A method and system for providing commodity trading
By obtaining and processing data from commodity trading platforms in real time, classification and feature identification, and optimizing supply adjustment factors with user consumption data, the accuracy and timeliness of commodity supply management in the existing technology are solved, and the efficiency of the supply chain is improved and Customer satisfaction.
Patent Information
- Application Number
- CN202411156010.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-22
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2044-08-22
AI Technical Summary
Due to the lack of real-time data acquisition and processing capabilities in the prior art, the accuracy and timeliness of commodity supply management are low, affecting the response speed, cost control and customer satisfaction of the supply chain.
By connecting to the commodity trading platform, real-time commodity sales and inventory data flows are obtained, data classification and feature identification are carried out, supply adjustment factors are generated, and product supply management is optimized in combination with user consumption data.
It improves the accuracy and timeliness of commodity supply management, ensures rapid response and cost control of the supply chain, and improves customer satisfaction.
Smart Images

Figure CN118674530B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of supply management technology, and in particular to a method and system for providing commodity transactions. Background Art
[0002] With the rapid development of Internet technology, e-commerce has become an important part of modern business. People are increasingly inclined to shop online because it provides a convenient, fast and diverse shopping experience. However, traditional e-commerce platforms often have problems such as information asymmetry, high transaction costs and insecure payments.
[0003] At present, existing commodity supply chain management technologies are often unable to obtain and analyze commodity sales and inventory data in real time, lack effective data classification and processing mechanisms, and in-depth analysis of inventory feature information. This leads to problems such as delayed decision-making, inaccurate inventory levels, and inaccurate demand forecasts in commodity supply management for suppliers. This further affects the response speed, cost control, and customer satisfaction of the supply chain, thereby restricting the improvement of the overall efficiency and competitiveness of the supply chain.
[0004] In summary, the existing technology lacks real-time data acquisition and processing capabilities, resulting in low accuracy and poor timeliness in the commodity supply management of commodity suppliers. Summary of the invention
[0005] The purpose of this application is to provide a method and system for providing commodity trading, so as to solve the technical problem that the commodity supply management of commodity suppliers has low accuracy and poor timeliness due to the lack of real-time data acquisition and processing capabilities in the prior art.
[0006] In view of the above problems, the present application provides a method and system for providing commodity trading.
[0007] In a first aspect, the present application provides a method for providing commodity transactions, which is implemented by a system for providing commodity transactions, wherein the method for providing commodity transactions includes: connecting to a commodity trading platform to obtain a real-time commodity sales data stream and a real-time commodity inventory data stream of a first commodity supplier; classifying according to the real-time commodity sales data stream to obtain a commodity sales data classification result, and extracting a first commodity sales data partition corresponding to the first commodity based on the commodity sales data classification result; performing feature recognition on the real-time commodity inventory data stream based on the first commodity to obtain first commodity inventory feature information; based on a predetermined future time zone, performing commodity supply reward and punishment factor analysis according to the first commodity sales data partition and the first commodity inventory feature information to generate a first commodity supply adjustment factor; obtaining a real-time user consumption data set according to the commodity trading platform, and performing association optimization on the first commodity supply adjustment factor according to the real-time user consumption data set to generate a second commodity supply adjustment factor; the first commodity supplier performs commodity supply management based on the second commodity supply adjustment factor.
[0008] In a second aspect, the present application further provides a system for providing commodity transactions, which is used to execute a method for providing commodity transactions as described in the first aspect, wherein the system for providing commodity transactions includes: a data stream acquisition module, which is used to connect to a commodity trading platform to obtain a real-time commodity sales data stream and a real-time commodity inventory data stream of a first commodity supplier; a data classification result acquisition module, which is used to classify according to the real-time commodity sales data stream, obtain a commodity sales data classification result, and extract a first commodity sales data partition corresponding to the first commodity based on the commodity sales data classification result; a feature recognition module, which is used to perform feature recognition on the real-time commodity inventory data stream based on the first commodity to obtain first commodity inventory feature information; a first supply adjustment factor generation module, which is used to perform commodity supply reward and punishment factor analysis based on the first commodity sales data partition and the first commodity inventory feature information based on a predetermined future time zone to generate a first commodity supply adjustment factor; a second supply adjustment factor generation module, which is used to obtain a real-time user consumption data set according to the commodity trading platform, and perform association optimization on the first commodity supply adjustment factor according to the real-time user consumption data set to generate a second commodity supply adjustment factor; a supply management module, in which the first commodity supplier performs commodity supply management based on the second commodity supply adjustment factor.
[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:
[0010] By connecting to a commodity trading platform, a real-time commodity sales data stream and a real-time commodity inventory data stream of a first commodity supplier are obtained; classification is performed according to the real-time commodity sales data stream to obtain a commodity sales data classification result, and a first commodity sales data partition corresponding to the first commodity is extracted based on the commodity sales data classification result; feature recognition is performed on the real-time commodity inventory data stream based on the first commodity to obtain first commodity inventory feature information; commodity supply reward and punishment factors are parsed based on the first commodity sales data partition and the first commodity inventory feature information based on a predetermined future time zone to generate a first commodity supply adjustment factor; a real-time user consumption data set is obtained according to the commodity trading platform, and association optimization is performed on the first commodity supply adjustment factor according to the real-time user consumption data set to generate a second commodity supply adjustment factor; the first commodity supplier manages commodity supply based on the second commodity supply adjustment factor, which effectively solves the technical problem of low accuracy and poor timeliness of commodity supply management of commodity suppliers due to lack of real-time data acquisition and processing capabilities in the prior art, and improves the accuracy and timeliness of commodity supply management of commodity suppliers through real-time data acquisition, classification processing, inventory feature recognition, forecasting analysis and integration of user consumption data.
[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0012] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.
[0013] Figure 1 A flowchart of a method for providing commodity trading for this application;
[0014] Figure 2 This is a schematic diagram of the structure of a system for providing commodity trading in the present application.
[0015] Description of reference numerals:
[0016] Data flow acquisition module 11, data classification result acquisition module 12, feature recognition module 13, first supply adjustment factor generation module 14, second supply adjustment factor generation module 15, supply management module 16. DETAILED DESCRIPTION
[0017] The present application solves the technical problem in the prior art of low accuracy and poor timeliness of commodity supply management of commodity suppliers due to the lack of real-time data acquisition and processing capabilities by providing a method and system for providing commodity transactions. The accuracy and timeliness of commodity supply management of commodity suppliers are improved through the acquisition, classification processing, inventory feature identification, predictive analysis and integration of user consumption data of real-time data.
[0018] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.
[0019] For example, please refer to the attached Figure 1 The present application provides a method for providing commodity transactions, wherein the method for providing commodity transactions is applied to a system for providing commodity transactions, and the method for providing commodity transactions specifically includes the following steps:
[0020] S1: Connect to the commodity trading platform to obtain the real-time commodity sales data stream and real-time commodity inventory data stream of the first commodity supplier.
[0021] Specifically, the commodity trading platform will provide an application programming interface API that allows third-party systems to access its data in real time over the Internet. Use the API key and documentation provided by the platform to establish a connection. Through the API, you can request the latest sales and inventory data regularly, such as every minute or every hour. You can also use webhooks to subscribe to real-time events, such as new sales orders or inventory changes. When these events occur, the platform will immediately send data to the supplier's system. Message queue systems such as RabbitMQ and Kafka can be used to temporarily store data streams to ensure that data is not lost and can be processed asynchronously.
[0022] S2: Classify the real-time commodity sales data stream to obtain a commodity sales data classification result, and extract a first commodity sales data partition corresponding to the first commodity based on the commodity sales data classification result.
[0023] Specifically, according to business needs, determine the classification standards, which include product category, brand, model, sales channel, etc. Use data mining techniques, such as decision trees, K-means clustering, neural networks, etc., to classify the sales data stream. Each sales record is labeled according to the classification criteria to indicate the category to which it belongs. Summarize the classification results to obtain a sales data set for each category, such as electronic products, clothing, etc. Determine the products that need to be analyzed in detail, whether they are the best-selling products or the most profitable products. Extract the sales data related to the first product from the classification results to form a specific data set, namely the first product sales data partition.
[0024] S3: Perform feature recognition on the real-time commodity inventory data stream based on the first commodity to obtain first commodity inventory feature information.
[0025] Specifically, determine the features that need to be extracted from the inventory data, such as inventory volume, inventory turnover rate, out-of-stock frequency, inventory in transit, safety stock, etc. Before performing feature recognition, clean the inventory data to remove invalid or erroneous data. Use stream data processing technologies such as Apache Kafka, Apache Flink, and Spark Streaming to process the inventory data stream in real time. Apply data mining and machine learning algorithms, such as time series analysis and pattern recognition, to extract feature information from the inventory data stream. Filter out data related to the first product from the inventory data stream. Calculate the features defined above for the filtered data to form inventory feature information for the first product.
[0026] S4: Based on the predetermined future time zone, the commodity supply reward and punishment factor is analyzed according to the first commodity sales data partition and the first commodity inventory characteristic information to generate a first commodity supply adjustment factor.
[0027] Specifically, determine the time range for the forecast, such as the next week, month, or quarter. Use time series analysis, regression analysis, machine learning, and other methods, combined with the first commodity sales data partition and inventory feature information, to predict commodity demand in future time zones. Set reward and punishment standards based on business goals, such as sales, profit margins, customer satisfaction, etc. Calculate supply reward and punishment factors based on the predicted demand and the set standards, which will affect supply decisions. Generate supply adjustment factors by comprehensively considering sales data, inventory characteristics, and reward and punishment factors. Supply adjustment factors include order quantity, replenishment time point, safety stock level, production speed, etc., which are used to guide each link of the supply chain.
[0028] S5: According to the commodity trading platform, a real-time user consumption data set is obtained, and the first commodity supply adjustment factor is optimized according to the real-time user consumption data set to generate a second commodity supply adjustment factor.
[0029] Specifically, through the API interface of the commodity trading platform, user consumption data is obtained in real time, including purchase records, browsing history, evaluation feedback, etc. User consumption data from different sources and formats are integrated into a unified data set. Use data mining techniques, such as cluster analysis and association rule mining, to identify user consumption patterns and preferences. Analyze user consumption data to understand the changing trends and potential needs of market demand. Conduct correlation analysis between user consumption data and the first commodity supply adjustment factor to evaluate the degree of match between the existing supply strategy and the actual needs of users. Use optimization algorithms, such as linear programming and integer programming, to optimize the supply adjustment factor based on user consumption data. Comprehensively consider the first commodity supply adjustment factor and user consumption data to generate a more refined second commodity supply adjustment factor. The second commodity supply adjustment factor includes more specific supply strategies, such as inventory allocation for specific promotional activities, inventory support for personalized recommendation systems, etc.
[0030] S6: The first commodity supplier performs commodity supply management based on the second commodity supply adjustment factor.
[0031] Specifically, based on the second commodity supply adjustment factor, update the demand forecast to ensure that the forecast results match the actual market demand. Based on the forecast results, adjust the order quantity placed with the manufacturer or distributor to avoid oversupply or shortage. Based on the second commodity supply adjustment factor, adjust the safety stock level to cope with demand fluctuations or supply uncertainties. By optimizing inventory levels, improve inventory turnover and reduce capital occupation and inventory costs. Based on the second commodity supply adjustment factor, adjust the replenishment point to optimize the replenishment timing. According to market demand changes, adjust the replenishment cycle to ensure timely response to market changes. According to the supply adjustment factor, adjust the production plan and scheduling to adapt to market demand and production capacity. Monitor the execution of the supply chain in real time, including order fulfillment, inventory levels, replenishment efficiency, etc. Establish a feedback mechanism to compare the actual execution results with the second commodity supply adjustment factor, and continuously adjust and optimize the supply strategy.
[0032] Furthermore, step S4 of the present application also includes:
[0033] Based on the predetermined future time zone, the sales quantity of the first commodity is predicted according to the first commodity sales data partition to obtain the predicted sales quantity of the first commodity; based on the predetermined future time zone and the first commodity inventory characteristic information, the effective inventory quantity of the first commodity is calculated; it is determined whether the predicted sales quantity of the first commodity is greater than the effective inventory quantity of the first commodity; if the predicted sales quantity of the first commodity is greater than the effective inventory quantity of the first commodity, a first commodity supply reward adjustment factor is generated according to the predicted sales quantity of the first commodity and the effective inventory quantity of the first commodity; if the predicted sales quantity of the first commodity is less than / equal to the effective inventory quantity of the first commodity, a first commodity supply penalty adjustment factor is generated according to the predicted sales quantity of the first commodity and the effective inventory quantity of the first commodity; the first commodity supply reward adjustment factor or the first commodity supply penalty adjustment factor is added to the first commodity supply adjustment factor.
[0034] Specifically, the future sales quantity is predicted based on the sales data partition of the first commodity using methods such as time series analysis, regression analysis, and machine learning. The predicted sales quantity of the first commodity in the predetermined future time zone is obtained. Based on the inventory characteristic information of the first commodity, such as inventory turnover rate, in-transit inventory, safety stock, etc., the effective inventory quantity in the future time zone is calculated. Including the existing inventory level, expected arrival time, possible inventory loss, etc. The predicted sales quantity of the first commodity is compared with the effective inventory quantity to determine whether there is a potential risk of out-of-stock. If the predicted sales quantity is greater than the effective inventory quantity, it indicates that the demand is strong and the supply needs to be increased, so a supply reward adjustment factor is generated to encourage an increase in supply. If the predicted sales quantity is less than or equal to the effective inventory quantity, it indicates that the supply is sufficient or excessive and the supply needs to be reduced, so a supply penalty adjustment factor is generated to avoid inventory backlogs. The generated supply reward or penalty adjustment factor is integrated into the supply adjustment factor of the first commodity to influence future supply decisions. According to the updated supply adjustment factor, the supply chain links such as procurement, production, and logistics are adjusted to optimize the supply strategy.
[0035] Furthermore, the present application also includes:
[0036] According to the predetermined future time zone, a commodity sales backtracking time point cloud is constructed, wherein the commodity sales backtracking time point cloud includes multiple historical time zones with the same characteristics corresponding to the predetermined future time zone; according to the first commodity, a commodity sales backtracking main point cloud is constructed, wherein the commodity sales backtracking main point cloud includes multiple commodities with the same characteristics corresponding to the first commodity; commodity sales records are backtracked according to the commodity sales backtracking time point cloud and the commodity sales backtracking main point cloud to generate a sample set of commodity sales quantities; a central value calculation is performed according to the commodity sales quantity sample set to generate a first commodity-associated sales quantity; a sales quantity prediction channel is constructed, wherein the sales quantity prediction channel includes A commodity sales quantity prediction models, wherein A is a positive integer greater than 1; the first commodity-associated sales quantity and the first commodity sales data are respectively input into the A commodity sales quantity prediction models to generate A predicted sales quantity parameters; a mean rounding-up calculation is performed according to the A predicted sales quantity parameters to generate the first commodity predicted sales quantity.
[0037] Specifically, according to the characteristics of the predetermined future time zone, such as season, promotional activities, holidays, etc., multiple corresponding historical time zones with the same characteristics are selected. These historical time zones are combined into a time point cloud for subsequent sales record backtracking. According to the characteristics of the first product, such as category, brand, price range, etc., multiple products with the same characteristics are selected. These products with the same characteristics are combined into a main point cloud for subsequent sales record backtracking. The sales records in the time point cloud and the main point cloud are analyzed to generate a sample set of product sales quantities. Historical sales data are collected to form a sample set for subsequent central value calculation. The sales quantity in the sample set is counted, such as calculating the average, median, etc., to generate the associated sales quantity of the first product. Historical sales data are collected and analyzed, including sales volume, sales frequency, sales trend, etc. Appropriate demand forecasting methods are selected, such as time series analysis, seasonal analysis, trend analysis, etc. Machine learning algorithms, such as ARIMA, Prophet, random forest, etc., are used to train the data and build a sales quantity forecasting channel. The associated sales quantity and sales data partition of the first product are input as inputs to A prediction models respectively. Each model generates a predicted sales quantity parameter based on the input data. The average of the A predicted sales quantity parameters is calculated. The average is rounded up to get an actual sales quantity forecast value.
[0038] Furthermore, the present application also includes:
[0039] If the predicted sales quantity of the first commodity is greater than the effective inventory quantity of the first commodity, calculate the first commodity gap quantity according to the predicted sales quantity of the first commodity and the effective inventory quantity of the first commodity; collect the basic information of the first commodity to obtain the first commodity information; based on the first commodity supplier and the first commodity, collect the upper-level supplier information according to the commodity trading platform to obtain the first upper-level supplier data set; build a commodity supply scheduling model; input the first commodity gap quantity, the first commodity information and the first upper-level supplier data set into the commodity supply scheduling model to generate the first commodity supply scheduling decision; add the first commodity gap quantity and the first commodity supply scheduling decision to the first commodity supply reward adjustment factor.
[0040] Specifically, the predicted sales quantity of the first commodity is subtracted from the effective inventory quantity to obtain the gap quantity, that is, the inventory quantity that needs to be replenished. Collect detailed information about the first commodity, including commodity ID, name, specifications, price, production cost, etc. According to the commodity trading platform, collect information about the upper-level suppliers related to the first commodity, including supplier ID, name, supply capacity, delivery time, etc., to form the first upper-level supplier data set. Evaluate the current inventory level, including in-transit inventory, safety inventory, available inventory, etc. Determine inventory management strategies based on inventory levels, such as quantitative replenishment and regular replenishment. Evaluate the supplier's supply capacity, delivery time, transportation cost, etc. Collect relevant data from suppliers, including supply price, transportation time, minimum order quantity, etc. Select a suitable supply scheduling model based on business needs and available data, such as linear programming, integer programming, mixed integer programming, etc. Set the parameters of the model, including objective function, constraints, decision variables, etc. Use historical data to train the model to optimize the parameters of the model. Use a new data set to verify the model to ensure the accuracy and reliability of the model. Input the gap quantity, commodity information, and upper-level supplier data set as input data into the supply scheduling model. The model output includes replenishment strategies, procurement recommendations, production adjustments, etc., forming the supply scheduling decision for the first commodity. The gap quantity and supply scheduling decision are added to the first commodity supply reward adjustment factor to strengthen the effect of the supply decision and ensure that inventory can be replenished in time to avoid out-of-stock.
[0041] Furthermore, the present application also includes:
[0042] If the predicted sales quantity of the first commodity is less than / equal to the effective inventory quantity of the first commodity, calculate the redundant quantity of the first commodity according to the predicted sales quantity of the first commodity and the effective inventory quantity of the first commodity; perform storage cost analysis according to the redundant quantity of the first commodity to determine the redundant storage cost of the first commodity; perform transaction probability trend prediction according to the redundant quantity of the first commodity to generate redundant transaction probability trend information of the first commodity; perform commodity redundancy impact evaluation according to the redundant storage cost of the first commodity and the redundant transaction probability trend information of the first commodity to generate a redundant impact coefficient of the first commodity; determine whether the redundant impact coefficient of the first commodity is greater than / equal to a commodity redundancy impact threshold; if the redundant impact coefficient of the first commodity is greater than / equal to the commodity redundancy impact threshold, make a promotion decision for the first commodity based on the redundant quantity of the first commodity, and generate a supply penalty adjustment factor for the first commodity.
[0043] Specifically, the effective inventory quantity is subtracted from the predicted sales quantity to obtain the redundant quantity, that is, the inventory quantity that exceeds the market demand. Based on the redundant quantity, the costs incurred in storing these goods are calculated, including storage fees, insurance premiums, capital occupation costs, etc. Market data and historical sales records are analyzed to predict the probability trend of these redundant goods being sold in future time zones. The prediction results are organized into trend information to evaluate the impact of redundant goods on future sales. Combined with the redundant storage cost and transaction probability trend information, the overall impact of redundant goods on the supply chain is evaluated to generate the first commodity redundant impact coefficient. The redundant impact coefficient is compared with the pre-set commodity redundant impact threshold to determine whether action is needed. If the redundant impact coefficient is greater than or equal to the threshold, it indicates that the overstock problem is more serious and a promotion strategy needs to be formulated to reduce inventory. Based on the redundant quantity and promotion decision, the first commodity supply penalty adjustment factor is generated to adjust the future supply strategy to avoid inventory backlogs.
[0044] Furthermore, step S5 of the present application also includes:
[0045] A consumption trend forecast is performed based on the real-time user consumption data set to obtain a user consumption trend forecast result; feature association is performed based on the first commodity and the user consumption trend forecast result to obtain a first commodity consumption trend feature association result; a supply trend forecast is performed on the first commodity based on the first commodity consumption trend feature association result to generate a first commodity supply trend forecast result; and the first commodity supply adjustment factor is adjusted based on the first commodity supply trend forecast result to obtain the second commodity supply adjustment factor.
[0046] Specifically, real-time user consumption data sets are collected, including purchase records, browsing history, evaluation feedback, etc. Time series analysis, machine learning and other technologies are used to predict the trend of consumption data sets and obtain user consumption trend prediction results. Features related to the first product are extracted from the consumption data set, such as purchase frequency, purchase time, purchase amount, etc. These features are associated with the first product to understand the user's consumption trend for the first product. Based on the association results of the consumption trend features of the first product, a prediction model such as time series analysis and regression analysis is used to predict the supply trend of the first product. The supply trend prediction results of the first product are generated, including changes in supply and demand in the future time zone. According to the supply trend prediction results of the first product, the supply adjustment factor of the first product is adjusted to adapt to the supply demand in the future time zone. Since the adjustment of the supply adjustment factor of the first product may affect the supply strategy of other products, it is necessary to generate the supply adjustment factor of the second product to achieve overall optimization of the supply chain.
[0047] Furthermore, the present application also includes:
[0048] The user consumption trend prediction result is sent to the first commodity supplier to obtain supplier feedback data; the first commodity supply trend prediction result and the supplier feedback data are integrated to generate a commodity supply adjustment correction factor; the first commodity supply adjustment factor is optimized according to the commodity supply adjustment correction factor to obtain the second commodity supply adjustment factor.
[0049] Specifically, the user consumption trend forecast results are sent to the first commodity supplier through electronic data interchange, application programming interface API or other data transmission mechanisms. The supplier system receives and processes the forecast results. The supplier analyzes the forecast results and internal data, adjusts its supply strategy or provides feedback on the forecast results. Collect feedback data from suppliers, including the degree of recognition of the forecast results, possible market changes, supply chain adjustment plans, etc. Integrate the first commodity supply trend forecast results and supplier feedback data to form a comprehensive data set. Based on the integrated data, generate a commodity supply adjustment correction factor to adjust the forecast results and supply chain strategy. Use the commodity supply adjustment correction factor to optimize the supply adjustment factor of the first commodity to ensure that the supply strategy matches the market changes and supplier feedback. Since the adjustment of the supply adjustment factor of the first commodity may affect the supply strategy of other commodities, it is necessary to generate the supply adjustment factor of the second commodity to achieve overall optimization of the supply chain.
[0050] In summary, the method for providing commodity trading provided by this application has the following technical effects:
[0051] By connecting to a commodity trading platform, a real-time commodity sales data stream and a real-time commodity inventory data stream of a first commodity supplier are obtained; classification is performed according to the real-time commodity sales data stream to obtain a commodity sales data classification result, and a first commodity sales data partition corresponding to the first commodity is extracted based on the commodity sales data classification result; feature recognition is performed on the real-time commodity inventory data stream based on the first commodity to obtain first commodity inventory feature information; commodity supply reward and punishment factors are parsed based on the first commodity sales data partition and the first commodity inventory feature information based on a predetermined future time zone to generate a first commodity supply adjustment factor; a real-time user consumption data set is obtained according to the commodity trading platform, and association optimization is performed on the first commodity supply adjustment factor according to the real-time user consumption data set to generate a second commodity supply adjustment factor; the first commodity supplier manages commodity supply based on the second commodity supply adjustment factor, which effectively solves the technical problem of low accuracy and poor timeliness of commodity supply management of commodity suppliers due to lack of real-time data acquisition and processing capabilities in the prior art, and improves the accuracy and timeliness of commodity supply management of commodity suppliers through real-time data acquisition, classification processing, inventory feature recognition, forecasting analysis and integration of user consumption data.
[0052] Embodiment 2: Based on the method for providing commodity trading in the above embodiment, and with the same inventive concept, the present application also provides a system for providing commodity trading, as shown in the attached Figure 2 , the system for providing commodity trading comprises:
[0053] The data stream acquisition module 11 is used to connect to the commodity trading platform and obtain the real-time commodity sales data stream and real-time commodity inventory data stream of the first commodity supplier.
[0054] The data classification result acquisition module 12 is used to classify the real-time commodity sales data flow to obtain a commodity sales data classification result, and extract a first commodity sales data partition corresponding to the first commodity based on the commodity sales data classification result.
[0055] The feature recognition module 13 is used to perform feature recognition on the real-time commodity inventory data stream based on the first commodity to obtain first commodity inventory feature information.
[0056] The first supply adjustment factor generating module 14 is used to perform commodity supply reward and punishment factor analysis based on the predetermined future time zone, the first commodity sales data partition and the first commodity inventory characteristic information, and generate a first commodity supply adjustment factor.
[0057] The second supply adjustment factor generating module 15 is used to obtain a real-time user consumption data set according to the commodity trading platform, and to perform correlation optimization on the first commodity supply adjustment factor according to the real-time user consumption data set to generate a second commodity supply adjustment factor.
[0058] The supply management module 16 is configured for the first commodity supplier to perform commodity supply management based on the second commodity supply adjustment factor.
[0059] Furthermore, in the system for providing commodity trading, the first supply adjustment factor generating module 14 is also used for:
[0060] Based on the predetermined future time zone, the sales quantity of the first commodity is predicted according to the first commodity sales data partition to obtain the predicted sales quantity of the first commodity; based on the predetermined future time zone and the first commodity inventory characteristic information, the effective inventory quantity of the first commodity is calculated; it is determined whether the predicted sales quantity of the first commodity is greater than the effective inventory quantity of the first commodity; if the predicted sales quantity of the first commodity is greater than the effective inventory quantity of the first commodity, a first commodity supply reward adjustment factor is generated according to the predicted sales quantity of the first commodity and the effective inventory quantity of the first commodity; if the predicted sales quantity of the first commodity is less than / equal to the effective inventory quantity of the first commodity, a first commodity supply penalty adjustment factor is generated according to the predicted sales quantity of the first commodity and the effective inventory quantity of the first commodity; the first commodity supply reward adjustment factor or the first commodity supply penalty adjustment factor is added to the first commodity supply adjustment factor.
[0061] Furthermore, the system for providing commodity transactions further includes a first predicted sales volume generating module, which is used to:
[0062] According to the predetermined future time zone, a commodity sales backtracking time point cloud is constructed, wherein the commodity sales backtracking time point cloud includes multiple historical time zones with the same characteristics corresponding to the predetermined future time zone; according to the first commodity, a commodity sales backtracking main point cloud is constructed, wherein the commodity sales backtracking main point cloud includes multiple commodities with the same characteristics corresponding to the first commodity; commodity sales records are backtracked according to the commodity sales backtracking time point cloud and the commodity sales backtracking main point cloud to generate a sample set of commodity sales quantities; a central value calculation is performed according to the commodity sales quantity sample set to generate a first commodity-associated sales quantity; a sales quantity prediction channel is constructed, wherein the sales quantity prediction channel includes A commodity sales quantity prediction models, wherein A is a positive integer greater than 1; the first commodity-associated sales quantity and the first commodity sales data are respectively input into the A commodity sales quantity prediction models to generate A predicted sales quantity parameters; a mean rounding-up calculation is performed according to the A predicted sales quantity parameters to generate the first commodity predicted sales quantity.
[0063] Furthermore, the system for providing commodity transactions further includes a supply reward adjustment factor updating module, which is used to:
[0064] If the predicted sales quantity of the first commodity is greater than the effective inventory quantity of the first commodity, calculate the first commodity gap quantity according to the predicted sales quantity of the first commodity and the effective inventory quantity of the first commodity; collect the basic information of the first commodity to obtain the first commodity information; based on the first commodity supplier and the first commodity, collect the upper-level supplier information according to the commodity trading platform to obtain the first upper-level supplier data set; build a commodity supply scheduling model; input the first commodity gap quantity, the first commodity information and the first upper-level supplier data set into the commodity supply scheduling model to generate the first commodity supply scheduling decision; add the first commodity gap quantity and the first commodity supply scheduling decision to the first commodity supply reward adjustment factor.
[0065] Furthermore, the system for providing commodity transactions further includes a first supply penalty adjustment factor generation module, which is used to:
[0066] If the predicted sales quantity of the first commodity is less than / equal to the effective inventory quantity of the first commodity, calculate the redundant quantity of the first commodity according to the predicted sales quantity of the first commodity and the effective inventory quantity of the first commodity; perform storage cost analysis according to the redundant quantity of the first commodity to determine the redundant storage cost of the first commodity; perform transaction probability trend prediction according to the redundant quantity of the first commodity to generate redundant transaction probability trend information of the first commodity; perform commodity redundancy impact evaluation according to the redundant storage cost of the first commodity and the redundant transaction probability trend information of the first commodity to generate a redundant impact coefficient of the first commodity; determine whether the redundant impact coefficient of the first commodity is greater than / equal to a commodity redundancy impact threshold; if the redundant impact coefficient of the first commodity is greater than / equal to the commodity redundancy impact threshold, make a promotion decision for the first commodity based on the redundant quantity of the first commodity, and generate a supply penalty adjustment factor for the first commodity.
[0067] Furthermore, the second supply adjustment factor generating module 15 in the system for providing commodity trading is also used for:
[0068] A consumption trend forecast is performed based on the real-time user consumption data set to obtain a user consumption trend forecast result; feature association is performed based on the first commodity and the user consumption trend forecast result to obtain a first commodity consumption trend feature association result; a supply trend forecast is performed on the first commodity based on the first commodity consumption trend feature association result to generate a first commodity supply trend forecast result; and the first commodity supply adjustment factor is adjusted based on the first commodity supply trend forecast result to obtain the second commodity supply adjustment factor.
[0069] Furthermore, the system for providing commodity transactions further includes an adjustment factor optimization module, which is used to:
[0070] The user consumption trend prediction result is sent to the first commodity supplier to obtain supplier feedback data; the first commodity supply trend prediction result and the supplier feedback data are integrated to generate a commodity supply adjustment correction factor; the first commodity supply adjustment factor is optimized according to the commodity supply adjustment correction factor to obtain the second commodity supply adjustment factor.
[0071] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1 The method and specific examples of providing commodity transactions in the first embodiment are also applicable to the system of providing commodity transactions in the present embodiment. Through the detailed description of the method of providing commodity transactions, those skilled in the art can clearly understand the system of providing commodity transactions in the present embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.
[0072] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
[0073] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.
Claims
1. A method for providing commodity trading, It is characterized in that The method for providing commodity trading comprises: Connect to the commodity trading platform to obtain the real-time commodity sales data stream and real-time commodity inventory data stream of the first commodity supplier; Classifying the real-time commodity sales data stream to obtain a commodity sales data classification result, and extracting a first commodity sales data partition corresponding to the first commodity based on the commodity sales data classification result; Based on the first commodity, feature recognition is performed on the real-time commodity inventory data stream to obtain first commodity inventory feature information; Based on the predetermined future time zone, performing commodity supply reward and punishment factor analysis according to the first commodity sales data partition and the first commodity inventory characteristic information, and generating a first commodity supply adjustment factor; According to the commodity trading platform, a real-time user consumption data set is obtained, and the first commodity supply adjustment factor is optimized according to the real-time user consumption data set to generate a second commodity supply adjustment factor; The first commodity supplier performs commodity supply management based on the second commodity supply adjustment factor; Wherein, based on the predetermined future time zone, the commodity supply reward and punishment factor is parsed according to the first commodity sales data partition and the first commodity inventory characteristic information to generate the first commodity supply adjustment factor, including: Based on the predetermined future time zone, predicting the sales quantity of the first commodity according to the first commodity sales data partition, to obtain the predicted sales quantity of the first commodity; Calculating the effective inventory quantity of the first commodity based on the predetermined future time zone and the first commodity inventory characteristic information; Determining whether the predicted sales quantity of the first commodity is greater than the effective inventory quantity of the first commodity; If the predicted sales quantity of the first commodity is greater than the effective inventory quantity of the first commodity, generating a first commodity supply reward adjustment factor according to the predicted sales quantity of the first commodity and the effective inventory quantity of the first commodity; If the predicted sales quantity of the first commodity is less than or equal to the effective inventory quantity of the first commodity, generating a first commodity supply penalty adjustment factor according to the predicted sales quantity of the first commodity and the effective inventory quantity of the first commodity; adding the first commodity supply reward adjustment factor or the first commodity supply penalty adjustment factor to the first commodity supply adjustment factor; The step of performing correlation optimization on the first commodity supply adjustment factor according to the real-time user consumption data set to generate the second commodity supply adjustment factor includes: Perform consumption trend prediction based on the real-time user consumption data set to obtain a user consumption trend prediction result; Performing feature association based on the first product and the user consumption trend prediction result to obtain a first product consumption trend feature association result; According to the result of associating the consumption trend feature of the first commodity, a supply trend prediction of the first commodity is performed to generate a supply trend prediction result of the first commodity; Adjust the first commodity supply adjustment factor according to the first commodity supply trend forecast result to obtain the second commodity supply adjustment factor; The step of adjusting the first commodity supply adjustment factor according to the first commodity supply trend prediction result to obtain the second commodity supply adjustment factor includes: Sending the user consumption trend prediction result to the first commodity supplier to obtain supplier feedback data; Integrate the first commodity supply trend forecast result and the supplier feedback data to generate a commodity supply adjustment correction factor; The first commodity supply adjustment factor is optimized according to the commodity supply adjustment correction factor to obtain the second commodity supply adjustment factor.
2. A method for providing commodity trading as claimed in claim 1, It is characterized in that Based on the predetermined future time zone, predicting the sales quantity of the first commodity according to the first commodity sales data partition to obtain the predicted sales quantity of the first commodity includes: According to the predetermined future time zone, construct a commodity sales retrospective time point cloud, wherein the commodity sales retrospective time point cloud includes a plurality of historical time zones with the same characteristics corresponding to the predetermined future time zone; According to the first commodity, construct a commodity sales tracing main point cloud, wherein the commodity sales tracing main point cloud includes a plurality of commodities with the same characteristics corresponding to the first commodity; Backtracking commodity sales records according to the commodity sales backtracking time point cloud and the commodity sales backtracking subject point cloud to generate a commodity sales quantity sample set; Performing concentrated value calculation based on the commodity sales quantity sample set to generate the first commodity associated sales quantity; Constructing a sales quantity prediction channel, wherein the sales quantity prediction channel includes A commodity sales quantity prediction models, wherein A is a positive integer greater than 1; Inputting the first commodity associated sales quantity and the first commodity sales data partition into the A commodity sales quantity prediction models to generate A predicted sales quantity parameters; The predicted sales quantity of the first commodity is generated by rounding up the mean of the A predicted sales quantity parameters.
3. A method for providing commodity trading as claimed in claim 1, It is characterized in that If the predicted sales quantity of the first commodity is greater than the effective inventory quantity of the first commodity, generating a first commodity supply reward adjustment factor according to the predicted sales quantity of the first commodity and the effective inventory quantity of the first commodity, including: If the predicted sales quantity of the first commodity is greater than the effective inventory quantity of the first commodity, calculate the shortage quantity of the first commodity according to the predicted sales quantity of the first commodity and the effective inventory quantity of the first commodity; Collecting basic information of the first product to obtain first product information; Based on the first commodity supplier and the first commodity, collecting upper-level supplier information according to the commodity trading platform to obtain a first upper-level supplier data set; Build a commodity supply scheduling model; Inputting the first commodity shortage quantity, the first commodity information and the first upper-level supplier data set into the commodity supply scheduling model to generate a first commodity supply scheduling decision; The first commodity shortage quantity and the first commodity supply scheduling decision are added to the first commodity supply reward adjustment factor.
4. A method for providing commodity trading as claimed in claim 1, It is characterized in that If the predicted sales quantity of the first commodity is less than or equal to the effective inventory quantity of the first commodity, a first commodity supply penalty adjustment factor is generated according to the predicted sales quantity of the first commodity and the effective inventory quantity of the first commodity, including: If the predicted sales quantity of the first commodity is less than or equal to the effective inventory quantity of the first commodity, calculating the redundant quantity of the first commodity according to the predicted sales quantity of the first commodity and the effective inventory quantity of the first commodity; Performing a storage cost analysis based on the redundant quantity of the first commodity to determine the redundant storage cost of the first commodity; Performing transaction probability trend prediction based on the redundant quantity of the first commodity to generate redundant transaction probability trend information of the first commodity; Performing a commodity redundancy impact evaluation based on the redundant storage cost of the first commodity and the redundant transaction probability trend information of the first commodity to generate a first commodity redundancy impact coefficient; Determining whether the first commodity redundancy impact coefficient is greater than or equal to a commodity redundancy impact threshold; If the redundancy impact coefficient of the first commodity is greater than or equal to the redundancy impact threshold of the commodity, a promotion decision is made for the first commodity based on the redundant quantity of the first commodity, and a supply penalty adjustment factor of the first commodity is generated.
5. A system for providing commodity trading, It is characterized in that Steps for implementing a method for providing commodity transactions as described in any one of claims 1 to 4, wherein the system for providing commodity transactions comprises: A data stream acquisition module is used to connect to the commodity trading platform to obtain the real-time commodity sales data stream and real-time commodity inventory data stream of the first commodity supplier; a data classification result acquisition module, configured to classify the real-time commodity sales data stream to obtain a commodity sales data classification result, and extract a first commodity sales data partition corresponding to the first commodity based on the commodity sales data classification result; a feature recognition module, configured to perform feature recognition on the real-time commodity inventory data stream based on the first commodity to obtain first commodity inventory feature information; A first supply adjustment factor generation module is used to perform commodity supply reward and punishment factor analysis based on a predetermined future time zone and the first commodity sales data partition and the first commodity inventory feature information to generate a first commodity supply adjustment factor; a second supply adjustment factor generating module, configured to obtain a real-time user consumption data set according to the commodity trading platform, and to perform correlation optimization on the first commodity supply adjustment factor according to the real-time user consumption data set to generate a second commodity supply adjustment factor; A supply management module, wherein the first commodity supplier performs commodity supply management based on the second commodity supply adjustment factor.
