Method and device for constructing electronic commerce large model, and medium
By building an e-commerce big model, combining historical transaction data, logistics data and unstructured data, the limitations of data utilization and decision-making support in the development of e-commerce are solved, and more accurate market positioning and business decision-making support are achieved.
Patent Information
- Application Number
- CN202411486108.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-23
- Publication Date
- 2025-02-14
AI Technical Summary
The development of e-commerce in the existing technology lacks a large platform for data utilization, model construction, system scalability and future trend forecasting, resulting in limitations in decision-making support, making it difficult for enterprises to fully understand the operating environment and market trends, miss business opportunities or face market risks.
By obtaining historical transaction data, logistics data and unstructured data, using natural language processing to extract unstructured data features, build sales forecasting models and logistics timeliness prediction models, and establish e-commerce large models based on e-commerce industry databases and AI models. , perform cross-verification and parameter tuning, and ultimately realize the microservice and service discovery mechanism of the e-commerce big model.
It realizes comprehensive data analysis and decision-making support, helping enterprises make smarter business decisions, avoid risks, seize opportunities, achieve sustainable development, and improve the accuracy of market positioning, product recommendations and customer service.
Smart Images
Figure CN119443269A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of e-commerce technology, and in particular to a method, device and medium for constructing a large e-commerce model. Background Art
[0002] In recent years, national policies have attached great importance to and supported the development of e-commerce. The government has introduced a series of policy measures aimed at promoting the healthy development of e-commerce, including optimizing the e-commerce business environment, strengthening the construction of e-commerce infrastructure, and promoting the deep integration of e-commerce and traditional industries. The implementation of these policies has provided strong guarantees and support for the rapid development of e-commerce.
[0003] However, without a large platform that fully integrates and utilizes historical transaction data, logistics data, and unstructured data, companies are unable to fully understand their operating environment and market trends. Furthermore, companies face a series of problems in data utilization, model building, system scalability, user experience, and resource utilization. There are limitations in decision support, which causes companies to miss business opportunities or face market risks. The inability to effectively predict sales trends may lead to problems such as excessive inventory or out-of-stocks, increasing operating costs.
[0004] Through the above analysis, the problems and defects of the prior art are as follows:
[0005] The development of e-commerce in existing technologies lacks data utilization, model building, system scalability, and a large platform for predicting future trends, and has limitations in decision support. Summary of the invention
[0006] The embodiments of the present application provide a method, device and medium for constructing a large e-commerce model, which can solve the problems in the prior art of e-commerce development, the lack of data utilization, model construction, system scalability, and a large platform for predicting future trends, and the limitations in decision support.
[0007] In a first aspect, an embodiment of the present application provides a method for constructing an e-commerce big model, the method comprising: obtaining historical transaction data, logistics data, and unstructured data, and extracting features of the unstructured data through natural language processing, the unstructured data including industry data, domestic and foreign market data, to obtain an e-commerce industry database; based on the historical transaction data and logistics data, constructing a sales forecasting model and a logistics timeliness forecasting model through Hadoop, and establishing an e-commerce model based on the e-commerce industry database and the AI big model; cross-validating and optimizing parameters of the sales forecasting model and the logistics timeliness forecasting model, and integrating them with the e-commerce model to obtain an e-commerce big model; microservice-izing the e-commerce big model, and configuring a service discovery mechanism to enable communication between microservices.
[0008] In one implementation of the present application, the e-commerce big model is microserviced, and a service discovery mechanism is configured to enable communication between microservices, specifically including: splitting the e-commerce big model into multiple microservice modules, the microservice modules include a payment module, an order module, a logistics module and a prediction module; configuring a RESTful API interface for the microservice module, and registering the address information to the service discovery tool when the microservice module is started; when the order module calls the logistics module, querying the service discovery tool for the address information of the logistics module.
[0009] In one implementation of the present application, features of unstructured data are extracted through natural language processing, specifically including: cleaning and preprocessing unstructured data within a preset time period, using lexical analysis and syntactic analysis in NLP technology to extract users and scenarios in the text, where users include corporate users and individual users, and scenarios include corporate side scenarios, social side scenarios, and industry side scenarios; performing cross-scenario analysis on corporate side scenarios, social side scenarios, and industry side scenarios, and using supervised learning algorithms to construct prediction models respectively; and integrating prediction models.
[0010] In one implementation of the present application, after integrating the prediction model, the method also includes: obtaining real-time transaction data, logistics data, and unstructured data, and obtaining the prediction results for the next preset time period based on the prediction model, and the prediction results are deployable models; comparing with actual data through an API interface to track the model prediction accuracy.
[0011] In one implementation of the present application, the method also includes: providing an enterprise user tracking option; when the enterprise user clicks, using the enterprise user behavior data and historical transaction data to build an enterprise user portrait and product portrait; based on the matching degree of the user portrait and the product portrait, using collaborative filtering, content-based recommendation and other algorithms to generate a recommendation list for the user.
[0012] In one implementation of the present application, after obtaining the prediction results for the next preset time period, the method further includes: providing a strategy prediction interface based on the prediction results; and providing user interaction functions for filtering conditions, time period selection, or exporting prediction results.
[0013] In one implementation of the present application, the method also includes: extracting entities, relationships and attributes from unstructured data; constructing an e-commerce industry knowledge graph based on entities and relationships, the e-commerce industry knowledge graph including a product graph, a user graph, and a market graph; discovering market trends through graph mining technology, and integrating the knowledge graph with the e-commerce big model.
[0014] In one implementation of the present application, the method further includes: establishing a user feedback mechanism through online surveys and user comments, and establishing a user feedback response mechanism to respond to user feedback in a timely manner.
[0015] In a second aspect, an embodiment of the present application also provides a device for constructing an e-commerce big model, the device comprising at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can: obtain historical transaction data, logistics data, and unstructured data, and extract features of the unstructured data through natural language processing, wherein the unstructured data includes industry data, domestic and foreign market data, to obtain an e-commerce industry database; based on the historical transaction data and logistics data, construct a sales forecasting model and a logistics timeliness forecasting model through Hadoop, and establish an e-commerce model based on the e-commerce industry database and the AI big model; cross-validate and optimize parameters of the sales forecasting model and the logistics timeliness forecasting model, and integrate them with the e-commerce model to obtain an e-commerce big model; microservice the e-commerce big model, and configure a service discovery mechanism to enable communication between microservices.
[0016] On the third aspect, the embodiment of the present application also provides a non-volatile computer storage medium for constructing an e-commerce big model, storing computer executable instructions, and the computer executable instructions are set to: obtain historical transaction data, logistics data and unstructured data, and extract the characteristics of the unstructured data through natural language processing, the unstructured data includes industry data, domestic and foreign market data, and obtain an e-commerce industry database; based on the historical transaction data and logistics data, build a sales forecasting model and a logistics timeliness forecasting model through Hadoop, and establish an e-commerce model based on the e-commerce industry database and the AI big model; cross-validate and optimize the parameters of the sales forecasting model and the logistics timeliness forecasting model, and integrate them with the e-commerce model to obtain an e-commerce big model; microservice the e-commerce big model, and configure a service discovery mechanism to enable communication between microservices.
[0017] The embodiments of the present application provide a method, device and medium for constructing a large e-commerce model, which integrates the sales forecasting model, the logistics timeliness forecasting model and the e-commerce model established based on the e-commerce industry database and the AI large model to form a comprehensive e-commerce large model. The e-commerce large model can provide comprehensive data analysis and decision-making support for enterprises, help enterprises make more informed business decisions, help enterprises avoid risks, seize opportunities, and achieve sustainable development. It helps enterprises achieve more accurate market positioning, product recommendations and customer service. It can effectively integrate resources from multiple parties, improve the digitalization level of the e-commerce industry, and provide accurate and efficient decision-making support and services to governments, enterprises, society and other parties. Through the construction of this system, it can promote the quality upgrade and high-quality development of the e-commerce industry, promote the transformation and upgrading of traditional industries, enhance the core competitiveness of e-commerce enterprises, and help small and medium-sized enterprises grow and develop. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0019] Figure 1 A flow chart of a method for constructing a large e-commerce model provided in an embodiment of the present application;
[0020] Figure 2 A user and scenario diagram of a method for constructing an e-commerce large model provided in an embodiment of the present application Figure 1 ;
[0021] Figure 3 A user and scenario diagram of a method for constructing an e-commerce large model provided in an embodiment of the present application Figure 2 ;
[0022] Figure 4 A schematic diagram of the internal structure of a device for building a large e-commerce model provided in an embodiment of the present application. DETAILED DESCRIPTION
[0023] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.
[0024] The embodiments of the present application provide a method, device and medium for constructing a large e-commerce model, which solves the problems in the prior art of e-commerce development, lack of data utilization, model construction, system scalability, and a large platform for predicting future trends, and limitations in decision support.
[0025] The technical solution proposed in the embodiments of the present application is described in detail below with reference to the accompanying drawings.
[0026] Figure 1 A flowchart of a method for constructing a large e-commerce model provided in an embodiment of the present application. Figure 1 As shown, a method for constructing an e-commerce large model provided in an embodiment of the present application specifically includes the following steps:
[0027] Step 10: Obtain historical transaction data, logistics data, and unstructured data, and extract the features of unstructured data through natural language processing. Unstructured data includes industry data, domestic and foreign market data, and obtain an e-commerce industry database;
[0028] In this step, we analyze the policy environment, market demand and industry trends for the development of the e-commerce industry, clarify the construction goals of the e-commerce industry brain system, and form a comprehensive and accurate e-commerce industry database by collecting and integrating data resources from multiple parties such as government, enterprises, and society.
[0029] As an optional embodiment, extracting features of unstructured data through natural language processing may specifically include: Step 101: cleaning and preprocessing the unstructured data within a preset time period, using lexical analysis and syntactic analysis in NLP technology to extract users and scenarios in the text, where users include corporate users and individual users, and scenarios include corporate side scenarios, social side scenarios, and industry side scenarios; Step 102: performing cross-scenario analysis on corporate side scenarios, social side scenarios, and industry side scenarios, and using supervised learning algorithms to respectively construct prediction models; Step 103: integrating the prediction models.
[0030] In this step, for example, we select the data of the most recent three months as the analysis object, remove duplicate, invalid or advertising content, correct spelling errors and grammatical errors, and convert the text into a unified format and encoding; determine the user's environment or situation based on the text content, such as "We plan to update the company's IT equipment in the next fiscal year - corporate procurement scenario, "The electronic product market is very hot recently" - social scenario, "The demand for tablets in the education industry is growing" - industry scenario. If the forecasting model shows that the demand for tablets in the education industry will increase significantly in the future, we can increase the inventory of related products in advance and optimize the marketing strategy to seize this market opportunity.
[0031] like Figure 2 and Figure 3 As shown, it can connect the data from "four sides", namely, the government side, the industry side, the social side and the enterprise side, to ensure the comprehensiveness and accuracy of the data, and can conduct intelligent analysis of massive e-commerce data and output "application scenarios + capability components" to meet the personalized needs of different user groups.
[0032] As an optional embodiment, after integrating the prediction model, the method may further include: Step 104: acquiring real-time transaction data, logistics data and unstructured data, and obtaining the prediction result for the next preset time period based on the prediction model, and the prediction result is a deployable mode; Step 105: comparing with the actual data through the API interface to track the model prediction accuracy.
[0033] In this step, for example, transaction data and logistics data before October 1, 2023 are obtained from the database. At the same time, unstructured data such as user comments and discussions are obtained through social media monitoring tools. The sales forecast results from October 8 to October 14, 2023 are calculated, including the sales volume and inventory demand of each commodity category. The forecast results are presented to the operation team in a deployable mode. The operation team formulates corresponding sales strategies and inventory plans based on the forecast results. After October 14, 2023, the actual transaction data and logistics data are obtained. The actual data are compared with the previous forecast results through the API interface, and the prediction accuracy of the model is calculated. It is found that the prediction accuracy of some commodity categories is low. For these low-accuracy commodity categories, the model is tuned or retrained.
[0034] Step 20: Based on historical transaction data and logistics data, build a sales forecasting model and a logistics time efficiency forecasting model through Hadoop, and build an e-commerce model based on the e-commerce industry database and AI big model;
[0035] In this step, Hadoop’s data processing capabilities are used to clean, convert, and integrate data. Machine learning algorithms, such as decision trees, random forests, and support vector machines, are used to build sales forecasting models. The logistics timeliness in the future is also predicted to help the platform optimize logistics planning and distribution strategies.
[0036] Step 30: Cross-validate and optimize the parameters of the sales forecast model and the logistics time efficiency forecast model, and integrate them with the e-commerce model to obtain the e-commerce large model;
[0037] In this step, the K-fold cross-validation method is used to divide the data set into K subsets, and K training and testing are performed. Each time, K-1 subsets are used for training, and the remaining subset is used for testing. K test results are obtained, and the overall performance of the model is evaluated by averaging these results to reduce the variance of the evaluation results and improve the reliability of the evaluation. Methods such as grid search or random search are used to exhaustively or randomly sample parameter combinations within the predefined parameter range, and the performance of each parameter combination is evaluated through cross-validation to select the optimal parameter combination.
[0038] Step 40: Microservice the e-commerce big model and configure the service discovery mechanism to enable communication between microservices.
[0039] As an optional embodiment, the e-commerce big model is microserviced and a service discovery mechanism is configured to enable communication between microservices. Specifically, the following may be included: Step 401: splitting the e-commerce big model into multiple microservice modules, the microservice modules including a payment module, an order module, a logistics module and a prediction module; Step 402: configuring a RESTful API interface for the microservice module, and registering the address information into a service discovery tool when the microservice module is started; Step 403: when the order module calls the logistics module, querying the service discovery tool for the address information of the logistics module.
[0040] In this step, when the order module needs to call the functions of the logistics module, for example, to query the logistics information of a certain order, it will first query the service discovery tool for the address information of the logistics module. The service discovery tool will return the address of the logistics module based on the registered information. Then, the order module will use this address information to call the functions of the logistics module through the RESTful API interface. In this way, the order module can communicate with the logistics module to realize the processing of business logic.
[0041] As an optional embodiment, the method may also include: providing an enterprise user tracking option; when the enterprise user clicks, using the enterprise user behavior data and historical transaction data to build an enterprise user portrait and product portrait; based on the matching degree of the user portrait and the product portrait, using collaborative filtering, content-based recommendation and other algorithms to generate a recommendation list for the user.
[0042] In this step, while providing tracking functions, the privacy and security of corporate users are ensured; based on the analyzed corporate user behavior characteristics and historical transaction data, a corporate user portrait is constructed, and a product portrait is constructed based on the attributes, categories, prices, sales volume and other information of the goods; the matching degree can be obtained through similarity calculation, distance measurement and other methods, reflecting the potential demand and interest of corporate users in the product.
[0043] As an optional embodiment, after obtaining the prediction result for the next preset time period, the method may further include: providing a strategy prediction interface based on the prediction result; providing user interaction functions for filtering conditions, time period selection or prediction result export.
[0044] In this step, for example, line graphs, bar graphs, pie charts and other charts can be used to display forecast data for different time periods, different products or different regions; users can filter forecast results based on product category, brand, region and other conditions; users can choose to view forecast results in different time periods; users can compare data from different time periods to understand changes in sales trends and logistics timeliness.
[0045] As an optional embodiment, the method may also include: extracting entities, relationships and attributes from unstructured data; constructing an e-commerce industry knowledge graph based on entities and relationships, the e-commerce industry knowledge graph including a product graph, a user graph, and a market graph; discovering market trends through graph mining technology, and integrating the knowledge graph with the e-commerce big model.
[0046] In this step, for example, in a recommendation system, by considering the social relationships in the user graph, products that are more in line with the preferences of the user's social circle can be recommended to the user.
[0047] As an optional embodiment, the method may further include: establishing a user feedback mechanism through online surveys and user comments, and establishing a user feedback response mechanism to respond to user feedback in a timely manner.
[0048] The above is an embodiment of the method proposed in this application. Based on the same inventive concept, the embodiment of this application also provides a device for constructing a large e-commerce model, the structure of which is as follows: Figure 4 shown.
[0049] Figure 4 This is a schematic diagram of the internal structure of a device for building a large e-commerce model provided in an embodiment of the present application. Figure 4 As shown, the device includes:
[0050] at least one processor 401;
[0051] and, a memory 402 communicatively coupled to the at least one processor;
[0052] Among them, the memory 402 stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor 401 so that the at least one processor 401 can: obtain historical transaction data, logistics data and unstructured data, and extract the characteristics of unstructured data through natural language processing, the unstructured data includes industry data, domestic and foreign market data, and obtain an e-commerce industry database; according to the historical transaction data and logistics data, build a sales forecasting model and a logistics time prediction model through Hadoop, and establish an e-commerce model based on the e-commerce industry database and the AI big model; cross-validate and optimize the parameters of the sales forecasting model and the logistics time prediction model, and integrate them with the e-commerce model to obtain an e-commerce big model; microservice the e-commerce big model, and configure a service discovery mechanism to enable communication between microservices.
[0053] Some embodiments of the present application provide corresponding Figure 1 A non-volatile computer storage medium for constructing an e-commerce big model, storing computer executable instructions, wherein the computer executable instructions are set to: obtain historical transaction data, logistics data and unstructured data, and extract features of unstructured data through natural language processing, wherein the unstructured data includes industry data, domestic and foreign market data, to obtain an e-commerce industry database; based on the historical transaction data and logistics data, build a sales forecasting model and a logistics timeliness forecasting model through Hadoop, and establish an e-commerce model based on the e-commerce industry database and the AI big model; cross-validate and optimize parameters of the sales forecasting model and the logistics timeliness forecasting model, and integrate them with the e-commerce model to obtain an e-commerce big model; microservice the e-commerce big model, and configure a service discovery mechanism to enable communication between microservices.
[0054] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the IoT device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.
[0055] The system and medium provided in the embodiments of the present application correspond one-to-one to the method. Therefore, the system and medium also have similar beneficial technical effects to the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the system and medium will not be repeated here.
[0056] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.
[0057] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0058] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0059] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0060] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0061] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0062] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0063] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0064] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims
1. A method for constructing a large e-commerce model, characterized in that: The method comprises: Obtain historical transaction data, logistics data and unstructured data, and extract the features of the unstructured data through natural language processing. The unstructured data includes industry data, domestic and foreign market data, and obtain an e-commerce industry database; Based on the historical transaction data and logistics data, a sales forecasting model and a logistics time efficiency forecasting model are constructed through Hadoop, and an e-commerce model is established based on the e-commerce industry database and the AI big model; Cross-validate and optimize the parameters of the sales forecast model and the logistics time efficiency forecast model, and integrate them with the e-commerce model to obtain a large e-commerce model; The e-commerce big model is microserviced, and a service discovery mechanism is configured to enable communication between microservices.
2. The method for constructing a large e-commerce model according to claim 1, characterized in that: The e-commerce big model is microserviced and a service discovery mechanism is configured to enable communication between microservices, specifically including: Splitting the e-commerce big model into multiple microservice modules, wherein the microservice modules include a payment module, an order module, a logistics module and a prediction module; Configure a RESTful API interface for the microservice module, and register the address information into a service discovery tool when the microservice module is started; When the order module calls the logistics module, the service discovery tool is queried for address information of the logistics module.
3. The method for constructing a large e-commerce model according to claim 1, characterized in that: The features of the unstructured data are extracted through natural language processing, specifically including: Clean and preprocess the unstructured data within a preset time period, and use lexical analysis and syntactic analysis in NLP technology to extract users and scenarios in the text. The users include enterprise users and individual users, and the scenarios include enterprise-side scenarios, social-side scenarios, and industry-side scenarios. Conduct cross-scenario analysis on the enterprise-side scenario, social-side scenario, and industry-side scenario, and use supervised learning algorithms to build prediction models respectively; The prediction models are integrated.
4. The method for constructing a large e-commerce model according to claim 3, characterized in that: After integrating the prediction model, the method further includes: Acquire real-time transaction data, logistics data and unstructured data, and obtain the prediction results for the next preset time period based on the prediction model, and the prediction results are deployable models; Track the model prediction accuracy by comparing it with actual data through the API interface.
5. The method for constructing a large e-commerce model according to claim 1, characterized in that: The method further comprises: Provide enterprise user tracking options; In the case of a click by the enterprise user, the enterprise user behavior data and historical transaction data are used to construct an enterprise user portrait and product portrait; Based on the matching degree between user portrait and product portrait, collaborative filtering, content-based recommendation and other algorithms are used to generate a recommendation list for users.
6. The method for constructing a large e-commerce model according to claim 1, characterized in that: After obtaining the prediction result for the next preset time period, the method further includes: Based on the prediction results, a strategy prediction interface is provided; Provides user interaction functions for filtering conditions, time period selection, or exporting forecast results.
7. The method for constructing a large e-commerce model according to claim 1, characterized in that: The method further comprises: extracting entities, relationships and attributes from the unstructured data; Based on the entities and relationships, construct an e-commerce industry knowledge graph, wherein the e-commerce industry knowledge graph includes a product graph, a user graph, and a market graph; Market trends are discovered through graph mining technology, and the knowledge graph is integrated with the e-commerce big model.
8. The method for constructing a large e-commerce model according to claim 1, characterized in that: The method further comprises: Establish a user feedback mechanism through online surveys and user comments, and establish a user feedback response mechanism to respond to user feedback in a timely manner.
9. A device for constructing a large e-commerce model, characterized in that: The device comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: Obtain historical transaction data, logistics data and unstructured data, and extract the features of the unstructured data through natural language processing. The unstructured data includes industry data, domestic and foreign market data, and obtain an e-commerce industry database; Based on the historical transaction data and logistics data, a sales forecasting model and a logistics time efficiency forecasting model are constructed through Hadoop, and an e-commerce model is established based on the e-commerce industry database and the AI big model; Cross-validate and optimize the parameters of the sales forecast model and the logistics time efficiency forecast model, and integrate them with the e-commerce model to obtain a large e-commerce model; The e-commerce big model is microserviced, and a service discovery mechanism is configured to enable communication between microservices.
10. A non-volatile computer storage medium for constructing an e-commerce macro model, storing computer executable instructions, characterized in that: The computer executable instructions are configured to: Obtain historical transaction data, logistics data and unstructured data, and extract the features of the unstructured data through natural language processing. The unstructured data includes industry data, domestic and foreign market data, and obtain an e-commerce industry database; Based on the historical transaction data and logistics data, a sales forecasting model and a logistics time efficiency forecasting model are constructed through Hadoop, and an e-commerce model is established based on the e-commerce industry database and the AI big model; Cross-validate and optimize the parameters of the sales forecast model and the logistics time efficiency forecast model, and integrate them with the e-commerce model to obtain a large e-commerce model; The e-commerce big model is microserviced, and a service discovery mechanism is configured to enable communication between microservices.