E-commerce live broadcast delivery information analysis method, equipment and medium

Abstract

The invention provides an e-commerce live broadcast goods carrying information analysis method and device and a medium, and belongs to the technical field of e-commerce live broadcast, and the method comprises the steps: obtaining a to-be-compared anchor information set and a to-be-compared commodity information set; obtaining a pre-configured target anchor ID and mapping information of an anchor ID in a preset time period corresponding to the target anchor ID and a cargo carrying code; carrying out splicing processing to obtain corresponding anchor goods carrying information; inserting the anchor cargo carrying information into a pre-constructed cargo carrying information verification table; through a dynamic weight distribution strategy, real-time priority ranking is carried out on abnormal interaction modes, a high-risk mode is automatically triggered to a specific partition of a goods-carrying information verification table, and a multi-dimensional verification rule is generated at the same time to drive adaptive optimization of a subsequent live broadcast process. The live broadcast goods carrying information can be analyzed comprehensively and accurately, abnormal conditions can be found and processed in time, the live broadcast process is optimized, and the live broadcast goods carrying efficiency and effect are improved.

Description

Technical Field

[0001] The present invention belongs to the field of e-commerce live broadcast technology, and specifically relates to an e-commerce live broadcast product information analysis method, equipment and medium. Background Art

[0002] Against the backdrop of the current booming e-commerce industry, live streaming e-commerce sales, as an emerging marketing model, has quickly become an important force in promoting product sales with its real-time interaction and intuitive display.

[0003] Related technologies typically collect only basic product information or a brief introduction to the host through livestreaming, lacking comprehensive data collection on the host's historical sales performance, fan profiles, product sales trends, user feedback, and other multi-dimensional data. This results in incomplete data analysis, making it difficult to accurately assess the host's sales performance and product sales potential.

[0004] Existing technologies for verifying livestream sales information lack effective anomaly detection methods. They often only perform simple data comparisons and fail to identify complex, anomalous interaction patterns. Existing e-commerce livestreaming processes are relatively rigid and lack the ability to dynamically adjust based on real-time data and anomalies. When issues such as poor product sales and poor user feedback arise during livestreams, the livestreaming strategy cannot be optimized in a timely manner, resulting in ineffective improvements to the livestream's effectiveness. Summary of the Invention

[0005] The present invention provides an e-commerce live streaming sales information analysis method, which can comprehensively and accurately analyze live streaming sales information, promptly discover and handle abnormal situations, optimize the live streaming process, and improve the efficiency and effectiveness of live streaming sales.

[0006] Methods include: S101: Obtaining a host information set and a product information set to be compared; S102: Obtain a pre-configured target anchor ID from a preset anchor product verification set, as well as mapping information between the anchor ID and the product product code corresponding to the target anchor ID in a preset time period; S103: Extracting the anchor information and product information corresponding to the target anchor ID from the anchor information set and the product information set respectively; S104: Based on the mapping information between the anchor ID and the product code for the preset time period, the anchor information and the product information are spliced ​​to obtain the corresponding anchor product information; S105: Insert the anchor's product information into a pre-built product information verification table; S106: Executing a preset cross-validation algorithm to identify abnormal interaction patterns with differences from the anchor's product information in the product information verification table; S107: Based on the abnormal interaction pattern, a multi-dimensional correlation model is constructed that includes the host's behavioral characteristics, product sales dynamics and user feedback. Through a dynamic weight allocation strategy, the abnormal interaction patterns are prioritized in real time, and high-risk patterns are automatically triggered to a specific partition of the product information verification table. At the same time, multi-dimensional verification rules are generated to drive the adaptive optimization of subsequent live broadcast processes.

[0007] Preferably, step S101 specifically includes: obtaining a set of information to be compared including a host's spatiotemporal behavior feature set, a product semantic association set, a user interaction heat set, and a scene multimodal feature set; The host's spatiotemporal behavior feature set covers the historical live broadcast time distribution vector and the high-frequency word matrix of the dialogue. The product semantic association set contains the cross-platform product description similarity vector space and the competitor feature comparison matrix. The user interaction heat set is composed of the barrage emotional polarity time series flow and the like behavior heat matrix. The scene multimodal feature set integrates the live broadcast audio and video semantic label sequence and the scene change detection vector.

[0008] Preferably, step S102 also includes: by integrating the anchor's historical sales records, real-time inventory data of goods and user portrait tags, based on the traffic characteristics of the live broadcast period and the sales trend of goods, building a dynamically adjusted mapping relationship between the anchor ID and the sales code, and verifying the real-time and accuracy of the mapping information through a cross-platform data interface to support the subsequent accurate analysis and verification of live broadcast sales information.

[0009] Preferably, step S103 also dynamically verifies and extracts structured anchor information and product information based on the mapping relationship between the anchor ID and the product code in a preset time period by integrating the anchor's real-time behavior data, product dynamic attributes and user interaction information.

[0010] Preferably, step S104 dynamically verifies and splices structured anchor product information by integrating anchor real-time behavior data, product dynamic attributes and user interaction information based on the mapping relationship between anchor ID and product code in a preset time period.

[0011] Preferably, before step S102, the method further includes: determining whether a configuration request corresponding to the anchor's product verification set triggered by a user is received; If so, display the preset configuration interface; receiving configuration information input by the user in the configuration interface; Based on a preset construction strategy, use the configuration information to construct a corresponding configuration checklist; The set of products brought by the anchor to be verified is stored and processed.

[0012] Preferably, step S106 also verifies and generates a live streaming sales analysis report based on the mapping relationship between the anchor ID and the sales code in a preset time period by integrating the anchor's real-time behavior data, product dynamic attributes and user interaction information.

[0013] Preferably, in step S107, the three types of data, namely, anchor behavior, product sales data, and user feedback, are used as a multidimensional correlation model; The dynamic weight allocation strategy is to define the risk factor, the formula is: risk factor = (anchor recommendation frequency × product return rate) ÷ user average stay time, and dynamically adjust the weight parameters based on real-time data; For abnormal patterns with a risk factor ≥ 0.8, they are first inserted into the high-risk partition of the verification table and the early warning mechanism is triggered; For patterns with a risk factor of 0.5 ≤ < 0.8, inserting into the low-risk partition is delayed; The adaptive optimization driving method is to link the abnormal interaction mode with the live broadcast process control module.

[0014] According to another embodiment of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the e-commerce live streaming information analysis method when executing the program.

[0015] According to another embodiment of the present application, a storage medium is also provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the e-commerce live streaming information analysis method are implemented.

[0016] It can be seen from the above technical solutions that the present invention has the following advantages: The e-commerce live streaming information parsing method provided in this application obtains the anchor information set and product information set to be compared through multi-source data collection, ensuring the comprehensiveness and richness of the data. Obtaining the target anchor ID and mapping information from the preset anchor's product verification set can focus on the key anchor and product combination, making subsequent data processing more targeted. Based on the mapping information, the corresponding anchor and product information is extracted to further narrow the data range and accurately obtain data directly related to the target anchor's product. Reduce the complexity of data processing and quickly locate key information. Splice the anchor information and product information to form a complete anchor's product information unit, improve the logic and readability of the data, and insert the spliced ​​anchor's product information into the pre-built verification table to provide a unified storage platform for data verification and analysis. It facilitates rapid query, call and management of data. Execute the cross-validation algorithm to identify abnormal interaction patterns, and timely discover data anomalies in the live streaming process. Construct a multidimensional association model based on the abnormal interaction pattern, prioritize it through a dynamic weight allocation strategy, and generate verification rules to drive the optimization of the live streaming process. This system enables hierarchical management of anomalies, prioritizing high-risk anomalies and minimizing business losses. Dynamic weighting allows risk assessments to be more tailored to actual scenarios. Generated validation rules drive continuous improvement in the livestreaming process, enhancing the effectiveness and user experience of livestreaming sales. It comprehensively and accurately analyzes livestreaming sales information, promptly identifies and handles anomalies, optimizes the livestreaming process, and improves the efficiency and effectiveness of livestreaming sales. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for the description. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 A flow chart of the method for analyzing information about live streaming sales for e-commerce; Figure 2 Schematic diagram of an electronic device. DETAILED DESCRIPTION

[0019] The following describes in detail the e-commerce live streaming information parsing method involved in this application. For the purpose of illustration rather than limitation, specific details such as specific system structures and technologies are proposed to facilitate a thorough understanding of the embodiments of this application. However, it should be clear to those skilled in the art that this application can also be implemented in other embodiments without these specific details.

[0020] It should be understood that when used in this specification, the term "comprising" indicates the presence of the described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or their collections. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0021] It should be understood that the "one or more" mentioned in this application refers to one, two or more, and the "multiple" mentioned in this application refers to two or more. In the description of this application, unless otherwise specified, " / " means or, for example, A / B can mean A or B. The "and / or" in this article is only a way to describe the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0022] The phrases "one embodiment" or "some embodiments" described in this application mean that the specific features, structures, or characteristics described in the embodiment are included in one or more embodiments of the application. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in other embodiments," etc. that appear in different places in this application do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized.

[0023] In embodiments of the present invention, computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or power server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (exemplarily via the Internet using an Internet service provider).

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0025] See also Figure 1 The figure is a flowchart of a method for analyzing information of live e-commerce sales in a specific embodiment, the method comprising: S101: Obtain the anchor information set and product information set to be compared.

[0026] In some embodiments, data is collected by establishing data interfaces with multiple data sources, such as e-commerce platform databases, live streaming platform backends, and social media platforms. The anchor information set not only includes basic information such as the anchor's name, age, and number of followers, but also covers historical performance data such as the number of live broadcasts, average number of viewers, interaction rate, sales conversion rate, and preferred language, as well as fan profile data such as the geographical distribution of fans, age group, and consumption habits. In addition to basic attributes such as product name, price, and specifications, the product information set also includes inventory change records, sales trend data, user reviews, and price and feature comparisons of competing products. Furthermore, data related to the live streaming scene is collected, such as the layout style of the live streaming room and lighting and sound effect parameters. This allows the actual performance of the anchor in bringing products to consumers to be reflected from multiple dimensions. This comprehensive data foundation facilitates more accurate subsequent analysis of the anchor's performance in bringing products to consumers and the sales potential of products.

[0027] S102: Obtain a pre-configured target anchor ID from a preset anchor sales verification set, as well as mapping information between the anchor ID and the sales code for a preset time period corresponding to the target anchor ID.

[0028] In some embodiments, the preset anchor promotion verification set is a set of anchors of key importance pre-defined in the system by operators based on business needs and stored in a specific data table or data file. By querying this set, the target anchor ID is obtained. Simultaneously, the mapping relationship between anchor ID and promotion code for the preset time period corresponding to the target anchor ID is searched in the associated data table to identify the specific product code that each target anchor is responsible for promoting during that time period. This mapping relationship may also include information such as the promotion time period and the identification of the main promoted product.

[0029] It should be noted that target anchor IDs are screened from the anchor sales verification pool based on anchor activity participation identification, key anchor tags, and other factors. Then, based on the target anchor ID, a correlation query is performed in the associated mapping relationship table to obtain the corresponding anchor ID and sales code mapping information, enabling precise data positioning and correlation extraction. This avoids indiscriminate processing of all anchor and product data, improves data processing efficiency, and also enables more targeted analysis of the sales performance of key anchors.

[0030] S103: Extracting the anchor information and product information corresponding to the target anchor ID from the anchor information set and the product information set respectively.

[0031] In some embodiments, based on the mapping information obtained in step S102, a filtering operation is performed within a large set of anchor information and product information. Within the anchor information set, live broadcast performance data for the target anchor within a preset time period is filtered out, such as the audience change curve, interactive message content, sales order data, etc. The anchor's speech text is also extracted to analyze the speech style and high-frequency vocabulary. Within the product information set, detailed information such as the corresponding product attributes, price adjustment records, real-time inventory changes, and user review details are extracted based on the product code.

[0032] This embodiment narrows the data scope, extracting data directly related to the target livestreamer's sales, removing a large amount of irrelevant data, and reducing the complexity and workload of subsequent data processing. It can quickly focus on key information and improve the accuracy and efficiency of data analysis.

[0033] As an example of the present application, step S103 also dynamically verifies and extracts structured anchor information and product information based on the mapping relationship between the anchor ID and the product code in the preset time period by integrating the anchor's real-time behavior data, product dynamic attributes and user interaction information.

[0034] S104: Based on the mapping information between the anchor ID and the product code for the preset time period, the anchor information and the product information are spliced ​​to obtain the corresponding anchor product information.

[0035] In some embodiments, the host information and product information extracted in step S103 are integrated according to the mapping relationship between the host ID and the product code for a preset time period. For example, the host's live broadcast speech and interaction during a certain time period are combined with the product introduction and promotion information corresponding to the product code for that time period to form a complete record. The record includes host-related information, product-related information, and the relationship between the two, such as the time and method of product promotion.

[0036] This embodiment uses mapping information as the link and basis for data splicing. By merging data records with the same associated target anchor ID and product code in anchor information and product information, and combining the relevant information fields according to the pre-designed data structure and format, structured anchor product information is constructed.

[0037] In some specific embodiments, step S104 dynamically verifies and splices structured anchor product information by integrating the anchor's real-time behavior data, product dynamic attributes, and user interaction information based on the mapping relationship between the anchor's ID and the product code during a preset time period.

[0038] This embodiment combines live streamer information with product information based on the mapping information between live streamer ID and product code during a preset time period, including live streamer's real-time behavioral characteristics, product inventory changes, price fluctuations, and real-time user feedback. This data is compared with the preset mapping information in real time, and the combination strategy is adjusted based on historical product conversion rates and user stay time. For example, during periods of tight inventory, alternative product information is automatically prioritized for combination, or the product display order is optimized during periods of low user activity, ensuring the timeliness and completeness of live streamer product information.

[0039] S105: Insert the anchor's product information into a pre-built product information verification table.

[0040] In some embodiments, the pre-built product sales information verification table is a database table structure designed based on the characteristics of the anchor's product sales information and the needs of subsequent verification and analysis. It contains fields for storing various aspects of the anchor's product sales information, such as anchor ID, product ID, product sales time, sales data, user reviews, etc. The anchor's product sales information spliced ​​in step S104 is inserted one by one into the corresponding position in the table according to the field requirements of the verification table to complete the data storage operation.

[0041] This embodiment leverages the database's insert functionality and the insert data statements provided by the database management system to write structured livestream product information records into a pre-created product information verification table. During the insertion process, the database checks and verifies the data according to the constraints of the table structure to ensure data integrity and accuracy, facilitating rapid data query and access.

[0042] S106: Execute a preset cross-validation algorithm to identify abnormal interaction patterns with differences from the anchor's sales information in the sales information verification table.

[0043] In some embodiments, the pre-set cross-validation algorithm is a set of verification rules developed by business experts and data analysts based on the business rules, industry standards, and historical data of e-commerce live streaming sales. These rules include product description consistency rules (e.g., the product features described by the host must be consistent with the product details page), abnormal sales growth within a short period of time must be verified, and user interaction logic rules. By comparing and analyzing each live streaming sales information in the sales information verification table against these rules, the logical relationship between the data, the rationality of the values, the semantic consistency, and other aspects are examined to identify abnormal interaction patterns that do not conform to the rules, such as live streaming exaggeration of product efficacy or suspected sales data fraud.

[0044] This embodiment sequentially matches and verifies the data records in the live streaming information verification table against pre-set cross-validation rules. For each data record, the data fields are checked and analyzed based on the conditions and logical relationships set by the rules. Through conditional judgments and logical operations, data records that do not comply with the rules are identified, and abnormal interaction patterns are determined. This allows for the timely detection of errors, falsities, or unreasonable content in live streaming information, preventing misleading e-commerce live streaming business decisions from erroneous information and ensuring data accuracy and reliability.

[0045] S107: Based on the abnormal interaction pattern, a multi-dimensional correlation model is constructed that includes the host's behavioral characteristics, product sales dynamics and user feedback. Through a dynamic weight allocation strategy, the abnormal interaction patterns are prioritized in real time, and high-risk patterns are automatically triggered to a specific partition of the product information verification table. At the same time, multi-dimensional verification rules are generated to drive the adaptive optimization of subsequent live broadcast processes.

[0046] In some embodiments, multi-dimensional data related to the abnormal interaction patterns identified in step S106 is collected. Regarding livestreamer behavioral characteristics, data such as recent changes in livestream duration, repetition rate of speech, and frequency of interaction with viewers is collected. Regarding product sales trends, data such as product sales fluctuation curves, refund rate changes, and inventory turnover rates are collected. Regarding user feedback, information such as user comment content, review text, and complaint records is compiled. Based on this data, a multi-dimensional correlation model is constructed, with each dimension in the model interrelated. Furthermore, a dynamic weighting strategy is used to assign weights to each dimension based on the impact of different dimensional data on the livestreaming business. By calculating the comprehensive score of each abnormal interaction pattern within the multi-dimensional model, abnormal interaction patterns are prioritized in real time. Abnormal interaction patterns with high scores and high risk levels are automatically transferred to specific sections of the product promotion information verification table for focused monitoring. Furthermore, based on the characteristics and causes of abnormal interaction patterns, new multi-dimensional verification rules are generated, such as real-time keyword monitoring rules for exaggerated promotional content by livestreamers, to optimize subsequent livestreaming processes.

[0047] In some specific embodiments, when inserting discrepancy data, analysis of unusual interaction patterns is added. For example, by using user dwell time and click-through rate to infer potential issues with the host's sales strategy, rather than simply recording discrepancies, the analysis can be combined with product sales trends and the host's historical performance to dynamically adjust and prioritize unusual patterns for high-value products.

[0048] In S103, in addition to extracting host and product information, the system further integrates bullet comment keywords, likes, share rates, product inventory changes, and price fluctuations. Through multimodal data fusion, a relationship graph between hosts, products, and users is constructed, identifying the status of hosts' product promotion information. For example, if a host recommends product A, the proportion of users who actually purchase product B is significantly abnormal.

[0049] In S107, the insertion of abnormal interaction patterns needs to be combined with dynamic weight allocation. Frequently occurring patterns are given higher priority. Low-frequency but high-risk patterns trigger warnings and are inserted first.

[0050] A high-frequency pattern is when the anchor's rhetoric leads to an increase in the return rate of a certain product category. A low-frequency but high-risk pattern is when a product suddenly runs out of stock and the anchor continues to recommend it.

[0051] The dynamic weight allocation strategy in this embodiment defines a risk factor, specifically the formula: risk factor = (anchor recommendation frequency × product return rate) ÷ average user stay time, and dynamically adjusts the weight parameters based on real-time data. For example, during peak hours, the weight of user stay time is increased.

[0052] For abnormal patterns with a risk factor ≥ 0.8, priority is given to inserting them into the high-risk partition of the verification table and triggering the early warning mechanism; for patterns with a risk factor of 0.5 ≤ < 0.8, insertion into the low-risk partition is delayed to avoid wasting resources.

[0053] In some specific embodiments, the host's recommendation frequency refers to the number of times a host verbally recommends a specific product within a specific live broadcast duration. This data is generated by parsing the live broadcast audio sentence by sentence using speech recognition technology to identify speech fragments containing product names and promotional information, and then combining them with timestamps to generate statistics. For example, if a host mentions a product 15 times during a 2-hour live broadcast, the recommendation frequency is 7.5 times / hour.

[0054] The product return rate is calculated based on e-commerce platform order data, measuring the ratio of return orders to total sales orders for a specific product over a specific period. The system automatically excludes returns due to non-quality issues to ensure the data reflects the true acceptance of the product.

[0055] The average duration of user stay is obtained from the live broadcast platform's user behavior logs. This records the time interval between a user entering the live broadcast room and leaving. After eliminating invalid data with a short stay time (e.g., less than 10 seconds), the average duration of stay for all viewers is calculated. For example, if a live broadcast has 1,000 viewers and a total stay time of 5,000 minutes, the average stay time is 5 minutes.

[0056] Dynamic weighting adjustments are made by increasing the weight of average user duration to 1.5 times the original coefficient during peak hours, as user traffic is high but attention is dispersed during these periods, making duration a better indicator of product appeal. During new product promotions, the weight of the host's recommendation frequency is increased to highlight the impact of promotional efforts on sales conversions. This adjustment is automatically executed by a rules engine that monitors live broadcast time tags, promotional activity types, and other signals in real time to trigger weighting changes.

[0057] The adaptive optimization-driven approach is to link abnormal interaction patterns with the live broadcast process control module. For example, when it is identified that "the host's words have caused a surge in the return rate of a certain product", the live broadcast script is automatically adjusted to block related words and keywords; when it is detected that "the user's interest in product A has decreased", the recommended product B is dynamically switched and the product code mapping information is updated.

[0058] It can be seen that this embodiment comprehensively uses data modeling, weight allocation and rule generation technologies. In terms of data modeling, multi-dimensional data is used to build an association model, and potential relationships and patterns between data are discovered through data mining and machine learning algorithms. The dynamic weight allocation strategy adjusts the weights of data of each dimension in real time according to business needs and data changes to ensure that the model can accurately reflect the severity of the abnormal situation. The priority sorting algorithm sorts abnormal interaction patterns according to the comprehensive score calculated by the model. For high-risk patterns, they are transferred to specific partitions through database operations. The rule generation module extracts key features and patterns based on the analysis of abnormal patterns and generates new verification rules. Centrally monitoring high-risk patterns facilitates operators to quickly locate and handle problems. The generated multi-dimensional verification rules can continuously improve the review and management mechanism of the live broadcast process, realize continuous optimization and adaptive adjustment of the live broadcast process, and improve the effect of live broadcasting and user experience.

[0059] In an embodiment of the present invention, based on step S102, a possible embodiment will be given below to illustrate its specific implementation scheme in a non-limiting manner.

[0060] Before step S102, it also includes: determining whether a configuration request corresponding to the anchor's goods to be verified set triggered by the user is received; if so, displaying a preset configuration interface; receiving the configuration information entered by the user in the configuration interface; based on a preset construction strategy, using the configuration information to construct a corresponding configuration verification table; and storing and processing the anchor's goods to be verified set.

[0061] Step S102 also includes: by integrating the anchor's historical sales records, real-time inventory data of goods and user portrait tags, based on the traffic characteristics of the live broadcast period and the sales trend of goods, building a dynamically adjusted mapping relationship between the anchor ID and the sales code, and verifying the real-time and accuracy of the mapping information through a cross-platform data interface to support the subsequent accurate analysis and verification of live broadcast sales information.

[0062] Specifically, the system continuously monitors user operation behavior to determine whether it has received a configuration request from the user for the anchor's product verification set. The request can be triggered by the user clicking a specific button or entering a command in the system management background. If a request is detected, the system immediately displays the preset configuration interface, which contains a variety of interactive elements, such as a text box for entering target anchor screening conditions, a time selector for selecting the verification period, and a drop-down menu for setting the verification priority. The user enters detailed configuration information in the configuration interface, such as specifying the IDs of certain key anchors, setting specific verification time periods, and marking certain product categories as requiring key verification. After obtaining the configuration information, the system classifies and organizes the information according to the preset construction strategy, fills it into the corresponding fields, and constructs a configuration verification table, which records in detail the various parameters and associations configured by the user. Finally, the system stores the constructed anchor's product verification set in the designated database table or storage area for easy subsequent retrieval and use.

[0063] When acquiring the target livestreamer ID and mapping information, this embodiment first integrates multi-dimensional data. It retrieves the livestreamer's historical product promotion records from the historical data storage area, including product categories promoted in past livestreams, sales performance, and user feedback. It also obtains real-time product inventory data through a real-time data interface to understand the current available quantity and inventory warning status. It also extracts user profile tags from the user profile database to understand user characteristics such as consumer preferences and purchasing power. Next, the system analyzes traffic characteristics during livestreams, such as the number of users online during different time periods and traffic source channels. It also studies product sales trends, including recent sales changes for similar products and the distribution of popular sales periods. Based on these data analysis results, it dynamically constructs a mapping relationship between livestreamer IDs and product promotion codes. For example, during peak traffic periods, popular products are assigned to livestreamers with strong sales capabilities. Once constructed, the system interacts with e-commerce platforms, livestreaming platforms, and other platforms through cross-platform data interfaces to verify the real-time and accuracy of the data related to livestreamers and products in the mapping information, ensuring that the information is consistent with actual conditions.

[0064] Step S106 of this embodiment also verifies and generates a live streaming sales analysis report based on the mapping relationship between the anchor ID and the sales code during a preset time period by integrating the anchor's real-time behavior data, product dynamic attributes, and user interaction information.

[0065] The system collects livestreamer behavioral data using cameras and microphones deployed on the livestreaming platform. Computer vision algorithms identify body movements and facial expressions, while voice recognition and sentiment analysis technologies analyze intonation and emotion. Dynamic product attribute data is obtained through a real-time database synchronization interface. User interaction information is captured in real time from the livestreaming platform's message queue, and natural language processing techniques are used for semantic analysis and sentiment classification. Based on the verification results, the system invokes pre-set report templates to convert the data into visual charts and textual analysis conclusions. This integration of multi-dimensional data enables comprehensive monitoring of the entire livestreaming sales process, not only identifying data logic errors but also uncovering potential issues from the perspectives of user emotion and livestreamer performance.

[0066] As an embodiment of the above method: a beauty brand conducts a live streaming sales activity on the Douyin platform, and needs to verify the sales information of the anchor "ID007" during the period of 20:00-22:00.

[0067] Based on step S101: the system captures the real-time barrage of the anchor's live broadcast room, such as 1,000 messages per minute, and the SKU information of "Liquid Foundation - Matte" in the product library is 600 pieces in stock, the original price is 300 yuan, and the live broadcast price is 200 yuan, and integrates the logistics data.

[0068] Based on step S102: According to the preset time period configuration table, confirm that the anchor's product code rule for this time period is "brand + category + color", and generate the product code "MH20230915-YZ-M".

[0069] Based on step S103: extract "the average conversion rate of the beauty category in the past 30 days is 15%" from the anchor information, obtain "the current inventory is 400 pieces" from the product information, and splice them into structured data.

[0070] Based on step S104: merge the data into JSON format, append the host's signature and timestamp, and write into the verification table.

[0071] Based on step S105: the verification table records show that the product code has no duplication in the historical data, and there is no conflict between the inventory and price fields.

[0072] Based on step S106: cross-validation found that there were only 10 "gift cotton pads" associated with "liquid foundation" in stock during the live broadcast, but the product information was marked "buy one get one free", triggering an inventory discrepancy anomaly.

[0073] Based on step S107: building an association model for analysis, it is found that the anomaly may lead to an increase in the user complaint rate, and the problem is automatically marked as "high risk", written into the hot partition and triggered the rule: suspend the deduction of gift inventory and simultaneously notify the operation staff to replenish the stock.

[0074] It can be seen that the system completes the exception interception within 20 seconds, avoiding overselling losses. At the same time, through adaptive rule optimization, subsequent similar events automatically verify the ratio of gift inventory to main product inventory, reducing manual intervention.

[0075] like Figure 2 As shown, the present application also provides an electronic device, including a display module 103, a memory 102, a processor 101, and a computer program stored on the memory and executable on the processor 101. When the processor 101 executes the program, the steps of the method for parsing information of live streaming sales of e-commerce products are implemented.

[0076] In the embodiments of the present invention, electronic devices include, but are not limited to, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of the present application described and / or claimed herein.

[0077] In the embodiment of the present application, the processor 101 can be implemented by using at least one of a special purpose integrated circuit, a programmable logic device, a field programmable gate array, a processor, a controller, a microcontroller, a microprocessor, and an electronic unit designed to perform the functions described herein. In some cases, such an embodiment can be implemented in a controller. For software implementation, an embodiment such as a process or function can be implemented with a separate software module that allows the execution of at least one function or operation. The software code can be implemented by a software application (or program) written in any appropriate programming language, and the software code can be stored in a memory and executed by a controller.

[0078] The display module 103 is used to display information input by the user or information provided to the user. The display module 103 may include a display panel, which may be configured in the form of a liquid crystal display, an organic light emitting diode, etc.

[0079] The memory 102 can be used to store software programs and various data. The memory 102 can include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0080] The present application also provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the e-commerce live streaming information analysis method are implemented.

[0081] The storage medium can be any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0082] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for analyzing information of live streaming sales of e-commerce, characterized in that: Methods include: S101: Obtaining a host information set and a product information set to be compared; S102: Obtain a pre-configured target anchor ID from a preset anchor product verification set, as well as mapping information between the anchor ID and the product product code corresponding to the target anchor ID in a preset time period; S103: Extracting the anchor information and product information corresponding to the target anchor ID from the anchor information set and the product information set respectively; S104: Based on the mapping information between the anchor ID and the product code for the preset time period, the anchor information and the product information are spliced ​​to obtain the corresponding anchor product information; S105: Insert the anchor's product information into a pre-built product information verification table; S106: Executing a preset cross-validation algorithm to identify abnormal interaction patterns with differences from the anchor's product information in the product information verification table; S107: Based on the abnormal interaction pattern, a multi-dimensional correlation model is constructed that includes the host's behavioral characteristics, product sales dynamics and user feedback. Through a dynamic weight allocation strategy, the abnormal interaction patterns are prioritized in real time, and high-risk patterns are automatically triggered to a specific partition of the product information verification table. At the same time, multi-dimensional verification rules are generated to drive the adaptive optimization of subsequent live broadcast processes.

2. The e-commerce live streaming product information analysis method according to claim 1 is characterized in that: Step S101 specifically includes: obtaining a set of information to be compared, including a host's spatiotemporal behavior feature set, a product semantic association set, a user interaction heat set, and a scene multimodal feature set; The host's spatiotemporal behavior feature set covers the historical live broadcast time distribution vector and the high-frequency word matrix of the dialogue. The product semantic association set contains the cross-platform product description similarity vector space and the competitor feature comparison matrix. The user interaction heat set is composed of the barrage emotional polarity time series flow and the like behavior heat matrix. The scene multimodal feature set integrates the live broadcast audio and video semantic label sequence and the scene change detection vector.

3. The e-commerce live streaming product information analysis method according to claim 1 is characterized in that: Step S102 also includes: by integrating the anchor's historical sales records, real-time inventory data of goods and user portrait tags, based on the traffic characteristics of the live broadcast period and the sales trend of goods, building a dynamically adjusted mapping relationship between the anchor ID and the sales code, and verifying the real-time and accuracy of the mapping information through a cross-platform data interface to support the subsequent accurate analysis and verification of live broadcast sales information.

4. The e-commerce live streaming product information analysis method according to claim 1 is characterized in that: Step S103 also dynamically verifies and extracts structured anchor information and product information by integrating the anchor's real-time behavior data, product dynamic attributes and user interaction information based on the mapping relationship between the anchor ID and the product code in the preset time period.

5. The e-commerce live streaming product information analysis method according to claim 1 is characterized in that: Step S104 dynamically verifies and splices structured anchor product information by integrating the anchor's real-time behavior data, product dynamic attributes and user interaction information based on the mapping relationship between the anchor ID and the product code in the preset time period.

6. The e-commerce live streaming product information analysis method according to claim 1 is characterized in that: Before step S102, the method further includes: determining whether a configuration request corresponding to the anchor's product verification set triggered by the user is received; If so, display the preset configuration interface; receiving configuration information input by the user in the configuration interface; Based on a preset construction strategy, use the configuration information to construct a corresponding configuration checklist; The set of products brought by the anchor to be verified is stored and processed.

7. The e-commerce live streaming product information analysis method according to claim 1 is characterized in that: Step S106 also verifies and generates a live streaming sales analysis report by integrating the host's real-time behavior data, product dynamic attributes and user interaction information, based on the mapping relationship between the host ID and the sales code during the preset time period.

8. The method for analyzing information of live streaming sales of e-commerce according to claim 1, characterized in that: In step S107, the three types of data, namely, anchor behavior, product sales data, and user feedback, are used as a multidimensional correlation model; The dynamic weight allocation strategy is to define the risk factor, the formula is: risk factor = (anchor recommendation frequency × product return rate) ÷ user average stay time, and dynamically adjust the weight parameters based on real-time data; For abnormal patterns with a risk factor ≥ 0.8, they are first inserted into the high-risk partition of the verification table and the early warning mechanism is triggered; For patterns with a risk factor of 0.5 ≤ < 0.8, inserting into the low-risk partition is delayed; The adaptive optimization driving method is to link the abnormal interaction mode with the live broadcast process control module.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the e-commerce live streaming information analysis method as described in any one of claims 1 to 7 are implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the steps of the e-commerce live streaming information analysis method as described in any one of claims 1 to 7 are implemented.

Images