Goods intelligent matching method and equipment based on e-commerce ERP (Enterprise Resource Planning) system, medium and product

By building user portraits and product recommendations in the e-commerce ERP system, combined with multi-dimensional characteristic analysis, the problem of inefficient matching of traditional goods is solved, personalized recommendations and market trend predictions are realized, and consumer satisfaction and merchant operation efficiency are improved. .

CN118982399APending Publication Date: 2024-11-19JIANGSU BANGBANGHU NETWORK CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202410960223.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-17
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

Traditional e-commerce ERP systems rely on simple rules when matching goods, resulting in inefficiency and frequent errors, which cannot meet the rapidly changing market demand.

Method used

By obtaining consumer data, building user portraits, conducting product recommendations and demand analysis, combining merchant data for multi-dimensional characteristic analysis, providing personalized recommendations and inventory recommendations, and optimizing product procurement and inventory management.

Benefits of technology

It improves consumer satisfaction and purchasing intention, enhances merchants' ability to predict market trends, optimizes product procurement and inventory management, and improves operational efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118982399A_ABST
    Figure CN118982399A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of e-commerce ERP systems, in particular to an e-commerce ERP system-based goods intelligent matching method and device, a medium and a product, and the method comprises the steps: carrying out the user portrait construction based on consumption data, obtaining a target user portrait, carrying out the goods recommendation based on the target user portrait, determining a target goods list, and carrying out the goods recommendation based on the target goods list. And sending the target goods list to the consumer terminal. And then, demand analysis is performed based on the target goods list corresponding to each consumer, and potential goods demands are determined. The consumption habits, preferences and demands of the consumers can be accurately understood by deeply analyzing the target user portraits, so that personalized goods recommendation is provided, and the satisfaction and purchase willingness of the consumers are remarkably improved. Meanwhile, multi-dimensional characteristic analysis is carried out based on the goods data and the goods potential demands, goods storage and sale suggestions are determined, and the goods storage and sale suggestions are sent to a merchant terminal, so that a merchant optimizes cooperation among goods purchase, stock and export sales.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of e-commerce ERP systems, and in particular to methods, devices, media and products for intelligent matching of goods based on e-commerce ERP systems. Background Art

[0002] Traditional e-commerce ERP systems integrate the sales, inventory, logistics and other resources of enterprises to a certain extent. In e-commerce ERP systems, intelligent product matching methods have become a key technology to enhance the competitiveness of e-commerce platforms, improve customer satisfaction and operational efficiency. However, with the continuous advancement of big data and artificial intelligence technologies, traditional product matching methods can no longer meet the needs of modern e-commerce businesses.

[0003] Traditional e-commerce ERP systems mainly rely on pre-set simple rules when matching goods. However, in complex e-commerce business scenarios, product matching using simple rules is inefficient, prone to errors, and cannot meet rapidly changing market demands.

[0004] Therefore, how to solve the above technical problems is an urgent problem to be solved by technical personnel in this field. Summary of the invention

[0005] The purpose of this application is to provide a method, device, medium and product for intelligent matching of goods based on an e-commerce ERP system to solve at least one of the above technical problems.

[0006] The above invention objectives of the present application are achieved through the following technical solutions: In the first aspect, the present application provides a method for intelligent matching of goods based on an e-commerce ERP system, which adopts the following technical solutions: A method for intelligent matching of goods based on an e-commerce ERP system, comprising: Obtaining consumption data corresponding to the consumer, and constructing a user profile based on the consumption data to obtain a target user profile; Recommend products based on the target user portrait, determine a target product list, and send the target product list to the consumer terminal to achieve personalized product recommendation, wherein the target product list is a collection of products that meet the consumer's consumption habits; Conducting demand analysis based on the target product list corresponding to each consumer to determine potential demand for products, wherein the potential demand for products helps to understand the consumer's product demand and market trends; The corresponding product data of the merchant is obtained, and a multi-dimensional characteristic analysis is performed based on the product data and the potential demand for the product to determine product inventory and sales suggestions, and the product inventory and sales suggestions are sent to the merchant terminal to facilitate the merchant to optimize the coordination between product procurement, inventory and export.

[0007] By adopting the above technical solution, a user portrait is constructed based on consumption data to obtain a target user portrait. Then, based on the target user portrait, product recommendations are made, a target product list is determined, and the target product list is sent to the consumer terminal to achieve personalized product recommendations. Furthermore, a demand analysis is performed based on the target product list corresponding to each consumer to determine the potential demand for the product. By deeply analyzing the target user portrait, the consumer's consumption habits, preferences and needs can be accurately understood, thereby providing personalized product recommendations and significantly improving consumer satisfaction and willingness to purchase. At the same time, a multi-dimensional characteristic analysis is performed based on product data and potential demand for products to determine product inventory and sales recommendations, and the product inventory and sales recommendations are sent to the merchant terminal to facilitate the merchant to optimize the coordination between product procurement, inventory and export.

[0008] In a preferred example, the present application may be further configured as follows: constructing a user profile based on the consumption data to obtain a target user profile includes: Extract key features based on the consumption data to determine key consumption features, wherein the key consumption features include: preferred product type, search preference keywords, purchase frequency, and purchase amount; Perform group classification based on the key consumption characteristics to obtain user group labels; A visual portrait is constructed based on the key consumption characteristics and the user group labels to obtain a structured target user portrait.

[0009] In a preferred example, the present application may be further configured as follows: the product recommendation based on the target user portrait and the determination of the target product list include: Perform collaborative filtering based on the target user portrait to determine a first product list, wherein the collaborative filtering includes: user collaborative filtering and item collaborative filtering; Acquire product data, and match products based on product features in the product data and the key consumption features to determine a second product list; Obtaining a correspondence between the user portrait and the product portrait corresponding to the product list, and determining a third product list based on the correspondence between the target user portrait and the product portrait; The first commodity list, the second commodity list and the third commodity list are integrated to obtain a target commodity list.

[0010] In a preferred example, the present application may be further configured as follows: performing demand analysis based on the target product list corresponding to each consumer to determine the potential demand for the product includes: Based on the target product list and key consumption characteristics corresponding to the target consumer, the product demand is predicted to determine the estimated product demand, wherein the target consumer is any one consumer; Comprehensively forecast the market trend based on the demand for goods corresponding to each target consumer and determine the estimated development trend; The estimated demand for goods and the estimated development trend are combined to determine the potential demand for goods.

[0011] In a preferred example, the present application can be further configured as follows: the product data includes: historical sales data, inventory data and purchase data, The multi-dimensional characteristic analysis based on the product data and the potential demand for the product to determine the product inventory and sales suggestions includes: Perform supply and sales analysis based on the inventory data and purchase data in the product data and the estimated product demand in the potential demand for the product to determine a first inventory and sales suggestion; Performing product sales analysis based on the estimated development trend of the potential demand for the product and the historical sales data in the product data to determine a second inventory sales suggestion; The first inventory and sales suggestion and the second inventory and sales suggestion are combined to determine the inventory and sales suggestion for the goods.

[0012] In a preferred example, the present application may be further configured as follows: sending the target product list to the consumer terminal includes: Acquire a virtual three-dimensional model corresponding to each target product in the target product list, and associate the target product in the target product list with the virtual three-dimensional model to determine an association relationship; The virtual three-dimensional model, each of the target products and each of the virtual three-dimensional models are sent to a consumer terminal to improve the consumer's shopping experience.

[0013] In a second aspect, the present application provides an electronic device, which adopts the following technical solution: at least one processor; Memory; At least one application, wherein at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the above-mentioned product intelligent matching method based on the e-commerce ERP system.

[0014] In a third aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium stores a computer program, which, when executed in a computer, causes the computer to execute the above-mentioned intelligent product matching method based on an e-commerce ERP system.

[0015] In a fourth aspect, the present application provides a computer program product, which adopts the following technical solution: A computer program product includes a computer program, which, when executed by a processor, implements the above-mentioned intelligent product matching method based on the e-commerce ERP system.

[0016] In summary, the present application includes at least one of the following beneficial technical effects: Based on consumption data, a user profile is constructed to obtain a target user profile. Then, based on the target user profile, product recommendations are made, a target product list is determined, and the target product list is sent to the consumer terminal to achieve personalized product recommendations. Furthermore, a demand analysis is performed based on the target product list corresponding to each consumer to determine the potential demand for the product. By deeply analyzing the target user profile, consumers' consumption habits, preferences, and needs can be accurately understood, thereby providing personalized product recommendations and significantly improving consumer satisfaction and willingness to purchase. At the same time, a multi-dimensional characteristic analysis is performed based on product data and potential demand for products to determine product inventory and sales recommendations, which are then sent to the merchant terminal to help merchants optimize the coordination between product procurement, inventory, and export.

[0017] Based on consumption data, key features are extracted to determine key consumption features. Then, groups are classified based on key consumption features to obtain user group labels. Finally, a visual portrait is constructed based on key consumption features and user group labels to obtain a structured target user portrait. Building a target user portrait provides an important basis for subsequent product recommendations, and can improve consumer satisfaction and loyalty through precision marketing and high-quality services. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a flow chart of a method for intelligently matching goods based on an e-commerce ERP system according to one embodiment of the present application; Figure 2 This is a structural diagram of a product intelligent matching device based on an e-commerce ERP system according to one embodiment of the present application; Figure 3 It is a structural schematic diagram of an electronic device according to one embodiment of the present application. DETAILED DESCRIPTION

[0019] The following combination Figures 1 to 3 This application is described in further detail.

[0020] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, a person skilled in the art may make non-creative modifications to the present embodiment as needed, but such modifications are protected by the patent law as long as they are within the scope of the present application.

[0021] In order to make the purpose, technical scheme and advantages of the embodiment of the present application clearer, the technical scheme in the embodiment of the present application will be clearly and completely described in conjunction with the drawings in the embodiment of the present application. Obviously, the described embodiment is a part of the embodiment of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application. It should be noted that in the optional embodiments of the present application, the object information and other related data involved, when the embodiments in the present application are applied to specific products or technologies, need to obtain the permission or consent of the object, and the collection, use and processing of the relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions. In other words, if the data related to the object is involved in the embodiment of the present application, it needs to be obtained through the authorization and consent of the object, the authorization and consent of the relevant departments, and in accordance with the relevant laws, regulations and standards of the country and region. If personal information is involved in the embodiment, the acquisition of all personal information needs to obtain the consent of the individual. If sensitive information is involved, the separate consent of the information subject needs to be obtained, and the embodiment also needs to be implemented with the authorization and consent of the object.

[0022] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0023] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0024] The embodiment of the present application provides a method for intelligent matching of goods based on an e-commerce ERP system, which is executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The embodiment of the present application is not limited here, such as Figure 1 As shown, the method includes step S101, step S102, step S103 and step S104, wherein: Step S101: Obtain consumption data corresponding to the consumer, and construct a user profile based on the consumption data to obtain a target user profile.

[0025] For the embodiment of the present application, consumers will search and purchase goods through the consumer terminal, so that the consumer's consumption data will be stored in the consumer terminal, and the consumer terminal and the electronic device communicate wirelessly, so that the electronic device can obtain the corresponding consumption data of the consumer, wherein the consumption data includes but is not limited to: the consumer's personal information (for example, age, gender, occupation, region), purchase history, search behavior and browsing behavior and other data. Then, a user portrait is constructed based on the consumption data to obtain a target user portrait, wherein the target user portrait is used to characterize the consumer's shopping habits, preferences, needs, etc., and provide an important basis for subsequent product recommendations. Through precision marketing and high-quality services, the satisfaction and loyalty of consumers can be improved. There are many ways to construct user portraits, which are no longer limited in the embodiment of the present application. In an achievable way, key features are extracted based on consumption data to determine key consumption features, wherein the key consumption features include: preferred product type, search tendency keywords, purchase frequency, and purchase amount; group classification is performed based on key consumption features to obtain user group labels; visual portraits are constructed based on key consumption features and user group labels to obtain structured target user portraits.

[0026] Step S102: Recommend products based on the target user portrait, determine a target product list, and send the target product list to the consumer terminal to achieve personalized product recommendation, wherein the target product list is a collection of products that meet the consumer's consumption habits.

[0027] For the embodiment of the present application, the target user portrait includes the consumer's user group marker and key consumption characteristics that characterize consumption characteristics. By deeply analyzing the target user portrait, the consumer's consumption habits, preferences and needs can be accurately understood, thereby providing personalized product recommendations, significantly improving consumer satisfaction and purchase intention. For the operation of using the target user portrait for product recommendation, there are multiple achievable methods. In one achievable method, collaborative filtering is performed based on the target user portrait to determine the first product list, wherein the collaborative filtering includes: user collaborative filtering and item collaborative filtering; obtaining product data, and matching products based on product characteristics in the product data and key consumption characteristics to determine the second product list; obtaining the corresponding relationship between the user portrait and the product portrait corresponding to the product list, and determining the third product list based on the corresponding relationship between the target user portrait and the product portrait; and combining the first product list, the second product list and the third product list to obtain the target product list. Of course, you can also use the product recommendation model to predict consumers' future shopping behavior. The product recommendation model is obtained by iteratively training the deep learning model based on the target user portrait and historical consumption data. It can automatically and accurately predict a variety of products that are highly matched with the target user portrait. Using the target user portrait to recommend products greatly improves the efficiency of product matching to meet the rapidly changing market demand.

[0028] Then, the target product list is sent to the consumer terminal, so that a product set that satisfies the consumer's consumption habits is recommended to the consumer at the consumer terminal. Of course, the target products displayed at the consumer terminal can be displayed in order according to the degree of matching with the consumer's consumption habits. Of course, in order to enhance the consumer's shopping experience, virtual reality technology is used to present the target products recommended to the consumer, so that the consumer can intuitively view and experience the appearance, structure and function of the target products. The use of three-dimensional visualization can attract the consumer's attention more than traditional pictures or text descriptions, and improve the shopping experience.

[0029] Step S103: Perform demand analysis based on the target product list corresponding to each consumer to determine potential demand for products, wherein the potential demand for products helps to understand consumers' demand for products and market trends.

[0030] For the embodiments of the present application, understanding the potential needs of consumers can help merchants better predict future market demand, thereby optimizing the coordination between product procurement, inventory, and export, and avoiding shortages or overstocking of inventory. Therefore, based on the target product list corresponding to each consumer, a demand analysis is performed to determine the potential demand for the product. There are many achievable methods for the demand analysis method, which are no longer limited in the embodiments of the present application. In one achievable method, a product demand forecast is performed based on the target product list corresponding to the target consumer and key consumer characteristics to determine the estimated demand for the product, wherein the target consumer is any one consumer; a market trend forecast is performed based on the product demand corresponding to each target consumer to determine the estimated development trend; the estimated product demand and the estimated development trend are combined to determine the potential demand for the product.

[0031] Step S104: Obtain the product data corresponding to the merchant, and perform multi-dimensional characteristic analysis based on the product data and potential demand for the product, determine product inventory and sales suggestions, and send the product inventory and sales suggestions to the merchant terminal to facilitate the merchant to optimize the coordination between product procurement, inventory and export.

[0032] For the embodiment of the present application, the merchant will manage the goods through the merchant terminal, so that the merchant data will be stored in the merchant terminal. The merchant terminal and the electronic device communicate wirelessly, so that the electronic device can obtain the goods data corresponding to the merchant, wherein the goods data includes but is not limited to: historical sales data, inventory data, goods characteristics (for example, goods category, brand, sales amount, etc.), procurement data and goods evaluation information. There are many ways to analyze multidimensional characteristics, and the embodiment of the present application is no longer limited. In one achievable method, supply and marketing analysis is performed based on the inventory data and procurement data in the goods data, and the estimated demand for goods in the potential demand for goods, and the first inventory and sales suggestion is determined; the goods sales analysis is performed based on the estimated development trend in the potential demand for goods and the historical sales data in the goods data, and the second inventory and sales suggestion is determined; the first inventory and sales suggestion is determined by combining the first inventory and sales suggestion and the second inventory and sales suggestion.

[0033] In another achievable manner, multi-step operations are performed based on product data to facilitate in-depth analysis of product data from multiple dimensions. The multi-step operations include but are not limited to: slicing, dicing, rolling up, drilling down and rotation operations, wherein the slicing operation is used to select a certain dimension to perform data analysis on product data, for example, slicing by product category, region or time to observe the sales of products under different dimensions; the dicing operation is used to perform selection operations on multiple dimensions, for example, dicing by product category and region at the same time to analyze sales data under different combinations; the rolling up operation is used to perform aggregation operations in the data cube to observe more generalized data, for example, rolling up from daily sales data to monthly or annual sales data; the drilling down operation is used to observe product data in more detail by introducing new dimensions, for example, drilling down from monthly sales data to sales data of a specific week or day; the rotation operation is used to rotate product data to data from different perspectives, for example, transformation of rows and columns to help observe and analyze product data from different angles. Furthermore, based on the analysis results of each dimension in the multi-step operation and the potential demand for goods, the inventory and sales suggestions for goods are determined, wherein the inventory and sales suggestions for goods include but are not limited to: adjusting inventory levels, optimizing procurement plans, adjusting sales strategies, etc. The corresponding relationship between the analysis results of each dimension, the potential demand for goods, and the inventory and sales suggestions for goods is verified by those skilled in the art based on a large number of experiments, and users can make adjustments according to actual needs.

[0034] It can be seen that in the embodiment of the present application, a user portrait is constructed based on consumption data to obtain a target user portrait, and then, based on the target user portrait, product recommendations are made, a target product list is determined, and the target product list is sent to the consumer terminal to achieve personalized product recommendations. Furthermore, a demand analysis is performed based on the target product list corresponding to each consumer to determine the potential demand for the product. By in-depth analysis of the target user portrait, the consumer's consumption habits, preferences, and needs can be accurately understood, thereby providing personalized product recommendations and significantly improving consumer satisfaction and willingness to purchase. At the same time, a multi-dimensional characteristic analysis is performed based on product data and potential demand for products to determine product inventory and sales recommendations, and the product inventory and sales recommendations are sent to the merchant terminal to facilitate the merchant to optimize the coordination between product procurement, inventory, and export.

[0035] Furthermore, in order to achieve precise marketing and high-quality services, and to improve consumer satisfaction and loyalty, in the embodiment of the present application, a user profile is constructed based on consumption data to obtain a target user profile, including: Extract key features based on consumption data and determine key consumption features, where key consumption features include: preferred product type, search preference keywords, purchase frequency, and purchase amount; Classify groups based on key consumption characteristics and obtain user group labels; Build a visual portrait based on key consumption characteristics and user group labels to obtain a structured target user portrait.

[0036] For the embodiments of the present application, a structured target user portrait is obtained by constructing a user portrait based on consumption data, which can more intuitively display the consumer's shopping habits, preferences, needs, etc., helping merchants to better understand consumers, achieve accurate market insights, refined user group classification and intuitive user portrait construction, and provide an important basis for subsequent product recommendations. Consumer satisfaction and loyalty can be improved through precision marketing and high-quality services.

[0037] Specifically, key features are extracted based on consumption data to determine key consumption features, wherein the key consumption features include but are not limited to: preferred product types, search tendency keywords, purchase frequency, and purchase amount. For determining the preferred product types, analyze the consumer's purchase history, count the types of products each consumer has purchased, and use a clustering algorithm to group the product types, and select the group with the most purchased products as the preferred product type. For search tendency keywords, extract keywords from the search behavior records in the consumption data, and use text mining technology to analyze the frequency and relevance of keywords to determine the corresponding search tendency keywords of the consumer. For purchase frequency, calculate the purchase frequency of consumers within a certain period of time based on the purchase history in the consumption data, so that consumers can be divided into different consumer groups according to the purchase frequency, such as high-frequency buyers and low-frequency buyers. For purchase amount, extract the purchase amount of each consumer based on the purchase history in the consumption data, and calculate indicators such as the total purchase amount and average purchase amount of the consumer. The purchase amount is used to analyze the purchasing power and consumption habits of consumers. Then, the group classification is performed based on the key consumption characteristics to obtain the user group label, that is, the key consumption characteristics are classified using the classification algorithm to determine the user group label, wherein the user group label should be able to clearly and accurately reflect the main consumption characteristics and behavior patterns of the group, such as "high-frequency shoppers", "fashion lovers", and "price-sensitive". Finally, a visual portrait is constructed based on the key consumption characteristics and user group labels to obtain a structured target user portrait, wherein the structured target user portrait can be represented by charts such as user information cards, radar charts, word cloud charts, and bar charts. Diversified user portraits can adapt to different analysis needs and display scenarios. For example, the target user portrait is presented in the form of user information cards, and the key consumption characteristics and user group labels are presented in the form of cards; radar charts are used to display the multi-dimensional characteristics of consumers, such as purchase frequency, price sensitivity, fashion, etc.; bar charts are used to display the purchase frequency or consumption amount of users in different commodity categories, intuitively displaying the preferences and purchasing power of consumers in different commodity categories, which helps to understand the purchasing habits of users.

[0038] It can be seen that in the embodiment of the present application, key features are extracted based on consumption data to determine key consumption features, and then group classification is performed based on the key consumption features to obtain user group labels. Finally, a visual portrait is constructed based on the key consumption features and user group labels to obtain a structured target user portrait. Building a target user portrait provides an important basis for subsequent product recommendations, and can improve consumer satisfaction and loyalty through precision marketing and high-quality services.

[0039] Furthermore, in order to improve the accuracy and diversity of recommended products, in an embodiment of the present application, product recommendations are made based on the target user portrait, and a target product list is determined, including: Perform collaborative filtering based on the target user portrait to determine the first product list, wherein the collaborative filtering includes: user collaborative filtering and item collaborative filtering; Acquire product data, and match products based on product features in the product data and key consumption features to determine a second product list; Obtaining a correspondence between the user portrait and the product portrait corresponding to the product list, and determining a third product list based on the correspondence between the target user portrait and the product portrait; The first commodity list, the second commodity list and the third commodity list are combined to obtain a target commodity list.

[0040] For the embodiments of the present application, in order to improve the accuracy and diversity of recommended products, in the process of performing product recommendation operations, multiple methods are used to screen target products that match the target user profile, and the results screened by multiple methods are combined to finally determine the target product list.

[0041] Specifically, collaborative filtering is performed based on the target user portrait to determine the first product list. Collaborative filtering includes user collaborative filtering and item collaborative filtering. User collaborative filtering is used to recommend products that the target user may be interested in based on the purchase history of similar consumers. Item collaborative filtering is used to recommend products that are similar to the products that the consumer has purchased and may be interested in based on the products that the consumer has purchased. The product features in the product data are used to record detailed information about the products, including but not limited to: product category, brand, sales amount, product description, etc. Then, the product features in the product data are matched with the key consumption features to determine the second product list. For the product matching operation, the key consumption features of the consumer are traversed and matched with the product features corresponding to each product, and the similarity between the product features and the key consumption features is calculated. Based on the matched similarity values, the products that meet the consumer's needs are screened out and put into the candidate list. The products in the candidate list are sorted to finally obtain the second product list. The candidate list can be sorted according to factors such as the matching degree of the product, user evaluation and sales volume. The electronic device pre-stores the corresponding relationship between the user portrait and the product portrait corresponding to the product list. The corresponding relationship between the product portrait is pre-set by a person skilled in the art and stored in the electronic device. Through algorithms such as K-means and hierarchical clustering, users are grouped according to similar shopping habits, interest preferences and other features, and a specific recommendation list is generated for each group of users to obtain the corresponding relationship between the product portraits, so that the third product list can be determined directly based on the corresponding relationship between the target user portrait and the product portrait. Finally, the first product list, the second product list and the third product list are combined to obtain the target product list, wherein the target product list is a collection of three product lists with duplicate products removed.

[0042] It can be seen that in the embodiment of the present application, collaborative filtering is performed based on the target user portrait to determine the first product list, wherein collaborative filtering includes: user collaborative filtering and item collaborative filtering. Then, the product features in the product data are matched with the key consumption features to determine the second product list. Furthermore, based on the correspondence between the target user portrait, the user portrait and the product portrait corresponding to the product list, the third product list is determined. The first product list, the second product list and the third product list are combined to obtain the target product list. A variety of methods are used to screen the target products that match the target user portrait, thereby improving the accuracy and diversity of the recommended products.

[0043] Furthermore, in order to ensure that goods can be supplied in a timely manner when market demand increases and to avoid inventory backlogs or out-of-stock situations, in the embodiment of the present application, demand analysis is performed based on the target product list corresponding to each consumer to determine the potential demand for the product, including: Based on the target product list and key consumption characteristics corresponding to the target consumer, the product demand is predicted to determine the estimated product demand, wherein the target consumer is any consumer; Comprehensively forecast the market trend based on the demand for goods corresponding to each target consumer and determine the estimated development trend; Comprehensively estimate the demand for goods and the estimated development trend to determine the potential demand for goods.

[0044] For the embodiments of the present application, in the process of performing demand analysis, forecasts are made on product demand and market trends so as to accurately predict the potential demand for products, which helps companies plan production, inventory and marketing strategies in advance, ensuring that products can be supplied in a timely manner when market demand increases, and avoiding inventory backlogs or out-of-stock situations.

[0045] Specifically, the demand for goods is predicted based on the target goods list and key consumption characteristics corresponding to the target consumer, and the estimated demand for goods is determined, wherein the target consumer is any consumer. There are many ways to predict the demand for goods. In one feasible way, a goods demand prediction model is obtained, wherein the goods demand prediction model uses historical sales data, historical consumption data and key consumer characteristics as training data, and uses a validation data set to verify the model and evaluate the prediction performance of the model. Then, the target goods list and key consumption characteristics are input into the trained goods demand prediction model, and the model will output the demand prediction value corresponding to each target goods in the target goods list. The demand prediction values ​​corresponding to all target goods are combined to obtain the estimated demand for goods. Then, the demand for goods corresponding to each target consumer is summarized to obtain the summarized demand for goods, and the market trend analysis is performed on the summarized demand for goods and the historical demand to observe the future change trend of the demand for the target goods, and the change trend includes: growth, stability and decline. Finally, the estimated demand for goods and the estimated development trend are combined to determine the potential demand for goods.

[0046] It can be seen that in the embodiment of the present application, the demand for goods is predicted based on the target goods list and key consumption characteristics corresponding to the target consumers, and the estimated demand for goods is determined. Then, the market trend forecast is made based on the demand for goods corresponding to each target consumer to determine the estimated development trend. Finally, the estimated demand for goods and the estimated development trend are combined to determine the potential demand for goods. Predicting the demand for goods and market trends helps companies plan production, inventory and marketing strategies in advance, ensuring that goods can be supplied in a timely manner when market demand increases, and avoiding inventory backlogs or out-of-stock situations.

[0047] Furthermore, in order to more accurately control inventory levels, in the embodiment of the present application, the product data includes: historical sales data, inventory data and purchase data. Conduct multi-dimensional characteristic analysis based on product data and potential demand for products to determine product inventory and sales recommendations, including: Based on the inventory data and purchase data in the product data, as well as the estimated product demand in the product potential demand, supply and sales analysis is performed to determine the first inventory and sales recommendation; Conduct product sales analysis based on the estimated development trend of product potential demand and historical sales data in product data to determine the second inventory sales recommendation; Based on the first inventory and sales suggestion and the second inventory and sales suggestion, determine the inventory and sales suggestion for the goods.

[0048] For the embodiments of the present application, in the process of multi-dimensional characteristic analysis of product data and potential demand for products, inventory data, procurement data and estimated demand for products can be comprehensively considered to facilitate more accurate control of inventory levels, which helps to adjust procurement plans and production plans in advance, ensure the smooth operation of the supply chain, and improve the overall efficiency of the supply chain.

[0049] Specifically, inventory data includes but is not limited to: current inventory, inventory turnover, inventory cost, etc., procurement data includes but is not limited to: historical procurement, procurement cycle, procurement cost, etc., and the estimated demand for goods refers to the demand for goods in the future forecast period. Then, based on the inventory data and procurement data in the product data, as well as the estimated demand for goods in the potential demand for goods, a supply and marketing analysis is performed to determine the first inventory and sales suggestion, that is, by comparing the current actual inventory, procurement plan and estimated demand of the goods, it is determined whether the goods need to adjust the inventory level and procurement plan. For example, if the inventory is too high, it may be necessary to reduce the procurement volume or increase the sales volume to reduce the inventory cost; if the inventory is too low, it may be necessary to increase the procurement volume or reduce the sales volume to avoid the risk of out-of-stock. The first inventory and sales suggestion includes but is not limited to: adjusting the inventory level, optimizing the procurement plan, increasing or reducing the sales volume and other specific measures to ensure the balance between inventory and demand, and to achieve an increase in inventory turnover and a reduction in inventory costs. At the same time, sales trends are visualized based on historical sales data to intuitively display the historical sales trends of each target product, that is, line charts, bar charts and other tools can be used to display the sales of target products. Then, based on historical sales trends and estimated development trends, product sales analysis is performed to analyze the current and future market demand for the products, determine the growth potential of the target products, and determine the second inventory and sales recommendations. For example, if the sales potential is large and market demand is growing, it is recommended to increase inventory and expand sales channels; if the sales potential is small or there is a downward trend in the future, it is recommended to optimize sales strategies and enhance product competitiveness. Finally, the first inventory and sales recommendations and the second inventory and sales recommendations are combined to determine the inventory and sales recommendations for the products.

[0050] It can be seen that in the embodiment of the present application, a supply and sales analysis is performed based on the inventory data and procurement data in the product data, as well as the estimated product demand in the potential demand for the product, to determine the first inventory and sales suggestion. At the same time, a product sales analysis is performed based on the estimated development trend in the potential demand for the product and the historical sales data in the product data to determine the second inventory and sales suggestion. Finally, the first inventory and sales suggestion and the second inventory and sales suggestion are combined to determine the inventory and sales suggestion for the product. Comprehensively considering the inventory data, procurement data, and the estimated product demand in order to more accurately control the inventory level, it is helpful to adjust the procurement plan and production plan in advance, ensure the smooth operation of the supply chain, and improve the overall efficiency of the supply chain.

[0051] Furthermore, in order to improve the accuracy and satisfaction of consumers' shopping decisions, in an embodiment of the present application, sending a target product list to a consumer terminal includes: Obtaining a virtual three-dimensional model corresponding to each target product in the target product list, and associating the target product in the target product list with the virtual three-dimensional model to determine an association relationship; The virtual three-dimensional model, each target product and each virtual three-dimensional model are sent to the consumer terminal to improve the consumer's shopping experience.

[0052] For the embodiment of the present application, in order to display the target product more vividly, a virtual three-dimensional model of the product is displayed to the consumer so that the consumer can fully understand the appearance, size, color and other details of the product, thereby improving the accuracy and satisfaction of the consumer's shopping decision.

[0053] Specifically, a virtual three-dimensional model corresponding to each target product in the target product list is obtained. The virtual three-dimensional model is a three-dimensional model that uses three-dimensional modeling software to build a product that maintains details and realism. Then, the target products in the target product list are associated with the virtual three-dimensional model to determine the association relationship. The association relationship is determined so that the consumer terminal can accurately display the three-dimensional model of each target product. When performing the association operation, the unique identifier of the target product can be associated with the unique identifier of the virtual three-dimensional model to determine the association relationship. Then, the virtual three-dimensional model, each target product, and each virtual three-dimensional model are sent to the consumer terminal. After receiving the virtual three-dimensional model, the consumer terminal will use a graphics rendering engine to render and display the virtual three-dimensional model, and provide consumers with functions for interacting with the virtual three-dimensional model, such as rotating, zooming, viewing details, etc., to enhance the shopping experience.

[0054] It can be seen that in the embodiment of the present application, the target goods in the target goods list are associated with the virtual three-dimensional model to determine the association relationship, and then the virtual three-dimensional model, each target product and each virtual three-dimensional model are sent to the consumer terminal. This allows consumers to fully understand the appearance, size, color and other details of the goods, thereby improving the accuracy and satisfaction of consumer shopping decisions.

[0055] The above embodiment introduces a method for intelligent matching of goods based on an e-commerce ERP system from the perspective of a method flow. The following embodiment introduces a device for intelligent matching of goods based on an e-commerce ERP system from the perspective of a virtual module or a virtual unit. For details, please refer to the following embodiment.

[0056] The present application embodiment provides a product intelligent matching device based on an e-commerce ERP system, such as Figure 2 As shown, the intelligent product matching device based on the e-commerce ERP system may specifically include: A user portrait construction module 210 is used to obtain consumption data corresponding to the consumer and construct a user portrait based on the consumption data to obtain a target user portrait; The product recommendation module 220 is used to recommend products based on the target user portrait, determine a target product list, and send the target product list to the consumer terminal to achieve personalized product recommendation, wherein the target product list is a collection of products that meet the consumer's consumption habits; Demand analysis module 230, for performing demand analysis based on the target product list corresponding to each consumer to determine potential demand for the product, wherein the potential demand for the product helps to understand the consumer's demand for the product and market trends; The multi-dimensional characteristic analysis module 240 is used to obtain the product data corresponding to the merchant, and perform multi-dimensional characteristic analysis based on the product data and potential demand for the product, determine the product inventory and sales suggestions, and send the product inventory and sales suggestions to the merchant terminal to facilitate the merchant to optimize the coordination between product procurement, inventory and export.

[0057] For the embodiment of the present application, a user portrait is constructed based on consumption data to obtain a target user portrait. Then, based on the target user portrait, product recommendations are made, a target product list is determined, and the target product list is sent to the consumer terminal to achieve personalized product recommendations. Furthermore, a demand analysis is performed based on the target product list corresponding to each consumer to determine the potential demand for the product. By in-depth analysis of the target user portrait, the consumer's consumption habits, preferences, and needs can be accurately understood, thereby providing personalized product recommendations and significantly improving consumer satisfaction and willingness to purchase. At the same time, a multi-dimensional characteristic analysis is performed based on the product data and the potential demand for the product to determine the inventory and sales recommendations for the product, and the inventory and sales recommendations for the product are sent to the merchant terminal to facilitate the merchant to optimize the coordination between product procurement, inventory, and export.

[0058] In a possible implementation of the embodiment of the present application, when the user portrait construction module 210 constructs a user portrait based on consumption data to obtain a target user portrait, it is used to: Extract key features based on consumption data and determine key consumption features, where key consumption features include: preferred product type, search preference keywords, purchase frequency, and purchase amount; Classify groups based on key consumption characteristics and obtain user group labels; Build a visual portrait based on key consumption characteristics and user group labels to obtain a structured target user portrait.

[0059] In a possible implementation of the embodiment of the present application, when the product recommendation module 220 performs product recommendation based on the target user portrait and determines the target product list, it is used to: Perform collaborative filtering based on the target user portrait to determine the first product list, wherein the collaborative filtering includes: user collaborative filtering and item collaborative filtering; Acquire product data, and match products based on product features in the product data and key consumption features to determine a second product list; Obtaining a correspondence between the user portrait and the product portrait corresponding to the product list, and determining a third product list based on the correspondence between the target user portrait and the product portrait; The first commodity list, the second commodity list and the third commodity list are combined to obtain a target commodity list.

[0060] In a possible implementation of the embodiment of the present application, when the demand analysis module 230 performs demand analysis based on the target product list corresponding to each consumer to determine the potential demand for the product, it is used to: Based on the target product list and key consumption characteristics corresponding to the target consumer, the product demand is predicted to determine the estimated product demand, wherein the target consumer is any consumer; Comprehensively forecast the market trend based on the demand for goods corresponding to each target consumer and determine the estimated development trend; Comprehensively estimate the demand for goods and the estimated development trend to determine the potential demand for goods.

[0061] In a possible implementation of the embodiment of the present application, the product data includes: historical sales data, inventory data and purchase data. When performing multi-dimensional characteristic analysis based on product data and product potential demand to determine product inventory and sales recommendations, the multi-dimensional characteristic analysis module 240 is used to: Based on the inventory data and purchase data in the product data, as well as the estimated product demand in the product potential demand, supply and sales analysis is performed to determine the first inventory and sales recommendation; Conduct product sales analysis based on the estimated development trend of product potential demand and historical sales data in product data to determine the second inventory sales recommendation; Based on the first inventory and sales suggestion and the second inventory and sales suggestion, determine the inventory and sales suggestion for the goods.

[0062] In a possible implementation of the embodiment of the present application, when the product recommendation module 220 sends the target product list to the consumer terminal, it is used to: Obtaining a virtual three-dimensional model corresponding to each target product in the target product list, and associating the target product in the target product list with the virtual three-dimensional model to determine an association relationship; The virtual three-dimensional model, each target product and each virtual three-dimensional model are sent to the consumer terminal to improve the consumer's shopping experience. Technical personnel in the relevant field can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described intelligent matching device for goods based on the e-commerce ERP system can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0063] An electronic device is provided in an embodiment of the present application, such as Figure 3 As shown, Figure 3 The electronic device 300 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of the present application.

[0064] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0065] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but it does not mean that there is only one bus or only one type of bus.

[0066] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0067] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0068] The electronic devices include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0069] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment.

[0070] The embodiment of the present application provides a computer program product, which includes a computer program, which implements the method in any of the above embodiments when executed by a processor. Compared with the related art, the embodiment of the present application constructs a user portrait based on consumption data to obtain a target user portrait, and then recommends goods based on the target user portrait, determines a target goods list, and sends the target goods list to the consumer terminal to achieve personalized recommendation of goods. Furthermore, demand analysis is performed based on the target goods list corresponding to each consumer to determine the potential demand for goods. By deeply analyzing the target user portrait, the consumer's consumption habits, preferences and needs can be accurately understood, thereby providing personalized goods recommendations, significantly improving consumer satisfaction and willingness to buy. At the same time, a multi-dimensional characteristic analysis is performed based on the goods data and the potential demand for goods, and the goods inventory and sales suggestions are determined, and the goods inventory and sales suggestions are sent to the merchant terminal, so that the merchant can optimize the coordination between goods procurement, inventory and export.

[0071] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0072] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for intelligent matching of goods based on an e-commerce ERP system, characterized in that: include: Obtaining consumption data corresponding to the consumer, and constructing a user profile based on the consumption data to obtain a target user profile; Recommend products based on the target user portrait, determine a target product list, and send the target product list to the consumer terminal to achieve personalized product recommendation, wherein the target product list is a collection of products that meet the consumer's consumption habits; Conducting demand analysis based on the target product list corresponding to each consumer to determine potential demand for products, wherein the potential demand for products helps to understand the consumer's product demand and market trends; The corresponding product data of the merchant is obtained, and a multi-dimensional characteristic analysis is performed based on the product data and the potential demand for the product to determine product inventory and sales suggestions, and the product inventory and sales suggestions are sent to the merchant terminal to facilitate the merchant to optimize the coordination between product procurement, inventory and export.

2. The method for intelligent matching of goods based on an e-commerce ERP system according to claim 1, characterized in that: The constructing of a user profile based on the consumption data to obtain a target user profile includes: Extract key features based on the consumption data to determine key consumption features, wherein the key consumption features include: preferred product type, search preference keywords, purchase frequency, and purchase amount; Perform group classification based on the key consumption characteristics to obtain user group labels; A visual portrait is constructed based on the key consumption characteristics and the user group labels to obtain a structured target user portrait.

3. The intelligent goods matching method based on the e-commerce ERP system according to claim 2 is characterized in that: The recommending products based on the target user portrait and determining the target product list includes: Perform collaborative filtering based on the target user portrait to determine a first product list, wherein the collaborative filtering includes: user collaborative filtering and item collaborative filtering; Acquire product data, and match products based on product features in the product data and the key consumption features to determine a second product list; Obtaining a correspondence between the user portrait and the product portrait corresponding to the product list, and determining a third product list based on the correspondence between the target user portrait and the product portrait; The first commodity list, the second commodity list and the third commodity list are integrated to obtain a target commodity list.

4. The method for intelligent matching of goods based on an e-commerce ERP system according to claim 2 is characterized in that: The demand analysis based on the target product list corresponding to each consumer to determine the potential demand for the product includes: Based on the target product list and key consumption characteristics corresponding to the target consumer, the product demand is predicted to determine the estimated product demand, wherein the target consumer is any one consumer; Comprehensively forecast the market trend based on the demand for goods corresponding to each target consumer and determine the estimated development trend; The estimated demand for goods and the estimated development trend are combined to determine the potential demand for goods.

5. The method for intelligent matching of goods based on an e-commerce ERP system according to claim 4 is characterized in that: The product data includes: historical sales data, inventory data and purchase data, The multi-dimensional characteristic analysis based on the product data and the potential demand for the product to determine the product inventory and sales suggestions includes: Perform supply and sales analysis based on the inventory data and purchase data in the product data and the estimated product demand in the potential demand for the product to determine a first inventory and sales suggestion; Performing product sales analysis based on the estimated development trend of the potential demand for the product and the historical sales data in the product data to determine a second inventory sales suggestion; The first inventory and sales suggestion and the second inventory and sales suggestion are combined to determine the inventory and sales suggestion for the goods.

6. The method for intelligent matching of goods based on an e-commerce ERP system according to claim 1, characterized in that: The sending of the target product list to the consumer terminal includes: Acquire a virtual three-dimensional model corresponding to each target product in the target product list, and associate the target product in the target product list with the virtual three-dimensional model to determine an association relationship; The virtual three-dimensional model, each of the target products and each of the virtual three-dimensional models are sent to a consumer terminal to improve the consumer's shopping experience.

7. An electronic device, characterized in that: include: at least one processor; Memory; At least one application, wherein at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the product intelligent matching method based on the e-commerce ERP system as described in any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed in a computer, the computer is caused to execute the intelligent product matching method based on the e-commerce ERP system as described in any one of claims 1 to 6.

9. A computer program product, characterized in that It includes a computer program, and the computer program is executed by a processor to implement the intelligent product matching method based on the e-commerce ERP system as described in any one of claims 1 to 6.

Citation Information

Cited By

  • A b2b liquor recommendation order generation method and system

    CN122779950A