Supply chain payable account intelligent management method and system based on multi-dimensional dynamic evaluation

Abstract

The invention provides a supply chain payable account intelligent management method and system based on multi-dimensional dynamic evaluation, belongs to the technical field of enterprise supply chain management and financial integration, and aims to reduce the risk of tail money loss caused by quality disputes and enhance the stability of a supply chain through a three-dimensional evaluation model. And due to dynamic account period configuration, the account payable turnover rate is improved. Full-link data connection from order purchasing to financial payment is realized, and a payment strategy is automatically synchronized to an ERP system to generate a voucher. The real-time monitoring billboard supports a management layer to analyze fund distribution according to supplier, category and account period dimensions, and the supply chain management refinement degree is improved. According to the supply chain account payable intelligent management system based on multi-dimensional dynamic evaluation provided by the invention, through multi-technology fusion innovation, a business and financial deep collaborative account payable intelligent management system is constructed, the problems of extensive payment strategies and lagging risk response in a complex business scene are solved, and the system is suitable for large-scale popularization and application. And the method has remarkable technical advancement and industrial application value.

Description

Technical Field

[0001] This application relates to the field of enterprise supply chain management and business-finance integration technology, and in particular to a method and system for intelligent management of supply chain accounts payable based on multi-dimensional dynamic evaluation. Background Technology

[0002] In self-operated e-commerce and industrial product procurement, accounts payable management is a core aspect of supply chain cash flow. Traditional management models suffer from the following problems: they rely on fixed payment terms (e.g., 30 days, 60 days) or a single dimension (e.g., supplier size) to formulate payment strategies, failing to consider the impact of product characteristics (e.g., warranty period for appliances, lifespan of electrical consumables) and user feedback (e.g., quality ratings, after-sales rate) on the pace of cash release. For example, for electrical appliances, repair costs may arise during the warranty period, requiring a partial withholding of the final payment, but traditional systems cannot automatically apply such business rules.

[0003] The data silos between the financial system (accounts payable) and the business system (purchase orders, product categories, user reviews) lead to a disconnect between payment strategies and actual business scenarios. For example, changes in supplier reputation (decreased on-time delivery rate) or product quality issues (increased negative review rate) cannot drive real-time adjustments to payment terms, increasing financial risks or supply chain friction.

[0004] Lack of flexibility in providing financial support to high-reputation suppliers (such as failure to take advantage of early payment discounts in a timely manner) and lack of oversight of final payments for high-risk goods (such as full payment before the warranty period has expired) may lead to quality disputes or unreasonable use of funds. Summary of the Invention

[0005] This application provides a method and system for intelligent management of supply chain accounts payable based on multi-dimensional dynamic evaluation to improve the above-mentioned problems.

[0006] To achieve the above objectives, this application adopts the following technical solution:

[0007] Firstly, embodiments of this application propose a supply chain accounts payable intelligent management method based on multi-dimensional dynamic evaluation, the method comprising:

[0008] The system acquires supplier data, product data, user data, and financial data through data collection terminals. Supplier data includes performance record data, credit rating data, and historical payment period execution data. Product data includes category data, warranty period data, cost price data, and risk level data. Financial data includes budget amount data, cash flow forecast data, and cost of capital rate data.

[0009] Construct a supplier reputation scoring model, input the supplier data corresponding to the target supplier into the supplier reputation scoring model, and obtain the real-time reputation score of the target supplier based on the output of the supplier reputation scoring model;

[0010] Supply chain risk levels are determined based on real-time credit scores.

[0011] In conjunction with the first aspect, in some implementations, the method includes:

[0012] Construct a commodity risk level model, input the commodity data corresponding to the target commodity into the commodity risk level model, and determine the commodity risk level corresponding to the target commodity based on the output of the commodity risk level model;

[0013] Determining supply chain risk levels based on real-time credit scoring includes:

[0014] The supply chain risk level is determined based on the risk level of the goods.

[0015] In conjunction with the first aspect, in some implementations, the method includes:

[0016] Construct a user feedback index model, input the user data corresponding to the target user into the user feedback index model, and determine the feedback index corresponding to the target user based on the output of the user feedback index model;

[0017] Determining supply chain risk levels based on real-time credit scoring includes:

[0018] The risk level of the supply chain is determined based on the feedback index.

[0019] In conjunction with the first aspect, in some implementations, a supplier reputation scoring model is constructed. Supplier data corresponding to the target supplier is input into the supplier reputation scoring model, and a real-time reputation score for the target supplier is obtained based on the output of the supplier reputation scoring model. This includes:

[0020] The first training set is determined, which includes on-time delivery rate, quality pass rate, historical payment period fulfillment rate, and dynamic performance data. The on-time delivery rate is the proportion of on-time delivery in each monthly delivery batch, the quality pass rate is the proportion of qualified products in each batch, the historical payment period fulfillment rate is the proportion of orders with timely payment, and the dynamic performance data includes the number of complaints and the number of early delivery rewards recorded by the logistics system.

[0021] In conjunction with the first aspect, in some implementations, the supplier credit rating model is used to output a credit rating of 1-100 points based on the input supplier data, and the credit rating is used to quantify the overall credit level of the supplier.

[0022] In conjunction with the first aspect, in some implementation methods, a commodity risk level model is constructed. The commodity data corresponding to the target commodity is input into the commodity risk level model, and the commodity risk level corresponding to the target commodity is determined based on the output of the commodity risk level model. This includes:

[0023] A second training set was determined, which included product category data, warranty period data, and historical after-sales rate. The product category data was based on the enterprise's product classification, the warranty period data was based on electronic purchase contract documents, and the historical after-sales rate was obtained from the after-sales management system.

[0024] In conjunction with the first aspect, in some implementations, the commodity risk level model is used to output low, medium, and high risk levels based on input data such as commodity category, warranty period, and historical after-sales rate.

[0025] In conjunction with the first aspect, in some implementations, a user feedback index model is constructed. User data corresponding to the target user is input into the user feedback index model, and the feedback index corresponding to the target user is determined based on the output of the user feedback index model, including:

[0026] A third training set was determined, which included user review texts and corresponding product after-sales rate, after-sales rate, and fault reporting rate. The user review texts were collected from the enterprise's e-commerce platform or after-sales feedback system.

[0027] In conjunction with the first aspect, in some implementations, the user feedback index model is used to output a feedback index of 0-10 based on the input user data.

[0028] Secondly, embodiments of this application propose a supply chain accounts payable intelligent management system based on multi-dimensional dynamic evaluation, which is configured as follows:

[0029] The system acquires supplier data, product data, user data, and financial data through data collection terminals. Supplier data includes performance record data, credit rating data, and historical payment period execution data. Product data includes category data, warranty period data, cost price data, and risk level data. Financial data includes budget amount data, cash flow forecast data, and cost of capital rate data.

[0030] Construct a supplier reputation scoring model, input the supplier data corresponding to the target supplier into the supplier reputation scoring model, and obtain the real-time reputation score of the target supplier based on the output of the supplier reputation scoring model;

[0031] Supply chain risk levels are determined based on real-time credit scores.

[0032] In conjunction with the second aspect, in some implementations, the system is configured as follows:

[0033] Construct a commodity risk level model, input the commodity data corresponding to the target commodity into the commodity risk level model, and determine the commodity risk level corresponding to the target commodity based on the output of the commodity risk level model;

[0034] Determining supply chain risk levels based on real-time credit scoring includes:

[0035] The supply chain risk level is determined based on the risk level of the goods.

[0036] In conjunction with the second aspect, in some implementations, the system is configured as follows:

[0037] Construct a user feedback index model, input the user data corresponding to the target user into the user feedback index model, and determine the feedback index corresponding to the target user based on the output of the user feedback index model;

[0038] Determining supply chain risk levels based on real-time credit scoring includes:

[0039] The risk level of the supply chain is determined based on the feedback index.

[0040] In conjunction with the second aspect, in some implementations, the system is configured as follows:

[0041] Construct a supplier reputation scoring model, input the supplier data corresponding to the target supplier into the supplier reputation scoring model, and obtain the real-time reputation score of the target supplier based on the output of the supplier reputation scoring model, including:

[0042] The first training set is determined, which includes on-time delivery rate, quality pass rate, historical payment period fulfillment rate, and dynamic performance data. The on-time delivery rate is the proportion of on-time delivery in each monthly delivery batch, the quality pass rate is the proportion of qualified products in each batch, the historical payment period fulfillment rate is the proportion of orders with timely payment, and the dynamic performance data includes the number of complaints and the number of early delivery rewards recorded by the logistics system.

[0043] In conjunction with the second aspect, in some implementations, the system is configured as follows:

[0044] The supplier reputation scoring model is used to output a reputation score of 1-100 based on the input supplier data. The reputation score is used to quantify the overall credit level of the supplier.

[0045] In conjunction with the second aspect, in some implementations, the system is configured as follows:

[0046] Construct a commodity risk level model by inputting the commodity data corresponding to the target commodity into the model, and determining the commodity risk level corresponding to the target commodity based on the output of the model, including:

[0047] A second training set was determined, which included product category data, warranty period data, and historical after-sales rate. The product category data was based on the enterprise's product classification, the warranty period data was based on electronic purchase contract documents, and the historical after-sales rate was obtained from the after-sales management system.

[0048] In conjunction with the second aspect, in some implementations, the system is configured as follows:

[0049] The product risk level model is used to output low, medium, and high risk levels based on input data such as product category, warranty period, and historical after-sales rate.

[0050] In conjunction with the second aspect, in some implementations, the system is configured as follows:

[0051] Construct a user feedback index model by inputting user data corresponding to the target user into the model, and determining the feedback index corresponding to the target user based on the output of the model, including:

[0052] A third training set was determined, which included user review texts and corresponding product after-sales rate, after-sales rate, and fault reporting rate. The user review texts were collected from the enterprise's e-commerce platform or after-sales feedback system.

[0053] In conjunction with the second aspect, in some implementations, the system is configured as follows:

[0054] The user feedback index model is used to output a feedback index of 0-10 based on input user data.

[0055] The present invention provides an electronic device in three aspects, the electronic device comprising:

[0056] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method proposed in the first aspect of the present invention.

[0057] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method as described in the first aspect of the present invention.

[0058] In summary, the above methods and systems have the following technical effects:

[0059] This application proposes a multi-dimensional dynamic assessment-based intelligent management method for supply chain accounts payable. Through a three-dimensional assessment model, it reduces the risk of final payment losses due to quality disputes, enhancing supply chain stability. Dynamic payment term configuration improves accounts payable turnover. It achieves end-to-end data connectivity from purchase orders to financial payments, with payment strategies automatically synchronized to the ERP system to generate vouchers. Real-time monitoring dashboards allow management to analyze fund distribution by supplier, product category, and payment term, improving the precision of supply chain management. This application's multi-dimensional dynamic assessment-based intelligent management system for supply chain accounts payable, through multi-technology integration and innovation, constructs a deeply collaborative intelligent accounts payable management system, solving the problems of crude payment strategies and delayed risk response in complex business scenarios. It possesses significant technological advancement and industry application value. Attached Figure Description

[0060] Figure 1 This is a flowchart illustrating a supply chain accounts payable intelligent management method based on multi-dimensional dynamic evaluation proposed in an embodiment of this application. Detailed Implementation

[0061] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0062] This application proposes a supply chain accounts payable intelligent management method based on multi-dimensional dynamic evaluation. Please refer to [link to relevant documentation]. Figure 1 This includes the following steps:

[0063] S101: Acquire supplier data, product data, user data, and financial data based on the data acquisition terminal. Supplier data includes performance record data, credit rating data, and historical payment period execution data. Product data includes category data, warranty period data, cost price data, and risk level data. Financial data includes budget amount data, cash flow forecast data, and cost of capital rate data.

[0064] Understandably, supplier data is one of the core data sets. It includes performance record data, which documents whether the supplier has fulfilled its contractual obligations on time in past collaborations, thus helping to assess its reliability and the risks associated with the partnership. Furthermore, supplier data includes credit rating data, provided by third-party agencies, reflecting the supplier's creditworthiness and market reputation. Finally, historical payment terms data records the supplier's adherence to payment terms in past collaborations, which helps to understand its cash flow and financial stability.

[0065] Category data covers product classification information, helping to understand the market performance and demand of different categories. Warranty period data records the product's warranty period, which is crucial for assessing product quality and after-sales service. Cost price data provides the product's procurement cost, aiding in cost control and pricing strategy development. Risk level data comprehensively assesses the product's potential risks, including market risk and supply chain risk, enabling the implementation of appropriate risk control measures.

[0066] Financial data is a crucial basis for decision-making. Budget allocation data records the budget allocation of various departments or projects, aiding in financial planning and resource optimization. Cash flow forecast data provides predictions of cash inflows and outflows over a future period, which is essential for cash management and liquidity planning. Cost of capital data reflects the cost of obtaining funds, including loan interest rates and financing costs, which is significant for financial decision-making and cost control.

[0067] S102: Construct a supplier reputation scoring model, input the supplier data corresponding to the target supplier into the supplier reputation scoring model, and obtain the real-time reputation score of the target supplier based on the output of the supplier reputation scoring model.

[0068] Understandably, building a comprehensive supplier reputation scoring model requires collecting and integrating various types of data related to the target suppliers. This data includes, but is not limited to, the supplier's historical transaction records, contract performance, product quality, delivery time, customer feedback, and financial status. Through this detailed data, the supplier's overall reputation can be assessed more accurately.

[0069] The collected supplier data is input into a meticulously designed supplier reputation scoring model. This model employs advanced algorithms and statistical methods to comprehensively analyze and process various data. It identifies supplier performance in different aspects and assigns corresponding weights, thereby generating a comprehensive score. Based on the output of the supplier reputation scoring model, a quantitative score is obtained, representing the target supplier's real-time reputation score. This score not only reflects the supplier's past performance but also predicts its future reliability. By updating this score in real time, changes in supplier reputation can be monitored promptly, thus providing strong support for procurement decisions.

[0070] For example, a first training set can be determined first. The first training set includes on-time delivery rate, quality pass rate, historical payment period fulfillment rate, and dynamic performance data. Among them, the on-time delivery rate is the proportion of on-time delivery in each monthly delivery batch, the quality pass rate is the proportion of qualified products in each batch of goods, the historical payment period fulfillment rate is the proportion of orders with timely payment, and the dynamic performance data includes the number of complaints and the number of early delivery rewards recorded by the logistics system.

[0071] Specifically, the data sources and composition need to be clearly defined. For example, the on-time delivery rate of suppliers for the past two years (such as the proportion of on-time delivery in each monthly batch), quality pass rate (such as the proportion of qualified products in each batch), historical payment period fulfillment rate (such as the proportion of orders with timely payment), and dynamic performance data for the past three months (such as the number of complaints recorded through the customer service system and the number of early delivery rewards recorded through the logistics system) should be extracted from the enterprise's procurement management system.

[0072] S103: Construct a commodity risk level model. Input the commodity data corresponding to the target commodity into the commodity risk level model. Based on the output of the commodity risk level model, determine the commodity risk level corresponding to the target commodity.

[0073] To effectively assess the risk level of a product, a product risk rating model must first be constructed. This model will comprehensively analyze and evaluate various attributes of the product based on a series of pre-defined parameters and algorithms. Specifically, relevant data on the target product will be collected, including but not limited to its origin, quality, historical sales records, user reviews, price fluctuations, and market supply and demand. This data will be input into a carefully designed product risk rating model. In the model, each parameter will be assigned a certain weight to ensure the accuracy of the assessment results. For example, for some high-value products, the weight of price fluctuations may be higher, while for food products, the weight of quality inspection results may be greater. Through this comprehensive assessment, the model can output a quantitative risk rating result.

[0074] For example, logistic regression is a machine learning algorithm used to solve binary classification (0 or 1) problems, and it can also be extended to multi-classification problems. In supply chain accounts payable management, it is mainly used to build supplier credit scoring models. It analyzes various aspects of a supplier's information, such as financial status, operating history, and market performance, using this data as independent variables and the supplier's credit risk level as the dependent variable to establish a regression equation. By training on historical data, the parameters in the model are determined, enabling it to output a credit score from 1 to 100 based on the input supplier data. This quantifies the supplier's overall creditworthiness, helps companies assess the supplier's creditworthiness, and provides a basis for accounts payable decisions.

[0075] For example, the Analytic Hierarchy Process (AHP) can be used to construct a product risk level model. AHP is a systematic and hierarchical analytical method that combines qualitative and quantitative approaches. It categorizes factors related to product risk assessment, such as product category, warranty period, and historical after-sales rate, into different levels to construct a hierarchical model. By constructing a judgment matrix, the relative importance of each factor is compared pairwise to determine its weight. Then, the product data corresponding to the target product is input into the model, and by comprehensively considering each factor and its weight, the model ultimately outputs low, medium, and high risk levels. This helps companies clearly understand the risk level of their products in the supply chain and rationally plan their accounts payable strategies.

[0076] Based on the model's output, the risk level of the target product can be determined. This level can be a numerical range or a classification label, such as low risk, medium risk, and high risk. In this way, corresponding management strategies and countermeasures can be developed for different products, thereby effectively controlling and reducing product risk, protecting consumer interests, and ensuring the stable operation of the market.

[0077] Specifically, a second training set is determined, which includes product category data, warranty period data, and historical after-sales rate. Among them, the product category data is based on the enterprise's product classification, the warranty period data is based on electronic documents of purchase contracts, and the historical after-sales rate is obtained from the after-sales management system.

[0078] It is understandable that the scope and method of data collection should be clearly stated. For example, product category data should be based on the company's product classification catalog (such as detailed classification standards and corresponding coding data for electrical appliances, labor protection products, etc.), warranty period data should be extracted from electronic documents of purchase contracts (such as data that clearly records fields such as "180-day warranty" and "no warranty"), and historical after-sales rate should be obtained from the after-sales management system (such as the proportion of after-sales repairs or returns of a certain type of product in the past year to the total sales volume).

[0079] For example, a combined algorithm of the Analytic Hierarchy Process (AHP) and fuzzy comprehensive evaluation can be used to achieve quantitative analysis of product categories, warranty periods, and historical after-sales rates. Taking fuzzy comprehensive evaluation as an example, qualitative indicators (product categories) and quantitative indicators (warranty periods, after-sales rates) are transformed into fuzzy membership degrees. Risk levels are synthesized through matrix operations to adapt to the fuzziness of risk boundaries (e.g., "medium to high risk"). After training, it can output low, medium, and high risk levels based on input data such as product categories, warranty periods, and historical after-sales rates. For example, given the input "appliances, 180-day warranty, historical after-sales rate 5%", the model will output "low risk" through the algorithm, helping companies adopt more cautious payment strategies (e.g., reserving more final payments) for high-risk products in accounts payable management.

[0080] S104: Construct a user feedback index model. Input the user data corresponding to the target user into the user feedback index model. Based on the output of the user feedback index model, determine the feedback index corresponding to the target user. Determine the third training set, which includes user review texts and the after-sales rate, after-sales service rate, and fault repair rate of the corresponding products. The user review texts are collected from the enterprise's e-commerce platform or after-sales feedback system.

[0081] Specifically, the training set includes data sources such as collecting a large amount of user review texts (e.g., reviews from the past 3 years) from enterprise e-commerce platforms or after-sales feedback systems, while also integrating data such as after-sales rate and fault repair rate from after-sales management systems (e.g., annual after-sales rate and monthly fault repair frequency for a product).

[0082] The trained model can take new user review text and corresponding product after-sales rate, fault reporting rate, etc., as input, and output a feedback index of 0-10 points to quantify quality and service issues during product use. The lower the index, the more problems there are, and companies can use this information to adjust payment schedules or deduction strategies with suppliers in accounts payable management.

[0083] For example, the construction and nesting process of the user feedback index model integrates natural language processing models and statistical analysis models, and achieves quantitative evaluation of product quality and service issues through multi-level data processing.

[0084] Specifically, the model nesting technique can be divided into the following layers:

[0085] Bottom layer: Text semantic parsing layer

[0086] Pre-trained language models, such as BERT, are used to perform semantic understanding on user review texts, identifying quality-related keywords such as "fault" and "poor after-sales service," sentiment (positive / negative), and problem types such as functional defects and service delays. This layer transforms unstructured text into structured semantic feature vectors.

[0087] Middle layer: Quantitative data processing layer

[0088] Quantitative data such as after-sales rate and fault reporting rate are standardized, such as by Z-score standardization, and the impact of data fluctuations is eliminated by time series analysis such as moving average, generating trend characteristics such as the month-on-month change in after-sales rate over the past 3 months.

[0089] Top layer: Comprehensive scoring fusion layer

[0090] Using weighted fusion models such as logistic regression or random forest, the semantic features and quantitative trend features of the text are input, and the weights of each dimension are determined through training. For example, the weight of negative features of the text is 40%, the weight of after-sales rate is 35%, and the weight of repair rate is 25%, and the feedback index of 0-10 is output.

[0091] For nested processes, specifically, the BERT model can be used to encode user reviews. An attention mechanism captures the contextual semantics of quality keywords such as "leakage" and "abnormal noise," generating text embedding vectors. Then, a pooling layer (e.g., CLS token) extracts the overall semantic features. Logarithmic transformation or binning is applied to after-sales rates (e.g., "percentage of after-sales orders in the past 12 months") and fault repair rates (e.g., "number of repairs per thousand devices"), and the month-on-month growth rate is calculated using a time window (e.g., sliding by quarter) to generate dynamic trend features. The text embedding vectors and quantitative features are concatenated into a multi-dimensional feature matrix, which is then input into a random forest model for training. The model selects key features (e.g., frequency of negative keywords in the text, abrupt changes in after-sales rates) using Gini impurity and calculates the final score through decision tree ensemble.

[0092] S105: Determine the supply chain risk level based on real-time credit scores, feedback indices, and product risk levels.

[0093] As one implementation method, the user feedback index model is used to output a feedback index of 0-10 based on the input user data.

[0094] Understandably, a rules engine establishes multi-dimensional decision-making rules, linking evaluation results with payment strategies. For example: \(\text{Payment Ratio} = f(\text{Supplier Reputation Score},\text{Product Risk Level},\text{User Feedback Index})\) Specific rule examples:

[0095] When the supplier's credit score is ≥90 and the product risk level is low, the down payment ratio is ≥90% and the payment period is ≤7 days.

[0096] When the product risk level is medium risk and the user feedback index is less than 6 points, the down payment ratio is ≤80%, and the final payment (20%) must be paid after the warranty period ends.

[0097] When the supplier's credit score is less than 70 or the product feedback index is less than 5, the down payment ratio is less than 70%, the payment period is extended to 180 days, and it is linked to the warranty period and acceptance milestones.

[0098] Machine learning optimization: Use algorithms such as random forest and reinforcement learning to train historical payment data, identify key factors affecting capital turnover and supplier satisfaction, and dynamically adjust rule weights (e.g., the weight of user feedback index on electrical appliances is automatically increased to 40%).

[0099] In some implementations, multi-dimensional data fusion and evaluation may include the following steps:

[0100] 1. The supplier reputation rating uses the Analytic Hierarchy Process (AHP) to determine the indicator weights and combines the rolling data of the past 3 months to calculate the real-time score, thus solving the problem of lag in traditional static rating.

[0101] 2. The product risk level adopts the fuzzy comprehensive evaluation method, which combines product category characteristics (such as warranty period length) and historical after-sales data (such as the historical failure rate of a certain brand of transformers) to generate a dynamic level;

[0102] 3. The user feedback index uses the BERT model to analyze evaluation text (such as keywords like "leakage" and "abnormal noise" to identify quality problems) and combines it with data from the after-sales work order system to quantify quality risks.

[0103] For example, construct a set of evaluation factors, and then generate dynamic payment strategy logic:

[0104] 1. Establish a three-dimensional decision matrix, with the horizontal axis representing supplier credit rating (high / medium / low), the vertical axis representing product risk level (low / medium / high), and the third dimension representing user feedback index (excellent / good / poor). Each matrix unit corresponds to a unique combination of payment ratio and payment period.

[0105] 2. Supports custom exception rules, such as giving strategic suppliers (marked as "core partners") an additional 10% down payment discount to improve supply chain collaboration efficiency.

[0106] Business and finance integration and synergy are achieved:

[0107] 1. Funding Optimization Module: When a supplier offers an early payment discount (such as "1% discount for payment within 10 days"), the net benefit is calculated based on the company's short-term funding cost rate (such as a bank loan interest rate of 4%). If the discount benefit is greater than the funding cost, early payment is automatically recommended.

[0108] 2. Budget Coordination Module: Payment strategies must meet departmental budget constraints (such as the monthly budget of the purchasing department). Payment requests exceeding the budget will trigger tiered approval to ensure the compliance of fund usage.

[0109] This application proposes a multi-dimensional dynamic assessment-based intelligent management method for supply chain accounts payable. Through a three-dimensional assessment model, it reduces the risk of final payment losses due to quality disputes, enhancing supply chain stability. Dynamic payment term configuration improves accounts payable turnover. It achieves end-to-end data connectivity from purchase orders to financial payments, with payment strategies automatically synchronized to the ERP system to generate vouchers. Real-time monitoring dashboards allow management to analyze fund distribution by supplier, product category, and payment term, improving the precision of supply chain management. This multi-dimensional dynamic assessment-based intelligent management method for supply chain accounts payable, through multi-technology integration and innovation, constructs a deeply collaborative intelligent accounts payable management system, solving the problems of crude payment strategies and delayed risk response in complex business scenarios. It possesses significant technological advancement and industry application value.

[0110] Based on the same inventive concept, embodiments of this application also propose a supply chain accounts payable intelligent management system based on multi-dimensional dynamic evaluation, which is configured as follows:

[0111] The system acquires supplier data, product data, user data, and financial data through data collection terminals. Supplier data includes performance record data, credit rating data, and historical payment period execution data. Product data includes category data, warranty period data, cost price data, and risk level data. Financial data includes budget amount data, cash flow forecast data, and cost of capital rate data.

[0112] Construct a supplier reputation scoring model, input the supplier data corresponding to the target supplier into the supplier reputation scoring model, and obtain the real-time reputation score of the target supplier based on the output of the supplier reputation scoring model;

[0113] Supply chain risk levels are determined based on real-time credit scores.

[0114] In some implementations, the system is configured as follows:

[0115] Construct a commodity risk level model, input the commodity data corresponding to the target commodity into the commodity risk level model, and determine the commodity risk level corresponding to the target commodity based on the output of the commodity risk level model;

[0116] Determining supply chain risk levels based on real-time credit scoring includes:

[0117] The supply chain risk level is determined based on the risk level of the goods.

[0118] In some implementations, the system is configured as follows:

[0119] Construct a user feedback index model, input the user data corresponding to the target user into the user feedback index model, and determine the feedback index corresponding to the target user based on the output of the user feedback index model;

[0120] Determining supply chain risk levels based on real-time credit scoring includes:

[0121] The risk level of the supply chain is determined based on the feedback index.

[0122] In some implementations, the system is configured as follows:

[0123] Construct a supplier reputation scoring model, input the supplier data corresponding to the target supplier into the supplier reputation scoring model, and obtain the real-time reputation score of the target supplier based on the output of the supplier reputation scoring model, including:

[0124] The first training set is determined, which includes on-time delivery rate, quality pass rate, historical payment period fulfillment rate, and dynamic performance data. The on-time delivery rate is the proportion of on-time delivery in each monthly delivery batch, the quality pass rate is the proportion of qualified products in each batch, the historical payment period fulfillment rate is the proportion of orders with timely payment, and the dynamic performance data includes the number of complaints and the number of early delivery rewards recorded by the logistics system.

[0125] In some implementations, the system is configured as follows:

[0126] The supplier reputation scoring model is used to output a reputation score of 1-100 based on the input supplier data. The reputation score is used to quantify the overall credit level of the supplier.

[0127] In some implementations, the system is configured as follows:

[0128] Construct a commodity risk level model by inputting the commodity data corresponding to the target commodity into the model, and determining the commodity risk level corresponding to the target commodity based on the output of the model, including:

[0129] A second training set was determined, which included product category data, warranty period data, and historical after-sales rate. The product category data was based on the enterprise's product classification, the warranty period data was based on electronic purchase contract documents, and the historical after-sales rate was obtained from the after-sales management system.

[0130] In some implementations, the system is configured as follows:

[0131] The product risk level model is used to output low, medium, and high risk levels based on input data such as product category, warranty period, and historical after-sales rate.

[0132] In some implementations, the system is configured as follows:

[0133] Construct a user feedback index model by inputting user data corresponding to the target user into the model, and determining the feedback index corresponding to the target user based on the output of the model, including:

[0134] A third training set was determined, which included user review texts and corresponding product after-sales rate, after-sales rate, and fault reporting rate. The user review texts were collected from the enterprise's e-commerce platform or after-sales feedback system.

[0135] In some implementations, the system is configured as follows:

[0136] The user feedback index model is used to output a feedback index of 0-10 based on input user data.

[0137] This application proposes a multi-dimensional dynamic assessment-based intelligent management method for supply chain accounts payable. Through a three-dimensional assessment model, it reduces the risk of final payment losses due to quality disputes, enhancing supply chain stability. Dynamic payment term configuration improves accounts payable turnover. It achieves end-to-end data connectivity from purchase orders to financial payments, with payment strategies automatically synchronized to the ERP system to generate vouchers. Real-time monitoring dashboards allow management to analyze fund distribution by supplier, product category, and payment term, improving the precision of supply chain management. This application's multi-dimensional dynamic assessment-based intelligent management system for supply chain accounts payable, through multi-technology integration and innovation, constructs a deeply collaborative intelligent accounts payable management system, solving the problems of crude payment strategies and delayed risk response in complex business scenarios. It possesses significant technological advancement and industry application value.

[0138] Based on the same inventive concept, embodiments of this application also propose an electronic device, which includes:

[0139] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the supply chain accounts payable intelligent management method based on multi-dimensional dynamic evaluation according to embodiments of this application.

[0140] Furthermore, to achieve the above objectives, embodiments of this application also propose a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the supply chain accounts payable intelligent management method based on multi-dimensional dynamic evaluation, as described in the embodiments of this application.

[0141] The following is a detailed introduction to the various components of the electronic device:

[0142] In this context, the processor is the control center of the electronic device. It can be a single processor or a collective term for multiple processing elements. For example, a processor can be one or more central processing units (CPUs), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).

[0143] Alternatively, the processor can perform various functions of the electronic device by running or executing software programs stored in memory and by calling data stored in memory.

[0144] The memory is used to store the software program that executes the solution of the present invention, and the execution is controlled by the processor. The specific implementation method can be referred to the above method embodiment, which will not be repeated here.

[0145] Optionally, the memory can be read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions, random access memory (RAM) or other types of dynamic storage devices capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory can be integrated with the processor or exist independently and coupled to the processor through an interface circuit of an electronic device; this embodiment of the invention does not specifically limit this.

[0146] A transceiver is used to communicate with network devices or with terminal devices.

[0147] Optionally, the transceiver may include a receiver and a transmitter. The receiver is used to implement the receiving function, and the transmitter is used to implement the sending function.

[0148] Optionally, the transceiver can be integrated with the processor or exist independently and coupled to the processor through the router's interface circuit. This embodiment of the invention does not specifically limit this.

[0149] Furthermore, the technical effects of the electronic device can be referred to the technical effects of the data transmission method in the above method embodiments, and will not be repeated here.

[0150] It should be understood that the processor in the embodiments of the present invention can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0151] It should also be understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0152] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the flow or function according to the embodiments of the present invention is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. A computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. Semiconductor media can be solid-state drives.

[0153] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0154] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0155] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0156] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

Claims

1. A supply chain accounts payable intelligent management method based on multi-dimensional dynamic evaluation, characterized in that, The method includes: The system acquires supplier data, product data, user data, and financial data through a data acquisition terminal. The supplier data includes performance record data, credit rating data, and historical payment period execution data. The product data includes category data, warranty period data, cost price data, and risk level data. The financial data includes budget amount data, cash flow forecast data, and cost of capital rate data. Construct a supplier reputation scoring model, input the supplier data corresponding to the target supplier into the supplier reputation scoring model, and obtain the real-time reputation score corresponding to the target supplier based on the output of the supplier reputation scoring model; The supply chain risk level is determined based on the real-time credit score.

2. The intelligent supply chain accounts payable management method based on multi-dimensional dynamic evaluation according to claim 1, characterized in that, The method includes: Construct a commodity risk level model, input the commodity data corresponding to the target commodity into the commodity risk level model, and determine the commodity risk level corresponding to the target commodity based on the output of the commodity risk level model; Determining the supply chain risk level also includes: The supply chain risk level is determined based on the risk level of the goods.

3. The intelligent supply chain accounts payable management method based on multi-dimensional dynamic evaluation according to claim 2, characterized in that, The method includes: Construct a user feedback index model, input the user data corresponding to the target user into the user feedback index model, and determine the feedback index corresponding to the target user based on the output of the user feedback index model; Determining the supply chain risk level based on the real-time credit score includes: The supply chain risk level is determined based on the feedback index.

4. The intelligent supply chain accounts payable management method based on multi-dimensional dynamic evaluation according to claim 1, characterized in that, Obtain the real-time reputation score corresponding to the target supplier, including: A first training set is determined, which includes on-time delivery rate, quality pass rate, historical payment period fulfillment rate, and dynamic performance data. The on-time delivery rate is the proportion of on-time delivery in each monthly delivery batch. The quality pass rate is the proportion of qualified products in each batch of goods. The historical payment period fulfillment rate is the proportion of orders with timely payment. The dynamic performance data includes the number of complaints and the number of early delivery rewards recorded by the logistics system.

5. The intelligent supply chain accounts payable management method based on multi-dimensional dynamic evaluation according to claim 1, characterized in that, The supplier credit rating model is used to output a credit rating of 1-100 points based on the input supplier data. The credit rating is used to quantify the supplier's overall credit level.

6. The intelligent supply chain accounts payable management method based on multi-dimensional dynamic evaluation according to claim 2, characterized in that, Determining the risk level of the target product includes: A second training set is determined, which includes product category data, warranty period data, and historical after-sales rate. The product category data is based on the enterprise's product classification, the warranty period data is based on electronic purchase contract documents, and the historical after-sales rate is obtained from the after-sales management system.

7. The intelligent supply chain accounts payable management method based on multi-dimensional dynamic evaluation according to claim 2, characterized in that, The product risk level model is used to output low, medium, and high risk levels based on input data such as product category, warranty period, and historical after-sales rate.

8. The intelligent supply chain accounts payable management method based on multi-dimensional dynamic evaluation according to claim 3, characterized in that, Determining the feedback index corresponding to the target user includes: A third training set is determined, which includes user review texts and corresponding product after-sales rate, after-sales rate, and fault reporting rate. The user review texts are collected from the enterprise's e-commerce platform or after-sales feedback system.

9. The intelligent supply chain accounts payable management method based on multi-dimensional dynamic evaluation according to claim 8, characterized in that, The user feedback index model is used to output a feedback index of 0-10 based on the input user data.

10. A supply chain accounts payable intelligent management system based on multi-dimensional dynamic evaluation, characterized in that, The system is configured as follows: The system acquires supplier data, product data, user data, and financial data through a data acquisition terminal. The supplier data includes performance record data, credit rating data, and historical payment period execution data. The product data includes category data, warranty period data, cost price data, and risk level data. The financial data includes budget amount data, cash flow forecast data, and cost of capital rate data. Construct a supplier reputation scoring model, input the supplier data corresponding to the target supplier into the supplier reputation scoring model, and obtain the real-time reputation score corresponding to the target supplier based on the output of the supplier reputation scoring model; The supply chain risk level is determined based on the real-time credit score.

Images