Traffic Delivery Method, Device, Storage Medium, and Electronic Device

Abstract

The present invention discloses a traffic delivery method, apparatus, storage medium, and electronic device. The method includes: when receiving a media request, obtaining a target quality score of the current traffic corresponding to the media request; obtaining a first minimum score value of multiple traffic within a first time period in the past for an ad slot; when the target quality score is greater than or equal to the first minimum score value, pushing the current traffic to the ad slot; and when the target quality score is less than the first minimum score value, prohibiting pushing the current traffic to the ad slot. The present invention solves the technical problem that the back-off ratio of the ad slot cannot be maintained when screening traffic for the ad slot.

Description

Technical Field

[0001] The present invention relates to the field of computers, and in particular, to a traffic delivery method, apparatus, storage medium, and electronic device. Background Art

[0002] PDB (Programmatic Direct Buying) is a mode of programmatic advertising delivery. In this mode, advertisers and media parties will agree on a volume return ratio for pushing and selecting volumes. Therefore, for the DSP (Demand-Side Platform, i.e., the advertising delivery platform), in the PDB mode, the top priority is to screen traffic while maintaining the volume return ratio. For the PDB delivery mode, the DSP generally classifies traffic into different types according to the KPI (Key Performance Indicator) settings of advertising projects, and then determines the preferred probabilities of different traffic types based on the volume return ratio and the preferred rate. The overall goal is to maximize the KPI indicators while ensuring the volume return ratio. However, in the prior art, it is impossible to utilize data such as delivery, clicks, and conversions, and it is also impossible to use data from other third parties such as media and customers to maintain the volume return ratio of the ad slot during traffic screening for the ad slot. Summary of the Invention

[0003] Embodiments of the present invention provide a traffic delivery method, apparatus, storage medium, and electronic device to at least solve the technical problem that the volume return ratio of the ad slot cannot be maintained during traffic screening for the ad slot.

[0004] According to one aspect of the embodiments of the present invention, a traffic delivery method is provided, including: when receiving a media request, obtaining a target quality score of the current traffic corresponding to the media request; obtaining a first minimum score value of multiple traffic volumes within a first time period in the past for the ad slot; when the target quality score is greater than or equal to the first minimum score value, pushing the current traffic to the ad slot; and when the target quality score is less than the first minimum score value, prohibiting pushing the current traffic to the ad slot.

[0005] According to another aspect of the embodiments of the present invention, there is provided a traffic delivery device, including: a first acquisition module, configured to acquire a target quality score of the current traffic corresponding to the media request when receiving the media request; a second acquisition module, configured to acquire a first minimum score value of multiple traffic volumes within a first time period in the past for the ad slot; a first processing module, configured to push the current traffic to the ad slot when the target quality score is greater than or equal to the first minimum score value; and a second processing module, configured to prohibit pushing the current traffic to the ad slot when the target quality score is less than the first minimum score value.

[0006] As an optional example, the second acquisition module includes: an acquisition unit, configured to acquire a traffic return ratio of the ad slot; a sorting unit, configured to sort the first quality scores of the multiple traffic volumes to obtain a first quality score array; and a determination unit, configured to determine the first minimum score value according to the traffic return ratio and the first quality score array.

[0007] As an optional example, the acquisition unit includes: a first acquisition subunit, configured to acquire a preferred volume and a pushed volume of the ad slot; and a first determination subunit, configured to determine the quotient of the preferred volume and the pushed volume as the traffic return ratio of the ad slot.

[0008] As an optional example, the sorting unit includes: a second acquisition subunit, configured to acquire the first quality score of each traffic volume of the multiple traffic volumes; a sorting subunit, configured to perform a descending order sorting according to the magnitudes of the first quality scores to obtain a second quality score array; and a calculation subunit, configured to divide each value in the second quality score array by a conversion value to obtain the first quality score array, where the result of dividing the maximum value in the second quality score array by the conversion value is 100.

[0009] As an optional example, the determination unit includes: a processing subunit, configured to convert the traffic return ratio into a percentage value; a second determination subunit, configured to determine the first quality scores of the first percentage values in the first quality score array as a third quality score array; and a third determination subunit, configured to determine the lowest score in the third quality score array as the first minimum score value.

[0010] As an optional example, the device further includes: a third processing module, configured to determine the current traffic as preferred traffic and send a comparison result to the media that sends the request when the target quality score is greater than or equal to the first minimum score value.

[0011] As an alternative example, the above device further includes: a sending module, configured to send the target quality score to the federated learning platform and obtain a second minimum score value when the target quality score is less than the first minimum score value; and a replacement module, configured to replace the first minimum score value with the second minimum score value.

[0012] According to another aspect of the embodiments of the present invention, there is also provided a storage medium storing a computer program, wherein the computer program, when run by a processor, executes the above-mentioned traffic delivery method.

[0013] According to another aspect of the embodiments of the present invention, there is also provided an electronic device including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the above-mentioned traffic delivery method through the computer program.

[0014] In the above-mentioned traffic delivery method of the present application, which can be used in the process of prediction and optimization of marketing intelligence technology, in the embodiments of the present invention, when a media request is received, the target quality score of the current traffic corresponding to the media request is obtained; the first minimum score value of multiple traffic within the past first time period of the advertising position is obtained; when the target quality score is greater than or equal to the first minimum score value, the current traffic is pushed to the advertising position; when the target quality score is less than the first minimum score value, the current traffic is prohibited from being pushed to the advertising position. Since in the above method, by comparing the target quality score of the current traffic with the first minimum score value, when the target quality score of the current traffic is greater than or equal to the first minimum score value, the current traffic is determined as the preferred traffic, thus realizing the screening of the traffic of the advertising position while ensuring the dropout ratio of the advertising position, and further solving the technical problem that the dropout ratio of the advertising position cannot be maintained when screening the traffic of the advertising position. Description of the Drawings

[0015] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The illustrative embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0016] Figure 1 is a flowchart of an alternative traffic delivery method according to an embodiment of the present invention;

[0017] Figure 2 is a system framework diagram of an alternative traffic delivery method according to an embodiment of the present invention;

[0018] Figure 3 is a timing diagram of an alternative traffic delivery method according to an embodiment of the present invention;

[0019] Figure 4 It is a schematic structural diagram of an optional traffic delivery device according to an embodiment of the present invention;

[0020] Figure 5 It is a schematic diagram of an optional electronic device according to an embodiment of the present invention. Specific embodiments

[0021] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0023] According to the first aspect of the embodiments of the present invention, a traffic delivery method is provided. Optionally, as Figure 1 shown, the above method includes:

[0024] S102, when receiving a media request, obtaining a target quality score of the current traffic corresponding to the media request;

[0025] S104, obtaining the first minimum score value of multiple traffic within the past first time period of the advertising space;

[0026] S106, when the target quality score is greater than or equal to the first minimum score value, pushing the current traffic to the advertising space;

[0027] S108, when the target quality score is less than the first minimum score value, prohibiting pushing the current traffic to the advertising space.

[0028] Optionally, in this embodiment, the quality score is used to indicate whether the quality of the traffic is good or not. The higher the score, the better the traffic quality. It can be 50, 80, or 120. Advertisement slot is the location where advertisements are placed on a web page. One ad slot corresponds to multiple traffic. The first minimum score value refers to the quality score of all traffic corresponding to the ad slot in the past first time period. The threshold value determined according to the drop-out ratio of the ad slot is used. When the quality score of the traffic is greater than or equal to the first minimum score value, the traffic is determined to be the preferred traffic. The first time period can be 1 hour or 2 hours.

[0029] Optionally, in this embodiment, when the media sends the user's current traffic to the advertising delivery platform to inquire whether to make an advertising delivery request, the current traffic is sent to the federated learning platform, the target quality score of the current traffic is calculated, and the first minimum score value of all traffic in the past first time period of the ad slot is obtained, and the target quality score and the first minimum score value are compared. When the target quality score is greater than or equal to the first minimum score value, the current traffic is determined to be the preferred traffic, and the current traffic is pushed to the ad slot. When the target quality score is less than the first minimum score value, pushing the current traffic to the ad slot is prohibited. For example, the target quality score of the current traffic is 90, the first minimum score value of all traffic in the past hour of the ad slot is 80, and the target quality score of 90 is greater than the first minimum score value 80. The current traffic is determined to be the preferred traffic, and the current traffic is pushed to the ad slot.

[0030] Optionally, in this embodiment, by comparing the target quality score of the current traffic with the first minimum score value, when the target quality score of the current traffic is greater than or equal to the first minimum score value, the current traffic is determined to be the preferred traffic, thereby achieving the screening of the traffic of the ad slot while ensuring the withdrawal ratio of the ad slot, thereby solving the technical problem of not being able to maintain the withdrawal ratio of the ad slot when screening the traffic of the ad slot.

[0031] As an optional example, obtaining the first lowest score values ​​of multiple traffic flows within the first time period in the past of the ad slot includes:

[0032] Get the ad placement return ratio;

[0033] Sorting the first quality scores of the plurality of flows to obtain a first quality score array;

[0034] A first minimum score value is determined according to the de-escalation ratio and the first quality score group.

[0035] Optionally, in this embodiment, the fallback ratio is the ratio of the preferred traffic value to the pushed traffic value of an ad slot over a certain period of time. The fallback ratio of the ad slot is obtained through the federated data platform, and the first quality scores of all the traffic of the ad slot within the first duration in the past are obtained. For example, a total of 5 first quality scores are obtained, which are 50, 90, 70, 120, and 88 respectively. After sorting, the first quality score array [41.7, 58.3, 78.3, 75, 100] is obtained. The first minimum score value is determined according to the fallback ratio of the ad slot and the first quality score array.

[0036] As an alternative example, obtaining the fallback ratio of an ad slot includes:

[0037] Obtaining the preferred quantity and the pushed quantity of the ad slot;

[0038] Determining the quotient of the preferred quantity and the pushed quantity as the fallback ratio of the ad slot.

[0039] Optionally, in this embodiment, the pushed quantity is the total traffic quantity pushed within a certain period of time, and the preferred quantity is the quantity of high-quality traffic among the total traffic pushed within a certain period of time. The preferred quantity and the pushed quantity of the ad slot are obtained through the federated data platform, and the quotient obtained by dividing the preferred quantity by the pushed quantity is determined as the fallback ratio of the ad slot. For example, if the preferred quantity of the ad slot is 72 and the pushed quantity is 120, then 0.6 is obtained as the fallback ratio of the ad slot.

[0040] As an alternative example, sorting the first quality scores of multiple traffic to obtain the first quality score array includes:

[0041] Obtaining the first quality score of each traffic of multiple traffic;

[0042] Sorting in descending order according to the magnitude of the first quality score to obtain the second quality score array;

[0043] Dividing each value in the second quality score array by the conversion value to obtain the first quality score array, where the result of dividing the maximum value in the second quality score array by the conversion value is 100.

[0044] Optionally, in this embodiment, the first quality scores of all the traffic of the ad slot within the first duration in the past are obtained through the federated data platform, and sorted in descending order according to the magnitude of the first quality score. For example, 5 first quality scores are obtained, which are 50, 90, 70, 120, and 88 respectively. After sorting in descending order, the second quality score array [120, 90, 88, 70, 50] is obtained. Divide each second quality score in the second score array by the conversion value, where the result of dividing the maximum value in the second quality score array by the conversion value is 100. The maximum value in the second quality score array is 120, so the conversion value is obtained as 1.2. Dividing each second quality score by the conversion value gives the first quality score array [100, 78.3, 75, 58.3, 41.7].

[0045] As an alternative example, determining the first minimum score value according to the return ratio and the first mass fraction group includes:

[0046] Convert the return ratio to a percentage value;

[0047] Determine the first mass scores of the first percentage value in the first mass fraction group as the third mass fraction group;

[0048] Determine the lowest score in the third mass fraction group as the first minimum score value.

[0049] Optionally, in this embodiment, the return ratio is converted to a percentage value, that is, the return ratio 0.6 is converted to the percentage value 60%, and the first mass scores of the first 60% in the first score group [100, 78.3, 75, 58.3, 41.7] are determined as the third mass fraction group [100, 78.3, 75], and the lowest score 75 in the third mass fraction group [100, 78.3, 75] is determined as the first minimum score value.

[0050] As an alternative example, the above method further includes:

[0051] When the target mass score is greater than or equal to the first minimum score value, determine the current traffic as the preferred traffic and send the comparison result to the media that sent the request.

[0052] Optionally, in this embodiment, if the target mass score of the current traffic is 90, and the target mass score of 90 is greater than the first minimum score value of 75, determine the current traffic as the preferred traffic, perform subsequent advertisement screening strategies, and send the comparison result to the media that sent the request.

[0053] As an alternative example, the above method further includes:

[0054] When the target mass score is less than the first minimum score value, send the target mass score to the federated learning platform to obtain the second minimum score value;

[0055] Replace the first minimum score value with the second minimum score value.

[0056] Optionally, in this embodiment, if the target mass score of the current traffic is 70, and the target mass score of 70 is less than the first minimum score value of 75, then the quality of the current traffic does not meet the condition for determining the preferred traffic. Send the target mass score to the federated learning platform and include it in the calculation of the minimum score value, recalculate the second minimum score value data, and perform iterative updates of the federated algorithm model.

[0057] Optionally, in this embodiment, a traffic delivery method is mainly provided. In the PDB programmatic advertising delivery mode, ad slots are optimized for traffic according to the "volume reduction ratio", where the volume reduction ratio = preferred volume / pushed volume. That is, in this mode, the first criterion for screening traffic is to ensure that the volume reduction ratio is qualified, i.e., greater than the specified value. This application combines the knowledge of quantiles and probability theory to design an application of the federated learning platform to the PDB programmatic advertising delivery mode to maximize the selection of high-quality traffic. The system architecture design is as follows: Figure 2 as shown.

[0058] Optionally, in this embodiment, the entire system is divided into three modules: an advertising delivery platform, a federated learning platform, and a big data platform.

[0059] 1. The advertising delivery platform is responsible for receiving media requests (the media sends user traffic to the advertising delivery platform to inquire whether to conduct advertising delivery), executing advertising delivery strategies, and recording delivery logs. The delivery logs are generated after each execution of the delivery strategy. The process of advertising delivery is a process of screening high-quality traffic. After receiving traffic each time, a delivery log is generated, and subsequently, the big data platform will collect this log and add it to the process of calculating historical traffic feature data. When delivering, historical traffic feature data is used to screen high-quality traffic;

[0060] 2. Federated learning is mainly used to score traffic, which is called the quality score here. The higher the score, the better the traffic quality;

[0061] 3. The big data platform collects delivery log data, calculates historical traffic features based on historical delivery data, and calculates the quantile value of the quality score.

[0062] The functional items between the three modules are decoupled, and the algorithm model can be iterated independently without affecting the functions of other modules.

[0063] Optionally, in this embodiment, in order to introduce the federated learning algorithm into the PDB programmatic advertising delivery mode, the system introduces the median to determine the preference of each traffic. After the big data obtains the federated learning quality score data of the traffic in the past 24 hours, it sorts the data in descending order and obtains the 1-100 quantiles according to certain rules (quantiles or fractiles, statistical concepts, which refer to the numerical points that divide the probability distribution range of a random variable into several levels. Commonly used fractiles such as: median, quartiles, percentiles) qualityScore, and qualityScore is an array. It can be known that qualityScore represents the distribution of the traffic quality scores in the past 24 hours. The Nth fractile means that the traffic quality scores of the past N% are greater than qualityScore[N]. Combining with the definition of the retreat ratio retreat of the ad slot, it can be known that when the traffic quality score is greater than or equal to qualityScore[retreat*100], this traffic is preferred, which can ensure that the actual retreat ratio in the future meets the preset of the position. The traffic time series diagram of one delivery process is as Figure 3 shown.

[0064] Optionally, an example is combined for illustration, such as Figure 3 shown:

[0065] 1. After the advertising delivery platform receives the media request, it first obtains the retreat ratio retreat of the ad slot;

[0066] 2. Then it forwards the feature information of the current traffic corresponding to the media request to the federated learning platform, and the federated learning platform will return the target quality score score of the current traffic;

[0067] 3. The advertising delivery platform requests the big data platform to obtain the first quality score array QualityScore (this result is an array) of this ad slot, and then calculates the first minimum score value minScore (minScore = QualityScore[retreat*100]) required to prefer this traffic;

[0068] 4. Compare the size of the first minimum score value minScore and the target quality score score. When score >= minScore, push the current traffic to the ad slot, determine the current traffic as the preferred traffic, perform subsequent ad screening strategies, and return the final comparison result to the media;

[0069] 5. When score < minScore, prohibit pushing the current traffic to the ad slot, no longer perform ad screening strategies, and finally record the delivery log of this traffic;

[0070] 6. After the delivery log is recorded, the target quality score score is collected by the big data platform and added to the calculation of the lowest score value to recalculate the second lowest score value data. The federated platform will perform iterative updates on the federated algorithm model based on multi-party data (the data sources are generally media, DSP, customers, and generally change according to cooperation needs).

[0071] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present invention is not limited by the described action sequence. Because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0072] According to another aspect of the embodiments of the present application, there is also provided a traffic delivery device, as Figure 4 shown, including:

[0073] A first acquisition module 402, configured to acquire the target quality score of the current traffic corresponding to the media request when receiving the media request;

[0074] A second acquisition module 404, configured to acquire the first lowest score value of multiple traffic within the past first time period for the advertising space;

[0075] A first processing module 406, configured to push the current traffic to the advertising space when the target quality score is greater than or equal to the first lowest score value;

[0076] A second processing module 408, configured to prohibit pushing the current traffic to the advertising space when the target quality score is less than the first lowest score value.

[0077] Optionally, in this embodiment, the quality score is used to represent the quality of the traffic. The higher the score, the better the traffic quality. It can be 50, 80, 120. The advertising space is the position where the advertisement is placed on the web page. One advertising space corresponds to multiple traffic. The first lowest score value is the threshold determined according to the withdrawal ratio of the advertising space among the quality scores of all traffic corresponding to the advertising space within the past first time period. When the quality score of the traffic is greater than or equal to this first lowest score value, this traffic is determined as the preferred traffic. The first time period can be 1 hour, 2 hours.

[0078] Optionally, in this embodiment, when receiving a request from the media to send the user's current traffic to the advertising platform to inquire about whether to place an advertisement, the current traffic is sent to the federated learning platform to calculate and obtain the target quality score of the current traffic, and the first lowest score value of all traffic within the past first time period for the advertising space is obtained. The target quality score and the first lowest score value are compared. When the target quality score is greater than or equal to the first lowest score value, the current traffic is determined as preferred traffic and pushed to the advertising space. When the target quality score is less than the first lowest score value, pushing the current traffic to the advertising space is prohibited. For example, if the target quality score of the current traffic is obtained as 90 and the first lowest score value of all traffic within the past 1 hour for the advertising space is 80, and the target quality score 90 is greater than the first lowest score value 80, the current traffic is determined as preferred traffic and pushed to the advertising space.

[0079] Optionally, in this embodiment, by comparing the target quality score of the current traffic with the first lowest score value, when the target quality score of the current traffic is greater than or equal to the first lowest score value, the current traffic is determined as preferred traffic, thereby achieving the screening of the traffic for the advertising space while ensuring the withdrawal ratio of the advertising space, and further solving the technical problem that the withdrawal ratio of the advertising space cannot be maintained when screening the traffic for the advertising space.

[0080] As an optional example, the second acquisition module includes:

[0081] An acquisition unit for acquiring the withdrawal ratio of the advertising space;

[0082] A sorting unit for sorting the first quality scores of multiple traffic to obtain a first quality score array;

[0083] A determination unit for determining the first lowest score value according to the withdrawal ratio and the first quality score array.

[0084] Optionally, in this embodiment, the withdrawal ratio is the ratio of the preferred traffic value to the pushed traffic value for the advertising space within a past period of time. The withdrawal ratio of the advertising space is obtained through the federated data platform, and the first quality scores of all traffic for the advertising space within the past first time period are obtained. For example, a total of 5 first quality scores are obtained, which are 50, 90, 70, 120, and 88 respectively. After sorting, the first quality score array [41.7, 58.3, 78.3, 75, 100] is obtained, and the first lowest score value is determined according to the withdrawal ratio of the advertising space and the first quality score array.

[0085] As an optional example, the acquisition unit includes:

[0086] A first acquisition subunit for acquiring the preferred quantity and the pushed quantity of the advertising space;

[0087] The first determination subunit is configured to determine the ratio of the preferred quantity to the pushed quantity as the return quantity ratio of the advertising space.

[0088] Optionally, in this embodiment, the pushed quantity is the total number of traffic pushed within a certain time period, and the preferred quantity is the number of high-quality traffic among the total traffic pushed within a certain time period. The preferred quantity and the pushed quantity of the advertising space are obtained through the federated data platform, and the quotient obtained by dividing the preferred quantity by the pushed quantity is determined as the return quantity ratio of the advertising space. For example, if the preferred quantity of the advertising space is obtained as 72 and the pushed quantity is 120, then 0.6 is obtained as the return quantity ratio of the advertising space.

[0089] As an alternative example, the sorting unit includes:

[0090] The second acquisition subunit is configured to acquire the first quality score of each of multiple traffic flows;

[0091] The sorting subunit is configured to perform a descending order sorting according to the magnitudes of the first quality scores to obtain a second quality score array;

[0092] The calculation subunit is configured to divide each value in the second quality score array by a conversion value to obtain a first quality score array, where the result of dividing the maximum value in the second quality score array by the conversion value is 100.

[0093] Optionally, in this embodiment, the first quality scores of all the traffic of the advertising space within the first time period in the past are obtained through the federated data platform, and a descending order sorting is performed according to the magnitudes of the first quality scores. For example, 5 first quality scores are obtained, which are 50, 90, 70, 120, and 88 respectively. After performing the descending order sorting, a second quality score array [120, 90, 88, 70, 50] is obtained. Each second quality score in the second score array is divided by the conversion value, where the result of dividing the maximum value in the second quality score array by the conversion value is 100, and the maximum value in the second quality score array is 120, so the conversion value is obtained as 1.2. Each second quality score is divided by the conversion value to obtain a first quality score array [100, 78.3, 75, 58.3, 41.7].

[0094] As an alternative example, the above determination unit includes:

[0095] The processing subunit is configured to convert the return quantity ratio into a percentage value;

[0096] The second determination subunit is configured to determine the first quality scores of the top percentage values in the first quality score array as a third quality score array;

[0097] The third determination subunit determines the lowest score in the third quality score array as the first lowest score value.

[0098] Optionally, in this embodiment, the reduction ratio is converted into a percentage value, that is, the reduction ratio of 0.6 is converted into a percentage value of 60%. The first 60% of the first quality scores in the first score array [100, 78.3, 75, 58.3, 41.7] are determined as the third quality score array [100, 78.3, 75], and the lowest score of 75 in the third quality score array [100, 78.3, 75] is determined as the first lowest score value.

[0099] As an alternative example, the above device further includes:

[0100] A third processing module, configured to determine the current traffic as the preferred traffic and send the comparison result to the media that sends the request when the target quality score is greater than or equal to the first lowest score value.

[0101] Optionally, in this embodiment, if the target quality score of the current traffic is 90, and the target quality score of 90 is greater than the first lowest score value of 75, the current traffic is determined as the preferred traffic, and subsequent advertisement screening strategies are performed, and the comparison result is sent to the media that sends the request.

[0102] As an alternative example, the above device further includes:

[0103] A sending module, configured to send the target quality score to the federated learning platform and obtain the second lowest score value when the target quality score is less than the first lowest score value;

[0104] A replacement module, configured to replace the first lowest score value with the second lowest score value.

[0105] Optionally, in this embodiment, if the target quality score of the current traffic is 70, and the target quality score of 70 is less than the first lowest score value of 75, then the quality of the current traffic does not meet the condition for being determined as the preferred traffic. The target quality score is sent to the federated learning platform and added to the calculation of the lowest score value, and the second lowest score value data is recalculated to perform iterative update of the federated algorithm model.

[0106] For other examples of this embodiment, please refer to the above examples and will not be elaborated here.

[0107] Figure 5 is a structural block diagram of an alternative electronic device according to an embodiment of the present application, as Figure 5 shown, including a processor 502, a communication interface 504, a memory 506, and a communication bus 508. Among them, the processor 502, the communication interface 504, and the memory 506 communicate with each other through the communication bus 508. Among them,

[0108] The memory 506 is used to store a computer program;

[0109] When the processor 502 executes the computer program stored in the memory 506, the following steps are implemented:

[0110] When a media request is received, obtain the target quality score of the current traffic corresponding to the media request;

[0111] Obtain the first lowest score value of multiple traffic flows within the first time period in the past for the ad slot;

[0112] When the target quality score is greater than or equal to the first lowest score value, push the current traffic to the ad slot;

[0113] When the target quality score is less than the first lowest score value, prohibit pushing the current traffic to the ad slot.

[0114] Optionally, in this embodiment, the above communication bus may be a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 5 only a thick line is shown in the figure, but it does not mean that there is only one bus or one type of bus. The communication interface is used for communication between the above electronic device and other devices.

[0115] The memory may include RAM, and may also include non-volatile memory, for example, at least one disk memory. Optionally, the memory may also be at least one storage device located far from the aforementioned processor.

[0116] As an example, the above memory 506 may but is not limited to include the first acquisition module 402, the second acquisition module 404, the first processing module 406, and the second processing module 408 in the above traffic delivery device. In addition, it may also include but is not limited to other module units in the above request processing device, which will not be elaborated in this example.

[0117] The above-mentioned processor can be a general-purpose processor, including but not limited to: CPU (Central Processing Unit, central processing unit), NP (Network Processor, network processor), etc.; it can also be a DSP (Digital Signal Processing, digital signal processor), ASIC (Application Specific Integrated Circuit, application-specific integrated circuit), FPGA (Field-Programmable Gate Array, field-programmable gate array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0118] Optionally, the specific examples in this embodiment can refer to the examples described in the above-mentioned embodiment, and will not be elaborated here.

[0119] Those of ordinary skill in the art can understand that Figure 5 The structure shown is only schematic. The device for implementing the above traffic delivery method can be a terminal device, which can be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a handheld computer, and a mobile Internet device (Mobile Internet Devices, MID), a PAD and other terminal devices. Figure 5 It does not limit the structure of the above-mentioned electronic device. For example, the electronic device may further include more or fewer components (such as a network interface, a display device, etc.) than those shown in Figure 5 or have a different configuration from that shown in Figure 5 shown.

[0120] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the relevant hardware of the terminal device through a program, and the program can be stored in a computer-readable storage medium. The storage medium can include: a flash drive, a ROM, a RAM, a magnetic disk or an optical disc, etc.

[0121] According to another aspect of the embodiment of the present invention, there is also provided a computer-readable storage medium, in which a computer program is stored, and when the computer program is run by a processor, it executes the steps in the above traffic delivery method.

[0122] Optionally, in this embodiment, those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the relevant hardware of the terminal device through a program, and this program can be stored in a computer-readable storage medium. The storage medium can include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, an optical disc, etc.

[0123] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0124] If the integrated unit in the above embodiments is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in the above computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing one or more computer devices (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0125] In the above embodiments of the present invention, the descriptions of the various embodiments each have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0126] In the several embodiments provided in this application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling, direct coupling, or communication connection can be through some interfaces. The indirect coupling or communication connection of units or modules can be in an electrical or other form.

[0127] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0128] In addition, in each embodiment of the present invention, each functional unit can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0129] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A traffic delivery method, characterized in that Including: When receiving a media request, obtaining a target quality score of the current traffic corresponding to the media request; Obtaining a first minimum score value of multiple traffic volumes within a first time period in the past for an ad slot, including: obtaining a drop-off ratio of the ad slot; sorting the first quality scores of the multiple traffic volumes to obtain a first quality score array; determining the first minimum score value according to the drop-off ratio and the first quality score array; The obtaining the drop-off ratio of the ad slot includes: obtaining a preferred volume and a pushed volume of the ad slot; determining the quotient of the preferred volume and the pushed volume as the drop-off ratio of the ad slot; The sorting the first quality scores of the multiple traffic volumes to obtain a first quality score array includes: obtaining the first quality score of each traffic volume of the multiple traffic volumes; sorting in descending order according to the magnitude of the first quality score to obtain a second quality score array; dividing each value in the second quality score array by a conversion value to obtain the first quality score array, where the result of dividing the maximum value in the second quality score array by the conversion value is 100; The determining the first minimum score value according to the drop-off ratio and the first quality score array includes: converting the drop-off ratio into a percentage value; determining the first quality scores of the first percentage values in the first quality score array as a third quality score array; determining the lowest score in the third quality score array as the first minimum score value; When the target quality score is greater than or equal to the first minimum score value, pushing the current traffic to the ad slot; When the target quality score is less than the first minimum score value, prohibiting pushing the current traffic to the ad slot.

2. The method according to claim 1, characterized in that The method further includes: When the target quality score is greater than or equal to the first minimum score value, determining the current traffic as preferred traffic and sending the comparison result to the media that sent the request.

3. The method according to claim 1, characterized in that, The method further includes: When the target quality score is less than the first minimum score value, sending the target quality score to a federated learning platform to obtain a second minimum score value; Replacing the first minimum score value with the second minimum score value.

4. A traffic delivery device, characterized in that, Including: A first obtaining module, configured to obtain a target quality score of the current traffic corresponding to the media request when receiving a media request; A second acquisition module, configured to acquire a first minimum score value of multiple traffic volumes within a first time period in the past for an ad slot, including: acquiring a bounce rate of the ad slot; sorting the first quality scores of the multiple traffic volumes to obtain a first quality score array; determining the first minimum score value according to the bounce rate and the first quality score array; the acquiring of the bounce rate of the ad slot includes: acquiring a preferred volume and a push volume of the ad slot; determining the quotient of the preferred volume and the push volume as the bounce rate of the ad slot; the sorting of the first quality scores of the multiple traffic volumes to obtain a first quality score array includes: acquiring the first quality score of each of the multiple traffic volumes; performing a descending order sorting according to the magnitudes of the first quality scores to obtain a second quality score array; dividing each value in the second quality score array by a conversion value to obtain the first quality score array, where the result of dividing the maximum value in the second quality score array by the conversion value is 100; the determining of the first minimum score value according to the bounce rate and the first quality score array includes: converting the bounce rate into a percentage value; determining the first quality scores of the first percentage values in the first quality score array as a third quality score array; determining the lowest score in the third quality score array as the first minimum score value; A first processing module, configured to push the current traffic volume to the ad slot when the target quality score is greater than or equal to the first minimum score value; A second processing module, configured to prohibit pushing the current traffic volume to the ad slot when the target quality score is less than the first minimum score value.

5. A computer-readable storage medium storing a computer program, characterized in that, The computer program, when run by a processor, executes the method according to any one of claims 1 to 3.

6. An electronic device, comprising a memory and a processor, characterized in that, A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 3 through the computer program.

Images