Procurement Sourcing Method and System Based on Intelligent Recommendation of Supplier Portfolio

Abstract

An embodiment of the present invention provides a procurement sourcing method and system based on intelligent recommendation of supplier combinations, belonging to the technical field of procurement sourcing. The method includes: collecting procurement requirement data, determining candidate suppliers based on the procurement requirement data, and obtaining candidate supplier combinations; calculating the combined evaluation scores of each candidate supplier combination and the basic evaluation scores of individual candidate suppliers within each corresponding candidate supplier combination respectively; determining the procurement scores of each candidate supplier combination based on the combined evaluation scores of each candidate supplier combination and the basic evaluation scores of individual candidate suppliers within each corresponding candidate supplier combination respectively, and sorting the procurement scores of each candidate supplier combination; performing candidate supplier combination recommendation based on the sorting result, and performing procurement sourcing based on the recommended candidate supplier combinations to obtain procurement sourcing results. The solution of the present invention improves the quality and efficiency of sourcing.

Description

Technical Field

[0001] The present invention relates to the technical field of procurement sourcing, and specifically relates to a procurement sourcing method based on intelligent recommendation of supplier combinations and a procurement sourcing system based on intelligent recommendation of supplier combinations. Background Art

[0002] Supplier relationship management (SRM) is a solution dedicated to establishing and maintaining long-term and close partnership with suppliers. It is a new management mechanism aiming to improve the relationship between an enterprise and its suppliers, implemented in the fields related to the procurement business of the enterprise. The goal is to establish a long-term and close business relationship with suppliers, and through the integration of the resources and competitive advantages of both parties, jointly explore the market, expand market demand and share, reduce the high upfront costs of products, and achieve a win-win enterprise management model. Currently, there is an intelligent procurement platform based on SRM, which can respond to the target procurement needs of a target procurement enterprise, analyze the material names, specifications, and quantities included in the target procurement needs, and screen the target suppliers corresponding to the minimum transaction costs required for purchasing each material in the current transaction cycle. For example, the Chinese patent application with the publication number CN116993444A can screen the target suppliers with the lowest transaction costs for a procurement enterprise by analyzing the transaction prices of the same-specification materials from different suppliers, thereby reducing the procurement costs.

[0003] However, the procurement needs of procurement enterprises are often relatively diverse. On the one hand, for demands with a large quantity and complex project collaboration relationships, a single supplier often cannot meet the demands. Therefore, for the same procurement demand, it may be necessary to divide it into multiple procurement lists for procurement sourcing. At this time, if the procurement lists are not reasonably divided, it may cause difficulties in sourcing or it may be difficult to find truly suitable suppliers. On the other hand, for procurement demands with scattered demand types and data but few project collaboration relationships, if each scattered procurement demand is separately sourced, it will often increase the procurement time and cost. In view of the problems of low sourcing accuracy and low sourcing efficiency existing in the existing procurement sourcing solutions when facing the procurement needs of procurement enterprises, a new procurement sourcing solution needs to be proposed. Summary of the Invention

[0004] The purpose of the embodiments of the present invention is to provide a procurement sourcing method and system based on intelligent recommendation of supplier combinations to at least solve the problems of low sourcing accuracy and low sourcing efficiency existing in the existing procurement sourcing solutions when facing the procurement needs of procurement enterprises.

[0005] To achieve the above object, a first aspect of the present invention provides a procurement sourcing method based on intelligent recommendation of supplier combinations, the method comprising: collecting procurement requirement data, and determining candidate suppliers based on the procurement requirement data to obtain candidate supplier combinations; respectively calculating the combined evaluation scores of each candidate supplier combination and the basic evaluation scores of individual candidate suppliers within each corresponding candidate supplier combination; determining the procurement scores of each candidate supplier combination based on the combined evaluation scores of each candidate supplier combination and the basic evaluation scores of individual candidate suppliers within each corresponding candidate supplier combination, and sorting the procurement scores of each candidate supplier combination; performing candidate supplier combination recommendation based on the sorting result, and performing procurement sourcing based on the recommended candidate supplier combinations to obtain procurement sourcing results.

[0006] Optionally, the collecting procurement requirement data, and determining candidate suppliers based on the procurement requirement data to obtain candidate supplier combinations includes: generating a corresponding standardized total procurement requirement list based on the procurement requirement data; determining the candidate suppliers corresponding to each procurement target based on the standardized total procurement requirement list to obtain a candidate supplier list; performing an exhaustive search and matching based on the standardized total procurement requirement list and the candidate supplier list to obtain all supplier combinations that meet the basic procurement requirements corresponding to the procurement requirement data as candidate supplier combinations.

[0007] Optionally, the performing an exhaustive search and matching based on the standardized total procurement requirement list and the candidate supplier list to obtain all supplier combinations that meet the basic procurement requirements corresponding to the procurement requirement data as candidate supplier combinations includes: traversing all suppliers in the supplier list, considering for each supplier whether to select or not select, so as to generate all possible supplier combinations; for each generated supplier combination, filtering out the supplier combinations that cannot meet the basic procurement requirements corresponding to the procurement requirement data, and taking the remaining supplier combinations as candidate supplier combinations.

[0008] Optionally, the respectively calculating the combined evaluation scores of each candidate supplier combination and the basic evaluation scores of individual candidate suppliers within each corresponding candidate supplier combination includes: calculating the matching degree between each individual candidate supplier within each candidate supplier combination and the procurement requirement data as the basic evaluation score of each individual candidate supplier within each candidate supplier combination; calculating the cooperation degree between each individual candidate supplier within each candidate supplier combination as the combined evaluation score of the corresponding candidate supplier combination.

[0009] Optionally, calculating the matching degree between each individual candidate supplier within each candidate supplier combination and the procurement requirement data as the basic evaluation score of each individual candidate supplier within each candidate supplier combination includes: determining the priority of each procurement indicator based on the procurement requirement data; where the procurement indicators include: procurement target, procurement quantity, procurement quality requirement, and required delivery time; calculating the matching degree between each individual candidate supplier and each procurement indicator based on a machine learning algorithm, and generating a matching degree score corresponding to each procurement indicator based on the determined matching degree; performing weighted summation on the matching degree scores corresponding to each procurement indicator based on the priority of each procurement indicator to obtain the matching degree between the corresponding individual candidate supplier and the procurement requirement data; traversing all individual candidate suppliers to obtain the basic evaluation scores of each individual candidate supplier within each candidate supplier combination.

[0010] Optionally, calculating the cooperation degree between each individual candidate supplier within each candidate supplier combination as the combined evaluation score corresponding to each candidate supplier combination includes: collecting the real-time supply capacity information and retained procurement cooperation information of each individual candidate supplier within each candidate supplier combination; training the real-time supply capacity information and the retained procurement cooperation information based on a pre-constructed combined evaluation score scoring model to obtain the combined evaluation score of each candidate supplier combination.

[0011] Optionally, the method further includes: pre-constructing a combined evaluation score scoring model, including: collecting historical procurement data and reading the historical cooperation information of each candidate supplier based on the historical procurement data; performing random combination of each candidate supplier to obtain multiple historical supplier combinations; pushing the multiple historical supplier combinations to the user terminal, and based on the user terminal, recovering the combined evaluation score annotation results of the user as the annotation information of each historical supplier combination to obtain an annotation sample; performing sample augmentation on the annotation sample to obtain an augmented annotation sample; performing model training on the augmented annotation sample in a pre-selected neural network to obtain a combined evaluation score scoring model.

[0012] Optionally, determining the procurement score of each candidate supplier combination based on the combined evaluation score of each candidate supplier combination and the basic evaluation score of each individual candidate supplier within the corresponding candidate supplier combination respectively includes: performing a summation process within each candidate supplier combination based on the basic evaluation score of each individual candidate supplier to obtain the sum of the basic evaluation scores of each candidate supplier combination; performing weighting on the sum of the basic evaluation scores of each candidate supplier combination and weighting on the combined evaluation score of each candidate supplier combination based on a preset weight allocation relationship, and calculating the procurement score of each candidate supplier combination based on the weighted result to obtain the procurement score of each candidate supplier combination.

[0013] Optionally, performing candidate supplier portfolio recommendation based on the sorting result includes: judging the number of candidate supplier portfolios with a procurement score greater than a preset recommended procurement score threshold based on the sorting result; if the number of candidate supplier portfolios with a procurement score greater than the preset recommended procurement score threshold is greater than a preset quantity threshold N, taking the first N candidate supplier portfolios equal to the preset quantity threshold N from the candidate supplier portfolios with a procurement score greater than the preset recommended procurement score threshold as the recommended candidate supplier portfolios; if the number of candidate supplier portfolios with a procurement score greater than the preset recommended procurement score threshold is not greater than the preset quantity threshold N, taking all candidate supplier portfolios with a procurement score greater than the preset recommended procurement score threshold as the recommended candidate supplier portfolios.

[0014] Optionally, performing procurement sourcing based on the recommended candidate supplier portfolios to obtain a procurement sourcing result includes: generating a recommended candidate supplier set corresponding to each candidate supplier portfolio based on each recommended candidate supplier portfolio; performing a union process on each recommended candidate supplier set to obtain all candidate recommended candidate suppliers to be sourced; performing sourcing for each candidate recommended candidate supplier to be sourced to obtain the sourcing results of each recommended candidate supplier; and performing a combination of the sourcing results of each recommended candidate supplier under each recommended candidate supplier portfolio to obtain the sourcing results of each recommended candidate supplier portfolio.

[0015] A second aspect of the present invention provides a procurement sourcing system based on intelligent recommendation of supplier portfolios. The system includes: a collection unit for collecting procurement requirement data and determining candidate suppliers based on the procurement requirement data to obtain candidate supplier portfolios; a scoring unit for calculating the combined evaluation scores of each candidate supplier portfolio and the basic evaluation scores of individual candidate suppliers within each candidate supplier portfolio respectively; a processing unit for determining the procurement scores of each candidate supplier portfolio based on the combined evaluation scores of each candidate supplier portfolio and the basic evaluation scores of individual candidate suppliers within each candidate supplier portfolio respectively, and sorting the procurement scores of each candidate supplier portfolio; and a sourcing unit for performing candidate supplier portfolio recommendation based on the sorting result and performing procurement sourcing based on the recommended candidate supplier portfolios to obtain a procurement sourcing result.

[0016] On the other hand, the present invention provides a computer-readable storage medium, on which instructions are stored, and when the instructions run on a computer, the computer is caused to execute the above-mentioned procurement sourcing method based on intelligent recommendation of supplier portfolios.

[0017] Through the above technical solution, the present invention has the following beneficial effects:

[0018] 1. Improve procurement efficiency: By intelligently recommending candidate supplier combinations, the potential scope of supplier selection can be quickly determined, saving the time and effort of procurement personnel.

[0019] 2. Optimize supplier selection: By calculating the combined evaluation score and the basic evaluation score, the overall performance of the supplier combination and the capabilities of individual suppliers can be comprehensively considered, which helps to select the optimal supplier combination.

[0020] 3. Improve the accuracy of procurement decisions: Recommendations based on the procurement scoring and ranking results can reduce the influence of subjective factors on supplier selection and improve the objectivity and accuracy of decisions.

[0021] 4. Enhance the reliability of procurement results: By implementing procurement sourcing based on the recommended candidate supplier combination, it can be ensured that the procurement process conforms to the recommended results, thereby improving the reliability and consistency of procurement results.

[0022] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent specific embodiments section. Brief Description of the Drawings

[0023] The drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the embodiments of the present invention, but do not constitute a limitation to the embodiments of the present invention. In the drawings:

[0024] Figure 1 is a flowchart of the steps of a procurement sourcing method based on intelligent recommendation of supplier combinations provided by an embodiment of the present invention;

[0025] Figure 2 is a system structure diagram of a procurement sourcing system based on intelligent recommendation of supplier combinations provided by an embodiment of the present invention. Detailed Description of the Embodiments

[0026] The following will describe in detail the specific embodiments of the present invention with reference to the drawings. It should be understood that the specific embodiments described herein are only for explaining and illustrating the present invention and are not used to limit the present invention.

[0027] Figure 1 is a flowchart of a method of a procurement sourcing method based on intelligent recommendation of supplier combinations provided by an embodiment of the present invention. As Figure 1 shown, an embodiment of the present invention provides a procurement sourcing method based on intelligent recommendation of supplier combinations, and the method includes:

[0028] Step S10: Collect procurement requirement data, and determine candidate suppliers based on the procurement requirement data to obtain a candidate supplier combination.

[0029] Specifically, generate a corresponding standardized total procurement demand list based on the procurement demand data; based on the standardized total procurement demand list, determine the candidate suppliers corresponding to each procurement target to obtain a candidate supplier list; perform an exhaustive search and matching based on the standardized total procurement demand list and the candidate supplier list to obtain all supplier combinations that meet the basic procurement requirements corresponding to the procurement demand data as candidate supplier combinations.

[0030] In the embodiments of the present invention, candidate suppliers can be determined based on the supplier portraits retained by historical cooperative suppliers or based on potential suppliers mined by big data.

[0031] In the embodiments of the present invention, in the modern business environment, procurement management is a crucial part of enterprise operations. To effectively manage procurement requirements and ensure the efficiency and transparency of the procurement process, many enterprises adopt automated and intelligent methods to process procurement demand data. Generating a corresponding standardized total procurement demand list based on the procurement demand data is a key task. This involves integrating and standardizing the procurement requirements proposed by each department or project team to better manage and analyze these requirements. Once the standardized total procurement demand list is obtained, the next step is to determine the candidate suppliers corresponding to each procurement target to obtain a candidate supplier list. This process usually involves screening and matching the supplier database to ensure that the selected suppliers can meet the enterprise's procurement requirements and comply with relevant standards and requirements. The selection of candidate suppliers may be based on multiple factors, including the supplier's reputation, product quality, delivery ability, price competitiveness, etc.

[0032] Furthermore, perform an exhaustive search and matching based on the standardized total procurement demand list and the candidate supplier list to obtain all supplier combinations that meet the basic procurement requirements corresponding to the procurement demand data as candidate supplier combinations. The corresponding supplier combination determination relationship proposed by the solution of the present invention ensures a comprehensive search and matching of all possible supplier combinations. Exhaustive search and matching can help enterprises find the best supplier combinations, thereby minimizing procurement costs and maximizing procurement efficiency.

[0033] Furthermore, the performing an exhaustive search and matching based on the standardized total procurement demand list and the candidate supplier list to obtain all supplier combinations that meet the basic procurement requirements corresponding to the procurement demand data as candidate supplier combinations includes: traversing all suppliers in the supplier list, considering whether to select or not select each supplier, so as to generate all possible supplier combinations; for each generated supplier combination, filtering out the supplier combinations that cannot meet the basic procurement requirements corresponding to the procurement demand data, and taking the remaining supplier combinations as candidate supplier combinations.

[0034] In the embodiments of the present invention, for the generated standardized total procurement requirement list and candidate supplier list, the process of performing exhaustive search and matching adopts a recursive algorithm. The recursive algorithm can traverse all suppliers in the supplier list and perform operations of selecting or not selecting each supplier, so as to generate all possible supplier combinations. In each step, the algorithm will consider whether the current supplier is selected or not, and then continue to recursively process the next supplier until all suppliers are traversed to form all possible supplier combinations.

[0035] Furthermore, for each generated supplier combination, it is necessary to perform matching and filtering of the basic procurement requirements. This step can be achieved by using conditional judgment and screening algorithms. For each supplier combination, the algorithm will check whether the suppliers in it can meet the basic procurement requirements corresponding to the procurement requirement data. If the suppliers in a certain supplier combination cannot meet the basic procurement requirements, then this supplier combination will be filtered out and not included in the candidate supplier combinations. The remaining supplier combinations are considered as candidate supplier combinations that meet the basic procurement requirements.

[0036] By performing such an exhaustive search, matching and filtering process, the present invention solution can obtain all possible supplier combinations and screen out candidate supplier combinations that meet the basic procurement requirements. The benefit of this method is that it can comprehensively consider all supplier combination situations, ensure that each supplier combination undergoes strict matching of basic procurement requirements, thereby improving the accuracy and reliability of the selected suppliers. At the same time, through the application of automated algorithms, it can greatly save human resources and time costs, and improve the efficiency and accuracy of procurement decisions.

[0037] Step S20: Calculate the combined evaluation scores of each candidate supplier combination and the basic evaluation scores of individual candidate suppliers within each corresponding candidate supplier combination respectively.

[0038] Specifically, in the solution of the present invention, each candidate supplier in the candidate supplier combination is scored to obtain the basic evaluation score, where the basic evaluation score represents the matching degree of the candidate supplier itself to the procurement requirements; the combined ability of the candidate supplier combination is scored to obtain the combined evaluation score, and the combined evaluation score represents the cooperation degree among the candidate suppliers; combining the combined evaluation score of each candidate supplier combination and the basic scores of each supplier within the candidate supplier combination, the total score of each candidate supplier combination is obtained.

[0039] Preferably, calculating the combined evaluation scores of each candidate supplier combination and the basic evaluation scores of individual candidate suppliers within each corresponding candidate supplier combination includes: calculating the matching degree between an individual candidate supplier within each candidate supplier combination and the procurement demand data as the basic evaluation score of the individual candidate supplier within each candidate supplier combination; and calculating the cooperation degree among individual candidate suppliers within each candidate supplier combination as the combined evaluation score corresponding to each candidate supplier combination.

[0040] Specifically, calculating the matching degree between an individual candidate supplier within each candidate supplier combination and the procurement demand data as the basic evaluation score of the individual candidate supplier within each candidate supplier combination includes: determining the priority of each procurement indicator based on the procurement demand data; where the procurement indicators include: procurement objectives, procurement quantity, procurement quality requirements, and required delivery time; evaluating the matching degree between each individual candidate supplier and each procurement indicator based on a machine learning algorithm, and generating a matching degree score corresponding to each procurement indicator based on the determined matching degree; performing weighted summation on the matching degree scores corresponding to each procurement indicator based on the priority of each procurement indicator to obtain the matching degree between the corresponding individual candidate supplier and the procurement demand data; and traversing all individual candidate suppliers to obtain the basic evaluation scores of individual candidate suppliers within each candidate supplier combination. Specifically, it includes the following steps:

[0041] 1) Determining the priority of procurement indicators: The procurement indicators include procurement objectives, procurement quantity, procurement quality requirements, and required delivery time. When processing procurement demand data, it is first necessary to determine the priority order of these procurement indicators to better balance the importance of each indicator in the subsequent matching and evaluation processes.

[0042] 2) Matching candidate suppliers with procurement indicators using a machine learning algorithm: Based on a machine learning algorithm, evaluate the matching degree between each individual candidate supplier and each procurement indicator. This can be achieved by analyzing the supplier's historical data, qualifications, delivery capabilities, etc. through the algorithm and comparing them with the procurement indicators to determine the matching degree of each supplier under different indicators.

[0043] 3) Generating matching degree scores for procurement indicators: Generate corresponding matching degree scores for each procurement indicator based on the determined matching degree. These scores reflect the performance of each supplier under different procurement indicators and provide a basis for subsequent evaluation and screening.

[0044] 4) Calculating the matching degree between the supplier and the procurement demand data through weighted summation: Based on the priority of each procurement indicator, perform weighted summation on the matching degree scores corresponding to each procurement indicator. Through this step, the importance of each indicator can be comprehensively considered to obtain the comprehensive matching degree score between each candidate supplier and the procurement demand data.

[0045] 5) Traverse all individual candidate suppliers to obtain the basic evaluation scores: Traverse all individual candidate suppliers, and for each individual supplier within each supplier combination, calculate its basic evaluation score. This evaluation score comprehensively considers the matching degree of each supplier under various procurement indicators and the priorities of each indicator, thereby providing a comprehensive evaluation result for each supplier combination.

[0046] The solution of the present invention can achieve comprehensive matching and evaluation of candidate suppliers, thereby generating candidate supplier combinations that meet the procurement requirement data. This method can more accurately evaluate the suitability of suppliers, improve the accuracy and reliability of selected suppliers. At the same time, through the application of machine learning algorithms, rapid processing and analysis of a large amount of supplier data can be achieved, saving human resources and time costs, and improving the efficiency and quality of procurement management. This procurement management method based on data-driven and algorithm support helps enterprises optimize supply chain management, reduce procurement costs, improve the accuracy and efficiency of procurement decisions, and thus enhance the competitiveness and sustainable development ability of enterprises.

[0047] Further, calculating the cooperation degree between each individual candidate supplier within each candidate supplier combination as the combined evaluation score corresponding to each candidate supplier combination includes: collecting the real-time supply capacity information and retained procurement cooperation information of each individual candidate supplier within each candidate supplier combination; training the real-time supply capacity information and the retained procurement cooperation information based on a pre-constructed combined evaluation score scoring model to obtain the combined evaluation score of each candidate supplier combination. Specifically, it includes the following steps:

[0048] 1) Collect real-time supply capacity information and retained procurement cooperation information: First, it is necessary to collect real-time supply capacity information from each candidate supplier, including data such as production capacity, inventory status, and delivery speed. At the same time, collect the retained procurement cooperation information, such as historical transaction records and cooperation stability, in order to more comprehensively evaluate the comprehensive performance of suppliers.

[0049] 2) Construct a combined evaluation score scoring model: Based on the collected real-time supply capacity information and retained procurement cooperation information, establish a combined evaluation score scoring model. This model can adopt machine learning algorithms, such as deep learning models or regression models, and through training and learning of the data, it can accurately predict and evaluate the performance and cooperation degree of supplier combinations.

[0050] 3) Train the model and generate the combined evaluation score: After the model is constructed, use the existing real-time data and historical information to train the model. By training the model, it can learn the association rules and cooperation degree between each individual candidate supplier within each candidate supplier combination. After training, the model will be able to generate the corresponding combined evaluation score for each candidate supplier combination.

[0051] 4) Evaluate the performance of the candidate supplier combinations: Utilize the generated combination evaluation scores to evaluate and rank the performance of each candidate supplier combination. These evaluation scores will reflect the compatibility and overall performance of different supplier combinations, assisting the procurement team in better selecting the optimal supplier combination.

[0052] The solution of the present invention can achieve a comprehensive evaluation of the candidate supplier combinations, considering not only the matching degree of individual suppliers with procurement indicators but also the compatibility and performance among suppliers. This comprehensive evaluation method can more accurately reflect the overall performance of the supplier combinations, providing more powerful support and guidance for procurement decisions. Meanwhile, through the application of machine learning algorithms, rapid processing and analysis of a large amount of data can be achieved, improving the efficiency of procurement management and the accuracy of decisions, thereby optimizing the enterprise's supply chain management and procurement process.

[0053] Furthermore, the method further includes: pre-constructing a combination evaluation score scoring model, including: collecting historical procurement data and reading the historical cooperation information of each candidate supplier based on the historical procurement data; performing random combinations of each candidate supplier to obtain multiple historical supplier combinations; pushing the multiple historical supplier combinations to the user side and, based on the user side, retrieving the user's combination evaluation score annotation results as the annotation information for each historical supplier combination to obtain an annotated sample; performing sample augmentation on the annotated sample to obtain an augmented annotated sample; and performing model training on the augmented annotated sample in a pre-selected neural network to obtain a combination evaluation score scoring model.

[0054] Specifically, first, it is necessary to collect the real-time supply capacity information and retained procurement cooperation information of each individual candidate supplier within each candidate supplier combination. This includes real-time data such as production capacity, on-time delivery rate, product quality, as well as retained information such as historical transaction records and cooperation stability. Before constructing the combined evaluation score model, a large amount of historical procurement data needs to be collected. This data includes past purchase orders, supplier transaction records, delivery situations, etc., and is used to analyze and evaluate the past performance of suppliers. Based on the historical procurement data, read the historical cooperation information of each candidate supplier. This includes analyzing past cooperation situations, transaction frequencies, problem feedback, etc., in order to understand the cooperation history between suppliers. By randomly combining each candidate supplier, multiple historical supplier combinations can be obtained, which helps to construct a more comprehensive dataset for training the evaluation model. Push multiple historical supplier combinations to the user side, and the user performs combined score scoring to obtain the target data of each sample data, and the trained model can then obtain the ability to score independently. Expand the sample of the combined evaluation score annotation results recovered by the user to increase the diversity and quantity of the data, and improve the generalization ability and accuracy of the model. Based on the expanded annotated samples, perform model training in a pre-selected neural network or other machine learning models. By training the model, the degree of cooperation between each individual candidate supplier within each candidate supplier combination can be learned, and the combined evaluation score can be generated.

[0055] Step S30: Based on the combined evaluation scores of each candidate supplier combination and the basic evaluation scores of each individual candidate supplier within the corresponding candidate supplier combination, respectively determine the procurement scores of each candidate supplier combination, and perform sorting on the procurement scores of each candidate supplier combination.

[0056] Specifically, based on the basic evaluation scores of each individual candidate supplier, perform a summation process within each candidate supplier combination to obtain the sum of the basic evaluation scores of each candidate supplier combination; perform weighted summation on the sum of the basic evaluation scores of each candidate supplier combination and weighted assignment of the combined evaluation scores of each candidate supplier combination based on the preset weight assignment relationship, and perform procurement score calculation for each candidate supplier combination based on the weighted results to obtain the procurement scores of each candidate supplier combination.

[0057] In the embodiments of the present invention, when the company faces urgent orders or short-term demands, the supply capacity of the supplier becomes crucial. In this case, the ability to deliver on time and ensure supply is the primary consideration. If the requirements for product quality and compliance are high, the supply capacity of the supplier directly affects product quality and compliance. Therefore, the production capacity, quality control, and compliance certification of the supplier become crucial. And when the company establishes a long-term cooperation and strategic partnership with the supplier, the degree of fit of the combined relationship between suppliers becomes important, which includes cooperation stability, communication efficiency, and the ability to develop together.

[0058] It can be seen that under different procurement needs, there are differences in the sensitivity to the supply capabilities of individual suppliers and the degree of cooperation between multiple suppliers. To accommodate this difference, the solution of the present invention performs adaptive weighting on the basic evaluation scores of each candidate supplier combination and the combined evaluation scores of each candidate supplier combination when performing procurement scoring calculations. This addresses the sensitivity requirements in different scenarios and ensures that the optimal supplier combination obtained is the supplier combination that meets the most sensitive needs of the current user.

[0059] Step S40: Recommend candidate supplier combinations based on the ranking results, and perform procurement sourcing based on the recommended candidate supplier combinations to obtain procurement sourcing results.

[0060] Specifically, the recommendation of candidate supplier combinations based on the sorting results includes: based on the sorting results, determining the number of candidate supplier combinations whose procurement scores are greater than a preset recommended procurement score threshold; if the number of candidate supplier combinations whose procurement scores are greater than the preset recommended procurement score threshold is greater than a preset quantity threshold N, then taking the first N candidate supplier combinations equal to the preset quantity threshold N among the candidate supplier combinations whose procurement scores are greater than the preset recommended procurement score threshold as recommended candidate supplier combinations; if the number of candidate supplier combinations whose procurement scores are greater than the preset recommended procurement score threshold is not greater than the preset quantity threshold N, then taking all candidate supplier combinations whose procurement scores are greater than the preset recommended procurement score threshold as recommended candidate supplier combinations.

[0061] Furthermore, the procurement sourcing is performed based on the recommended candidate supplier combinations to obtain procurement sourcing results, including: generating a recommended candidate supplier set corresponding to each candidate supplier combination based on each recommended candidate supplier combination; performing union processing on each recommended candidate supplier set to obtain all candidate recommended candidate supplier targets to be sourced; performing sourcing for each candidate recommended candidate supplier target to be sourced to obtain sourcing results for each recommended candidate supplier; performing a sourcing result combination corresponding to each recommended candidate supplier under each recommended candidate supplier combination to obtain sourcing results for each recommended candidate supplier combination.

[0062] In this embodiment of the present invention, there's a high probability that each supplier combination contains the same supplier. If sourcing is performed separately based on each recommended candidate supplier, duplicate sourcing will inevitably occur. To avoid this issue, the present solution first performs a union on each recommended candidate supplier combination, ensuring that each candidate supplier is sourced only once. To facilitate customer review, after sourcing is complete, the present solution displays the sourcing results based on each candidate supplier combination for user selection.

[0063] Figure 2It is the system structure diagram of the procurement sourcing system based on intelligent recommendation of supplier combination provided by an embodiment of the present invention. As Figure 2 shown, an embodiment of the present invention provides a procurement sourcing system based on intelligent recommendation of supplier combination. The system includes: a collection unit, configured to collect procurement requirement data, and determine candidate suppliers based on the procurement requirement data to obtain a candidate supplier combination; a scoring unit, configured to calculate the combined evaluation scores of each candidate supplier combination and the basic evaluation scores of individual candidate suppliers within each candidate supplier combination respectively; a processing unit, configured to determine the procurement scores of each candidate supplier combination based on the combined evaluation scores of each candidate supplier combination and the basic evaluation scores of individual candidate suppliers within each candidate supplier combination respectively, and perform sorting on the procurement scores of each candidate supplier combination; a sourcing unit, configured to perform recommendation of candidate supplier combinations based on the sorting result, and perform procurement sourcing based on the recommended candidate supplier combinations to obtain a procurement sourcing result.

[0064] An embodiment of the present invention also provides a computer-readable storage medium, on which instructions are stored, and when running on a computer, the computer is caused to execute the above-mentioned procurement sourcing based on intelligent recommendation of supplier combination.

[0065] Those skilled in the art can understand that all or part of the steps in the methods of the above embodiments can be completed by instructing relevant hardware through a program. The program is stored in a storage medium, including several instructions for causing a single-chip microcomputer, a chip or a processor to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disc that can store program codes.

[0066] The optional embodiments of the present invention have been described in detail above in conjunction with the accompanying drawings. However, the embodiments of the present invention are not limited to the specific details in the above embodiments. Within the scope of the technical concept of the embodiments of the present invention, various simple modifications can be made to the technical solutions of the embodiments of the present invention, and these simple modifications all fall within the protection scope of the embodiments of the present invention. In addition, it should be noted that, in the above specific embodiments, the various specific technical features described can be combined in any appropriate manner without conflict. To avoid unnecessary repetition, the embodiments of the present invention will not separately describe various possible combination manners.

[0067] In addition, any combination can be made among various different embodiments of the present invention, as long as it does not violate the idea of the embodiments of the present invention, and it should also be regarded as the content disclosed by the embodiments of the present invention.

Claims

1. A procurement sourcing method based on intelligent recommendation of supplier portfolio, characterized in that, The method includes: Collect procurement requirement data, determine candidate suppliers based on the procurement requirement data, and obtain a candidate supplier combination; Calculate the matching degree between each individual candidate supplier within each candidate supplier combination and the procurement requirement data, and use it as the basic evaluation score of each individual candidate supplier within each candidate supplier combination; Collect the real-time supply capacity information and retained procurement cooperation information of each individual candidate supplier within each candidate supplier combination; Train the real-time supply capacity information and the retained procurement cooperation information based on a pre-constructed combined evaluation score model to obtain the combined evaluation score of each candidate supplier combination; Determine the procurement scores of each candidate supplier combination based on the combined evaluation scores of each candidate supplier combination and the basic evaluation scores of the individual candidate suppliers within the corresponding candidate supplier combinations, and sort the procurement scores of each candidate supplier combination; Perform candidate supplier combination recommendation based on the sorting result, and perform procurement sourcing based on the recommended candidate supplier combination to obtain a procurement sourcing result.

2. The method according to claim 1, characterized in that, The collecting of procurement requirement data, determining candidate suppliers based on the procurement requirement data, and obtaining a candidate supplier combination includes: Generate a corresponding standardized total procurement requirement list based on the procurement requirement data; Based on the standardized total procurement requirement list, determine the candidate suppliers corresponding to each procurement target to obtain a candidate supplier list; Perform an exhaustive search and matching based on the standardized total procurement requirement list and the candidate supplier list to obtain all supplier combinations that meet the basic procurement requirements corresponding to the procurement requirement data, as the candidate supplier combination.

3. The method according to claim 2, wherein The performing of an exhaustive search and matching based on the standardized total procurement requirement list and the candidate supplier list to obtain all supplier combinations that meet the basic procurement requirements corresponding to the procurement requirement data, as the candidate supplier combination, includes: Traverse all suppliers in the supplier list, consider whether to select or not select each supplier, so as to generate all possible supplier combinations; For each generated supplier combination, filter out the supplier combinations that cannot meet the basic procurement requirements corresponding to the procurement requirement data, and use the remaining supplier combinations as the candidate supplier combination.

4. The method according to claim 1, wherein The calculating of the matching degree between each individual candidate supplier within each candidate supplier combination and the procurement requirement data, and using it as the basic evaluation score of each individual candidate supplier within each candidate supplier combination, includes: Determine the priority of each procurement indicator based on the procurement requirement data; Among them, the procurement indicators include: procurement target, procurement quantity, procurement quality requirement, and required delivery time; Calculate the matching degree between each individual candidate supplier and each procurement indicator based on a machine learning algorithm, and generate a matching degree score corresponding to each procurement indicator based on the determined matching degree; Perform weighted summation on the matching degree scores corresponding to each procurement indicator based on the priority of each procurement indicator to obtain the matching degree between the corresponding individual candidate supplier and the procurement requirement data; Traverse all individual candidate suppliers to obtain the basic evaluation scores of the individual candidate suppliers within each candidate supplier combination.

5. The method according to claim 1, characterized in that, The method further includes: performing pre-construction of a combined evaluation score scoring model, including: Collecting historical procurement data and reading historical cooperation information of each candidate supplier based on the historical procurement data; Performing random combinations of each candidate supplier to obtain multiple historical supplier combinations; Pushing the multiple historical supplier combinations to the user side and, based on the user side, receiving the combined evaluation score annotation results of the user as the annotation information of each historical supplier combination to obtain an annotation sample; Performing sample augmentation on the annotation sample to obtain an augmented annotation sample; Performing model training on the augmented annotation sample in a pre-selected neural network to obtain a combined evaluation score scoring model.

6. The method according to claim 1, wherein The determining of the procurement score of each candidate supplier combination based on the combined evaluation score of each candidate supplier combination and the basic evaluation score of each individual candidate supplier within the corresponding candidate supplier combination respectively includes: Performing a summation process within each candidate supplier combination based on the basic evaluation scores of each individual candidate supplier to obtain the sum of the basic evaluation scores of each candidate supplier combination; Performing weighted sum of the sum of the basic evaluation scores of each candidate supplier combination and weighted sum of the combined evaluation scores of each candidate supplier combination based on a preset weight distribution relationship, and calculating the procurement score of each candidate supplier combination based on the weighted results to obtain the procurement score of each candidate supplier combination.

7. The method according to claim 1, characterized in that, The performing of candidate supplier combination recommendation based on the sorting result includes: Based on the sorting result, determining the number of candidate supplier combinations with a procurement score greater than a preset recommended procurement score threshold; If the number of candidate supplier combinations with a procurement score greater than the preset recommended procurement score threshold is greater than a preset quantity threshold N, then taking the first N candidate supplier combinations equal to the preset quantity threshold N from the candidate supplier combinations with a procurement score greater than the preset recommended procurement score threshold as the recommended candidate supplier combinations; If the number of candidate supplier combinations with a procurement score greater than the preset recommended procurement score threshold is not greater than the preset quantity threshold N, then taking all candidate supplier combinations with a procurement score greater than the preset recommended procurement score threshold as the recommended candidate supplier combinations.

8. The method according to claim 1, characterized in that, The performing of procurement sourcing based on the recommended candidate supplier combinations to obtain a procurement sourcing result includes: Generating a recommended candidate supplier set corresponding to each recommended candidate supplier combination based on each recommended candidate supplier combination; Performing a union process on each recommended candidate supplier set to obtain all target candidate recommended suppliers to be sourced; Performing sourcing for each target candidate recommended supplier to be sourced to obtain the sourcing results of each recommended candidate supplier; Performing combination of the sourcing results of each recommended candidate supplier under each recommended candidate supplier combination to obtain the sourcing results of each recommended candidate supplier combination.

9. A computer-readable storage medium, characterized in that, Instructions are stored on the computer-readable storage medium, and when running on a computer, the computer is caused to execute the procurement sourcing method based on intelligent recommendation of supplier combinations according to any one of claims 1-8.

10. A procurement sourcing system based on intelligent recommendation of supplier combinations, characterized in that, The system includes: A collection unit, configured to collect procurement requirement data and determine candidate suppliers based on the procurement requirement data to obtain candidate supplier combinations; A scoring unit, which is used to calculate the matching degree between a single candidate supplier within each candidate supplier combination and the procurement requirement data, as the basic evaluation score of a single candidate supplier within each candidate supplier combination, collect the real-time supply capacity information and retained procurement cooperation information of each single candidate supplier within each candidate supplier combination, and perform training on the real-time supply capacity information and the retained procurement cooperation information based on a pre-constructed combined evaluation score model to obtain the combined evaluation score of each candidate supplier combination; A processing unit, which is used to determine the procurement score of each candidate supplier combination respectively based on the combined evaluation score of each candidate supplier combination and the basic evaluation score of a single candidate supplier within the corresponding candidate supplier combination, and perform sorting on the procurement scores of each candidate supplier combination; A sourcing unit, which is used to perform candidate supplier combination recommendation based on the sorting result, and perform procurement sourcing based on the recommended candidate supplier combination to obtain a procurement sourcing result.

Images