Big Data-Based Live Streaming E-commerce Content Management Methods and Systems

Abstract

This application provides a big data-based live-streaming e-commerce content management method and system. By acquiring live-streaming guidance information and content response parameter data at various live-streaming promotion nodes and adaptively adjusting them, the system can effectively improve live-streaming interaction and participation, thereby optimizing the promotion effect of e-commerce live-streaming rooms. Based on live-streaming interaction and participation, target live-streaming promotion nodes that meet the set live-streaming participation requirements can be selected, and matching live-streaming promotion nodes can be further determined, thereby increasing user engagement. Based on the live-streaming interaction and participation corresponding to the target and matching live-streaming promotion nodes, the influence of the e-commerce live-streaming room can be determined more accurately. Based on the live-streaming room influence and live-streaming interaction and participation, push strategies for live-streaming guidance information at each live-streaming promotion node can be configured, effectively improving the effectiveness of the push strategy and helping e-commerce platforms better understand user behavior.

Description

Technical Field

[0001] This application relates to the field of big data technology, and more specifically, to a method and system for managing live-streaming e-commerce content based on big data. Background Technology

[0002] In recent years, e-commerce live streaming has become a popular sales model, showcasing products to users and attracting them to participate and purchase. However, how to effectively promote the live stream, attract more users, and increase its influence and sales has become a crucial issue.

[0003] Traditional e-commerce live streaming promotion methods are usually fixed, meaning one or a few pre-set promotional methods are applied to all live streaming promotion stages. This approach ignores the fact that different live streaming promotion stages may require different promotional strategies, potentially leading to poor promotional results. Furthermore, traditional promotional methods cannot adjust promotional strategies based on real-time interaction data, lacking flexibility.

[0004] Meanwhile, traditional promotion methods often overlook user engagement. User engagement in a live stream is a crucial factor influencing its impact; if users are uninterested in the content and engagement is low, the stream's influence will diminish. Therefore, there is an urgent need for a new method for configuring promotion strategies that can be adjusted based on different live stream promotion stages and real-time interaction data to increase engagement and influence, thereby optimizing the promotional effect of e-commerce live streams. Summary of the Invention

[0005] In view of this, the purpose of this application is to provide a method and system for managing live e-commerce content based on big data.

[0006] According to a first aspect of this application, a big data-based method for managing live-streaming e-commerce content is provided, applied to a live-streaming e-commerce service platform, the method comprising:

[0007] The system acquires live streaming guidance information and content response parameter data for each live streaming promotion node of the target e-commerce live streaming room. The content response parameter data is generated by adaptively adjusting the live streaming interaction big data of the live streaming guidance information of the e-commerce live streaming room under each live streaming promotion node.

[0008] The live streaming interaction participation level corresponding to each of the live streaming promotion nodes is determined based on the content response parameter data.

[0009] In each of the live streaming promotion nodes, the target live streaming promotion node corresponding to the live streaming interaction participation level meeting the set live streaming participation requirements is obtained, and the matching live streaming promotion node is determined based on the live streaming guidance information under the target live streaming promotion node.

[0010] Based on the live interaction participation rate corresponding to the target live promotion node and the live interaction participation rate corresponding to the matched live promotion node, the influence of the live room corresponding to the target e-commerce live room is determined.

[0011] Based on the influence of the live stream and the level of interaction and participation in the live stream, a push strategy is configured for the live stream guidance information under each of the live stream promotion nodes.

[0012] In one possible implementation of the first aspect, before obtaining the live streaming guidance information of the target e-commerce live streaming room under each live streaming promotion node and the content response parameter data of each of the live streaming promotion nodes, the method further includes:

[0013] The system acquires live streaming interaction big data of the e-commerce live streaming room under each of the aforementioned live streaming promotion nodes; the live streaming interaction big data includes live streaming dialogue event data, the live streaming dialogue trigger domain corresponding to the live streaming dialogue event data, and the dialogue response results corresponding to the live streaming dialogue event data.

[0014] The live dialogue event data, live dialogue trigger domain and dialogue response results of each of the live promotion nodes are analyzed to generate the dialogue conversion rate, actual dialogue participation rate and average dialogue frequency of each of the live promotion nodes.

[0015] The conversion rate of the dialogue, the actual participation rate of the dialogue, and the average frequency of the dialogue for each of the live streaming promotion nodes are weighted and fused to generate content response parameter data for each of the live streaming promotion nodes.

[0016] In one possible implementation of the first aspect, before acquiring the live interaction big data of the e-commerce live streaming room under each of the live streaming promotion nodes, the method further includes:

[0017] Acquire basic live dialogue event data of the e-commerce live streaming room under each of the live streaming promotion nodes;

[0018] Noisy dialogue event data is removed from the basic live stream dialogue event data to generate live stream dialogue event data for each of the live stream promotion nodes.

[0019] The live dialogue content, order data, and e-commerce live streaming room in the live dialogue event data are analyzed to generate dialogue response results.

[0020] In one possible implementation of the first aspect, before performing noisy dialogue event data removal on the basic live dialogue event data, the method further includes:

[0021] Obtain the dialogue attributes corresponding to each of the basic live dialogue event data;

[0022] The basic live chat event data is subjected to violation analysis to generate the first violation analysis data;

[0023] Perform violation analysis on the dialogue attributes to generate second violation analysis data;

[0024] In the basic live dialogue event data, the basic live dialogue event data corresponding to at least one of the first violation analysis data and the second violation analysis data that is an unqualified result is determined as noisy dialogue event data.

[0025] In one possible implementation of the first aspect, the step of weightedly fusing the dialogue conversion rate, the actual dialogue participation rate, and the average dialogue frequency of each of the live streaming promotion nodes to generate content response parameter data for each of the live streaming promotion nodes includes:

[0026] The dialogue conversion rate, actual dialogue participation rate, and average dialogue frequency of each of the live streaming promotion nodes are converted into rules to generate the rule-based dialogue conversion rate, rule-based actual dialogue participation rate, and rule-based average dialogue frequency of each of the live streaming promotion nodes.

[0027] Obtain the first influence coefficient corresponding to the dialogue conversion rate, the second influence coefficient corresponding to the actual dialogue participation rate, and the third influence coefficient corresponding to the average dialogue frequency;

[0028] Based on the first influence coefficient, the second influence coefficient, and the third influence coefficient, the conversion rate of the rule-based dialogue, the actual participation rate of the rule-based dialogue, and the average frequency of the rule-based dialogue are fused to generate content response parameter data for each of the live streaming promotion nodes.

[0029] In one possible implementation of the first aspect, the content response parameters include multiple time-domain content response parameters in the time domain of live content;

[0030] The determination of the live streaming interaction participation level corresponding to each of the live streaming promotion nodes based on the content response parameter data includes:

[0031] Based on the time-domain content response parameters of the multiple live streaming content in the time domain, determine the time-domain live streaming interaction participation degree of each of the live streaming promotion nodes in the time domain of the multiple live streaming content;

[0032] Determine the difference between the temporal-domain live streaming interaction participation levels of the multiple live streaming content;

[0033] Based on the difference, determine the time domain influence coefficient of the live streaming content corresponding to the time domain of the multiple live streaming content;

[0034] Based on the time-domain influence coefficient of the live content, the time-domain live interaction participation of the multiple live content is integrated to generate the live interaction participation corresponding to each of the live promotion nodes.

[0035] In one possible implementation of the first aspect, the number of matched live streaming promotion nodes is multiple;

[0036] The step of determining the livestream influence of the target e-commerce livestream room based on the livestream interaction participation rate corresponding to the target livestream promotion node and the livestream interaction participation rate corresponding to the matched livestream promotion node includes:

[0037] Based on the live streaming interaction participation of multiple matched live streaming promotion nodes, the participation influence weight is determined;

[0038] Based on the participation influence weight, the live interaction participation degree corresponding to the target live promotion node is updated to generate the live room influence degree corresponding to the target e-commerce live room.

[0039] In one possible implementation of the first aspect, configuring a push strategy for live streaming guidance information under each of the live streaming promotion nodes based on the live streaming room influence and the live streaming interaction participation includes:

[0040] Based on the live stream interaction participation, candidate live stream promotion nodes are determined among the live stream promotion nodes.

[0041] The live streaming guidance information of the candidate live streaming promotion node in the live streaming guidance information is determined as candidate live streaming guidance information;

[0042] When the influence of the live stream meets the first set live stream participation requirements, the push strategy configuration for the candidate live stream guidance information is directly implemented.

[0043] When the influence of the live stream meets the second set live stream participation requirements, recommendation guidance data matching the second set live stream participation requirements is generated for the candidate live stream promotion node, and the candidate live stream guidance information and the recommendation guidance data are pushed.

[0044] When the influence of the live broadcast room meets the third set live broadcast participation requirements and the guidance environment of the live broadcast guidance information meets the environmental conditions, the push strategy for the candidate live broadcast guidance information is configured in the guidance environment.

[0045] In one possible implementation of the first aspect, the method further includes:

[0046] Obtain the target live stream interaction big data of the candidate live stream guidance information;

[0047] Based on the candidate live stream guidance information, the content response parameter data of the candidate live stream promotion node is adjusted to generate the adjusted content response parameter data of the candidate live stream promotion node.

[0048] The adjusted live interaction participation level of the candidate live promotion node is determined based on the adjusted content response parameter data. The adjusted live interaction participation level is used to guide the configuration of the push strategy for live guidance information under the candidate live promotion node.

[0049] According to a second aspect of this application, a live-streaming e-commerce service platform is provided, the live-streaming e-commerce service platform including a processor and a readable storage medium, the readable storage medium storing a program, which, when executed by the processor, implements the aforementioned big data-based live-streaming e-commerce content management method.

[0050] According to a third aspect of this application, a computer-readable storage medium is provided, wherein computer-executable instructions are stored in the computer-readable storage medium, and when the execution of the computer-executable instructions is detected, the aforementioned big data-based live e-commerce content management method is implemented.

[0051] Based on any of the above aspects, this application, by acquiring live streaming guidance information and content response parameter data under each live streaming promotion node of the e-commerce live streaming room and making adaptive adjustments, can effectively improve live streaming interaction participation, thereby optimizing the promotion effect of the e-commerce live streaming room. Based on live streaming interaction participation, target live streaming promotion nodes that meet the set live streaming participation requirements can be selected, further determining the matching live streaming promotion nodes, thereby increasing user engagement. According to the live streaming interaction participation corresponding to the target live streaming promotion node and the matching live streaming promotion node, the influence of the e-commerce live streaming room can be determined more accurately. Based on the influence of the live streaming room and the live streaming interaction participation, push strategies can be configured for the live streaming guidance information under each live streaming promotion node. This method is both flexible and practical, effectively improving the effect of push strategies, thereby helping e-commerce platforms better understand user behavior. Attached Figure Description

[0052] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 A flowchart illustrating the big data-based live-stream e-commerce content management method provided in this application embodiment;

[0054] Figure 2 This illustration shows a schematic diagram of the component structure of a live-streaming e-commerce service platform provided in an embodiment of this application for implementing the above-described big data-based live-streaming e-commerce content management method. Detailed Implementation

[0055] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present application.

[0056] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0057] Figure 1 This document illustrates a flowchart of a big data-based live-streaming e-commerce content management method provided in an embodiment of this application. It should be understood that in other embodiments, the order of some steps in this big data-based live-streaming e-commerce content management method may be interchanged as needed, or some steps may be omitted or deleted. The detailed steps of this big data-based live-streaming e-commerce content management method are described below.

[0058] Step S110: Obtain the live streaming guidance information and content response parameter data of each live streaming promotion node for the target e-commerce live streaming room. The content response parameter data is generated adaptively based on the live streaming interaction big data of the live streaming guidance information of the e-commerce live streaming room under each live streaming promotion node.

[0059] For example, the goal of this application embodiment is to optimize a live stream room for an upcoming new product launch. First, it is necessary to collect live stream guidance information for this room at various promotional nodes (such as social media platforms, ad placements, email notifications, etc.), such as click-through rates and viewing durations. Simultaneously, it is also necessary to obtain content response parameter data for each promotional node, which may include user behavior patterns and user feedback.

[0060] Step S120: Determine the live streaming interaction participation level corresponding to each of the live streaming promotion nodes based on the content response parameter data.

[0061] For example, the collected data can be used to calculate the live stream engagement at each promotional node, which means assessing the user's activity level at each promotional node. For instance, if a social media platform has a high click-through rate and long viewing time, then the engagement at that promotional node is relatively high.

[0062] Step S130: Among the live streaming promotion nodes, obtain the target live streaming promotion node corresponding to the live streaming interaction participation degree meeting the set live streaming participation requirements, and determine the matching live streaming promotion node based on the live streaming guidance information under the target live streaming promotion node.

[0063] For example, the goal of this step is to identify promotional nodes that have high engagement and meet set requirements (such as viewing time, click-through rate, etc.). For instance, if a specific ad placement is found to have a high click-through rate and viewing time, then that ad placement is likely an ideal target promotional node. Then, based on the live stream guidance information under this target promotional node, such as the live stream content and time, other promotional nodes with similar characteristics can be found.

[0064] Step S140: Based on the live interaction participation level corresponding to the target live promotion node and the live interaction participation level corresponding to the matched live promotion node, determine the live room influence level corresponding to the target e-commerce live room.

[0065] For example, in this step, the overall influence of the live stream will be assessed based on the interaction and engagement of the target promotion nodes and the matching promotion nodes. If the interaction and engagement of these nodes are high, then the overall influence of the live stream is likely to be significant.

[0066] Step S150: Based on the influence of the live room and the participation in the live interaction, configure the push strategy for the live guidance information under each of the live promotion nodes.

[0067] For example, the push strategy can be adjusted based on the influence of the live stream and the interaction and participation of each promotion node. For instance, if the interaction and participation of a promotion node is high, the frequency of pushes at that node may be increased; conversely, if the interaction and participation of a node is low, the promotion content may be changed or the number of pushes at that node may be reduced.

[0068] Based on the above steps, by acquiring livestream guidance information and content response parameter data at each livestream promotion node and adaptively adjusting them, the livestream interaction participation can be effectively improved, thereby optimizing the promotion effect of the e-commerce livestream. Based on livestream interaction participation, target livestream promotion nodes that meet the set livestream participation requirements can be selected, further determining the matching livestream promotion nodes, thereby increasing user engagement. The influence of the e-commerce livestream can be more accurately determined based on the livestream interaction participation corresponding to the target and matching livestream promotion nodes. Based on the livestream influence and livestream interaction participation, push strategies for livestream guidance information at each livestream promotion node can be configured. This method is both flexible and practical, effectively improving the effectiveness of push strategies and helping e-commerce platforms better understand user behavior.

[0069] In one possible implementation, prior to step S110, the method further includes:

[0070] Step S101: Obtain the live interaction big data of the e-commerce live streaming room under each of the live streaming promotion nodes. The live interaction big data includes live dialogue event data, the live dialogue trigger domain corresponding to the live dialogue event data, and the dialogue response result corresponding to the live dialogue event data.

[0071] Step S1021: Analyze the live dialogue event data, the live dialogue trigger domain, and the dialogue response results of each of the live promotion nodes to generate the dialogue conversion rate, actual dialogue participation rate, and average dialogue frequency of each of the live promotion nodes.

[0072] Step S103: The dialogue conversion rate, actual dialogue participation rate and average dialogue frequency of each of the live streaming promotion nodes are weighted and fused to generate content response parameter data for each of the live streaming promotion nodes.

[0073] For example, in optimizing a live stream for a new product launch, it's necessary to first collect big data on live stream interactions at various promotional stages. This data includes, but is not limited to, live stream dialogue event data (e.g., user comments, likes, etc.), dialogue triggering domains (e.g., the time and context in which these behaviors occurred), and dialogue response results (e.g., the host's or other users' replies to user comments).

[0074] Next, this data needs to be analyzed to evaluate the performance of each promotion node. Specifically, this can be done by calculating conversation conversion rate (e.g., the percentage of users who participate in comments), actual conversation engagement rate (e.g., the number of users who actually participate in the conversation), and average conversation frequency (e.g., how many comments each user posts on average).

[0075] Finally, the above metrics can be weighted and combined to generate content response parameter data for each promotion node. For example, if it is believed that the conversation conversion rate has a greater impact on the promotion effect, then this metric may be given a higher weight.

[0076] Through such analysis and calculation, the content response parameter data of each promotion node can be obtained, thereby enabling further optimization decisions.

[0077] In one possible implementation, prior to step S101, the method further includes:

[0078] Step A110: Obtain basic live dialogue event data of the live guidance information of the e-commerce live room under each of the live promotion nodes.

[0079] Step A120: Remove noisy dialogue event data from the basic live dialogue event data to generate live dialogue event data for each of the live promotion nodes.

[0080] Step A130: Analyze the live dialogue content, order data, and e-commerce live streaming room in the live dialogue event data to generate dialogue response results.

[0081] For example, in continuing to optimize the live stream for a new product launch, the first step is to collect all basic live stream dialogue event data. This data includes all interactive information such as comments, questions, and likes posted by users at each promotional stage.

[0082] Next, this data needs to be cleaned up, removing irrelevant or misleading information (noisy dialogue event data), such as advertising messages and malicious attacks. After this step, more accurate and effective live dialogue event data will be obtained.

[0083] Finally, conversation response results can be generated by analyzing what users talk about in the conversation, whether they place orders during the conversation, and their other activities in the e-commerce live stream. For example, if many users are discussing a product and placing orders during this period, it can be inferred that this product has a significant impact on the live stream.

[0084] The above three steps enable a better understanding of user behavior and the extraction of valuable information to optimize e-commerce live streaming rooms.

[0085] In one possible implementation, prior to step A120, the method further includes:

[0086] Step A111: Obtain the dialogue attributes corresponding to each of the basic live dialogue event data.

[0087] Step A112: Perform violation analysis on the basic live chat event data to generate the first violation analysis data.

[0088] Step A113: Perform violation analysis on the dialogue attributes to generate second violation analysis data.

[0089] Step A114: In the basic live dialogue event data, the basic live dialogue event data corresponding to at least one of the first violation analysis data and the second violation analysis data that is an unqualified result is determined as noisy dialogue event data.

[0090] For example, in continuously optimizing a live stream for a new product launch, the first step is to obtain the dialogue attributes corresponding to each basic live stream dialogue event. Dialogue attributes may include user identity information, speaking time, and the nature of the speaking content.

[0091] Next, violation analysis can be performed on the basic live chat event data. For example, some comments may contain illegal content such as advertisements or malicious attacks. Through natural language processing technology and machine learning algorithms, these illegal comments can be identified and marked as the first violation analysis data.

[0092] Next, it's necessary to perform violation analysis on the conversation attributes. For example, if it's discovered that some users frequently post similar comments within a short period, these behaviors may be spamming, and these conversation attributes can be marked as secondary violation analysis data.

[0093] Finally, the underlying live chat event data corresponding to at least one unqualified result in either the first or second violation analysis data can be identified as noisy chat event data. This noisy data will be removed in subsequent analyses.

[0094] The steps above can help filter valuable information from massive amounts of dialogue event data, improving the accuracy and efficiency of data analysis.

[0095] In one possible implementation, step S103 may include:

[0096] Step S1031: Perform rule-based conversion on the dialogue conversion rate, actual dialogue participation rate, and average dialogue frequency of each of the live streaming promotion nodes to generate rule-based dialogue conversion rate, rule-based actual dialogue participation rate, and rule-based average dialogue frequency of each of the live streaming promotion nodes.

[0097] Step S1032: Obtain the first influence coefficient corresponding to the dialogue conversion rate, the second influence coefficient corresponding to the actual dialogue participation rate, and the third influence coefficient corresponding to the average dialogue frequency.

[0098] Step S1033: Based on the first influence coefficient, the second influence coefficient, and the third influence coefficient, the conversion rate of the rule-based dialogue, the actual participation rate of the rule-based dialogue, and the average frequency of the rule-based dialogue are fused to generate content response parameter data for each of the live streaming promotion nodes.

[0099] For example, in optimizing a live stream for a new product launch, firstly, to ensure that different promotional stages can be compared on the same scale, each metric needs to be transformed using rules. For instance, dialogue conversion rate, actual dialogue engagement, and average dialogue frequency can all be mapped to a range of 0-1.

[0100] Next, it's necessary to determine the impact of each metric on the final result. For example, if we find that conversation conversion rate has a greater impact on the live stream, then its impact coefficient would be set higher.

[0101] Finally, based on the various influence coefficients, the regularized dialogue conversion rate, actual dialogue participation rate, and average dialogue frequency can be integrated. For example, the content response parameter data for a promotion node might be 0.6 * regularized dialogue conversion rate + 0.3 * regularized actual dialogue participation rate + 0.1 * regularized average dialogue frequency.

[0102] In one possible implementation, the content response parameters include multiple time-domain content response parameters in the time domain of live content.

[0103] Step S120 may include:

[0104] Step S121: Based on the time-domain content response parameters of the multiple live content time domains, determine the time-domain live interaction participation degree of each of the live promotion nodes in the multiple live content time domains.

[0105] Step S122: Determine the difference between the time-domain live streaming interaction participation levels of the multiple live streaming content in the time domain.

[0106] Step S123: Based on the difference, determine the live content time domain influence coefficient corresponding to the time domain of the multiple live content.

[0107] Step S124: Based on the time-domain influence coefficient of the live content, the time-domain live interaction participation of the multiple live content time domains is fused to generate the live interaction participation corresponding to each of the live promotion nodes.

[0108] For example, in optimizing a live stream for a new product launch, it's essential to first understand that the content response parameter data may include time-domain content response parameters across multiple live stream time domains. For instance, user behavior data regarding watching the live stream in the morning, noon, and evening might be collected.

[0109] Next, this data needs to be analyzed to determine the engagement level of each promotional node during different time periods. For example, a certain social media platform may have higher engagement levels in the evening.

[0110] Next, it's necessary to calculate the difference in engagement levels between different time periods. For example, if a promotion node's engagement level is significantly lower in the morning than in the evening, then this difference will be substantial.

[0111] Next, the impact coefficient for each time period needs to be determined based on these differences. For example, if the difference in interaction participation is large in a time period, then the impact coefficient for that time period may be high.

[0112] Finally, the interaction engagement levels from different time periods can be merged based on the influence coefficient of each time period. For example, the interaction engagement level of a promotion node might be 0.4 * morning interaction engagement level + 0.3 * noon interaction engagement level + 0.3 * evening interaction engagement level.

[0113] The above steps can help to understand users' behavior more accurately at different times, thereby optimizing the e-commerce live streaming room.

[0114] In one possible implementation, the number of matched live streaming promotion nodes is multiple.

[0115] Step S140 may include:

[0116] Step S141: Determine the participation influence weight based on the live interaction participation of multiple matched live promotion nodes.

[0117] Step S142: Update the live interaction participation degree corresponding to the target live promotion node according to the participation influence weight, and generate the live room influence degree corresponding to the target e-commerce live room.

[0118] For example, there may be multiple matching live stream promotion nodes. In optimizing a new product launch live stream, multiple promotion nodes that match the target promotion node may be found first. For instance, it may be discovered that, in addition to the target promotion node (a certain social media platform), user behavior on several other social media platforms is very similar to that of the target promotion node.

[0119] Next, the participation influence weights of these matched promotional nodes need to be determined based on their interaction engagement levels. For example, if a matched promotional node has a high interaction engagement level, its participation influence weight may be set to a higher level.

[0120] Finally, the engagement level of the target promotion node can be updated based on the participation influence weight of each matched promotion node. For example, if a matched promotion node has a high participation influence weight, it may increase the engagement level of the target promotion node, thereby enhancing the overall influence of the e-commerce live stream.

[0121] The above steps can provide a more comprehensive understanding of user behavior and extract valuable information to optimize e-commerce live streaming rooms.

[0122] In one possible implementation, step S150 may include:

[0123] Step S151: Based on the live streaming interaction participation, determine the candidate live streaming promotion nodes among the live streaming promotion nodes.

[0124] Step S152: Determine the live streaming guidance information of the candidate live streaming promotion node in the live streaming guidance information as candidate live streaming guidance information.

[0125] Step S153: When the influence of the live room meets the first set live room participation requirements, the push strategy configuration is directly performed on the candidate live room guidance information.

[0126] Step S154: When the influence of the live room meets the second set live participation requirements, generate recommendation guidance data for the candidate live promotion node that matches the second set live participation requirements, and push the candidate live guidance information and the recommendation guidance data.

[0127] Step S155: When the influence of the live room meets the third set live participation requirements and the guidance environment of the live guidance information meets the environmental conditions, the push strategy for the candidate live guidance information is configured in the guidance environment.

[0128] For example, in optimizing a live stream for a new product launch, the first step is to select candidate promotion nodes based on the engagement level of each promotion node. For instance, if the engagement level of a promotion node exceeds a set threshold, then it can be considered a candidate promotion node.

[0129] Next, it is necessary to select the live streaming guidance information of candidate promotion nodes from all the live streaming guidance information as candidate live streaming guidance information.

[0130] If the influence of the live stream meets the first set participation requirements (e.g., the influence is higher than a certain threshold), then the live stream guidance information for the candidate can be pushed directly.

[0131] If the influence of the live stream meets the second set participation requirements (e.g., the influence is within a certain range), then some recommendation guidance data that matches this requirement needs to be generated (e.g., change the live stream time, add interactive elements, etc.), and this guidance data and candidate live stream guidance information are pushed together.

[0132] If the influence of the live stream meets the participation requirements set in the third setting (e.g., the influence is below a certain threshold), and the guidance environment also meets certain set conditions (e.g., most users are active at night), then the candidate live stream guidance information can be pushed in the guidance environment that meets the conditions.

[0133] The above steps can be used to develop more effective push strategies based on different conditions, thereby optimizing the e-commerce live streaming room.

[0134] In one possible implementation, the method further includes:

[0135] Step B110: Obtain the target live stream interaction big data of the candidate live stream guidance information.

[0136] Step B120: Based on the candidate live stream guidance information, adjust the content response parameter data of the candidate live stream promotion node to generate the adjusted content response parameter data of the candidate live stream promotion node.

[0137] Step B130: Determine the adjusted live interaction participation level of the candidate live promotion node based on the adjusted content response parameter data. The adjusted live interaction participation level is used to guide the configuration of the push strategy for live guidance information under the candidate live promotion node.

[0138] For example, in optimizing a live stream for a new product launch, the first step is to collect and analyze big data on target live stream interactions for the candidate live stream guidance information. This might include data such as user click-through rates and engagement after seeing specific guidance information.

[0139] Next, the content response parameters of the candidate promotion nodes need to be adjusted based on this data and the candidate live stream guidance information. For example, if the data shows that user engagement increases after seeing specific guidance information, then the weight of this type of guidance information may be increased.

[0140] Finally, the adjusted live stream engagement level of candidate promotion nodes can be determined based on the adjusted content response parameter data. This adjusted engagement level can guide the push strategy for live stream guidance information under candidate promotion nodes. For example, if a node's engagement level increases after the guidance information is adjusted, it may push more of this type of guidance information.

[0141] The above steps can provide a more accurate understanding of user behavior and optimize the push strategy for e-commerce live streaming rooms based on this understanding.

[0142] Furthermore, Figure 2 A schematic diagram of the hardware structure of a live-streaming e-commerce service platform 100 for implementing the methods provided in the embodiments of this application is shown. Figure 2 As shown, the live-streaming e-commerce service platform 100 may include one or more processors 102 (processor 102 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, a transmission device 106 for communication functions, and a controller 108. Those skilled in the art will understand that... Figure 2 The structure shown is for illustrative purposes only and does not limit the structure of the live-streaming e-commerce service platform 100 described above. For example, the live-streaming e-commerce service platform 100 may also include... Figure 2 The more or fewer components shown, or having the same Figure 2 The different configurations shown.

[0143] The memory 104 can be used to store software programs and modules of application software, such as the program instructions corresponding to the method embodiments described above in this application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the above-described method for managing live e-commerce content based on big data. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the live e-commerce service platform 100 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0144] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the live-streaming e-commerce service platform 100. In one example, the transmission device 106 includes a network adapter that can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a radio frequency module used for wireless communication with the Internet.

[0145] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some implementations, multitasking and parallel processing are also possible or may be advantageous.

[0146] The 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 its differences from other embodiments. In particular, since the above different embodiments are basically similar to the method embodiments, the descriptions are relatively simple, and relevant parts can be referred to the descriptions of the method embodiments.

[0147] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be loaded into a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

Claims

1. A method for managing live-streaming e-commerce content based on big data, characterized in that, The method includes: The system acquires live streaming guidance information and content response parameter data for each live streaming promotion node of the target e-commerce live streaming room. The content response parameter data is generated by adaptively adjusting the live streaming interaction big data of the live streaming guidance information of the e-commerce live streaming room under each live streaming promotion node. The live streaming interaction participation level corresponding to each of the live streaming promotion nodes is determined based on the content response parameter data. In each of the live streaming promotion nodes, the target live streaming promotion node corresponding to the live streaming interaction participation level meeting the set live streaming participation requirements is obtained, and the matching live streaming promotion node is determined based on the live streaming guidance information under the target live streaming promotion node. Based on the live interaction participation rate corresponding to the target live promotion node and the live interaction participation rate corresponding to the matched live promotion node, the influence of the live room corresponding to the target e-commerce live room is determined. Based on the influence of the live stream room and the live interaction participation corresponding to each of the live stream promotion nodes, a push strategy is configured for the live stream guidance information under each of the live stream promotion nodes. The configuration of the push strategy for live streaming guidance information under each of the live streaming promotion nodes, based on the influence of the live streaming room and the live streaming interaction participation corresponding to each of the live streaming promotion nodes, includes: Based on the live interaction participation level corresponding to each of the live promotion nodes, candidate live promotion nodes are determined among the live promotion nodes. The live streaming guidance information of the candidate live streaming promotion node in the live streaming guidance information is determined as candidate live streaming guidance information; When the influence of the live stream meets the first set live stream participation requirements, the push strategy configuration for the candidate live stream guidance information is directly implemented. When the influence of the live stream meets the second set live stream participation requirements, recommendation guidance data matching the second set live stream participation requirements is generated for the candidate live stream promotion node, and the candidate live stream guidance information and the recommendation guidance data are pushed. When the influence of the live room meets the third set live participation requirements and the guidance environment of the live guidance information meets the environmental conditions, the push strategy for the candidate live guidance information is configured in the guidance environment. The method further includes: Obtain the target live stream interaction big data of the candidate live stream guidance information; Based on the candidate live stream guidance information, the content response parameter data of the candidate live stream promotion node is adjusted to generate the adjusted content response parameter data of the candidate live stream promotion node. The adjusted live interaction participation level of the candidate live promotion node is determined based on the adjusted content response parameter data. The adjusted live interaction participation level is used to guide the configuration of the push strategy for live guidance information under the candidate live promotion node.

2. The live-streaming e-commerce content management method based on big data according to claim 1, characterized in that, Before obtaining the live streaming guidance information of the target e-commerce live streaming room under each live streaming promotion node and the content response parameter data of each live streaming promotion node, the method further includes: The system acquires live streaming interaction big data of the e-commerce live streaming room under each of the aforementioned live streaming promotion nodes; the live streaming interaction big data includes live streaming dialogue event data, the live streaming dialogue trigger domain corresponding to the live streaming dialogue event data, and the dialogue response results corresponding to the live streaming dialogue event data. The live dialogue event data, live dialogue trigger domain and dialogue response results of each of the live promotion nodes are analyzed to generate the dialogue conversion rate, actual dialogue participation rate and average dialogue frequency of each of the live promotion nodes. The conversion rate of the dialogue, the actual participation rate of the dialogue, and the average frequency of the dialogue for each of the live streaming promotion nodes are weighted and fused to generate content response parameter data for each of the live streaming promotion nodes.

3. The live-streaming e-commerce content management method based on big data according to claim 2, characterized in that, Before acquiring the live interaction big data of the e-commerce live streaming room under each of the live streaming promotion nodes, the method further includes: Acquire basic live dialogue event data of the e-commerce live streaming room under each of the live streaming promotion nodes; Noisy dialogue event data is removed from the basic live stream dialogue event data to generate live stream dialogue event data for each of the live stream promotion nodes. The live dialogue content, order data, and e-commerce live streaming room in the live dialogue event data are analyzed to generate dialogue response results.

4. The live-streaming e-commerce content management method based on big data according to claim 3, characterized in that, Before removing noisy dialogue event data from the basic live dialogue event data, the method further includes: Obtain the dialogue attributes corresponding to each of the basic live dialogue event data; The basic live chat event data is subjected to violation analysis to generate the first violation analysis data; Perform violation analysis on the dialogue attributes to generate second violation analysis data; In the basic live dialogue event data, the basic live dialogue event data corresponding to at least one of the first violation analysis data and the second violation analysis data that is an unqualified result is determined as noisy dialogue event data.

5. The live-streaming e-commerce content management method based on big data according to claim 2, characterized in that, The process involves weighting and fusing the dialogue conversion rate, actual dialogue participation rate, and average dialogue frequency of each of the live streaming promotion nodes to generate content response parameter data for each of the live streaming promotion nodes, including: The dialogue conversion rate, actual dialogue participation rate, and average dialogue frequency of each of the live streaming promotion nodes are converted into rules to generate the rule-based dialogue conversion rate, rule-based actual dialogue participation rate, and rule-based average dialogue frequency of each of the live streaming promotion nodes. Obtain the first influence coefficient corresponding to the dialogue conversion rate, the second influence coefficient corresponding to the actual dialogue participation rate, and the third influence coefficient corresponding to the average dialogue frequency; Based on the first influence coefficient, the second influence coefficient, and the third influence coefficient, the conversion rate of the rule-based dialogue, the actual participation rate of the rule-based dialogue, and the average frequency of the rule-based dialogue are fused to generate content response parameter data for each of the live streaming promotion nodes.

6. The live-streaming e-commerce content management method based on big data according to claim 1, characterized in that, The content response parameters include multiple time-domain content response parameters for live content in the time domain; The determination of the live streaming interaction participation level corresponding to each of the live streaming promotion nodes based on the content response parameter data includes: Based on the time-domain content response parameters of the multiple live streaming content in the time domain, determine the time-domain live streaming interaction participation degree of each of the live streaming promotion nodes in the time domain of the multiple live streaming content; Determine the difference between the temporal-domain live streaming interaction participation levels of the multiple live streaming content; Based on the difference, determine the time domain influence coefficient of the live streaming content corresponding to the time domain of the multiple live streaming content; Based on the time-domain influence coefficient of the live content, the time-domain live interaction participation of the multiple live content is integrated to generate the live interaction participation corresponding to each of the live promotion nodes.

7. The live-streaming e-commerce content management method based on big data according to claim 1, characterized in that, The number of matched live streaming promotion nodes is multiple; The step of determining the livestream influence of the target e-commerce livestream room based on the livestream interaction participation rate corresponding to the target livestream promotion node and the livestream interaction participation rate corresponding to the matched livestream promotion node includes: Based on the live streaming interaction participation of multiple matched live streaming promotion nodes, the participation influence weight is determined; Based on the participation influence weight, the live interaction participation degree corresponding to the target live promotion node is updated to generate the live room influence degree corresponding to the target e-commerce live room.

8. A live-streaming e-commerce service platform, characterized in that, The live-streaming e-commerce service platform includes a processor and a readable storage medium, wherein the readable storage medium stores a program that, when executed by the processor, implements the live-streaming e-commerce content management method based on big data as described in any one of claims 1-7.

Images