Industrial chain manufacturer evaluation and optimal allocation method based on collaborative element mining

Abstract

The invention discloses an industrial chain manufacturer evaluation and optimal allocation method based on collaborative element mining, and aims to mine collaborative element features and realize manufacturer evaluation and high-order many-to-many relationship production task allocation modeling in an industrial chain so as to solve the optimal allocation problem under resource limitation. The method comprises the following steps: acquiring demand data of a user for each product, maximum production capacity limit data of a manufacturer for each product and collaborative element feature original data of the manufacturer for each product; according to the collaborative element feature original data of the producer for each product, evaluating the production qualification value of the producer for each product, and constructing an optimization objective function; the demand data of the user for each product and the maximum production capacity limit data of the manufacturer for each product are taken as optimization target constraint conditions; and constructing a high-order group role assignment model based on the optimization target constraint condition and the optimization target function, solving the model, and outputting a target optimal allocation scheme for a decision maker to make a decision.

Description

Technical Field

[0001] The present invention relates to the field of industrial chain supply service technology, and in particular to an industrial chain producer evaluation and optimal allocation method based on collaborative factor mining. Background Art

[0002] Collaborative manufacturing is an innovative production model that integrates the resources of multiple companies, relying on cross-enterprise collaboration in the industrial chain to jointly respond to changes in market demand. This model can quickly respond to market fluctuations and dynamically adjust production plans and processes to better meet the personalized and diversified needs of customers, thereby enhancing the competitiveness and market adaptability of enterprises.

[0003] In addition, collaborative manufacturing can also optimize resource allocation and achieve more efficient production and supply chain management in the industrial chain. In this model, customers can directly publish their demands for various products, and manufacturers in the industrial chain can quickly respond and complete production tasks together through collaboration, and finally deliver products that meet customer requirements. For example, different consumers may have specific needs or preferences for products. Some consumers may require products that meet specific quality standards, while others are more concerned with fast production and delivery. This model can not only improve customer satisfaction by accurately meeting their unique needs, but also enable each manufacturer in the industrial chain to use their own advantageous resources more efficiently to meet the personalized requirements of customers to the greatest extent.

[0004] However, this model also brings huge challenges because it involves complex interactions between users, products, and manufacturers, which form high-order many-to-many relationships. For example, the various product requirements posted by users are converted into corresponding production tasks. These tasks can be completed independently by a single manufacturer in the industrial chain or by multiple manufacturers working together. This complex many-to-many relationship not only makes the allocation process of production tasks extremely difficult and complicated, but also increases the difficulty of coordination and management. Therefore, in order to effectively coordinate and manage the allocation of production tasks in high-order many-to-many relationships, a comprehensive high-order task allocation model must be established.

[0005] At present, in the process of building a high-level task allocation model, one of the most important links is to evaluate the production qualification values ​​of each supplier in the industrial chain. However, due to the significant differences in the characteristics of the synergy factors corresponding to each manufacturer in the industrial chain, such as production costs, production quality, production cycle, transportation costs and transportation time, it is difficult to directly derive the production qualification values ​​of these manufacturers through simple calculations. In addition, the advantages and disadvantages of different manufacturers vary in different demand scenarios, and a more refined method is needed to distinguish the production qualification values ​​of each manufacturer for each product.

[0006] Therefore, in order to achieve efficient allocation of high-order many-to-many production tasks, it is urgent to solve the problems of producer evaluation in the industrial chain, formal modeling of high-order many-to-many relationship production tasks, and their optimal allocation under resource constraints. Summary of the invention

[0007] The present invention provides an industrial chain producer evaluation and its optimal allocation method based on collaborative factor mining, which is used to solve the technical problems of producer evaluation in the industrial chain and formal modeling of high-order many-to-many relationship production tasks and their optimal allocation under resource constraints.

[0008] The present invention provides an industrial chain producer evaluation based on collaborative factor mining and an optimal allocation method thereof, including:

[0009] Obtaining demand data for various products from multiple users, maximum production capacity limit data for various products from multiple manufacturers, and original data on collaborative factor characteristics for various products from multiple manufacturers;

[0010] According to the original data of the collaborative factor characteristics of the multiple manufacturers for each product, the production qualifications of the multiple manufacturers for each product are evaluated to determine the production qualification values ​​of the multiple manufacturers for each product;

[0011] Using the production qualification values ​​of the multiple manufacturers for each product, constructing an optimization objective function;

[0012] Taking the demand data of the plurality of users for each product and the maximum production capacity limit data of the plurality of manufacturers for each product as optimization target constraint conditions;

[0013] A high-order group role assignment model is constructed based on the optimization target constraint conditions and the optimization target function, and the high-order group role assignment model is solved to output the target optimal allocation plan for decision makers to make.

[0014] Optionally, evaluating the production qualifications of the multiple manufacturers for the various products based on the original data of the collaborative factor characteristics of the multiple manufacturers for the various products, and determining the production qualification values ​​of the multiple manufacturers for the various products, includes:

[0015] Normalizing the original data of the synergistic factor characteristics of each product of each manufacturer to the maximum and minimum values, and determining the normalized synergistic factor characteristic data of multiple manufacturers for each product;

[0016] Performing mean calculation on the normalized collaborative factor feature data of the multiple manufacturers for each product, and outputting multiple collaborative factor feature means;

[0017] Calculating standard deviations of normalized synergistic factor feature data of multiple manufacturers for each product and multiple synergistic factor feature means, and outputting multiple synergistic factor feature standard deviations;

[0018] Based on the plurality of collaborative element characteristic standard deviations, determining an initial weight corresponding to each of the collaborative element characteristic standard deviations;

[0019] Using each of the initial weights and each of the standard deviations of the collaborative factor characteristics, the original data of the collaborative factor characteristics of the multiple manufacturers for each product are standardized, and the standardized collaborative factor characteristic data of the multiple manufacturers for each product are output;

[0020] Constructing a synergistic factor characteristic association matrix according to the mean values ​​of the synergistic factor characteristics and the standardized synergistic factor characteristic data of the multiple manufacturers for each product;

[0021] Performing eigendecomposition on the collaborative factor feature association matrix to determine the eigenvalues ​​of the collaborative factor feature association matrix and its eigenmatrix;

[0022] Calculating a plurality of target weights according to each of the initial weights, the eigenvalues ​​of the collaborative element feature association matrix and its feature matrix;

[0023] The target weights and the normalized collaborative factor characteristic data of the multiple manufacturers for each product are used to determine the production qualification values ​​of the multiple manufacturers for each product.

[0024] Optionally, the calculation process of the manufacturer for the production qualification value of each product is specifically as follows:

[0025] ;

[0026] in, is the production qualification value of the i-th manufacturer for the j-th product; is the jth target weight; is the j-th normalized collaborative factor characteristic data of the ith producer.

[0027] Optionally, the optimization objective function is specifically:

[0028] ;

[0029] in, is the optimization objective function; u is the number of users; m is the number of manufacturers; n is the number of products; Whether the i-th manufacturer is responsible for meeting the product demand of the k-th user for the j-th product; is the production qualification value of the i-th manufacturer for the j-th product.

[0030] Optionally, the optimization objective constraint condition is specifically:

[0031] ;

[0032] in, Whether the i-th manufacturer is responsible for meeting the product demand of the k-th user for the j-th product; is the demand data of the kth user for the jth product; is the maximum production capacity limit data of the i-th manufacturer for the j-th product; u is the number of users; m is the number of manufacturers; n is the number of products.

[0033] Optionally, the target weight calculation process is specifically as follows:

[0034] ;

[0035] in, is the jth target weight; is the jth initial weight; It is a fixed value, and its value is 1; is the softmax activation function; is the i-th eigenvalue of the collaborative factor feature association matrix; is the contribution of the j-th collaborative element feature to the i-th component (the eigenvector corresponding to the eigenvalue of the i-th collaborative element association matrix in the feature matrix).

[0036] Optionally, the calculation process of the collaborative factor feature mean is specifically as follows:

[0037] ;

[0038] in, is the characteristic mean of the jth collaborative factor; is the j-th normalized collaborative factor characteristic data of the ith producer; m is the number of producers.

[0039] Optionally, the calculation process of the collaborative factor characteristic standard deviation is specifically as follows:

[0040] ;

[0041] in, is the characteristic standard deviation of the jth collaborative factor; is the characteristic mean of the jth collaborative factor; is the j-th normalized collaborative factor characteristic data of the ith producer; m is the number of producers.

[0042] Optionally, the calculation process of the initial weight is specifically as follows:

[0043] ;

[0044] in, is the characteristic standard deviation of the jth collaborative factor; is the jth initial weight; is the sum of the standard deviations of the synergistic factors’ characteristics.

[0045] Optionally, the calculation process of the standardized collaborative element feature data is specifically as follows:

[0046] ;

[0047] in, is the jth standardized collaborative factor characteristic data of the i-th manufacturer; is the original data of the jth collaborative factor characteristics of the i-th producer; is the characteristic mean of the jth collaborative factor; is the characteristic standard deviation of the jth collaborative factor.

[0048] It can be seen from the above technical solutions that the present invention has the following advantages:

[0049] The above scheme of the present invention provides an industrial chain manufacturer evaluation and optimal allocation method based on collaborative factor mining, firstly, obtaining the demand data of multiple users for each product, the maximum production capacity limit data of multiple manufacturers for each product and the original data of collaborative factor characteristics of multiple manufacturers for each product; then, based on the original data of collaborative factor characteristics of multiple manufacturers for each product, evaluating the production qualifications of multiple manufacturers for each product, determining the production qualification values ​​of multiple manufacturers for each product; using the production qualification values ​​of multiple manufacturers for each product, constructing an optimization objective function; using the demand data of multiple users for each product and the maximum production capacity limit data of multiple manufacturers for each product as optimization objective constraints; finally, based on the optimization objective constraints, the optimization objective constraints and the optimization objective function, the optimization objective function is constructed. The objective function is optimized to construct a high-order group role assignment model, and the high-order group role assignment model is solved to output the optimal target allocation plan for decision makers to make decisions; based on the above plan, the present invention evaluates and calculates the manufacturer qualification value according to the original data of the collaborative factor characteristics corresponding to each product by the manufacturer and constructs a high-order group role assignment model, thereby realizing the real-time evaluation of the production qualifications of each product by the manufacturers in the industrial chain, and can solve the problem of analyzing the collaborative factor characteristics of the manufacturers in the industrial chain; by solving the high-order group role assignment model, it is possible to achieve the optimal calculation of high-order many-to-many relationship production tasks, and provide the optimal decision plan for production task allocation, thereby solving the problem of manufacturer evaluation in the industrial chain and formal modeling of high-order many-to-many relationship production tasks and their optimal allocation under resource constraints. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] 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 only 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.

[0051] Figure 1 A flowchart of a method for evaluating and optimally allocating industrial chain manufacturers based on collaborative factor mining provided by an embodiment of the present invention;

[0052] Figure 2 A schematic diagram of a manufacturer qualification value evaluation process based on collaborative factor mining in an industrial chain provided by an embodiment of the present invention;

[0053] Figure 3 A schematic diagram of an optimal allocation result of production tasks provided by an embodiment of the present invention;

[0054] Figure 4 A schematic diagram of the execution process of the industrial chain manufacturer evaluation and its optimal allocation method based on collaborative factor mining provided by an embodiment of the present invention;

[0055] Figure 5 A structural block diagram of an industrial chain manufacturer evaluation and optimal allocation device based on collaborative factor mining provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The embodiment of the present invention provides an industrial chain producer evaluation and optimal allocation method based on collaborative factor mining, which is used to solve the technical problems of producer evaluation in the industrial chain and formal modeling of high-order many-to-many relationship production tasks and their optimal allocation under resource constraints.

[0057] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions 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 embodiments described below 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 are within the scope of protection of the present invention.

[0058] In order to facilitate better understanding by those skilled in the art, the relevant technical features or technical means involved in the technical solution of the present invention are first explained and illustrated.

[0059] Pulp: A linear programming calculation package in Python language, used for linear programming model establishment and calculation.

[0060] As an example, in the context of collaborative manufacturing, although cross-enterprise cooperation and collaboration can quickly respond to market fluctuations and dynamically adjust production plans and processes, it still faces significant challenges. First, the production tasks in the industrial chain present complex high-order many-to-many relationships, which are difficult to effectively handle with traditional allocation methods, resulting in difficulties in formal modeling and thus reducing production efficiency. Secondly, there are differences among manufacturers in collaborative factors such as production costs, quality, cycles, transportation costs and time. Traditional simple calculation methods cannot fully evaluate their comprehensive qualifications, affecting the accuracy of task allocation. In addition, the resource constraints of each manufacturer in the industrial chain have not been fully considered, and traditional allocation methods are difficult to ensure rapid response and smooth execution of tasks. Therefore, optimizing the task allocation strategy and comprehensively considering complex task relationships, differences in collaborative factor characteristics and resource constraints are the key to improving the efficiency of collaborative manufacturing.

[0061] Therefore, one of the core inventive points of the embodiment of the present invention is: by real-time evaluation of the production qualifications of manufacturers in the industrial chain, the accuracy of task allocation is ensured. A high-order group role assignment model is proposed to realize the formal modeling of production tasks with high-order many-to-many relationships. By solving the high-order group role assignment model, not only the shortcomings of traditional methods in dealing with complex task allocation are solved, but also the optimal calculation of production tasks is achieved, and the optimal decision-making plan is provided, which significantly improves the efficiency and effect of task allocation and ensures the best use of resources. In addition, the technical solution provided by the embodiment of the present invention has strong adaptability and flexibility, is suitable for complex and changeable production task scenarios, can cope with diversified production needs, and effectively integrates upstream and downstream enterprises in the industrial chain to improve the collaborative efficiency and overall competitiveness of the industrial chain.

[0062] See also Figure 1 , Figure 1 A flowchart of the steps of an industrial chain manufacturer evaluation and optimal allocation method based on collaborative factor mining provided in an embodiment of the present invention.

[0063] The present invention provides an industrial chain producer evaluation and optimal allocation method based on collaborative factor mining, comprising:

[0064] Step 101: Obtain demand data of multiple users for each product, maximum production capacity limit data of multiple manufacturers for each product, and original data of collaborative factor characteristics of multiple manufacturers for each product.

[0065] It should be noted that the demand data of multiple users for various products are the demand of each user for various products, that is, the production task information data to be allocated; wherein the production task information data is used It is an n×u-dimensional matrix, where n represents the number of product types and u represents the number of users. represents the demand (demand data) of the kth user for the jth product. For example, Table 1 shows an example of production task information data (unit: kg), p i Indicates different types of products, User i Indicates different users.

[0066] Table 1 Example of production task information data

[0067]

[0068] Furthermore, the maximum production capacity limit data of multiple manufacturers for each product is the production capacity limit of multiple manufacturers to be assigned for each product, that is, the manufacturer resource limit information data. Since the production capacity and resource distribution of different manufacturers are different, the corresponding production capacity is different; wherein the manufacturer resource limit information data is L a It is an m×n dimensional matrix, where m represents the number of manufacturers and n represents the product type data. represents the maximum quantity of the jth product that the ith producer can provide (i.e., the maximum production capacity limit data of the ith producer for the jth product); for example, Table 2 shows an example of producer resource limit information data (unit: kg), p i Indicates different types of products, Manufacturer i Indicates manufacturers that provide different products.

[0069] Table 2 Example of manufacturer resource restriction information data

[0070]

[0071] Furthermore, the original data of the collaborative factor characteristics of each product of the manufacturer is obtained. The original data of the collaborative factor characteristics include production cost, production quality, production cycle, transportation cost and transportation time, that is, each manufacturer has corresponding production cost, production quality, production cycle, transportation cost and transportation time for each product; for example, Table 3 shows the original data of the collaborative factor characteristics of each manufacturer for each product.

[0072] Table 3 Example of raw data of producer collaborative factor characteristics

[0073]

[0074] Step 102: Based on the original data of the collaborative factor characteristics of the multiple manufacturers for the various products, the production qualifications of the multiple manufacturers for the various products are evaluated to determine the production qualification values ​​of the multiple manufacturers for the various products.

[0075] Further, step 102 may include the following sub-steps:

[0076] S21, normalizing the maximum and minimum values ​​of the original data of the collaborative factor characteristics of each manufacturer for each product, and determining the normalized collaborative factor characteristic data of multiple manufacturers for each product;

[0077] S22, performing mean calculation on the normalized collaborative factor feature data of various products of multiple manufacturers, and outputting multiple collaborative factor feature means;

[0078] S23, calculating the standard deviation of the normalized synergistic factor characteristic data of various products of multiple manufacturers and the mean values ​​of multiple synergistic factor characteristics, and outputting multiple synergistic factor characteristic standard deviations;

[0079] S24, based on the characteristic standard deviations of the plurality of collaborative elements, determining the initial weight corresponding to the characteristic standard deviation of each collaborative element;

[0080] S25, using each initial weight and each standard deviation of the collaborative factor characteristics to standardize the original data of the collaborative factor characteristics of various products of multiple manufacturers, and output the standardized collaborative factor characteristic data of various products of multiple manufacturers;

[0081] S26. constructing a synergistic factor characteristic association matrix based on the mean value of each synergistic factor characteristic and the standardized synergistic factor characteristic data of multiple manufacturers for each product;

[0082] S27, performing eigendecomposition on the collaborative factor characteristic association matrix to determine the eigenvalues ​​of the collaborative factor characteristic association matrix and its characteristic matrix;

[0083] S28, calculating multiple target weights according to each initial weight, the eigenvalue of the collaborative element feature association matrix and its feature matrix;

[0084] S29. Use the target weights and the normalized collaborative factor characteristic data of multiple manufacturers for each product to determine the production qualification values ​​of multiple manufacturers for each product.

[0085] It should be noted that the production qualification values ​​of multiple manufacturers for various products can form an m×n dimensional matrix Q, where m represents the number of manufacturers and n represents the type of product data. It represents the production qualification value of the i-th manufacturer to produce the j-th product (that is, the production qualification value of the i-th manufacturer for the j-th product).

[0086] Specifically, when evaluating the production qualifications of multiple manufacturers for various products, the present invention refers to Figure 2First, the original data of the collaborative factor characteristics of multiple manufacturers for each product are subjected to maximum-minimum normalization processing to determine the normalized collaborative factor characteristic data of multiple manufacturers for each product; the normalized collaborative factor characteristic data of multiple manufacturers for each product are subjected to mean calculation to output multiple collaborative factor characteristic means; wherein, the calculation process of the collaborative factor characteristic mean is specifically as follows:

[0087] ;

[0088] in, is the characteristic mean of the jth collaborative factor; is the j-th normalized collaborative factor characteristic data of the ith producer; m is the number of producers.

[0089] Next, the standard deviation of the normalized synergistic factor feature data and the mean values ​​of multiple synergistic factor features for various products of multiple manufacturers is calculated, and multiple synergistic factor feature standard deviations are output; wherein the calculation process of the synergistic factor feature standard deviation is specifically as follows:

[0090] ;

[0091] in, is the characteristic standard deviation of the jth collaborative factor; is the characteristic mean of the jth collaborative factor; is the j-th normalized collaborative factor characteristic data of the ith producer; m is the number of producers.

[0092] Furthermore, based on the characteristic standard deviations of multiple collaborative elements, the initial weight corresponding to the characteristic standard deviation of each collaborative element is determined; wherein the calculation process of the initial weight is specifically as follows:

[0093] ;

[0094] in, is the characteristic standard deviation of the jth collaborative factor; is the jth initial weight; is the sum of the standard deviations of the synergistic factors’ characteristics.

[0095] Furthermore, the original data of collaborative factor characteristics of multiple manufacturers for each product are standardized by using each initial weight and each collaborative factor characteristic standard deviation, and the standardized collaborative factor characteristic data of multiple manufacturers for each product are output; wherein the calculation process of the standardized collaborative factor characteristic data is specifically as follows:

[0096] ;

[0097] in, is the jth standardized collaborative factor characteristic data of the i-th manufacturer; is the original data of the jth collaborative factor characteristics of the i-th producer; is the characteristic mean of the jth collaborative factor; is the characteristic standard deviation of the jth collaborative factor.

[0098] Furthermore, according to the mean of each synergistic factor characteristic and the standardized synergistic factor characteristic data of multiple manufacturers for each product, a synergistic factor characteristic association matrix is ​​constructed; wherein the synergistic factor characteristic association matrix is ​​composed of the correlation degrees between multiple ith synergistic factor characteristics and jth synergistic factor characteristics. If the correlation degree Corr[i,j] between the ith synergistic factor characteristic and the jth synergistic factor characteristic is greater than 0, it indicates that the two indicators are positively correlated, otherwise it indicates a negative correlation. The processing process of the correlation degree between the ith synergistic factor characteristic and the jth synergistic factor characteristic can be expressed as:

[0099] ;

[0100] in, is the degree of association between the i-th collaborative factor feature and the j-th collaborative factor feature; is the i-th standardized collaborative factor characteristic data of the k-th producer; is the characteristic mean of the ith collaborative factor; is the jth standardized collaborative factor characteristic data of the kth producer; is the mean characteristic value of the jth collaborative factor; m is the number of manufacturers.

[0101] Furthermore, the eigenvalues ​​and the eigenmatrix of the synergistic factor feature association matrix are determined by eigendecomposition; multiple target weights are calculated according to each initial weight, the eigenvalues ​​and the eigenmatrix of the synergistic factor feature association matrix; wherein the eigenmatrix includes eigenvectors corresponding to the eigenvalues ​​of multiple synergistic factor association matrices; the calculation process of the target weight is specifically as follows:

[0102] ;

[0103] in, is the jth target weight; is the jth initial weight; It is a fixed value, and its value is 1; is the softmax activation function; is the i-th eigenvalue of the collaborative factor feature association matrix; is the contribution of the j-th collaborative element feature to the i-th component (the eigenvector corresponding to the eigenvalue of the i-th collaborative element association matrix in the feature matrix).

[0104] Finally, the target weights and the normalized synergistic factor characteristic data of multiple manufacturers for each product are used to determine the production qualification values ​​of multiple manufacturers for each product; among them, the process of calculating the production qualification value of a certain manufacturer for a certain product, that is, the calculation process of the production qualification value of each product by the manufacturer, is specifically:

[0105] ;

[0106] in, is the production qualification value of the i-th manufacturer for the j-th product; is the jth target weight; is the j-th normalized collaborative factor characteristic data of the ith producer.

[0107] Step 103: Use the production qualification values ​​of multiple manufacturers for various products to construct an optimization objective function.

[0108] The optimization objective function is the optimization objective function of the high-order many-to-many relationship production task.

[0109] It should be noted that the present invention defines the allocation result T of each production task undertaken by the manufacturer, and the corresponding allocation result is represented by T, which is an m×n×u-dimensional matrix. Indicates whether producer i is responsible for satisfying user k's demand for product j (i.e., whether the i-th producer is responsible for satisfying the k-th user's demand for the j-th product). Next, a formal modeling of production tasks with a high-order many-to-many relationship is established, that is, the production task problem is modeled based on a high-order group role assignment model, and the corresponding optimization objective function is established; wherein, the optimization objective function is specifically:

[0110] ;

[0111] in, is the optimization objective function; u is the number of users; m is the number of manufacturers; n is the number of products; Whether the i-th manufacturer is responsible for meeting the product demand of the k-th user for the j-th product; is the production qualification value of the i-th manufacturer for the j-th product.

[0112] Step 104: Using the demand data of multiple users for each product and the maximum production capacity limit data of multiple manufacturers for each product as optimization target constraint conditions.

[0113] It should be noted that the corresponding optimization target constraint conditions are established, and the optimization target constraint conditions are specifically:

[0114] ;

[0115] in, Whether the i-th manufacturer is responsible for meeting the product demand of the k-th user for the j-th product; is the demand data of the kth user for the jth product; is the maximum production capacity limit data of the i-th manufacturer for the j-th product; u is the number of users; m is the number of manufacturers; n is the number of products.

[0116] It is worth mentioning that the above expression in the optimization objective constraint condition constructed based on the demand data of multiple users for each product and the maximum production capacity limit data of multiple manufacturers for each product is Indicates that each user's product demand can be met by multiple manufacturers, but the number of products provided by the manufacturer cannot exceed the user's demand limit; the expression It means that a sufficient number of manufacturers must be assigned to each user's product demand to ensure that each user's product demand is met; the expression It means that each manufacturer has the ability to provide multiple products to different users, but the quantity of the same product provided shall not exceed its own production capacity limit.

[0117] Step 105: construct a high-order group role assignment model based on the optimization target constraint conditions and the optimization target function, solve the high-order group role assignment model, and output the target optimal allocation plan for decision makers to make decisions.

[0118] In practical applications, step 105 uses the Pulp package in the Python language to model and calculate the high-order group role model, and can obtain the final allocation plan of production tasks with a high-order many-to-many relationship (target optimal allocation plan), and save the relevant result data; for example, see Figure 3 , Figure 3 (a) shows the allocation result of the production tasks corresponding to User1. User1's demand for product p1 is borne by Manufacturer2, while the demand for product p2 is jointly borne by Manufacturer2 and Manufacturer3.

[0119] In an embodiment of the present invention, the above scheme of the present invention provides an industrial chain manufacturer evaluation and optimal allocation method based on collaborative factor mining, firstly, obtaining demand data of multiple users for each product, maximum production capacity limit data of multiple manufacturers for each product and original data of collaborative factor characteristics of multiple manufacturers for each product; then, based on the original data of collaborative factor characteristics of multiple manufacturers for each product, evaluating the production qualifications of multiple manufacturers for each product, determining the production qualification values ​​of multiple manufacturers for each product; using the production qualification values ​​of multiple manufacturers for each product, constructing an optimization objective function; using the demand data of multiple users for each product and the maximum production capacity limit data of multiple manufacturers for each product as optimization objective constraints; finally, based on the optimization objective constraint The invention constructs a high-order group role assignment model based on constraint conditions and optimization objective functions, solves the high-order group role assignment model, and outputs the optimal target allocation plan for decision makers to make decisions; based on the above plan, the present invention evaluates and calculates the producer qualification value according to the original data of collaborative factor characteristics corresponding to each product by the producer, and constructs a high-order group role assignment model, thereby realizing real-time evaluation of the production qualifications of each product by the producers in the industrial chain, and can solve the problem of analyzing the collaborative factor characteristics of the producers in the industrial chain; by solving the high-order group role assignment model, it can realize the optimal calculation of high-order many-to-many relationship production tasks, and provide the optimal decision plan for production task allocation, thereby solving the problems of producer evaluation and formal modeling of high-order many-to-many relationship production tasks in the industrial chain and their optimal allocation under resource constraints.

[0120] For better explanation, refer to Figure 4 , showing a schematic diagram of the execution process of the method for evaluating industrial chain producers based on collaborative factor mining and their optimal allocation provided by an embodiment of the present invention. It should be pointed out that this embodiment only briefly describes the general process of evaluating industrial chain producers based on collaborative factor mining and their optimal allocation. The specific implementation process of each step can be understood by referring to the relevant content in the aforementioned embodiment, which will not be described here. It can be understood that the present invention is not limited to this.

[0121] 1. Obtain production task information data, which is the demand of each user for each product;

[0122] 2. Obtain resource restriction information data of each manufacturer involved in the production task. Different manufacturers have different production capabilities and resource distributions, so the corresponding production capabilities are different. These production capabilities constitute the manufacturer resource restriction information data;

[0123] 3. Obtain the original data of the collaborative factor characteristics of each product from each manufacturer involved in the production task (not shown to simplify the process). Different manufacturers have different original data of the collaborative factor characteristics of each product. The original data of the collaborative factor characteristics include production cost, production quality, production cycle, transportation cost and transportation time;

[0124] 4. Based on the original data of the collaborative factor characteristics of each product, the manufacturer's production qualifications for each product are evaluated to obtain the manufacturer's production qualification value for each product, thereby completing the evaluation and calculation of the manufacturer's qualification value;

[0125] 5. Formal modeling of production tasks with high-order many-to-many relationships, including: using the production qualification values ​​of manufacturers for various products to construct an optimization objective function, using production task information data and manufacturer resource restriction information data as optimization objective constraints, and constructing a high-order group role assignment model based on the optimization objective constraints and optimization objective function;

[0126] 6. Solve the optimal allocation plan for the high-order group role assignment model and obtain the production task allocation execution result (target optimal allocation plan).

[0127] Among them, the present invention performs evaluation and calculation of the manufacturer's qualification value according to the original data of the collaborative factor characteristics corresponding to each product of the manufacturer and constructs a high-order group role assignment model, so as to realize the real-time evaluation of the manufacturer's production qualifications and solve the problem of analyzing the collaborative factor characteristics of the manufacturer in the industrial chain. At the same time, the present invention proposes a high-order group role assignment model to realize efficient modeling of production task problems and solve the problem of formal modeling of high-order many-to-many relationships of production tasks in the industrial chain; in addition, the process of solving the optimal allocation plan of the high-order group role assignment model can realize the optimal calculation of production tasks and provide the optimal decision-making plan for production task allocation, thereby solving the optimal allocation problem of production tasks with high-order many-to-many relationships in the industrial chain under resource constraints, and further realizing the efficient use of production resources.

[0128] See also Figure 5 , Figure 5 A structural block diagram of an industrial chain manufacturer evaluation and optimal allocation device based on collaborative factor mining provided in an embodiment of the present invention.

[0129] The present invention provides an industrial chain manufacturer evaluation and optimal allocation device based on collaborative factor mining, comprising:

[0130] The to-be-processed data acquisition module 501 is used to acquire the demand data of multiple users for each product, the maximum production capacity limit data of multiple manufacturers for each product, and the original data of the collaborative element characteristics of multiple manufacturers for each product;

[0131] The production qualification evaluation module 502 is used to evaluate the production qualifications of multiple manufacturers for each product based on the original data of the collaborative factor characteristics of multiple manufacturers for each product, and determine the production qualification values ​​of multiple manufacturers for each product;

[0132] The optimization objective function construction module 503 is used to construct an optimization objective function using production qualification values ​​of multiple manufacturers for various products;

[0133] Constructing an optimization target constraint condition module 504, which is used to use the demand data of multiple users for each product and the maximum production capacity limit data of multiple manufacturers for each product as optimization target constraint conditions;

[0134] The optimal allocation solution solving module 505 is used to construct a high-order group role assignment model based on the optimization target constraint conditions and the optimization target function, solve the high-order group role assignment model, and output the target optimal allocation solution for decision makers to make decisions.

[0135] In an optional embodiment, the production qualification evaluation module 502 is specifically used to:

[0136] Normalize the maximum and minimum values ​​of the original data of the synergistic factor characteristics of each manufacturer for each product, and determine the normalized synergistic factor characteristic data of multiple manufacturers for each product;

[0137] Performing mean calculation on normalized collaborative factor feature data of various products of multiple manufacturers, and outputting multiple collaborative factor feature means;

[0138] Calculate the standard deviation of the normalized synergistic factor characteristic data of various products of multiple manufacturers and the mean values ​​of multiple synergistic factor characteristics, and output multiple synergistic factor characteristic standard deviations;

[0139] Based on the characteristic standard deviations of multiple collaborative factors, determining the initial weight corresponding to the characteristic standard deviation of each collaborative factor;

[0140] The original data of collaborative factor characteristics of various products from multiple manufacturers are standardized by using each initial weight and each collaborative factor characteristic standard deviation, and the standardized collaborative factor characteristic data of various products from multiple manufacturers are output;

[0141] According to the mean value of each collaborative factor characteristic and the standardized collaborative factor characteristic data of multiple manufacturers for each product, a collaborative factor characteristic correlation matrix is ​​constructed;

[0142] Perform eigendecomposition on the collaborative factor feature association matrix to determine the eigenvalues ​​of the collaborative factor feature association matrix and its feature matrix;

[0143] Calculate multiple target weights based on each initial weight, the eigenvalue of the collaborative element feature association matrix and its feature matrix;

[0144] The target weights and the normalized synergistic factor characteristic data of multiple manufacturers for each product are used to determine the production qualification values ​​of multiple manufacturers for each product.

[0145] In an optional embodiment, the calculation process of the production qualification value of each product by the manufacturer is specifically as follows:

[0146] ;

[0147] in, is the production qualification value of the i-th manufacturer for the j-th product; is the jth target weight; is the j-th normalized collaborative factor characteristic data of the ith producer.

[0148] In an optional embodiment, the optimization objective function is specifically:

[0149] ;

[0150] in, is the optimization objective function; u is the number of users; m is the number of manufacturers; n is the number of products; Whether the i-th manufacturer is responsible for meeting the product demand of the k-th user for the j-th product; is the production qualification value of the i-th manufacturer for the j-th product.

[0151] In an optional embodiment, the optimization target constraint condition is specifically:

[0152] ;

[0153] in, Whether the i-th manufacturer is responsible for meeting the product demand of the k-th user for the j-th product; is the demand data of the kth user for the jth product; is the maximum production capacity limit data of the i-th manufacturer for the j-th product; u is the number of users; m is the number of manufacturers; n is the number of products.

[0154] In an optional embodiment, the target weight calculation process is specifically as follows:

[0155] ;

[0156] in, is the jth target weight; is the jth initial weight; It is a fixed value, and its value is 1; is the softmax activation function; is the i-th eigenvalue of the collaborative factor feature association matrix; is the contribution of the j-th collaborative element feature to the i-th component (the eigenvector corresponding to the eigenvalue of the i-th collaborative element association matrix in the feature matrix).

[0157] In an optional embodiment, the calculation process of the collaborative element feature mean is specifically as follows:

[0158] ;

[0159] in, is the characteristic mean of the jth collaborative factor; is the j-th normalized collaborative factor characteristic data of the ith producer; m is the number of producers.

[0160] In an optional embodiment, the calculation process of the standard deviation of the collaborative element characteristics is specifically as follows:

[0161] ;

[0162] in, is the characteristic standard deviation of the jth collaborative factor; is the characteristic mean of the jth collaborative factor; is the j-th normalized collaborative factor characteristic data of the ith producer; m is the number of producers.

[0163] In an optional embodiment, the calculation process of the initial weight is specifically as follows:

[0164] ;

[0165] in, is the characteristic standard deviation of the jth collaborative factor; is the jth initial weight; is the sum of the standard deviations of the synergistic factors’ characteristics.

[0166] In an optional embodiment, the calculation process of the standardized collaborative element feature data is specifically as follows:

[0167] ;

[0168] in, is the jth standardized collaborative factor characteristic data of the i-th manufacturer; is the original data of the jth collaborative factor characteristics of the i-th producer; is the characteristic mean of the jth collaborative factor; is the characteristic standard deviation of the jth collaborative factor.

[0169] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the aforementioned method embodiment.

[0170] An embodiment of the present invention further provides an electronic device, the device comprising a processor and a memory:

[0171] The memory is used to store the program code and transmit the program code to the processor;

[0172] The processor is used to execute the industrial chain producer evaluation and its optimal allocation method based on collaborative factor mining according to the instructions in the program code of any embodiment of the present invention.

[0173] An embodiment of the present invention also provides a computer-readable storage medium, which is used to store program code, and the program code is used to execute the industrial chain producer evaluation and its optimal allocation method based on collaborative factor mining according to any embodiment of the present invention.

[0174] An embodiment of the present invention also provides a computer program product, including a computer program / instruction, which is executed by a processor to provide an industrial chain producer evaluation and optimal allocation method based on collaborative factor mining according to any embodiment of the present invention.

[0175] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0176] In the several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as 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 devices or units, which can be electrical, mechanical or other forms.

[0177] 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 network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0178] 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.

[0179] 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. The computer software product is stored in a storage medium, including several 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, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0180] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for evaluating and optimally allocating industrial chain manufacturers based on collaborative factor mining, characterized in that: include: Obtaining demand data for various products from multiple users, maximum production capacity limit data for various products from multiple manufacturers, and original data on collaborative factor characteristics for various products from multiple manufacturers; According to the original data of the collaborative factor characteristics of the multiple manufacturers for each product, the production qualifications of the multiple manufacturers for each product are evaluated to determine the production qualification values ​​of the multiple manufacturers for each product; Using the production qualification values ​​of the multiple manufacturers for each product, constructing an optimization objective function; Taking the demand data of the plurality of users for each product and the maximum production capacity limit data of the plurality of manufacturers for each product as optimization target constraint conditions; A high-order group role assignment model is constructed based on the optimization target constraint conditions and the optimization target function, and the high-order group role assignment model is solved to output the target optimal allocation plan for decision makers to make.

2. The method for evaluating and optimally allocating industrial chain manufacturers based on collaborative factor mining according to claim 1 is characterized in that: The step of evaluating the production qualifications of the multiple manufacturers for the various products based on the original data of the collaborative factor characteristics of the multiple manufacturers for the various products and determining the production qualification values ​​of the multiple manufacturers for the various products includes: Normalizing the original data of the synergistic factor characteristics of each product of each manufacturer to the maximum and minimum values, and determining the normalized synergistic factor characteristic data of multiple manufacturers for each product; Performing mean calculation on the normalized collaborative factor feature data of the multiple manufacturers for each product, and outputting multiple collaborative factor feature means; Calculating standard deviations of normalized synergistic factor feature data of multiple manufacturers for each product and multiple synergistic factor feature means, and outputting multiple synergistic factor feature standard deviations; Based on the plurality of collaborative element characteristic standard deviations, determining an initial weight corresponding to each of the collaborative element characteristic standard deviations; Using each of the initial weights and each of the standard deviations of the collaborative factor characteristics to standardize the original data of the collaborative factor characteristics of the multiple manufacturers for each of the products, and outputting the standardized collaborative factor characteristic data of the multiple manufacturers for each of the products; Constructing a synergistic factor characteristic association matrix according to the mean values ​​of the synergistic factor characteristics and the standardized synergistic factor characteristic data of the multiple manufacturers for each product; Performing eigendecomposition on the collaborative factor feature association matrix to determine the eigenvalues ​​of the collaborative factor feature association matrix and its eigenmatrix; Calculating a plurality of target weights according to each of the initial weights, the eigenvalues ​​of the collaborative element feature association matrix and its feature matrix; The target weights and the normalized collaborative factor characteristic data of the multiple manufacturers for each product are used to determine the production qualification values ​​of the multiple manufacturers for each product.

3. The method for evaluating and optimally allocating industrial chain manufacturers based on collaborative factor mining according to claim 2 is characterized in that: The calculation process of the manufacturer's production qualification value for each product is specifically as follows: ； in, is the production qualification value of the i-th manufacturer for the j-th product; is the jth target weight; is the j-th normalized collaborative factor characteristic data of the ith producer.

4. The method for evaluating and optimally allocating industrial chain manufacturers based on collaborative factor mining according to claim 1 is characterized in that: The optimization objective function is specifically: ； in, is the optimization objective function; u is the number of users; m is the number of manufacturers; n is the number of products; Whether the i-th manufacturer is responsible for meeting the product demand of the k-th user for the j-th product; is the production qualification value of the i-th manufacturer for the j-th product.

5. The method for evaluating and optimally allocating industrial chain manufacturers based on collaborative factor mining according to claim 1 is characterized in that: The optimization objective constraints are specifically: ； in, Whether the i-th manufacturer is responsible for meeting the product demand of the k-th user for the j-th product; is the demand data of the kth user for the jth product; is the maximum production capacity limit data of the i-th manufacturer for the j-th product; u is the number of users; m is the number of manufacturers; n is the number of products.

6. The method for evaluating and optimally allocating industrial chain manufacturers based on collaborative factor mining according to claim 3 is characterized in that: The calculation process of the target weight is specifically as follows: ； in, is the jth target weight; is the jth initial weight; It is a fixed value, and its value is 1; is the softmax activation function; is the i-th eigenvalue of the collaborative factor feature association matrix; is the contribution of the j-th collaborative element feature to the i-th component (the eigenvector corresponding to the eigenvalue of the i-th collaborative element association matrix in the feature matrix).

7. The method for evaluating and optimally allocating industrial chain manufacturers based on collaborative factor mining according to claim 2 is characterized in that: The calculation process of the collaborative factor feature mean is specifically as follows: ； in, is the characteristic mean of the jth collaborative factor; is the j-th normalized collaborative factor characteristic data of the ith producer; m is the number of producers.

8. The method for evaluating and optimally allocating industrial chain manufacturers based on collaborative factor mining according to claim 2 is characterized in that: The calculation process of the standard deviation of the collaborative factor characteristics is specifically as follows: ； in, is the characteristic standard deviation of the jth collaborative factor; is the characteristic mean of the jth collaborative factor; is the j-th normalized collaborative factor characteristic data of the ith producer; m is the number of producers.

9. The method for evaluating and optimally allocating industrial chain manufacturers based on collaborative factor mining according to claim 2 is characterized in that: The calculation process of the initial weight is specifically as follows: ； in, is the characteristic standard deviation of the jth collaborative factor; is the jth initial weight; is the sum of the standard deviations of the synergistic factors’ characteristics.

10. The method for evaluating and optimally allocating industrial chain manufacturers based on collaborative factor mining according to claim 2 is characterized in that: The calculation process of the standardized collaborative element feature data is specifically as follows: ； in, is the jth standardized collaborative factor characteristic data of the i-th manufacturer; is the original data of the jth collaborative factor characteristics of the i-th producer; is the characteristic mean of the jth collaborative factor; is the characteristic standard deviation of the jth collaborative factor.

Images