An intelligent processing system for e-commerce order information based on big data

Abstract

The present invention discloses an e-commerce order information intelligent processing system based on big data, and relates to the technical field of e-commerce. The present invention comprises an information acquisition module, an order analysis module, a decision module and an automatic processing module; the information acquisition module is used to acquire the order information of the user; firstly, before acquiring the order information, the legitimacy of the information acquisition request is verified through an authentication mechanism; the order analysis module is used to analyze the acquired order information; the decision module is used to automatically generate the optimal order processing strategy according to the order analysis result; the present invention utilizes advanced machine learning algorithms and data mining technologies to deeply analyze order data, identify purchase patterns and user behaviors, predict sales trends, and automatically generate the optimal order processing strategy based on data analysis, thereby providing strong decision support for e-commerce enterprises.

Description

Technical Field

[0001] The present invention relates to the technical field of e-commerce, and in particular to an intelligent processing system for e-commerce order information based on big data. Background Art

[0002] With the rapid development of Internet technology and the booming e-commerce, e-commerce platforms have become one of the main channels for consumers to shop. The daily operation of e-commerce platforms generates a large amount of order information, including but not limited to order numbers, purchaser information, product details, payment status, logistics tracking, etc. However, with the surge in the number of orders, traditional order processing methods can no longer meet the market's demand for high efficiency and high accuracy.

[0003] Existing order processing systems mostly rely on manual operations, which is not only time-consuming and labor-intensive, but also prone to errors, resulting in a poor customer experience. In addition, manual processing of large amounts of data is inefficient and difficult to respond to market changes and customer needs in real time. In the context of the big data era, how to effectively utilize these data resources and improve the automation and intelligence level of order processing has become an urgent problem that e-commerce platforms need to solve.

[0004] Some advanced e-commerce platforms have begun to try to apply data analysis and machine learning technologies to optimize order processing. However, these attempts are usually limited to a single data processing link and lack systematic integration and intelligent decision support. Therefore, the market urgently needs an order information intelligent processing system that can comprehensively analyze order information, intelligently predict order trends, automatically formulate processing strategies, and adjust in real time to adapt to market changes.

[0005] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0006] The purpose of the present invention is to solve the problem that the existing e-commerce order information intelligent processing system is usually limited to a single data processing link and lacks systematic integration and intelligent decision support, and to propose an e-commerce order information intelligent processing system based on big data.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] An e-commerce order information intelligent processing system based on big data, comprising:

[0009] Information acquisition module, used to acquire and parse the user's order information;

[0010] The order analysis module is used to analyze the acquired order information;

[0011] The decision-making module is used to automatically generate the optimal order processing strategy based on the order analysis results; the specific steps are as follows:

[0012] Receive data from the order analysis module. Order processing strategies include order trend forecasting, user purchase behavior analysis, and promotion activity suggestions;

[0013] The steps for order trend prediction are as follows:

[0014] First, time series analysis and machine learning techniques are used to predict the trend of order volume;

[0015] Then, the trend is predicted and corrected by the influence of seasonal factors, promotional activities and market dynamics. The quarterly ratio, activation value and market value are obtained through seasonal factors, promotional activities and market dynamics analysis respectively. After normalization, they are entered into the following formula: To obtain the modified parameter value XCZ, where JBZ, CHZ and STZ are quarterly ratio, activation value and market status value respectively. , and They are the preset weight coefficients of quarterly ratio, activation value and market value;

[0016] The calculated correction parameter value is then compared with the five preset correction parameter value intervals, wherein the five correction parameter value intervals correspond to five correction levels, and the five correction levels correspond to the degree of correction of the trend prediction; when the correction parameter value interval corresponding to the obtained real-time correction parameter value is determined, the degree of correction of the trend prediction is determined;

[0017] The automatic processing module is used to automatically process the order process according to the processing strategy determined by the decision module, including order confirmation, inventory preparation and activity determination.

[0018] Furthermore, in the order trend forecasting step, the specific steps of obtaining the quarterly ratio, activation value and market status value through seasonal factors, promotion activities and market dynamics analysis are as follows:

[0019] Seasonal factors are analyzed by obtaining the recorded historical order volume, selecting several years for analysis, summing up the order volume of each quarter of several years, calculating the ratio of the order volume of the four quarters, and determining the current quarter. The ratio of the quarter is used as the standard to measure the impact of seasonal factors on orders;

[0020] Promotional activities are analyzed by collecting user participation, coverage and conversion rate. User participation includes comprehensive analysis of users' average browsing time, likes, reposts and comments on promotional activities. The average browsing time, likes, reposts and comments are marked as ls, dz, zf and pl respectively, and then normalized and entered into the following formula: To obtain the parameter value YCZ;

[0021] The coverage rate is the ratio of the target customer group reached by the promotional activity multiplied by the number of people covered by the promotional activity, and is recorded as the coverage value;

[0022] The conversion rate is the proportion of users who actually place orders among those who participate in the promotion, recorded as the conversion rate value;

[0023] The calculated parameter value, coverage value and conversion rate value are normalized and then input into the following formula: To obtain the activation value CHZ; , and They are the preset weight coefficients for the parameter value, coverage value and conversion rate value respectively;

[0024] Market dynamics are analyzed through market growth rate, market share changes and competition intensity; market growth rate is the increase in the market size of the same type of order within a preset time period, quantified by the number of people and recorded as market value added;

[0025] Market share changes are calculated by counting the changes in market share and recorded as share percentage;

[0026] The competitive intensity is calculated by adding the total number of other similar competing products of the order type to the market share of similar competing products, and the result is recorded as the competitive intensity value.

[0027] The obtained market value added, share ratio and competitive strength value are marked as sz, fz and jq respectively, and then normalized and entered into the following formula: To obtain the market value STZ.

[0028] Furthermore, the specific operation steps of the user purchase behavior analysis in the order processing strategy are as follows:

[0029] First, by extracting and constructing analytical features;

[0030] Then use statistical methods and data mining techniques to identify and construct features that influence user purchasing behavior;

[0031] Then, users are divided into different groups or market segments based on their purchasing behavior characteristics, and unsupervised learning methods are used to identify user groups;

[0032] Then, we apply association rule mining technology to discover frequent patterns and associations in user purchase behaviors; and analyze the associations between the products purchased by users;

[0033] Use machine learning models to predict users’ purchasing behavior and, based on their historical purchasing data and behavior patterns, predict their future purchasing probabilities and preferences.

[0034] Then, based on the results of the user purchasing behavior analysis, we formulate personalized marketing strategies and product recommendations and design targeted promotional activities.

[0035] Furthermore, the specific operation steps of the promotion activity suggestion in the order processing strategy are as follows:

[0036] Firstly, the data of historical promotion activities are obtained, and the activation values ​​of different promotion activities are obtained by calculating the activation value;

[0037] Then analyze the average customer acquisition cost, sustainability and risk assessment of the promotion activities; the average customer acquisition cost is calculated by the average cost required to attract each new customer, and the average cost is recorded as the customer attraction value;

[0038] Durability is calculated by analyzing the average length of time that a promotion can attract customers, recorded as the duration value;

[0039] Risk assessment is to assess the risks brought by the promotional activities and assign a score of 1-10 to the risks based on the assessment, which is recorded as the risk value;

[0040] After normalizing the activation value, customer attraction value, persistence value and risk value, the activation value is used as the bottom circle radius to establish a bottom circle, and the product of the persistence value and the constant k is used as the height to establish a cylinder, and then the center of mass of the established cylinder is used as the center of the circle, and the sum of the customer attraction value and the risk value is used as the radius to establish a transverse cutting circle, and the transverse cutting circle is used to perform left and right horizontal cutting of the established cylinder, and the volume of the irregular shape after cutting is calculated and recorded as the excellent value;

[0041] Sort the priority values ​​of all historical promotions by size, select promotions that match the order products and implement them, and implement the promotions in the order of priority values.

[0042] Furthermore, the specific operation steps of the automatic processing module to automatically process the order flow according to the processing strategy determined by the decision module are as follows:

[0043] The order confirmation includes the following steps: first, automatically checking the completeness and accuracy of the order information, including customer information, product information and payment status;

[0044] The order is then assigned to the appropriate processing team or automated system based on the order's specific requirements, including priority and special processing needs;

[0045] Finally, an order confirmation notification is sent to the customer, including order details and estimated delivery time information;

[0046] Inventory preparation includes the following steps: first, the total order quantity is automatically checked and compared with the existing inventory based on the order trend forecast in the decision module;

[0047] In case of insufficient inventory, the replenishment process is automatically triggered. The specific process is as follows:

[0048] First, the management personnel are notified to make replenishment decisions. The replenishment demand is automatically calculated based on historical sales data, predicted sales trends and current inventory levels. Replenishment orders are generated and purchase requests are automatically sent to suppliers. At the same time, the systems of suppliers and logistics partners are integrated to quickly respond to supply chain changes when inventory is insufficient, and coordinate with suppliers to speed up production or logistics to speed up distribution.

[0049] Combined with the degree of correction of trend forecasts in the decision-making module, the replenishment quantity is adjusted dynamically to optimize the inventory level; additional safety stock is established, and when the inventory is insufficient, the safety stock is used first;

[0050] Finally, we optimize inventory. The specific steps are as follows: integrate multiple suppliers and logistics channels, and select the fastest or lowest-cost replenishment channel to replenish inventory as quickly as possible; then establish a multi-warehouse complementary model to automatically allocate inventory between multiple warehouses, and transfer from sufficient warehouses to out-of-stock warehouses during idle time;

[0051] The specific steps of activity determination are as follows: first, automatically set the rules and conditions of the promotion activity according to the promotion activity selected;

[0052] Then automatically publish promotional information on different channels; then update relevant information of the promotion in real time; finally, display the real-time effects of the promotion, including order data and customer participation.

[0053] Furthermore, the specific operation steps of the information acquisition module to acquire the user's order information are as follows:

[0054] First, before obtaining order information, the legitimacy of the information acquisition request is verified through the authentication mechanism, specifically using OAuth, API key or access token to verify the identity of the acquirer;

[0055] Then, according to business needs, send a data request to obtain order information within a specific time period, and the request contains filtering conditions;

[0056] Receive the response data and return it in JSON or XML format; then verify the accuracy and consistency of the data through verification or digital signature;

[0057] Then parse the received data, extract the key information of the order, convert the data into a recognizable structured format by using a parser or parsing script, and design a reasonable database structure for data storage;

[0058] Finally, synchronize data regularly according to the preset update frequency.

[0059] Furthermore, the specific operation steps of the order analysis module for analyzing the acquired order information are as follows:

[0060] First, the data obtained in the information acquisition module is received and cleaned to remove invalid, incomplete or erroneous data records and process missing values ​​and outliers;

[0061] Then integrate data from different sources and formats into a unified data model, combining historical data and real-time data;

[0062] Then extract features from the raw data and use statistical methods and data mining techniques to identify key features and apply machine learning algorithms to identify purchase patterns and user behavior patterns, and discover potential relationships in the data by using cluster analysis and association rule mining methods;

[0063] Further analyze the time trend of order data, predict future sales trends, and use time series analysis and moving average technology to predict trends;

[0064] Finally, evaluate the efficiency and effectiveness of order processing, including order fulfillment time and error rate, by quantifying performance using key performance indicators; and present the analysis results in the form of charts and dashboards.

[0065] Compared with the prior art, the present invention has the following beneficial effects:

[0066] The present invention uses advanced machine learning algorithms and data mining technology to deeply analyze order data, identify purchase patterns and user behaviors, predict sales trends, and automatically generate optimal order processing strategies based on data analysis, providing strong decision support for e-commerce companies;

[0067] The present invention automates processes such as order confirmation, inventory management, and promotion execution, reduces manual intervention, and improves efficiency and accuracy. At the same time, it can also intelligently optimize inventory levels and promotion selection to ensure optimal resource allocation and agility in market response. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0069] Figure 1 This is the overall system block diagram of the present invention. DETAILED DESCRIPTION

[0070] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0071] It should be understood that the terms "include" and "comprising" used in the specification and claims of the present disclosure indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0072] It should also be understood that the terms used in this disclosure are only for the purpose of describing specific embodiments and are not intended to limit the disclosure. As used in this disclosure and claims, the singular forms of "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should also be further understood that the term "and / or" used in this disclosure and claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0073] like Figure 1 As shown, an e-commerce order information intelligent processing system based on big data includes an information acquisition module, an order analysis module, a decision module and an automatic processing module;

[0074] The information acquisition module is used to obtain the user's order information;

[0075] First, before obtaining order information, the legitimacy of the information acquisition request is verified through an authentication mechanism. Specifically, OAuth, API key or access token is used to verify the identity of the acquirer to avoid information leakage. OAuth is an open standard authorization protocol that allows users to authorize third-party applications to access specific information stored on another service provider without providing usernames and passwords to third-party applications. OAuth authorizes access by using tokens, which do not contain any sensitive information, such as passwords. It includes the following steps: the user accesses the third-party application and agrees to the authorization; the third-party application obtains the authorization token (Access Token); third-party applications use authorization tokens to access user data on service providers; API key is a simple authentication mechanism, which is a unique string of characters used to identify the user or application calling the API. The API key is sent together with the request so that the API service can verify the legitimacy of the request and control access rights; according to business needs, send data requests to obtain order information within a specific time period. The request can contain filtering conditions, including order status, product category and transaction amount, in order to obtain specific types of order data; then receive response data and return it in JSON or XML format; then verify the accuracy and consistency of the data through verification or digital signature; then parse the received data, extract the key information of the order, convert the data into a recognizable structured format by using a parser or parsing script, and design a reasonable database structure for data storage; then synchronize the data regularly according to the preset update frequency to ensure the latest order information.

[0076] The order analysis module is used to analyze the acquired order information;

[0077] The specific steps are as follows:

[0078] Receive data obtained from the information acquisition module, clean the data, remove invalid, incomplete or erroneous data records, process missing values ​​and outliers, and ensure the accuracy of analysis; then integrate data from different sources and formats into a unified data model, merge historical data and real-time data, to facilitate time series analysis;

[0079] Useful features are then extracted from the raw data, including order amounts, purchase frequency, and customer geographic distribution, and key features are identified using statistical methods and data mining techniques. Machine learning algorithms are then applied to identify purchase patterns and user behavior patterns, and potential relationships in the data are discovered using cluster analysis and association rule mining methods.

[0080] Reanalyze the time trend of order data and predict future sales trends, using time series analysis and moving average techniques to predict trends; evaluate the efficiency and effectiveness of order processing, including order fulfillment time and error rate, and quantify performance by using key performance indicators (KPIs);

[0081] Finally, the analysis results are intuitively displayed in the form of charts and dashboards, allowing decision makers to quickly understand the data content and analysis conclusions.

[0082] The decision-making module is used to automatically generate the optimal order processing strategy based on the order analysis results;

[0083] The order processing strategy includes: order trend prediction, user purchase behavior analysis and promotion activity suggestions; firstly, it receives data from the order analysis module, including sales data, customer behavior data and promotion activity data, integrates historical data and real-time data, and provides comprehensive information support for decision-making;

[0084] Order trend forecasting uses time series analysis and machine learning technology to forecast the order volume trend; then forecasts and corrects the impact of seasonal factors, promotional activities and market dynamics on the trend. The specific steps are as follows:

[0085] The seasonal factors are obtained by obtaining the recorded historical order volume, intercepting several years for analysis, summing up the order volume of each quarter of several years, calculating the ratio of the order volume of the four quarters, namely the ratio of the first quarter, the ratio of the second quarter, the ratio of the third quarter and the ratio of the fourth quarter, and determining the current quarter, and using the ratio of this quarter as the standard for measuring the impact of seasonal factors on orders;

[0086] Promotional activities are analyzed by collecting user participation, coverage and conversion rate. User participation includes comprehensive analysis of users' average browsing time, likes, reposts and comments on promotional activities. The average browsing time, likes, reposts and comments are marked as ls, dz, zf and pl respectively, and then normalized and entered into the following formula: To obtain the usage parameter YCZ; the coverage rate is the ratio of the target customer group reached by the promotion activity multiplied by the number of people covered by the promotion activity, and is recorded as the coverage value, which is used as the standard for measuring the coverage rate; the conversion rate is the ratio of users who actually place orders among the users who participate in the promotion activity, which is recorded as the conversion rate value, and is used as the standard for measuring the conversion rate; the calculated usage parameter, coverage value and conversion rate value are normalized and then entered into the following formula: To obtain the activation value CHZ, and use this activation value CHZ as a standard to measure the impact of promotional activities on orders; , and are the preset weight coefficients of the parameter value, coverage value and conversion rate value, and are 0.954, 1.035 and 1.004 respectively. FFZ and ZLZ refer to the coverage value and conversion rate value respectively;

[0087] Market dynamics are analyzed through market growth rate, market share change and competition intensity; market growth rate is the increase in the market size of the same type of order within a preset time period, quantified by the number of people and recorded as market value added; market share change is recorded as share percentage by counting the change in market share, and this share percentage is used as the standard for measuring market share changes; competition intensity is recorded as the competitive strength value by counting the total number of other similar competing products of the same order type plus the sum of the market shares of similar competing products; the obtained market value added, share percentage and competitive strength value are calibrated as sz, fz and jq respectively, and after normalization, they are entered into the following formula: To obtain the market state value STZ, and use this market state value as the standard for the impact of market dynamics on orders;

[0088] Then, the calculated quarterly ratio, activation value and market status value are normalized and entered into the following formula: To obtain the modified parameter value XCZ, where JBZ is the quarterly ratio, , and They are the preset weight coefficients of quarterly ratio, activation value and market value, and their values ​​are 1.241, 0.943 and 0.884 respectively;

[0089] The calculated correction parameter value is then compared with the five preset correction parameter value intervals, wherein the five correction parameter value intervals correspond to five correction levels, namely the first correction level, the second correction level, the third correction level, the fourth correction level and the fifth correction level, and the five correction levels correspond to the correction degree of the trend forecast of 1%, 2%, 3%, 4% and 5% respectively; when the correction parameter value interval corresponding to the obtained real-time correction parameter value is determined, the correction degree of the trend forecast is determined, so as to more accurately predict the future order volume;

[0090] User purchase behavior analysis extracts and constructs analytical features, including user purchase frequency, average purchase amount, last purchase time (recency), and purchase diversity; statistical methods and data mining techniques are then used to identify and construct features that influence user purchase behavior;

[0091] Then, based on the characteristics of users’ purchasing behavior, users are divided into different groups or market segments, and cluster analysis including K-means or hierarchical clustering unsupervised learning methods are used to identify user groups. Association rule mining techniques including Apriori algorithm are then applied to discover frequent patterns and associations in users’ purchasing behavior, and the associations between the products purchased by users are analyzed, including combinations of products purchased at the same time. Machine learning models including decision trees, random forests or neural networks are then used to predict users’ purchasing behavior, and based on users’ historical purchasing data and behavior patterns, their future purchasing probabilities and preferences are predicted. Based on the results of the user purchasing behavior analysis, personalized marketing strategies and product recommendations are formulated, and targeted promotional activities are designed to improve users’ purchase conversion rates and customer loyalty.

[0092] The promotion activity suggestion is obtained by obtaining the data of historical promotion activities, and the activation value of different promotion activities is obtained by calculating the activation value. Then the average customer acquisition cost, sustainability and risk assessment of the promotion activities are obtained for analysis. The average customer acquisition cost is calculated by the average cost required to attract each new customer, and the average cost is recorded as the customer attraction value; sustainability is analyzed by analyzing the average length of time that promotion activities can attract customers, recorded as sustainability value; risk assessment is performed by evaluating the risks that may be brought about by promotion activities, including inventory backlogs or negative impacts, and assigning a score of 1-10 to the risk based on the assessment, recorded as the risk value. The higher the risk value, the greater the corresponding risk of the assessment, and vice versa. Then The activation value, customer attraction value, continuity value and risk value obtained are normalized and the activation value is used as the radius of the bottom circle to establish the bottom circle, and the product of the continuity value and the constant k is used as the height to establish a cylinder with the constant k being 8.33. The center of mass of the established cylinder is used as the center of the circle and the sum of the customer attraction value and the risk value is used as the radius to establish a transverse cutting circle. The transverse cutting circle is used to cut the established cylinder horizontally from left to right, and the volume of the irregular shape after cutting is calculated and recorded as the superior value. This superior value is used as the standard for measuring the effectiveness of promotional activities. The superior values ​​of all historical promotional activities are sorted by size, and promotional activities suitable for order products are selected for promotion. The order of promotional activities is implemented in sequence according to the size of the superior value.

[0093] The automatic processing module is used to automatically process the order process according to the processing strategy determined by the decision module, including order confirmation, inventory preparation and activity determination;

[0094] Order confirmation includes the following steps: first, automatically checking the completeness and accuracy of order information, including customer information, product information and payment status; then assigning the order to the corresponding processing team or automated system based on the specific requirements of the order, including priority and special processing needs; and finally sending an order confirmation notification to the customer, including order details and estimated delivery time information;

[0095] Inventory preparation includes the following steps: automatically check the total order volume, and check the order trend forecast in the decision module with the existing inventory to ensure that there are enough goods to meet the existing and subsequent order needs; in the case of insufficient inventory, automatically trigger the replenishment process, the specific process is as follows: first notify the management personnel to determine the replenishment decision, and then automatically calculate the replenishment demand through historical sales data, predicted sales trends and current inventory levels, and generate replenishment orders at the same time, and automatically send purchase requests to suppliers; and integrate with the systems of suppliers and logistics partners to achieve information sharing and process collaboration. When inventory is insufficient, quickly respond to changes in the supply chain and coordinate suppliers to speed up production or logistics to speed up distribution; then combine the degree of correction of trend forecasts in the decision module to dynamically adjust the replenishment quantity and optimize inventory levels; then set up additional safety stock to cope with sudden market demand. When inventory is insufficient, safety stock is used first to meet orders;

[0096] Finally, we optimize inventory. The specific steps are as follows: integrate multiple suppliers and logistics channels, and select the fastest or lowest-cost replenishment channel to replenish inventory as quickly as possible; then establish a multi-warehouse complementary model to automatically allocate inventory between multiple warehouses to solve the problem of insufficient local inventory, and transfer inventory from sufficient warehouses to out-of-stock warehouses during idle time to balance the inventory levels of each warehouse;

[0097] The specific steps for activity determination are as follows: first, automatically set the rules and conditions of the promotion according to the selected promotion, including the discount rate, event time and participating products, and then automatically publish the promotion information on websites, social media, mailing lists and other channels; then update the relevant information of the promotion in real time, including the remaining inventory and the number of discounts used; and display the real-time effects of the promotion, including order data and customer engagement.

[0098] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. An intelligent processing system for e-commerce order information based on big data, characterized in that: include: Information acquisition module, used to acquire and parse the user's order information; The order analysis module is used to analyze the acquired order information; The decision-making module is used to automatically generate the optimal order processing strategy based on the order analysis results; the specific steps are as follows: Receive data from the order analysis module. The order processing strategy includes order trend prediction, user purchase behavior analysis and promotion activity suggestions. The process of promotion activity suggestions is as follows: Firstly, the data of historical promotion activities are obtained, and the activation values ​​of different promotion activities are obtained by calculating the activation value; Then analyze the average customer acquisition cost, sustainability and risk assessment of the promotion activities; the average customer acquisition cost is calculated by the average cost required to attract each new customer, and the average cost is recorded as the customer attraction value; Durability is calculated by analyzing the average length of time that a promotion can attract customers, recorded as the duration value; Risk assessment is to assess the risks brought by the promotional activities and assign a score of 1-10 to the risks based on the assessment, which is recorded as the risk value; After normalizing the activation value, customer attraction value, persistence value and risk value, the activation value is used as the bottom circle radius to establish a bottom circle, and the product of the persistence value and the constant k is used as the height to establish a cylinder, and then the center of mass of the established cylinder is used as the center of the circle, and the sum of the customer attraction value and the risk value is used as the radius to establish a transverse cutting circle, and the transverse cutting circle is used to perform left and right horizontal cutting of the established cylinder, and the volume of the irregular shape after cutting is calculated and recorded as the excellent value; Sort the priority values ​​of all historical promotional activities by size, select promotional activities that match the order products and implement them, and implement the promotional activities in the order of priority values; The steps for order trend prediction are as follows: First, time series analysis and machine learning techniques are used to predict the trend of order volume; Then, the trend is predicted and corrected by the influence of seasonal factors, promotional activities and market dynamics. The quarterly ratio, activation value and market value are obtained through seasonal factors, promotional activities and market dynamics analysis respectively. After normalization, they are entered into the following formula: To obtain the modified parameter value XCZ, where JBZ, CHZ and STZ are quarterly ratio, activation value and market status value respectively. They are the preset weight coefficients of quarterly ratio, activation value and market value; The calculated correction parameter value is then compared with the five preset correction parameter value intervals, wherein the five correction parameter value intervals correspond to five correction levels, and the five correction levels correspond to the degree of correction of the trend prediction; when the correction parameter value interval corresponding to the obtained real-time correction parameter value is determined, the degree of correction of the trend prediction is determined; The specific steps to obtain the quarterly ratio, activation value and market status value through seasonal factors, promotion activities and market dynamics analysis are as follows: Seasonal factors are analyzed by obtaining the recorded historical order volume, selecting several years for analysis, summing up the order volume of each quarter of several years, calculating the ratio of the order volume of the four quarters, and determining the current quarter. The ratio of the quarter is used as the standard to measure the impact of seasonal factors on orders; Promotional activities are analyzed by collecting user participation, coverage and conversion rate. User participation includes comprehensive analysis of users' average browsing time, likes, reposts and comments on promotional activities. The average browsing time, likes, reposts and comments are marked as ls, dz, zf and pl respectively, and then normalized and entered into the following formula: To obtain the parameter value YCZ; The coverage rate is the ratio of the target customer group reached by the promotional activity multiplied by the number of people covered by the promotional activity, and is recorded as the coverage value; The conversion rate is the proportion of users who actually place orders among those who participate in the promotion, recorded as the conversion rate value; The calculated parameter value, coverage value and conversion rate value are normalized and then input into the following formula: To obtain the activation value CHZ; are the preset weight coefficients of the parameter value, coverage value and conversion rate value, FFZ and ZLZ refer to the coverage value and conversion rate value respectively; Market dynamics are analyzed through market growth rate, market share changes and competition intensity; market growth rate is the increase in the market size of the same type of order within a preset time period, quantified by the number of people and recorded as market value added; Market share changes are calculated by counting the changes in market share and recorded as share percentage; The competitive intensity is calculated by adding the total number of other similar competing products of the order type to the market share of similar competing products, and the result is recorded as the competitive intensity value. The obtained market value added, share ratio and competitive strength value are marked as sz, fz and jq respectively, and then normalized and entered into the following formula: To obtain the market value STZ; The automatic processing module is used to automatically process the order process according to the processing strategy determined by the decision module, including order confirmation, inventory preparation and activity determination. The specific steps are as follows: Order confirmation includes the following steps: first, automatically checking the completeness and accuracy of the order information, including customer information, product information and payment status; The order is then assigned to the appropriate processing team or automated system based on the order's specific requirements, including priority and special processing needs; Finally, an order confirmation notification is sent to the customer, including order details and estimated delivery time information; Inventory preparation includes the following steps: first, the total order quantity is automatically checked and compared with the existing inventory based on the order trend forecast in the decision module; In case of insufficient inventory, the replenishment process is automatically triggered. The specific process is as follows: First, the management personnel are notified to make replenishment decisions. The replenishment demand is automatically calculated based on historical sales data, predicted sales trends and current inventory levels. Replenishment orders are generated and purchase requests are automatically sent to suppliers. At the same time, the systems of suppliers and logistics partners are integrated to quickly respond to supply chain changes when inventory is insufficient, and coordinate with suppliers to speed up production or logistics to speed up distribution. Combined with the degree of correction of trend forecasts in the decision-making module, the replenishment quantity is adjusted dynamically to optimize the inventory level; additional safety stock is established, and when the inventory is insufficient, the safety stock is used first; The specific steps for inventory optimization are as follows: Integrate multiple suppliers and logistics channels, and select the fastest or lowest-cost replenishment channel to replenish inventory as quickly as possible; then establish a multi-warehouse complementary model to automatically allocate inventory between multiple warehouses, and transfer from sufficient warehouses to out-of-stock warehouses during idle time; The specific steps of activity determination are as follows: first, automatically set the rules and conditions of the promotion activity according to the promotion activity selected; Then automatically publish promotional information on different channels; then update relevant information of the promotion in real time; finally, display the real-time effects of the promotion, including order data and customer participation.

2. According to claim 1, the intelligent processing system for e-commerce order information based on big data is characterized in that: The specific operation steps of the user purchase behavior analysis in the order processing strategy are as follows: First, by extracting and constructing analytical features; Then use statistical methods and data mining techniques to identify and construct features that influence user purchasing behavior; Then, users are divided into different groups or market segments based on their purchasing behavior characteristics, and unsupervised learning methods are used to identify user groups; Then, we apply association rule mining technology to discover frequent patterns and associations in user purchase behaviors; and analyze the associations between the products purchased by users; Use machine learning models to predict users’ purchasing behavior and, based on their historical purchasing data and behavior patterns, predict their future purchasing probabilities and preferences. Then, based on the results of the user purchasing behavior analysis, we formulate personalized marketing strategies and product recommendations, and design targeted promotional activities.

3. According to the big data-based e-commerce order information intelligent processing system of claim 1, it is characterized by: The specific operation steps of the information acquisition module to acquire the user's order information are as follows: First, before obtaining order information, the legitimacy of the information acquisition request is verified through the authentication mechanism, specifically using OAuth, API key or access token to verify the identity of the acquirer; Then, according to business needs, send a data request to obtain order information within a specific time period, and the request contains filtering conditions; Then receive the response data and return it in JSON or XML format; The data is then verified for accuracy and consistency through verification or digital signature means; Then parse the received data, extract the key information of the order, convert the data into a recognizable structured format by using a parser or parsing script, and design a reasonable database structure for data storage; Finally, synchronize data regularly according to the preset update frequency.

4. According to the big data-based e-commerce order information intelligent processing system of claim 1, it is characterized in that: The specific operation steps of the order analysis module to analyze the acquired order information are as follows: First, the data obtained in the information acquisition module is received and cleaned to remove invalid, incomplete or erroneous data records and process missing values ​​and outliers; Then integrate data from different sources and formats into a unified data model, combining historical data and real-time data; Then extract features from the raw data and use statistical methods and data mining techniques to identify key features and apply machine learning algorithms to identify purchase patterns and user behavior patterns, and discover potential relationships in the data by using cluster analysis and association rule mining methods; Further analyze the time trend of order data, predict future sales trends, and use time series analysis and moving average technology to predict trends; Finally, evaluate the efficiency and effectiveness of order processing, including order fulfillment time and error rate, by quantifying performance using key performance indicators; and present the analysis results in the form of charts and dashboards.

Images