Material supply matching method and device, computer equipment, storage medium and computer program product
Through the prediction model, predicting market demand and supplier capabilities, and combining with the target optimization model, the existing material supply matching methods are solved, and more efficient and accurate material supply matching is achieved.
Patent Information
- Application Number
- CN202510045333.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-13
- Publication Date
- 2025-04-11
AI Technical Summary
The existing material supply matching method relies on manual experience and traditional database query, which is inefficient and has low accuracy. Especially when market demand changes rapidly or supplier information is frequently updated, it is easy to have inaccurate matching problems.
By obtaining the current material demand data and inputting it into the pre-trained prediction model, the prediction results of market demand and supplier material supply capacity are obtained, and then these results are input into the pre-constructed target optimization model. Based on the preset objective function and constraints, the genetic algorithm is solved to obtain the best material supply matching solution.
It improves the accuracy and efficiency of material supply matching, reduces uncertainty caused by market fluctuations, and ensures the best match between target material demand and target suppliers, thereby reducing supply chain costs and inventory backlog.
Smart Images
Figure CN119809272A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data processing technology, and in particular to a material supply matching method, apparatus, computer equipment, storage medium and computer program product. Background Art
[0002] Material supply matching is crucial in the supply chain management system. Currently, material supply matching methods rely on manual experience, traditional database queries, and simple data analysis. These methods are inefficient and inaccurate. For example, the traditional material supply matching method requires manual input of a large amount of material demand information and supplier data, and then obtains matching suppliers through database queries. When material demand changes rapidly or supplier information is frequently updated, inaccurate matching is prone to occur, affecting the efficiency of material supply matching. Therefore, how to effectively improve the efficiency of material supply matching has become a problem to be solved. Summary of the invention
[0003] Based on this, it is necessary to provide a material supply matching method, apparatus, computer equipment, computer-readable storage medium and computer program product to address the above-mentioned technical problem of how to effectively improve the efficiency of material supply matching.
[0004] In a first aspect, the present application provides a material supply matching method, comprising:
[0005] Obtaining current material demand data and inputting it into a pre-trained prediction model to obtain a first prediction result of the corresponding market demand and a second prediction result of the supplier's material supply capacity; wherein the prediction model is trained based on historical material demand data, historical supplier data, historical market demand corresponding to the historical material demand data, and historical supplier material supply capacity corresponding to the historical supplier data;
[0006] The first prediction result and the second prediction result are input into a pre-built target optimization model to obtain corresponding target material demand data and target suppliers corresponding to each target material demand data; wherein the target optimization model is established based on a preset objective function and preset constraints, and is solved based on a preset genetic algorithm.
[0007] In one embodiment, the current material demand data is obtained and input into a pre-trained prediction model to obtain a first prediction result of the corresponding market demand and a second prediction result of the supplier's material supply capacity, including: obtaining the current material demand data and pre-processing it to obtain first normalized data mapped to a first preset interval; extracting a material feature data set associated with the current material demand data based on the first normalized data; inputting the material feature data set into a pre-trained prediction model to obtain a first prediction result of the corresponding market demand and a second prediction result of the supplier's material supply capacity.
[0008] In one embodiment, the current material demand data is obtained and input into a pre-trained prediction model to obtain a first prediction result of the corresponding market demand and a second prediction result of the supplier's material supply capacity, including: obtaining the current material demand data and the current supplier data updated based on the current material demand data, and pre-processing them to obtain first normalized data mapped to a first preset interval and second normalized data mapped to a second preset interval; extracting a material feature data set associated with the current material demand data based on the first normalized data; and extracting a supplier feature data set associated with the current supplier data based on the second normalized data; inputting the material feature data set and the supplier feature data set into the pre-trained prediction model to obtain the first prediction result of the corresponding market demand and a second prediction result of the supplier's material supply capacity.
[0009] In one of the embodiments, before obtaining the current material demand data, it also includes: obtaining historical material demand data, historical supplier data, historical market demand corresponding to the historical material demand data, and historical supplier material supply capacity corresponding to the historical supplier data, and preprocessing them to obtain normalized material data mapped to a first preset interval, and normalized supplier data mapped to a second preset interval; extracting a first feature data set associated with the historical material demand data based on the normalized material data, and extracting a second feature data set associated with the historical supplier data based on the normalized supplier data; training an initial model based on the first feature data set and the second feature data set to obtain a trained training model.
[0010] In one embodiment, the first feature data set includes time series features and material category features; the second feature data set includes the supplier's credit rating, production capacity indicators, and logistics distribution features.
[0011] In one of the embodiments, the preset objective function is determined based on material supply cost, material arrival delay time and material quality satisfaction; the preset constraint conditions include the supplier's production capacity, inventory and logistics distribution capabilities.
[0012] In a second aspect, the present application also provides a material supply matching device, including:
[0013] A prediction result output module is used to obtain current material demand data and input it into a pre-trained prediction model to obtain a first prediction result of the corresponding market demand and a second prediction result of the supplier's material supply capacity; wherein the prediction model is trained based on historical material demand data, historical supplier data, historical market demand corresponding to the historical material demand data, and historical supplier material supply capacity corresponding to the historical supplier data;
[0014] A target output module is used to input the first prediction result and the second prediction result into a pre-built target optimization model to obtain corresponding target material demand data and target suppliers corresponding to each target material demand data; wherein the target optimization model is established based on a preset objective function and preset constraints, and is solved based on a preset genetic algorithm.
[0015] In a third aspect, the present application further provides a computer device, the computer device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program:
[0016] Obtaining current material demand data and inputting it into a pre-trained prediction model to obtain a first prediction result of the corresponding market demand and a second prediction result of the supplier's material supply capacity; wherein the prediction model is trained based on historical material demand data, historical supplier data, historical market demand corresponding to the historical material demand data, and historical supplier material supply capacity corresponding to the historical supplier data;
[0017] The first prediction result and the second prediction result are input into a pre-built target optimization model to obtain corresponding target material demand data and target suppliers corresponding to each target material demand data; wherein the target optimization model is established based on a preset objective function and preset constraints, and is solved based on a preset genetic algorithm.
[0018] In a fourth aspect, the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:
[0019] Obtaining current material demand data and inputting it into a pre-trained prediction model to obtain a first prediction result of the corresponding market demand and a second prediction result of the supplier's material supply capacity; wherein the prediction model is trained based on historical material demand data, historical supplier data, historical market demand corresponding to the historical material demand data, and historical supplier material supply capacity corresponding to the historical supplier data;
[0020] The first prediction result and the second prediction result are input into a pre-built target optimization model to obtain corresponding target material demand data and target suppliers corresponding to each target material demand data; wherein the target optimization model is established based on a preset objective function and preset constraints, and is solved based on a preset genetic algorithm.
[0021] In a fifth aspect, the present application further provides a computer program product, the computer program product comprising a computer program, which implements the following steps when executed by a processor:
[0022] Obtaining current material demand data and inputting it into a pre-trained prediction model to obtain a first prediction result of the corresponding market demand and a second prediction result of the supplier's material supply capacity; wherein the prediction model is trained based on historical material demand data, historical supplier data, historical market demand corresponding to the historical material demand data, and historical supplier material supply capacity corresponding to the historical supplier data;
[0023] The first prediction result and the second prediction result are input into a pre-built target optimization model to obtain corresponding target material demand data and target suppliers corresponding to each target material demand data; wherein the target optimization model is established based on a preset objective function and preset constraints, and is solved based on a preset genetic algorithm.
[0024] The above-mentioned material supply matching method, device, computer equipment, storage medium and computer program product have the following beneficial effects in the process of material supply matching: first, the current material demand data is obtained and input into the pre-trained prediction model to obtain the first prediction result of the corresponding market demand and the second prediction result of the supplier's material supply capacity; wherein the prediction model is trained based on historical material demand data, historical supplier data, historical market demand corresponding to the historical material demand data, and historical supplier material supply capacity corresponding to the historical supplier data; then the first prediction result and the second prediction result are input into the pre-constructed target optimization model to obtain the corresponding target material demand data and the target suppliers corresponding to each target material demand data; wherein the target optimization model is established based on a preset objective function and preset constraints, and is solved based on a preset genetic algorithm. In the above process, by inputting the current material demand data into the prediction model pre-trained based on multi-party historical data, the market demand and supplier material supply capacity can be predicted more accurately, reducing the uncertainty caused by market fluctuations; and by inputting the first prediction result and the second prediction result into the target optimization model established based on the preset objective function and preset constraints, the resource allocation can be adjusted in a targeted manner to ensure the best match between the target material demand data and the target supplier, thereby reducing supply chain costs and inventory backlogs. Therefore, the purpose of effectively improving the efficiency of material supply matching is achieved through the above process. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0026] Figure 1 A schematic diagram of a flow chart of a material supply matching method in one embodiment;
[0027] Figure 2 A schematic diagram of a process flow of a material supply matching step in an embodiment;
[0028] Figure 3 A schematic diagram of a module of intelligent monitoring in one embodiment;
[0029] Figure 4 It is a structural block diagram of a material supply matching device in one embodiment;
[0030] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION
[0031] The current material supply matching method lacks effective data analysis and forecasting functions, and is unable to accurately predict market demand and supplier supply capacity, resulting in inaccurate material supply matching and frequent oversupply or shortages, which not only increases the company's operating costs, but also affects the overall efficiency of the supply chain.
[0032] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0033] In an exemplary embodiment, Figure 1 As shown, a material supply matching method is provided, including the following steps S102 to S104. Among them:
[0034] Step S102, obtain current material demand data and input it into a pre-trained prediction model to obtain a first prediction result of the corresponding market demand and a second prediction result of the supplier's material supply capacity; wherein the prediction model is trained based on historical material demand data, historical supplier data, historical market demand corresponding to the historical material demand data, and historical supplier material supply capacity corresponding to the historical supplier data.
[0035] Among them, current material demand data refers to the immediate quantity and type of materials that need to be purchased or allocated; the pre-trained prediction model is a model built based on historical material demand data, historical supplier data, historical market demand corresponding to historical material demand data, and historical supplier material supply capacity corresponding to historical supplier data. It is a model that can identify patterns and trends through machine learning training in order to predict future demand and supply capacity; the first prediction result of market demand is the estimated result of the market's expected demand for specific materials output by the prediction model; the second prediction result of the supplier's material supply capacity refers to the result obtained by evaluating the supplier's capabilities based on the prediction model, including its ability to respond to demand and deliver products; historical material demand data refers to the material procurement situation driven by market demand in a certain period of time in the past; historical supplier data contains information about the performance, delivery time, and material quality of suppliers in multiple transactions in the past.
[0036] Step S104, input the first prediction result and the second prediction result into a pre-constructed target optimization model to obtain corresponding target material demand data and target suppliers corresponding to each target material demand data; wherein the target optimization model is established based on a preset objective function and preset constraints, and is solved based on a preset genetic algorithm.
[0037] Among them, the target optimization model refers to a mathematical model constructed under certain constraints to achieve specific business goals, such as reducing costs and improving efficiency; the target material demand data is the optimal material supply plan determined after optimization to ensure that the material quantity can meet market demand; the target supplier refers to finding the best supplier combination based on the model output to meet the predicted target material demand data; the preset objective function is a mathematical expression set in the optimization model, which is used to quantify the goal to be optimized, such as minimizing costs or maximizing supply efficiency; the preset constraints refer to the conditions that limit the scope of the target optimization model solution, such as the upper limit of supply capacity, the lower limit of market demand, budget constraints, etc.; the genetic algorithm refers to an optimization algorithm based on the principles of natural selection and genetics, which generally simulates biological evolution through selection, crossover, mutation, etc. to obtain the optimal solution.
[0038] In the above-mentioned material supply matching method, firstly, the current material demand data is obtained and input into the pre-trained prediction model to obtain the first prediction result of the corresponding market demand and the second prediction result of the supplier's material supply capacity; wherein, the prediction model is trained based on historical material demand data, historical supplier data, historical market demand corresponding to the historical material demand data, and historical supplier material supply capacity corresponding to the historical supplier data; then the first prediction result and the second prediction result are input into the pre-built target optimization model to obtain the corresponding target material demand data and the target supplier corresponding to each target material demand data; wherein, the target optimization model is established based on a preset objective function and preset constraints, and is solved based on a preset genetic algorithm. In the above process, by inputting the current material demand data into the prediction model pre-trained based on multi-party historical data, the market demand and the supplier's material supply capacity can be predicted more accurately, reducing the uncertainty caused by market fluctuations; and by inputting the first prediction result and the second prediction result into the target optimization model established based on the preset objective function and preset constraints, the resource allocation can be adjusted in a targeted manner to ensure the best match between the target material demand data and the target supplier, thereby reducing the supply chain cost and reducing the inventory backlog. Therefore, the above process achieves the purpose of efficiently improving the efficiency of material supply matching.
[0039] In one embodiment, current material demand data is obtained and input into a pre-trained forecasting model to obtain a first forecast result of the corresponding market demand and a second forecast result of the supplier's material supply capacity, including:
[0040] The current material demand data is obtained and preprocessed to obtain first normalized data mapped to a first preset interval; a material feature data set associated with the current material demand data is extracted based on the first normalized data; the material feature data set is input into a pre-trained prediction model to obtain a first prediction result of the corresponding market demand and a second prediction result of the supplier's material supply capacity.
[0041] Among them, the first preset interval refers to the fixed range used to map data in the normalization process to eliminate the dimensional influence between different features; the first normalized data refers to the data obtained after preprocessing, which is normalized within the first preset interval so that subsequent model training and analysis can unify the scale, thereby improving the model effect; the material feature data set refers to the feature set extracted from the first normalized data, which is directly related to the current material demand data.
[0042] In this embodiment, by preprocessing the current material demand data to obtain the first normalized data mapped in the first preset interval, the material feature data set is obtained based on the first normalized data, and then input into the prediction model to obtain the first prediction result and the second prediction result. This not only improves the responsiveness to current market demand and enhances the flexibility and adaptability of the supply chain, but also maximizes the effective use of resources, reduces inventory costs, provides data support for subsequent decision-making, improves decision-making efficiency, and ensures the timely supply of materials.
[0043] Furthermore, in one embodiment, current material demand data is obtained and input into a pre-trained prediction model to obtain a first prediction result of the corresponding market demand and a second prediction result of the supplier's material supply capacity, including:
[0044] Acquire current material demand data and current supplier data updated based on the current material demand data, and preprocess them to obtain first normalized data mapped to a first preset interval, and second normalized data mapped to a second preset interval; extract a material feature data set associated with the current material demand data based on the first normalized data; and extract a supplier feature data set associated with the current supplier data based on the second normalized data; input the material feature data set and the supplier feature data set into a pre-trained prediction model to obtain a first prediction result of the corresponding market demand and a second prediction result of the supplier's material supply capacity.
[0045] Among them, the second preset interval refers to a specified range of values used to map the second normalized data to ensure dimensional consistency when processing the current supplier data; the second normalized data refers to the current supplier data that has been denormalized and mapped in the second preset interval; the supplier feature data set refers to a set of features related to the current supplier data extracted from the second normalized data, which is used to reflect the supplier's capabilities, historical performance, etc., and affect its ability to respond to demand.
[0046] In this embodiment, through accurate data acquisition and processing, enterprises can quickly adjust their strategies to adapt to changes in market demand; using the extracted features as inputs into the prediction model can reduce prediction bias and improve the prediction accuracy of market demand and supplier material supply capabilities; the combined analysis of material feature data sets and supplier feature data sets allows enterprises to allocate resources more reasonably, reduce surpluses or shortages, and reduce inventory costs.
[0047] In an exemplary embodiment, before obtaining the current material demand data, the method further includes:
[0048] Acquire historical material demand data, historical supplier data, historical market demand corresponding to the historical material demand data, and historical supplier material supply capacity corresponding to the historical supplier data, and preprocess them to obtain normalized material data mapped to a first preset interval, and normalized supplier data mapped to a second preset interval; extract a first feature data set associated with the historical material demand data based on the normalized material data, and extract a second feature data set associated with the historical supplier data based on the normalized supplier data; train an initial model based on the first feature data set and the second feature data set to obtain a trained training model.
[0049] Among them, historical material demand data refers to the demand records for various materials of the enterprise or market in the past period of time; historical supplier data contains historical transaction information, delivery performance, supply time, quality, etc. related to the supplier; historical market demand represents the actual demand for a certain material in the market in a specific time period in the past; historical supplier material supply capacity is data that reflects the supplier's actual ability to provide materials in historical records; preprocessing refers to the cleaning and standardization of the collected historical data for subsequent analysis and modeling, which may include steps such as missing value processing, outlier detection, and data partitioning.
[0050] More generally, normalizing material data refers to converting the original data into a fixed range to eliminate the dimensional impact between different features; the first preset interval is used to normalize the specific numerical range of material data, usually to adapt to the model input requirements; normalizing supplier data is to normalize the supplier-related data to ensure that it is at the same scale as the material data during model training; the first feature data set refers to the feature set related to historical material demand data extracted from the normalized material data, which is usually used to capture the key factors affecting demand; the second feature data set refers to the feature set extracted from the normalized supplier data, which is associated with the performance and capabilities of the supplier to reflect its impact on material supply.
[0051] In this embodiment, by acquiring historical data and performing preprocessing, noise and redundancy in the data are eliminated to ensure that subsequent analysis can be based on standardized data; by extracting the first and second feature data sets from the normalized material and supplier data, and combining the feature data of materials and suppliers, market demand and supplier capabilities can be more comprehensively evaluated, the operation of the supply chain can be optimized, and response speed and flexibility can be improved.
[0052] In one embodiment, the first feature data set includes time series features and material category features; the second feature data set includes the supplier's credit rating, production capacity indicators, and logistics distribution features.
[0053] Among them, time series characteristics refer to the patterns and trends that reflect the changes in material demand over time, usually including information such as seasonality and cyclicality; material category characteristics refer to the classification information of materials, such as different types of materials, such as raw materials, finished products, etc.; suppliers include historical suppliers and new suppliers; credit rating refers to the credit score of the supplier, reflecting its financial health and ability to perform; production capacity indicators refer to relevant data for evaluating the supplier's production capacity, including output, production efficiency, etc.; logistics and distribution characteristics refer to the supplier's capabilities in material distribution, including delivery time, distribution range, transportation method, etc.
[0054] In this embodiment, by analyzing the time series characteristics, the enterprise can identify the peaks and troughs of demand, so as to better manage inventory and production planning; by obtaining the results of credit ratings, the enterprise can choose more reliable suppliers and reduce supply risks; by obtaining logistics and distribution characteristics, Jiu Er Yi helps enterprises choose suppliers with good logistics capabilities to ensure that materials can arrive on time.
[0055] Furthermore, in one embodiment, the preset objective function is determined based on the material supply cost, material arrival delay time, and material quality satisfaction; the preset constraints include the supplier's production capacity, inventory, and logistics distribution capabilities.
[0056] Among them, the preset objective function refers to the goal that needs to be achieved in the target optimization model, usually the quantity that needs to be minimized or maximized; the material supply cost refers to the total cost required to purchase and transport materials, including production costs, transportation costs and other related costs; the material arrival delay time refers to the time required for the materials to be shipped from the supplier to the final destination. The shorter the delay time, the higher the supply chain efficiency; the material quality satisfaction refers to the customer's satisfaction with the quality of the received materials, which is usually related to factors such as the product's performance, reliability and compliance with specifications; the preset constraints refer to the restrictions that need to be followed during the optimization process; the supplier's production capacity refers to the maximum quantity of materials that the supplier can produce and provide within a certain period of time; inventory refers to the quantity of materials currently held by the enterprise or supplier; logistics distribution capability refers to the supplier's ability in material transportation and delivery, including transportation methods, delivery time and distribution range.
[0057] In this embodiment, by setting clear goals and constraints, the enterprise can formulate procurement and supply strategies more effectively to ensure the rational allocation of resources; by optimizing the cost of material supply, the enterprise can improve the profit margin; and by paying attention to material quality and delivery time, it helps to improve customer satisfaction and loyalty, thereby promoting the sustainable development of the business; through reasonable inventory management and supplier selection, the enterprise can respond to market changes more flexibly and reduce potential risks.
[0058] This application provides a material supply matching method. In order to better understand the process of the above material supply matching method, combined with Figure 2 As shown, the specific process of the material supply matching method of this application is described in detail below, including the following steps:
[0059] Step S202, obtaining historical material demand data, historical supplier data, historical market demand corresponding to the historical material demand data, and historical supplier material supply capacity corresponding to the historical supplier data, and training a prediction model based on the above data.
[0060] Step S204, inputting the acquired ethical material demand data into the prediction model to obtain a first prediction result of the market demand and a second prediction result of the supplier's material supply capacity.
[0061] Step S206: establishing a target optimization model based on a preset objective function and preset constraints.
[0062] Step S208: input the first prediction result and the second prediction result into the target optimization model to obtain corresponding target material demand data and target suppliers corresponding to each target material demand data.
[0063] As an example, Figure 3As shown, intelligent monitoring also includes a data acquisition module, a data processing module, a monitoring module, and a feedback and adjustment module; and the data acquisition module includes sensor data, location data, and status data; the data processing module includes data cleaning, data analysis, and data processing; the monitoring module includes real-time monitoring, early warning system, and report production; the feedback and adjustment module includes result feedback, strategy adjustment, and instruction execution. Therefore, the Internet of Things technology can be used to automatically collect the above historical data through sensors and smart devices, including but not limited to material type, quantity, demand time, and user department; the collected data is stored and analyzed through a big data platform, and the data is analyzed using machine learning algorithms to predict market demand and supplier supply capabilities.
[0064] In addition, the collected raw data is cleaned to handle missing values, outliers and duplicate data. The mean filling method is used to handle missing numerical data. Outliers are identified and corrected by setting a reasonable threshold range. Then the data is standardized to make data with different characteristics comparable. The normalization method is used to map the data to a specific interval; key features related to material demand and supplier supply capacity are extracted. Time series features such as seasonality, cyclicality, etc., and material category-related features such as sales trends of major and minor categories of materials are extracted from historical material demand data; supplier credit ratings, production capacity indicators such as equipment quantity, capacity utilization, etc., and logistics and distribution-related features such as average delivery time and delivery range are extracted from supplier data.
[0065] Furthermore, an algorithm that combines the Long Short-Term Memory Network (LSTM) and Convolutional Neural Network (CNN) in deep learning is used to predict market demand. Among them, LSTM is good at processing time series data and can capture long-term trends and short-term fluctuations in demand, while CNN is used to extract local features in the data and enhance the model's ability to recognize complex data patterns.
[0066] In addition, for the prediction of supplier supply capacity, the random forest algorithm is used to build multiple decision trees and comprehensively consider multiple factors to evaluate the supplier supply capacity. The historical data can be divided into training set, validation set and test set in a ratio of 7:2:1. The training set is used to train the model (prediction model). During the training process, the model parameters such as the number of hidden layers and learning rate of LSTM, the number of trees and tree depth of random forest are adjusted. The validation set is used to evaluate the model performance and the model parameters with the best performance on the validation set are selected. Finally, the model accuracy, mean square error and other indicators are evaluated on the test set to ensure that the model has good generalization ability. The trained model can predict the market demand and supplier supply capacity in the future based on the data collected in real time.
[0067] Moreover, the real-time matching algorithm dynamically adjusts the matching rules according to the results of intelligent data analysis. The algorithm can consider multiple factors, such as the supplier's delivery time, price, quality, etc., to ensure the matching efficiency and accuracy of material supply; a multi-objective optimization model is established, and the objective function is to minimize the material supply cost, including procurement cost, transportation cost, etc., minimize the delivery delay time and maximize the material quality satisfaction; the constraints include the supplier's production capacity limit, inventory limit, logistics distribution capacity limit, etc. For example, let the material supply cost be C, the delivery delay time be T, and the material quality satisfaction be Q, then the objective function can be expressed as minimizeαC+βT+(1-α-β)(1-Q), where α and β are weight coefficients, which are set according to the importance of cost, delivery time and quality. The above multi-objective optimization model can be solved by genetic algorithm. First, the supplier group is encoded, and each individual represents a material supply plan, including the selected supplier, purchase quantity, etc.; then the group is continuously optimized through selection, crossover and mutation operations. In the selection operation, excellent individuals are selected to enter the next generation according to their fitness values (calculated by the objective function); the crossover operation simulates biological gene recombination and generates new individuals by exchanging part of the codes of two individuals; the mutation operation randomly changes the codes of individuals with a certain probability to increase the diversity of the group. After multiple iterations, until the termination conditions are met, such as reaching the maximum number of iterations or the convergence of the objective function value, the optimal material supply matching solution is obtained.
[0068] Furthermore, the real-time monitoring system can monitor the material supply process, provide timely feedback on the supply situation, and adjust the matching strategy. The intelligent monitoring system can track the transportation status of materials in real time to ensure that the materials arrive on time and adjust the supply plan in time to cope with market changes.
[0069] Through the above embodiments, the above process can help enterprises better understand market trends, optimize inventory management, and reduce the risk of oversupply or shortage; thereby realizing the automation and intelligence of material supply, reducing labor costs, improving supply efficiency, reducing operational risks, and significantly improving the matching efficiency and accuracy of material supply.
[0070] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0071] Based on the same inventive concept, the embodiment of the present application also provides a material supply matching device for implementing the material supply matching method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more material supply matching device embodiments provided below can refer to the limitations of the material supply matching method above, and will not be repeated here.
[0072] In an exemplary embodiment, Figure 4 As shown, a material supply matching device is provided, including: a prediction result output module 401 and a target output module 402, wherein:
[0073] The prediction result output module 401 is used to obtain the current material demand data and input it into the pre-trained prediction model to obtain the first prediction result of the corresponding market demand and the second prediction result of the supplier's material supply capacity; wherein the prediction model is trained based on the historical material demand data, the historical supplier data, the historical market demand corresponding to the historical material demand data, and the historical supplier material supply capacity corresponding to the historical supplier data;
[0074] The target output module 402 is used to input the first prediction result and the second prediction result into a pre-built target optimization model to obtain the corresponding target material demand data and the target supplier corresponding to each target material demand data; wherein the target optimization model is established based on a preset objective function and preset constraints, and is solved based on a preset genetic algorithm.
[0075] Furthermore, in one embodiment, the prediction result output module 401 is also used to obtain and preprocess the current material demand data to obtain first normalized data mapped to a first preset interval; extract a material feature data set associated with the current material demand data based on the first normalized data; input the material feature data set into a pre-trained prediction model to obtain a first prediction result of the corresponding market demand and a second prediction result of the supplier's material supply capacity.
[0076] Furthermore, in one embodiment, the prediction result output module 401 is also used to obtain current material demand data and current supplier data updated based on the current material demand data, and preprocess the data to obtain first normalized data mapped to a first preset interval and second normalized data mapped to a second preset interval; extract a material feature data set associated with the current material demand data based on the first normalized data; and extract a supplier feature data set associated with the current supplier data based on the second normalized data; input the material feature data set and the supplier feature data set into a pre-trained prediction model to obtain a first prediction result of the corresponding market demand and a second prediction result of the supplier's material supply capacity.
[0077] Furthermore, in one embodiment, the prediction result output module 401 is also used to obtain historical material demand data, historical supplier data, historical market demand corresponding to the historical material demand data, and historical supplier material supply capacity corresponding to the historical supplier data, and preprocess them to obtain normalized material data mapped to a first preset interval, and normalized supplier data mapped to a second preset interval; extract a first feature data set associated with the historical material demand data based on the normalized material data, and extract a second feature data set associated with the historical supplier data based on the normalized supplier data; train an initial model based on the first feature data set and the second feature data set to obtain a trained training model.
[0078] Furthermore, in one embodiment, in the prediction result output module 401, the first feature data set includes time series features and material category features; the second feature data set includes the supplier's credit rating, production capacity indicators, and logistics distribution features.
[0079] Furthermore, in one embodiment, in the target output module 402, the preset target function is determined based on the material supply cost, material arrival delay time and material quality satisfaction; the preset constraints include the supplier's production capacity, inventory and logistics distribution capacity.
[0080] Each module in the above-mentioned material supply matching device can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.
[0081] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 5 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store material supply matching data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a material supply matching method is implemented.
[0082] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0083] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.
[0084] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.
[0085] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.
[0086] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.
[0087] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.
[0088] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0089] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A material supply matching method, characterized in that: The method comprises: Obtaining current material demand data and inputting it into a pre-trained prediction model to obtain a first prediction result of the corresponding market demand and a second prediction result of the supplier's material supply capacity; wherein the prediction model is trained based on historical material demand data, historical supplier data, historical market demand corresponding to the historical material demand data, and historical supplier material supply capacity corresponding to the historical supplier data; The first prediction result and the second prediction result are input into a pre-built target optimization model to obtain corresponding target material demand data and target suppliers corresponding to each target material demand data; wherein the target optimization model is established based on a preset objective function and preset constraints, and is solved based on a preset genetic algorithm.
2. The method according to claim 1, characterized in that The current material demand data is obtained and input into the pre-trained prediction model to obtain a first prediction result of the corresponding market demand and a second prediction result of the supplier's material supply capacity, including: Acquire current material demand data and perform preprocessing to obtain first normalized data mapped to a first preset interval; extracting a material feature data set associated with the current material demand data based on the first normalized data; The material feature data set is input into a pre-trained prediction model to obtain a first prediction result of the corresponding market demand and a second prediction result of the supplier's material supply capacity.
3. The method according to claim 1, characterized in that The current material demand data is obtained and input into the pre-trained prediction model to obtain a first prediction result of the corresponding market demand and a second prediction result of the supplier's material supply capacity, including: Acquire current material demand data and current supplier data updated based on the current material demand data, and preprocess the data to obtain first normalized data mapped to a first preset interval and second normalized data mapped to a second preset interval; Extracting a material feature data set associated with the current material demand data based on the first normalized data; and extracting a supplier feature data set associated with the current supplier data based on the second normalized data; The material feature data set and the supplier feature data set are input into a pre-trained prediction model to obtain a first prediction result of the corresponding market demand and a second prediction result of the supplier's material supply capacity.
4. The method according to claim 1, characterized in that Before obtaining the current material demand data, the method further includes: Acquire historical material demand data, historical supplier data, historical market demand corresponding to the historical material demand data, and historical supplier material supply capacity corresponding to the historical supplier data, and preprocess them to obtain normalized material data mapped to a first preset interval and normalized supplier data mapped to a second preset interval; Extracting a first feature data set associated with the historical material demand data based on the normalized material data, and extracting a second feature data set associated with the historical supplier data based on the normalized supplier data; An initial model is trained based on the first feature data set and the second feature data set to obtain a trained training model.
5. The method according to claim 4, characterized in that The first feature data set includes time series features and material category features; The second characteristic data set includes the supplier's credit rating, production capacity indicators, and logistics and distribution characteristics.
6. The method according to claim 1, characterized in that The preset objective function is determined based on the material supply cost, material arrival delay time and material quality satisfaction; The preset constraints include the supplier's production capacity, inventory, and logistics distribution capabilities.
7. A material supply matching device, characterized in that: The device comprises: A prediction result output module is used to obtain current material demand data and input it into a pre-trained prediction model to obtain a first prediction result of the corresponding market demand and a second prediction result of the supplier's material supply capacity; wherein the prediction model is trained based on historical material demand data, historical supplier data, historical market demand corresponding to the historical material demand data, and historical supplier material supply capacity corresponding to the historical supplier data; A target output module is used to input the first prediction result and the second prediction result into a pre-built target optimization model to obtain corresponding target material demand data and target suppliers corresponding to each target material demand data; wherein the target optimization model is established based on a preset objective function and preset constraints, and is solved based on a preset genetic algorithm.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.