Purchase plan generation method and device and electronic equipment

Abstract

The embodiment of the invention relates to the technical field of artificial intelligence, and discloses a purchase plan generation method and device and electronic equipment. The method comprises the following steps: extracting a relationship among parameters in product sales associated data and a dependency relationship of the parameters on time to form product sales characteristics, and predicting and generating a purchase demand according to the product sales characteristics; the product sales associated data comprises historical sales data, market trends, seasonal change data, sales promotion activities and macroeconomic conditions; clustering the plurality of suppliers according to the supplier associated data, and extracting relevance among parameters in the supplier associated data; evaluating each supplier according to the clustering result and the relevance extraction result to obtain a supplier sorting result; the purchase plan is generated according to the purchase demand, the supplier sorting result, the inventory monitoring result and the production plan, the demand is predicted intelligently, the prediction accuracy is improved, and the optimal partner can be selected through comprehensive evaluation of suppliers, so that the generation reasonability of the purchase plan is improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, can be applied to the field of financial technology, and in particular to a procurement plan generation method, device and electronic equipment. Background Art

[0002] In product production, it is usually necessary to purchase a variety of raw materials to produce the product. In order to reasonably plan the purchase of the product, it is usually necessary to manage the purchase.

[0003] In the prior art, inventory statistics, supplier research, and procurement plans are usually generated through manual operations. However, the manual operation method has the problem that information transmission and data analysis are not real-time and accurate enough, resulting in poor timeliness and accuracy of procurement plans. Summary of the invention

[0004] The present invention provides a method, device and electronic device for generating a procurement plan, which can intelligently predict demand and comprehensively evaluate suppliers to improve the rationality of generating a procurement plan.

[0005] According to one aspect of the present invention, a method for generating a procurement plan is provided, the method comprising:

[0006] Extracting the relationship between parameters in the product sales related data and the dependency of the parameters on time to form product sales features, and predicting and generating procurement demand based on the product sales features;

[0007] The product sales-related data include: historical sales data, market trends, seasonal change data, promotional activities and macroeconomic conditions;

[0008] Clustering multiple suppliers according to supplier association data and extracting the correlation between parameters in the supplier association data; wherein the supplier association data includes: supplier qualification review results, credibility score, contract performance capability, supplier image data, product quality and price fluctuation;

[0009] Evaluate each supplier based on the clustering results and correlation extraction results to obtain the supplier ranking results;

[0010] A procurement plan is generated according to the procurement demand, the supplier ranking result, the inventory monitoring result, and the production plan.

[0011] According to another aspect of the present invention, there is provided a procurement plan generating device, the device comprising:

[0012] A purchasing demand generation module is used to extract the relationship between parameters in the product sales related data and the dependency of the parameters on time to form product sales characteristics, and to predict and generate purchasing demand based on the product sales characteristics;

[0013] The product sales-related data include: historical sales data, market trends, seasonal change data, promotional activities and macroeconomic conditions;

[0014] A supplier data processing module is used to cluster multiple suppliers according to supplier association data and extract the correlation between parameters in the supplier association data; wherein the supplier association data includes: supplier qualification review results, reputation score, contract performance ability, supplier image data, product quality and price fluctuation;

[0015] The supplier evaluation module is used to evaluate each supplier based on the clustering results and correlation extraction results to obtain the supplier ranking results;

[0016] The procurement plan generation module is used to generate a procurement plan based on the procurement demand, the supplier ranking result, the inventory monitoring result, and the production plan.

[0017] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0018] at least one processor; and

[0019] a memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the procurement plan generating method described in any embodiment of the present invention.

[0021] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the procurement plan generation method described in any embodiment of the present invention when executed.

[0022] According to another aspect of the present invention, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the method for generating a procurement plan according to any embodiment of the present invention is implemented.

[0023] The technical solution of the embodiment of the present invention forms product sales characteristics by extracting the relationship between parameters in product sales related data and the dependence of parameters on time, and generates procurement demand based on the product sales characteristics; wherein the product sales related data includes: historical sales data, market trends, seasonal change data, promotional activities and macroeconomic conditions; multiple suppliers are clustered according to supplier related data, and the correlation between parameters in the supplier related data is extracted; wherein the supplier related data includes: supplier qualification review results, credibility scores, performance capabilities, supplier image data, product quality and price fluctuations; each supplier is evaluated according to the clustering results and the correlation extraction results to obtain supplier ranking results; a procurement plan is generated according to the procurement demand, the supplier ranking results, the inventory monitoring results, and the production plan, which solves the demand analysis and supplier evaluation problems in the generation of procurement plans, and can improve the accuracy of demand prediction by intelligently predicting demand, and can select the best partner by comprehensively evaluating suppliers, thereby improving the rationality of procurement plan generation.

[0024] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0026] Figure 1 is a flowchart of a method for generating a procurement plan according to an embodiment of the present invention;

[0027] Figure 2 is a structural schematic diagram of a procurement plan generating device provided according to an embodiment of the present invention;

[0028] Figure 3 is a structural diagram of a procurement plan generation system provided according to an embodiment of the present invention;

[0029] Figure 4 It is a structural schematic diagram of an electronic device for implementing the procurement plan generating method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention 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 interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] Figure 1 This is a flowchart of a method for generating a procurement plan according to an embodiment of the present invention. This embodiment is applicable to the situation where the required materials are purchased during product production. The method can be executed by a procurement plan generating device. The procurement plan generating device can be implemented in the form of hardware and / or software. The procurement plan generating device can be configured in an electronic device. The electronic device can be a mobile device such as a mobile phone, a tablet computer (PAD), a wearable device, or a personal computer (PC). Figure 1 As shown, the method includes:

[0033] Step 110: extract the relationship between parameters in the product sales related data and the dependency of the parameters on time to form product sales characteristics, and generate procurement demand based on the product sales characteristics.

[0034] Among them, product sales related data include: historical sales data, market trends, seasonal change data, promotional activities and macroeconomic conditions. The acquired product sales related data can be integrated and cleaned. The relationship between parameters in the product sales related data can be extracted by establishing a relationship model between parameter variables through regression analysis to predict the impact of specific factors on demand.

[0035] Extracting the time dependency of parameters in product sales-related data can be based on machine learning algorithms or big data analysis technology, learning the rules of historical product sales-related data, analyzing internal and external factors, accurately predicting material and service requirements, and automatically generating and optimizing procurement demand plans. For example, identifying and predicting the time-dependent demand changes of product sales-related data through time series analysis. Processing time series data through the AutoRegressive Integrated Moving Average Model (ARIMA) to predict future values. Processing long-term dependencies through deep learning such as the Long Short-Term Memory (LSTM) network to predict time series data.

[0036] For the information extracted by the multi-network model, product sales features can be formed through feature fusion. There are many ways to fuse features, such as linear weighting, dynamic weight adjustment, and stacking.

[0037] Specifically, the output of each network model can be multiplied by the corresponding weight, and then summed to obtain the feature fusion result. When generating purchase demand through product sales feature prediction, the weight of each network model can be dynamically adjusted according to real-time information. Real-time information includes but is not limited to user feedback or performance evaluation results of purchase demand prediction. Alternatively, the output results of multiple network models are used as input to train a new model and fuse these output results.

[0038] Model training based on the integrated product sales characteristics and prediction of purchasing demand can improve the accuracy and robustness of the prediction. During model training, the accuracy and generalization ability of the model can be evaluated through the validation set and test set, and the model parameters can be adjusted based on the evaluation results. By using the model prediction results to generate a purchasing demand plan, automated and intelligent purchasing decisions can be achieved.

[0039] The multi-algorithm fusion method can fully utilize the advantages of different models and improve the overall forecasting performance. Through technologies such as linear weighting, dynamic weight adjustment and stacking, the model weights can be dynamically adjusted according to real-time data and feedback to achieve more accurate forecasts. In addition, the use of deep learning models such as LSTM can process complex time series data, capture long-term dependencies, and further improve the accuracy of forecasts. This fusion strategy not only improves the accuracy of forecasts, but also enhances adaptability and flexibility, enabling it to better cope with market changes and uncertainties. By integrating multiple sets of intelligent algorithms, clear and controllable procurement plans for multiple formats and multiple sectors can be achieved.

[0040] Step 120: Cluster multiple suppliers according to the supplier association data, and extract the correlation between parameters in the supplier association data.

[0041] Among them, the supplier-related data includes: supplier qualification review results, reputation score, performance capability, supplier image data, product quality and price fluctuations. The supplier qualification review results can be obtained by checking the supplier's business license, production license, quality certification and other documents to ensure that the supplier meets industry standards and regulatory requirements. For example, the supplier qualification review results are obtained by checking each document through an artificial intelligence algorithm. The reputation score can be calculated by analyzing the supplier's historical transaction records, customer feedback, industry evaluation, etc. For example, the reputation score can be obtained by performing data analysis through a machine learning model. The performance capability can be the result obtained by analyzing the supplier's delivery punctuality rate, contract performance and other data to evaluate its performance capability. The supplier image data can be the data obtained by performing sentiment analysis on user reviews and social media feedback to quantify the supplier's public image and customer satisfaction. For example, the supplier image data is quantified through natural language processing technology. Product quality and price fluctuations can be obtained by collecting and summarizing supplier data.

[0042] Clustering multiple suppliers based on supplier association data can be to cluster suppliers based on characteristics such as price, quality, and delivery time, and identify the characteristics and differences of supplier groups to enable more targeted evaluation and management.

[0043] Extracting correlations between parameters in supplier association data can be to discover correlations between supplier characteristics, for example, the correlation between price and quality, or the relationship between delivery time and customer satisfaction.

[0044] Step 130: Evaluate each supplier based on the clustering results and the correlation extraction results to obtain a supplier ranking result.

[0045] Supplier evaluation can be achieved by simulating the results of different supplier selection strategies and using reinforcement learning algorithms to continuously optimize the supplier selection process, thereby obtaining supplier ranking results. Through continuous iterative learning, the best suppliers can be matched more accurately. By combining multiple dimensions such as the supplier's financial data, operational data, and customer feedback, a comprehensive quantitative evaluation model can be built to conduct multi-dimensional quantitative evaluation of suppliers. Applying sentiment analysis to supplier evaluation can enhance the comprehensiveness of supplier evaluation by using unstructured data (such as customer reviews). Using reinforcement learning algorithms, supplier selection strategies can be dynamically adjusted based on market feedback and supplier performance to improve the adaptability and accuracy of decision-making. Self-adjustment based on evaluation results and market changes can achieve continuous optimization and improvement.

[0046] Step 140: Generate a procurement plan based on procurement requirements, supplier ranking results, inventory monitoring results, and production plan.

[0047] When generating a procurement plan, procurement needs, supplier ranking results, inventory monitoring results, and production plans can be comprehensively considered in an intelligent way to form a procurement plan and budget plan that meets constraints and has the lowest cost or maximizes value, ensuring that the procurement plan is both reasonable and cost-effective.

[0048] Among them, intelligent methods may include but are not limited to: linear programming, integer programming, genetic algorithms or mixed integer programming and other operations research methods, as well as deep reinforcement learning. The inventory monitoring result can be real-time monitoring of inventory levels, and the replenishment point and replenishment quantity can be determined through inventory management algorithms. When generating a procurement plan, cost-effectiveness can be considered. For example, combining procurement costs, transportation costs, storage costs, etc., and using linear programming, integer programming and other operations research methods for cost-effectiveness analysis. The constraints in the procurement plan can be to consider production plans, supplier delivery time, inventory capacity and other constraints to form a preliminary plan for the procurement plan. Based on the preliminary plan, genetic algorithms, simulated annealing, deep reinforcement learning and other technologies can be used for optimization to meet the goal of minimum cost or maximum value. Then, the optimized procurement plan can be evaluated and adjusted according to actual operating conditions and market changes.

[0049] For example, the procurement requirements, supplier ranking results, inventory monitoring results, and production plans can be integrated and cleaned. The cost-effectiveness is analyzed through linear programming to determine the procurement plan with the lowest cost. Discrete variables in the procurement plan, such as the order quantity, are processed through integer programming. The genetic mechanism in the natural selection process can be simulated by genetic algorithms to optimize the procurement plan. The optimal solution is avoided by simulated annealing to find the global optimal solution. In each model, the features that affect the procurement plan can be extracted, and the most relevant features are selected for the subsequent fusion process. For example, the final result is determined based on the prediction results of different models through a voting mechanism. In order to improve the accuracy of model prediction, different model weights can also be given to calculate the weighted average. Alternatively, the prediction results of multiple base models are used as inputs of the new model through Stacking, and these prediction results are fused by training a meta-model. In the stacking method, a meta-learner is trained with the outputs of each base learner as input, and learns to best combine these outputs to improve the overall performance. The performance of the fused model is evaluated, and the generalization ability of the model is ensured by using methods such as cross-validation. According to the evaluation results, the model is adjusted and continuously optimized through a feedback mechanism.

[0050] By combining multiple algorithms such as linear programming, integer programming, genetic algorithms, simulated annealing, etc., a unique optimization strategy is formed. Use deep reinforcement learning to dynamically optimize the procurement plan to improve the adaptability and flexibility of the plan. Improve the timeliness and accuracy of the procurement plan through real-time data-driven decision-making. Be able to fully utilize the advantages of different algorithms to improve the optimization effect of the procurement plan. Adaptively adjust algorithm parameters and fusion strategies based on real-time data and feedback. Real-time optimization of procurement plans is achieved by real-time monitoring of market and inventory status.

[0051] The technical solution of this embodiment forms product sales characteristics by extracting the relationship between parameters in product sales related data and the dependence of parameters on time, and generates procurement demand based on product sales characteristics prediction; wherein, product sales related data include: historical sales data, market trends, seasonal change data, promotional activities and macroeconomic conditions; multiple suppliers are clustered according to supplier related data, and the correlation between parameters in supplier related data is extracted; wherein, supplier related data include: supplier qualification review results, credibility score, performance ability, supplier image data, product quality and price fluctuation; each supplier is evaluated according to the clustering results and the correlation extraction results to obtain the supplier ranking results; a procurement plan is generated according to procurement demand, supplier ranking results, inventory monitoring results, and production plan, which solves the problems of demand analysis and supplier evaluation in procurement plan generation, and can improve the accuracy of demand prediction by intelligently predicting demand, and can select the best partner by comprehensively evaluating suppliers, thereby improving the rationality of procurement plan generation.

[0052] On the basis of the above implementation mode, optionally, after generating the procurement plan, it also includes: determining the comprehensive score of each supplier's quotation based on the supplier's quotation data and a preset quotation parameter weight model; wherein the supplier's quotation data includes: material price, quality, delivery time, freight and after-sales service; determining a reasonable price range based on market price trends, supplier's historical transaction records, cost structure and industry benchmark data; conducting price negotiations on the quotations of each supplier based on the comprehensive score of the supplier's quotation and the reasonable price range to obtain price negotiation results.

[0053] Among them, the supplier's quotation data can be cleaned to remove invalid or erroneous data, process missing values, and ensure data quality. The key features of the pre-processed data can be extracted, and then data mining and multi-attribute decision analysis (MADM) can be used to decompose and standardize the cost components of the supplier's quotation.

[0054] The preset quotation parameter weight model can be a weight model established for the quotation data of suppliers such as price, quality, delivery time, after-sales service, etc. through expert scoring, historical data analysis or machine learning algorithms. Based on the preset quotation parameter weight model and the quotation data of suppliers, the comprehensive score of each supplier's quotation can be determined by a decision algorithm. Among them, the decision algorithm includes but is not limited to: Technique for Order Preference by Similarity to Ideal Solution (TOPSIS), Analytic Hierarchy Process (AHP), fuzzy logic, and gray system theory. TOPSIS can evaluate the comprehensive score of each supplier by calculating the distance between the ideal solution and the negative ideal solution. AHP can calculate the relative importance of each factor through a pairwise comparison matrix to obtain the comprehensive score of each supplier. Fuzzy logic and gray system theory can be used to deal with uncertainty and ambiguity. According to the weight model and decision algorithm, the comprehensive score of each quotation is calculated. Select the procurement plan with the highest cost performance and update the best quotation in real time. Verify the selected plan and collect feedback information for further optimization and adjustment of the model.

[0055] In the embodiment of the present invention, after determining the comprehensive score of the supplier's quotation, a reasonable price range can also be determined for the material, so as to conduct price negotiations on the supplier's quotation based on the reasonable price range and the comprehensive score of the supplier's quotation.

[0056] Among them, determining a reasonable price range can be to collect all cost data related to the product or service, analyze the cost structure, measure the impact of changes in various factors on the completion of the cost plan, calculate the cost profit margin, understand the market conditions and competitors' pricing strategies, and help purchasing personnel determine a reasonable negotiation starting point and target price.

[0057] Specifically, cost data includes direct costs (such as raw materials, labor costs) and indirect costs (such as management expenses, equipment depreciation). Costs can be divided into fixed costs and variable costs to more accurately analyze the cost structure. Using factor analysis, the various factors that constitute the cost are decomposed, and the degree of influence of changes in each factor on the completion of the cost plan is determined. Based on this, the implementation of the enterprise's cost plan is evaluated and further improvement measures are proposed. Calculate the cost profit margin, that is, the ratio of profit to cost, to determine the minimum profit margin required after covering the cost. Study the prices of similar products or services in the market to understand the market situation and the pricing strategies of competitors. Set a reasonable price range based on the results of cost analysis and market price research. The lowest price can cover all costs and guarantee the lowest profit, while the highest price takes into account market acceptance and competition. Conduct sensitivity analysis to evaluate the impact of cost changes on the price range to ensure the robustness of the price strategy. According to market feedback and cost changes, dynamically adjust the price range to adapt to market changes. Based on the price range, formulate negotiation strategies, including starting quotes, concession strategies and final acceptable prices. Use game theory models to simulate the negotiation process, predict the supplier's possible response, and optimize the negotiation strategy accordingly. After the negotiation, evaluate the negotiation results and collect data for further optimization of the model. Through the above steps, the intelligent price negotiation consultant can provide negotiators with data-supported strategic suggestions, help determine a reasonable price range in the negotiation, and improve the success rate and efficiency of the negotiation.

[0058] Among them, the specific process of game theory model negotiation simulation can be: according to the specific situation of the negotiation, choose an appropriate game theory model. For example, if the negotiation is a one-time one, you can choose a static game model; if it is multiple times, you can choose a dynamic game model. Identify the participants in the game, including the purchaser and the supplier. Set possible strategies for each participant. For example, the supplier's possible strategies include offering different prices or discounts, while the purchaser's strategy may include accepting, rejecting or making a counter-offer. Construct a payoff function for each participant to reflect the benefits under different strategy combinations. This may include factors such as price, cost, and profit. Use concepts such as Nash equilibrium to analyze the game and find the optimal strategy combination. Nash equilibrium refers to a strategy combination in which no participant can obtain higher benefits by unilaterally changing the strategy given the strategies of other participants. Predict the possible response of the supplier by simulating different negotiation scenarios. This can be achieved through machine learning algorithms, using historical data to train the model and improve the accuracy of predictions. Based on the simulation results and equilibrium analysis, optimize the purchaser's negotiation strategy to achieve the best negotiation results. During the negotiation process, dynamically adjust the strategy based on the feedback from the supplier and market changes. After the negotiation, evaluate the negotiation results and collect data for further optimization of the model.

[0059] Game theory models can simulate complex negotiation environments, predict suppliers’ responses, and provide data-supported strategic recommendations to buyers, thereby increasing the success rate and efficiency of negotiations. Through game theory models, intelligent price negotiation consultants can assist decision makers in developing optimal negotiation strategies and provide real-time data support and feedback during the negotiation process, thereby improving negotiation effectiveness and efficiency.

[0060] After obtaining the price negotiation results, the following steps may be optional: obtaining the contract document and extracting the contract text information in the contract document; constructing a legal requirement knowledge graph based on legal clauses, cases and regulations; comparing the contract text information with the legal requirement knowledge graph to determine the compliance of the contract document; when the contract document is compliant, filling the contract document with data based on the procurement plan and the price negotiation results to obtain the target contract document.

[0061] Users can upload contract documents through the interface. Contract documents support multiple formats such as PDF, Word, etc. For contract documents, optical character recognition (OCR) technology can be used to extract text to obtain contract text information, and language model processing can be performed to identify and correct grammatical errors. For contract text information, the natural language processing (NLP) model can be used to parse the contract text, identify key entities (such as date, amount, parties) and terms; and the deep learning model can be used to understand the intent and context of the contract terms.

[0062] By building a structured knowledge graph of legal terms, cases, regulations, and other information, we can compare the contract terms with the legal requirements in the knowledge graph to identify compliance issues. We can automatically check whether the contract terms comply with relevant laws and regulations. We can use the risk point library to identify potential risks in the contract.

[0063] Select the appropriate contract template from the template library based on the contract type. Automatically fill in the corresponding fields in the template based on the results of NLP analysis. Generate text that meets the contract requirements using semantic generation technology. Show the contract review results to the user, including compliance issues and risk warnings. Allow users to review and modify the automatically generated contract text. Generate the final contract text based on user feedback and review results. Continuously optimize the NLP model and knowledge graph based on user feedback and new legal changes. Archive the generated contract text for future retrieval and auditing. Provide contract management functions to track contract status and remind key dates and terms. Automatically review contract terms through natural language processing technology to prevent legal risks, and be able to automatically generate contract text based on preset templates and negotiation results.

[0064] After generating the procurement plan, the following options are optionally included: determining the priority of the procurement plan according to the order urgency, user importance, material quantity, product type and delivery deadline in each procurement plan; scheduling each procurement plan according to the priority, and adjusting the priority in real time according to the delivery deadline during the scheduling process.

[0065] First, conduct a detailed analysis of order demand, including order urgency, quantity, product type, delivery deadline, etc. At the same time, monitor and accurately evaluate the current status of all resources in real time, including the current load of the production line, inventory level, availability of logistics channels, etc. Based on the results of demand analysis and resource status evaluation, select or design appropriate scheduling algorithms and strategies. For example, for urgent orders, it is necessary to select a priority scheduling algorithm; for complex orders that need to consider multiple factors, it is necessary to use a genetic algorithm or simulated annealing algorithm. For the selected algorithm, set initial parameters such as population size, crossover rate, mutation rate (genetic algorithm), or initial temperature, cooling rate (simulated annealing algorithm). Before actual deployment, use historical data or simulation environment to test the selected strategy, evaluate its performance, and adjust and optimize it when necessary. According to the real-time monitored resource status and order demand changes, dynamically adjust the scheduling strategy to ensure the efficiency and flexibility of order execution. Use workflow engine and rule engine to build an automated approval process, and combine fuzzy logic, neural network and other technologies to predict order priority, and intelligently schedule the order execution sequence according to factors such as inventory level, production capacity, and logistics conditions.

[0066] The specific steps of the priority scheduling algorithm may be: when a new order arrives, a priority is assigned to each order according to a preset rule or algorithm. These rules may include factors such as the urgency of the order, the importance of the customer, the size of the order, and the profit margin. Orders may be placed in different queues according to their priority. High-priority orders are placed in front for priority processing. Priority scheduling may be preemptive or non-preemptive. In preemptive scheduling, if a high-priority order arrives, even if a low-priority order is currently being processed, the processing of the low-priority order may be suspended and the high-priority order may be processed instead. In non-preemptive scheduling, once an order is processed, it is processed to completion, even if a higher-priority order arrives. Orders are executed in order of priority. High-priority orders are processed first, followed by the next-highest-priority orders, and so on. In some cases, the priority of an order may need to be adjusted dynamically. For example, if an order is about to be delivered, its priority may be increased. To avoid the priority inversion problem, some strategies such as priority inheritance or priority ceiling may be implemented to ensure that low-priority tasks are not left unprocessed for a long time due to preemption of high-priority tasks.

[0067] The implementation steps of the genetic algorithm can be: convert the order scheduling problem into a coding form that the genetic algorithm can handle, such as a chromosome string. Randomly generate a certain number of chromosomes to form the initial population. Define the fitness function to evaluate the pros and cons of each chromosome (scheduling plan), which can be based on indicators such as order completion time and resource utilization. According to the fitness function, select the better chromosomes for reproduction, and methods such as roulette selection and tournament selection can be used. Perform a crossover operation on the selected chromosomes to generate new chromosomes to simulate gene recombination in biological genetics. Perform a mutation operation on the chromosomes to randomly change some genes of the chromosomes with a certain probability to increase the diversity of the population. The new chromosomes generated by crossover and mutation constitute a new generation of population. Check whether the algorithm meets the termination conditions, such as reaching the maximum number of iterations or the fitness of the population is no longer significantly improved. Extract the optimal chromosome from the final population and decode it to obtain the optimal scheduling plan.

[0068] The specific steps of the simulated annealing algorithm can be: set the initial solution and initial temperature, and the initial solution can be a randomly generated scheduling plan. Define the objective function to evaluate the quality of the scheduling plan, which is usually similar to the fitness function in the genetic algorithm. Generate a neighborhood solution through random perturbations based on the current solution. According to the acceptance criteria of simulated annealing, decide whether to accept the neighborhood solution. If the neighborhood solution is better, accept it; if it is not better, accept it with a certain probability, and the probability is related to the temperature and the quality difference of the solution. Reduce the temperature according to a predetermined annealing strategy, such as linear cooling or geometric cooling. Repeat the neighborhood solution generation, acceptance criteria and temperature decay steps until the termination condition is met. After the algorithm ends, extract the current optimal solution as the scheduling plan. According to the algorithm performance, adjust parameters such as initial temperature and cooling rate to optimize the algorithm effect.

[0069] After generating the procurement plan, it may optionally include: obtaining cargo logistics data related to the procurement plan, and predicting the order delivery time based on the cargo logistics data; and issuing a procurement delay alarm when it is determined that there is a risk of delay based on the order delivery time and the delivery period in the procurement plan.

[0070] Specifically, enter new order information into the system. Assign a unique identifier to each order and initialize monitoring parameters. Deploy Internet of Things (IoT) devices on cargo transportation vehicles. Collect order-related logistics data in real time. Transmit data collected by IoT devices through wireless networks to the data center. Store the received data in the database for further analysis. Clean the real-time data to remove noise and errors. Convert the raw data into the format required by the analysis model. Update the order status based on the real-time data. Use anomaly detection algorithms to identify anomalies in order execution. Select a suitable prediction model based on the characteristics of the order. Apply prediction models, such as time series prediction tools (Prophet) or recursive algorithms (Kalman) filtering, to predict the delivery time of the order. Evaluate the prediction results to determine whether there is a risk of delay. Automatically trigger an alert when a risk is detected. Generate an alert notification, including the alert level, reason, and recommended measures. Send alerts through preset channels (such as SMS, email, in-app notifications). Display real-time tracking information of the order in the user interface. Display alert information and allow users to view details and history. Allow users to confirm or object to the alert information. Adjust the alert parameters and prediction model based on user feedback. Automatically generate order execution reports, including forecast results, early warning records, etc. Provide data analysis tools to help users deeply understand order execution status.

[0071] After generating a purchase plan, the following may be optional: capturing material images, identifying the material images, and obtaining material identification results; scanning barcodes on the materials, and obtaining material scanning results; comparing the material identification results with the material scanning results; and when the comparison passes, updating the inventory information according to the inventory monitoring results and the material identification results.

[0072] Specifically, collect image data of various materials to ensure data diversity and representativeness. Manually annotate images to clarify material categories and features. Select a suitable Convolutional Neural Network (CNN) architecture, such as Residual Network (ResNet), as the basic model. Use the annotated data set to train the CNN model and optimize the model parameters through back propagation and gradient descent. Evaluate model performance through the validation set and adjust the model structure and parameters to improve accuracy. Select a suitable camera according to material characteristics, such as high resolution and high frame rate. Deploy cameras in the warehousing area to ensure that all material warehousing paths are covered. Calibrate the camera to ensure that the image is clear and accurate. Collect material images in real time through the camera. Perform preprocessing operations such as denoising, enhancement, and normalization on the image. Use the pretrained CNN model to extract image features. Input the preprocessed image into the CNN model for material identification. Use a barcode scanner to read the material barcode and compare it with the CNN recognition result. Perform secondary verification based on the physical characteristics of the material (such as shape, color, and size). Develop an interface with the Enterprise Resource Planning (ERP) system to achieve two-way data transmission. Ensure that the inventory information in the ERP system can reflect the inventory status of materials in real time. Design an exception handling process to provide a way for manual intervention for materials that are misidentified or unidentified. Develop a user interface to display material identification results and inventory update information. Provide operation instructions and error prompts to facilitate user material management and system maintenance. Collect user feedback and continuously optimize the user interface and interactive experience.

[0073] After obtaining the target contract document, the following may be optional: determining automatic payment rules and payment conditions based on the payment information in the target contract document and the user's financial policy; making payments according to the automatic payment rules when the payment conditions are met, and generating payment records; obtaining invoice information corresponding to the payment records, verifying the invoice information, and generating invoice verification results; and displaying the payment records and the corresponding invoice verification results.

[0074] Specifically, capture invoice images through a scanner or mobile device camera. Use OCR technology to extract key information on the invoice, such as invoice number, amount, date, etc. Compare the information extracted by OCR with tax-related databases to ensure the authenticity of the invoice. Use Robotic Process Automation (RPA) technology to automate the invoice verification and payment process to reduce manual operations. Set rules and conditions for automatic payment based on corporate financial policies and contract terms. Develop a rule engine to automatically determine whether payment conditions are met based on contract agreements and corporate financial policies. When payment conditions are met, the system automatically triggers the payment process to complete the payment. Integrate the intelligent invoice verification and automatic payment system with the company's existing ERP system to achieve data synchronization. Ensure the security of the system when processing financial data, including data encryption and access control. Design an intuitive user interface to display the invoice verification status and payment records. Allow users to operate on the interface, such as manual review, adjustment of payment rules, etc. The system can identify and report abnormal situations, such as OCR recognition errors, payment failures, etc. Establish a monitoring mechanism to monitor the system operation status in real time to ensure the stability of the process.

[0075] On the basis of the above implementation mode, it is optional to further include: obtaining real-time procurement data in procurement, and evaluating procurement performance indicators based on the real-time procurement data; and issuing procurement risk warnings when there are risks in the procurement evaluation results.

[0076] Specifically, collect procurement-related data from sources such as ERP systems, supply chain management systems, and market databases. Clean the data to remove errors and incomplete records. Format the data to ensure consistency. Extract features from the raw data for model training. Apply data mining techniques such as cluster analysis and association rule learning to identify procurement patterns and associations. For example, use K-means or density-based spatial clustering of applications with noise (DBSCAN) to perform cluster analysis, calculate the distance between each data point and the cluster center, and set a threshold to identify abnormal data points. Build a supply chain network model to analyze the importance of nodes and risk propagation. Use core normalized closeness (Cnc), total sum of squares around the mean (TSM), average distance to decentralized distribution (ADD), iterative K-means with swap (IKS), etc. to evaluate the importance of nodes. Use random forest models to evaluate feature importance and predict procurement performance and risks. The accuracy and robustness of predictions can be improved through integrated learning of random forest models. Integrate the results of data mining, complex network analysis, and random forest models to form a comprehensive evaluation. Deploy a real-time monitoring system to continuously monitor procurement activities. Set a risk threshold, and trigger an early warning when the risk predicted by the model exceeds the threshold. Display key performance indicators (KPIs) and risk warning information through visualization tools and generate reports. Develop a user interface that allows users to view and analyze performance evaluations and risk warnings. Integrate the intelligent system with an existing ERP or supply chain management system. Through these steps, the intelligent procurement performance evaluation and risk warning system can achieve comprehensive monitoring of procurement activities, timely detect and warn of potential risks, thereby improving procurement efficiency and reducing supply chain risks. At the same time, seamless docking with the ERP system ensures real-time updating of inventory information, further improving the level of intelligence in supply chain management.

[0077] The technical solution of the embodiment of the present invention can reduce inventory costs and improve asset turnover through efficient demand forecasting; can monitor supplier performance in real time through accurate supplier selection, and intelligently recommend partners; and can significantly reduce cost waste caused by imbalance between supply and demand through demand forecasting and supplier selection. By providing comprehensive price comparison analysis and procurement plan optimization suggestions, it helps management to make more scientific and reasonable procurement decisions. By automating the procurement process, the time cost of manual operation is greatly reduced and work efficiency is improved. By real-time monitoring of order execution and supplier performance, potential problems are warned in time, reducing the risk of supply chain disruption. By intelligently scheduling order execution and material warehousing, the efficient allocation and use of internal resources of the enterprise are ensured. The whole process from procurement plan formulation to invoice settlement is embedded with an intelligent decision-making mechanism to achieve seamless connection and optimized execution. By using intelligent data mining and pattern recognition capabilities, various risk factors that may exist in the procurement process are actively discovered and warned. The above-mentioned methods significantly improve the efficiency of the procurement process, reduce operating costs, and help enterprises to achieve more scientific, reasonable and efficient procurement plan generation, thereby improving the overall supply chain management level and enterprise competitiveness. Procurement plan generation based on artificial intelligence can effectively improve the quality and efficiency of procurement plan generation in multiple links, strongly promote enterprises to gain advantages in supply chain competition, and has extremely high commercial value and social benefits.

[0078] Figure 2 Schematic diagram of a purchasing plan generating device provided according to an embodiment of the present invention. Figure 2 As shown, the device includes: a procurement demand generation module 210, a supplier data processing module 220, a supplier evaluation module 230 and a procurement plan generation module 240. Among them:

[0079] The purchasing demand generation module 210 is used to extract the relationship between parameters in the product sales related data and the dependency of the parameters on time, form product sales characteristics, and generate purchasing demand based on the product sales characteristics;

[0080] Among them, product sales related data include: historical sales data, market trends, seasonal change data, promotional activities and macroeconomic conditions;

[0081] The supplier data processing module 220 is used to cluster multiple suppliers according to the supplier association data and extract the correlation between parameters in the supplier association data; wherein the supplier association data includes: supplier qualification review results, reputation score, contract performance ability, supplier image data, product quality and price fluctuation;

[0082] The supplier evaluation module 230 is used to evaluate each supplier according to the clustering results and the correlation extraction results to obtain a supplier ranking result;

[0083] The procurement plan generation module 240 is used to generate a procurement plan according to procurement requirements, supplier ranking results, inventory monitoring results, and production plans.

[0084] Optionally, the device further includes:

[0085] The supplier quotation module is used to determine the comprehensive score of each supplier's quotation based on the supplier's quotation data and the preset quotation parameter weight model after generating the procurement plan; the supplier's quotation data includes: material price, quality, delivery time, freight and after-sales service;

[0086] Reasonable price range determination module, used to determine the reasonable price range based on market price trends, supplier historical transaction records, cost structure and industry benchmark data;

[0087] The price negotiation result determination module is used to negotiate prices for the quotations of various suppliers based on the comprehensive scores of the quotations of the suppliers and the reasonable price range, and obtain the price negotiation results.

[0088] Optionally, the device further includes:

[0089] The contract text information determination module is used to obtain the contract document and extract the contract text information in the contract document after obtaining the price negotiation result;

[0090] The knowledge graph construction module is used to construct a knowledge graph of legal requirements based on legal clauses, cases, and regulations;

[0091] The contract compliance determination module is used to compare the contract text information with the legal requirements knowledge graph to determine the compliance of the contract document;

[0092] The target contract document determination module is used to fill the contract document with data according to the procurement plan and price negotiation results when the contract document is compliant to obtain the target contract document.

[0093] Optionally, the device further includes:

[0094] A procurement plan priority determination module is used to determine the priority of procurement plans after generating procurement plans according to order urgency, user importance, material quantity, product type and delivery deadline in each procurement plan;

[0095] The priority adjustment module is used to schedule each procurement plan according to priority, and during the scheduling process, adjust the priority in real time according to the delivery deadline.

[0096] Optionally, the device further includes:

[0097] The order delivery time prediction module is used to obtain the cargo logistics data related to the procurement plan after the procurement plan is generated, and predict the order delivery time based on the cargo logistics data;

[0098] The procurement delay alarm module is used to issue a procurement delay alarm when it is determined that there is a risk of delay based on the order delivery time and the delivery period in the procurement plan.

[0099] Optionally, the device further includes:

[0100] The material identification module is used to collect material images and identify the material images after generating the procurement plan to obtain material identification results;

[0101] The result comparison module is used to scan the barcode on the material to obtain the material scanning result; the material identification result is compared with the material scanning result;

[0102] The inventory information update module is used to update the inventory information according to the inventory monitoring results and material identification results when the comparison is passed.

[0103] Optionally, the device further includes:

[0104] The automatic payment formulation module is used to determine the automatic payment rules and payment conditions according to the payment information in the target contract file and the user's financial policy after obtaining the target contract file;

[0105] A payment record generation module is used to make payment according to automatic payment rules and generate payment records when payment conditions are met;

[0106] An invoice verification result generation module is used to obtain invoice information corresponding to the payment record, verify the invoice information, and generate an invoice verification result;

[0107] The display module is used to display the payment records and the corresponding invoice verification results.

[0108] Optionally, the device further includes:

[0109] The procurement performance indicator evaluation module is used to obtain real-time procurement data in procurement and evaluate procurement performance indicators based on the real-time procurement data;

[0110] The procurement risk warning module is used to issue procurement risk warnings when there are risks in the procurement evaluation results.

[0111] The procurement plan generation device provided in the embodiment of the present invention can execute the procurement plan generation method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0112] Figure 3Schematic diagram of a procurement plan generation system provided according to an embodiment of the present invention. Figure 3 As shown, the procurement plan generation system may include: demand forecasting engine, supplier selector, procurement plan selector, price inquiry and comparison analyzer, price negotiation consultant, contract review and generation tool, order execution monitor, material identification and warehousing tool, invoice verification and automatic payment tool, and procurement performance evaluation tool. Figure 3 The procurement plan generation system shown can implement the procurement plan generation method in the embodiment of the present invention and has the same beneficial effects.

[0113] In the technical solution of the embodiment of the present invention, the collection, storage, use, processing, transmission, provision and disclosure of the procurement information involved (such as product sales related data, supplier related data, inventory monitoring results, and production plans, etc.) all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0114] The information collected is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of relevant countries and regions, take necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0115] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0116] like Figure 4As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0117] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0118] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a procurement plan generation method.

[0119] In some embodiments, the procurement plan generation method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the procurement plan generation method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the procurement plan generation method in any other appropriate manner (e.g., by means of firmware).

[0120] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0121] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0122] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0123] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0124] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0125] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0126] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0127] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for generating a procurement plan, characterized in that: include: Extracting the relationship between parameters in the product sales related data and the dependency of the parameters on time to form product sales features, and predicting and generating procurement demand based on the product sales features; The product sales-related data include: historical sales data, market trends, seasonal change data, promotional activities and macroeconomic conditions; Clustering multiple suppliers according to supplier association data and extracting the correlation between parameters in the supplier association data; wherein the supplier association data includes: supplier qualification review results, credibility score, contract performance capability, supplier image data, product quality and price fluctuation; Evaluate each supplier based on the clustering results and correlation extraction results to obtain the supplier ranking results; A procurement plan is generated according to the procurement demand, the supplier ranking result, the inventory monitoring result, and the production plan.

2. The method according to claim 1, characterized in that After generating the procurement plan, it also includes: Determine the comprehensive score of each supplier's quotation based on the supplier's quotation data and a preset quotation parameter weight model; wherein the supplier's quotation data includes: material price, quality, delivery date, freight and after-sales service; Determine a reasonable price range based on market price trends, suppliers’ historical transaction records, cost structure, and industry benchmark data; Based on the comprehensive scores of the supplier's quotations and the reasonable price range, price negotiations are conducted on the quotations of each supplier to obtain price negotiation results.

3. The method according to claim 2, characterized in that After obtaining the price negotiation results, it also includes: Obtaining a contract document and extracting contract text information from the contract document; Build a knowledge graph of legal requirements based on legal clauses, cases, and regulations; Compare the contract text information with the legal requirements knowledge graph to determine the compliance of the contract document; When the contract document complies with the regulations, the contract document is filled with data according to the procurement plan and the price negotiation result to obtain the target contract document.

4. The method according to claim 1, characterized in that: After generating the procurement plan, it also includes: Determine the priority of procurement plans based on order urgency, user importance, material quantity, product type and delivery deadline in each procurement plan; Each procurement plan is scheduled according to the priority, and during the scheduling process, the priority is adjusted in real time according to the delivery deadline.

5. The method according to claim 1, characterized in that After generating the procurement plan, it also includes: Acquire cargo logistics data related to the procurement plan, and predict order delivery time based on the cargo logistics data; When it is determined that there is a risk of delay based on the order delivery time and the delivery period in the procurement plan, a procurement delay alarm is issued.

6. The method according to claim 1, characterized in that After generating the procurement plan, it also includes: Collecting material images, and identifying the material images to obtain material identification results; Scan the barcode on the material to obtain the material scanning result; compare the material identification result with the material scanning result; When the comparison is passed, the inventory information is updated according to the inventory monitoring results and the material identification results.

7. The method according to claim 3, characterized in that After obtaining the target contract documents, it also includes: Determine automatic payment rules and payment conditions based on the payment information in the target contract document and the user's financial policy; When payment conditions are met, payment is made according to the automatic payment rules and a payment record is generated; Acquire invoice information corresponding to the payment record, verify the invoice information, and generate an invoice verification result; The payment record and the corresponding invoice verification results are displayed.

8. The method according to any one of claims 1 to 7, characterized in that: Also includes: Acquire real-time procurement data in procurement, and evaluate procurement performance indicators based on the real-time procurement data; When there are risks in the procurement assessment results, a procurement risk warning will be issued.

9. A purchasing plan generating device, characterized in that: include: A purchasing demand generation module is used to extract the relationship between parameters in the product sales related data and the dependency of the parameters on time to form product sales characteristics, and to predict and generate purchasing demand based on the product sales characteristics; The product sales-related data include: historical sales data, market trends, seasonal change data, promotional activities and macroeconomic conditions; A supplier data processing module is used to cluster multiple suppliers according to supplier association data and extract the correlation between parameters in the supplier association data; wherein the supplier association data includes: supplier qualification review results, reputation score, contract performance ability, supplier image data, product quality and price fluctuation; The supplier evaluation module is used to evaluate each supplier based on the clustering results and correlation extraction results to obtain the supplier ranking results; The procurement plan generation module is used to generate a procurement plan based on the procurement demand, the supplier ranking result, the inventory monitoring result, and the production plan.

10. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the procurement plan generating method according to any one of claims 1 to 8.

Images