contribution supplier subset is randomly configured to form multiple virtual supply chains.

[0022] Furthermore, the business demand includes at least one demand or a combination of multiple demands among supply chain efficiency, supply chain cost and customer satisfaction.

[0023] Furthermore, the supplier evaluation index database includes at least: a supply chain efficiency supplier evaluation index system, a supply chain cost supplier evaluation index system, and a customer satisfaction supplier evaluation index system;

[0024] The supply chain efficiency supplier evaluation index system includes the following first-tier evaluation indicators: product quality, delivery timeliness, and supply chain flexibility; product quality includes: product qualification rate and return rate; delivery timeliness includes on-time delivery rate, average delivery time, and delivery delay rate; supply chain flexibility includes order response speed and emergency handling capability; the second-tier auxiliary evaluation indicators include information transparency, innovation capability, and supply chain cost; information transparency includes information sharing degree and product quality data accuracy; innovation capability includes product update capability; supply chain cost includes system logistics cost and system inventory holding cost;

[0025] The supply chain cost supplier evaluation index system includes the first-level evaluation indicators of procurement cost, logistics cost, inventory holding cost, order processing cost, return processing cost, and out-of-stock cost; the second-level auxiliary evaluation indicators include supplier management cost and quality problem cost; the logistics cost includes: transportation cost and distribution cost;

[0026] The customer satisfaction supplier evaluation index system includes the following first-level evaluation indicators: customer satisfaction, net recommendation rate, customer complaint rate, on-time delivery rate, return rate, and order accuracy rate; the second-level auxiliary evaluation indicators include customer retention rate and customer response time.

[0027] Furthermore, the step S4 specifically includes:

[0028] Based on the supplier evaluation index database, the supplier corresponding to a certain link in a virtual supply chain is evaluated to obtain supply chain collaborative optimization results, including:

[0029] S41. Collect and preprocess the data related to the evaluation indicators of the supplier based on big data technology; and determine the indicator values ​​corresponding to various evaluation indicator data according to the preprocessed evaluation indicator data;

[0030] S42, determining whether the dimension of the business demand to which the current supplier belongs is unique;

[0031] If the current supplier has only one business requirement, the weight of each indicator is determined according to the fuzzy analytic hierarchy process, and the fuzzy synthesis operator is used to conduct a comprehensive evaluation of the supplier. The comprehensive score of the supplier corresponding to a certain link in the virtual supply chain is determined according to the comprehensive evaluation result;

[0032] If the business demand of the current supplier is not unique, select the supplier evaluation index system corresponding to the business demand type of the supplier according to the fuzzy hierarchical analysis method, determine the weight of each index, and use the fuzzy synthesis operator to obtain the evaluation result of the supplier corresponding to the dimension, determine the weight of each dimension, and obtain the comprehensive score of the supplier corresponding to a certain link in the virtual supply chain;

[0033] S43. Obtain the comprehensive scores of suppliers at each link one by one, and determine the corresponding supply chain collaborative optimization results according to the total score.

[0034] The present invention also includes an e-commerce platform supplier management system based on big data analysis, including: a data collection unit, a first data acquisition unit, a second data acquisition unit, a collaborative optimization unit, and a result display unit, wherein:

[0035] The data collection unit is used to perform attribute analysis on each supplier in the supplier set to be evaluated and analyzed and assign a corresponding attribute label to each supplier to obtain a first supplier set;

[0036] The first data acquisition unit is used to form a plurality of virtual supply chains according to the first supplier set;

[0037] The second data acquisition unit is used to perform demand matching on each virtual supply chain in turn to determine the business needs of the e-commerce platform users in each link of the supply chain;

[0038] The collaborative optimization unit is used to create a supplier evaluation index database, and obtain a supply chain collaborative optimization result corresponding to each virtual supply chain based on the supplier evaluation index database;

[0039] The result display unit is used to display the virtual supply chain corresponding to the supply chain collaborative optimization result with the highest score as the currently available supply chain, thereby completing the organizational structure management of each supplier in the supply chain.

[0040] Compared with the prior art, the present invention has the following advantages:

[0041] The e-commerce platform supplier management method and system based on big data analysis provided by the present invention determines the evaluation system based on the key business needs that each supplier needs to undertake in each link of the current supply chain, and uses the best supply chain collaborative optimization result among multiple potential supply chain organizational structures as the currently available supply chain, thereby performing comprehensive analysis from multiple demand dimensions, realizing a comprehensive and comprehensive analysis of supplier evaluation, which is more in line with reality and is conducive to improving the objectivity and reliability of the analysis results.

[0042] The e-commerce platform supplier management method and system based on big data analysis provided by the present invention improve the overall efficiency and response speed of the supply chain, and realize the coordinated optimization and dynamic adjustment of each link of the supply chain.

[0043] Based on the above reasons, the present invention can be widely promoted in the field of supplier evaluation technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0045] Figure 1 This is a flow chart of the e-commerce platform supplier management method based on big data analysis in the present invention.

[0046] Figure 2 A schematic diagram of forming multiple virtual supply chains in an embodiment of the present invention.

[0047] Figure 3 This is a structural framework diagram of the e-commerce platform supplier management system based on big data analysis in the present invention. DETAILED DESCRIPTION

[0048] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0049] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0050] like Figure 1 As shown, the present invention provides an e-commerce platform supplier management method based on big data analysis, comprising:

[0051] S1. Integrate various types of suppliers into a set of suppliers to be evaluated and analyzed, perform attribute analysis on each supplier and assign attribute labels to each supplier to obtain a first set of suppliers;

[0052] Since the suppliers supporting the normal operation of e-commerce platforms involve various types and play different roles in each link of the supply chain network (i.e., classified by function / role), only by clarifying the role attributes of each supplier in each link of the supply chain can the efficient operation of the entire supply chain be guaranteed; preferably, a basic e-commerce platform supply chain may involve roles such as product suppliers, logistics and warehousing suppliers, and after-sales service suppliers; for a large e-commerce platform, the mature supply chain it needs may involve raw material suppliers (providing the raw materials needed to manufacture products), manufacturers / producers (responsible for processing raw materials into finished products or semi-finished products, which can be OEM or ODM), assemblers (assembling different components into final products), logistics and warehousing suppliers (providing transportation services, responsible for domestic and International transportation and / or warehousing services, managing inventory to ensure that goods can be supplied to e-commerce platforms in a timely manner), packaging suppliers (providing internal and external packaging services for products, including customized packaging design and production), quality inspection and certification agencies (conducting quality inspection and certification of products to ensure compliance with domestic and international standards), after-sales service providers (providing after-sales service support such as returns, exchanges, and repairs), technical support providers (providing technical support, such as software development, system integration, data analysis and other services), marketing and advertising service providers (helping e-commerce platforms with product promotion, brand building, etc.), payment solution providers (providing online payment solutions), etc.; what’s more, you can consider adding law firms and other companies or institutions that provide legal consulting services to the collection of suppliers to provide consulting services on regulatory compliance, intellectual property protection and other aspects to e-commerce platforms.

[0053] In specific implementation, as a preferred embodiment of the present invention, the specific implementation steps of S1 include:

[0054] S11. Analyze the attributes of each supplier in the supplier set to be evaluated and analyzed, and determine the role attributes of each supplier in each link of the supply chain;

[0055] The purpose of classifying and counting the supplier role attributes in the supplier set is to clarify whether the suppliers in each supply chain link are unique and irreplaceable. If so, in the subsequent task demand analysis, only the key role they play in the entire link needs to be considered. On the contrary, if there are multiple suppliers with little difference in this link (high substitutability), they can be evaluated and considered from multiple dimensions, so as to further improve the operational performance of the entire supply chain. For example, in the manufacturer link, if there is only one company whose products can meet the design indicators of the platform, it is only necessary to consider the quality of its supplied goods and whether the supply is timely, that is, the dimension of supply chain efficiency. For a large number of logistics and warehousing suppliers, the platform often pays more attention to the dimensions of supply chain cost and / or customer satisfaction.

[0056] S12, counting the number of suppliers belonging to each type of role attribute, and determining whether the number of suppliers belonging to each type of role attribute is 1;

[0057] If the number of suppliers is 1, the supplier is identified as a first-level contribution supplier, and a first attribute label is assigned to the supplier, wherein the first attribute label includes at least a role attribute and a first-level contribution attribute;

[0058] If the number of suppliers is not 1, the supplier is identified as a secondary contribution supplier and a second attribute label is assigned to the supplier, wherein the second attribute label includes at least a role attribute and a secondary contribution attribute;

[0059] S13. Form a first supplier set according to the attribute tag category, wherein the first supplier set includes a first-level contributing supplier sub-set and a second-level contributing supplier sub-set.

[0060] Distinguishing between two types of supplier sets can effectively facilitate the subsequent construction of a virtual supply chain, that is, in each virtual supply chain, all suppliers in the first-level contribution supplier subset should be covered, while the second-level contribution supplier subset should be randomly matched.

[0061] In addition to the role attribute Role and the contribution rate attribute contribution rate, the content of the attribute tag also includes the supplier's unique identifier SupplierID, the supplier's name Name, the product or service introduction Products, etc. In order to effectively manage and analyze the role of suppliers in their supply chains, a structured data format can be used to store this information; the optional method is to use a relational database table or a data structure in JSON (JavaScript Object Notation) format; for example, assume that there is a relational database that contains a table called Suppliers, which is used to store information about suppliers and their roles in the supply chain.

[0062]

[0063] S2, forming multiple virtual supply chains according to the first supplier set obtained in S1;

[0064] In specific implementation, as a preferred embodiment of the present invention, step S2 specifically includes:

[0065] Based on the first supplier set, in accordance with the role attributes required by each link in the supply chain, each supplier in the first-level contribution supplier subset is preferentially configured. After the configuration is completed, each supplier in the second-level contribution supplier subset is randomly configured to form multiple virtual supply chains.

[0066] like Figure 2 Assuming a basic e-commerce platform supply chain, the roles required in each link of the supply chain include product suppliers, logistics and warehousing suppliers, and after-sales service suppliers. The first-level contribution supplier subset includes product supplier A, the second-level contribution supplier subset includes logistics and warehousing suppliers B and C, and after-sales service suppliers D and E. Then four virtual supply chains are formed, namely ABD, ACD, ABE, and ACE.

[0067] S3, matching the needs of each virtual supply chain in S2 in turn, and determining the business needs of e-commerce platform users in each link of the supply chain;

[0068] In specific implementation, as a preferred implementation mode of the present invention, the business demand includes at least one demand or a combination of multiple demands among supply chain efficiency, supply chain cost and customer satisfaction.

[0069] For each supplier in each link of the virtual supply chain, key business needs are matched to determine the tasks that each supplier needs to undertake with the goal of optimizing the overall utility of the virtual supply chain. For example, for virtual supply chains ABD, the key business need corresponding to product supplier A is the dimension of supply chain efficiency, in order to meet the overall demand for product quality and timeliness of supply and delivery. For logistics and warehousing supplier B, the dimension of supply chain cost is more considered to measure whether the products or services provided by the supplier are lower in price, or the dimension of supply chain efficiency can also be considered; for after-sales service supplier D, the two dimensions of supply chain cost and customer satisfaction are generally considered. The method for matching suppliers' key business needs can be achieved by using expert experience research in the early stage, and gradually using data mining and machine learning techniques in the subsequent development process. For example, clustering algorithms (such as K-means, hierarchical clustering, etc.) can be used to group historical behavior data, identify group attributes with similar habits or preferences, and thus infer key needs. Association rule learning methods can also be used to analyze the correlation between behaviors of dimensions selected by platforms with the same attributes in the same or similar supply chain architectures, such as using frequent item set mining algorithms such as FP-growth to infer the potential needs of platform users in various links of the supply chain.

[0070] S4. Create a supplier evaluation index database, and obtain the supply chain collaborative optimization result corresponding to each virtual supply chain based on the supplier evaluation index database, wherein the supplier evaluation index database is used to provide a supplier evaluation index system for various types of key business requirements;

[0071] In specific implementation, as a preferred embodiment of the present invention, the supplier evaluation index database at least includes: a supply chain efficiency supplier evaluation index system, a supply chain cost supplier evaluation index system and a customer satisfaction supplier evaluation index system;

[0072] The supply chain efficiency supplier evaluation index system includes the following first-tier evaluation indicators: product quality, delivery timeliness, and supply chain flexibility; product quality includes: product qualification rate and return rate; delivery timeliness includes on-time delivery rate, average delivery time, and delivery delay rate; supply chain flexibility includes order response speed and emergency handling capability; the second-tier auxiliary evaluation indicators include information transparency, innovation capability, and supply chain cost; information transparency includes information sharing degree and product quality data accuracy; innovation capability includes product update capability; supply chain cost includes system logistics cost and system inventory holding cost;

[0073] The supply chain cost supplier evaluation index system includes the first-level evaluation indicators of procurement cost, logistics cost, inventory holding cost, order processing cost, return processing cost, and out-of-stock cost; the second-level auxiliary evaluation indicators include supplier management cost and quality problem cost; the logistics cost includes: transportation cost and distribution cost;

[0074] The customer satisfaction supplier evaluation index system includes the following first-level evaluation indicators: customer satisfaction, net recommendation rate, customer complaint rate, on-time delivery rate, return rate, and order accuracy rate; the second-level auxiliary evaluation indicators include customer retention rate and customer response time.

[0075] S5. The virtual supply chain corresponding to the supply chain collaborative optimization result with the highest score is used as the currently available supply chain to implement supplier management.

[0076] In specific implementation, as a preferred embodiment of the present invention, step S4 specifically includes:

[0077] Based on the supplier evaluation index database, the supplier corresponding to a certain link in a virtual supply chain is evaluated to obtain supply chain collaborative optimization results, including:

[0078] S41. Collect and preprocess the data related to the evaluation indicators of the supplier based on big data technology; and determine the indicator values ​​corresponding to various evaluation indicator data according to the preprocessed evaluation indicator data;

[0079] S42, determining whether the dimension of the business demand to which the current supplier belongs is unique;

[0080] If the current supplier has only one business requirement, the weight of each indicator is determined according to the fuzzy analytic hierarchy process, and the fuzzy synthesis operator is used to conduct a comprehensive evaluation of the supplier. The comprehensive score of the supplier corresponding to a certain link in the virtual supply chain is determined according to the comprehensive evaluation result;

[0081] If the business demand of the current supplier is not unique, select the supplier evaluation index system corresponding to the business demand type of the supplier according to the fuzzy hierarchical analysis method, determine the weight of each index, and use the fuzzy synthesis operator to obtain the evaluation result of the supplier corresponding to the dimension, determine the weight of each dimension, and obtain the comprehensive score of the supplier corresponding to a certain link in the virtual supply chain;

[0082] S43. Obtain the comprehensive scores of suppliers at each link one by one, and determine the corresponding supply chain collaborative optimization results according to the total score.

[0083] The present invention also includes an e-commerce platform supplier management system based on big data analysis, including: a data collection unit, a first data acquisition unit, a second data acquisition unit, a collaborative optimization unit, and a result display unit, wherein:

[0084] The data collection unit is used to perform attribute analysis on each supplier in the supplier set to be evaluated and analyzed and assign a corresponding attribute label to each supplier to obtain a first supplier set;

[0085] The first data acquisition unit is used to form a plurality of virtual supply chains according to the first supplier set;

[0086] The second data acquisition unit is used to perform demand matching on each virtual supply chain in turn to determine the business needs of the e-commerce platform users in each link of the supply chain;

[0087] The collaborative optimization unit is used to create a supplier evaluation index database, and obtain a supply chain collaborative optimization result corresponding to each virtual supply chain based on the supplier evaluation index database;

[0088] The result display unit is used to display the virtual supply chain corresponding to the supply chain collaborative optimization result with the highest score as the currently available supply chain, thereby completing the organizational structure management of each supplier in the supply chain.

[0089] Example 1

[0090] like Figure 1As shown, the present invention provides an e-commerce platform supplier management method and system based on big data analysis. For e-commerce platforms, from the perspective of long-term historical cycles, it is impossible for suppliers in their supplier set to remain unchanged. Supplier A may withdraw, and suppliers W and Y may also join. More importantly, the long-term existence of first-level contributing suppliers is not conducive to the development of the platform (new targets should be selected as much as possible to change them to second-level contributing suppliers). Therefore, it is necessary to set up a corresponding supplier set adjustment early warning mechanism. The supplier set adjustment early warning mechanism aims to regularly find potential first-level contributing suppliers for the platform or to evaluate and analyze new suppliers that have joined or intend to join, so as to judge in the early stage whether their corresponding indicators meet the current supply chain task requirements. The evaluation and analysis can use big data and machine learning algorithms for multi-dimensional analysis. This embodiment can adopt the following method when regularly looking for potential first-level contributing suppliers for the platform:

[0091] Based on big data analysis technology, suppliers outside the supplier set are updated and searched to obtain potential first-tier contributing suppliers.

[0092] Based on big data analysis technology, according to the role attributes of each supplier in the first-level contributing supplier subset, obtain the corresponding potential supplier list from the public network platform; based on the potential supplier list, obtain the historical data corresponding to each potential supplier, the historical data includes but is not limited to public purchase order data, supplier performance data, market demand data, industry competition data, etc.; perform data cleaning and preprocessing on the historical data to obtain optimized data, such as cleaning, deduplication, format conversion and missing value processing of the historical data to ensure that the data quality meets the needs of subsequent analysis;

[0093] Based on the optimized data, the supplier exclusivity analysis results are determined through the pre-created supplier exclusivity analysis model; the supplier exclusivity analysis model is an indicator structure analysis model obtained based on the analysis of indicators such as market competition, technical patents, and brand influence. The model formula is:

[0094] U i =w1·M i +w2·T i +w3·B i

[0095] Among them, U i represents the exclusivity score of the ith supplier, M i represents the market competitiveness of the ith supplier, T i represents the patent technology capability of the i-th supplier, B i represents the brand influence of the i-th supplier; w1, w2, w3 represent the weight coefficients of each indicator of the i-th supplier;

[0096] M i Size and market share of MS i Competitive Strength CU i Therefore, the weights of the two are given by subjective judgment, entropy weight method or least squares method to obtain M i .

[0097] MS i =S total / S i

[0098] S total S is the total sales of this type of product or service in the market. i represents the sales volume of a product or service of the i-th supplier;

[0099] CU i Use Porter's five forces analysis model to assess the intensity of market competition.

[0100] T i The value is mainly analyzed by its patent data and the number of patents PN i It is directly related to the patent quality PQi. The weights of the two are given by the entropy weight method or the least squares method to obtain T i .

[0101] PN i Using a simple counting algorithm, the number of patents of the i-th supplier PN i =Count(Patents i )

[0102] PQ i The influence scoring model is used to obtain

[0103]

[0104] PQi represents the patent quality of the ith supplier, Cik represents the number of citations of the kth patent of the ith supplier, and Lik represents the lifespan (in years) of the kth patent of the ith supplier.

[0105] B i The value is directly related to brand awareness BNi, BNi = Mention s i / TotalMentions Where BNi represents the brand awareness of the ith supplier, Mentions i represents the number of times the ith supplier is mentioned in social media and search engines, and Total Mentions represents the total number of mentions of all suppliers.

[0106] Based on the optimized data, the supplier irreplaceability evaluation result is determined through a pre-created supplier irreplaceability evaluation model; the supplier irreplaceability evaluation model is an indicator structure analysis model obtained by analyzing indicators such as the supplier's unique resources, supply chain dependence, and conversion costs, and its model formula is:

[0107] I i =w4·R i +w5·D i +w6·C i

[0108] Among them, I i represents the irreplaceability evaluation score of the ith supplier, R i represents the unique resource competitiveness of the i-th supplier, D i represents the supply chain dependency of the ith supplier, C i represents the switching cost of the ith supplier; w4, w5, w6 represent the weight coefficients of each indicator of the ith supplier;

[0109] Unique resource competitiveness i Generally, it is aimed at raw material suppliers to evaluate the scarcity and uniqueness of supplier resources and give specific values ​​through subjective judgment. If the i-th supplier belongs to this category, it will be evaluated. If it does not belong to this category, it can be assigned a value of 0. The scarcity evaluation formula can use the resource scarcity score of the i-th supplier:

[0110] UR i =R1 i / R avg ;

[0111] R1 i represents the quantity or quality of resources of the i-th supplier, R avg It represents the average resource quantity or quality in the industry. The resource uniqueness score of the i-th supplier can be directly replaced by the number of patents or standard essential patents.

[0112] D i Supply chain dependence is generally considered from the perspective of the supplier's control over key raw materials or components, the supplier's market share, etc.:

[0113]

[0114] C i Conversion cost: The factors affecting conversion cost include supplier replacement cost, technology conversion cost, training cost, contract breach cost, etc. The data sources for the survey can include financial statements, contract documents, market research, etc. i is the mean of the above costs;

[0115] Based on the results of supplier exclusivity analysis and supplier irreplaceability assessment, potential target suppliers are selected from the list of optional suppliers through subjective judgment, so as to prepare to become a member of the platform's supplier set through subsequent negotiations.

[0116] Example 2

[0117] In this embodiment, the big data technology involved in the entire data collection and analysis process, the corresponding big data platform framework can use Hadoop or Spark frameworks and use the big data analysis services provided by the AWS cloud platform. The processing engine uses Apache Flink to perform real-time processing and monitor the key evaluation indicators of each supplier. At the same time, this technology can also be used to establish a visual real-time monitoring system to form a corresponding interactive dashboard and report to intuitively display the corresponding data information of the supplier, such as using the Tableau tool to visualize the data of interest and the indicator deviation threshold, and the system automatically alarms;

[0118] After the big data platform architecture is completed, the process of evaluating suppliers corresponding to a certain link in a virtual supply chain based on the various indicators stated in the supply chain efficiency supplier evaluation index system includes:

[0119] Based on big data technology, data related to evaluation indicators on suppliers are collected and preprocessed through e-commerce platforms, supply chain management systems, customer feedback systems and other channels; the Z-score method can be used to clean the data, and the Min-Max standardization method can be used to standardize the data; at the same time, the text data is converted into corresponding numerical representations, such as the "qualified" and "unqualified" labels in this data are converted to 1 and 0, so as to facilitate use in subsequent process analysis;

[0120] Based on the preprocessed evaluation index data, determine the index values ​​corresponding to various types of evaluation index data;

[0121] For the supply chain efficiency supplier evaluation index system, product quality is one of the key factors affecting supply chain efficiency. Product quality includes: product qualification rate and return rate. The product qualification rate is the proportion of products provided by the supplier that meet the quality standards, that is, the ratio of the number of qualified products to the total number of products; the return rate is the ratio of the number of products returned by customers due to quality problems to the total number of products; the on-time delivery rate is one of the key factors affecting supply chain efficiency, which is used to evaluate the supplier's ability to deliver on time, which is determined by the ratio of the number of on-time delivery orders to the total number of orders; the average delivery time is the average time from order placement to delivery, that is, the ratio of the number of orders to the delivery time, where the delivery time can be calculated by the timestamp recorded by the order system; the delivery delay rate is the ratio of the number of delayed delivery orders to the total number of orders; the order response speed is the supplier's response speed to new orders, the ratio of the total order response time to the order number, where the order response time refers to the time from the supplier receiving the order to confirming the order; the emergency handling capability is to evaluate the supplier's emergency handling capability in emergency situations, such as evaluating and scoring its handling records of simulated emergencies or actual emergencies through the expert direct scoring method;

[0122] The degree of information sharing is to evaluate the degree of information sharing between suppliers and e-commerce platforms. It is scored by direct expert scoring. For example, the preset expert scoring system assesses the completeness of the information replied by suppliers to the requirements put forward by the platform and scores it. At the same time, the timeliness of the joint reply can be considered. If there is no relevant data, it can be assigned 0 points. The accuracy of product quality data is determined by comparing the difference between the data provided by the supplier and the actual inspection results. The product update capability is the frequency of suppliers launching new products or improving existing products within a certain time frame. If there are corresponding patents, the corresponding score will be increased. It is scored by direct expert scoring. The system logistics cost is the logistics and transportation cost of the supplier. The system inventory holding cost is the inventory management cost of the supplier.

[0123] For the supply chain cost supplier evaluation index system, procurement cost is the cost of purchasing raw materials or products, which is determined by the unit price and total quantity of raw materials or products; logistics cost is the cost incurred during the transportation and distribution of all orders of goods within a specific evaluation period, which includes: transportation cost, distribution cost; inventory holding cost is the cost incurred in the process of storing inventory, including warehousing costs, capital occupation costs, losses, etc., inventory holding cost = average inventory × unit inventory holding cost and unit inventory holding cost = unit value × holding cost rate; order processing cost is the cost required to process each order, which includes the costs incurred in multiple links, such as entry, confirmation, picking, packaging and delivery processes; through order Processing cost = number of orders × average processing fee for a single order; return processing cost refers to the additional costs incurred in the process of processing return orders, including return transportation costs, re-warehousing costs, product inspection costs, etc.; out-of-stock costs refer to the losses incurred when insufficient inventory leads to the inability to meet customer needs, including the cost of lost sales opportunities, i.e. sales losses, and the cost of restoring customer trust; supplier management costs refer to the costs required to manage and maintain relationships with suppliers, including negotiation costs, contract management costs, supplier evaluation costs, etc.; quality problem costs refer to the costs caused by quality problems, including inspection costs, rework costs, quality assurance costs, etc. At the same time, if there is no historical data of the corresponding type, each indicator is directly assigned a value of 0;

[0124] For the customer satisfaction supplier evaluation index system, customer satisfaction refers to the degree of satisfaction with the supplier's services / products, which includes the customer's satisfaction with the supplier's after-sales service - after-sales service satisfaction and the customer's satisfaction with the quality of the product provided by the supplier, i.e. product quality satisfaction; net recommendation refers to the customer's willingness to recommend the supplier, that is, the degree to which the supplier's services / products are recommended to others, which is specifically the difference between the percentage of recommenders and the percentage of detractors. Recommenders are the proportion of customers with a score of 8.5-10 in a given evaluation cycle, and detractors are the proportion of customers with a score of 0-6 in a given evaluation cycle; customer complaint rate refers to the customer's complaints about the supplier's products or services, which is specifically the percentage of customers within the evaluation cycle. The ratio of total complaints to total order quantity; on-time delivery rate is the ratio of suppliers that can deliver products according to the agreed time to observe the supplier's ability to deliver on time; return rate is the ratio of returns caused by quality problems; order accuracy rate is the degree of accuracy of the supplier in the order processing process; customer retention rate is the ability of the supplier's products or services to retain existing customers, which is determined by (∑ number of customers at the end of the period - ∑ number of new customers) / ∑ number of customers at the beginning of the period × 100%; customer response time is the supplier's response speed to customer inquiries and questions, which is the sum of the response times of all customer inquiries during the evaluation period divided by the total number of customer inquiries, etc. At the same time, if there is no historical data of the corresponding type, each indicator is directly assigned a value of 0.

[0125] Example 3

[0126] This embodiment obtains the comprehensive score of the supplier corresponding to a certain link in the virtual supply chain based on the weight of each dimension determined by the expert scoring method; obtains the comprehensive score of the supplier in each link one by one, and determines the corresponding supply chain collaborative optimization result according to the total score; if the key business demand type of the supplier includes supply chain efficiency and supply chain cost, then first determine that the key business demand is supply chain efficiency, and its corresponding supplier evaluation index system is the supply chain efficiency supplier evaluation index system, then determine the weight of each indicator according to the fuzzy analytic hierarchy process (Fuzzy AHP), and use the fuzzy synthesis operator to comprehensively evaluate the supplier, and then obtain the first dimension score result Q1 of the supplier corresponding to a certain link in the virtual supply chain (the key business demand type is supply chain efficiency); secondly determine that the key business demand is supply chain cost, and its corresponding supplier evaluation index system is the supply chain cost supplier evaluation index system, then according to the fuzzy analytic hierarchy process (Fuzzy AHP), the supplier is comprehensively evaluated. AHP) is used to determine the weight of each indicator, and the fuzzy synthesis operator is used to comprehensively evaluate the suppliers, and then the first dimension score of the supplier corresponding to a certain link in the virtual supply chain (the key business demand type is supply chain cost) is obtained as Q2. The weights of each dimension determined by the expert scoring method are w1 and w2 respectively, so the comprehensive score of the supplier corresponding to a certain link in the virtual supply chain is Q f ,

[0127] Q f =Q1·w1+Q2·w2.

[0128] As the platform continues to change and develop, even if each supplier in the current supplier set has not been updated for a certain period of time, considering the leapfrog development needs of large e-commerce platforms, the weight analysis method of its indicators should also be adaptively updated and adjusted, especially in combination with changes in the market environment and the company's strategic goals. Dynamic adjustment (ensuring that the evaluation system is consistent with the company's long-term strategic goals) to obtain new supply chain collaborative optimization results; specifically, the method for determining the weight of each indicator in S42 can also be implemented using the following dynamic weight adjustment method, and the specific steps include:

[0129] S400, determining the initial weight corresponding to the current sampling time of each evaluation indicator by an expert scoring method, that is, completing the initialization;

[0130] S401, adjusting the weights corresponding to the various evaluation indicators in real time according to the weight adjustment strategy; the formula corresponding to the weight adjustment strategy is expressed as follows

[0131] W i (t) = W i(t-1)+α·ΔW i (t)

[0132] Among them, W i (t) represents the weight of the i-th indicator at sampling time t, W i (t-1) represents the weight of the previous sampling time, α represents the adjustment factor, ΔW i (t) represents the change in weight, which is determined based on the current strategic goals of the e-commerce platform. For example, the current strategic goals of the e-commerce platform can be determined based on changes in the market environment and the company's development strategic goals. For example, if the platform's current strategic focus is to improve product quality, then the weight adjustment of the product quality indicator can be increased to better adapt to the company's strategic goals and changes in the market environment.

[0133] The change in the weight of a certain evaluation index ΔW i (t) can be determined by a reinforcement learning algorithm, such as using the Q-learning algorithm in reinforcement learning to determine the weight adjustment amount of a supplier evaluation indicator. The specific implementation steps include: S4011, defining state space variables, that is, taking changes in the market environment and the company's strategic goals as part of the state. For example, factors such as market demand growth, changes in competitor behavior, and company strategy adjustments are quantified as state variables; S4012, defining the action space, that is, defining a series of possible actions, namely, weight adjustment plans (the magnitude and direction of weight adjustment to increase or decrease the weight of the evaluation indicator corresponding to this state); S4013, defining a reward function to measure the effect of weight adjustment. The reward is calculated based on the benefits brought to the company by the supplier evaluation results, such as increased profits, improved customer satisfaction, etc., and is set by experts; S4014, initializing the Q-table. The Q-table is used to store the Q value (expected return) of each state-action pair. The rows of the Q-table correspond to the elements of the state space, and the columns correspond to the elements of the action space; S4015, based on the Q-learning algorithm, learning prediction is performed to update the Q-table until convergence; the learning process is to select an action (weight adjustment scheme) according to the current state; adjust the weight according to the selected action and apply it to the supplier evaluation index; recalculate the supplier evaluation results according to the adjusted weights, and observe the impact on the company's revenue-expected return; calculate the reward based on the revenue brought to the company by the new supplier evaluation results, that is, use the Q-learning formula to update the Q value in the Q-table, the formula is

[0134] Q(s,a)←Q(s,a)+α[R(s′,a′)+γmax a′ Q(s′,a′)-Q(s,a)]

[0135] Where s represents the current state, a represents the action performed, α represents the learning rate and 0<α≤1, α represents the influence of new information on the old Q value, γ represents the discount factor and 0≤γ≤1, which is used to determine the importance of future rewards. γ is usually set to a positive value less than 1 to ensure the discount of future rewards, and ← represents update; then Q(s,a) represents the current Q value of performing action a in state s, and R(s′,a′) is the immediate reward obtained by transferring from state s to state s′ after taking action a; max a′ Q(s′,a′) represents the action with the maximum Q value among all possible actions in the new state s′.

[0136] Finally, enter the next state and repeat the above process, and judge in real time whether the convergence condition is reached. When the change of the Q value in the Q-table does not exceed the threshold, the current weight adjustment scheme is finally selected as the appropriate weight change.

[0137] Among them, in some specific embodiments, S5, the virtual supply chain corresponding to the supply chain collaborative optimization result with the highest score is used as the current available supply chain, and then the organizational structure management of each supplier in the supply chain is completed. If the final virtual supply chain ABD has the highest score, then the organizational structure of the supplier at this time is supply chain ABD.

[0138] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0139] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0140] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0141] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0142] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0143] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0144] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for managing suppliers on an e-commerce platform based on big data analysis, characterized in that: include: S1. Integrate various types of suppliers into a set of suppliers to be evaluated and analyzed, perform attribute analysis on each supplier and assign attribute labels to each supplier to obtain a first set of suppliers; S2, forming multiple virtual supply chains according to the first supplier set obtained in S1; S3, matching the needs of each virtual supply chain in S2 in turn, and determining the business needs of e-commerce platform users in each link of the supply chain; S4. Create a supplier evaluation index database, and obtain the supply chain collaborative optimization result corresponding to each virtual supply chain based on the supplier evaluation index database, wherein the supplier evaluation index database is used to provide a supplier evaluation index system for various types of key business requirements; S5. The virtual supply chain corresponding to the supply chain collaborative optimization result with the highest score is used as the currently available supply chain to implement supplier management.

2. The e-commerce platform supplier management method based on big data analysis according to claim 1 is characterized in that: The specific implementation steps of S1 include: S11. Analyze the attributes of each supplier in the supplier set to be evaluated and analyzed, and determine the role attributes of each supplier in each link of the supply chain; S12, counting the number of suppliers belonging to each type of role attribute, and determining whether the number of suppliers belonging to each type of role attribute is 1; If the number of suppliers is 1, the supplier is identified as a first-level contribution supplier, and a first attribute label is assigned to the supplier, wherein the first attribute label includes at least a role attribute and a first-level contribution attribute; If the number of suppliers is not 1, the supplier is identified as a secondary contribution supplier and a second attribute label is assigned to the supplier, wherein the second attribute label includes at least a role attribute and a secondary contribution attribute; S13. Form a first supplier set according to the attribute tag category, wherein the first supplier set includes a first-level contributing supplier sub-set and a second-level contributing supplier sub-set.

3. The e-commerce platform supplier management method based on big data analysis according to claim 1 is characterized in that: The step S2 specifically includes: Based on the first supplier set, in accordance with the role attributes required by each link in the supply chain, each supplier in the first-level contribution supplier subset is preferentially configured. After the configuration is completed, each supplier in the second-level contribution supplier subset is randomly configured to form multiple virtual supply chains.

4. The e-commerce platform supplier management method based on big data analysis according to claim 1, characterized in that: The business requirements include at least one requirement or a combination of multiple requirements among supply chain efficiency, supply chain cost and customer satisfaction.

5. The e-commerce platform supplier management method based on big data analysis according to claim 1, characterized in that: The supplier evaluation index database includes at least: a supply chain efficiency supplier evaluation index system, a supply chain cost supplier evaluation index system, and a customer satisfaction supplier evaluation index system; The supply chain efficiency supplier evaluation index system includes the following first-tier evaluation indicators: product quality, delivery timeliness, and supply chain flexibility; product quality includes: product qualification rate and return rate; delivery timeliness includes on-time delivery rate, average delivery time, and delivery delay rate; supply chain flexibility includes order response speed and emergency handling capability; the second-tier auxiliary evaluation indicators include information transparency, innovation capability, and supply chain cost; information transparency includes information sharing degree and product quality data accuracy; innovation capability includes product update capability; supply chain cost includes system logistics cost and system inventory holding cost; The supply chain cost supplier evaluation index system includes the first-level evaluation indicators of procurement cost, logistics cost, inventory holding cost, order processing cost, return processing cost, and out-of-stock cost; the second-level auxiliary evaluation indicators include supplier management cost and quality problem cost; the logistics cost includes: transportation cost and distribution cost; The customer satisfaction supplier evaluation index system includes the following first-level evaluation indicators: customer satisfaction, net recommendation rate, customer complaint rate, on-time delivery rate, return rate, and order accuracy rate; the second-level auxiliary evaluation indicators include customer retention rate and customer response time.

6. The e-commerce platform supplier management method based on big data analysis according to claim 4 is characterized in that: The step S4 specifically includes: Based on the supplier evaluation index database, the supplier corresponding to a certain link in a virtual supply chain is evaluated to obtain supply chain collaborative optimization results, including: S41. Collect and preprocess the data related to the evaluation indicators of the supplier based on big data technology; and determine the indicator values ​​corresponding to various evaluation indicator data according to the preprocessed evaluation indicator data; S42, determining whether the dimension of the business demand to which the current supplier belongs is unique; If the current supplier has only one business requirement, the weight of each indicator is determined according to the fuzzy analytic hierarchy process, and the fuzzy synthesis operator is used to conduct a comprehensive evaluation of the supplier. The comprehensive score of the supplier corresponding to a certain link in the virtual supply chain is determined according to the comprehensive evaluation result; If the business demand of the current supplier is not unique, select the supplier evaluation index system corresponding to the business demand type of the supplier according to the fuzzy hierarchical analysis method, determine the weight of each index, and use the fuzzy synthesis operator to obtain the evaluation result of the supplier corresponding to the dimension, determine the weight of each dimension, and obtain the comprehensive score of the supplier corresponding to a certain link in the virtual supply chain; S43. Obtain the comprehensive scores of suppliers at each link one by one, and determine the corresponding supply chain collaborative optimization results according to the total score.

7. An e-commerce platform supplier management system based on big data analysis, characterized in that: include: Data collection unit, first data acquisition unit, second data acquisition unit, collaborative optimization unit, result display unit, wherein: The data collection unit is used to perform attribute analysis on each supplier in the supplier set to be evaluated and analyzed and assign a corresponding attribute label to each supplier to obtain a first supplier set; The first data acquisition unit is used to form a plurality of virtual supply chains according to the first supplier set; The second data acquisition unit is used to perform demand matching on each virtual supply chain in turn to determine the business needs of the e-commerce platform users in each link of the supply chain; The collaborative optimization unit is used to create a supplier evaluation index database, and obtain a supply chain collaborative optimization result corresponding to each virtual supply chain based on the supplier evaluation index database; The result display unit is used to display the virtual supply chain corresponding to the supply chain collaborative optimization result with the highest score as the currently available supply chain, thereby completing the organizational structure management of each supplier in the supply chain.

Images