Traffic control method, device and equipment of live broadcast room, and storage medium

Abstract

The present disclosure provides a traffic control method and device for a live broadcast room, equipment and a storage medium, relates to the technical field of computers, in particular to the technical fields of data analysis, live broadcast streaming, smart e-commerce and the like. The specific implementation scheme is as follows: a plurality of traffic indicators of a target live broadcast room are counted in real time; initial weights corresponding to the various traffic indicators are determined; the maximum weight of the target live broadcast room is determined based on the initial weights corresponding to the various traffic indicators; and the traffic of the target live broadcast room is adjusted based on the maximum weight.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to the fields of data analysis, live streaming, and smart e-commerce. Background Technology

[0002] With the development of information technology, e-commerce live streaming has become a promising new form of live streaming, and it has been gradually applied and developed in many industries.

[0003] E-commerce live streaming can enhance the shopping experience through real-time interaction, thereby accelerating the conversion process from watching to purchasing, providing convenience for consumers, and creating new sales opportunities for merchants. Summary of the Invention

[0004] This disclosure provides a method, apparatus, device, and storage medium for controlling the traffic of a live streaming room.

[0005] According to one aspect of this disclosure, a method for controlling traffic in a live streaming room is provided, comprising:

[0006] Real-time statistics of various traffic metrics for the target live stream room;

[0007] Determine the initial weights for each of the various traffic metrics;

[0008] The final weight of the target live stream room is determined based on the initial weights corresponding to various traffic metrics.

[0009] Adjust the traffic to the target live stream based on the final weight.

[0010] According to another aspect of this disclosure, a traffic control device for a live streaming room is provided, comprising:

[0011] The statistics module is used to collect various traffic metrics for the target live streaming room in real time.

[0012] The first determination module is used to determine the initial weights corresponding to various traffic indicators;

[0013] The second determining module is used to determine the final weight of the target live streaming room based on the initial weights corresponding to various traffic indicators.

[0014] The adjustment module is used to adjust the traffic of the target live stream based on the final weight.

[0015] According to another aspect of this disclosure, an electronic device is provided, comprising:

[0016] At least one processor; and

[0017] The memory is communicatively connected to the at least one processor; wherein,

[0018] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform any of the methods described in the present disclosure.

[0019] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform any of the methods according to embodiments of this disclosure.

[0020] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements any of the methods according to embodiments of this disclosure.

[0021] In this embodiment of the disclosure, various traffic indicators of the live broadcast room are acquired in real time and assigned corresponding weights. Based on the final comprehensive weight, the live broadcast room is given corresponding traffic support to promote healthy competition among merchants and the healthy development of the live broadcast ecosystem.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0023] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0024] Figure 1 This is a schematic diagram of a live streaming room traffic control method according to an embodiment of the present disclosure;

[0025] Figure 2 This is a schematic diagram of the process for determining initial weights according to an embodiment of the present disclosure;

[0026] Figure 3 This is a schematic diagram of the structure of a live streaming room traffic control device according to an embodiment of the present disclosure;

[0027] Figure 4 This is a block diagram of an electronic device used to implement the live streaming room traffic control method in the embodiments of this disclosure. Detailed Implementation

[0028] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0029] The terms “first,” “second,” etc., used in this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion, such as including a series of steps or units. A method, system, product, or apparatus is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products, or apparatuses.

[0030] Unlike traditional shelf-based e-commerce, live-streaming e-commerce content is characterized by its timeliness and rapid turnover. Providing traffic support to a live-streaming room with strong performance data often results in greater exposure. However, current traffic support strategies need improvement for live-streaming rooms with varying performance data.

[0031] For example, timely traffic support for high-performing live streams can boost the streamer's enthusiasm and attract more consumers and traffic. However, most related technologies focus on cold-start support for new streamers and push-streaming mechanisms to reach the fans of established streamers. The lack of real-time signal feedback from the live stream results in slow data feedback, hindering real-time perception and the ability to increase traffic distribution to the live stream in real time.

[0032] In view of this, the present disclosure provides a method for controlling traffic in a live streaming room. This method can acquire various traffic metrics of the live streaming room in real time, assign corresponding weights to them, and provide appropriate traffic support to the live streaming room based on the final comprehensive weight, thereby achieving real-time traffic support for live streaming rooms with better performance data.

[0033] like Figure 1 The diagram shown is a flowchart illustrating the live streaming room traffic control method proposed in this embodiment of the present disclosure, including:

[0034] S101 provides real-time statistics on various traffic metrics for the target live stream.

[0035] The target live streaming room in this embodiment of the disclosure may include not only e-commerce live streaming rooms, but also other types of live streaming rooms, such as art and literature exhibition live streaming rooms, parent-child education live streaming rooms, etc.

[0036] By collecting and analyzing various traffic metrics in real time, the system ensures the timeliness and accuracy of the data. These metrics reflect the activity and popularity of the target live stream from different perspectives.

[0037] S102, determine the initial weights corresponding to each of the various flow indicators.

[0038] An initial weight can be assigned to each traffic metric based on the live streaming platform's operational goals and strategies. This weighting can be determined by the metric's importance and its impact on the overall traffic of the live stream. For example, if the live streaming platform prioritizes audience interaction, metrics related to interaction rates can be assigned a higher initial weight.

[0039] S103 determines the final weight of the target live stream room based on the initial weights corresponding to various traffic metrics.

[0040] By combining various traffic metrics collected in real time with their corresponding initial weights, the final weight of the target live stream is obtained. This final weight comprehensively reflects the quality and attractiveness of the live stream by integrating various performance indicators.

[0041] S104, adjusts the traffic of the target live stream based on the final weight.

[0042] The live streaming platform adjusts the traffic allocation for a target live stream based on its final weight. Live streams with higher final weights will receive more exposure and recommended traffic, thereby attracting more target audiences to enter and stay on the platform.

[0043] During implementation, adjustments can be made dynamically based on real-time data and operational performance of the live stream. For example, when a live stream exhibits violations or a decline in content quality, the platform can lower its weight and reduce traffic allocation; conversely, when a live stream performs well, its weight can be increased and traffic allocation can be improved.

[0044] In this embodiment, by comprehensively considering multiple traffic metrics rather than a single metric, the popularity and quality of target live streams can be more accurately assessed, leading to more reasonable traffic allocation. Directing more traffic to high-quality and popular live streams can improve viewer satisfaction and audience retention rates. Simultaneously, to attract more traffic, streamers will strive to improve their live stream quality, thereby obtaining higher traffic metric scores and weights, which contributes to the overall improvement of platform content quality. Through positive support and incentives, high-quality live streams can be selected in real-time, resulting in better traffic allocation, leveraging the supply of live streams, and rapidly identifying trending, high-quality live streams. In summary, the live stream traffic control method proposed in this embodiment helps promote healthy competition among merchants and the healthy development of the ecosystem, thereby improving the utilization rate of the live streaming platform's computing resources.

[0045] In this embodiment of the disclosure, for each traffic metric, it can be achieved through, as follows: Figure 2 The method shown determines the initial weights for each of the various traffic metrics:

[0046] S201, based on the traffic metrics of multiple reference live streaming rooms, divides the traffic metrics into a preset number of intervals.

[0047] All traffic metrics are divided into a predetermined number of intervals according to preset rules. For example, if there are m reference live streaming rooms, and the traffic metrics are to be divided into n intervals, then the traffic metrics from the lowest score to the highest score might be divided into n different intervals.

[0048] Taking a single traffic metric from among multiple traffic metrics as an example, by statistically analyzing the traffic data of this metric in m reference live streaming rooms within the same time period, and sorting the data, we obtain the ranking of the target live streaming room from highest to lowest among the m reference live streaming rooms. Then, based on the different needs of different live streaming rooms, the traffic metric is divided into a preset number of intervals. For example, the top 5% of the ranked segments are used as the first interval; the top 10%-5% are used as the second interval, and so on.

[0049] It is understood that the preset number of intervals corresponding to different types of traffic indicators may be different. For example, traffic indicator 1 corresponds to 3 intervals, and traffic indicator 2 corresponds to 2 intervals. This disclosure does not limit this.

[0050] S202, obtain the preset weight corresponding to the interval where the traffic metric of the target live room is located, and use it as the initial weight corresponding to the traffic metric of the target live room.

[0051] After processing the traffic metrics into intervals, a preset weight can be assigned to each interval. This preset weight represents the importance of the traffic metrics within that interval. For example, a higher preset weight can be assigned to the first interval, which ranks higher in the order.

[0052] In this embodiment, by dividing traffic metrics into different intervals, the level of a live streaming room on specific metrics can be objectively reflected, avoiding evaluation bias caused by differences in the absolute magnitude of metric values. This provides support for more fair, accurate, and reasonable traffic support for live streaming rooms in the future. By setting preset weights, the evaluation criteria for different intervals can be easily adjusted, making the evaluation system more flexible and in line with actual needs, thus enabling more flexible traffic support for different live streaming rooms. Especially for newly added live streaming rooms, the traffic metric values ​​corresponding to different intervals can be dynamically determined, allowing for better identification of new high-quality live streaming rooms.

[0053] In this embodiment of the disclosure, the various traffic metrics that are statistically analyzed in real time include at least two of the following:

[0054] I. Duration Indicators

[0055] Duration metrics can include the time the target audience spends in the live stream. Duration metrics reflect how attractive the live stream content and format are to the target audience; longer dwell time usually means the target audience is more interested in the live stream content, which may lead to higher interaction and conversion opportunities.

[0056] In this embodiment of the disclosure, the duration indicator includes at least one of the following first sub-indicators:

[0057] (1) The average viewing time of multiple target objects in the target live room within a preset time period;

[0058] This refers to the average viewing time of all target audience members in a live stream over a given period. This metric helps understand the average time target audience members spend in a live stream, thereby assessing the attractiveness of the live stream content to the target audience and its ability to maintain their interest. A higher average value indicates a longer average viewing time for target audience members, suggesting that the live stream content may be more popular or engaging. This, in turn, allows the live stream to receive more traffic allocation.

[0059] (2) The minimum viewing time of multiple target objects in the target live room within the preset time.

[0060] This refers to the shortest viewing time for a live stream among all target audiences within the same time period. This metric helps identify potential reasons for audience churn. A very low minimum value may mean that some target audiences left almost immediately after entering the live stream, reflecting a mismatch between the live stream's content, title, or cover image and the target audience's expectations, or a failure to capture their attention from the outset. A higher minimum value generally indicates greater appeal and reflects the quality of the live stream. Therefore, a higher value for this metric should correspond to a higher weight, and more traffic should be allocated to the live stream.

[0061] In this embodiment, by calculating the average viewing time, the average engagement of the target audience can be assessed, revealing their interest and engagement with the live stream content. A higher average value indicates greater attention and satisfaction from the target audience. The minimum viewing time helps identify which target audiences have shorter viewing times, potentially indicating insufficient interest in the live stream content. This is significant for adjusting live stream strategies and optimizing content quality. In summary, analyzing the viewing time data of the target audience not only helps live stream planners optimize live stream content and duration but also improves the engagement and satisfaction of the target audience, thereby enhancing the overall effectiveness of the live stream and increasing the resource utilization of the live stream platform.

[0062] II. Interaction Indicators

[0063] Interaction metrics refer to the level of engagement of the target audience during a live stream. These metrics help assess audience participation and activity levels. A high interaction rate typically means that the live stream content effectively stimulates the target audience's enthusiasm, promotes interaction between the target audience and the live stream, and facilitates content dissemination.

[0064] In this embodiment of the disclosure, the interaction metric includes at least one of the following second sub-metrics:

[0065] (1) Number of likes within a preset time period;

[0066] The number of likes within a preset duration refers to the number of times the target audience expresses approval and liking for the live stream content within a specific time period (i.e., the preset duration). Likes are one of the most direct indicators of the quality and popularity of a live stream's content; a high number of likes indicates that the target audience holds a positive attitude towards the streamer and the live stream's content.

[0067] (2) Number of interactions within a preset time period;

[0068] The number of interactions within a preset duration can include the number of clicks made by the target audience in the live stream within a specific time period. This metric can more comprehensively reflect the target audience's participation and activity level in the live stream content.

[0069] (3) Number of comments within the preset time period;

[0070] The number of comments within the preset duration refers to the number of comments posted by the target audience in the live stream. Commenting is a more active way for the target audience to participate in the live stream, providing more feedback on their opinions and content. A high number of comments indicates that the target audience is actively participating in the discussion and that the live stream atmosphere is lively.

[0071] (4) The number of target viewers in the target live stream within the preset time period;

[0072] This refers to the number of new viewers who follow a live stream within a specific timeframe. It is an important indicator for evaluating the continued appeal of a live stream's content and its ability to build a loyal target audience.

[0073] (5) The number of times the target live room is shared within the preset time period.

[0074] As the name suggests, this refers to the total number of times a target live stream is shared by users through social networks, instant messaging software, and other means within a specified time period. It reflects the popularity of the live stream content and the level of audience engagement.

[0075] In this embodiment, higher likes and interactions can increase the activity level of the live stream, attracting more target audiences. Increased comments promote interaction among target audiences, creating a positive live stream atmosphere. This not only improves target audience retention but also attracts more potential target audiences through their interactive behavior. An increase in the number of target audiences following the live stream signifies their approval and anticipation of the content. This positively impacts the live stream's ranking and attracts more sponsors or advertising partnerships. In summary, by monitoring these interaction metrics in real time, the live stream can gain better exposure on the platform, attracting more target audiences and thus receiving more traffic support. This creates a virtuous cycle, promoting the continuous development of the live stream and improving the resource utilization of the live stream platform.

[0076] III. Conversion Indicators

[0077] Conversion metrics focus on product sales volume and order value during live streams. These are crucial indicators for evaluating the effectiveness of live stream marketing, directly reflecting the commercial value and conversion efficiency of the live stream. A high conversion rate means the live stream event is highly effective in driving product sales and enhancing brand influence. Specifically for e-commerce live streams, high conversion efficiency effectively improves the resource utilization of the live stream platform.

[0078] In this embodiment of the disclosure, the conversion metric includes at least one third sub-metric from the following:

[0079] (1) The number of orders generated within the preset time period;

[0080] This refers to the number of orders generated by products sold in a live stream within a preset duration. It reflects the merchant's sales performance or the popularity of their services during a specific time period. This metric is directly related to the live stream's sales conversion rate; a high number of orders indicates that the products in the live stream are popular with the target audience and that sales are performing well.

[0081] (2) The first acceleration of order volume within the preset time period.

[0082] The first acceleration of order volume within the preset time period can show the speed at which the sales trend in the live broadcast room changes, that is, the speed at which orders increase or decrease.

[0083] During implementation, the first acceleration of order volume within a preset time period can be determined through the following steps:

[0084] Step A1: Obtain the number of orders within the previous preset duration.

[0085] The preset duration can be any time window shorter than the duration of a single live stream, such as one second, one minute, or five minutes, depending on the business needs of the live stream. Based on the current preset duration T2, the previous preset duration T1 is determined. For example, if T2 is the most recent 5 minutes, then T1 is the previous 5 minutes.

[0086] After determining the preset duration, query and obtain the total number of orders in the previous preset duration T1 and the total number of orders in the current preset duration T2 from the order data system.

[0087] Step A2: Determine the acceleration of the number of orders within a preset time period relative to the number of orders within the previous preset time period, and use it as the first acceleration.

[0088] In physics, acceleration is the ratio of the change in velocity to the time taken for that change to occur. In this embodiment of the disclosure, the change in the number of orders between T2 and T1 can be regarded as the "change in velocity", and the time difference between the two preset durations can be regarded as the "time taken for that change to occur".

[0089] Dividing the change in the number of orders by the change in time yields the acceleration of the number of orders, also known as the first acceleration. This acceleration reflects the rate at which the number of orders increases or decreases between two preset time intervals.

[0090] For example, a positive first acceleration in order volume indicates an increase in order quantity at an accelerating rate; conversely, a negative first acceleration indicates a decrease in order quantity at an accelerating rate. By obtaining the number of orders within the previous preset time period and determining the acceleration of the order number within the current preset time period relative to the order number within the previous preset time period, as the first acceleration, the growth trend of order volume can be effectively analyzed and predicted. This can help merchants adjust their market strategies in a timely manner, optimize inventory management, or make other corresponding business decisions, thereby enabling the live stream to obtain more traffic support and increase its recommendation probability.

[0091] In summary, by focusing on the number of orders generated within a preset time period and the first acceleration of order volume, the popularity and influence of the live streaming room can be assessed more directly. This allows for traffic support for live streaming rooms with higher order volumes, increasing their exposure and promoting their long-term development.

[0092] IV. Flow velocity index

[0093] Traffic flow metrics refer to the frequency with which a target audience enters the live stream, and can include the number of concurrent viewers and the target audience's growth rate. These metrics help understand the traffic trends in the live stream and the peak times when the target audience is most active, which is crucial for optimizing and adjusting the live stream's traffic.

[0094] In this embodiment of the disclosure, the flow rate index includes at least one fourth sub-index of the following:

[0095] (1) The number of target viewers watching the target live stream within a preset time period;

[0096] This refers to the number of target viewers who watched the target live stream within a specific timeframe. The number of target viewers reflects the live stream's popularity; a high number of viewers indicates that the live stream has broad appeal.

[0097] (2) The second acceleration of the number of target objects watching the target live room within the preset time.

[0098] The second acceleration of the number of target objects watching the target live room within a preset time period can represent the rate at which the number of target objects watching the target live room increases or decreases within a preset time period.

[0099] During implementation, the second acceleration for determining the number of target viewers watching the target live stream within a preset duration can be achieved through the following steps:

[0100] Step B1: Obtain the number of target objects who watched the target live stream within the previous preset duration.

[0101] Step B2: Determine the acceleration between the number of target objects watching the target live stream within the preset time period and the number of target objects watching the target live stream within the previous preset time period, and use this acceleration as the second acceleration.

[0102] Similar to the first acceleration in determining the order volume within a preset duration described earlier, the number of target viewers watching the target live stream within the preset duration T4 and the number of target viewers watching the target live stream within the previous preset duration T3 are obtained. The change in the number of target viewers watching the target live stream between T4 and T3 is divided by the change in time, and the result is the second acceleration in the number of target viewers watching the target live stream within the preset duration.

[0103] For example, a positive second acceleration indicates that the number of target viewers in the target live stream is increasing, and the rate of increase is accelerating; a negative second acceleration indicates that the number of target viewers is decreasing, and the rate of decrease is accelerating. By determining the second acceleration of the number of target viewers in the target live stream within a preset time period, it is possible to effectively grasp the audience size and its changing trends, and promptly identify potential live streams. This allows for providing more exposure opportunities to the live stream, such as homepage recommendations and popular lists, thereby achieving traffic support.

[0104] In this embodiment of the disclosure, by analyzing the number of target viewers watching the target live stream within a preset time period and their second acceleration, operators can predict potential changes in the live stream's popularity, thereby adjusting strategies in a timely manner, seizing growth opportunities, and avoiding or reducing the loss of target viewers. This helps live streamers develop more targeted promotional strategies and optimize content arrangements, thereby effectively increasing the exposure and traffic of the live stream.

[0105] In summary, in this embodiment, the duration metric measures the time the target audience spends in the live stream, the interaction metric assesses the target audience's participation and engagement, the conversion metric tracks the number of times the target audience completes a specific goal or makes a purchase, and the flow rate metric focuses on the speed and fluctuation of traffic. By integrating these metrics, the real-time data performance of live streams can be analyzed and evaluated more comprehensively. This allows live streams with better data performance to receive more traffic support, enabling them to utilize resources more efficiently. Simultaneously, it incentivizes streamers to provide higher-quality content and enhances the target audience's experience.

[0106] In this embodiment of the disclosure, when any target traffic indicator includes multiple sub-indicators, the initial weights corresponding to each traffic indicator are determined. The following operations can be performed for each sub-indicator of each target traffic indicator:

[0107] Step C1: Based on the sub-indicators of the target traffic indicators in multiple reference live streaming rooms, divide the sub-indicators into a preset number of sub-intervals; obtain the preset sub-weights corresponding to the sub-intervals where the target live streaming room's sub-indicators are located.

[0108] Each sub-metric is an independent statistical analysis dimension, sorting the corresponding data from all reference live streams. For example, if the sub-metric is "number of viewers," then the number of viewers from all reference live streams within this time period needs to be sorted. Based on preset rules, the data for each sub-metric is divided into multiple sub-intervals. For example, if it's decided to divide each sub-metric into three sub-intervals, the top 8% could be used as the first sub-interval; the top 15%-8% could be used as the second sub-interval.

[0109] Based on preset rules or algorithms, a preset sub-weight is assigned to each sub-interval. This sub-weight reflects the importance or performance level of the data within that sub-interval relative to other sub-intervals. These sub-weights can be predefined or set based on the business situation of the live broadcast room. For example, important business can have a higher sub-weight than less important business.

[0110] Step C2: Select the maximum value from the preset sub-weights corresponding to the multiple sub-indicators of the target traffic indicator as the initial weight corresponding to the target traffic indicator of the target live room.

[0111] For each sub-metric of the target traffic metric, its corresponding preset sub-weights are obtained, and the maximum value is selected from these sub-weights. This maximum value is used as the initial weight of the target live streaming room on that target traffic metric. This ensures that in the initial stage, the weight allocation highlights the best-performing sub-metric, while also providing a foundation for subsequent optimization and adjustments. This is beneficial for discovering high-quality new live streaming rooms.

[0112] In this embodiment, by dividing the sub-indicators into different sub-intervals and assigning corresponding sub-weights, the specific performance of the live streaming room on each sub-indicator can be more precisely located. Selecting the maximum value as the initial weight helps the platform better allocate resources and support. This allows live streaming rooms that perform well on certain key sub-indicators to receive more promotional traffic. In short, it helps the platform to evaluate the performance of live streaming rooms more scientifically and fairly, and implement effective traffic support strategies accordingly.

[0113] In this embodiment of the disclosure, the final weight of the target live stream is determined based on the initial weights corresponding to various traffic metrics. This can be achieved by multiplying the initial weights corresponding to each traffic metric, or by weighted summing the initial weights corresponding to each traffic metric.

[0114] The final weight of the target live stream is obtained by multiplying the initial weights corresponding to various traffic metrics. This method emphasizes the combined effect of the weights of each metric; an excessively low weight for any metric can significantly impact the final result.

[0115] The final weight of the target live stream is obtained by weighting and summing the initial weights corresponding to various traffic metrics. This is achieved by assigning different priorities or weighting coefficients to different traffic metrics, reflecting their importance. The final weight of the target live stream is obtained by multiplying the initial weights by their respective weighting coefficients and then summing the results. The weighted summation method allows certain metrics to have a larger weight in the final weight, thus more accurately reflecting the live stream's traffic performance.

[0116] In practical applications, the method chosen to determine the final weight of the target live streaming room can be determined based on the specific needs of the live streaming business, and this disclosed embodiment does not limit this.

[0117] In this embodiment, the final weight of the target live stream is obtained by multiplying the initial weights corresponding to various traffic metrics. Each metric reflects different behaviors or preferences of the target audience, allowing for a comprehensive consideration of the impact of each traffic metric. The final weight of the target live stream is obtained by weighted summing of the initial weights corresponding to each traffic metric, enabling flexible adjustment of weight allocation based on actual needs.

[0118] In summary, the live streaming traffic control method provided in this disclosure can read real-time statistical characteristics of the live streaming room, such as reading time, number of comments, number of likes, number of orders, number of viewers, and corresponding order volume acceleration and viewer acceleration within a preset time period. It also calculates segmented thresholds for each real-time characteristic online in real time. This ensures that both the real-time statistical characteristics and thresholds are updated in real time, allowing for dynamic adjustments to support for each live streaming room based on online distribution. Live streaming rooms exceeding the dynamic threshold are given corresponding boosts, aiming to provide real-time incentives for live streaming rooms with good real-time performance and achieve real-time traffic amplification for high-performing live streaming rooms.

[0119] Based on the same technical concept, this disclosure also provides a live streaming room traffic control device 300, such as... Figure 3 As shown, it includes:

[0120] The statistics module 301 is used to collect various traffic metrics of the target live streaming room in real time.

[0121] The first determining module 302 is used to determine the initial weights corresponding to various flow indicators;

[0122] The second determining module 303 is used to determine the final weight of the target live broadcast room based on the initial weights corresponding to various traffic indicators.

[0123] Adjustment module 304 is used to adjust the traffic of the target live room based on the final weight.

[0124] In some embodiments, the first determining module is specifically used for:

[0125] Perform the following operations for each traffic metric:

[0126] Based on the traffic metrics of multiple reference live streaming rooms, the traffic metrics are divided into preset number of intervals.

[0127] Obtain the preset weight corresponding to the interval where the traffic metric of the target live room is located, and use it as the initial weight corresponding to the traffic metric of the target live room.

[0128] In some embodiments, the multiple traffic metrics include at least two of the following:

[0129] Duration metrics, interaction metrics, conversion metrics, and flow rate metrics.

[0130] In some embodiments, the duration metric includes at least one of the following first sub-metrics:

[0131] The average viewing time of multiple target objects in the target live stream within a preset time period;

[0132] The minimum viewing time of multiple target objects in the target live stream within a preset time period.

[0133] In some embodiments, the interaction metric includes at least one second sub-metric of the following:

[0134] The number of likes within a preset time period;

[0135] Number of interactions within a preset duration;

[0136] Number of comments within the preset time period;

[0137] The number of target viewers in the target live stream within a preset duration;

[0138] The number of times the target live stream is shared within a preset time period.

[0139] In some embodiments, the conversion metric includes at least one third sub-metric from the following:

[0140] The number of orders generated within the preset time period;

[0141] The first acceleration of order volume within the preset time period.

[0142] In some embodiments, the statistics module includes:

[0143] The first acquisition unit is used to acquire the number of orders within the previous preset time period of the preset time period;

[0144] The first determining unit is used to determine the acceleration of the number of orders within a preset time period relative to the number of orders within the previous preset time period, as the first acceleration.

[0145] In some embodiments, the flow rate index includes at least one fourth sub-index of the following:

[0146] The number of target viewers watching the target live stream within a preset time period;

[0147] The second acceleration is the number of target viewers watching the target live stream within a preset time period.

[0148] In some embodiments, the statistics module includes:

[0149] The second acquisition unit is used to acquire the number of target objects who watched the target live broadcast room within the previous preset time period.

[0150] The second determining unit is used to determine the acceleration between the number of target objects watching the target live room within a preset time period and the number of target objects watching the target live room within the previous preset time period, as the second acceleration.

[0151] In some embodiments, where any target traffic metric includes multiple sub-metrics, the first determining module includes:

[0152] The first execution unit is used to perform the following operations for each sub-indicator of each target traffic indicator: based on the sub-indicators in the target traffic indicators of multiple reference live broadcast rooms, divide the sub-indicators into a preset number of sub-intervals; obtain the preset sub-weights corresponding to the sub-intervals where the sub-indicators of the target live broadcast room are located;

[0153] The filtering unit is used to select the maximum value from the preset sub-weights corresponding to the multiple sub-indicators of the target traffic indicator as the initial weight corresponding to the target traffic indicator of the target live room.

[0154] In some embodiments, the second determining module includes:

[0155] The first calculation unit is used to determine the product of the initial weights corresponding to various traffic indicators, and thus obtain the final weight of the target live stream; or,

[0156] The second calculation unit is used to perform a weighted summation of the initial weights corresponding to various traffic indicators to obtain the final weight of the target live broadcast room.

[0157] The specific functions and examples of each module and submodule of the apparatus in this disclosure can be found in the relevant descriptions of the corresponding steps in the above method embodiments, and will not be repeated here.

[0158] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0159] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0160] Figure 4A schematic block diagram of an example electronic device 400 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0161] like Figure 4 As shown, device 400 includes a computing unit 401, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 402 or a computer program loaded from storage unit 408 into random access memory (RAM) 403. RAM 403 may also store various programs and data required for the operation of device 400. The computing unit 401, ROM 402, and RAM 403 are interconnected via bus 404. Input / output (I / O) interface 405 is also connected to bus 404.

[0162] Multiple components in device 400 are connected to I / O interface 405, including: input unit 406, such as keyboard, mouse, etc.; output unit 407, such as various types of monitors, speakers, etc.; storage unit 408, such as disk, optical disk, etc.; and communication unit 409, such as network card, modem, wireless transceiver, etc. Communication unit 409 allows device 400 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0163] The computing unit 401 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as the live streaming room traffic control method. For example, in some embodiments, the live streaming room traffic control method can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 408. In some embodiments, part or all of the computer program can be loaded and / or installed on device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of the live streaming room traffic control method described above can be performed. Alternatively, in other embodiments, the computing unit 401 can be configured to perform the live streaming room traffic control method by any other suitable means (e.g., by means of firmware).

[0164] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0165] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0166] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0167] To provide interaction with a target object, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor for displaying information to the target object; and a keyboard and pointing device (e.g., a mouse or trackball) through which the target object provides input to the computer. Other types of devices can also be used to provide interaction with the target object; for example, feedback provided to the target object can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the target object can be received in any form (including sound input, voice input, or tactile input).

[0168] Furthermore, this disclosure also provides a vehicle including the aforementioned electronic equipment.

[0169] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a target computer with a graphical user interface or web browser through which a target object can interact with the implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication (e.g., a communication network) of any form or medium. Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0170] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0171] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0172] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for controlling traffic in a live streaming room, comprising: Real-time statistics of various traffic metrics for the target live stream room; Determine the initial weights for each of the various traffic metrics, including: Based on the traffic metrics of multiple reference live streaming rooms, the traffic metrics are divided into a preset number of intervals. Obtain the preset weight corresponding to the interval where the traffic metric of the target live room is located, and use it as the initial weight corresponding to the traffic metric of the target live room; When any target traffic metric includes multiple sub-metrics, based on the sub-metrics in the target traffic metric of multiple reference live streaming rooms, a preset number of sub-intervals are divided for the sub-metrics; a preset sub-weight corresponding to the sub-interval where the sub-metric of the target live streaming room is located is obtained; the preset sub-weight reflects the importance of the data in the sub-interval relative to other sub-intervals, and the preset sub-weight corresponding to important business is higher than the preset sub-weight corresponding to secondary business. From the preset sub-weights corresponding to the multiple sub-indicators of the target traffic indicator, the maximum value is selected as the initial weight corresponding to the target traffic indicator of the target live room; The final weight of the target live streaming room is determined based on the initial weights corresponding to various traffic metrics. Based on the final weight, the traffic of the target live stream room is adjusted.

2. The method according to claim 1, wherein, The multiple flow metrics include at least two of the following: Duration metrics, interaction metrics, conversion metrics, and flow rate metrics.

3. The method according to claim 2, wherein the duration indicator includes at least one of the following first sub-indicators: The average viewing time of multiple target objects in the target live stream within a preset time period; The minimum viewing time of multiple target objects for the target live stream within a preset time period.

4. The method according to claim 2, wherein, The interaction metrics include at least one of the following second sub-metrics: The number of likes within a preset time period; Number of interactions within a preset duration; Number of comments within the preset time period; The number of target objects in the target live stream room to be monitored within a preset time period; The number of times the target live stream is shared within a preset time period.

5. The method according to claim 2, wherein, The conversion metric includes at least one of the following third sub-metrics: The number of orders generated within the preset time period; The first acceleration of order volume within the preset time period.

6. The method according to claim 5, wherein, Determine the first acceleration of order volume within a preset time period, including: Get the number of orders within the previous preset time period; The acceleration of the number of orders within the preset time period relative to the number of orders within the previous preset time period is determined as the first acceleration.

7. The method according to claim 2, wherein, The flow rate index includes at least one of the following fourth sub-indicators: The number of target viewers watching the target live stream within a preset time period; The second acceleration is the number of target objects watching the target live stream within a preset time period.

8. The method according to claim 7, wherein, The second acceleration for determining the number of target viewers watching the target live stream within a preset time period includes: Get the number of target objects who watched the target live broadcast room within the previous preset duration; The acceleration between the number of target objects watching the target live stream within the preset duration and the number of target objects watching the target live stream within the previous preset duration is determined as the second acceleration.

9. The method according to any one of claims 1-8, wherein, The determination of the final weight of the target live stream room based on the initial weights corresponding to various traffic metrics includes: The final weight of the target live stream room is obtained by multiplying the initial weights corresponding to various traffic metrics; or, The final weight of the target live streaming room is obtained by weighting and summing the initial weights corresponding to various traffic metrics.

10. A traffic control device for a live streaming room, comprising: The statistics module is used to collect various traffic metrics for the target live streaming room in real time. The first determining module is used to determine the initial weights corresponding to various traffic metrics, including: Based on the traffic metrics of multiple reference live streaming rooms, the traffic metrics are divided into a preset number of intervals. Obtain the preset weight corresponding to the interval where the traffic metric of the target live room is located, and use it as the initial weight corresponding to the traffic metric of the target live room; In cases where any target traffic metric includes multiple sub-metrics, the first determining module includes: The first execution unit is configured to perform the following operations for each sub-indicator of each target traffic indicator: based on the sub-indicators among the target traffic indicators of multiple reference live streaming rooms, divide the sub-indicators into a preset number of sub-intervals; and obtain the preset sub-weights corresponding to the sub-intervals where the sub-indicators of the target live streaming room are located. The filtering unit is used to filter out the maximum value from the preset sub-weights corresponding to the multiple sub-indicators of the target traffic indicator as the initial weight corresponding to the target traffic indicator of the target live room. The second determining module is used to determine the final weight of the target live streaming room based on the initial weights corresponding to various traffic indicators. The adjustment module is used to adjust the traffic of the target live streaming room based on the final weight.

11. The apparatus according to claim 10, wherein, The multiple flow metrics include at least two of the following: Duration metrics, interaction metrics, conversion metrics, and flow rate metrics.

12. The apparatus of claim 11, wherein the duration index comprises at least one first sub-index of: The average viewing time of multiple target objects in the target live stream within a preset time period; The minimum viewing time of multiple target objects for the target live stream within a preset time period.

13. The apparatus according to claim 11, wherein, The interaction metrics include at least one of the following second sub-metrics: The number of likes within a preset time period; Number of interactions within a preset duration; Number of comments within the preset time period; The number of target objects in the target live stream room to be monitored within a preset time period; The number of times the target live stream is shared within a preset time period.

14. The apparatus according to claim 11, wherein, The conversion metric includes at least one of the following third sub-metrics: The number of orders generated within the preset time period; The first acceleration of order volume within the preset time period.

15. The apparatus according to claim 14, wherein, The statistics module includes: The first acquisition unit is used to acquire the number of orders within the previous preset time period of the preset time period; The first determining unit is used to determine the acceleration of the number of orders within the preset time period relative to the number of orders within the previous preset time period, as the first acceleration.

16. The apparatus according to claim 11, wherein, The flow rate index includes at least one of the following fourth sub-indicators: The number of target viewers watching the target live stream within a preset time period; The second acceleration is the number of target objects watching the target live stream within a preset time period.

17. The apparatus according to claim 16, wherein, The statistics module includes: The second acquisition unit is used to acquire the number of target objects that watched the target live broadcast room within the previous preset duration of the preset duration. The second determining unit is used to determine the acceleration between the number of target objects watching the target live room within the preset time period and the number of target objects watching the target live room within the previous preset time period, as the second acceleration.

18. The apparatus according to any one of claims 10-17, wherein, The second determining module includes: The first calculation unit is used to determine the product of the initial weights corresponding to various traffic indicators, and obtain the final weight of the target live broadcast room; or, The second calculation unit is used to perform a weighted summation of the initial weights corresponding to various traffic indicators to obtain the final weight of the target live streaming room.

19. An electronic device comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-9.

20. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-9.

21. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-9.

Images