A data processing method, device and medium for live-streaming e-commerce

Abstract

This application discloses a data processing method, device, and medium for live-streaming e-commerce. The method includes: receiving multi-source data from a live-streaming platform; standardizing the multi-source data according to a pre-set data dictionary and field mapping relationships; preprocessing the standardized multi-source data; determining multi-dimensional indicators based on the processed multi-source data, including indicators for the broadcaster layer, product layer, platform layer, and public opinion layer; performing early warning analysis based on the multi-dimensional indicators to identify anomalies; determining data trends and risk distribution based on the anomalies; and generating an early warning report based on the data trends and risk distribution. This application first standardizes the multi-source data to ensure consistent quality, then determines multi-dimensional indicators to comprehensively cover all levels, followed by early warning analysis to accurately locate anomalies, and finally generates a report for intuitive presentation, providing an efficient, accurate, and systematic data processing workflow for the supervision of live-streaming e-commerce.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a data processing method, device and medium for live-streaming e-commerce. Background Technology

[0002] With the rapid development of the live-streaming e-commerce industry, its transaction volume has grown exponentially. However, related violations have also emerged one after another. First, the data is complex. Different live-streaming e-commerce platforms have significantly different data structures and inconsistent field standards. Second, the behavior is often covert. Violations such as false advertising, order manipulation, and tax evasion are often difficult to detect quickly. Third, regulation is lagging. Currently, the regulation of live-streaming e-commerce relies heavily on data reported by companies or post-event inspections, lacking real-time monitoring and early warning capabilities. Fourth, compliance pressure is high. With increasingly stringent regulations, the regulation of live-streaming e-commerce requires the support of systematic tools.

[0003] Traditional live-streaming e-commerce data processing methods have many drawbacks, such as serious data silos, lagging data processing, and high reliance on manual labor, making it difficult to meet regulatory requirements for real-time performance, accuracy, and traceability. Summary of the Invention

[0004] To address the aforementioned issues, this application proposes a data processing method for live-streaming e-commerce, comprising: receiving multi-source data from a live-streaming platform; standardizing the multi-source data according to a pre-set data dictionary and field mapping relationships; preprocessing the standardized multi-source data; determining multi-dimensional indicators based on the processed multi-source data, the multi-dimensional indicators including anchor-level indicators, product-level indicators, platform-level indicators, and public opinion-level indicators; performing early warning analysis based on the multi-dimensional indicators to identify abnormal situations; determining data trends and risk distribution based on the abnormal situations; and generating an early warning report based on the data trends and risk distribution.

[0005] In one example, the method further includes preprocessing the standardized multi-source data by: identifying and removing abnormal data points in the multi-source data to determine outliers based on the abnormal data points; identifying duplicate data in the multi-source data and removing the duplicate data; aligning the removed multi-source data according to a time series; and performing association processing on the multi-source data according to a predetermined association relationship to generate a corresponding data view.

[0006] In one example, the method further includes: using a pre-set time series model to predict sales and popularity trends based on the multi-dimensional indicators and the multi-source data; determining market fluctuations based on the predicted sales and popularity trends; identifying abnormal behaviors based on a pre-set detection algorithm, including fraudulent order placement, false advertising, price anomalies, and abnormal public opinion; and determining risk warning information based on the market fluctuations and the abnormal behaviors.

[0007] In one example, the method further includes: the anchor layer metrics include calculating live broadcast duration, interaction rate, GMV contribution, and violation risk score; the product layer metrics include calculating conversion rate, sales rate, price fluctuation, and return dispute rate; the platform layer metrics include calculating the penetration rate of non-compliant product categories and abnormal order distribution; and the public opinion layer metrics include calculating the proportion of negative comments, the popularity of sensitive words, and the propagation chain.

[0008] In one example, the method further includes: displaying the data trends in real time through a pre-built monitoring screen, the data trends including GMV change trends, user activity, and product sales rankings; and visually displaying the risk distribution to present the geographical, temporal, and type distribution of abnormal situations; and viewing detailed data and risk warning details by clicking on data points on the monitoring screen.

[0009] In one example, the method further includes: automatically integrating the early warning analysis results, data trends, and risk distribution according to a preset report template to obtain a report file; the report file supports export in multiple formats, including PDF and Word, and the report file is archived.

[0010] In one example, the method further includes: deploying through a pre-determined cloud data center and providing API interfaces or SDK toolkits to enable integration with third-party platforms, thereby achieving data sharing and regulatory collaboration.

[0011] In one example, the method further includes: collecting feedback through pre-set feedback channels, and periodically iterating and upgrading based on the feedback to optimize data processing algorithms, early warning rules, and report templates.

[0012] On the other hand, this application also proposes a data processing device for live-streaming e-commerce, 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, the instructions being executed by the at least one processor to enable the data processing device for live-streaming e-commerce to perform: the method described in any of the examples above.

[0013] On the other hand, this application also proposes a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to be the method described in any of the examples above.

[0014] This application utilizes standardized preprocessing of multi-source data to ensure data quality and consistency, laying a solid foundation for subsequent analysis. The construction of multi-dimensional indicators comprehensively covers all aspects of livestreamers, products, platforms, and public opinion, providing in-depth insights. The early warning analysis mechanism combines time series forecasting and anomaly detection algorithms to accurately identify market fluctuations and abnormal behaviors, generating timely risk warnings and improving regulatory efficiency. Visualized monitoring screens and image display functions intuitively present data trends and risk distribution, facilitating rapid decision-making. Report files are automatically integrated and support multi-format export, with archiving and enhanced traceability. Cloud data center deployment and API / SDK toolkits are provided to promote data sharing and regulatory collaboration. Finally, feedback channels and iterative upgrade mechanisms ensure continuous system optimization, adapting to the rapid development and changes in the e-commerce industry, providing strong support for building a smart, efficient, and collaborative e-commerce regulatory system. Attached Figure Description

[0015] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a flowchart illustrating a data processing method for live-streaming e-commerce as described in an embodiment of this application. Figure 2 This is a schematic diagram of a data processing device for live-streaming e-commerce in an embodiment of this application. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0017] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0018] like Figure 1As shown, to address the aforementioned problems, this application provides a data processing method for live-streaming e-commerce, applied in a live-streaming e-commerce data processing system. This system includes a data access and standardization module, a data cleaning and preprocessing module, an indicator calculation and monitoring module, an intelligent analysis and early warning module, a visualization and reporting module, and a system deployment and expansion module. The method includes: S101. Receive multi-source data from the live streaming platform and standardize the multi-source data according to the pre-set data dictionary and field mapping relationship.

[0019] The data access and standardization module, as the cornerstone of the live-streaming e-commerce regulatory data processing system, undertakes the crucial task of connecting to diverse data sources and achieving unified data standardization. This module first seamlessly connects to the data output ports of major live-streaming platforms and brands through standardized interface technology, ensuring stable and efficient data transmission. Building upon this, the module internally constructs a comprehensive and detailed data dictionary, clearly defining the definition, format, and business meaning of each data type. Simultaneously, it designs a precise field mapping table, uniformly mapping data fields from different sources and with varying formats to standard fields within the system, achieving initial data integration and standardization.

[0020] In addition, this module has powerful data processing capabilities, capable of processing structured data, such as transaction records and user behavior logs, as well as unstructured data, such as user comments and live stream bullet comments. Through natural language processing, text mining and other technologies, it extracts valuable information, providing solid data support for subsequent data analysis, indicator calculation and intelligent early warning.

[0021] S102. The multi-source data after standardization is preprocessed, and multi-dimensional indicators are determined based on the processed multi-source data. The multi-dimensional indicators include anchor layer indicators, product layer indicators, platform layer indicators, and public opinion layer indicators.

[0022] The data cleaning and preprocessing module is an indispensable part of the data processing workflow for live-streaming e-commerce supervision, bearing the important responsibility of ensuring data quality and improving the accuracy of data analysis. This module first uses advanced algorithm models to perform a deep scan of the incoming raw data, accurately identifying and removing outliers, such as data generated from extremely short dwell times due to fraudulent activities. If this data is not processed, it will seriously interfere with the accuracy of subsequent analysis results. Simultaneously, the module performs rigorous data deduplication to eliminate duplicate records that may have occurred during data collection or transmission, ensuring the uniqueness of each data set. Furthermore, to ensure the consistency and accuracy of time series analysis, the module performs time series alignment processing, allowing data from different time points to be arranged and compared along a unified timeline. Building upon this foundation, the data cleaning and preprocessing module also achieves deep correlation of multi-source data, including user, product, and streamer data. By constructing a complex relationship network, it connects scattered data points into an organic whole, providing rich data dimensions for subsequent comprehensive analysis.

[0023] The next module is the indicator calculation and monitoring module. Based on pre-set algorithms and models, this module performs in-depth mining and calculations on the cleaned data to generate a series of key indicators that comprehensively and objectively reflect the operational status and risk level of live-streaming e-commerce. At the streamer level, the module calculates indicators such as live-streaming duration, interaction rate, GMV contribution, and violation risk score to help regulators assess the streamer's activity and compliance. At the product level, indicators such as conversion rate, sales rate, price fluctuation, and return dispute rate reveal the product's market performance and potential problems. At the platform level, indicators such as the penetration rate of non-compliant categories and the distribution of abnormal orders help regulators grasp the platform's overall operational status and risk distribution. And at the public opinion level, indicators such as the proportion of negative comments, the popularity of sensitive words, and the dissemination chain provide regulators with an important window into understanding public sentiment and market feedback.

[0024] S103. Perform early warning analysis based on the multidimensional indicators to identify abnormal situations, and determine data trends and risk distribution based on the abnormal situations, so as to generate an early warning report based on the data trends and risk distribution.

[0025] The intelligent analysis and early warning module, as one of the core functions of the live-streaming e-commerce regulatory data processing system, bears the important responsibility of accurate prediction and timely early warning. This module cleverly utilizes time series models to deeply analyze historical sales and popularity data, accurately predicting future trends and providing regulators with forward-looking market insights. Simultaneously, it leverages advanced anomaly detection algorithms to monitor abnormal fluctuations in transaction data in real time, effectively identifying fraudulent order practices and price anomalies, thus maintaining market order. In terms of public opinion monitoring, the module uses text sentiment analysis technology to deeply mine the emotional tendencies in user comments and bullet screen messages, promptly identifying false advertising and negative public opinion, protecting consumer rights. Once a potential risk is detected, the system automatically generates a detailed risk warning report and immediately pushes it to regulators, ensuring that regulatory measures can be implemented quickly and effectively, providing a solid guarantee for the healthy development of the live-streaming e-commerce industry.

[0026] In one embodiment, the visualization and reporting module is a crucial display and output component of the live-streaming e-commerce regulatory data processing system. This module meticulously constructs an intuitive regulatory dashboard, clearly presenting the trends and changes in key data points and the distribution of risk points through dynamic charts and real-time data updates, enabling regulators to grasp market dynamics and potential risks at a glance. Simultaneously, the module supports the automated generation of daily, weekly, and special reports, covering multiple dimensions such as sales overview, risk warnings, and public opinion analysis, providing comprehensive and detailed data support for regulatory decisions. These reports are not only formatted correctly and rich in content, but also support export to multiple formats such as PDF and Word, facilitating flexible use and sharing by regulators according to different needs. Furthermore, the report archiving function ensures the traceability of all output content, providing strong support for subsequent auditing and verification work.

[0027] In one embodiment, the system deployment and expansion module provides a flexible and powerful operating environment and growth potential for the live-streaming e-commerce regulatory data processing system. This module not only supports efficient deployment of the system on local government clouds or provincial big data centers, ensuring secure data storage and high-speed processing, but also fully considers the system's scalability to adapt to ever-changing e-commerce regulatory needs. Through modular design, the system can easily integrate new functional components and data interfaces, seamlessly expanding to the regulatory fields of emerging e-commerce formats such as short-video e-commerce and cross-border e-commerce. This scalability not only enhances the system's applicability but also provides strong technical support for the future innovative development of the e-commerce industry. Simultaneously, the system deployment and expansion module also emphasizes compatibility with existing government systems, ensuring smooth data flow and business collaboration, laying a solid foundation for building a smart and efficient e-commerce regulatory system.

[0028] like Figure 2 As shown in the illustration, this application also provides a data processing device for live-streaming e-commerce, comprising: At least one processor; and, A memory that is communicatively connected to at least one processor; wherein, The memory stores instructions that can be executed by at least one processor to enable a live-streaming e-commerce data processing device to perform the method as described in any of the embodiments above.

[0029] This application also provides a non-volatile computer storage medium storing computer-executable instructions, which are configured as described in any of the above embodiments.

[0030] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many methodological improvements today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that a methodological improvement cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program and "integrate" a digital system onto a PLD themselves, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must also be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0031] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0032] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0033] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components.

[0034] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device and medium embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the description of the method embodiments.

[0035] The devices and media provided in this application are one-to-one with the methods. Therefore, the devices and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0036] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0037] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0038] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0039] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0040] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0041] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, 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 technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0042] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0043] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A data processing method for live-streaming e-commerce, characterized in that, include: Receive multi-source data from live streaming platforms and standardize the multi-source data according to a pre-set data dictionary and field mapping relationship; The standardized multi-source data is preprocessed, and multi-dimensional indicators are determined based on the processed multi-source data. The multi-dimensional indicators include anchor layer indicators, product layer indicators, platform layer indicators, and public opinion layer indicators. Early warning analysis is performed based on the multidimensional indicators to identify abnormal situations, and data trends and risk distributions are determined based on the abnormal situations, so as to generate early warning reports based on the data trends and risk distributions.

2. The method according to claim 1, characterized in that, The method further includes preprocessing the standardized multi-source data, wherein the preprocessing is performed on the data. Identify and remove abnormal data points from the multi-source data to determine outlier values ​​based on the abnormal data points; Identify duplicate data in the multi-source data, remove the duplicate data, and align the removed multi-source data according to the time series. The multi-source data is correlated according to a predetermined relationship to generate a corresponding data view.

3. The method according to claim 1, characterized in that, The method further includes: The predicted sales volume and popularity trends are obtained by using a pre-set time series model based on the multi-dimensional indicators and multi-source data. Market fluctuations are then determined based on the predicted sales volume and popularity trends. The multi-source data is identified according to a pre-set detection algorithm to determine abnormal behaviors, including fraudulent order placement, false advertising, abnormal pricing, and abnormal public opinion. Risk warning information is determined based on the market fluctuations and the abnormal behavior.

4. The method according to claim 1, characterized in that, The method further includes: The metrics for the broadcaster level include the calculation of live broadcast duration, interaction rate, GMV contribution, and violation risk score; The product-level metrics include conversion rate, sales rate, price fluctuation, and return dispute rate. The platform-level metrics include calculating the penetration rate of non-compliant product categories and the distribution of abnormal orders; The public opinion layer indicators include the calculation of the proportion of negative comments, the popularity of sensitive words, and the transmission chain.

5. The method according to claim 1, characterized in that, The method further includes: The data trends are displayed in real time through a pre-built monitoring screen, including GMV change trends, user activity, and product sales rankings. The risk distribution is then visualized using images to present the geographical, temporal, and type distribution of abnormal situations. View detailed data and risk warnings by clicking on the data points on the monitoring screen.

6. The method according to claim 1, characterized in that, The method further includes: The system automatically integrates early warning analysis results, data trends, and risk distribution based on a preset report template to generate a report document. The report file supports export in multiple formats, including PDF and Word, and the report file is archived.

7. The method according to claim 1, characterized in that, The method further includes: Deployed through pre-defined cloud data centers and provided with API interfaces or SDK toolkits to enable integration with third-party platforms, thereby achieving data sharing and regulatory collaboration.

8. The method according to claim 1, characterized in that, The method further includes: Feedback is collected through pre-set feedback channels, and iterative upgrades are carried out regularly based on the feedback to optimize data processing algorithms, early warning rules, and report templates.

9. A data processing device for live-streaming e-commerce, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the data processing device for live-streaming e-commerce to perform the method as described in any one of claims 1-8.

10. A non-volatile computer storage medium storing computer-executable instructions, characterized in that, The computer-executable instructions are configured to be the method as described in any one of claims 1-8.

Images