Popup window advertisement putting strategy real-time updating method and device, equipment and medium

Abstract

The invention is suitable for the technical field of artificial intelligence, and particularly relates to a real-time updating method and device for a pop-up advertisement putting strategy, equipment and a medium. The degree of interest of the user on the popup advertisement is evaluated according to the putting feedback value determined by the collected first feedback action, and the accuracy of evaluating the putting effect of the popup advertisement is effectively improved. Through the pop-up advertisement putting effect evaluated by the putting feedback value, the target putting strategy of pop-up advertisement putting in the target program is updated in time, so that the target putting strategy is more fit with the user portrait of the put pop-up advertisement, continuous low income or even no income of part of pop-up advertisements is avoided, and the user experience is improved. And meanwhile, the phenomena of collapse and the like of part of high-income pop-up advertisements are avoided, and the operation effect of pop-up advertisement putting is improved, so that the propaganda strength and the profit conversion rate in financial scenes and intelligent medical scenes are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of artificial intelligence, and particularly to a method, device, equipment and medium for real-time updating of a pop-up advertisement delivery strategy. Background Art

[0002] With the development of the mobile Internet, more and more offline services have expanded their online services, and APP (Application) has become the core platform of many enterprises. Placing pop-up advertisements in APPs is one of the most important marketing means for many enterprises, which can bring brand promotion and profit conversion to the enterprises.

[0003] Currently, the common pop-up advertisement delivery strategy is to place a large number of pop-up advertisements frequently at the entrances of major home pages to guide users to click and jump, so as to improve the enterprise profit conversion rate through the frequent click volume of users. However, a large number of high-frequency pop-up advertisements are likely to cause user disgust and even lead to user complaints or uninstallation of the application, etc., thereby affecting the operation effect of pop-up advertisement delivery and greatly reducing the brand promotion intensity and profit conversion rate of the enterprise. Summary of the Invention

[0004] Embodiments of the present invention provide a method, device, equipment and medium for real-time updating of a pop-up advertisement delivery strategy, so as to solve the problem that the brand promotion intensity and profit conversion rate of enterprises are relatively low due to the large number of high-frequency pop-up advertisement delivery methods in the prior art.

[0005] A method for real-time updating of a pop-up advertisement delivery strategy includes: When a target program delivers pop-up advertisements with a target delivery strategy, real-time monitoring of a first feedback action of a user with respect to the pop-up advertisements in the target program; there are multiple pop-up advertisements in the target program; Based on the first feedback action corresponding to each pop-up advertisement, real-time updating of the delivery feedback value corresponding to the target program; Based on the delivery feedback value, determining a new target delivery strategy corresponding to the target program; Sending the new target delivery strategy to the target program, so that the target program delivers pop-up advertisements with the new target delivery strategy.

[0006] A device for real-time updating of a pop-up advertisement delivery strategy includes: A feedback monitoring module, configured to, when a target program delivers pop-up advertisements with a target delivery strategy, real-time monitor a first feedback action of a user with respect to the pop-up advertisements in the target program; there are multiple pop-up advertisements in the target program; A feedback value updating module, configured to, based on the first feedback action corresponding to each pop-up advertisement, real-time update the delivery feedback value corresponding to the target program; A delivery strategy determination module, configured to determine a new target delivery strategy corresponding to the target program based on the delivery feedback value; A delivery strategy update module, configured to send the new target delivery strategy to the target program, so that the target program performs pop-up ad delivery with the new target delivery strategy.

[0007] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above real-time update method for pop-up ad delivery strategy is implemented.

[0008] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above real-time update method for pop-up ad delivery strategy is implemented.

[0009] The above real-time update method, device, equipment and medium for pop-up ad delivery strategy. The method effectively improves the accuracy of the effect evaluation of pop-up ad delivery by real-time monitoring the first feedback action of the user on the pop-up ad in the target program and evaluating the user's interest in the pop-up ad according to the delivery feedback value determined by the collected first feedback action. By evaluating the pop-up ad delivery effect through the delivery feedback value, the target delivery strategy for pop-up ad delivery in the target program is updated in a timely manner, making the target delivery strategy more in line with the user portrait of the pop-up ad being delivered, avoiding some pop-up ads with continuously low returns or even no returns, and also avoiding phenomena such as crashes of some high-return pop-up ads, thereby improving the operation effect of pop-up ad delivery, the brand promotion strength of the enterprise, and the profit conversion rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments of the present invention. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0011] Figure 1 is a schematic diagram of an application environment of the real-time update method for pop-up ad delivery strategy in an embodiment of the present invention; Figure 2 is a flowchart of the real-time update method for pop-up ad delivery strategy in an embodiment of the present invention; Figure 3 is a schematic block diagram of the real-time update device for pop-up ad delivery strategy in an embodiment of the present invention; Figure 4 is a schematic diagram of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0012] Next, in combination with the accompanying drawings in the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described. Obviously, the described embodiments are 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 belong to the protection scope of the present invention.

[0013] The real-time update method for pop-up advertisement placement strategy provided by the embodiments of the present invention can be applied in the application environment as Figure 1 shown. Specifically, the real-time update method for pop-up advertisement placement strategy is applied in a real-time update system for pop-up advertisement placement strategy. The real-time update system for pop-up advertisement placement strategy includes a client and a server as Figure 1 shown. The client communicates with the server through a network, and is used to solve the problem that the large-scale and high-frequency pop-up advertisement placement method in the prior art results in low brand promotion intensity and profit conversion rate of enterprises. Among them, the client, also known as the user side, refers to a program that provides local services for the client corresponding to the server. The client can be installed on, but not limited to, various personal computers, laptop computers, smart phones, tablet computers, and portable wearable devices. The server can be implemented by an independent server or a server cluster composed of multiple servers. Among them, the server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms.

[0014] In one embodiment, as Figure 2 shown, a real-time update method for pop-up advertisement placement strategy is provided. Taking the server in Figure 1 as an example, the method includes the following steps: S10: When the target program places pop-up advertisements according to the target placement strategy, real-time monitor the first feedback actions of users on the pop-up advertisements in the target program; there are multiple pop-up advertisements in the target program.

[0015] Understandably, the target program is the application program, which can be a chat software, a video software, a music software, etc. downloaded by users on the mobile terminal. The target program can also be a web page in addition to the application program. For example, the display page of search engines such as Baidu, the display page of the web version of the application program, etc. The target placement strategy is the strategy for placing pop-up ads in the target program. This target placement strategy can be set by the advertiser or the administrator of the target program. This target placement strategy can include the number, frequency, etc. of the pop-up ads to be placed. Exemplarily, assuming that a target program needs to place five pop-up ads, the target placement strategy can be set to place five pop-up ads, and the placement frequency of the five pop-up ads is set to five times a day.

[0016] Among them, the pop-up ad refers to a pop-up window ad, that is, an ad that automatically pops up a window after the user opens the target program. Generally speaking, the pop-up ads are ads containing enterprise introductions, enterprise businesses, or enterprise products, etc. placed by different enterprises in the target program. Exemplarily, in the financial scenario, financial enterprises will place pop-up ads containing relevant content such as financial enterprise information and financial product information (such as a certain type of insurance) in the target program. In the intelligent medical scenario, pop-up ads containing relevant content such as preventive measures for recently highly prevalent diseases, the process of seeking medical treatment at the hospital, or adjustments to medical insurance can be placed in the target program.

[0017] Further, after the target program places pop-up ads according to the target placement strategy, the first feedback actions of the user for the pop-up ads in the target program are monitored in real time. Among them, the first feedback action can be: the user clicks on the pop-up ad, the user closes the pop-up ad, or the user neither clicks on the pop-up ad nor closes the pop-up ad. Different first feedback actions may exist for different pop-up ads displayed in the same target program. For example, if the user is interested in a certain pop-up ad, the user will click on that pop-up ad, and other pop-up ads will not be clicked. At this time, the first feedback actions corresponding to the clicked pop-up ad and the unclicked pop-up ad are different.

[0018] S20: Based on the first feedback action corresponding to each pop-up ad, the placement feedback value corresponding to the target program is updated in real time.

[0019] Understandably, it is mentioned in the background technology that the current strategy for pop-up advertisement delivery is to deliver pop-up advertisements in large quantities and at high frequency. This method is likely to cause user disgust and even user complaints or uninstall applications, thereby affecting the operational effect of pop-up advertisement delivery. Therefore, in this embodiment, the first feedback action of the user for pop-up advertisements is monitored in real time, and the frequency and quantity of pop-up advertisements delivered in the target program are adjusted in a manner that updates the delivery feedback value corresponding to the target program in real time. Among them, the delivery feedback value is used to reflect the user's preference for pop-up advertisements in the target program. For example, if the user is interested in the pop-up advertisements in the target program (the number of times the user clicks on the pop-up advertisements is high), the delivery feedback value is high at this time; if the user is not interested in the pop-up advertisements in the target program (the number of times the user closes or does not click on the pop-up advertisements is high), the delivery feedback value is low at this time.

[0020] Furthermore, since the number and frequency of pop-up ads are different and there are multiple users opening the target program, the delivery feedback value of the target program can be updated in real time by real-time monitoring of the first feedback action corresponding to the pop-up ads.

[0021] S30: Determine a new target delivery strategy corresponding to the target program based on the delivery feedback value.

[0022] It can be understood that after the delivery feedback value corresponding to the target program is updated in real time based on the first feedback action corresponding to each pop-up advertisement, it can be evaluated whether it is appropriate to deliver pop-up advertisements in the target program with a target delivery strategy according to the delivery feedback value, so as to adjust the new target delivery strategy to make the new target delivery strategy more suitable for the pop-up advertisements in the target program, thereby avoiding some pop-up advertisements from having continuous low or even no returns, and also avoiding the crash of some high-return pop-up advertisements.

[0023] S40: Send the new target delivery strategy to the target program, so that the target program delivers pop-up advertisements according to the new target delivery strategy.

[0024] Specifically, after determining the new target delivery strategy corresponding to the target program based on the delivery feedback value, the new target delivery strategy can be sent to the target program so that the target program delivers pop-up ads with the new target delivery strategy. That is, the target program no longer delivers pop-up ads with the previous target delivery strategy, but with the new target delivery strategy.

[0025] Furthermore, when the target program delivers pop-up ads with a new target delivery strategy, continue to execute steps S10 to S40, so as to continuously monitor the pop-up ads delivered in the target program, adjust the target delivery strategy for the pop-up ads in the target program in real time, and improve the operational effect of the pop-up ads delivery.

[0026] In this embodiment, by real-time monitoring of the user's first feedback action on the pop-up advertisement in the target program, and evaluating the user's interest level in the pop-up advertisement according to the delivery feedback value determined based on the collected first feedback action, the accuracy of the evaluation of the pop-up advertisement delivery effect is effectively improved. By evaluating the pop-up advertisement delivery effect through the delivery feedback value, the target delivery strategy for the pop-up advertisement in the target program is updated in a timely manner, making the target delivery strategy more in line with the user portrait of the delivered pop-up advertisement, avoiding that some pop-up advertisements continuously have low returns or even no returns, and also avoiding phenomena such as crashes of some high-return pop-up advertisements, improving the operation effect of pop-up advertisement delivery, the brand promotion intensity of the enterprise, and the profit conversion rate.

[0027] Exemplarily, in the intelligent medical scenario, pop-up advertisements related to prevention measures for recently highly prevalent diseases, in-hospital medical treatment processes, or medical security adjustments can be placed in medical-related official accounts, web pages, or application programs. Through the real-time update method of the pop-up advertisement delivery strategy proposed in this embodiment, the user's interest level in these delivered pop-up advertisements can be monitored, so as to dynamically adjust the quantity or frequency of pop-up advertisement delivery, making the pop-up advertisements more in line with the user interest portrait, and popularizing useful medical-related knowledge to a wider range of users.

[0028] Another example, in the financial scenario, pop-up advertisements related to financial enterprise information, financial product information (such as a certain type of insurance), etc. can be placed in official accounts, web pages, or application programs related to production lines and insurance. Through the real-time update method of the pop-up advertisement delivery strategy proposed in this embodiment, the user's interest level in these delivered pop-up advertisements can be monitored to dynamically adjust the quantity or frequency of pop-up advertisement delivery, making the pop-up advertisements more in line with the user interest portrait. Thus, users can quickly understand the latest information in the financial industry and have a more comprehensive understanding before purchasing a new insurance policy for an individual, avoiding purchasing the wrong insurance products and further avoiding the occurrence of financial fraud through the popularization of financial knowledge.

[0029] In one embodiment, in step S20, that is, based on the first feedback action corresponding to each pop-up advertisement, the delivery feedback value corresponding to the target program is updated in real time, including: Classify the first feedback action corresponding to each pop-up advertisement to determine the action feedback type corresponding to each first feedback action.

[0030] Understandably, as described above, the first feedback actions of the user for the pop-up advertisement may include that the first feedback action can be: the user clicks on the pop-up advertisement, the user closes the pop-up advertisement, or the user neither clicks on the pop-up advertisement nor closes the pop-up advertisement. The action feedback types can be divided into positive feedback types and negative feedback types. For example, when the user clicks on the pop-up advertisement and performs other actions on the page after the jump, a positive benefit is generated for this pop-up advertisement, and such actions are the first feedback actions of the positive feedback type. When the user immediately closes the pop-up advertisement after opening the target program, or the user neither clicks on the pop-up advertisement nor closes the pop-up advertisement, no benefit is generated for this pop-up advertisement, and such actions are the first feedback actions of the negative feedback type.

[0031] Real-time statistics are made on the total number of the first feedback actions belonging to the same action feedback type.

[0032] The delivery feedback value corresponding to the target program is updated in real time according to the total number.

[0033] Among them, as can be seen from the above description, the delivery feedback value in this embodiment can include two feedback values, one is the positive feedback value and the other is the negative feedback value. In this way, the positive feedback value and the negative feedback value can be updated in real time according to the total number of the first feedback actions belonging to the same action feedback type. Further, when the first feedback action corresponding to a pop-up advertisement is of the positive feedback type, the first feedback action of the pop-up advertisement is recorded as a positive feedback value. When the first feedback action corresponding to a pop-up advertisement is of the negative feedback type, the first feedback action of the pop-up advertisement is recorded as a negative feedback value. Thus, the positive feedback value is finally updated by accumulating the total number of pop-up advertisements whose first feedback actions are of the positive feedback type in real time, and the negative feedback value is updated by accumulating the total number of pop-up advertisements whose first feedback actions are of the negative feedback type in real time.

[0034] Further, as indicated in the above description: Due to the different numbers and frequencies of pop-up advertisement deliveries, and there are multiple users who open the target program. Therefore, even if a pop-up advertisement is clicked by one user and a positive feedback value is calculated, the pop-up advertisement still needs to calculate a positive feedback value when it is clicked by other users. That is, when monitoring the first feedback actions of users for the pop-up advertisements in the target program, the first feedback actions of different users for the pop-up advertisements are counted separately.

[0035] In one embodiment, classifying the first feedback actions corresponding to each pop-up advertisement and determining the action feedback type corresponding to each first feedback action includes: When the first feedback action represents that the user clicks on the pop-up advertisement, determine the action feedback type corresponding to the first feedback action based on the second feedback action of the user on the redirected page; the redirected page refers to the page displayed after the user clicks on the pop-up advertisement and is redirected.

[0036] Understandably, when the first feedback action represents that the user clicks on the pop-up advertisement, it may indicate that the user is interested in the content of the pop-up advertisement, or it may indicate that the user has accidentally clicked on the pop-up advertisement. Therefore, in order to improve the accuracy of classifying the first feedback action, it is necessary to determine the action feedback type of the first feedback action of the user clicking on the pop-up advertisement based on the second feedback action of the user on the redirected page. After the user clicks on the pop-up advertisement, the target program will be redirected to another page (i.e., the redirected page) of the pop-up advertisement link. For example, in the context of intelligent healthcare, assume that a pop-up advertisement popularizes the transmission, prevention, and medical treatment of influenza. When the user clicks on the pop-up advertisement, they will be redirected to a page that displays the popularization of influenza, and this display page is the redirected page.

[0037] Furthermore, when the second feedback action represents that the user's stay time on the redirected page exceeds a preset duration, or when the user clicks on the redirected page, determine that the action feedback type of the first feedback action corresponding to the second feedback action is a positive feedback type. Among them, the preset duration can be set according to user needs. Exemplarily, the preset duration can be set to 3s, 5s, or 10s, etc. Generally, when the user's stay time on the redirected page exceeds the preset duration, it indicates that the user is browsing the redirected page, thus generating a positive benefit for the content of the pop-up advertisement. Or there is a download link on the redirected page and the user clicks on this download link, which also generates a positive benefit for the content of the pop-up advertisement. In this way, the action feedback type of this type of first feedback action is determined to be a positive feedback type.

[0038] Furthermore, when the second feedback action represents that the user's stay time on the redirected page is less than the preset duration, or when the user closes the redirected page within the preset duration, determine that the action feedback type of the first feedback action corresponding to the second feedback action is a negative feedback type. Generally, when the user's stay time on the redirected page is less than the preset duration, or when the user closes the redirected page within the preset duration, it indicates that the user is not interested in the content of the pop-up advertisement. It may be that an accidental click has caused the redirection action from the pop-up advertisement to the redirected page. This type of first feedback action has not generated a positive benefit for the content of the pop-up advertisement, and the action feedback type of this type of first feedback action is determined to be a negative feedback type.

[0039] When the first feedback action represents that the user closes the pop-up advertisement, or when the first feedback action is a static action and the static time corresponding to the static action exceeds a preset static duration threshold, it is determined that the action feedback type corresponding to the first feedback action is a negative feedback type; the stay action represents that the user does not close the pop-up advertisement and does not click on the pop-up advertisement.

[0040] It can be understood that when the first feedback action represents that the user closes the pop-up advertisement, or when the first feedback action represents that the user neither closes the pop-up advertisement nor clicks on the pop-up advertisement within the preset static duration threshold, it indicates that the user is not interested in the content of the pop-up advertisement. Therefore, the action feedback type of this type of first feedback action is determined to be a negative feedback type. Among them, the preset static duration threshold can be set according to user needs. Exemplarily, the preset static duration threshold can be set to 10s, 15s, or 20s, etc.

[0041] In this embodiment, by classifying the first feedback actions of users for pop-up advertisements, the accuracy of updating the delivery feedback value can be improved, thereby improving the evaluation of the delivery effect of pop-up advertisements, so as to better adjust the delivery strategies of different pop-up advertisements and improve the operation effect of pop-up advertisement delivery.

[0042] In one embodiment, in step S30, that is, the determining the new target delivery strategy corresponding to the target program based on the delivery feedback value includes: Obtain the positive feedback value and the negative feedback value from the delivery feedback value.

[0043] It can be understood that in the above description, it is pointed out that the action feedback type of the first feedback action includes the positive feedback type and the negative feedback type. Therefore, the pop-up advertisement corresponding to the first feedback action belonging to the positive feedback type brings positive benefits, and thus the positive feedback value represents the number of first feedback actions whose action feedback type is the positive feedback type. On the contrary, the pop-up advertisement corresponding to the first feedback action belonging to the negative feedback type does not bring positive benefits, and thus the negative feedback value represents the number of pop-up advertisements corresponding to the first feedback actions whose action feedback type is the negative feedback type. Exemplarily, assume that within a certain period of time, there are 3 pop-up advertisements that are clicked 5 times by different users, and these 5 click actions are all regarded as the first feedback actions of the positive feedback type. At this time, the positive feedback value is 5, and the first feedback actions are sorted sequentially according to the time when the user clicks.

[0044] Obtain the positive risk threshold and the negative risk threshold.

[0045] Understandably, the positive risk threshold is used to evaluate whether the resources occupied by the pop-up ads with high user click-through rates in the target program exceed the available resources of the target program. For example, there are 4 pop-up ads with high user click-through rates in a target program, and several users click on these pop-up ads. At this time, the load of the server corresponding to the target program may not be able to bear the click volume of several users, resulting in a high load of the target program, which is likely to cause the target program to crash and cause losses. The negative risk threshold is used to evaluate whether the resources occupied by the pop-up ads with low user click-through rates in the target program cause resource waste. For example, there are 5 pop-up ads with low user click-through rates in a target program. These pop-up ads have not been clicked by users, but these pop-up ads still occupy the resources of the target program. To avoid resource waste, by introducing the negative risk threshold for evaluation, the delivery of pop-up ads with low user click-through rates can be reduced.

[0046] Based on the positive feedback value, the positive risk threshold, the negative feedback value, and the negative risk threshold, determine a new target delivery strategy corresponding to the target program.

[0047] Specifically, after obtaining the positive risk threshold and the negative risk threshold, the delivery effect of the target delivery strategy currently adopted by the target program can be evaluated based on the positive feedback value, the positive risk threshold, the negative feedback value, and the negative risk threshold in the delivery feedback value. Furthermore, the number, frequency, etc. of pop-up ad deliveries in the target delivery strategy can be adjusted to form a new target delivery strategy.

[0048] In one embodiment, the determining the new target delivery strategy corresponding to the target program based on the positive feedback value, the positive risk threshold, the negative feedback value, and the negative risk threshold includes: Obtain a preset warning value, and compare the positive feedback value with the preset warning value.

[0049] Understandably, the preset warning value can be set based on the positive risk threshold. For example, if the number of pop-up ads corresponding to the first feedback action of the positive feedback type that the positive risk threshold can bear is 10,000, then the preset warning value can be set to 1 / 10, 1 / 50, or 1 / 100 of the positive risk threshold.

[0050] When the positive feedback value is greater than or equal to the preset warning value, record the positive feedback value equal to the preset warning value as an outlier.

[0051] Specifically, since the positive feedback value continues to be updated over time. When comparing the positive feedback value with the preset warning value, it is necessary to calculate the same number of first feedback actions as the preset warning value starting from the first first feedback action recorded in the positive feedback value, record the total number of these first feedback actions as an outlier value, and exclude all the first feedback actions that have been recorded as outlier values from the positive feedback value. Exemplarily, assume that a total of 105 first feedback actions belonging to the positive feedback type are recorded in a target program (i.e., the positive feedback value is 105), and the preset warning value is 100. At this time, starting from the first first feedback action belonging to the positive feedback type recorded to the 100th first feedback action belonging to the positive feedback type, the total number (100) corresponding to these first feedback actions is recorded as an outlier value, and these 100 first feedback actions are excluded from the first feedback actions included in the positive feedback value. At this time, the positive feedback value is updated to 5. Updating the positive feedback value means excluding all the first feedback actions belonging to the positive feedback type that are recorded as outlier values from the first feedback actions belonging to the positive feedback type included in the positive feedback value.

[0052] Continue to compare the positive feedback value with the preset warning value and obtain a new outlier value.

[0053] Compare the total outlier value with the positive risk threshold to obtain an outlier comparison result; the total outlier value refers to the total number of all the outlier values.

[0054] Determine a new target delivery strategy corresponding to the target program according to the outlier comparison result.

[0055] It can be understood that after updating the positive feedback value, the total number of first feedback actions belonging to the positive feedback type included in the positive feedback value is less than the preset warning value. However, over time, the total number of first feedback actions belonging to the positive feedback type included in the positive feedback value is continuously increasing. Thus, whenever the positive feedback value is equal to the preset warning value, the preset warning value number of first feedback actions belonging to the positive feedback type with a higher ranking in the positive feedback value is recorded as a new outlier value, and the positive feedback value is continuously updated.

[0056] Furthermore, it is necessary to compare the total number of all anomalies (i.e., the total anomaly value) with the positive risk threshold in real time. If the obtained anomaly comparison result indicates that the total anomaly value is greater than or equal to the positive risk threshold, the load of the server corresponding to the target program may not be able to bear the click volume of several users at this time, resulting in a high load of the target program and easily leading to the crash of the target program. Therefore, it is necessary to adjust the target delivery strategy, reduce the number or frequency of pop-up ads with high click-through rates in the target program, and thus reduce the resources used by these pop-up ads with high click-through rates. If the obtained anomaly comparison result indicates that the total anomaly value is less than the positive risk threshold, it means that the available resources in the target program can still support the resource occupancy rate of each pop-up ad in the target program, and there is no need to adjust the target delivery strategy for the time being. At this time, the new target delivery strategy is still the target delivery strategy set at the beginning.

[0057] Determining the new target delivery strategy corresponding to the target program based on the positive feedback value, the positive risk threshold, the negative feedback value, and the negative risk threshold further includes: Compare the negative feedback value with the negative risk threshold.

[0058] When the negative feedback value is greater than or equal to the negative risk threshold, determine the preset negative feedback strategy as the new target delivery strategy.

[0059] Specifically, since the negative feedback value is continuously updated over time. When comparing the negative feedback value with the negative risk threshold, it is necessary to compare the number of all first feedback actions belonging to the negative feedback type recorded in the negative feedback value with the total number corresponding to the negative risk threshold. If the negative feedback value is greater than or equal to the negative risk threshold, it means that there are many pop-up ads that have not been clicked by users and have not brought positive benefits. These pop-up ads are likely to cause resource waste, so reduce the number and frequency of these pop-up ads in the target delivery strategy, or even prohibit the delivery of these pop-up ads. If the negative feedback value is less than the negative risk threshold, it means that there are few pop-up ads that have not been clicked by users and have not brought positive benefits. At this time, the new target strategy can maintain the initially set target strategy, or appropriately reduce the number or frequency of these pop-up ads.

[0060] Exemplarily, assume that a total of 13 first feedback actions belonging to the negative feedback type (i.e., the negative feedback value is 13) are recorded in a target program, and the negative risk threshold is 10. At this time, the negative feedback value exceeds the negative risk threshold, and thus the delivery frequency of the pop-up ads corresponding to the first feedback actions belonging to the negative feedback type recorded in the negative feedback value can be reduced, or the delivery quantity can be reduced.

[0061] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not imply the order of execution. The order of execution of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0062] In one embodiment, a real-time update device for a pop-up advertisement delivery strategy is provided. The real-time update device for a pop-up advertisement delivery strategy corresponds one-to-one to the real-time update method for a pop-up advertisement delivery strategy in the above embodiment. As Figure 3 shown, the real-time update device for a pop-up advertisement delivery strategy includes a feedback monitoring module 10, a feedback value update module 20, a delivery strategy determination module 30, and a delivery strategy update module 40. The detailed description of each functional module is as follows: The feedback monitoring module 10 is configured to, when a target program delivers a pop-up advertisement according to a target delivery strategy, monitor in real time a first feedback action of a user with respect to the pop-up advertisement in the target program; there are multiple pop-up advertisements in the target program; The feedback value update module 20 is configured to, based on the first feedback action corresponding to each pop-up advertisement, update in real time the delivery feedback value corresponding to the target program; The delivery strategy determination module 30 is configured to determine a new target delivery strategy corresponding to the target program based on the delivery feedback value; The delivery strategy update module 40 is configured to send the new target delivery strategy to the target program, so that the target program delivers a pop-up advertisement according to the new target delivery strategy.

[0063] Further, the feedback value update module 20 includes: An action classification sub-module, configured to classify the first feedback action corresponding to each pop-up advertisement, and determine the action feedback type corresponding to each first feedback action; An action statistics sub-module, configured to statistically count in real time the total number of first feedback actions belonging to the same action feedback type; A feedback value update sub-module, configured to update in real time the delivery feedback value corresponding to the target program according to the total number.

[0064] Further, the action classification sub-module includes: A first classification unit, configured to, when the first feedback action represents that the user clicks the pop-up advertisement, determine the action feedback type corresponding to the first feedback action based on a second feedback action of the user on the jump page; the jump page refers to the page displayed after the user clicks the pop-up advertisement and jumps; A second classification unit is configured to determine that the action feedback type corresponding to the first feedback action is a negative feedback type when the first feedback action indicates that the user closes the pop-up advertisement, or when the first feedback action is a static action and the static time corresponding to the static action exceeds a preset static duration threshold; the stay action indicates that the user does not close the pop-up advertisement and does not click on the pop-up advertisement.

[0065] Further, the first classification unit includes: A positive feedback classification subunit is configured to determine that the action feedback type of the first feedback action corresponding to the second feedback action is a positive feedback type when the second feedback action indicates that the user's stay time on the jump page exceeds a preset duration, or when the user clicks on the jump page; A negative feedback classification subunit is configured to determine that the action feedback type of the first feedback action corresponding to the second feedback action is a negative feedback type when the second feedback action indicates that the user's stay time on the jump page is less than a preset duration, or when the user closes the jump page within the preset duration.

[0066] Further, the delivery strategy determination module 30 includes: A feedback value acquisition sub-module is configured to acquire a positive feedback value and a negative feedback value from the delivery feedback value; A risk threshold acquisition sub-module is configured to acquire a positive risk threshold and a negative risk threshold; A delivery strategy determination sub-module is configured to determine a new target delivery strategy corresponding to the target program based on the positive feedback value, the positive risk threshold, the negative feedback value, and the negative risk threshold.

[0067] Further, the delivery strategy determination sub-module includes: A first feedback value comparison unit is configured to acquire a preset warning value and compare the positive feedback value with the preset warning value; A feedback value update unit is configured to record the positive feedback value equal to the preset warning value as an outlier when the positive feedback value is greater than or equal to the preset warning value, and update the positive feedback value; A second feedback value comparison unit is configured to continue comparing the positive feedback value with the preset warning value and acquire a new outlier; A positive risk value comparison unit is configured to compare the total number of outliers with the positive risk threshold to obtain an outlier comparison result; the total number of outliers refers to the total number of all the outliers; A first delivery strategy determination unit is configured to determine a new target delivery strategy corresponding to the target program according to the outlier comparison result.

[0068] Further, the delivery strategy determination sub-module includes: A negative risk value comparison unit for comparing the negative feedback value with the negative risk threshold; A second delivery strategy determination unit for determining a preset negative feedback strategy as a new target delivery strategy when the negative feedback value is greater than or equal to the negative risk threshold.

[0069] For the specific limitations of the pop-up window advertisement delivery strategy real-time update device, reference can be made to the limitations of the pop-up window advertisement delivery strategy real-time update method in the foregoing text, which will not be elaborated herein. Each module in the above pop-up window advertisement delivery strategy real-time update device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in or independent of a processor in a computer device in the form of hardware, or stored in a memory in the computer device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to the above modules.

[0070] In one embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 4 shown. The computer device includes a processor, a memory, a network interface, and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the data used in the pop-up window advertisement delivery strategy real-time update method in the above embodiment. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer program, when executed by the processor, implements a pop-up window advertisement delivery strategy real-time update method.

[0071] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the pop-up window advertisement delivery strategy real-time update method in the above embodiment is implemented.

[0072] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the pop-up window advertisement delivery strategy real-time update method in the above embodiment is implemented.

[0073] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0074] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0075] The above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments or equivalently replace some of the technical features. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention and should all be included in the protection scope of the present invention.

Claims

1. A method for real-time updating of pop-up advertisement delivery strategy, characterized in that: include: When a target program delivers a pop-up advertisement using a target delivery strategy, monitoring in real time a first feedback action of a user with respect to the pop-up advertisement in the target program; There are multiple pop-up ads in the target program; Based on the first feedback action corresponding to each pop-up advertisement, updating the delivery feedback value corresponding to the target program in real time; Determine a new target delivery strategy corresponding to the target program based on the delivery feedback value; The new target delivery strategy is sent to the target program, so that the target program delivers pop-up advertisements according to the new target delivery strategy.

2. The method for real-time updating of pop-up advertisement delivery strategy according to claim 1, characterized in that: The updating of the delivery feedback value corresponding to the target program in real time based on the first feedback action corresponding to each pop-up advertisement includes: Classifying the first feedback action corresponding to each of the pop-up advertisements, and determining an action feedback type corresponding to each of the first feedback actions; Real-time statistics of the total number of first feedback actions belonging to the same action feedback type; The delivery feedback value corresponding to the target program is updated in real time according to the total quantity.

3. The method for real-time updating of pop-up advertisement delivery strategy according to claim 1, characterized in that: The classifying the first feedback action corresponding to each pop-up advertisement to determine the action feedback type corresponding to each first feedback action includes: When the first feedback action represents that the user clicks on the pop-up advertisement, determining the action feedback type corresponding to the first feedback action based on the second feedback action of the user on the jump page; the jump page refers to the page displayed after the user clicks on the pop-up advertisement and jumps; When the first feedback action represents that the user closes the pop-up advertisement, or when the first feedback action is a static action and the static time corresponding to the static action exceeds a preset static time threshold, it is determined that the action feedback type corresponding to the first feedback action is a negative feedback type; the stay action represents that the user does not close the pop-up advertisement and does not click on the pop-up advertisement.

4. The method for real-time updating of pop-up advertisement delivery strategy according to claim 3, characterized in that: The determining, based on the second feedback action of the user on the redirected page, an action feedback type corresponding to the first feedback action includes: When the second feedback action indicates that the user stays on the jump page for more than a preset time, or the user clicks on the jump page, determining that the action feedback type of the first feedback action corresponding to the second feedback action is a positive feedback type; When the second feedback action indicates that the user stays on the jump page for less than a preset time period, or closes the jump page within the preset time period, it is determined that the action feedback type of the first feedback action corresponding to the second feedback action is a negative feedback type.

5. The method for real-time updating of pop-up advertisement delivery strategy according to claim 1, characterized in that: The determining a new target delivery strategy corresponding to the target program based on the delivery feedback value includes: Obtaining positive feedback values ​​and negative feedback values ​​from the delivery feedback values; Get positive risk threshold and negative risk threshold; Based on the positive feedback value, the positive risk threshold, the negative feedback value and the negative risk threshold, a new target delivery strategy corresponding to the target program is determined.

6. The method for real-time updating of pop-up advertisement delivery strategy according to claim 5, characterized in that: The determining of a new target delivery strategy corresponding to the target program based on the positive feedback value, the positive risk threshold, the negative feedback value and the negative risk threshold includes: Obtaining a preset warning value, and comparing the positive feedback value with the preset warning value; When the positive feedback value is greater than or equal to the preset warning value, the positive feedback value equal to the preset warning value is recorded as an abnormal value, and the positive feedback value is updated; Continue to compare the positive feedback value with the preset warning value, and obtain a new abnormal value; Compare the total abnormal value with the positive risk threshold to obtain an abnormal comparison result; the total abnormal value refers to the total number of all the abnormal values; According to the abnormal comparison result, a new target delivery strategy corresponding to the target program is determined.

7. The method for real-time updating of pop-up advertisement delivery strategy according to claim 5, characterized in that: The determining of a new target delivery strategy corresponding to the target program based on the positive feedback value, the positive risk threshold, the negative feedback value and the negative risk threshold includes: comparing the negative feedback value with the negative risk threshold; When the negative feedback value is greater than or equal to the negative risk threshold, the preset negative feedback strategy is determined as a new target delivery strategy.

8. A device for real-time updating of pop-up advertisement delivery strategy, characterized in that: include: A feedback monitoring module, used for real-time monitoring of a user's first feedback action on a pop-up advertisement in a target program when the target program delivers a pop-up advertisement with a target delivery strategy; there are a plurality of pop-up advertisements in the target program; A feedback value updating module, used for updating the delivery feedback value corresponding to the target program in real time based on the first feedback action corresponding to each pop-up advertisement; A delivery strategy determination module, used to determine a new target delivery strategy corresponding to the target program based on the delivery feedback value; The delivery strategy update module is used to send the new target delivery strategy to the target program, so that the target program can deliver pop-up advertisements according to the new target delivery strategy.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for real-time updating of pop-up advertisement delivery strategy as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, the method for real-time updating of pop-up advertisement delivery strategy as claimed in any one of claims 1 to 7 is implemented.

Images