Supplier determination method and device and storage medium

Abstract

The invention discloses a supplier determination method and device and a storage medium, relates to the technical field of production and manufacturing, and aims to at least solve the problem that a matched supplier result is not accurate. The method comprises the following steps: determining a plurality of candidate suppliers providing a target material based on a mapping relationship between suppliers and materials; determining a target constraint condition satisfied by the target supplier under the target demand; and selecting a target supplier satisfying a target constraint condition from the plurality of candidate suppliers.

Description

Technical Field

[0001] The present application relates to the field of production and manufacturing technology, and in particular to a supplier determination method, device and storage medium. Background Art

[0002] The agreement matching business mainly involves the demand department submitting a purchase application based on actual demand. After internal approval, the material department manually determines whether the inventory is balanced. If the condition of balanced inventory is not met, the material department regularly matches an agreement supplier according to fixed matching rules to complete the agreement matching. The above agreement matching method of determining suppliers is mainly based on a single matching based on simple material coding rules. The above matched suppliers are not accurate and it is difficult to meet the requirements of the demand department. There are problems such as high risks of contract termination and substandard quality. Summary of the invention

[0003] The present invention provides a supplier determination method, device and storage medium to at least solve the problem that the matching supplier results in the related art are not accurate. The technical solution of the present invention is as follows:

[0004] According to a first aspect of an embodiment of the present invention, a supplier determination method is provided, the method comprising: determining multiple candidate suppliers that provide target materials based on a mapping relationship between suppliers and materials; determining target constraints that the target supplier must satisfy under target demand; and selecting a target supplier that satisfies the target constraints from among multiple candidate suppliers.

[0005] Optionally, in order to ensure the quality requirements for materials, multiple candidate suppliers whose historical quality qualification rates are higher than a preset quality qualification rate are determined from the candidate suppliers associated with the target supplier, so as to preliminarily ensure that the quality of the materials supplied by the multiple candidate suppliers is high.

[0006] The preset quality pass rate may be set by the user or may be a default pass rate value, and this application does not make any specific limitation on this.

[0007] The above-mentioned target demand may be a demand input by the user, or a target demand identified and converted based on the demand information input by the user, or a default demand, which is not specifically limited in this application.

[0008] According to a second aspect of an embodiment of the present invention, a supplier determination device is provided, which includes: a first determination unit, used to determine multiple candidate suppliers providing target materials based on a mapping relationship between suppliers and materials; a second determination unit, used to determine target constraints satisfied by the target supplier under target demand; and a selection unit, used to select a target supplier that satisfies the target constraints from multiple candidate suppliers.

[0009] According to a third aspect of an embodiment of the present invention, a supplier determination device is provided. The supplier determination device is configured to execute the supplier determination method according to the first aspect and any possible implementation manner thereof.

[0010] According to a fourth aspect of an embodiment of the present invention, a computer device is provided, comprising: a processor and a memory for storing processor executable instructions; wherein the processor is configured to execute the executable instructions to implement a supplier determination method as in the first aspect and any possible implementation thereof.

[0011] According to a fifth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, on which instructions are stored. When the instructions in the computer-readable storage medium are executed by a processor of a computer device, the computer device is enabled to execute a supplier determination method such as the first aspect and any possible implementation thereof.

[0012] According to a sixth aspect of an embodiment of the present application, a computer program product is provided, the computer program product comprising computer instructions, which, when executed on a computer device, enables the computer device to execute the supplier determination method of the first aspect and any possible implementation thereof.

[0013] The technical solution provided by the embodiment of the present invention brings at least the following beneficial effects: First, based on the mapping relationship between the material and the supplier that can provide the material, multiple candidate suppliers associated with the target material are determined to ensure that the selected multiple candidate suppliers have the supply capacity to supply the target material. Further, target constraints are constructed based on the target demand to screen out target suppliers that meet the target constraints, so as to ensure that the screened target suppliers can better meet the supply demand, improve the matching degree and accuracy of the supplier, and reduce the risk of contract termination and substandard quality.

[0014] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application, and do not constitute improper limitations on the present application.

[0016] Figure 1 is a flow chart showing a method for determining a supplier according to an exemplary embodiment;

[0017] Figure 2 is a block diagram of a supplier determination device according to an exemplary embodiment;

[0018] Figure 3 The figure is a schematic diagram showing a supplier determination device according to an exemplary embodiment. DETAILED DESCRIPTION

[0019] In order to enable ordinary persons in the art to better understand the technical solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0020] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.

[0021] Before introducing in detail the supplier determination method provided in the embodiment of the present application, a brief introduction to the application scenarios involved in the embodiment of the present application is first given.

[0022] The agreement matching business mainly involves the demand department submitting a purchase application based on actual demand. After internal approval, the material department manually determines whether the inventory is balanced. If the condition of balanced inventory is not met, the material department regularly matches an agreement supplier according to fixed matching rules to complete the agreement matching. The above agreement matching method of determining suppliers is mainly based on a single matching based on simple material coding rules. The above matched suppliers are not accurate and it is difficult to meet the requirements of the demand department. There are problems such as high risks of contract termination and substandard quality.

[0023] Specifically, the agreement matching business mainly involves the demand department submitting a purchase application based on actual demand. After internal approval, the material department manually determines whether the inventory is balanced. If the condition of balanced inventory is not met, the material department regularly matches an agreement supplier according to fixed matching rules to complete the agreement matching. The agreement matching process cannot take into account whether the supplier's production capacity, supply cycle, etc. meet the requirements of the demand department. In addition, the matching process cannot avoid human intervention, resulting in risks in the later performance of the contract.

[0024] Research has found that the traditional agreement inventory matching method only matches multiple conditions through simple material coding, and there is the possibility of human intervention. It is unable to consider multiple conditions including supplier performance capabilities, production capacity, transportation distance, etc. The matching results may be difficult to meet the requirements of the demand department, and there are problems such as high risks of contract termination and substandard quality.

[0025] In view of the above problems, in order to optimize and improve the above supplier matching business process, this application provides a supplier determination method. First, based on the mapping relationship between the material and the supplier that can provide the material, multiple candidate suppliers associated with the target material are determined to ensure that the selected multiple candidate suppliers have the supply capacity to supply the target material. Further, target constraints are constructed based on the target demand to screen out target suppliers that meet the target constraints. In this way, it is ensured that the selected target suppliers can better meet the supply demand, improve the matching degree and accuracy of the supplier, and reduce the risk of contract termination and substandard quality.

[0026] When the above-mentioned supplier determination method is applied to the agreement matching process, the characteristics of the agreement matching related information systems and business scenarios are analyzed. Relying on the smart material allocation platform and the data middle platform, the material allocation mechanism is optimized and improved, and the work processes such as agreement matching, order execution, and fulfillment coordination are comprehensively sorted out. Through big data analysis, various factors such as supplier fulfillment capabilities, timeliness of delivery, delivery distance, and transportation cycle are fully considered. After comprehensive analysis, intelligent and agile agreement matching is carried out to avoid matching suppliers with high fulfillment risk levels, effectively reducing the risks of late contract termination and unqualified quality.

[0027] For ease of understanding, the supplier determination method provided in this application is specifically introduced below with reference to the accompanying drawings.

[0028] Figure 1 is a flow chart showing a method for determining a supplier according to an exemplary embodiment. Figure 1 As shown, the supplier determination method includes the following steps.

[0029] S11, based on the mapping relationship between suppliers and materials, determine multiple candidate suppliers that provide the target material.

[0030] It is understandable that the above-mentioned multiple candidate suppliers are suppliers associated with the target material.

[0031] Optionally, in order to ensure the quality requirements for materials, multiple candidate suppliers whose historical quality qualification rates are higher than a preset quality qualification rate are determined from the candidate suppliers associated with the target supplier, so as to preliminarily ensure that the quality of the materials supplied by the multiple candidate suppliers is high.

[0032] The preset quality pass rate may be set by the user or may be a default pass rate value, and this application does not make any specific limitation on this.

[0033] S12, determining the target constraints satisfied by the target supplier under the target demand.

[0034] The above target requirements may be requirements such as the lowest cost, the best speed, or the shortest delivery time, etc. It may also be requirements such as the delivery time is less than the preset time, and the cost is less than the preset cost, etc.

[0035] The above-mentioned target demand may be a demand input by the user, or a target demand identified and converted based on the demand information input by the user, or a default demand, which is not specifically limited in this application.

[0036] S13, selecting a target supplier that meets the target constraint conditions from multiple candidate suppliers.

[0037] In the above implementation, firstly, based on the mapping relationship between the material and the supplier that can provide the material, multiple candidate suppliers associated with the target material are determined to ensure that the selected multiple candidate suppliers have the supply capacity to supply the target material. Then, target constraints are further constructed based on the target demand to screen out target suppliers that meet the target constraints. In this way, it is ensured that the selected target suppliers can better meet the supply demand, improve the matching degree and accuracy of the suppliers, and reduce the risks of contract termination and substandard quality.

[0038] As a refinement and extension of the specific implementation methods of the above-mentioned embodiment, in order to fully illustrate the specific implementation process of this embodiment, the embodiment of the present application provides implementation methods of other supplier determination methods.

[0039] As a constraint method, a corresponding preset cost constraint method is set for the lowest cost demand scenario. The specific process of determining the target constraint in the above step S12 includes: when the target demand indicates that the total supply cost of the target supplier is the lowest; based on the preset cost constraint, constructing the target constraint.

[0040] Optionally, the preset cost constraints include material supply price cost constraints, supply delay costs, inventory cost constraints, and material transportation cost constraints. The supply delay costs are related to the material delivery time and the expected delivery time, and the inventory cost constraints are related to the material delivery time and the material planned production time.

[0041] The specific process of constructing the target constraint condition based on the preset cost constraint condition is as follows: Based on the preset cost constraint condition, construct the target constraint condition of minimizing the sum of the target material supply price cost, target supply delay cost, target inventory cost and target material transportation cost under the target quantity of target materials.

[0042] Based on this, the specific process of selecting a target supplier that meets the target constraint conditions from multiple candidate suppliers in the above step S13 is as follows.

[0043] First, determine each candidate cost of supplying the target material to each candidate supplier among multiple candidate suppliers.

[0044] The candidate cost is the sum of the candidate material supply price cost, the candidate supply delay cost, the candidate inventory cost and the candidate material transportation cost.

[0045] Secondly, the candidate supplier with the smallest candidate cost is selected from among all the candidate costs and determined as the target supplier.

[0046] Furthermore, the candidate delivery time of the target material in the above-mentioned candidate supply delay cost is determined according to the historical delivery time and actual productivity of the corresponding candidate supplier.

[0047] It is understandable that before determining each candidate cost of supplying the target material by each candidate supplier among multiple candidate suppliers, the method also includes: for any candidate supplier, based on the candidate supplier's historical delivery period and current actual productivity for materials of the same type of the target material, determining the candidate delivery time for the candidate supplier to supply the target material.

[0048] In order to ensure rapidity and accuracy in determining the candidate delivery time, the above-mentioned determination of the candidate delivery time for the candidate supplier to supply the target material includes the following process.

[0049] First, for any candidate supplier, based on the historical delivery dates of the same type of materials supplied by the candidate supplier, the corresponding historical actual productivity and historical material quantity, the mapping relationship between the actual productivity and material quantity and the delivery date is trained to obtain a preset model of the candidate supplier.

[0050] Different suppliers in this application correspond to different preset models.

[0051] Secondly, after identifying and obtaining the material type, target quantity and current actual productivity of the target material, the material type, target quantity and current actual productivity of the target material are input into the preset model to predict the candidate delivery period of the target material supplied by the candidate supplier, so as to calculate the candidate delivery time according to the candidate delivery period.

[0052] Understandably, the productivity of suppliers is usually different, considering that the actual productivity of the same supplier in different time periods is completely different, such as the peak production season or the low production season.

[0053] As another constraint method, a corresponding preset time constraint method is set for the shortest delivery period demand scenario. The specific process of determining the target constraint condition in the above step S12 includes: when the target demand indicates that the target supplier has the shortest delivery period; based on the preset time constraint condition, constructing the target constraint condition.

[0054] The above-mentioned time constraints include production time constraints and transportation time constraints.

[0055] The specific process of constructing the target constraint condition based on the preset time constraint condition is as follows: based on the preset time constraint condition, construct a target constraint condition that minimizes the sum of the target production time and the target transportation time of the target quantity of the target material;

[0056] Based on this, the specific process of selecting a target supplier that meets the target constraint conditions from multiple candidate suppliers in the above step S13 is as follows.

[0057] First, determine each candidate delivery time for each candidate supplier among multiple candidate suppliers to supply the target material.

[0058] The candidate delivery time is the sum of the candidate production time and the candidate transportation time.

[0059] Secondly, the candidate supplier with the shortest delivery time is selected from among all the candidate costs and is determined as the target supplier.

[0060] Furthermore, the candidate production time may be determined based on the actual productivity and target quantity of the candidate supplier; the candidate transportation time may be determined based on the distance between the shipping address and the receiving address of the candidate supplier and the delivery speed of the candidate supply equipment.

[0061] The specific process of determining each candidate delivery time for each candidate supplier among multiple candidate suppliers to supply the target material includes:

[0062] First, for any candidate supplier, the candidate production time is determined based on the actual productivity of the candidate supplier and the target quantity of the target material.

[0063] Second, determine the candidate transportation time based on the distance between the candidate supplier's shipping address and the delivery address and the delivery speed of the candidate supply equipment.

[0064] In the above implementation, multiple key factors are fully considered to ensure the comprehensiveness and accuracy of supplier matching.

[0065] Several key factors can be some of the following are important factors to consider.

[0066] First, supplier performance capability: This is the supplier's ability to fulfill its obligations according to the contract terms and delivery commitments. It can be measured by indicators such as historical delivery records, quality ratings, and historical contract termination rates.

[0067] Second, the timely delivery rate: The supplier's delivery punctuality is one of the key factors. This can be evaluated through historical delivery time data to ensure that the supplier can deliver materials on time.

[0068] Third, delivery distance and transportation cycle: These two factors take into account the distance between the supplier's geographical location and the demand department and the time required for transportation. This will affect the delivery cost and time.

[0069] Fourth, supplier production capacity: It is key to understand the production capacity of suppliers to ensure that they can meet the requirements of the demand department and there will be no shortage of supply.

[0070] Fifth, shipping time: Consider shipping time, including the time it takes for the supplier to deliver the item and the time it takes to deliver the item. This can be determined through historical shipping data and delivery schedules.

[0071] Sixth, delivery range: ensure that the supplier’s delivery range can cover the area of ​​the demand department to avoid additional transportation costs and delays.

[0072] As a specific embodiment, according to the data storage platform and protocol matching method, the specific process of implementing the above-mentioned supplier determination is as follows.

[0073] First, collect data.

[0074] First, it is necessary to collect data related to the agreement inventory from various channels, including sales data, inventory data, transaction data, supplier information, etc., in order to determine the historical supply data of each supplier, and the historical supply data is used to determine the preset model.

[0075] This data can come from the company's internal systems or from external data sources, such as supply chain systems, e-commerce platforms, logistics companies, etc. The collected data needs to be cleaned, processed, and standardized to ensure that it can be used for subsequent analysis and modeling.

[0076] Data collection and integration is one of the key steps in the intelligent agile matching method of agreement inventory. It involves collecting agreements, contracts and related data from multiple data sources and then integrating these data into a unified data storage platform. The following is a detailed description of the data collection and integration process.

[0077] (1) Determine the data source: Before starting data collection and integration, you first need to identify the source of the data to be collected. Usually, these data sources include but are not limited to:

[0078] Purchase Requisition: Contains purchase requisition and demand information of the demand department.

[0079] Contract data: Contains all agreements, contracts and related documents.

[0080] Supplier information: Contains information about the supplier, such as supplier name, address, contact information, etc.

[0081] Material code: Contains material code, description, specifications and other information.

[0082] Other data sources that may be involved in protocol matching.

[0083] (2) Data collection: Once the data sources are determined, the next step is to collect data from these data sources. Data collection can be carried out in the following ways:

[0084] Manual entry: For some data sources, manual data entry may be required, such as special requirements in purchase requisitions or manual entry of contracts.

[0085] Automatic import: For electronic data sources such as databases and supplier information systems, you can write programs or use ETL (Extract, Transform, Load) tools to automatically import data into the collection system.

[0086] Data interface: Some systems provide data interfaces, from which data can be directly obtained to ensure the real-time and accuracy of the data.

[0087] (3) Data integration: Once data collection is completed, the next key step is to integrate this data into a single data storage platform to ensure data consistency and accessibility. This includes the following operations:

[0088] Data standardization: Standardize data from different data sources to ensure consistency in field names, formats, and data types. For example, unify date formats, naming rules for material codes, etc.

[0089] Data cleaning: During the integration process, errors, duplications, or incomplete information may be found in the data. These issues need to be identified and corrected to improve data quality.

[0090] Data association: Associating data from different data sources to establish relationships between data, for example, associating a purchase requisition with the corresponding agreement or contract.

[0091] (4) Data storage: The integrated data needs to be stored in a data storage platform for subsequent analysis and matching operations. This storage platform is usually a large data storage system, such as Hadoop HDFS, database management system, etc., which has high capacity and high performance and can accommodate large amounts of data.

[0092] (5) Data indexing and metadata management: In order to support fast data retrieval and management, it is necessary to establish a data indexing and metadata management system. Data indexing can create indexes based on key fields (such as contract number, material code, etc.) to improve retrieval efficiency. The metadata management system is used to record the basic attributes and description information of the data to help users understand and use the data.

[0093] (6) Security and authority control: During the data integration and storage process, data security must be considered. Appropriate authority control mechanisms should be implemented to ensure that only authorized personnel can access and operate data.

[0094] Through data collection and integration, the agreement matching system can obtain a comprehensive and accurate data set, providing a strong foundation for subsequent intelligent matching algorithms. This data set includes agreements, contracts, suppliers, and material information from different data sources, providing key input for machine learning and intelligent matching.

[0095] Second: Data storage and management, so as to quickly obtain the historical supply data of each supplier and quickly build the preset model.

[0096] (1) Data storage platform

[0097] In the relevant data management, the big data storage platform plays a vital role. This platform is usually a distributed, high-performance storage system. Common solutions include:

[0098] Hadoop HDFS: Hadoop distributed file system, designed to store large-scale data with high capacity, fault tolerance and scalability.

[0099] Distributed database systems: For example, distributed databases such as HBase, Cassandra, and MongoDB can store structured or semi-structured data.

[0100] Cloud storage: Cloud platforms provide various storage services, such as Amazon S3, Google Cloud Storage, Azure Blob Storage, etc., which are suitable for cloud-native architecture.

[0101] (2)Data format and compression.

[0102] Before storing data, you usually need to select a suitable data format and compression method to reduce storage costs and improve data transmission efficiency. Common data formats include JSON, Parquet, Avro, etc. Compression methods such as GZIP and Snappy can reduce the size of data files.

[0103] (3) Data partitioning and bucketing.

[0104] To improve query efficiency, large-scale data is usually divided into smaller partitions or buckets. Partitions divide data into logical fragments, while buckets store data in groups, which can be divided according to certain keys (such as date, geographic location). This allows queries to more accurately locate the required data without having to scan the entire data set.

[0105] (4)Data index.

[0106] A data index is a key element for quickly locating data. Indexes are usually created based on one or more fields to speed up data retrieval operations. In an agreement matching scenario, an index may be created to speed up matching queries based on fields such as supplier, material code, or contract number.

[0107] (5) Metadata management.

[0108] Metadata is the descriptive information of data, which includes information about the attributes, structure and meaning of data. Metadata management is the operation performed to better understand and manage data. It includes:

[0109] Data Catalog: A list of all available datasets, including their name, description, owner, creation date, etc.

[0110] Field Description: Provide a detailed description for each field in the dataset, including data type, unit, meaning, etc.

[0111] Data dependencies: Record the dependencies between data to help users understand the source and relevance of data.

[0112] (6)Data backup and fault tolerance.

[0113] In order to ensure the security and availability of data, data backup and fault tolerance management are usually required. The data storage platform should have automatic backup, fault tolerance and disaster recovery mechanisms to ensure data continuity.

[0114] (7) Security and authority control.

[0115] Data storage management also needs to consider data security. This includes data encryption, access control, identity authentication and other security measures to ensure that only authorized users can access sensitive data.

[0116] Through effective data storage and management, the system can ensure the efficiency, security and availability of data. This provides a solid foundation for subsequent data analysis and intelligent matching operations, enabling the system to quickly retrieve, analyze and match data and provide efficient protocol inventory management services.

[0117] Third, for the same supplier, different preset models are constructed based on different algorithms, that is, one supplier corresponds to multiple candidate preset models.

[0118] The output results of each candidate preset model are evaluated, and the candidate preset model with the best evaluation result is determined as the preset model of the supplier.

[0119] In order to improve the accuracy and intelligence of matching, the specific process of obtaining the preset model by applying technologies such as machine learning and natural language processing (NLP) is as follows.

[0120] (1) Feature Engineering: Use machine learning techniques to extract important features from the data. These features can include historical supplier performance, delivery history, delivery location, delivery time, etc.

[0121] (2) Model selection: Select an appropriate machine learning model to solve the protocol matching problem. For example, you can consider using classification algorithms such as decision trees, random forests, and support vector machines (SVM).

[0122] (3) Deep Learning: For complex matching problems, one can consider using deep learning techniques, such as neural networks, to capture more complex patterns and relationships.

[0123] (4) Natural Language Processing: If text data is involved, such as supplier contracts or technical specifications, NLP techniques can be used to extract information about supplier performance and material descriptions.

[0124] (5) Comprehensive factor analysis. The specific process is described as follows.

[0125] Smart matching algorithms should consider a variety of factors, and they can use weighted scoring to analyze these factors. For example, you can assign a weight to each factor, and then apply these weights to the scores of each factor to get the overall match score. This can be achieved through a machine learning model, which can learn the influence of different factors on the final match.

[0126] (6) Real-time and adaptability evaluation.

[0127] As the supply chain environment is constantly changing, intelligent matching algorithms should be real-time and adaptive. The algorithm needs to be regularly updated with data and retrained to adapt to new supplier performance and market conditions.

[0128] (7)User feedback and improvement process.

[0129] Continuously monitor the matching effect and accuracy, collect user feedback, and continuously adjust and improve algorithms and models based on user feedback and actual operation to improve the matching accuracy and intelligence.

[0130] By comprehensively considering multiple factors and applying machine learning and natural language processing technologies, the intelligent matching algorithm can more accurately and intelligently select the most suitable agreement supplier to support the agility and efficiency of agreement inventory management. This helps reduce risks, improve the stability of contract execution, and save costs and resources for enterprises.

[0131] Fourth, the optimization process of the automatic matching preset model algorithm is as follows.

[0132] In the process of applying the model, it is necessary to continuously optimize and improve the effect of the model. Through the analysis and evaluation of the model, some existing problems and bottlenecks can be discovered, so as to further improve the model performance. For example, model parameters can be optimized, data collection strategies can be adjusted, and data sources can be added. Automatic matching and optimization are the core parts of the intelligent agile matching method of protocol inventory. It ensures that after the demand department submits a purchase application, the system can automatically trigger the matching process, use the intelligent matching algorithm to automatically select the most suitable protocol supplier, and improve the matching efficiency and accuracy through the optimization algorithm. The following is a detailed description of this process:

[0133] (1) Automatically trigger the matching process.

[0134] Once the demand department submits a purchase requisition, the system should be able to automatically identify and trigger the matching process. This can be achieved by setting the trigger conditions and rules of the system. The trigger conditions may include the submission time of the purchase requisition, the demand level of the demand department, the urgency of the material, etc. Once the trigger conditions are met, the system will immediately start the matching process.

[0135] (2) Application of intelligent matching algorithm.

[0136] During the matching process, the system uses intelligent matching algorithms to comprehensively analyze various factors to determine the most suitable supplier for the agreement, including supplier performance, delivery timeliness, delivery distance, transportation cycle, supplier production capacity, transportation time, distribution range and other factors.

[0137] Application example of smart matching algorithm: The system can calculate the matching score of each contract supplier, based on the weight of various factors and historical data. For example, a supplier may perform well in delivery timeliness, but have a long delivery distance. The smart matching algorithm can take these factors into consideration, assign a comprehensive score to each supplier, and select the supplier with the highest score.

[0138] (3) Application of optimization algorithms.

[0139] To improve matching efficiency and accuracy, optimization algorithms can be applied to further refine the matching process. These algorithms can ensure the best matching results within a given time.

[0140] Application examples of optimization algorithms: The system can use optimization techniques such as linear programming, integer programming or genetic algorithms to find the best combination of agreement suppliers to minimize total cost or meet specific requirements or deliver the fastest. For example, taking into account the supplier's fulfillment ability and delivery timeliness, the optimization algorithm can determine which suppliers should undertake which procurement requirements to minimize the total delivery cost.

[0141] (4) Real-time and adaptability.

[0142] The matching process needs to be real-time to adapt to the ever-changing supply chain environment. Therefore, the system should regularly update data, recalculate matching results, and automatically trigger the matching process. Adaptability means that the system can automatically adjust matching rules and weights according to different situations and needs to meet specific business requirements.

[0143] (5) User interface and feedback.

[0144] End users usually need a user-friendly interface to view the matching results and make necessary approvals or actions. The user interface should clearly display the matching results, including supplier information, cost estimates, delivery time, etc. In addition, the user interface should also allow users to provide feedback to improve the performance of the matching algorithm.

[0145] Through automatic matching and optimization, agreement inventory management can select agreement suppliers more efficiently and intelligently, reduce the need for manual intervention, improve the speed and accuracy of decision-making, and help reduce procurement costs and supply chain risks.

[0146] Fifth, the risk assessment and decision support process is as follows.

[0147] Agreement matching risk assessment and decision support is a crucial part of the agreement inventory intelligent agile matching method. It helps identify potential performance risks and provides decision support to help the material department and the demand department choose the agreement supplier more wisely. The following are the detailed implementation steps:

[0148] (1) Data preparation process.

[0149] Before conducting risk assessment and decision support, data must be prepared. This includes purchase application data, supplier performance data, historical transaction data, transportation and distribution data, etc. These data should be cleaned and organized to ensure their accuracy and completeness.

[0150] (2) Risk assessment model design process.

[0151] Design a risk assessment model that can automatically identify potential performance risks. This model can be built based on historical data and statistical methods, or it can use machine learning techniques to predict potential risks. The following are some common risk factors:

[0152] Supplier performance history: Analyze the supplier's historical delivery records to see if there are frequent delays in delivery or contract terminations.

[0153] On-time delivery rate: Consider the supplier's on-time delivery rate to identify whether there is a trend of delayed delivery.

[0154] Quality issues: Check whether the materials provided by the supplier meet the quality requirements and whether there are any complaints about quality issues.

[0155] Shipping issues: Consider the supplier’s shipping record, including issues such as damaged goods and shipping delays.

[0156] Financial health: Assess the supplier’s financial health to see if there are any financial risks, such as debt issues or payment problems.

[0157] (3) Risk assessment calculation process.

[0158] Using a risk assessment model, conduct a risk assessment for each potential agreement supplier. This may include assigning weights to each risk factor, calculating scores based on historical data and indicators, and combining these scores into an overall risk score.

[0159] (4) The decision support tools are as follows.

[0160] Provide a decision support tool that can combine the results of risk assessment with other factors (such as cost, delivery time, etc.) to provide decision support for the material department and the demand department. This tool can be a user-friendly interface that contains detailed information and risk assessment results for each agreed supplier.

[0161] (5) The decision-making process and rules are as follows.

[0162] Establish a decision-making process and rules to help users choose agreement suppliers more wisely. This can include setting thresholds. When the risk assessment score exceeds a certain threshold, the system will issue a warning or suggest choosing another supplier. At the same time, the decision-making process can also be defined to determine the next step of procurement, such as renegotiating the contract, selecting an alternative supplier, etc.

[0163] (6) Real-time update and feedback process.

[0164] Risk assessment and decision support tools should be real-time, so that risk assessments and recommendations can be updated as supply chain conditions change. User interfaces should allow users to provide feedback to improve the performance of risk assessment models and decision support tools.

[0165] (7)Continuous improvement process.

[0166] Monitor the performance and risks of the contract suppliers and continuously improve the risk assessment model and decision support tools. According to the actual performance, adjust the weight of risk factors and assessment methods to improve the accuracy of forecasts.

[0167] Through risk assessment and decision support, enterprises can more effectively manage the risks of contract suppliers, reduce potential performance issues, and improve the stability and efficiency of procurement. This process helps decision makers choose suppliers more wisely, making the procurement process more reliable and controllable.

[0168] Sixth, automatic fulfillment monitoring process.

[0169] Automatic performance monitoring is a key step in ensuring the success of agreement inventory management during the contract execution phase. This process aims to ensure that suppliers fulfill their obligations in accordance with the requirements and deadlines of the contract, and to issue alerts and provide solutions in a timely manner when abnormal situations are found. The following are detailed implementation steps:

[0170] (1) Data collection and monitoring trigger process.

[0171] During the contract execution phase, the system needs to collect relevant data from multiple data sources in real time or regularly, including supplier delivery records, quality inspection results, delivery time, etc. This can be achieved through system integration with suppliers, manual data entry, or external data providers. At the same time, monitoring trigger conditions need to be set to indicate when the system should monitor.

[0172] (2) Data integration and preprocessing process.

[0173] The collected data may come from different formats and sources, so it is necessary to integrate and preprocess the data. This includes data cleaning, removing errors and redundant information, format conversion, etc. The integrated data will become the basis for monitoring.

[0174] (3) The design process of the performance monitoring model.

[0175] Design a performance monitoring model that can evaluate the supplier's performance based on the collected data. This can be achieved using techniques such as rule engines, machine learning, statistical methods, etc. Here are some key indicators to monitor:

[0176] Timely delivery: By comparing the actual delivery time with the delivery time agreed in the contract, the system can evaluate whether the supplier delivers on time.

[0177] Quality pass rate: Through the inspection result data, the system can evaluate whether the materials provided by the supplier meet the quality standards specified in the contract.

[0178] Anomaly detection: The system can set rules or models to detect anomalies, such as frequent delivery delays, increase in quality issues, etc.

[0179] (4) Monitoring and alarm triggering process.

[0180] Based on the results of the monitoring model, the system should be able to monitor the supplier's performance in real time. When an abnormal situation is found, the system should immediately trigger an alarm. These alarms can be sent to relevant managers and teams through email, SMS, notifications, etc.

[0181] (5) Process of handling abnormal situations and providing solutions.

[0182] After an alert is issued, the system should provide solutions or suggestions to deal with the abnormal situation. This can include measures such as renegotiating contracts, finding alternative suppliers, tracking deliveries, quality reviews, etc. The system can record and track the execution of these solutions.

[0183] (6) Real-time reporting and analysis process.

[0184] The system should provide real-time reporting and analysis tools to monitor trends and statistics on supplier performance. This will help the management team better understand the supply chain status and make more effective strategic decisions.

[0185] (7) Automated processes and feedback loops.

[0186] Automated processes should be integrated with monitoring systems so that solutions are automatically triggered and feedback is recorded. This ensures a quick response to exceptions while also helping to establish a feedback loop to continuously improve supplier performance monitoring processes and rules.

[0187] By automating contract performance monitoring, companies can achieve more efficient contract execution, reduce risk, and improve supply chain reliability and transparency. This helps ensure that suppliers fulfill their obligations as required by the contract, reducing potential problems and costs, thereby driving the success of contract inventory management.

[0188] Seventh, feedback and improvement process.

[0189] Feedback and improvement are key links in the protocol inventory intelligent agile matching method. By continuously collecting user feedback and system performance data, and optimizing matching rules and strategies, we ensure that the system can adapt to changing needs and market conditions. The following are the detailed implementation steps:

[0190] (1) User feedback collection process.

[0191] Build a system that enables users to provide feedback easily. This can include feedback forms in the user interface, regular satisfaction surveys, user support channels, etc. Make sure user feedback channels are easy to access and use.

[0192] (2) Data collection and analysis.

[0193] Collect information from user feedback and system performance data. This may include user suggestions, complaints, problem reports, system performance indicators, matching success rates, etc. Use data analysis tools to analyze this data to identify potential problems and improvement points.

[0194] (3) Problem prioritization process.

[0195] Based on user feedback and data analysis results, issues are prioritized. Some issues may have a greater impact on the criticality of the supply chain and therefore need to be addressed more urgently, while others can be put on the back burner.

[0196] (4) Improve the planning process.

[0197] Develop improvement plans for the identified issues. Each plan should clearly specify the problem, solution, owner, and deadline. In addition, a priority plan can be established to ensure that critical issues are addressed first.

[0198] (5) Develop and test improvement processes.

[0199] According to the improvement plan, develop new matching rules, algorithms or system functions. Before implementation, ensure that the improvements will not introduce new problems through testing. Testing can include functional testing, performance testing, regression testing, etc.

[0200] (6) Implement the improvement process.

[0201] Once the improvements have been adequately tested and approved, they can be implemented in the production environment, ensuring that the implementation is smooth and with minimal disruption to existing operations.

[0202] (7) Monitoring and evaluation process.

[0203] After improvements are implemented, monitor system performance and user feedback to ensure the effectiveness of the improvements. Continue to collect data to assess the impact of the improvements and the extent to which the problems have been resolved. If problems are found to persist or new problems arise, take timely measures to fix them.

[0204] (8) Periodic review and adjustment process.

[0205] Establish a cyclical review and adjustment process to ensure continuous improvement of the system. This can include regular improvement meetings to discuss user feedback and performance data, develop new improvement plans, and update priorities.

[0206] (9) Document and knowledge management process.

[0207] Maintain detailed documentation of all improvement plans, implementation steps, test results, and user feedback. This helps with knowledge management and ensures the team can leverage previous experiences in the future.

[0208] Through a continuous feedback and improvement cycle, the system is able to gradually improve matching accuracy, performance, and user satisfaction. This ensures that the system can adapt to changing needs and market conditions, maintain competitive advantage, and continue to provide value.

[0209] In order to achieve the above functions, the supplier determines that the device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0210] The present application also provides a method Figure 2 The supplier determination device shown includes: a first determination unit 201, a second determination unit 202 and a selection unit 203.

[0211] The first determining unit 201 is used to determine a plurality of candidate suppliers that provide the target material based on the mapping relationship between the supplier and the material.

[0212] The second determining unit 202 is used to determine the target constraint conditions satisfied by the target supplier under the target demand.

[0213] The selection unit 203 is used to select a target supplier that meets the target constraint condition from multiple candidate suppliers.

[0214] As an implementation manner, the second determining unit 202 is specifically used for: when the target demand indicates that the total supply cost of the target supplier is the lowest; and based on a preset cost constraint condition, constructing a target constraint condition.

[0215] As another implementation method, the preset cost constraints include material supply price cost constraints, supply delay costs, inventory cost constraints, and material transportation cost constraints. The supply delay costs are related to the material delivery time and the expected delivery time, and the inventory cost constraints are related to the material delivery time and the material planned production time. The second determination unit 202 is specifically used to: based on the preset cost constraints, construct a target constraint condition for minimizing the sum of the target material supply price cost, target supply delay cost, target inventory cost, and target material transportation cost under the target quantity of the target material.

[0216] The selection unit 203 is specifically used for: determining each candidate cost of supplying the target material by each candidate supplier among multiple candidate suppliers; the candidate cost is the sum of the candidate material supply price cost, the candidate supply delay cost, the candidate inventory cost and the candidate material transportation cost; and selecting the candidate supplier with the smallest candidate cost from each candidate cost and determining it as the target supplier.

[0217] Among them, the candidate delivery time of the target material in the candidate supply delay cost is determined according to the historical delivery time and actual productivity of the corresponding candidate supplier.

[0218] As another implementation, the second determining unit 202 is specifically configured to: when the target demand indicates that the target supplier has the shortest delivery period; and construct a target constraint condition based on a preset time constraint condition.

[0219] As another implementation, the preset time constraint condition includes a production time constraint and a transportation time constraint; the second determination unit 202 is specifically used to: construct a target constraint condition for minimizing the sum of a target production time and a target transportation time of a target quantity of target materials based on the preset time constraint condition;

[0220] The selection unit 203 is specifically used to: determine each candidate delivery time for each candidate supplier among multiple candidate suppliers to supply the target material; the candidate delivery time is the sum of the candidate production time and the candidate transportation time; select the candidate supplier with the smallest candidate delivery time from each candidate cost and determine it as the target supplier.

[0221] The candidate production time is determined based on the actual productivity and target quantity of the candidate supplier; the candidate transportation time is determined based on the distance between the shipping address and the receiving address of the candidate supplier and the delivery speed of the candidate supply equipment.

[0222] As another embodiment, before determining each candidate cost of supplying the target material by each candidate supplier among multiple candidate suppliers, the device is also used to: for any candidate supplier, determine the candidate delivery time of the candidate supplier for supplying the target material based on the candidate supplier's historical delivery period and current actual productivity for materials of the same type of the target material.

[0223] As another embodiment, the device is also used to: for any candidate supplier, train the mapping relationship between actual productivity and material quantity and delivery period based on the historical delivery periods of materials of the same type of target material supplied by the candidate supplier, the corresponding historical actual productivity and historical material quantity, and obtain a preset model of the candidate supplier; based on the preset model, identify the material type and target quantity of the target material, predict the candidate delivery period of the target material supplied by the candidate supplier, and calculate the candidate delivery time according to the candidate delivery period.

[0224] As another embodiment, the device is also used to: for any candidate supplier, determine the candidate production time based on the actual productivity of the candidate supplier and the target quantity of the target material; determine the candidate transportation time based on the distance between the shipping address and the receiving address of the candidate supplier and the delivery speed of the candidate supply equipment.

[0225] Regarding the device in the above embodiment, the specific manner in which each unit module performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.

[0226] Figure 3 is a schematic diagram of a supplier determination device provided by this application. Figure 3 The supplier determination device 60 may include at least one processor 601 and a memory 603 for storing processor executable instructions. The processor 601 is configured to execute instructions in the memory 603 to implement the supplier determination method in the following embodiments.

[0227] In addition, the supplier determination device 60 may further include a communication bus 602 , at least one communication interface 604 , an input device 606 , and an output device 605 .

[0228] The processor 601 may be a central processing unit (CPU), a microprocessing unit, an ASIC, or one or more integrated circuits for controlling the execution of the program of the present application.

[0229] Communication bus 602 may include a pathway for transmitting information between the above-mentioned components.

[0230] The communication interface 604 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0231] The input device 606 is used to receive input signals and the output device 605 is used to output signals.

[0232] The memory 603 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory may exist independently and be connected to the processing unit through a bus. The memory may also be integrated with the processing unit.

[0233] The memory 603 is used to store instructions for executing the solution of the present application, and the execution is controlled by the processor 601. The processor 601 is used to execute the instructions stored in the memory 603, so as to realize the functions in the method of the present application.

[0234] In a specific implementation, as an embodiment, the processor 601 may include one or more CPUs, such as Figure 3 CPU0 and CPU1 in.

[0235] In a specific implementation, as an embodiment, the supplier determination device 60 may include multiple processors, such as Figure 3 601 and processor 607 in FIG. Each of these processors may be a single-CPU processor or a multi-CPU processor. A processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0236] The supplier determines the equipment as Figure 3 The system shown includes: a processor 601 and a memory 603 for storing executable instructions of the processor 601; wherein the processor 601 is configured to execute the executable instructions to implement the supplier determination method of any possible implementation method described above. And the same technical effect can be achieved, so it will not be described here to avoid repetition.

[0237] The embodiment of the present application also provides a computer-readable storage medium, when the instructions in the computer-readable storage medium are executed by the processor of the supplier determination device or supplier determination equipment, the supplier determination device or supplier determination equipment can perform the supplier determination method as any of the possible implementations described above. And the same technical effect can be achieved, so it will not be repeated here to avoid repetition.

[0238] The embodiment of the present application also provides a computer program product, including a computer program or an instruction, which is executed by a processor to perform a supplier determination method in any of the above possible implementations. The same technical effect can be achieved, and to avoid repetition, it will not be described here.

[0239] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0240] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for determining a supplier, characterized in that: The method comprises: Based on the mapping relationship between suppliers and materials, multiple candidate suppliers that provide target materials are determined; Determine the target constraints that the target supplier must meet under the target demand; The target supplier that meets the target constraint condition is selected from the multiple candidate suppliers.

2. The supplier determination method according to claim 1, characterized in that: The target constraint conditions to be satisfied by the target supplier under the target demand are determined as follows: When the target demand indicates that the total supply cost of the target supplier is the lowest; Based on the preset cost constraint condition, the target constraint condition is constructed.

3. The supplier determination method according to claim 2, characterized in that: The preset cost constraints include material supply price cost constraints, supply delay costs, inventory cost constraints, and material transportation cost constraints. The supply delay costs are related to the material delivery time and expected delivery time, and the inventory cost constraints are related to the material delivery time and the material planned production time. The target constraints are constructed based on the preset cost constraints, including: Based on the preset cost constraint condition, construct the target constraint condition that minimizes the sum of the target material supply price cost, the target supply delay cost, the target inventory cost and the target material transportation cost under the target quantity; The step of selecting the target supplier satisfying the target constraint condition from the multiple candidate suppliers comprises: Determine each candidate cost of each candidate supplier among the multiple candidate suppliers supplying the target material; the candidate cost is the sum of the candidate material supply price cost, the candidate supply delay cost, the candidate inventory cost and the candidate material transportation cost; A candidate supplier with the smallest candidate cost is selected from the candidate costs and determined as the target supplier.

4. The method for determining a supplier according to claim 1, characterized in that: The target constraint conditions to be satisfied by the target supplier under the target demand are determined as follows: The target demand indicates that the target supplier has the shortest delivery time; Based on the preset time constraint, the target constraint is constructed.

5. The method for determining a supplier according to claim 4, characterized in that: The preset time constraint condition includes a production time constraint and a transportation time constraint; the target constraint condition is constructed based on the preset time constraint condition, including: Based on the preset time constraint, construct the target constraint that the sum of the target production time and the target transportation time of the target quantity of the target material is minimized; The step of selecting the target supplier satisfying the target constraint condition from the multiple candidate suppliers comprises: Determine each candidate delivery time of the target material supplied by each candidate supplier among the multiple candidate suppliers; the candidate delivery time is the sum of the candidate production time and the candidate transportation time; A candidate supplier with the shortest candidate delivery time is selected from the candidate costs and determined as the target supplier.

6. The method for determining a supplier according to claim 3, characterized in that: Before determining each candidate cost of each candidate supplier among the plurality of candidate suppliers for supplying the target material, the method further includes: For any of the candidate suppliers, a candidate delivery time for the target material to be supplied by the candidate supplier is determined based on the historical delivery period and current actual productivity of the candidate supplier for materials of the same type as the target material.

7. The supplier determination method according to claim 6, characterized in that: The step of determining the candidate delivery time for the target material supplied by the candidate supplier according to the historical delivery period and current actual productivity of the candidate supplier for the same type of the target material includes: For any candidate supplier, according to each historical delivery period of the same type of materials supplied by the candidate supplier as the target material, the corresponding historical actual productivity and historical material quantity, the mapping relationship representing the actual productivity and material quantity and the delivery period is trained to obtain a preset model of the candidate supplier; Based on the preset model, the material type and target quantity of the target material are identified, and the candidate delivery period for the candidate supplier to supply the target material is predicted, so as to calculate the candidate delivery time according to the candidate delivery period.

8. The method for determining a supplier according to claim 5, characterized in that: The determining each candidate delivery time of each candidate supplier among the multiple candidate suppliers for supplying the target material comprises: For any of the candidate suppliers, determining the candidate production time according to the actual productivity of the candidate supplier and the target quantity of the target material; The candidate transportation time is determined according to the distance between the shipping address and the receiving address of the candidate supplier and the delivery speed of the candidate supply equipment.

9. A supplier determination device, characterized in that: The device comprises: A first determining unit, configured to determine a plurality of candidate suppliers providing the target material based on a mapping relationship between the supplier and the material; The second determination unit is used to determine the target constraint conditions satisfied by the target supplier under the target demand; A selection unit is used to select the target supplier that meets the target constraint condition from the multiple candidate suppliers.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor of a supplier determination device, the supplier determination device is caused to perform the supplier determination method according to any one of claims 1 to 8.

Images