Advertisement recall method, medium, system, and computing device

Abstract

Embodiments of the present disclosure provide an advertisement recall method, medium, system and computing device, wherein the advertisement recall method comprises: based on an advertisement request, selecting a first controller or a second controller by a mode selector, so that the advertisement request is sent to each DSP by the first controller or the second controller, the timeout time of the advertisement is controlled, the advertisement recall is performed, and a way of dynamically controlling the timeout time for the advertisement recall is provided. The timeout time is controlled by different controllers for each advertisement request, and the advertisement revenue and user experience are improved. In addition, embodiments of the present disclosure provide a computing device.

Description

Technical Field

[0001] The embodiments of this disclosure relate to the field of Internet technology, and more specifically, the embodiments of this disclosure relate to advertising recall methods, media, systems, and computing devices. Background Technology

[0002] This section is intended to provide background or context for the embodiments of this disclosure as set forth in the claims. The description herein is not intended to be a prior art simply because it is included in this section.

[0003] Currently, the advertising server ADX can receive and respond to advertising requests, thereby enabling the playback of advertisements. The media for ad playback can be videos, web pages, etc.

[0004] In related technologies, if the advertising server's ADX does not return an ad when the client requests it, the ad will not be displayed. Specifically, the advertising server's ADX uses HTTP connection pooling technology and a uniformly configured timeout when requesting each DSP.

[0005] However, the uniform timeout configuration used by the ad server's ADX for DSP requests means that each request needs to reach the slowest DSP to return. If the slow return time of this DSP is consistently slow, it will consume a lot of resources, leading to a vicious cycle where other DSPs will have no resources available, resulting in a large number of timeouts. Consequently, the server cannot respond in a timely manner within the response time configured by the client, affecting ad exposure, reducing ad revenue, and impacting user experience. Summary of the Invention

[0006] This disclosure provides an advertising recall method, medium, system, and computing device to improve the reliability of the reference answers provided by the customer service system and further improve the service efficiency of human agents.

[0007] In a first aspect of this disclosure, an ad recall method is provided, comprising: acquiring an ad request; selecting a first controller or a second controller based on the ad request using a mode selector; sending the ad request to various DSPs via the first controller or the second controller, controlling the ad timeout period, and performing ad recall.

[0008] In one embodiment of this disclosure, the step of selecting a first controller or a second controller based on the advertising request via a mode selector includes: obtaining device information of the requesting device based on the advertising request; determining, via the mode selector, whether the first controller and the second controller will perform advertising recall on the requesting device within a preset time period based on the device information; and selecting the first controller or the second controller based on the advertising recall situation.

[0009] In one embodiment of this disclosure, the step of sending the advertising request to each DSP through the first controller or the second controller, controlling the advertising timeout time, and performing advertising recall includes: when the mode selector selects the first controller, obtaining a user score through the first controller, the user score being calculated offline based on the profile information of the requesting user; obtaining the pre-stored response rate scores of each DSP; counting each target DSP currently responding to the advertising request and returning data, determining the number of target DSPs, and calculating the total response rate score of the target DSPs based on the response rate scores of each DSP; when the total score is not lower than the user score and the number meets the pre-set recall quantity requirement, stopping the waiting and recalling each target DSP; otherwise, continuing to wait.

[0010] In one embodiment of this disclosure, the step of sending the advertising request to each DSP through the first controller or the second controller, controlling the advertising timeout time, and performing advertising recall includes: when the mode selector selects the second controller, obtaining device information and environmental information of the requesting device through the second controller; obtaining the corresponding response time interval based on the device information and the environmental information; obtaining the intersection point of the historical response rate analysis curve and the historical advertising exposure rate curve of any DSP among the DSPs; when the time corresponding to the intersection point is within the response time interval, using the time corresponding to the intersection point as the upper limit waiting time; when the time corresponding to the intersection point is outside the response time interval, using the maximum endpoint value of the response time interval as the upper limit waiting time; recalling the DSP within the upper limit waiting time corresponding to each DSP, and no longer waiting after exceeding the upper limit waiting time.

[0011] In one embodiment of this disclosure, the response rate score of each DSP is calculated based on the historical response time of each DSP.

[0012] In one embodiment of this disclosure, the method further includes: removing DSPs with response rate scores below a preset threshold.

[0013] In one embodiment of this disclosure, the device information includes at least one of the following: device type, device model, device operator, or device price; the environmental information includes at least one of the following: the region where the device is located or the network where the device is currently located.

[0014] In a second aspect of the present disclosure, a computer-readable storage medium is provided, which stores computer-executable instructions that, when executed by a processor, implement the advertising recall method provided in the first aspect.

[0015] In a third aspect of the present disclosure, an ad recall system is provided, comprising: a mode selector for selecting a first controller or a second controller based on an ad request; the first controller or the second controller for sending the ad request to each DSP, controlling the ad timeout period, and performing ad recall.

[0016] In one embodiment of this disclosure, the mode selector is specifically used to: obtain device information of the requesting device based on the advertising request; determine, based on the device information of the requesting device, whether the first controller and the second controller will perform advertising recall on the requesting device within a preset time period, and select the first controller or the second controller based on the advertising recall situation.

[0017] In one embodiment of this disclosure, when the mode selector selects the first controller, the first controller is specifically configured to: obtain a user score, which is calculated offline based on the profile information of the requesting user; obtain the response rate scores of each DSP that are pre-stored; count each target DSP that is currently responding to the advertising request and returning data, determine the number of target DSPs, and calculate the total response rate score of the target DSPs based on the response rate scores of each DSP; when the total score is not lower than the user score and the number of DSPs meets the pre-set recall quantity requirement, stop waiting and recall each target DSP; otherwise, continue waiting.

[0018] In one embodiment of this disclosure, when the mode selector selects the second controller, the second controller is specifically configured to: acquire device information and environmental information of the requesting device; acquire a corresponding response time interval based on the device information and the environmental information; acquire the intersection of the historical response rate analysis curve and the historical ad exposure rate curve of any DSP among the DSPs, and when the time corresponding to the intersection point is within the response time interval, use the time corresponding to the intersection point as the upper limit waiting time; when the time corresponding to the intersection point is outside the response time interval, use the maximum endpoint of the response time interval as the upper limit waiting time; recall the DSP within the upper limit waiting time corresponding to each DSP, and stop waiting if the upper limit waiting time is exceeded.

[0019] In one embodiment of this disclosure, the response rate score of each DSP is calculated based on the historical response time of each DSP.

[0020] In one embodiment of this disclosure, the first controller is further configured to: remove DSPs with response rate scores below a preset threshold.

[0021] In one embodiment of this disclosure, the device information includes at least one of the following: device type, device model, device operator, or device price; the environmental information includes at least one of the following: the region where the device is located or the network where the device is currently located.

[0022] In a fourth aspect of this disclosure, a computing device is provided, comprising: at least one processor and a memory; the memory storing computer execution instructions; and at least one processor executing the computer execution instructions stored in the memory, such that the at least one processor performs the advertising recall method as provided in the first aspect.

[0023] In this embodiment, based on the advertising request, a first controller or a second controller is selected by a mode selector. The advertising request is then sent to each DSP by the first controller or the second controller to control the advertising timeout and perform advertising recall. This provides a way to dynamically control the timeout for advertising recall, using different controllers to control the timeout for each advertising request, thereby improving advertising revenue and user experience. Attached Figure Description

[0024] The above and other objects, features, and advantages of this disclosure will become readily apparent from the following detailed description of exemplary embodiments, taken in conjunction with the accompanying drawings. Several embodiments of this disclosure are illustrated in the drawings by way of example and not limitation, in which:

[0025] Figure 1 A schematic diagram illustrating an advertising recall according to an embodiment of the present disclosure is shown.

[0026] Figure 2 A schematic diagram illustrating an application scenario provided according to an embodiment of this disclosure is shown.

[0027] Figure 3 A schematic flowchart of an advertising recall method according to an embodiment of the present disclosure is shown.

[0028] Figure 4 A schematic flowchart of an advertising recall method according to another embodiment of the present disclosure is shown.

[0029] Figure 5 A schematic diagram of the structure of a first controller provided according to an embodiment of the present disclosure is shown.

[0030] Figure 6 A schematic flowchart of an advertising recall method according to another embodiment of the present disclosure is shown.

[0031] Figure 7The historical response rate analysis curve and historical ad exposure rate curve of a DSP provided according to an embodiment of the present disclosure are schematically shown, as well as a schematic diagram of the intersection of the two curves;

[0032] Figure 8 A schematic diagram of the structure of a second controller provided according to an embodiment of the present disclosure is shown.

[0033] Figure 9 A schematic diagram of the structure of a storage medium provided according to an embodiment of the present disclosure is shown.

[0034] Figure 10 A schematic diagram of the structure of an advertising recall system provided according to an embodiment of the present disclosure is shown.

[0035] Figure 11 A schematic diagram of the structure of a computing device provided according to an embodiment of the present disclosure is shown.

[0036] In the accompanying drawings, the same or corresponding reference numerals indicate the same or corresponding parts. Detailed Implementation

[0037] The principles and spirit of this disclosure will now be described with reference to several exemplary embodiments. It should be understood that these embodiments are given merely to enable those skilled in the art to better understand and implement this disclosure, and are not intended to limit the scope of this disclosure in any way. Rather, these embodiments are provided to make this disclosure more thorough and complete, and to fully convey the scope of this disclosure to those skilled in the art.

[0038] Those skilled in the art will recognize that embodiments of this disclosure can be implemented as a system, apparatus, device, method, or computer program product. Therefore, this disclosure can be specifically implemented in the following forms: entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0039] According to embodiments of this disclosure, an advertising recall method, medium, system, and computing device are proposed.

[0040] In this article, it is important to understand the following terms and their meanings:

[0041] (1)DSP stands for Demand Side Platform, which means that advertising demand can be purchased and traded through DSP.

[0042] (2) ADX, short for AdExchange, is an advertising exchange center that facilitates the purchase of media advertising inventory by multiple advertising demanders.

[0043] Furthermore, the number of any elements in the accompanying drawings is for illustrative purposes only and not for limitation, and any naming is for distinction only and has no limiting meaning.

[0044] The principles and spirit of this disclosure will be explained in detail below with reference to several representative embodiments. Invention Overview

[0046] The inventors have discovered that when a user opens an app containing ads, the ADX typically sends this ad display opportunity to all connected DSPs for bidding to purchase the exposure opportunity. The ADX uses HTTP connection pooling technology when requesting each DSP. Related technologies include... Figure 1 As shown in the diagram (using DSP1, DSP2, and DSP3 as examples), when a client requests an ad, it sets a uniform timeout (fixed timeout). If a DSP fails to return within the set timeout, the ADX discards that DSP's bid and selects a suitable ad from the returning DSPs. However, using a uniform timeout for the ADX means that each request requires the slowest DSP to return within that timeout period, consuming significant resources and preventing HTTP connections from being released. This leads to a vicious cycle, leaving other DSPs without resources, resulting in numerous timeouts. Consequently, the server cannot respond promptly within the client's configured response time, impacting ad exposure, reducing ad revenue, and affecting user experience. Therefore, it is necessary to consider how to dynamically control the timeout for ad recall to improve ad revenue and user experience.

[0047] Based on the idea of ​​dynamically controlling the timeout period during ad recall, in the embodiments of this disclosure, a first controller or a second controller is selected through a mode selector based on the ad request. The ad request is then sent to each DSP through the first controller or the second controller to control the ad timeout period and recall the ad. This not only optimizes the user experience, shortens the waiting time, and increases the user's acceptance of the ad, but also reduces server pressure, saves resources, and increases the advertising revenue of the media by dynamically controlling the timeout period to recall the ad.

[0048] After introducing the basic principles of this disclosure, various non-limiting embodiments of this disclosure will be described in detail below.

[0049] Application Scenarios Overview

[0050] The scenarios to which this disclosure applies include advertising recall scenarios.

[0051] First refer to Figure 2 , Figure 2The diagram schematically illustrates an application scenario provided according to an embodiment of the present disclosure. The device involved in this application scenario includes a mode selector 201, a first controller 202, and a second controller 203. DSP1, DSP2, and DSP3 are also used as examples in the diagram.

[0052] When the application scenario is ad recall: If a user opens an APP with ads, the ADX can send this ad display opportunity to the mode selector 201. The mode selector 201 selects the first controller 202 or the second controller 203. Then, through the first controller 202 or the second controller 203, the DSP request is distributed using a strategy, the timeout time is dynamically controlled, and ad recall is performed to improve ad revenue and user experience.

[0053] Optionally, the first controller 202 can be a response rate controller, which uses the response rate to control the advertising response time, and the second controller 203 can be a response time controller, which uses device information and environmental information to control the advertising response time.

[0054] Exemplary methods

[0055] The following is combined Figure 2 Application scenarios, refer to Figures 3-8 This document describes an advertising recall method provided according to exemplary embodiments of the present disclosure. It should be noted that the above application scenarios are shown only to facilitate understanding of the spirit and principles of the present disclosure, and the embodiments of the present disclosure are not limited in any way. Rather, the embodiments of the present disclosure can be applied to any applicable scenario.

[0056] refer to Figure 3 , Figure 3 A schematic flowchart illustrating an advertising recall method according to an embodiment of this disclosure is shown. Figure 3 As shown, advertising recall methods include:

[0057] S301, Obtain advertising request.

[0058] Here, taking an example where a user opens an app with ads installed on the client, this embodiment obtains an ad request when the user opens the app. This ad request can then be sent to a mode selector. The mode selector chooses either a first controller or a second controller and distributes the ad request using a strategy. The ad request may carry device information, including device type, device model, and other information used to identify the requesting device.

[0059] S302. Based on the above advertising request, select the first controller or the second controller through the mode selector.

[0060] Optionally, this embodiment can obtain device information of the requesting device based on the above-mentioned advertising request, and then, based on the device information, determine the situation of the first controller and the second controller performing advertising recall on the requesting device within a preset time period through the above-mentioned mode selector, and select the first controller or the second controller based on the advertising recall situation.

[0061] The aforementioned preset time period can be set according to actual conditions, such as 7 days or 10 days. In this embodiment, after obtaining the device information of the requesting device based on the aforementioned advertising request, the device information can be further used by the aforementioned mode selector to determine the advertising recall status of the first controller and the second controller within a certain period, such as within 7 days. This includes the overall advertising response rate and advertising revenue of the advertising recall. Based on the advertising recall status, the first controller or the second controller is selected. For example, the controller with a fast overall advertising response rate and high advertising revenue is selected for advertising recall, so that the controller can be used to better distribute DSP requests and dynamically control the timeout period for advertising recall. Furthermore, this embodiment can further determine the percentage of advertising requests allocated daily by the first controller and the second controller, thereby enabling relevant personnel to promptly understand the advertising request distribution status through the first controller and the second controller.

[0062] S303. The above-mentioned advertising request is sent to each DSP through the first controller or the second controller to control the advertising timeout time and recall the advertisement.

[0063] Optionally, the first controller can be a response rate controller, which uses the response rate to control the advertising response time, and the second controller can be a response time controller, which uses device information and environmental information to control the advertising response time.

[0064] Here, this embodiment uses the first or second controller to send the aforementioned advertising requests to each DSP, control the advertising timeout period, and perform advertising recall. This provides a dynamic timeout control method, using different strategies to control the timeout period for each advertising request. In this way, when the number of advertising requests is high, the waiting time is no longer a uniformly set timeout period, meaning there is no need to wait for a long time. This reduces the pressure on the HTTP connection pool of the DSP that distributes the ADX requests, releases connections as early as possible, and solves the problem of waiting for large amounts of traffic and resources. Moreover, because there is no need to wait for a uniformly set timeout period, the time from client requesting an advertisement to displaying the advertisement is shortened, improving the user experience. In addition, by dynamically controlling the timeout period, the server can respond to the client's advertising requests in a timely manner, increasing the advertising exposure rate and helping advertising media increase revenue.

[0065] In this embodiment of the disclosure, based on the advertising request, a first controller or a second controller is selected by a mode selector. Then, the advertising request is sent to each DSP through the first controller or the second controller to control the advertising timeout time and perform advertising recall. Different controllers are used to control the timeout time for each advertising request to improve advertising revenue and user experience.

[0066] Furthermore, in this embodiment, different controllers are used to control the timeout for each ad request. When the mode selector selects the first controller, the first controller can be used to control the ad response time based on the response rate, thereby dynamically controlling the timeout and improving ad revenue and user experience. For example, this embodiment can use the first controller to obtain a user score and pre-store the response rate scores of each DSP. Then, it can count the number of target DSPs currently responding to the ad request and returning data, determine the number of target DSPs, and calculate the total response rate score of the target DSPs based on the response rate scores of each DSP. When the total score is not lower than the user score and the number of DSPs meets the pre-set recall quantity requirement, the waiting stops and the target DSPs are recalled; otherwise, the waiting continues. Figure 4 This is a flowchart illustrating an advertising recall method provided in another embodiment of the present disclosure, the method comprising:

[0067] S401, Obtain an advertising request.

[0068] S402. Based on the above advertising request, select the first controller or the second controller through the mode selector.

[0069] The implementation methods for steps S401-S402 are described in [reference needed]. Figure 3 The relevant descriptions in the embodiments will not be repeated here.

[0070] S403. When the mode selector selects the first controller, the user score is obtained through the first controller.

[0071] The user score mentioned above can be calculated offline based on the profile information of the requesting user.

[0072] Here, the aforementioned requesting user refers to the user corresponding to the aforementioned advertising request. For example, if a user opens an app with ads installed on the client, the aforementioned requesting user is the user who opens the app to request ads. The profile information of the aforementioned requesting user may include the user's consumption preferences, acceptance of ads, etc. Optionally, the aforementioned advertising request may carry the device information of the requesting device. In this embodiment, based on the device information of the requesting device, the advertisements requested by the requesting device within a certain period of time, such as 7 days or 10 days, can be obtained. Then, based on the advertisements requested by the requesting device within this period of time, the consumption preferences, acceptance of ads, and other information of the aforementioned requesting user can be determined. Thus, based on the consumption preferences, acceptance of ads, and other information of the aforementioned requesting user, the user score of the aforementioned requesting user can be calculated. For example, if it is determined that the aforementioned requesting user prefers sports ads and has a high acceptance of sports ads, this embodiment can calculate the user score of the aforementioned requesting user as the highest score, such as 10 points, for sports ads. In this way, the advertising response time can be dynamically controlled based on the user score.

[0073] S404: Obtain the pre-stored response rate scores for each DSP.

[0074] Optionally, the response rate scores of each of the aforementioned DSPs can be calculated based on the historical response times of each of the aforementioned DSPs.

[0075] For example, this embodiment can obtain the response time of each DSP to different types of advertisements within a certain period of time, such as 7 days or 10 days. Then, based on the response time of each DSP to different types of advertisements, the response rate score of each DSP can be determined. The response rate score of each DSP can include the response rate score of each DSP to different types of advertisements.

[0076] S405. Count the number of target DSPs that currently respond to the above advertising request and return data, determine the number of each target DSP, and calculate the total score of the response rate scores of each target DSP based on the response rate scores of each DSP.

[0077] Here, this embodiment can count the number of target DSPs that are currently responding to the above-mentioned advertising requests and returning data in real time, and determine the number of each target DSP. It can also determine the response rate score of each target DSP based on the response rate score of each target DSP for different types of advertisements. In other words, it can determine the response rate score of each target DSP for different types of advertisements based on the response rate score of each target DSP. Then, based on the response rate score of each target DSP, it can calculate the total response rate score of each target DSP for different types of advertisements. This allows for subsequent early truncation operations based on the number of target DSPs and the total response rate score for different types of advertisements, dynamically controlling the timeout time, and improving advertising revenue and user experience.

[0078] In order to further improve the response speed to the above-mentioned advertising requests, increase the advertising exposure rate and user experience, this embodiment can first remove DSPs with response rate scores lower than a preset threshold, then count each target DSP that currently responds to the above-mentioned advertising requests and returns data, determine the number of each target DSP, and calculate the total response rate score of each target DSP based on the response rate scores of each DSP.

[0079] Here, the above-mentioned preset threshold can be set according to the actual situation. For example, in this embodiment, the response rate score threshold of the DSP for different types of advertisements can be set (such as setting the response rate score threshold of the DSP for sports advertisements to 3 points, setting the response rate score threshold of the DSP for maternal and infant advertisements to 4 points, etc.), and then using the above-mentioned response rate score threshold as the above-mentioned preset threshold.

[0080] In this embodiment, if the DSP response rate score is lower than the preset threshold, it means that the DSP has a longer response time for sports-related advertisements. If the DSP is removed, the remaining DSPs will have a higher response rate score for sports-related advertisements, meaning that the remaining DSPs will have a shorter response time for sports-related advertisements. If the advertisement request is for a sports-related advertisement, the remaining DSPs can respond to the advertisement request quickly, reducing waiting time and improving user experience and advertising revenue.

[0081] S406. When the total score is not lower than the user score and the number of targets meets the preset recall quantity requirement, stop waiting and recall each target DSP; otherwise, continue waiting.

[0082] Here, this embodiment can determine in real time whether the total score of the response rate of each target DSP is not lower than the above-mentioned user score. If the total score of the response rate of each target DSP is not lower than the above-mentioned user score, such as the above-mentioned advertisement request is for sports advertisements, the above-mentioned user score is 10 points, and the response rate scores of each target DSP that currently responds to the above-mentioned advertisement request and returns data for sports advertisements are 4 points, 3 points and 4 points respectively, with a total score of 11 points, which is not lower than 10 points, this embodiment can further determine whether the number of each target DSP that currently responds to the above-mentioned advertisement request and returns data meets the preset recall quantity requirement.

[0083] To ensure the diversity of advertisements, this embodiment pre-sets the above-mentioned recall quantity requirements. The recall quantity requirements can be set according to the actual situation. For example, this embodiment sets DSP recall quantity requirements for different types of advertisements (such as setting the DSP recall quantity requirement for sports advertisements to be no less than 3, and setting the DSP recall quantity requirement for maternal and infant advertisements to be no less than 4, etc.). Then, the set recall quantity is used as the above-mentioned pre-set recall quantity.

[0084] If this embodiment further determines that the number of target DSPs currently responding to the aforementioned ad requests and returning data also meets the pre-set recall quantity requirement, then all distributed data can be truncated in advance, stopping the waiting and recalling each target DSP. Here, this embodiment no longer waits for a uniformly set timeout, but instead dynamically controls the timeout to perform an early truncation operation. This reduces the pressure on the HTTP connection pool of the ADX distribution request DSP, releases connections as early as possible, solves the problem of waiting for large amounts of traffic and resources, and shortens the time from client requesting an ad to ad display, improving user experience and increasing ad exposure, thus helping advertising media increase revenue.

[0085] In this embodiment, when the total response rate score of each target DSP currently responding to the above-mentioned advertising request and returning data is lower than the above-mentioned user score, or when the number of each target DSP currently responding to the above-mentioned advertising request and returning data does not meet the preset recall quantity requirement, the system continues to wait until the total score is not lower than the above-mentioned user score and the number of DSPs meets the preset recall quantity requirement. Then, the system stops waiting and recalls each of the target DSPs. This achieves dynamic control of the advertising timeout during advertising recall, optimizes the user experience, and improves the advertising revenue of the media.

[0086] Additionally, for example, such as Figure 5As shown, the first controller may include a score fitter, a DSP response rate score pool, a bid rate guaranteeer, and a response truncation mechanism. The first controller can obtain the user score through the score fitter and retrieve the pre-stored response rate scores of each DSP from the DSP response rate score pool. Furthermore, it can use the bid rate guaranteeer to count the number of target DSPs currently responding to the ad request and returning data, determine the number of each target DSP, and calculate the total response rate score of all target DSPs based on their respective response rate scores. When the total score is not lower than the user score and the number of DSPs meets a pre-set recall requirement, the first controller can also stop waiting and recall the target DSPs using the response truncation mechanism; otherwise, it continues waiting.

[0087] In this embodiment, when the mode selector selects the first controller, the first controller is used to obtain the user score and the pre-stored response rate scores of each DSP. Then, the number of target DSPs currently responding to the ad request and returning data is determined, and based on the response rate scores of each DSP, the total response rate score of the target DSPs is calculated. When the total score is not lower than the user score and the number of DSPs meets the pre-set recall quantity requirement, waiting stops and the target DSPs are recalled, subsequent requests are truncated, reducing the pressure on the HTTP connection pool of the ADX distribution request DSP, releasing connections as early as possible, and solving the problem of high traffic and large resource waiting. Furthermore, this embodiment, by considering the user score and the response rate scores of each DSP, dynamically controls the ad timeout while ensuring the display opportunities of high-yield ads. In addition, this embodiment also pre-sets a recall quantity requirement, and truncation is only performed when the number of target DSPs currently responding to the ad request and returning data meets the recall quantity requirement, ensuring the diversity of ads.

[0088] In this embodiment of the present disclosure, when the mode selector selects the second controller, the second controller can be used to control the ad response time based on device information and environmental information to dynamically control the timeout time, thereby improving ad revenue and user experience. For example, this embodiment can use the second controller to first obtain the device information and environmental information of the requesting device, then obtain the corresponding response time interval based on the device information and environmental information, and obtain the intersection point of the historical response rate analysis curve and the historical ad exposure rate curve of any of the aforementioned DSPs. When the time corresponding to the intersection point is within the aforementioned response time interval, the time corresponding to the intersection point is used as the upper limit waiting time. When the time corresponding to the intersection point is outside the aforementioned response time interval, the maximum endpoint value of the aforementioned response time interval is used as the upper limit waiting time. Thus, the DSP is recalled within the aforementioned upper limit waiting time corresponding to each of the aforementioned DSPs; if the upper limit waiting time is exceeded, the DSP no longer waits. Figure 6 This is a flowchart illustrating an advertising recall method provided in another embodiment of the present disclosure, the method comprising:

[0089] S601, Obtain advertising request.

[0090] S602. Based on the above advertising request, select the first controller or the second controller through the mode selector.

[0091] The implementation methods for steps S601-S602 are described in [reference needed]. Figure 3 The relevant descriptions in the embodiments will not be repeated here.

[0092] S603. When the mode selector selects the second controller, the device information and environmental information of the requesting device are obtained through the second controller.

[0093] The aforementioned equipment information may include at least one of the following: equipment type, equipment model, equipment operator, or equipment price; the aforementioned environmental information may include at least one of the following: the region where the equipment is located or the network where the equipment is currently located.

[0094] Here, the device types mentioned above can be categorized by device performance. For example, taking a mobile phone as an example, mobile phone types can include flagship models, gaming phones, etc. The network currently the device is connected to can be categorized by the network type, such as Wi-Fi, 5G, 4G, wired, etc.

[0095] S604. Obtain the corresponding response time range based on the above equipment information and environmental information.

[0096] In this embodiment, the response time intervals of each DSP under different device information and different environmental information recorded in historical data can also be obtained. Therefore, based on the response time intervals of each DSP under different device information and different environmental information, and the aforementioned obtained device information and environmental information of the requesting device, the response time interval of each DSP under the aforementioned device information and environmental information of the requesting device can be determined. For example, assuming the aforementioned device information includes device type (e.g., a mobile phone, specifically a flagship model mobile phone), and the aforementioned environmental information includes the current network (e.g., a 5G network), this embodiment can obtain the response time intervals of each DSP under different device types and different networks recorded in historical data. Therefore, based on the response time intervals of each DSP under different device types and different networks, and the aforementioned obtained device type and network of the requesting device, the response time interval of each DSP under the aforementioned flagship model mobile phone and 5G network can be determined, such as 60 to 120 ms.

[0097] S605. Obtain the intersection of the historical response rate analysis curve and the historical ad exposure rate curve of any of the above DSPs.

[0098] Here, in this embodiment, the historical response rate analysis curve and historical ad exposure rate curve of any of the above-mentioned DSPs can be determined first, and then the corner points of the two curves can be calculated to obtain the intersection point of the historical response rate analysis curve and historical ad exposure rate curve of any of the above-mentioned DSPs.

[0099] In this embodiment, the response time of any one of the aforementioned DSPs over a period of time, such as 7 or 10 days, can be obtained first. Then, based on the response time over this period, the historical response rate analysis curve and historical ad exposure rate curve of any one of the aforementioned DSPs can be determined. Here, in the aforementioned historical response rate analysis curve, the relationship between response time and DSP response rate is an increasing function, that is, as the response time increases, the DSP response rate increases. This can be represented by a transformation of the sigmoid function, such as... In the aforementioned historical ad exposure rate curves, the relationship between response time and ad exposure rate is a decreasing function; that is, as response time increases, ad exposure rate decreases. The curve can be a variation of the sigmoid function, for example, as shown below. Figure 7 As shown, Figure 7 The diagram shows the historical response rate analysis curve and historical ad exposure rate curve of a DSP, as well as the intersection point of the two curves. The response time corresponding to this intersection point is the optimal response time of the DSP. That is, at the response time corresponding to this intersection point, the DSP's response rate and ad exposure rate are both good, and the optimal response time of the DSP is (e.g., 80ms).

[0100] S606. When the time corresponding to the above intersection point is within the above response time interval, the time corresponding to the above intersection point shall be the upper limit of the waiting time. When the time corresponding to the above intersection point is outside the above response time interval, the maximum endpoint of the above response time interval shall be the upper limit of the waiting time.

[0101] In this embodiment, after obtaining the intersection of the historical response rate analysis curve and the historical ad exposure rate curve of any DSP, although Figure 7 The diagram shows that the response time corresponding to the intersection point is the optimal response time of the DSP. However, it is also necessary to consider whether the time corresponding to the intersection point is within the above response time interval. Therefore, this embodiment further determines whether the time corresponding to the intersection point is within the above response time interval. If the time corresponding to the intersection point is within the above response time interval, the upper limit waiting time is the time corresponding to the intersection point. If the time corresponding to the intersection point is outside the above response time interval, the upper limit waiting time is the maximum endpoint of the above response time interval, thereby meeting the application requirements.

[0102] S607. Recall the DSP within the upper limit waiting time corresponding to each of the above DSPs; if the upper limit waiting time is exceeded, stop waiting.

[0103] Here, in this embodiment, the corresponding response time interval can be obtained by requesting device information and environmental information of the device, and the response time of any DSP in each of the above-mentioned DSPs within a certain period of time can be obtained. Based on these response times, the intersection of the historical response rate analysis curve and the historical ad exposure rate curve of any DSP in each DSP is calculated. When the time corresponding to the intersection point is within the above-mentioned response time interval, the time corresponding to the intersection point is taken as the upper limit waiting time. When the time corresponding to the intersection point is outside the above-mentioned response time interval, the maximum endpoint of the above-mentioned response time interval is taken as the upper limit waiting time. Then, all DSP requests are distributed, and the DSP is recalled within the upper limit waiting time corresponding to each DSP. If the upper limit waiting time is exceeded, no further waiting is required.

[0104] Additionally, for example, such as Figure 8As shown, the second controller may include a fractional fitting unit, a DSP response rate parser, an ad exposure rate statistician, a response dispatcher, and a response truncate unit. The second controller can use the fractional fitting unit to obtain the corresponding response time interval based on the device and environmental information. It can also use the DSP response rate parser to determine the historical response rate parsing curve of any DSP and the ad exposure rate statistician to determine the historical ad exposure rate curve of any DSP. Furthermore, it calculates the corner point of the two curves. When the time corresponding to the intersection point is within the response time interval, the upper limit waiting time is set at the time corresponding to the intersection point. When the time corresponding to the intersection point is outside the response time interval, the upper limit waiting time is set at the maximum endpoint of the response time interval. Then, the response dispatcher distributes all DSP requests, recalling the DSP within the upper limit waiting time corresponding to each DSP. If the upper limit waiting time is exceeded, the DSP stops waiting and is truncated by the response truncate unit.

[0105] In this embodiment, when the mode selector selects the second controller, the second controller is used to obtain the device information and environmental information of the requesting device. Then, based on this device information and environmental information, the corresponding response time interval is obtained, and the intersection of the historical response rate analysis curve and the historical ad exposure rate curve of any of the DSPs is obtained. When the time corresponding to the intersection point is within the response time interval, the time corresponding to the intersection point is used as the upper limit waiting time. When the time corresponding to the intersection point is outside the response time interval, the maximum endpoint of the response time interval is used as the upper limit waiting time. DSPs are recalled within the upper limit waiting time corresponding to each DSP. If the upper limit waiting time is exceeded, the waiting stops, and subsequent requests are truncated. This reduces the pressure on the HTTP connection pool of the ADX distributing request DSPs, releases connections as early as possible, and solves the problem of high traffic and large resource waiting. Furthermore, this embodiment considers the device information and environmental information of the requesting device, uses response rate and exposure rate statistics to analyze the optimal timeout time for each response, and dynamically sets the timeout time for each DSP, saving resources and improving user experience.

[0106] Exemplary media

[0107] After introducing the methods of exemplary embodiments of this disclosure, the following references are made. Figure 9 The storage medium of the exemplary embodiments of this disclosure will be described.

[0108] refer to Figure 9As shown, the storage medium 90 stores a program product for implementing the above-described method according to embodiments of the present disclosure. This program product may be a portable compact disc read-only memory (CD-ROM) and includes program code, and can run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto.

[0109] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, 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 thereof.

[0110] A readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying readable program code. This propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium.

[0111] Program code for performing the operations disclosed herein can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing devices can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN).

[0112] Exemplary device

[0113] Having introduced the medium of exemplary embodiments of this disclosure, the following references are made to... Figure 10 The advertising recall system of the exemplary embodiments of this disclosure will be described. The advertising recall system is used to implement the advertising recall method provided in any of the above method embodiments. Its implementation principle and technical effect are similar, and will not be repeated here.

[0114] refer to Figure 10 , Figure 10This is a schematic diagram of the structure of an advertising recall system provided in one embodiment of this disclosure. Figure 10 As shown, the ad recall system includes:

[0115] The mode selector 1001 is used to select either the first controller or the second controller based on the advertising request.

[0116] The first controller 1002 or the second controller 1003 is used to send the advertising request to each DSP, control the advertising timeout time, and perform advertising recall.

[0117] In one embodiment of this disclosure, the mode selector 1001 is specifically used to: obtain device information of the requesting device based on the advertising request; determine, based on the device information of the requesting device, whether the first controller and the second controller will perform advertising recall on the requesting device within a preset time period, and select the first controller or the second controller based on the advertising recall situation.

[0118] In another embodiment of this disclosure, when the mode selector 1001 selects the first controller 1002, the first controller 1002 is specifically configured to: obtain a user score, which is calculated offline based on the profile information of the requesting user; obtain the response rate scores of each DSP that are pre-stored; count each target DSP that is currently responding to the advertising request and returning data, determine the number of target DSPs, and calculate the total response rate score of the target DSPs based on the response rate scores of each DSP; when the total score is not lower than the user score and the number of DSPs meets the pre-set recall quantity requirement, stop waiting and recall each target DSP; otherwise, continue waiting.

[0119] In another embodiment of this disclosure, when the mode selector 1001 selects the second controller 1003, the second controller 1003 is specifically configured to: obtain device information and environmental information of the requesting device; obtain the corresponding response time interval based on the device information and the environmental information; obtain the intersection point of the historical response rate analysis curve and the historical ad exposure rate curve of any DSP among the various DSPs; when the time corresponding to the intersection point is within the response time interval, the time corresponding to the intersection point is used as the upper limit waiting time; when the time corresponding to the intersection point is outside the response time interval, the maximum endpoint value of the response time interval is used as the upper limit waiting time; recall the DSP within the upper limit waiting time corresponding to each DSP, and stop waiting if the upper limit waiting time is exceeded.

[0120] In yet another embodiment of this disclosure, the response rate score of each DSP is calculated based on the historical response time of each DSP.

[0121] In yet another embodiment of this disclosure, the first controller 1002 is further configured to: remove DSPs with response rate scores below a preset threshold.

[0122] In another embodiment of this disclosure, the device information includes at least one of the following: device type, device model, device operator, or device price; the environmental information includes at least one of the following: the region where the device is located or the network where the device is currently located.

[0123] Exemplary computing device

[0124] Having described the methods, media, and apparatus of exemplary embodiments of this disclosure, the following references... Figure 11 A computing device according to an exemplary embodiment of the present disclosure will be described.

[0125] Figure 11 The computing device 110 shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments disclosed herein.

[0126] like Figure 11 As shown, the computing device 110 is presented in the form of a general-purpose computing device. The components of the computing device 110 may include, but are not limited to: at least one processing unit 1101, at least one storage unit 1102, and a bus 1103 connecting different system components (including the processing unit 1101 and the storage unit 1102).

[0127] Bus 1103 includes a data bus, a control bus, and an address bus.

[0128] Storage unit 1102 may include readable media in the form of volatile memory, such as random access memory (RAM) 11021 and / or cache memory 11022, and may further include readable media in the form of non-volatile memory, such as read-only memory (ROM) 11023.

[0129] Storage unit 1102 may also include a program / utility 11025 having a set (at least one) of program modules 11024, such program modules 11024 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0130] The computing device 110 can also communicate with one or more external devices 1104 (e.g., keyboard, pointing device, etc.). This communication can be performed via input / output (I / O) interface 1105. Furthermore, the computing device 110 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 1106. Figure 11 As shown, network adapter 1106 communicates with other modules of computing device 110 via bus 1103. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with computing device 110, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0131] It should be noted that although several units / modules or sub-units / modules of the advertising recall system have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided and embodied by multiple units / modules.

[0132] Furthermore, although the operations of the methods disclosed herein are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all of the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0133] While the spirit and principles of this disclosure have been described with reference to several specific embodiments, it should be understood that this disclosure is not limited to the disclosed specific embodiments, and the division of aspects does not imply that features in these aspects cannot be combined for benefit; such division is merely for convenience of expression. This disclosure is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.

Claims

1. An advertisement recall method, comprising: obtaining an advertisement request; based on the advertisement request, obtaining device information of a requesting device; based on the device information, determining, by a mode selector, a situation of advertisement recall of the requesting device by a first controller and a second controller within a preset time period, and selecting the first controller or the second controller based on the situation of advertisement recall; when the mode selector selects the first controller, obtaining, by the first controller, a user score, the user score being calculated offline according to portrait information of a requesting user; obtaining a response rate score of each DSP stored in advance; counting a number of target DSPs currently responding to the advertisement request and returning data, determining the number of the target DSPs, and based on the response rate score of each DSP, counting a total score of the response rate score of the target DSPs; when the total score is not lower than the user score and the number meets a preset recall quantity requirement, stopping waiting and recalling the target DSPs, otherwise, continuing to wait; when the mode selector selects the second controller, obtaining, by the second controller, device information and environment information of the requesting device; obtaining a corresponding response time interval according to the device information and the environment information; obtaining an intersection of a historical response rate analysis curve and a historical advertisement exposure rate curve of any DSP of the DSPs, when a time corresponding to the intersection is located in the response time interval, taking the time corresponding to the intersection as an upper limit waiting time; when the time corresponding to the intersection is located outside the response time interval, taking a maximum endpoint value of the response time interval as the upper limit waiting time; recalling the DSPs within the upper limit waiting time corresponding to the DSPs, and no longer waiting when the upper limit waiting time is exceeded. 2.The advertisement recall method of claim 1, wherein the response rate score of each DSP is calculated according to historical response time of the DSP. 3.The advertisement recall method of claim 1, further comprising: eliminating a DSP with a response rate score lower than a preset threshold. 4.The advertisement recall method of claim 1, wherein the device information comprises at least one of the following: a device type, a device model, a device operator, or a device price; and the environment information comprises at least one of the following: a region where the device is located or a network where the device is currently located. 5.A computer readable storage medium, the computer readable storage medium storing computer execution instructions, when a processor executes the computer execution instructions, realizing the advertisement recall method of any one of claims 1 to 4. 6.An advertisement recall system for realizing the advertisement recall method of any one of claims 1 to 4, the system comprising: a mode selector configured to: based on the advertisement request, obtain device information of a requesting device; ​ determine, according to device information of a requesting device, an advertisement recall condition of the requesting device in a preset time period by the first controller and the second controller, and select the first controller or the second controller based on the advertisement recall condition; when the mode selector selects the first controller, the first controller is configured to: obtain a user score calculated offline according to portrait information of a requesting user; obtain a response rate score of each DSP stored in advance; count a number of target DSPs currently responding to the advertisement request and returning data, determine a number of the target DSPs, and based on the response rate score of each DSP, count a total score of the response rate score of the target DSPs; when the total score is not lower than the user score and the number meets a preset recall quantity requirement, stop waiting and recall the target DSPs, otherwise, continue waiting; when the mode selector selects the second controller, the second controller is configured to: obtain device information and environment information of a requesting device; obtain a corresponding response time interval according to the device information and the environment information; obtain an intersection of a historical response rate analysis curve and a historical advertisement exposure rate curve of any DSP in the plurality of DSPs, when a time corresponding to the intersection is located in the response time interval, take the time corresponding to the intersection as an upper limit waiting time; when the time corresponding to the intersection is located outside the response time interval, take a maximum endpoint value of the response time interval as the upper limit waiting time; recall the DSPs within the upper limit waiting time corresponding to the DSPs, and do not wait any more when the upper limit waiting time is exceeded.

7. The advertisement recall system of claim 6, wherein the response rate score of each DSP is calculated according to historical response time of the DSP.

8. The advertisement recall system of claim 6, wherein the first controller is further configured to: eliminate a DSP with a response rate score lower than a preset threshold.

9. The advertisement recall system of claim 6, wherein the device information comprises at least one of the following: device type, device model, device operator, or device price; and the environment information comprises at least one of the following: region where the device is located or network where the device is currently located. at least one processor and a memory; 10. A computing device comprising: the memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor performs the advertisement recall method of any one of claims 1 to 4. ​

Images