Commodity operation management method and system applied to cross-border e-commerce

Abstract

The invention relates to the technical field of cross-border e-commerce commodity operation, and provides a commodity operation management method and system applied to cross-border e-commerce, and the method comprises the steps: carrying out the data division of commodity operation data, obtaining a divided data set, carrying out the data set optimization of the divided data set, and obtaining an optimized data set; performing multi-source analysis on the commodity operation data, and constructing an operation network of the operation commodity; querying potential users operating commodities, extracting target potential users from the potential users, constructing a screening matrix of the target potential users, and performing user screening on the target potential users to obtain screened users; and carrying out user updating on the screened users to obtain updated users, constructing an initial operation strategy of the operation commodity, carrying out supply risk assessment on a target operation user to obtain an assessment result, and constructing a commodity operation management strategy of cross-border e-commerce. According to the invention, high efficiency of commodity operation management can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of cross-border e-commerce commodity operation, and in particular to a commodity operation management method and system applied to cross-border e-commerce. Background Art

[0002] In the field of cross-border e-commerce, commodity operation management is a key link in improving business performance and user satisfaction. Effective commodity operation management methods can ensure accurate promotion of commodities, reasonable control of inventory, and accurate satisfaction of customer needs, thereby improving the competitiveness of cross-border e-commerce enterprises. Building a commodity operation management system suitable for cross-border e-commerce can help enterprises accurately locate market demand, optimize commodity selection strategies, reasonably plan inventory, and effectively track commodity operations, thereby improving operational efficiency and profit levels. At the same time, enterprises can predict market trends and consumer preferences based on data analysis, and adjust commodity strategies in a timely manner to provide commodities and services that better meet market demand, and promote information flow and coordination between different operating channels, between different national markets, and between various departments within the enterprise, thereby reducing operational risks and improving overall operational efficiency.

[0003] At present, the commodity operation management method under cross-border e-commerce generally uses traditional data analysis tools and manual experience judgment to build a preliminary commodity operation framework to achieve basic commodity operation management. However, with this method, many decisions rely on manual judgment and limited data. Since cross-border e-commerce involves massive commodity data and complex market environment, enterprises are not accurate enough in making decisions on commodity operations when facing large amounts of data and changing markets, which leads to inefficient commodity operation management. Summary of the invention

[0004] In order to solve the above problems, the present invention provides a commodity operation management method and system applied to cross-border e-commerce, which can improve the efficiency of commodity operation management.

[0005] In a first aspect, the present invention provides a commodity operation management method applied to cross-border e-commerce, the method comprising:

[0006] Collect commodity operation data on cross-border e-commerce, query key operation attributes of the commodity operation data, divide the commodity operation data based on the key operation attributes to obtain a divided data set, calculate the data gain of the divided data in the divided data set, and optimize the divided data set based on the data gain to obtain an optimized data set;

[0007] Performing multi-source analysis on the commodity operation data, selecting data features of the optimized data set according to the analysis results of the multi-source analysis, querying the operation commodities in the cross-border e-commerce, and calculating the mutual information value between the data features and the operation commodities, and constructing the operation network of the operation commodities based on the mutual information value;

[0008] Acquire the operation channel of the operation product, query the potential users of the operation product based on the operation channel, query the sticky users of the operation product, analyze the user similarity between the potential users and the sticky users, extract target potential users from the potential users based on the user similarity, construct a screening matrix for the target potential users, and use the screening matrix to screen the target potential users to obtain screened users;

[0009] The operation network is used to update the screened users to obtain updated users. After the updated users are used as target operation users of the operation products, an initial operation strategy for the operation products is constructed. A supply risk assessment is performed on the target operation users to obtain an assessment result. Based on the initial operation strategy and the assessment result, a product operation management strategy for the cross-border e-commerce is constructed.

[0010] Optionally, the data segmentation of the commodity operation data based on the operation key attribute to obtain the segmented data set includes:

[0011] Performing vector transformation on the key operation attributes, and constructing the vector centroid of the key operation attributes after the vector transformation;

[0012] Performing vector conversion on the commodity operation data to obtain an operation vector;

[0013] The vector distance between the operation vector and the vector centroid is calculated using the following formula:

[0014]

[0015] Where D represents the vector distance, ∈ represents the spatial dimension of the operation vector, and x o represents the horizontal coordinate of the centroid of the i-th vector, y i represents the ordinate of the centroid of the i-th vector;

[0016] Based on the vector distance, the commodity operation data is divided to obtain a divided data set.

[0017] Optionally, the calculating the data gain of the divided data in the divided data set includes:

[0018] The information entropy of the partitioned data in the partitioned data set is calculated using the following formula:

[0019]

[0020] Among them, S represents information entropy, n represents the number of categories of the data set, and c j Indicates the probability that the data set corresponding to the partitioned data c belongs to the jth category;

[0021] The conditional entropy of the key attributes of the divided data in the divided data set is calculated, and based on the information entropy and the conditional entropy, the data gain of the divided data in the divided data set is calculated using the following formula:

[0022] Gain=S-Ent

[0023] Among them, Gain represents data gain, S represents information entropy, and Ent represents conditional entropy.

[0024] Optionally, the performing multi-source analysis on the commodity operation data to select data features of the optimized data set according to the analysis results of the multi-source analysis includes:

[0025] Performing data integration on the commodity operation data to obtain integrated data;

[0026] determining analysis indicators for the integrated data;

[0027] Based on the analysis index, performing correlation analysis on the integrated data to obtain a correlation analysis result;

[0028] Based on the analysis indicators, performing trend analysis on the integrated data to obtain trend analysis results;

[0029] Based on the analysis indicators, comparative analysis is performed on the integrated data to obtain comparative analysis results;

[0030] Based on the correlation analysis result, the trend analysis result and the comparison analysis result, data features of the optimized data set are determined.

[0031] Optionally, the querying of the operating commodities in the cross-border e-commerce and calculating the mutual information value between the data feature and the operating commodities includes:

[0032] The mutual information value between the data feature and the operating product is calculated using the following formula:

[0033]

[0034] Among them, ME(A,B) represents the mutual information value, A represents the data feature, B represents the operating product, P(a,b) represents the joint probability distribution of A and B, P(a) represents the marginal probability distribution of A, P(b) represents the marginal probability distribution of B, b represents the serial number of the operating product, and a represents the serial number of the data feature.

[0035] Optionally, the analyzing the user similarity between the potential user and the sticky user includes:

[0036] Performing vector conversion on the potential users and the sticky users to obtain a first vector and a second vector;

[0037] The vector similarity between the first vector and the second vector is calculated using the following formula:

[0038]

[0039] Among them, VS represents vector similarity, represents the first vector, represents the second vector, represents the magnitude of the first vector, represents the magnitude of the second vector, represents the inclination of the spatial coordinate point i corresponding to the first vector, Represents the inclination of the space coordinate point i corresponding to the second vector;

[0040] Based on the vector similarity, user similarity between the potential user and the sticky user is determined.

[0041] Optionally, constructing a screening matrix for the target potential users includes:

[0042] Determine the screening dimensions of the target potential users, and calculate the dimension weights of the screening dimensions;

[0043] Constructing a matrix framework of the target potential users;

[0044] Acquire user data of the target potential user;

[0045] Based on the dimension weights and the user data, the matrix framework is filled with data to obtain a screening matrix.

[0046] Optionally, the updating the screened user by using the operation network to obtain the updated user includes:

[0047] Using the operation network to construct the interest set of the screened user;

[0048] Based on the interest set, the following formula is used to calculate the interest preference of the screened user for the interest set:

[0049]

[0050] Where F represents the interest preference degree, N(i) represents the set of screened users who have rated the interest set too highly, and P Ri Indicates the rating of user R for interest i. represents the average mean of the interests of the filtered user R for its rated ones, M represents the set of filtered users, Represents the rating vector of the filtered user R;

[0051] According to the interest preference degree, the screened users are updated to obtain updated users.

[0052] Optionally, the using the operation network to construct the interest set of the screened user includes:

[0053] Querying the user data of the screened user using the operation network;

[0054] Extracting data features of the user data;

[0055] Clustering the data features to obtain cluster features;

[0056] Constructing interest tags of the clustering features;

[0057] Performing weight allocation on the interest tags to obtain weight allocation tags;

[0058] After optimizing the weight distribution labels, the interest set of the screened user is obtained.

[0059] In a second aspect, the present invention provides a commodity operation management system applied to cross-border e-commerce, the system comprising:

[0060] A data set optimization module is used to collect commodity operation data about cross-border e-commerce, query the key operation attributes of the commodity operation data, divide the commodity operation data based on the key operation attributes to obtain a divided data set, calculate the data gain of the divided data in the divided data set, and optimize the divided data set based on the data gain to obtain an optimized data set;

[0061] An operation network construction module, used to perform multi-source analysis on the commodity operation data, select data features of the optimized data set according to the analysis results of the multi-source analysis, query the operation commodities in the cross-border e-commerce, and calculate the mutual information value between the data features and the operation commodities, and construct the operation network of the operation commodities based on the mutual information value;

[0062] A user screening module is used to obtain the operating channels of the operating products, query the potential users of the operating products based on the operating channels, query the sticky users of the operating products, analyze the user similarity between the potential users and the sticky users, extract target potential users from the potential users based on the user similarity, construct a screening matrix for the target potential users, and use the screening matrix to screen the target potential users to obtain screened users;

[0063] The operation strategy construction module is used to use the operation network to update the screened users to obtain updated users, and after using the updated users as the target operation users of the operation products, to construct the initial operation strategy of the operation products, to conduct supply risk assessment on the target operation users to obtain assessment results, and to construct the commodity operation management strategy of the cross-border e-commerce based on the initial operation strategy and the assessment results.

[0064] Compared with the prior art, the technical principle and beneficial effects of this solution are:

[0065] The embodiments of the present invention can collect commodity operation data about cross-border e-commerce by collecting commodity sales data, user search and browsing data, etc., and can gain insights into consumer needs and preferences, thereby providing a basis for product selection and commodity promotion. Furthermore, the embodiments of the present invention can comprehensively understand the operation status by performing multi-source analysis on the commodity operation data and selecting data features of the optimized data set according to the analysis results of the multi-source analysis, thereby formulating more targeted and effective operation strategies, such as promotional activities or product improvements for specific regions. , and querying the operating commodities in the cross-border e-commerce, and calculating the mutual information value between the data features and the operating commodities can reveal the degree of correlation between the data features and the operating commodities, and by obtaining the operating channels of the operating commodities, querying the potential users of the operating commodities based on the operating channels can discover new customer groups, expand the market coverage of commodities, increase sales opportunities, and formulate more targeted and personalized marketing strategies based on the characteristics and needs of potential users, improve marketing effects and conversion rates, further, the embodiment of the present invention uses the operating network to update the screened users, and the updated users can adapt to market changes. With the changes in market dynamics and user needs, timely updating the screened users can ensure that the latest potential valuable users are captured, and based on the initial operating strategy and the evaluation results, constructing the commodity operation management strategy of the cross-border e-commerce can improve operational efficiency and effect: comprehensively considering factors such as initial strategies and supply risks, it can plan operational activities more comprehensively and accurately, avoid blindness and one-sidedness, thereby improving operational efficiency and the final effect of reducing risks, and adjusting and optimizing the operating strategy according to the supply risk assessment results, which helps to respond to possible supply problems in advance and reduce business risks caused by supply interruptions and delays. The embodiments of the present invention provide a method and system for commodity operation management applied to cross-border e-commerce, which can improve the efficiency of commodity operation management. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0067] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0068] Figure 1 A flowchart of a commodity operation management method applied to cross-border e-commerce provided by an embodiment of the present invention;

[0069] Figure 2 A schematic diagram of a module of a commodity operation management system applied to cross-border e-commerce provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0070] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0071] The embodiment of the present invention provides a commodity operation management method applied to cross-border e-commerce, and the execution subject of the commodity operation management method applied to cross-border e-commerce includes but is not limited to at least one of the electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided by the embodiment of the present invention. In other words, the commodity operation management method applied to cross-border e-commerce can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.

[0072] See also Figure 1 FIG. 1 is a flow chart of a commodity operation management method applied to cross-border e-commerce provided by an embodiment of the present invention. Figure 1 A commodity operation management method described in the specification for cross-border e-commerce includes:

[0073] S1. Collect commodity operation data on cross-border e-commerce, query the key operation attributes of the commodity operation data, divide the commodity operation data based on the key operation attributes to obtain a divided data set, calculate the data gain of the divided data in the divided data set, and optimize the divided data set based on the data gain to obtain an optimized data set.

[0074] The embodiment of the present invention can collect commodity operation data about cross-border e-commerce by collecting commodity sales data, user search and browsing data, etc., and can gain insights into consumers' needs and preferences, thereby providing a basis for product selection and commodity promotion. The commodity operation data can be obtained through e-commerce platforms, such as Amazon or Google Analytics and other websites.

[0075] Furthermore, the embodiment of the present invention can make targeted decisions based on key attributes by querying the key operational attributes of the commodity operation data, thereby improving the accuracy and efficiency of the decision. The key operational attributes refer to features or indicators that have a key impact and significant effect on the effect, efficiency and profitability of commodity operations, such as target market, commodity category, price range, brand awareness and commodity quality.

[0076] Furthermore, the embodiment of the present invention divides the commodity operation data based on the operation key attributes to obtain a divided data set, which can classify a large amount of disordered data and facilitate data analysis.

[0077] As an embodiment of the present invention, the data division of the commodity operation data based on the operation key attribute to obtain the divided data set includes: performing vector conversion on the operation key attribute and constructing the vector centroid of the operation key attribute after the vector conversion, performing vector conversion on the commodity operation data to obtain an operation vector, and calculating the vector distance between the operation vector and the vector centroid using the following formula:

[0078]

[0079] Where D represents the vector distance, ∈ represents the spatial dimension of the operation vector, and x i represents the horizontal coordinate of the centroid of the i-th vector, y i represents the ordinate of the centroid of the i-th vector;

[0080] Based on the vector distance, the commodity operation data is divided to obtain a divided data set.

[0081] It should be noted that the vector transformation can be converted through a preconfigured vector transformation matrix. After the vector transformation is constructed, the vector centroid of the key operating attribute can be obtained by constructing a small sample set of initial points based on the key operating attributes, namely the initial vector centroid, such as a small sample of the target market, a small sample of product categories, and a small sample of price ranges.

[0082] The embodiment of the present invention can help users determine which attributes or features are more valuable for distinguishing different data categories by calculating the data gain of the divided data in the divided data set, so as to select more representative and influential features in subsequent analysis.

[0083] As an embodiment of the present invention, the calculating the data gain of the divided data in the divided data set includes: calculating the information entropy of the divided data in the divided data set using the following formula:

[0084]

[0085] Among them, S represents information entropy, n represents the number of categories of the data set, and c j Indicates the probability that the data set corresponding to the partitioned data c belongs to the jth category;

[0086] The conditional entropy of the key attributes of the divided data in the divided data set is calculated, and based on the information entropy and the conditional entropy, the data gain of the divided data in the divided data set is calculated using the following formula:

[0087] Gain=S-Ent

[0088] Among them, Gain represents data gain, S represents information entropy, and Ent represents conditional entropy.

[0089] Furthermore, the embodiment of the present invention optimizes the divided data set based on the data gain to obtain an optimized data set, which can reduce the time and computing resource consumption for processing and analyzing data and improve work efficiency.

[0090] Optionally, based on the data gain, the divided data set is optimized to obtain the optimized data set. The data set can be optimized by the data gain calculation result. For example, we have various attribute data of commodities, such as price, color, size, brand, origin, material, etc. By calculating the data gain, it is found that the two attributes of price and brand have a higher contribution to predicting the sales volume of commodities, while the contribution of color and size is relatively small. Then, when optimizing the data set, we can only keep the data of the two attributes of price and brand, and remove the data of color and size, so as to reduce the amount of data and improve the analysis efficiency.

[0091] S2. Perform multi-source analysis on the commodity operation data to select data features of the optimized data set according to the analysis results of the multi-source analysis, query the operation commodities in the cross-border e-commerce, and calculate the mutual information value between the data features and the operation commodities, and build an operation network of the operation commodities based on the mutual information value.

[0092] The embodiment of the present invention performs multi-source analysis on the commodity operation data and selects the data features of the optimized data set according to the analysis results of the multi-source analysis, so as to fully understand the operation status and formulate more targeted and effective operation strategies, such as promotional activities or product improvements for specific regions.

[0093] As an embodiment of the present invention, the multi-source analysis of the commodity operation data is performed to select data features of the optimized data set according to the analysis results of the multi-source analysis, including: data integration of the commodity operation data to obtain integrated data, determining analysis indicators of the integrated data, performing correlation analysis on the integrated data based on the analysis indicators to obtain correlation analysis results, performing trend analysis on the integrated data based on the analysis indicators to obtain trend analysis results, performing comparative analysis on the integrated data based on the analysis indicators to obtain comparative analysis results, and determining the data features of the optimized data set based on the correlation analysis results, the trend analysis results and the comparative analysis results.

[0094] Optionally, the data integration of the commodity operation data to obtain integrated data refers to data operations to ensure data consistency and accuracy, which can be achieved through data cleaning. The determination of analysis indicators can determine key analysis indicators based on operation objectives, such as sales, profit margin, customer satisfaction, and market share, etc., which can be determined in combination with actual analysis needs. The correlation analysis of the integrated data based on the analysis indicators to obtain correlation analysis results refers to correlation analysis of data from different data sources with determined analysis indicators, such as analyzing the correlation between product mention frequency on social media and sales, or the relationship between logistics delivery time and customer satisfaction, which can be analyzed through regression function. The trend analysis of the integrated data based on the analysis indicators to obtain trend analysis results refers to Analyze the changing trend of various indicators over time and understand the dynamic development of commodity operation. The analysis can be performed through time series functions. Based on the analysis indicators, the integrated data is compared and analyzed to obtain the comparative analysis results, which means comparing the data of different regions, different product lines, and different time periods to find out the differences and advantages. The comparative analysis can be performed by constructing data charts. Based on the correlation analysis results, the trend analysis results, and the comparative analysis results, the data characteristics of the optimized data set are determined. The data characteristics closely related to the operation objectives can be selected through the above analysis results. For example, in cross-border e-commerce, the transaction data of the sales platform (including commodity sales, prices, return rates, etc.), user comments on social media (evaluations on product quality, packaging, services, etc.), and delivery time and cost data of the logistics system are integrated. Through correlation analysis, it is found that the return rate of commodities has a strong positive correlation with the number of negative comments on product quality on social media; through trend analysis, it is seen that the sales of a certain product line have a significant upward trend in a specific season; through comparative analysis, it is found that the market in a certain region has a large demand for commodities of specific colors and styles.

[0095] Furthermore, the embodiment of the present invention can reveal the degree of association between the data feature and the operational commodity by querying the operational commodity in the cross-border e-commerce and calculating the mutual information value between the data feature and the operational commodity. A strong mutual information value indicates that there is a close connection between the feature and the commodity, and vice versa, it indicates a weak connection, thereby optimizing the operational strategy.

[0096] As an embodiment of the present invention, the querying of the operating commodities in the cross-border e-commerce and calculating the mutual information value between the data feature and the operating commodity includes: calculating the mutual information value between the data feature and the operating commodity using the following formula:

[0097]

[0098] Among them, ME(A,B) represents the mutual information value, A represents the data feature, B represents the operating product, P(a,b) represents the joint probability distribution of A and B, P(a) represents the marginal probability distribution of A, P(b) represents the marginal probability distribution of B, b represents the serial number of the operating product, and a represents the serial number of the data feature.

[0099] Furthermore, the embodiment of the present invention can intuitively display the complex relationship between data features and operating commodities by constructing the operating network of the operating commodities based on the mutual information value, which is convenient for users to quickly understand and gain insights. For example, for a certain clothing commodity in cross-border e-commerce, data features such as color, size, price, fabric, and the clothing commodity itself are used as nodes. After calculating the mutual information value of these features and the commodity, weights are set for the connections and the network is drawn. If the mutual information value between the color and the commodity is large and the connection weight is high, it means that the color has a greater impact on the operation of the clothing commodity. By analyzing the network, it is possible to focus on promoting or optimizing inventory with respect to the color.

[0100] S3. Obtain the operation channel of the operation product, query the potential users of the operation product based on the operation channel, query the sticky users of the operation product, analyze the user similarity between the potential users and the sticky users, extract target potential users from the potential users based on the user similarity, construct a screening matrix for the target potential users, and use the screening matrix to screen the target potential users to obtain screened users.

[0101] The embodiment of the present invention can discover new customer groups by obtaining the operating channels of the operating products and querying the potential users of the operating products based on the operating channels, expand the market coverage of the products, increase sales opportunities, and formulate more targeted and personalized marketing strategies based on the characteristics and needs of potential users, thereby improving marketing effects and conversion rates. The operating channels can be obtained through market research or data analysis, and the potential users can be obtained through platform user data mining.

[0102] It should be noted that the sticky users usually refer to those users who are highly dependent on the operating products and frequently purchase and use them. They can be obtained through membership system data, user behavior tracking and data analysis tools.

[0103] Furthermore, the embodiment of the present invention can understand the similarities between potential users and sticky users by analyzing the user similarities between the potential users and the sticky users, and then formulate more targeted marketing activities for cross-border e-commerce merchants, thereby improving the success rate of converting potential users into sticky users.

[0104] As an embodiment of the present invention, the analyzing the user similarity between the potential user and the sticky user includes: performing vector transformation on the potential user and the sticky user to obtain a first vector and a second vector, and calculating the vector similarity between the first vector and the second vector using the following formula:

[0105]

[0106] Among them, VS represents vector similarity, represents the first vector, represents the second vector, represents the magnitude of the first vector, represents the magnitude of the second vector, represents the inclination of the spatial coordinate point i corresponding to the first vector, Represents the inclination of the space coordinate point i corresponding to the second vector;

[0107] Based on the vector similarity, user similarity between the potential user and the sticky user is determined.

[0108] It should be explained that if the calculation result of the vector similarity is not less than a preset similarity value, it means that the potential user and the sticky user are highly similar users. The preset similarity value is 0.5, which can also be set according to the actual application scenario.

[0109] The embodiment of the present invention can more accurately predict the needs of the target potential users by extracting the target potential users from the potential users, and make product preparations and inventory management in advance.

[0110] Furthermore, the embodiment of the present invention can quickly and systematically screen out target potential users that meet specific criteria from a large number of potential users by constructing the screening matrix of the target potential users, thereby improving the efficiency and accuracy of screening.

[0111] As an embodiment of the present invention, constructing the screening matrix of the target potential users includes: determining the screening dimensions of the target potential users, calculating the dimension weights of the screening dimensions, constructing a matrix framework of the target potential users, obtaining user data of the target potential users, and filling the matrix framework with data based on the dimension weights and the user data to obtain a screening matrix.

[0112] Optionally, the screening dimensions of the target potential users may be determined by market research techniques (such as questionnaires, user interviews) and data analysis tools, the dimension weights of the screening dimensions may be calculated by assigning weights of the dimensions by analytic hierarchy process (AHP) or expert evaluation and scoring, the matrix framework may be established by a data structure in programming (such as a two-dimensional array), and the matrix framework is filled with data based on the dimension weights and the user data to obtain a screening matrix in the following process:

[0113] Based on the dimension weights, the scores of each potential user in each dimension are calculated and summarized to obtain a comprehensive score, and a threshold of the comprehensive score is determined. Potential users above the threshold are assigned to the same dimension.

[0114] Furthermore, the embodiment of the present invention uses the screening matrix to screen the target potential users, and the screened users can comprehensively consider the age, consumption ability, purchase history, browsing behavior and other factors of the target potential users, so as to accurately find the potential user group that is most likely to be converted into actual customers, and provide strong support for subsequent precision marketing and personalized services. For example, if a screening matrix for target potential users of an e-commerce platform is to be constructed, the dimensions include age (weight 0.2), consumption amount in the past three months (weight 0.3), number of times of browsing specific product pages (weight 0.2), and number of times of adding to the shopping cart but not purchasing (weight 0.3). It is set that the age is 20-40 years old, the consumption amount in the past three months is greater than 500 yuan, the specific product page is browsed more than 10 times, and the number of times of adding to the shopping cart but not purchasing more than 3 times is qualified. Then collect the potential user data to fill the matrix, calculate the comprehensive score, set the threshold to 70 points, and the target potential user is scored above 70 points.

[0115] S4. Utilize the operation network to update the screened users to obtain updated users. After taking the updated users as the target operation users of the operation products, construct an initial operation strategy for the operation products, conduct a supply risk assessment on the target operation users to obtain an assessment result, and construct a product operation management strategy for the cross-border e-commerce based on the initial operation strategy and the assessment result.

[0116] The embodiment of the present invention uses the operation network to update the screened users, and the updated users can adapt to market changes. As market dynamics and user needs change, timely updating of the screened users can ensure that the latest potential valuable users are captured.

[0117] As an embodiment of the present invention, the method of updating the screened user by using the operation network to obtain the updated user includes: constructing an interest set of the screened user by using the operation network, and calculating the interest preference degree of the screened user for the interest set based on the interest set by using the following formula:

[0118]

[0119] Where F represents the interest preference degree, N(i) represents the set of screened users who have rated the interest set too highly, and P Ri Indicates the rating of user R for interest i. represents the average mean of the interests of the filtered user R for its rated ones, M represents the set of filtered users, Represents the rating vector of the filtered user R;

[0120] According to the interest preference degree, the screened users are updated to obtain updated users.

[0121] Optionally, the screened users are updated according to the interest preference levels, and the updated users can be updated according to the scoring results by scoring the screened users according to the interest preference levels. For example, an interest preference level between 0.1 and 0.5 indicates an average score, 0.5 to 0.7 indicates a medium score, and 0.7 to 1 indicates a high score. Users with scores above 0.7 can be extracted as target users.

[0122] As an optional embodiment of the present invention, the use of the operation network to construct the interest set of the screened user includes: using the operation network to query the user data of the screened user, extracting data features of the user data, clustering the data features to obtain cluster features, constructing interest tags of the cluster features, weighting the interest tags to obtain weighted assigned tags, and optimizing the weighted assigned tags to obtain the interest set of the screened user.

[0123] The data features of the user data can be obtained by taking the commodity categories frequently browsed by the user, the brands purchased, the promotional activities concerned by the user, etc. as data features; the data features are clustered to obtain cluster features, which means that similar interest features are classified into one category, and clustering can be performed through a clustering algorithm; the interest tags can be constructed through code generated by Java; the weight distribution of the interest tags can be performed by assigning weights to different interest tags according to factors such as the frequency and depth of the user's behavior in each interest category to indicate the user's attention to the interest; the weight distribution tags are optimized

[0124] The user's interest set can be formed by integrating all interest tags and weights. At the same time, the interest set is continuously optimized, noise and inaccurate interest tags are removed, and the weights are updated to reflect changes in user interests.

[0125] The embodiment of the present invention, by taking the updated user as the target operation user of the operation product, constructs the initial operation strategy of the operation product and can formulate strategies in a targeted manner, avoid waste of resources and blind investment, make operation activities more efficient, and formulate strategies based on the characteristics and needs of target users, which can better meet their expectations and improve user satisfaction.

[0126] Optionally, the initial operation strategy may formulate product strategy, price strategy, channel strategy and promotion strategy according to the target operation users.

[0127] Among them, the product strategy refers to optimizing product features and launching new product lines to meet the needs of target users; the price strategy refers to formulating pricing, promotion and discount plans based on the price sensitivity of target users; the channel strategy refers to selecting channels suitable for target users to obtain information and purchase, such as specific e-commerce platforms, social media, etc.; the promotion strategy refers to determining the method, content and platform of advertising, as well as the form of activities to interact with users.

[0128] Furthermore, the embodiment of the present invention performs supply risk assessment on the target operating user, and the assessment result can help the user to identify possible supply problems in advance, such as out-of-stock, delayed delivery, etc., so as to take timely preventive measures.

[0129] Optionally, the supply risk assessment of the target operating user may be performed by determining risk factors, collecting data, quantifying risks, and calculating a comprehensive risk score.

[0130] Among them, the risk factors determined may include: supplier aspects, including supplier stability, financial status, production capacity, delivery capacity, etc., logistics links, such as the reliability of transportation methods, stability of transportation routes, complexity of customs clearance, etc., market demand fluctuations, the magnitude and predictability of demand changes of target operating users, raw material supply, supply stability of raw materials, price fluctuations, etc.; the data collection may include: obtaining relevant information from suppliers, such as financial statements, production plans, etc., analyzing market research data and sales history data, understanding demand trends, and collecting service level data of logistics partners; the risk quantification may include: setting scoring standards for each risk factor, such as 1-5 points, 1 for low risk and 5 for high risk, and scoring each risk factor according to the collected data; the calculated comprehensive risk score can be obtained by weighted summing the scores of each risk factor according to the set weights, for example, if the supplier's financial status is unstable and the score is 4 points, the logistics transportation route is easily affected by weather and the score is 3 points, and the target operating user's demand fluctuations are large and the score is 4 points, the weights of each factor are set to be the same, and the comprehensive risk score is 3.67 points, which belongs to medium risk. Further analysis revealed that financial problems at suppliers could lead to supply disruptions, necessitating the search for alternative suppliers or the creation of inventory buffers.

[0131] Furthermore, the embodiment of the present invention can improve operational efficiency and effectiveness by constructing the cross-border e-commerce commodity operation management strategy based on the initial operation strategy and the evaluation results: by comprehensively considering factors such as the initial strategy and supply risk, it can plan operational activities more comprehensively and accurately, avoid blindness and one-sidedness, thereby improving operational efficiency and the ultimate effect of reducing risks, and adjusting and optimizing the operation strategy according to the supply risk assessment results, which helps to respond to possible supply problems in advance and reduce business risks caused by supply interruptions and delays.

[0132] like Figure 2 The figure shows a functional module diagram of a commodity operation management system applied to cross-border e-commerce in the present invention.

[0133] The commodity operation management system 200 applied to cross-border e-commerce of the present invention can be installed in an electronic device. According to the functions implemented, the commodity operation management system applied to cross-border e-commerce can include a data set optimization module 201, an operation network construction module 202, a user screening module 203 and an operation strategy construction module 204. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0134] In the embodiment of the present invention, the functions of each module / unit are as follows:

[0135] The data set optimization module 201 is used to collect commodity operation data about cross-border e-commerce, query the key operation attributes of the commodity operation data, divide the commodity operation data based on the key operation attributes to obtain a divided data set, calculate the data gain of the divided data in the divided data set, and optimize the divided data set based on the data gain to obtain an optimized data set;

[0136] The operation network construction module 202 is used to perform multi-source analysis on the commodity operation data, select data features of the optimized data set according to the analysis results of the multi-source analysis, query the operation commodities in the cross-border e-commerce, and calculate the mutual information value between the data features and the operation commodities, and construct the operation network of the operation commodities based on the mutual information value;

[0137] The user screening module 203 is used to obtain the operating channel of the operating product, query the potential users of the operating product based on the operating channel, query the sticky users of the operating product, analyze the user similarity between the potential users and the sticky users, extract target potential users from the potential users based on the user similarity, construct a screening matrix for the target potential users, and use the screening matrix to screen the target potential users to obtain screened users;

[0138] The operation strategy construction module 204 is used to use the operation network to update the screened users to obtain updated users, and after using the updated users as the target operation users of the operation products, to construct the initial operation strategy of the operation products, to conduct supply risk assessment on the target operation users to obtain assessment results, and to construct the product operation management strategy of the cross-border e-commerce based on the initial operation strategy and the assessment results.

[0139] In detail, each module in the commodity operation management system 200 applied to cross-border e-commerce in the embodiment of the present invention adopts the same method as above when used. Figure 1 The same technical means as the commodity operation management method applied to cross-border e-commerce described in , and can produce the same technical effects, will not be repeated here.

[0140] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. 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 invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A commodity operation management method applied to cross-border e-commerce, characterized in that: The method comprises: Collect commodity operation data on cross-border e-commerce, query key operation attributes of the commodity operation data, divide the commodity operation data based on the key operation attributes to obtain a divided data set, calculate the data gain of the divided data in the divided data set, and optimize the divided data set based on the data gain to obtain an optimized data set; Performing multi-source analysis on the commodity operation data, selecting data features of the optimized data set according to the analysis results of the multi-source analysis, querying the operation commodities in the cross-border e-commerce, and calculating the mutual information value between the data features and the operation commodities, and constructing the operation network of the operation commodities based on the mutual information value; Acquire the operation channel of the operation product, query the potential users of the operation product based on the operation channel, query the sticky users of the operation product, analyze the user similarity between the potential users and the sticky users, extract target potential users from the potential users based on the user similarity, construct a screening matrix for the target potential users, and use the screening matrix to screen the target potential users to obtain screened users; The operation network is used to update the screened users to obtain updated users. After the updated users are used as target operation users of the operation products, an initial operation strategy for the operation products is constructed. A supply risk assessment is performed on the target operation users to obtain an assessment result. Based on the initial operation strategy and the assessment result, a product operation management strategy for the cross-border e-commerce is constructed.

2. The method according to claim 1, characterized in that The data segmentation of the commodity operation data based on the operation key attributes to obtain the segmented data set includes: Performing vector transformation on the key operation attributes, and constructing the vector centroid of the key operation attributes after the vector transformation; Performing vector conversion on the commodity operation data to obtain an operation vector; The vector distance between the operation vector and the vector centroid is calculated using the following formula: Where D represents the vector distance, ∈ represents the spatial dimension of the operation vector, and x i represents the horizontal coordinate of the centroid of the i-th vector, y i represents the ordinate of the centroid of the i-th vector; Based on the vector distance, the commodity operation data is divided to obtain a divided data set.

3. The method according to claim 1, characterized in that The calculating the data gain of the divided data in the divided data set includes: The information entropy of the partitioned data in the partitioned data set is calculated using the following formula: Among them, S represents information entropy, n represents the number of categories of the data set, and c j Indicates the probability that the data set corresponding to the partitioned data c belongs to the jth category; The conditional entropy of the key attributes of the divided data in the divided data set is calculated, and based on the information entropy and the conditional entropy, the data gain of the divided data in the divided data set is calculated using the following formula: Gain=S-Ent Among them, Gain represents data gain, S represents information entropy, and Ent represents conditional entropy.

4. The method according to claim 1, characterized in that: The performing multi-source analysis on the commodity operation data to select data features of the optimized data set according to the analysis results of the multi-source analysis includes: Performing data integration on the commodity operation data to obtain integrated data; determining analysis indicators for the integrated data; Based on the analysis index, performing correlation analysis on the integrated data to obtain a correlation analysis result; Based on the analysis indicators, performing trend analysis on the integrated data to obtain trend analysis results; Based on the analysis indicators, comparative analysis is performed on the integrated data to obtain comparative analysis results; Based on the correlation analysis result, the trend analysis result and the comparison analysis result, data features of the optimized data set are determined.

5. The method according to claim 1, characterized in that The calculating the mutual information value between the data feature and the operating commodity includes: The mutual information value between the data feature and the operating product is calculated using the following formula: Among them, ME(A,B) represents the mutual information value, A represents the data feature, B represents the operating product, P(a,b) represents the joint probability distribution of A and B, P(a) represents the marginal probability distribution of A, P(b) represents the marginal probability distribution of B, b represents the serial number of the operating product, and a represents the serial number of the data feature.

6. The method according to claim 1, characterized in that The analyzing the user similarity between the potential user and the sticky user includes: Performing vector conversion on the potential users and the sticky users to obtain a first vector and a second vector; The vector similarity between the first vector and the second vector is calculated using the following formula: Among them, VS represents vector similarity, represents the first vector, represents the second vector, represents the magnitude of the first vector, represents the magnitude of the second vector, represents the inclination of the space coordinate point g corresponding to the first vector, Represents the inclination of the space coordinate point g corresponding to the second vector; Based on the vector similarity, user similarity between the potential user and the sticky user is determined.

7. The method according to claim 1, characterized in that The step of constructing a screening matrix for target potential users includes: Determine the screening dimensions of the target potential users, and calculate the dimension weights of the screening dimensions; Constructing a matrix framework of the target potential users; Acquire user data of the target potential user; Based on the dimension weights and the user data, the matrix framework is filled with data to obtain a screening matrix.

8. The method according to claim 1, characterized in that The step of updating the screened user by using the operation network to obtain the updated user includes: Using the operation network to construct the interest set of the screened user; Based on the interest set, the following formula is used to calculate the interest preference of the screened user for the interest set: Where F represents the interest preference degree, N(L) represents the set of screened users who have rated the interest set too highly, and P RL Indicates the rating of filtering user R on interest L, represents the average mean of the interests of the filtered user R for its rated ones, M represents the set of filtered users, Represents the rating vector of the filtered user R; According to the interest preference degree, the screened users are updated to obtain updated users.

9. The method according to claim 8, characterized in that The using the operation network to construct the interest set of the screened user includes: Querying the user data of the screened user using the operation network; Extracting data features of the user data; Clustering the data features to obtain cluster features; Constructing interest tags of the clustering features; Performing weight allocation on the interest tags to obtain weight allocation tags; After optimizing the weight distribution labels, the interest set of the screened user is obtained.

10. A commodity operation management system applied to cross-border e-commerce, the system implementing the method according to any one of claims 1 to 9, characterized in that: The system comprises: A data set optimization module is used to collect commodity operation data about cross-border e-commerce, query the key operation attributes of the commodity operation data, divide the commodity operation data based on the key operation attributes to obtain a divided data set, calculate the data gain of the divided data in the divided data set, and optimize the divided data set based on the data gain to obtain an optimized data set; An operation network construction module, used to perform multi-source analysis on the commodity operation data, select data features of the optimized data set according to the analysis results of the multi-source analysis, query the operation commodities in the cross-border e-commerce, and calculate the mutual information value between the data features and the operation commodities, and construct the operation network of the operation commodities based on the mutual information value; A user screening module is used to obtain the operating channels of the operating products, query the potential users of the operating products based on the operating channels, query the sticky users of the operating products, analyze the user similarity between the potential users and the sticky users, extract target potential users from the potential users based on the user similarity, construct a screening matrix for the target potential users, and use the screening matrix to screen the target potential users to obtain screened users; The operation strategy construction module is used to use the operation network to update the screened users to obtain updated users, and after using the updated users as the target operation users of the operation products, to construct the initial operation strategy of the operation products, to conduct supply risk assessment on the target operation users to obtain assessment results, and to construct the commodity operation management strategy of the cross-border e-commerce based on the initial operation strategy and the assessment results.

Images