Supplier recommendation system and method based on large model

Abstract

The invention relates to the technical field of enterprise management, and particularly discloses a supplier recommendation system and method based on a large model, and the method comprises the steps: obtaining historical supplier data, constructing a supplier similar matrix, constructing a classification model through employing a hierarchical clustering algorithm, determining the same type of suppliers, and then analyzing the data of the same type of suppliers, obtaining similar characterization values Ts, constructing a model training data set, constructing a supplier large model based on different algorithms, determining a target model algorithm through comparative analysis, analyzing and adjusting training times according to related numerical values of the target model algorithm, determining a recommendation model algorithm, and outputting recommendation suppliers; the system comprises a data acquisition module, a classification judgment module, a data analysis module, a model construction module and a model determination module. The supplier data can be effectively processed, the accuracy and reliability of supplier recommendation are improved through various algorithms and analysis means, and powerful support is provided for enterprise purchase.

Description

Technical Field

[0001] The present invention relates to the technical field of enterprise management, and in particular to a supplier recommendation system and method based on a large model. Background Art

[0002] As the market becomes increasingly complex and the scale of corporate business continues to expand, how to accurately select partners that meet corporate needs from a large number of suppliers has become a key challenge facing companies.

[0003] A Chinese patent application with announcement number CN112927037B discloses a supplier recommendation method and system, including: receiving at least one supplier sample; predicting the recommended operation corresponding to each supplier sample based on an adaptive multi-layer perception online transfer learning model; tracking and obtaining the actual adoption effect of each supplier sample by supplier users; adjusting the weight distribution and nonlinear parameter vector between the user characteristics of the previous batch and the user characteristics of the current batch of purchasing users served by the adaptive multi-layer perception online transfer learning model based on the comparison between the recommended operation and the actual adoption effect; re-acquiring new supplier samples and predicting the corresponding recommended operation with the adjusted online transfer learning model, and repeating the above steps until all supplier samples that meet the needs of supplier users are screened out.

[0004] In model construction, the existing technology selects a relatively single algorithm and only uses an adaptive multi-layer perception online transfer learning model. It has certain limitations in capturing the complex nonlinear relationships and dynamic change characteristics of supplier data. It cannot adapt to the advantages brought by the collaboration of multiple algorithms and cannot meet the diverse needs of different types of supplier data. If a large supplier model is built through multiple algorithms and the optimal model algorithm is determined through comparison, it can better adapt to complex data characteristics and changes in enterprise needs.

[0005] When adjusting the model, the existing technology only considers the weight distribution of user characteristics and the nonlinear parameter vector, and does not comprehensively consider multiple factors such as weight ratio, similar misjudgment mean, and similar characterization value to dynamically adjust the number of model training times and determine the recommendation model algorithm; through the dynamic adjustment mechanism, the model performance can be more comprehensively optimized and the reliability of supplier recommendations can be improved. Summary of the invention

[0006] The purpose of the present invention is to provide a supplier recommendation system and method based on a large model to solve the above background problems.

[0007] The purpose of the present invention can be achieved through the following technical solutions: A supplier recommendation method based on a large model includes the following steps: Step 1: Obtain historical supplier data and store it in a supplier data group, perform similarity analysis on the supplier data group, and build a supplier similarity matrix ; Step 2: Based on the supplier similarity matrix , build a supplier classification model to identify the same suppliers in different categories; Step 3: Perform numerical analysis on the supplier similarity of the same type of suppliers in the same category to obtain the central similarity difference Zx, obtain the historical supply times of suppliers in the same category, and perform numerical calculations to obtain the same type characterization value Ts, sort the same type of suppliers based on the same type characterization value Ts, and construct a model training data set; Step 4: Based on the model training data set, use different algorithms to build a supplier model, output recommended suppliers based on the supplier model, and conduct comparative analysis to determine the target model algorithm; Step 5: Based on the target model algorithm, perform numerical analysis on the output results of the target model algorithm to obtain the training enhancement ratio Xlq of the target model algorithm, and dynamically adjust the training times of the supplier large model of the target model algorithm. Based on the dynamically adjusted target algorithm model, determine the supplier large model corresponding to the recommended model algorithm, and determine the recommended supplier.

[0008] As a further technical solution of the present invention: the supplier similarity matrix The way to obtain is: Based on the internal procurement management system of the enterprise, the historical transaction record data between the enterprise and different suppliers is obtained, and the historical transaction record data of different suppliers is used as the supplier data set a i ; Among them, the historical transaction records include the supplier's goods category and time limit, i is the supplier's number, i=1,2,...,n, n is the number of suppliers; Put all supplier data sets into the supplier data group and construct the supplier data group A, where A={a1, a2, ...a n}; Extract supplier data set a i The goods category data in is used as the goods category c i , calculate the supplier similarity G of different supplier data sets ij ; By formula: Get the supplier similarity G of the supplier data set ij ; where j=i+1, i+2,...,n, Represents the supplier data set c i With c j The number of intersections, Represents the supplier data set c i With c j The number of unions, X 12 The supplier similarity G between two suppliers with supplier numbers 1 and 2 ij ; Based on the supplier similarity G in different supplier data ij , construct supplier similarity matrix S ij ; Construct the supplier similarity matrix S ij = ; The supplier similarity matrix S ij Perform preprocessing to remove the supplier similarity matrix S ij The meaningless data in the matrix includes the matrix diagonal and the data in the upper triangle of the matrix. The preprocessed supplier similarity matrix is ​​marked as .

[0009] As a further technical solution of the present invention: the method of obtaining the same type of suppliers of different categories is: Supplier Similarity Matrix Use hierarchical clustering algorithm to identify unique suppliers and homogeneous suppliers; The supplier classification model is constructed as follows: S1. Calculate the similarity distance d(i,j) by the formula: Get the similarity distance d(i,j), and construct a similarity distance matrix based on the similarity distance d(i,j); S2. Input the supplier matrix into the hierarchical clustering algorithm. The hierarchical clustering algorithm establishes different clusters based on the similarity distance d(i,j), calculates the distance between each cluster, and updates and iterates each cluster. S3. Analyze the clusters output by the hierarchical clustering algorithm. If there is only one supplier in the cluster, mark the corresponding supplier as the only supplier. If there are multiple suppliers in the cluster, mark the suppliers in the cluster as the same type of suppliers.

[0010] As a further technical solution of the present invention: the model training data set is constructed in the following manner: Sort the elements of the same level of detail sequence in descending order of the same level of characterization value Ts; Get all unique suppliers and put all unique suppliers into the unique supplier sequence; Obtain similarity sequences and unique supplier sequences of all categories that have been sorted, and build a model training data set.

[0011] As a further technical solution of the present invention: the same type characterization value Ts is obtained in the following manner: Get the historical supply times of the same type of supplier in the same category and the historical supply times of all suppliers of the same type; The historical supply times of the same supplier and the historical supply times of all the same suppliers are compared to obtain the same supply ratio, which is marked as T1; The supplier similarities of the same suppliers in the same category are arranged in descending order, and the sorted suppliers of the same type are taken as elements and put into the similarity sequence of the same type; Get the total number of elements of the same similarity sequence, mark the total number of elements as Zs, and make parity judgment on the total number of elements; If the total number of elements Zs is an odd number, obtain the similarity sequence of the same type. The similarity of suppliers is taken as the central similarity; If the total number of elements Zs is an even number, obtain the similarity between the (Zs / 2)th and (Zs / 2+1)th suppliers in the same similarity sequence, sum and average the similarities between the (Zs / 2)th and (Zs / 2+1)th suppliers in the similarity sequence, and obtain the central similarity; Based on the similarity sequence of the same type, calculate the difference between each element and the center similarity of the similarity sequence, obtain the center similarity difference, and mark the center similarity difference as Zx; Based on the center similarity difference Zx and the similar supply ratio TI, calculate the similar characterization value Ts; By formula: Get the same type of characterization value Ts, f and g are preset proportional coefficients.

[0012] As a further technical solution of the present invention: the target model algorithm is constructed as follows: Based on the model training data set, different algorithms are used to build a large supplier model; The supplier model built based on different algorithms inputs the category and timeliness of goods, outputs recommended suppliers, and compares the recommended suppliers with the actual suppliers; If the recommended supplier is inconsistent with the actually adopted supplier, the supplier will be marked as a misjudged supplier; If the recommended supplier is consistent with the actually adopted supplier, the supplier is marked as the adopted supplier; Obtain the number of misjudged suppliers in the supplier big models constructed by different algorithms, as well as the number of recommended suppliers output by the supplier big models; The number of misjudged suppliers is compared with the number of recommended suppliers output by the suppliers to obtain the misjudgment value ratio; Calculate the supplier model constructed by different algorithms, output recommended suppliers and misjudgment ratios multiple times, sum and average the misjudgment ratios output multiple times to obtain the mean of the misjudgment ratios; If the mean value of the false positive ratio is lower than the false positive threshold, the algorithm corresponding to the supplier's large model is obtained, and the model constructed by the corresponding algorithm is marked as the target model algorithm.

[0013] As a further technical solution of the present invention: the method of dynamically adjusting the number of supplier large model training times of the target model algorithm is: Obtain the supplier large model training times Mxc of the target model algorithm, calculate the additional training times of the target model algorithm, and mark the additional training times of the target model algorithm as Ew; Based on the additional training times Ew of the target model algorithm and the training enhancement ratio Xlq of the target model algorithm, the additional training times Ew of the target model algorithm are calculated; By formula: Get the additional training times of the target model algorithm; Based on the additional training times of the target model algorithm, the training times of the supplier large model constructed by the target model algorithm are dynamically adjusted.

[0014] As a further technical solution of the present invention: the training enhancement ratio Xlq of the target model algorithm is obtained as follows: Obtain the number of adopted suppliers output by the target model algorithm and the number of recommended suppliers output by the target model algorithm; The number of adopted suppliers output by the target model algorithm is compared with the number of recommended suppliers output by the target model algorithm to obtain the adopted supply ratio; Obtain the adoption supply ratios of all target model algorithms, sum the adoption supply ratios of all target algorithms, and obtain the total adoption ratio value; The adoption supply ratio is processed by comparing it with the total value of the adoption ratio to obtain the adoption weight ratio, and the adoption weight ratio is marked as Cnq; Obtain the target model algorithm output, the supplier similarity corresponding to the misjudged supplier, and the similarity corresponding to the actually adopted supplier; Perform difference processing on the supplier similarity corresponding to the misjudged supplier and the similarity corresponding to the actually adopted supplier to obtain the misjudged similarity difference; Obtain the misjudgment similarity differences output by the target model algorithm multiple times, sum and average the misjudgment similarity differences output multiple times, obtain the misjudgment similarity mean, and mark the misjudgment similarity mean as Wp; Obtain the misjudged suppliers output by the target model algorithm, and compare and analyze the misjudged suppliers with the supplier categories output by the hierarchical clustering algorithm; If the supplier is misjudged as a supplier of the same type, obtain the same type characterization value Ts of the supplier; Based on the adopted weight ratio Cnq, the misjudgment similarity mean Wp, and the misjudged supplier's similar characterization value Ts, the training enhancement ratio Xlq of the target model algorithm is calculated; By formula: Obtain the training enhancement ratio Xlq of the target model algorithm, where α=0.561, β=0.487, z is the total number of misjudged suppliers output by the target model algorithm, c=1, 2, ..., z; if the misjudged supplier is a supplier of the same type, then γ=1, otherwise, γ=0.

[0015] As a further technical solution of the present invention: the method for determining the supplier macro model corresponding to the recommendation model algorithm is as follows: Based on the dynamically adjusted target model algorithm and the mean error ratio of the target model algorithm, all the mean error ratios of the target model algorithms are arranged in ascending order, and the target model algorithm corresponding to the minimum mean error ratio is selected as the recommended model algorithm; The recommended suppliers are obtained as follows: Based on the supplier model constructed by the recommendation model algorithm, the recommended suppliers are output.

[0016] A supplier recommendation system based on a large model, comprising: Data collection module: obtain historical supplier data and store it in the supplier data group, perform similarity analysis on the supplier data group, and build a supplier similarity matrix ; Classification and discrimination module: based on supplier similarity matrix , build a supplier classification model to identify the same suppliers in different categories; Data analysis module: Perform numerical analysis on the supplier similarity of the same type of suppliers in the same category to obtain the central similarity difference Zx, obtain the historical supply times of suppliers in the same category, and perform numerical calculations to obtain the same type characterization value Ts. Based on the same type characterization value Ts, the same type of suppliers are sorted to build a model training data group; Model building module: Based on the model training data set, use different algorithms to build a supplier model, recommend suppliers based on the supplier model output, and conduct comparative analysis to determine the target model algorithm; Model determination module: Based on the target model algorithm, perform numerical analysis on the output results of the target model algorithm to obtain the training enhancement ratio Xlq of the target model algorithm, and dynamically adjust the training times of the supplier large model of the target model algorithm. Based on the dynamically adjusted target algorithm model, determine the supplier large model corresponding to the recommended model algorithm and determine the recommended supplier.

[0017] Beneficial effects of the present invention: Through in-depth mining and analysis of historical supplier data, we build supplier similarity matrices, classification models, and supplier big models built using algorithms. We are able to identify and screen suppliers that meet the needs of the enterprise. By analyzing multi-dimensional factors such as product category, timeliness, and number of deliveries, we select a variety of algorithms to build a supplier big model. Through complex calculations and model training, we continuously optimize the accuracy of the big model's recommendations on suppliers.

[0018] Based on the training reinforcement ratio of the target model algorithm, the training times of the supplier large model are dynamically adjusted. In actual application, as the market environment and corporate procurement needs continue to change, the model can continuously adapt to new data features and business needs. The dynamic optimization mechanism enables the model to maintain a high level of prediction accuracy and recommendation quality, and can provide companies with the most appropriate supplier recommendation solutions under different market conditions and corporate development stages. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The present invention will be further described below in conjunction with the accompanying drawings.

[0020] Figure 1 is a flow chart of a supplier recommendation method based on a large model of the present invention; Figure 2 It is a device module diagram of a supplier recommendation system based on a large model of the present invention; Figure 3 The present invention discloses a structural diagram of a device and storage medium of a supplier recommendation system based on a large model. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 are within the scope of protection of the present invention.

[0022] Example 1: Please refer to Figure 1 As shown, the present invention is a supplier recommendation method based on a large model, comprising: Step 1: Obtain historical supplier data and store it in a supplier data group, perform similarity analysis on the supplier data group, and build a supplier similarity matrix ; Based on the internal procurement management system of the enterprise, the historical transaction record data between the enterprise and different suppliers is obtained, and the historical transaction record data of different suppliers is used as the supplier data set a i ; The supplier data group contains historical transaction records of multiple suppliers, including data such as the category and time limit of goods supplied by the supplier; Where i is the supplier number, i=1,2,...,n, n is the number of suppliers; Put all supplier data sets into the supplier data group and construct the supplier data group A, where A={a1, a2, ...a n}; Extract supplier data set a i The goods category data in is used as the goods category c i , calculate the supplier similarity G of different supplier data sets ij ; By formula: Get the supplier similarity G of the supplier data set ij ; where j=i+1, i+2,...,n, Represents the supplier data set c i With c j The number of intersections, Represents the supplier data set c i With c j The number of unions, X 12 The supplier similarity G between two suppliers with supplier numbers 1 and 2 ij ; Based on the supplier similarity G in different supplier data ij , construct supplier similarity matrix S ij ; Among them, the supplier similarity matrix is ​​constructed as S ij = ; The supplier similarity matrix S ij Perform preprocessing to remove the supplier similarity matrix S ij The meaningless data in the matrix includes the matrix diagonal and the data in the upper triangle of the matrix. The preprocessed supplier similarity matrix is ​​marked as ; It should be noted that the matrix diagonal G ii Elements, such as G 11 Indicates the supplier similarity of the commodity category c1 in the supplier data set. The upper triangular elements of the matrix have the same meaning as the lower triangular elements. For example, G 12 , G 21 The supplier similarity between the goods category c1 in the supplier data set and the goods category c2 in the supplier data set indicates that they have the same meaning, so they are removed; For example, ; Step 2: Based on the supplier similarity matrix , build a supplier classification model to identify the same suppliers in different categories; Supplier Similarity Matrix Use hierarchical clustering algorithm to identify unique suppliers and homogeneous suppliers; Specifically, the supplier classification model is constructed as follows: S1. Calculate the similarity distance d(i,j) by the formula: Get the similarity distance d(i,j), and construct a similarity distance matrix based on the similarity distance d(i,j); It should be noted that the smaller the similarity distance d(i, j), the more similar the two suppliers are; S2. Input the supplier matrix into the hierarchical clustering algorithm. The hierarchical clustering algorithm establishes different clusters based on the similarity distance d(i,j), calculates the distance between each cluster, and updates and iterates each cluster until the distance between each cluster is less than the cluster threshold; It should be noted that, in the initial state, the hierarchical clustering algorithm assigns each supplier a i Treat it as a cluster, calculate the similarity distance d(i,j) between all clusters, find the two clusters with the closest similarity distance, merge the two clusters into one cluster, update the similarity distance between clusters, and stop the merging operation between clusters when the similarity distance between clusters is less than the cluster threshold. The cluster threshold is set by professionals in this field; S3, analyzing the clusters output by the hierarchical clustering algorithm. If there is only one supplier in the cluster, mark the corresponding supplier as the only supplier. If there are multiple suppliers in the cluster, mark the suppliers in the cluster as the same type of suppliers. It should be noted that there are multiple clusters in the hierarchical clustering algorithm, that is, there are different categories of the same type of suppliers; The same type of suppliers belonging to the same cluster are marked as b ki , k = 1, 2, ..., m, m is the number of remaining clusters after removing the cluster containing the only supplier in the hierarchical clustering algorithm, that is, the number of categories of the same supplier, and i is the supplier number; For example, when k=1, i=1,2, b 11 、b 12 indicates that two suppliers of the same type are both in category k 1, b 11 、b 12 They are suppliers of the same type; The technical solution of this embodiment is: obtain historical supplier data and store it in a supplier data group, perform similarity analysis on the supplier data group, and construct a supplier similarity matrix , based on the supplier similarity matrix , build a supplier classification model, identify the same suppliers in different categories, and provide data support for subsequent supplier analysis.

[0023] Example 2: Please refer to Figure 1 As shown, the supplier recommendation method based on the large model of the present invention also includes: Step 3: Perform numerical analysis on the supplier similarity of the same type of suppliers in the same category to obtain the central similarity difference Zx, combine the historical supply times of the same category and perform numerical calculation to obtain the same type characterization value Ts, sort the same type of suppliers based on the same type characterization value Ts, and construct a model training data set; Get the historical supply times of the same supplier in the same category; The historical supply times of all suppliers of the same type in the same category; The historical supply times of the same supplier and the historical supply times of all the same suppliers are compared to obtain the same supply ratio, which is marked as T1; Get the center similarity of the same type of suppliers in the same category; Specifically, the center similarity is obtained as follows: The similarities of suppliers of the same type in the same category are arranged in descending order, and the sorted suppliers of the same type are taken as elements and put into the similarity sequence of the same type; Get the total number of elements of the same similarity sequence, mark the total number of elements as Zs, and make parity judgment on the total number of elements; If the total number of elements Zs is an odd number, obtain the similarity sequence of the same type. The similarity of suppliers is taken as the central similarity; It should be noted that It means that the total number of elements Zs is ratioed to 2 and rounded up. For example, if the total number of elements Zs is 5, the ratio of Zs to 2 is 2.5, which is rounded up to 3. The similarity of the third supplier in the same similarity sequence is taken as the central similarity. If the total number of elements Zs is an even number, obtain the similarity between the (Zs / 2)th and (Zs / 2+1)th suppliers in the same similarity sequence, sum and average the similarities between the (Zs / 2)th and (Zs / 2+1)th suppliers in the similarity sequence, and obtain the central similarity; Based on the similarity sequence of the same type, calculate the difference between each element and the center similarity of the similarity sequence, obtain the center similarity difference, and mark the center similarity difference as Zx; Based on the center similarity difference Zx and the similar supply ratio TI, calculate the similar characterization value Ts; By formula: Obtain the same type of characterization value Ts, f=0.683, g=0.789; Sort the elements of the same level of detail sequence in descending order of the same level of characterization value Ts; Get all unique suppliers and put all unique suppliers into the unique supplier sequence; Obtain similarity sequences and unique supplier sequences of all categories that have been sorted, and construct a model training data set; It should be noted that the elements in the similarity sequence are sorted according to the similarity characterization value Ts, and the priority of suppliers in the same category is determined by sorting. The similarity characterization value Ts comprehensively considers the central similarity difference Zx and the similarity supply ratio Tl, which can more comprehensively reflect the importance of the supplier in the category. Through sorting, suppliers with larger similarity characterization values ​​Ts can be regarded as more critical suppliers in the corresponding category, providing data support for the construction of the subsequent supplier model. Step 4: Based on the model training data set, use different algorithms to build a supplier model, output recommended suppliers based on the supplier model, and conduct comparative analysis to determine the target model algorithm; Based on the model training data set, different algorithms are used to build a large supplier model; Among them, the supplier model is constructed by different algorithms such as graph convolutional network (GCN), graph attention network (GAT), multi-layer perceptron (MLP), etc. It should be noted that the graph convolutional network can use suppliers and buyers as nodes in the graph, and purchase behaviors as edges. The graph convolution operation is used to learn the supplier similarity and timeliness of the supplier nodes. Since the model training data group sorts the same suppliers, the sorting order is used as the weight of each supplier for model training, which is input into the graph convolutional network and model training is performed to obtain recommended suppliers. The graph attention network uses the attention mechanism to learn the weights between nodes, integrates supplier similarity and timeliness into the attention mechanism, and improves the influence of similar suppliers with similarities. The graph attention network can capture the complex relationship between buyers and suppliers, and then obtain recommended suppliers; The multi-layer perceptron model is used to learn the nonlinear relationship between suppliers and goods. It takes supplier similarity and timeliness as input features, encodes the supplier similarity and timeliness information of similar suppliers, and then splices the characteristic information of other suppliers and inputs it into the multi-layer perceptron model for training to obtain recommended suppliers. The supplier model built based on different algorithms inputs the category and timeliness of goods, outputs recommended suppliers, and compares the recommended suppliers with the actual suppliers; If the recommended supplier is inconsistent with the actually adopted supplier, the supplier will be marked as a misjudged supplier; If the recommended supplier is consistent with the actually adopted supplier, the supplier is marked as the adopted supplier; Obtain the number of misjudged suppliers in the supplier big models constructed by different algorithms, as well as the number of recommended suppliers output by the supplier big models; The number of misjudged suppliers is compared with the number of recommended suppliers output by the suppliers to obtain the misjudgment value ratio; Calculate the supplier model constructed by different algorithms, output recommended suppliers and misjudgment ratios multiple times, sum and average the misjudgment ratios output multiple times to obtain the mean of the misjudgment ratios; Compare the mean value of the false positive ratio with the false positive threshold to determine the target model algorithm; If the mean value of the false positive ratio is higher than the false positive threshold, the algorithm corresponding to the supplier's large model is obtained, and the algorithm is marked as a non-target model algorithm; If the mean value of the false positive ratio is lower than the false positive threshold, the algorithm corresponding to the supplier's large model is obtained, and the model constructed by the corresponding algorithm is marked as the target model algorithm; It should be noted that there are multiple target model algorithms; Step 5: Based on the target model algorithm, numerically analyze the output results of the target model algorithm to obtain the training enhancement ratio Xlq of the target model algorithm. Based on the training enhancement ratio Xlq of the target model algorithm, dynamically adjust the number of supplier large model trainings of the target model algorithm. Based on the dynamically adjusted target algorithm model, determine the supplier large model corresponding to the recommended model algorithm, and determine the recommended supplier. Obtain the number of adopted suppliers output by the target model algorithm and the number of recommended suppliers output by the target model algorithm; The number of adopted suppliers output by the target model algorithm is compared with the number of recommended suppliers output by the target model algorithm to obtain the adopted supply ratio; Obtain the adoption supply ratios of all target model algorithms, sum the adoption supply ratios of all target algorithms, and obtain the total adoption ratio value; The adoption supply ratio is processed by comparing it with the total value of the adoption ratio to obtain the adoption weight ratio, and the adoption weight ratio is marked as Cnq; Obtain the target model algorithm output, the supplier similarity corresponding to the misjudged supplier, and the similarity corresponding to the actually adopted supplier; Perform difference processing on the supplier similarity corresponding to the misjudged supplier and the similarity corresponding to the actually adopted supplier to obtain the misjudged similarity difference; Obtain the misjudgment similarity differences output by the target model algorithm multiple times, sum and average the misjudgment similarity differences output multiple times, obtain the misjudgment similarity mean, and mark the misjudgment similarity mean as Wp; Obtain the misjudged suppliers output by the target model algorithm, and compare and analyze the misjudged suppliers with the supplier categories output by the hierarchical clustering algorithm; If a supplier is mistakenly identified as the sole supplier, no action will be taken; If the supplier is misjudged as a supplier of the same type, obtain the same type characterization value Ts of the supplier; Based on the adopted weight ratio Cnq, the misjudgment similarity mean Wp, and the misjudged supplier's similar characterization value Ts, the training enhancement ratio Xlq of the target model algorithm is calculated; By formula: Obtain the training enhancement ratio Xlq of the target model algorithm, where α=0.561, β=0.487, z is the total number of misjudged suppliers output by the target model algorithm, c=1, 2, ..., z; if the misjudged supplier is a supplier of the same type, then γ=1, otherwise, γ=0; It should be noted that the adoption weight ratio Cnq highlights the relative advantages or disadvantages of a single target model algorithm in the overall. When the adoption weight ratio Cnq is high, it means that the adoption supply ratio of the target model algorithm is relatively prominent among all target model algorithms, and it accounts for a large proportion of the overall recommendation effect. Therefore, the target algorithm with a higher adoption weight ratio Cnq should require fewer additional training times. The misjudgment similarity mean Wp quantifies the difference in similarity between the misjudged suppliers and the actual adopted suppliers. The higher the misjudgment similarity mean Wp, the higher the average level of misjudgment similarity differences output by the target model algorithm. That is, the model has a large error in judging the supplier similarity, and there is a large room for improvement. The number of model training times needs to be increased. If there is a misjudgment of a supplier of the same type, if the misjudged supplier's similar characterization value Ts is high, it means that the misjudged supplier of the same type has a higher importance or uniqueness in the same type. When calculating the similar characterization value Ts of the misjudged supplier, combined with other parameters, a higher similar characterization value Ts of the misjudged supplier will make the model pay more attention to the learning and adjustment of the relevant features of such misjudged suppliers, thereby increasing the number of training reinforcements; Obtain the supplier large model training times Mxc of the target model algorithm, calculate the additional training times of the target model algorithm, and mark the additional training times of the target model algorithm as Ew; By formula: Get the additional training times of the target model algorithm; Based on the additional training times of the target model algorithm, the training times of the supplier large model constructed by the target model algorithm are dynamically adjusted; Based on the dynamically adjusted target model algorithm and the mean error ratio of the target model algorithm, all the mean error ratios of the target model algorithms are arranged in ascending order, and the target model algorithm corresponding to the minimum mean error ratio is selected as the recommended model algorithm; Based on the supplier model constructed by the recommendation model algorithm, the recommended suppliers are output; The technical solution of this embodiment is: numerically analyze the supplier similarity of the same type of suppliers in the same category to obtain the central similarity difference Zx, obtain the historical supply times of suppliers in the same category, and perform numerical calculations to obtain the same type characterization value Ts, sort the same type of suppliers based on the same type characterization value Ts, construct a model training data group, and use different algorithms to construct a supplier big model based on the model training data group, output recommended suppliers based on the supplier big model, and perform comparative analysis to determine the target model algorithm, and based on the target model algorithm, perform numerical analysis on the output result of the target model algorithm to obtain the training enhancement ratio Xlq of the target model algorithm, and dynamically adjust the training times of the supplier big model of the target model algorithm, and determine the supplier big model corresponding to the recommended model algorithm based on the dynamically adjusted target algorithm model, and determine the recommended suppliers, and continuously optimize the recommendation results through complex calculations and model training, thereby greatly improving the accuracy and reliability of the recommended suppliers.

[0024] Example 3: Please refer to Figure 3 As shown, the supplier recommendation system based on the large model of the present invention includes the following device modules: Data collection module: obtain historical supplier data and store it in the supplier data group, perform similarity analysis on the supplier data group, and build a supplier similarity matrix ; Classification judgment module: Based on the supplier similarity matrix, a supplier classification model is constructed to determine the same suppliers in different categories; Data analysis module: Perform numerical analysis on the supplier similarity of the same type of suppliers in the same category to obtain the central similarity difference Zx, obtain the historical supply times of suppliers in the same category, and perform numerical calculations to obtain the same type of supply ratio TI, combine the central similarity difference Zx and the same type of supply ratio TI for analysis to obtain the same type of representation value Ts, sort the same type of suppliers based on the same type of representation value Ts, and build a model training data group; Model building module: Based on the model training data set, use different algorithms to build a supplier model, recommend suppliers based on the supplier model output, and conduct comparative analysis to determine the target model algorithm; Model determination module: Based on the target model algorithm, perform numerical analysis on the output results of the target model algorithm to obtain the training enhancement ratio Xlq of the target model algorithm. Based on the training enhancement ratio Xlq of the target model algorithm, dynamically adjust the number of supplier large model training times of the target model algorithm. Based on the dynamically adjusted target algorithm model, determine the supplier large model corresponding to the recommended model algorithm and determine the recommended supplier.

[0025] Example 4: Please refer to Figure 3 As shown, an embodiment of the present invention provides a computer device 3, comprising a memory 302, a processor 301 and a computer program 303 stored in the memory 302; Processor 301 uses a central processing unit (CPU) to handle basic and data-intensive tasks such as building a supplier similarity matrix. During the construction process, a large amount of supplier data needs to be extracted, sorted, and analyzed, and the CPU can quickly complete these operations. The digital signal processor (DSP) focuses on processing time-related data processing tasks. For example, when analyzing supplier delivery timeliness data, the DSP can extract timeliness features and perform quantitative analysis. For application-specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), and other programmable logic devices, they can be highly customized based on the complex logic and special computing requirements of the supplier recommendation method in the present invention. When running model algorithms such as graph convolutional networks (GCNs), graph attention networks (GATs), and multi-layer perceptrons (MLPs), these customized processors can optimize the model structure and data flow at the hardware level, greatly improving the computing speed and accuracy, thereby ensuring the efficient operation of the entire supplier recommendation process. The memory 302 serves as a storage medium, storing the relevant information of basic software such as the operating system, application programs, boot loaders, etc., and also stores the program code of the supplier recommendation system involved in the present invention. These program codes, when called by the processor 301, drive the execution of the entire supplier recommendation process. At the same time, the internal memory also stores a large amount of historical supplier data obtained from the enterprise procurement management system. These data cover detailed information such as the categories of goods supplied by the supplier, the timeliness of each supply, the number of supplies, etc.; after the data acquisition module obtains the data, these data will first be stored in the internal memory, and then read and updated during the operation of the classification judgment module, the data analysis module, etc. For example, when constructing a supplier similarity matrix, it is necessary to read the supplier's goods category data from the internal memory for similarity calculation; when analyzing the supply situation of the same supplier, it is necessary to extract the corresponding number of supplies and timeliness data from the internal memory for analysis and statistics; Through the collaborative work of computer equipment 3, storage media and devices, computing support, data storage environment and function implementation mechanism are provided for the supplier recommendation system based on the large model.

[0026] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the present invention.

Claims

1. A supplier recommendation method based on a large model, characterized by: The following steps are involved: Step 1: Obtain historical supplier data and store it in a supplier data group, perform similarity analysis on the supplier data group, and build a supplier similarity matrix ; Step 2: Based on the supplier similarity matrix , build a supplier classification model to identify the same suppliers in different categories; Step 3: Perform numerical analysis on the supplier similarity of the same type of suppliers in the same category to obtain the central similarity difference Zx, obtain the historical supply times of suppliers in the same category, and perform numerical calculations to obtain the same type characterization value Ts, sort the same type of suppliers based on the same type characterization value Ts, and construct a model training data set; Step 4: Based on the model training data set, use different algorithms to build a supplier model, output recommended suppliers based on the supplier model, and conduct comparative analysis to determine the target model algorithm; Step 5: Based on the target model algorithm, perform numerical analysis on the output results of the target model algorithm to obtain the training enhancement ratio Xlq of the target model algorithm, and dynamically adjust the training times of the supplier large model of the target model algorithm. Based on the dynamically adjusted target algorithm model, determine the supplier large model corresponding to the recommended model algorithm, and determine the recommended supplier.

2. The supplier recommendation method based on a large model according to claim 1, characterized in that: The Supplier Similarity Matrix The way to obtain is: Based on the internal procurement management system of the enterprise, the historical transaction record data between the enterprise and different suppliers is obtained, and the historical transaction record data of different suppliers is used as the supplier data set a i ; Among them, the historical transaction records include the supplier's goods category and time limit, i is the supplier's number, i=1,2,...,n, n is the number of suppliers; Put all supplier data sets into the supplier data group and construct the supplier data group A, where A={a1, a2, ...a n }; Extract supplier data set a i The goods category data in is used as the goods category c i , calculate the supplier similarity G of different supplier data sets ij ; By formula: Get the supplier similarity G of the supplier data set ij ; where j=i+1,i+2,...,n, Represents the supplier data set c i With c j The number of intersections, Represents the supplier data set c i With c j The number of unions, X 12 The supplier similarity G between two suppliers with supplier numbers 1 and 2 ij ; Based on the supplier similarity G in different supplier data ij , construct supplier similarity matrix S ij ; Construct the supplier similarity matrix S ij = ; The supplier similarity matrix S ij Perform preprocessing to remove the supplier similarity matrix S ij The meaningless data in the matrix includes the matrix diagonal and the data in the upper triangle of the matrix. The preprocessed supplier similarity matrix is ​​marked as .

3. The supplier recommendation method based on a large model according to claim 1, characterized in that: The methods for obtaining the same type of suppliers of different categories are as follows: Supplier Similarity Matrix Use hierarchical clustering algorithm to identify unique suppliers and homogeneous suppliers; The supplier classification model is constructed as follows: S1. Calculate the similarity distance d(i,j) by the formula: Get the similarity distance d(i,j), and construct a similarity distance matrix based on the similarity distance d(i,j); S2. Input the supplier matrix into the hierarchical clustering algorithm. The hierarchical clustering algorithm establishes different clusters based on the similarity distance d(i,j), calculates the distance between each cluster, and updates and iterates each cluster. S3. Analyze the clusters output by the hierarchical clustering algorithm. If there is only one supplier in the cluster, mark the corresponding supplier as the only supplier. If there are multiple suppliers in the cluster, mark the suppliers in the cluster as the same type of suppliers.

4. The supplier recommendation method based on a large model according to claim 1, characterized in that: The model training data set is constructed as follows: Sort the elements of the same level of detail sequence in descending order of the same level of characterization value Ts; Get all unique suppliers and put all unique suppliers into the unique supplier sequence; Obtain similarity sequences and unique supplier sequences of all categories that have been sorted, and build a model training data set.

5. The supplier recommendation method based on a large model according to claim 4, characterized in that: The same type characterization value Ts is obtained in the following manner: Get the historical supply times of the same type of supplier in the same category and the historical supply times of all suppliers of the same type; The historical supply times of the same supplier and the historical supply times of all the same suppliers are compared to obtain the same supply ratio, which is marked as T1; The supplier similarities of the same suppliers in the same category are arranged in descending order, and the sorted suppliers of the same type are taken as elements and put into the similarity sequence of the same type; Get the total number of elements of the same similarity sequence, mark the total number of elements as Zs, and make parity judgment on the total number of elements; If the total number of elements Zs is an odd number, obtain the similarity sequence of the same type. The similarity of suppliers is taken as the central similarity; If the total number of elements Zs is an even number, obtain the similarity between the (Zs / 2)th and (Zs / 2+1)th suppliers in the same similarity sequence, sum and average the similarities between the (Zs / 2)th and (Zs / 2+1)th suppliers in the similarity sequence, and obtain the central similarity; Based on the similarity sequence of the same type, calculate the difference between each element and the center similarity of the similarity sequence, obtain the center similarity difference, and mark the center similarity difference as Zx; Based on the center similarity difference Zx and the similar supply ratio TI, calculate the similar characterization value Ts; By formula: Get the same type of characterization value Ts, f and g are preset proportional coefficients.

6. The supplier recommendation method based on a large model according to claim 1, characterized in that: The target model algorithm is constructed as follows: Based on the model training data set, different algorithms are used to build a large supplier model; The supplier model built based on different algorithms inputs the category and timeliness of goods, outputs recommended suppliers, and compares the recommended suppliers with the actual suppliers; If the recommended supplier is inconsistent with the actually adopted supplier, the supplier will be marked as a misjudged supplier; If the recommended supplier is consistent with the actually adopted supplier, the supplier is marked as the adopted supplier; Obtain the number of misjudged suppliers in the supplier big models constructed by different algorithms, as well as the number of recommended suppliers output by the supplier big models; The number of misjudged suppliers is compared with the number of recommended suppliers output by the suppliers to obtain the misjudgment value ratio; Calculate the supplier model constructed by different algorithms, output recommended suppliers and misjudgment ratios multiple times, sum and average the misjudgment ratios output multiple times to obtain the mean of the misjudgment ratios; If the mean value of the false positive ratio is lower than the false positive threshold, the algorithm corresponding to the supplier's large model is obtained, and the model constructed by the corresponding algorithm is marked as the target model algorithm.

7. The supplier recommendation method based on a large model according to claim 1, characterized in that: The method for dynamically adjusting the number of supplier large model training times of the target model algorithm is as follows: Obtain the supplier large model training times Mxc of the target model algorithm, calculate the additional training times of the target model algorithm, and mark the additional training times of the target model algorithm as Ew; Based on the additional training times Ew of the target model algorithm and the training enhancement ratio Xlq of the target model algorithm, the additional training times Ew of the target model algorithm are calculated; By formula: Get the additional training times of the target model algorithm; Based on the additional training times of the target model algorithm, the training times of the supplier large model constructed by the target model algorithm are dynamically adjusted.

8. The supplier recommendation method based on a large model according to claim 7, characterized in that: The training enhancement ratio Xlq of the target model algorithm is obtained as follows: Obtain the number of adopted suppliers output by the target model algorithm and the number of recommended suppliers output by the target model algorithm; The number of adopted suppliers output by the target model algorithm is compared with the number of recommended suppliers output by the target model algorithm to obtain the adopted supply ratio; Obtain the adoption supply ratios of all target model algorithms, sum the adoption supply ratios of all target algorithms, and obtain the total adoption ratio value; The adoption supply ratio is processed by comparing it with the total value of the adoption ratio to obtain the adoption weight ratio, and the adoption weight ratio is marked as Cnq; Obtain the target model algorithm output misjudged suppliers, the corresponding supplier similarity, and the similarity corresponding to the actually adopted suppliers; The supplier similarity corresponding to the misjudged supplier is processed with the similarity corresponding to the actually adopted supplier to obtain the misjudged similarity difference; Obtain the misjudgment similarity differences output by the target model algorithm multiple times, sum and average the misjudgment similarity differences output multiple times, obtain the misjudgment similarity mean, and mark the misjudgment similarity mean as Wp; Obtain the misjudged suppliers output by the target model algorithm, and compare and analyze the misjudged suppliers with the supplier categories output by the hierarchical clustering algorithm; If the supplier is misjudged as a supplier of the same type, obtain the same type characterization value Ts of the supplier; Based on the adopted weight ratio Cnq, the misjudgment similarity mean Wp, and the misjudged supplier's similar characterization value Ts, the training enhancement ratio Xlq of the target model algorithm is calculated; By formula: Obtain the training enhancement ratio Xlq of the target model algorithm, where α and β are preset proportional coefficients, where z is the total number of misjudged suppliers output by the target model algorithm, c=1, 2, ..., z; if the misjudged supplier is a supplier of the same type, γ=1, otherwise, γ=0.

9. The supplier recommendation method based on a large model according to claim 1, characterized in that: The method for determining the supplier model corresponding to the recommendation model algorithm is as follows: Based on the dynamically adjusted target model algorithm and the mean error ratio of the target model algorithm, all the mean error ratios of the target model algorithms are arranged in ascending order, and the target model algorithm corresponding to the minimum mean error ratio is selected as the recommended model algorithm; The recommended suppliers are obtained as follows: Based on the supplier model constructed by the recommendation model algorithm, the recommended suppliers are output.

10. A supplier recommendation system based on a large model, characterized by: Data collection module: obtain historical supplier data and store it in the supplier data group, perform similarity analysis on the supplier data group, and build a supplier similarity matrix ; Classification and discrimination module: based on supplier similarity matrix , build a supplier classification model to identify the same suppliers in different categories; Data analysis module: Perform numerical analysis on the supplier similarity of the same type of suppliers in the same category to obtain the central similarity difference Zx, obtain the historical supply times of suppliers in the same category, and perform numerical calculations to obtain the same type characterization value Ts. Based on the same type characterization value Ts, the same type of suppliers are sorted to build a model training data group; Model building module: Based on the model training data set, use different algorithms to build a supplier model, recommend suppliers based on the supplier model output, and conduct comparative analysis to determine the target model algorithm; Model determination module: Based on the target model algorithm, perform numerical analysis on the output results of the target model algorithm to obtain the training enhancement ratio Xlq of the target model algorithm, and dynamically adjust the training times of the supplier large model of the target model algorithm. Based on the dynamically adjusted target algorithm model, determine the supplier large model corresponding to the recommended model algorithm and determine the recommended supplier.

Images