Advertising evaluation method, device, and computer-readable storage medium

Abstract

The present application provides a method, device and computer-readable storage medium for evaluating advertisements, including: obtaining advertisements in a preset set and at least one advertisement placement metric; every preset time period, for the advertisement placement metric, counting the metric quantity of the advertisements in the preset set; according to a plurality of attention intervals divided by the numerical range of the metric quantity, and the metric quantity of the advertisement, determining the attention interval in which the advertisement in the preset set is located for the advertisement placement metric. The present application enables different attention intervals to be used to characterize a corresponding advertisement placement effect under the advertisement placement metric, so that the attention interval in which the advertisement in the set is located under the advertisement placement metric can be used as the placement performance of the advertisement under the advertisement placement metric, achieving the purpose of quickly positioning the placement effect of the advertisement under the advertisement placement metric, and having a good advertisement evaluation effect.

Description

Technical Field

[0001] This application belongs to the field of computer technology, and particularly relates to a method and device for evaluating advertisements and a computer-readable storage medium. Background Art

[0002] With the continuous maturity of information sharing technology, advertising placement has become an important part of information sharing.

[0003] In related technologies, the exposure of an advertisement during placement is related to the competitive ranking of the advertisement. During the bidding process, an advertisement with a higher ranking position receives more exposure, while an advertisement with a lower ranking position receives relatively less exposure.

[0004] However, in the current solution, users can only analyze the advertisement placement process through the competitive ranking of advertisements. Due to the relatively high understanding cost of competitive ranking, the analysis effect is poor. Summary of the Invention

[0005] In view of this, this application provides a method and device for evaluating advertisements and a computer-readable storage medium, which to a certain extent solve the problem that in the current solution, users can only analyze the advertisement placement process through the competitive ranking of advertisements, resulting in a poor analysis effect.

[0006] According to the first aspect of this application, a method for evaluating an advertisement is provided. The method includes:

[0007] Obtain advertisements in a preset set and at least one advertisement placement metric;

[0008] At each preset time period, for the advertisement placement metric, count the metric quantity of the advertisements in the preset set;

[0009] According to a plurality of attention intervals divided by the numerical range of the metric quantity and the metric quantity of the advertisement, determine the attention interval in which the advertisement in the preset set is located for the advertisement placement metric.

[0010] According to the second aspect of this application, an advertisement evaluation device is provided. The device includes:

[0011] An obtaining module, configured to obtain advertisements in a preset set and at least one advertisement placement metric;

[0012] A statistics module, configured to count the metric quantity of the advertisements in the preset set for the advertisement placement metric at each preset time period;

[0013] A partitioning module, configured to determine, according to a plurality of concerned intervals divided based on the numerical range of the metric quantity of the advertisement, and the metric quantity of the advertisement, the concerned interval to which the advertisement in the preset set belongs with respect to the advertisement placement metric.

[0014] According to a third aspect of the present application, an embodiment of the present application provides a computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the advertisement evaluation method described in the first aspect are implemented.

[0015] Regarding the related art, the present application has the following advantages:

[0016] An advertisement evaluation method provided by the present application divides a plurality of concerned intervals based on the numerical range of the metric quantity of the advertisement statistically obtained according to the advertisement placement metric, so that different concerned intervals can be used to represent a corresponding advertisement placement effect under the advertisement placement metric. Thus, the concerned interval to which the advertisement in the set belongs under the advertisement placement metric can be used as the placement performance of the advertisement under the advertisement placement metric, achieving the purpose of quickly positioning the advertisement placement effect under the advertisement placement metric, and having a good advertisement evaluation effect.

[0017] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the description. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the specific embodiments of the present application are hereinafter specifically described. Description of the Drawings

[0018] By reading the detailed description of the preferred embodiments below, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present application. And throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0019] Figure 1 is a flowchart of the steps of an advertisement evaluation method provided by an embodiment of the present application;

[0020] Figure 2 is a specific flowchart of the steps of an advertisement evaluation method provided by an embodiment of the present application;

[0021] Figure 3 is a schematic diagram of the advertisement evaluation results of the same advertising industry provided by an embodiment of the present application;

[0022] Figure 4 is a schematic diagram of the advertisement evaluation results of the same advertising position provided by an embodiment of the present application;

[0023] Figure 5It is a specific step flowchart of another advertisement evaluation method provided by an embodiment of the present application;

[0024] Figure 6 It is a block diagram of an advertisement evaluation device provided by an embodiment of the present application. Detailed implementation manners

[0025] Hereinafter, exemplary embodiments of the present application will be described in more detail with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present application can be more thoroughly understood and the scope of the present application can be fully conveyed to those skilled in the art.

[0026] Figure 1 It is a step flowchart of an advertisement evaluation method provided by an embodiment of the present application. As Figure 1 shown, the method may include:

[0027] Step 101, obtain advertisements in a preset set and at least one advertisement placement metric.

[0028] In an embodiment of the present application, the advertisement evaluation method can be applied to a server, which can be a server corresponding to an advertisement publisher, used to collect evaluation results of the placement effects of advertisements in a preset set and feedback the evaluation results to the target advertisement applying for evaluation. The specific form of the server can be a physical server, a cloud server, etc.

[0029] Among them, the preset set can be a set storing advertisements, such as a set storing all advertisements placed within a preset time range. In addition, the preset set can be further divided according to a finer classification granularity. For example, the preset set can be divided into different advertisement position sets according to different advertisement positions, so that the advertisements placed in one advertisement position are constructed into an advertisement position set; the preset set can also be divided into different industry sets according to different advertisement industries, so that the advertisements belonging to the advertisement industry are constructed into an industry set.

[0030] In this step, while obtaining the advertisements in the preset set, in order to provide a multi-granularity and comprehensive analysis of the advertisement placement process, at least one advertisement placement metric can also be obtained. The advertisement placement metric is a parameter used to measure the advertisement placement effect. Since the advertisement placement effect can be analyzed from multiple dimensions, there can be multiple advertisement placement metrics, and each advertisement placement metric is used to reflect the advertisement placement effect under one analysis dimension.

[0031] Optionally, the advertisement placement metrics include one or more of: revenue per mille, estimated click-through rate, estimated conversion rate.

[0032] In the embodiments of the present application, the advertisement delivery metrics include, but are not limited to, the predicted click-through rate (PCTR) of the advertisement, the predicted conversion rate (PCVR), the earnings per thousand impressions (ECPM); the predicted click-through rate of the advertisement = the predicted number of clicks of the advertisement / the predicted number of impressions of the advertisement, and the predicted click-through rate of the advertisement is related to the shooting quality of the advertisement. The better the content material of the advertisement, the higher the predicted click-through rate of the advertisement; the predicted conversion rate of the advertisement = the predicted number of conversions of the advertisement / the predicted number of clicks of the advertisement, and the predicted conversion rate of the advertisement is related to the comprehensive quality of the product in the advertisement. The better the product recommended by the advertisement, the higher the predicted conversion rate of the advertisement.

[0033] Furthermore, the earnings per thousand impressions of the advertisement is used to measure the core delivery effect of the advertisement. The earnings per thousand impressions of the advertisement = advertisement bid × PCTR × PCVR × 1000; for advertisers, it can reflect the delivery cost of the advertisement, and for users, it can reflect the earnings brought by the delivery of the advertisement.

[0034] Step 102: At each preset time period, for the advertisement delivery metrics, count the metric quantities of the advertisements in the preset set.

[0035] In the embodiments of the present application, the performance of the advertisement under the advertisement delivery metrics can be specifically expressed by collecting the metric quantities of the advertisement under the advertisement delivery metrics. In the embodiments of the present application, at each preset time period, for the advertisement delivery metrics, count the metric quantities of the advertisements in the preset set, where the time units of the preset time period include, but are not limited to, seconds, minutes, hours, days, months, quarters, years, etc.

[0036] For example, assuming that the advertisement delivery metrics of predicted click-through rate and predicted conversion rate are set; and the time unit of the preset time period is hours, then the metric quantities of the predicted click-through rate and predicted conversion rate of the advertisements in the preset set can be counted every hour, and finally the corresponding relationship between the time unit and the metric quantities of the predicted click-through rate and predicted conversion rate of the advertisement can be obtained.

[0037] Step 103: According to the multiple attention intervals divided by the numerical ranges of the metric quantities, and the metric quantities of the advertisement, determine the attention interval where the advertisement in the preset set is located for the advertisement delivery metric.

[0038] In the embodiments of the present application, since there is a certain number of advertisements in the preset set, the metric values statistically obtained for each advertisement fall within a numerical range. From the analysis requirements of the user on the advertising delivery effect, it can be known that: users usually do not pay attention to the ranking of the metric value of their advertisement under a certain advertising delivery metric, but are more concerned about the metric value of their advertisement and the ranking interval in which it is located within the numerical range formed by the metric values of all advertisements under this advertising delivery metric. Therefore, based on this requirement, the embodiments of the present application can determine multiple attention intervals divided by the numerical range of the metric value, and then determine the attention interval in which the advertisement in the preset set is located. One attention interval is used to represent a specific performance effect of the advertising delivery metric.

[0039] In addition, if the method of calculating the full - volume data ranking is used to determine the specific ranking order of each advertisement, so as to output the data performance of the advertisement under the advertising delivery metric, since this process has high requirements for data timeliness and a huge amount of computation, it will require a large amount of computing resources, resulting in a high computing cost. However, the embodiments of the present application can divide the numerical range of the metric value into multiple attention intervals and only obtain the attention interval in which the advertisement is located, which can greatly reduce the computing cost brought by calculating the full - volume data ranking, saving computing resources.

[0040] For example, for the 10 advertisements included in the preset set: Advertisement 1 to Advertisement 10; the corresponding metric values statistically obtained under the advertising delivery metric of estimated conversion rate are: 10, 20, 30, 40, 50, 60, 70, 80, 90, 100; the larger the metric value, the better the performance of the advertisement under the advertising delivery metric of estimated conversion rate. Therefore, the numerical range of the metric value is 100 - 10. Suppose the numerical range of the metric value is divided into 5 attention intervals: Attention interval 1 is the top 20%; Attention interval 2 is the top 20% - 40%; Attention interval 3 is the top 40% - 60%; Attention interval 4 is the top 60% - 80%; Attention interval 5 is the bottom 20%; Attention interval 1 is the interval of the advertisement with the best performance under the advertising delivery metric of estimated conversion rate, Attention interval 2 is the second best, and Attention interval 5 is the interval of the advertisement with the worst performance.

[0041] Based on the above division of the attention intervals, it is possible to further determine the attention intervals 1 in which the metric quantities of advertisement 9 and advertisement 10 are located, such that advertisement 9 and advertisement 10 can be determined as the advertisements with the best performance under the estimated conversion rate of the advertisement placement metrics; at the same time, it is also possible to determine the attention intervals 2 in which the metric quantities of advertisement 7 and advertisement 8 are located, and the performance of advertisement 7 and advertisement 8 is worse than that of advertisement 9 and advertisement 10; at the same time, it is also possible to determine the attention intervals 3 in which the metric quantities of advertisement 5 and advertisement 6 are located, and the performance of advertisement 5 and advertisement 6 is worse than that of advertisement 7, 8 and advertisement 10; at the same time, it is also possible to determine the attention intervals 4 in which the metric quantities of advertisement 3 and advertisement 4 are located, and the performance of advertisement 3 and advertisement 4 is worse than that of advertisement 5 and advertisement 6; at the same time, it is also possible to determine the attention intervals 5 in which the metric quantities of advertisement 1 and advertisement 2 are located, and advertisement 1 and advertisement 2 have the worst performance.

[0042] Furthermore, in the embodiment of the present application, after dividing the numerical range of the metric quantity into multiple attention intervals and determining the attention intervals in which the advertisements in the preset set are located according to the metric quantities of the advertisements, the attention intervals divided for the numerical range of the metric quantity and the attention intervals in which the advertisements in the preset set are located can be stored locally. When the subsequent user requests to feedback the evaluation result of the target advertisement, the attention interval in which the target advertisement is located can be directly extracted from the local area and fed back to the user, which greatly improves the response speed.

[0043] It should be noted that, due to the timeliness requirement of the advertisement placement metrics of the advertisement, the embodiment of the present application can also set a scheduled task to periodically clean the information of the attention intervals in which the advertisements with earlier local statistical times are located. Specifically, after setting the scheduled task, the embodiment of the present application can, in response to the scheduled task, automatically delete the stored data locally that is older than the specified time (such as 48 hours), thereby further optimizing the storage space.

[0044] After determining the attention interval in which the advertisement is located for the advertisement placement metrics, the attention interval in which the advertisement is located can be used as one of the parameters for the server to manage the advertisement. That is, for different attention intervals in which the advertisement is located, processing such as recommendation, classification, and filtering can be implemented for the advertisement. For example, if the attention interval in which the advertisement is located under the attention metric is an interval with a larger attention degree, the advertisement can be preferentially recommended to other users and classified into the "excellent" category; if the attention interval in which the advertisement is located for the advertisement placement metrics is an interval with a smaller attention degree, the advertisement can be filtered and classified into the "poor" category.

[0045] In addition, the server side of the embodiment of the present application can use the attention interval where the target advertisement is located as the advertisement delivery effect of the target advertisement within a preset time range for the advertisement delivery index, and add it to the response to the evaluation request and return it to the user client. The user client can quickly locate the advertisement delivery effect of the target advertisement under the advertisement delivery index based on the attention interval where the target advertisement is located, so that the user can quickly find the reason why the target advertisement performs well or the reason for its poor performance.

[0046] In summary, in the advertisement evaluation method provided by the embodiment of the present application, the present application can divide a plurality of attention intervals based on the numerical range of the index quantity of the advertisement statistically calculated for the advertisement delivery index, so that different attention intervals can be used to represent a corresponding advertisement delivery effect under the advertisement delivery index. Therefore, the attention interval where the advertisement in the set is located under the advertisement delivery index can be used as the advertisement delivery performance of the advertisement under the advertisement delivery index, achieving the purpose of quickly locating the advertisement delivery effect of the advertisement under the advertisement delivery index, and having a good advertisement evaluation effect.

[0047] Figure 2 is a specific step flowchart of an advertisement evaluation method provided by an embodiment of the present application, as Figure 2 shown, the method may include:

[0048] Step 201, obtain advertisements in a preset set and at least one advertisement delivery index.

[0049] In the embodiment of the present application, step 201 may specifically refer to the relevant description of step 101, which will not be elaborated here.

[0050] Step 202, at each preset time period, statistically calculate the index quantity of the advertisements in the preset set for the advertisement delivery index.

[0051] In the embodiment of the present application, step 202 may specifically refer to the relevant description of step 102, which will not be elaborated here.

[0052] Optionally, the preset set includes: a first set and a second set, the advertisements in the first set are in the same advertisement industry, and the advertisements in the second set are in the same advertisement position; the method further includes:

[0053] Step 203, determine the first attention interval where the advertisements in the first set are located for the advertisement delivery index according to the multiple first attention intervals divided according to the numerical range of the index quantity statistically calculated for the first set and the index quantity of the advertisements in the first set.

[0054] In an embodiment of the present application, the preset set can be further divided into a first set and a second set according to the granularity of the advertising industry and the advertising position, wherein the advertisements in the first set are in the same advertising industry, so as to facilitate subsequent feedback to users on the delivery performance of the target advertisement compared with other advertisements in the same advertising industry.

[0055] For example, assuming that there is a first set 1 for the sports advertising industry and a first set 2 for the beauty advertising industry; then the embodiment of the present application can count the statistical indicators of all advertisements in the first set 1 for the advertising delivery indicators. If the statistical indicator value range is ab, multiple first focus areas 1 can be divided within the range of ab, and the first focus area 1 where the advertisements in the first set 1 are located can be determined; the embodiment of the present application can also count the statistical indicators of all advertisements in the first set 2 for the advertising delivery indicators. If the statistical indicator value range is cd, multiple first focus areas 2 can be divided within the range of cd, and the first focus area 1 where the advertisements in the first set 2 are located can be determined.

[0056] Step 204: determine the second attention interval in which the advertisements in the second set are located for the advertising delivery indicator according to the plurality of second attention intervals divided according to numerical ranges of the indicator quantities of the second set statistics and the indicator quantities of the advertisements in the second set.

[0057] In an embodiment of the present application, the advertisements in the second set are in the same advertisement slot, where the advertisement slot is a window for placing advertisements. For example, the welcome homepage when a mobile application is started can be an advertisement slot, in which various advertisements can be placed; the electronic screen in a public transportation vehicle can also be an advertisement slot for placing advertisements for rotation. In an embodiment of the present application, the preset set is divided into the second set based on the granularity of the same advertisement slot, so as to facilitate subsequent feedback to the user on the delivery performance of the target advertisement compared with other advertisements in the same advertisement slot.

[0058] For example, assuming that there is a second set 1 of advertising spaces on the welcome homepage of the application and a second set 2 of advertising spaces on the electronic screen of the bus stop; then the embodiment of the present application can count the statistical indicators of all advertisements in the second set 1 for the advertising delivery index. If the numerical range of the statistical indicators is ef, multiple second areas of interest 1 can be divided within the range of ef, and the second areas of interest 1 where the advertisements in the second set 1 are located can be determined; the embodiment of the present application can also count the statistical indicators of all advertisements in the second set 2 for the advertising delivery index. If the numerical range of the statistical indicators is gh, multiple areas of interest 2 can be divided within the range of gh, and the second areas of interest 1 where the advertisements in the second set 2 are located can be determined.

[0059] Further, in the embodiments of the present application, when a user (such as a merchant) has a need to evaluate the delivery effect of the target advertisement for their own product, the user client can send an evaluation request for the target advertisement. After receiving the evaluation request, the server in the embodiments of the present application can, based on the attention interval where the advertisement in the preset set obtained in step 103 is located, use the attention interval where the target advertisement is located within the preset time range (such as within 48 hours, within 3 hours, etc.) as the delivery effect of the target advertisement within the preset time range for the advertisement delivery metrics, and add it to the response to the evaluation request and return it to the user client. The user client can quickly locate the delivery effect of the target advertisement under the advertisement delivery metrics based on the attention interval where the target advertisement is located, enabling the user to quickly find the reasons for the good or poor performance of the target advertisement.

[0060] For example, for the 5 attention intervals provided in the example of step 103: attention interval 1 is the top 20%; attention interval 2 is from the top 20% - 40%; attention interval 3 is from the top 40% - 60%; attention interval 4 is from the top 60% - 80%; attention interval 5 is the bottom 20%. Attention interval 1 is the interval of the advertisement with the best performance under the estimated conversion rate of the advertisement delivery metrics, followed by attention interval 2, and attention interval 5 is the interval of the advertisement with the worst performance.

[0061] If the target advertisement of the user is in attention interval 1 at time A, it can be considered that at time A, the delivery performance of the target advertisement under the estimated conversion rate of the advertisement delivery metrics is excellent. Since the estimated conversion rate characterizes the comprehensive quality of the product in the advertisement, the advertisement user can quickly locate that the reason for the excellent performance of the target advertisement at time A is that the product is more popular.

[0062] If the target advertisement of the user is in attention interval 5 at time B, it can be considered that at time B, the delivery performance of the target advertisement under the estimated conversion rate of the advertisement delivery metrics is poor. The advertisement user can quickly locate that the reason for the poor performance of the target advertisement at time B is that the product is not popular, and the user can further improve the quality of their own product to achieve the purpose of discovering and solving problems.

[0063] Optionally, the method further includes:

[0064] Step 205: When receiving an evaluation request for the target advertisement, determine the target advertisement industry and target advertisement position where the target advertisement is located.

[0065] In the embodiments of the present application, when the user client requests an evaluation of the target advertisement, the server can obtain the description information of the target advertisement, and then determine the target advertisement industry and target advertisement position where the target advertisement is located.

[0066] Step 206, determine a target first set that matches the target advertising industry and a target second set that matches the target advertising space.

[0067] Step 207, for the advertising placement metrics, add the first attention interval in which the target advertisement is located in the target first set within the preset time range to the response to the evaluation request.

[0068] Step 208, for the advertising placement metrics, add the second attention interval in which the target advertisement is located in the target second set within the preset time range to the response to the evaluation request.

[0069] In the embodiments of the present application, since the server locally caches the first attention areas where the advertisements in the first set corresponding to each advertising industry are located, and caches the second attention areas where the advertisements in the second set corresponding to each advertising space are located, therefore, based on the target advertising industry and target advertising space to which the target advertisement to be evaluated belongs, the server can respectively determine a target first set that matches the target advertising industry and a target second set that matches the target advertising space in the server's local cache, and determine the advertisements in the target first set as advertisements belonging to the same advertising industry as the target advertisement, and determine the advertisements in the target second set as advertisements belonging to the same advertising space as the target advertisement.

[0070] Further, when feedbacking the evaluation result of the target advertisement, for the advertising placement metrics, the first attention interval in which the target advertisement is located in the target first set within the preset time range and the second attention interval in which the target advertisement is located in the target second set can be added to the response to the evaluation request, so that the user client can quickly and accurately locate the placement effect performance of the target advertisement based on the granularity of each advertising placement metric in the advertising industry to which it belongs, and locate the placement effect performance of the target advertisement based on the granularity of each advertising placement metric in the advertising space to which it belongs.

[0071] The embodiments of the present application provide a specific example of the evaluation result for the target advertisement:

[0072] Suppose the target advertisement requested by the user for evaluation belongs to the sports advertising industry and the bus stop electronic screen advertising space. The statistically preset time period is 12 hours. The advertising placement metrics are the estimated click-through rate and the estimated conversion rate, and the numerical ranges of the metric values of the estimated click-through rate and the estimated conversion rate are divided into 5 attention intervals. Attention interval 1 is the top 20%, corresponding to very strong performance; attention interval 2 is 20%-40%, corresponding to relatively strong performance; attention interval 3 is 40%-60%, corresponding to average performance; attention interval 4 is 60%-80%, corresponding to relatively weak performance; attention interval 5 is the bottom 20%, corresponding to very weak performance.

[0073] Reference Figure 3 , which shows a schematic diagram of the advertising evaluation results of the same advertising industry provided by the embodiments of the present application. Figure 3 It expresses the advertising performance of the target advertisement within 48 hours in the sports advertising industry. It can be seen that the estimated click-through rate of the target advertisement within 48 hours in the sports advertising industry is relatively good, but the estimated conversion rate is relatively poor. This reflects that in the sports advertising industry, the advertising quality of the target advertisement is relatively good, but the popularity of the sports products in the advertisement is relatively low. Users can Figure 3 , and focus on improving the popularity of the sports products in the advertisement in the follow-up to improve the performance of the estimated conversion rate of the target advertisement in the sports advertising industry.

[0074] Reference Figure 4 , which shows a schematic diagram of the advertising evaluation results of the same advertising space provided by the embodiments of the present application. Figure 4 It expresses the advertising performance of the target advertisement within 48 hours in the bus stop electronic screen advertising space. It can be seen that the estimated click-through rate of the target advertisement within 48 hours in the bus stop electronic screen advertising space is relatively poor, but the estimated conversion rate is relatively good. This reflects that in the bus stop electronic screen advertising space, the popularity of the sports products in the target advertisement is relatively high, but the advertising quality is relatively poor. Users can Figure 4 , and focus on improving the content quality of the advertisement in the follow-up to improve the performance of the estimated click-through rate of the target advertisement in the bus stop electronic screen advertising space.

[0075] In summary, in the advertising evaluation method provided by the embodiments of the present application, the present application can divide multiple attention intervals based on the numerical range of the index quantity of the advertisement statistically counted by the advertising placement index, so that different attention intervals can be used to characterize a corresponding advertising placement effect under the advertising placement index. Thus, the attention interval where the advertisement in the set is located under the advertising placement index can be used as the advertising placement performance under the advertising placement index, achieving the purpose of quickly positioning the advertising placement effect under the advertising placement index and having a good advertising evaluation effect.

[0076] Figure 5 is a specific step flowchart of another advertising evaluation method provided by the embodiments of the present application. As Figure 5 shown, this method may include:

[0077] Step 301, obtain the advertisements in the preset set and at least one advertising placement index.

[0078] In the embodiments of the present application, step 301 may specifically refer to the relevant description of step 101, which will not be elaborated here.

[0079] Step 302: At every preset time period, count the metric quantity of the advertisements in the preset set for the advertisement delivery metrics.

[0080] In the embodiment of the present application, Step 302 can specifically refer to the relevant description of Step 101, which will not be elaborated here.

[0081] Step 303: Obtain the total number of advertisements in the preset set, and the number of advertisements in the preset set whose metric quantity is less than that of the advertisement.

[0082] Step 304: Determine the attention interval where the advertisement is located according to multiple attention intervals divided by the numerical range of the metric quantity, and the ratio of the number of advertisements whose metric quantity is less than that of the advertisement to the total number of advertisements.

[0083] In the embodiment of the present application, after dividing the numerical range of the metric quantity into multiple attention intervals, when determining the attention interval where the advertisement in the preset set is located according to the metric quantity of the advertisement, it can specifically calculate the attention interval where the advertisement in the preset set is located according to the calculation method of the cumulative distribution. The calculation method of the cumulative distribution mainly determines the attention interval where the advertisement is located by counting the total number of advertisements in the preset set and the number of advertisements in the preset set whose metric quantity is less than that of the advertisement, and according to the ratio of the number of advertisements whose metric quantity is less than that of the advertisement to the total number of advertisements. This calculation method does not require statistical ranking of the full quantity of advertisements in the preset set, effectively solving the problem of increased calculation volume brought by full quantity ranking.

[0084] It should be noted that when the preset set includes a first set and a second set, when determining the attention interval of the advertisement in the first set, the number of advertisements whose metric quantity is less than that of the advertisement is the number of advertisements in the first set whose metric quantity is less than that of the advertisement, and the total number of advertisements counted is the total number of advertisements in the first set. The same applies to the second set.

[0085] Optionally, one attention interval corresponds to a ranking percentage range; Step 304 can be specifically implemented by determining the attention interval corresponding to the ranking percentage range where the ratio is located as the attention interval where the advertisement is located.

[0086] In the embodiment of the present application, one attention interval corresponds to a ranking percentage range. In the embodiment of the present application, the ranking percentage range where the ratio of the number of advertisements whose metric quantity is less than that of the advertisement to the total number of advertisements is located can be specifically determined as the attention interval where the advertisement is located.

[0087] For example, assume that the numerical range of the metric quantity is divided into 5 focus intervals. Focus interval 1 is the top 20%; focus interval 2 is from the top 20% to 40%; focus interval 3 is from the top 40% to 60%; focus interval 4 is from the top 60% to 80%; focus interval 5 is the bottom 20%.

[0088] Assume that the preset set has 100 advertisements. For the target advertisement, the number of advertisements in the preset set with a metric quantity smaller than it is 45. Then the ratio of the number of advertisements with a metric quantity smaller than the advertisement to the total number of advertisements = 45 / 100 = 45%. Since 45% is in focus interval 3, focus interval 3 is the focus interval where the target advertisement is located.

[0089] Optionally, different focus intervals are set with different focus labels. The determination of the focus interval where the advertisement in the preset set is located for the advertisement placement metric can be specifically achieved by determining the focus interval where the advertisement is located within the preset time range and the corresponding focus label.

[0090] In one implementation manner of the embodiment of the present application, the focus label is used to specifically describe the performance degree of the corresponding focus interval in terms of placement effect, thereby effectively reducing the understanding cost of the advertisement evaluation result. Referring to Figure 3 and Figure 4 , assume that the 5 divided focus intervals include: focus interval 1 is 0 - a, and the corresponding focus label is very strong; focus interval 2 is a - b, and the corresponding focus label is relatively strong; focus interval 3 is b - c, and the corresponding focus label is average; focus interval 4 is c - d, and the corresponding focus label is relatively weak; focus interval 5 is d - e, and the corresponding focus label is very weak.

[0091] By setting corresponding focus labels for each focus area, it is possible to enable users to more intuitively understand the specific performance effect of advertisement placement, improve the intuitiveness of the advertisement evaluation result, and reduce the understanding cost of the advertisement evaluation result.

[0092] Optionally, the method may further include:

[0093] Step 305: Sort the advertisements in the focus interval where the advertisement is located according to the metric quantity within the preset time range to obtain a sorting result.

[0094] In another implementation manner of the embodiment of the present application, in the embodiment of the present application, it is also possible to sort the advertisements in the focus interval where the advertisement is located according to the metric quantity within the preset time range to obtain a sorting result. By feeding back the sorting result to the user, the user can intuitively see the ranking of the target advertisement through the sorting result. In addition, the sorting result can also be used as one of the parameters for the server to manage advertisements.

[0095] In summary, in the advertisement evaluation method provided by the embodiments of the present application, the present application can divide a plurality of attention intervals based on the numerical range of the index quantity of the advertisement statistically counted by the advertisement placement index, so that different attention intervals can be used to represent a corresponding advertisement placement effect under the advertisement placement index. Therefore, the attention interval in which the advertisement in the set is located under the advertisement placement index can be used as the placement performance of the advertisement under the advertisement placement index, achieving the purpose of quickly positioning the placement effect of the advertisement under the advertisement placement index and having a good advertisement evaluation effect.

[0096] Figure 6 It is a block diagram of an advertisement evaluation device provided by an embodiment of the present application. As Figure 6 shown, the device may include:

[0097] An acquisition module 401, configured to acquire advertisements in a preset set and at least one advertisement placement index;

[0098] A statistics module 402, configured to statistically count the index quantity of the advertisements in the preset set for the advertisement placement index every preset time period;

[0099] A division module 403, configured to determine the attention interval in which the advertisements in the preset set are located for the advertisement placement index according to a plurality of attention intervals divided based on the numerical range of the index quantity and the index quantity of the advertisement;

[0100] Optionally, the preset set includes: a first set and a second set. The advertisements in the first set are in the same advertisement industry, and the advertisements in the second set are in the same advertisement position;

[0101] The division module 403 includes:

[0102] A first sub-division module, configured to determine the first attention interval in which the advertisements in the first set are located for the advertisement placement index according to a plurality of first attention intervals divided based on the index quantity statistically counted by the first set and the index quantity of the advertisements in the first set;

[0103] A second sub-division module, configured to determine the second attention interval in which the advertisements in the second set are located for the advertisement placement index according to a plurality of second attention intervals divided based on the index quantity statistically counted by the second set and the index quantity of the advertisements in the second set.

[0104] Optionally, the device further includes:

[0105] A first determination module, configured to determine the target advertisement industry and target advertisement position in which the target advertisement is located when receiving an evaluation request for the target advertisement;

[0106] A second determination module, configured to determine a target first set matching the target advertising industry and a target second set matching the target ad slot;

[0107] A first addition module, configured to, for the ad placement metric, add a first attention interval in which the target ad is located in the target first set within the preset time range to a response to the evaluation request;

[0108] A second addition module, configured to, for the ad placement metric, add a second attention interval in which the target ad is located in the target second set within the preset time range to a response to the evaluation request.

[0109] Optionally, the partitioning module 403 includes:

[0110] An acquisition sub-module, configured to acquire the total number of ads in the preset set and the number of ads in the preset set whose metric quantity is less than that of the ad;

[0111] A ratio sub-module, configured to determine the attention interval in which the ad is located according to the ratio of the number of ads in the preset set whose metric quantity is less than that of the ad to the total number of ads.

[0112] Optionally, one attention interval corresponds to a ranking percentage range; the ratio sub-module includes:

[0113] A determination unit, configured to determine the attention interval corresponding to the ranking percentage range in which the ratio is located as the attention interval in which the ad is located.

[0114] Optionally, different attention intervals are set with different attention labels, and the partitioning module 403 includes:

[0115] A third addition sub-module, configured to determine the attention interval in which the ad is located within the preset time range and the corresponding attention label.

[0116] Optionally, the apparatus further includes:

[0117] A sorting module, configured to sort the ads in the attention interval in which the ad is located according to the metric quantity within the preset time range to obtain a sorting result.

[0118] Optionally, the ad placement metric includes one or more of revenue per thousand impressions, estimated click-through rate, and estimated conversion rate.

[0119] In summary, the advertisement evaluation device provided by the embodiments of the present application can divide multiple attention intervals based on the numerical range of the advertisement index quantity statistically calculated by the advertisement placement index, so that different attention intervals can be used to represent a corresponding advertisement placement effect under the advertisement placement index. Therefore, the attention interval in which the advertisement in the set is located under the advertisement placement index can be used as the placement performance of the advertisement under the advertisement placement index, achieving the purpose of quickly positioning the placement effect of the advertisement under the advertisement placement index and having a good advertisement evaluation effect.

[0120] For the above device embodiments, since they are basically similar to the method embodiments, the description is relatively simple. For the relevant parts, please refer to the partial description of the method embodiments.

[0121] Preferably, the embodiments of the present application further provide a terminal, including a processor, a memory, and a computer program stored on the memory and executable on the processor. When the computer program is executed by the processor, it implements each process of the above advertisement evaluation method embodiment and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0122] The embodiments of the present application further provide a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by the processor, it implements each process of the above advertisement evaluation method embodiment and can achieve the same technical effect. To avoid repetition, it will not be elaborated here. Among them, the computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc, etc.

[0123] Each embodiment in this specification is described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. For the same or similar parts among the embodiments, reference can be made to each other.

[0124] Those skilled in the art can easily think that any combination application of the above embodiments is feasible. Therefore, any combination among the above embodiments is an implementation solution of the present application. However, due to space limitations, this specification will not elaborate on them one by one here.

[0125] The method for evaluating advertisements provided herein is not inherently related to any particular computer, virtual system, or other device. A variety of general-purpose systems can also be used in conjunction with the teachings provided herein. Based on the above description, the structure required to construct a system with the solution of the present application is obvious. In addition, the present application is not directed to any particular programming language. It should be understood that the content of the present application described herein can be implemented using a variety of programming languages, and the above description of a particular language is for the purpose of disclosing the best mode of the present application.

[0126] In the specification provided herein, a large number of specific details are set forth. However, it can be understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0127] Similarly, it should be understood that, in order to streamline the present application and assist in understanding one or more of the various aspects of the application, in the above description of the exemplary embodiments of the present application, the various features of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, the disclosed method should not be construed as reflecting an intention that the claimed application requires more features than are expressly recited in each claim. Rather, as reflected in the claims, the aspects of the application lie in less than all of the features of the single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into the detailed description, where each claim stands on its own as a separate embodiment of the present application.

[0128] Those skilled in the art will appreciate that the modules in the devices in the embodiments can be adaptively changed and disposed in one or more devices different from the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and in addition, they can be divided into multiple sub-modules or sub-units or sub-components. Except that at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all the features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all the processes or units of any method or device so disclosed. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) can be replaced by an alternative feature that provides the same, equivalent, or similar purpose.

[0129] In addition, those skilled in the art can understand that although some of the embodiments described herein include certain features included in other embodiments rather than other features, the combination of features of different embodiments means that it is within the scope of this application and forms different embodiments. For example, in the claims, any one of the claimed embodiments can be used in any combination.

[0130] Each component embodiment of the present application can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) can be used in practice to implement some or all of the functions of some or all of the components in the advertisement evaluation method according to the embodiments of the present application. The present application can also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for performing part or all of the methods described herein. Such a program implementing the present application can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, or provided on a carrier signal, or in any other form.

[0131] It should be noted that the above embodiments illustrate the present application rather than limit the present application, and those skilled in the art can design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in the claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present application can be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In the unit claims listing several devices, several of these devices can be embodied by the same item of hardware. The use of the words first, second, and third, etc. does not denote any order. These words can be interpreted as names.

Claims

1. An advertising evaluation method, characterized in that, The method includes: Obtaining advertisements in a preset set and at least one advertisement delivery metric; Every preset time period, for the advertisement delivery metric, counting the metric quantity of advertisements in the preset set; According to multiple attention intervals divided by the numerical range of the metric quantity, and the metric quantity of the advertisement, determining the attention interval where the advertisement in the preset set is located for the advertisement delivery metric; The determining the attention interval where the advertisement in the preset set is located for the advertisement delivery metric includes: Obtaining the total number of advertisements in the preset set, and the number of advertisements in the preset set whose metric quantity is less than that of the advertisement; According to the ratio of the number of advertisements whose metric quantity is less than that of the advertisement to the total number of advertisements, determining the attention interval where the advertisement is located.

2. The method according to claim 1, wherein The preset set includes: a first set and a second set. The advertisements in the first set are in the same advertisement industry, and the advertisements in the second set are in the same advertisement position; The determining the attention interval where the advertisement in the preset set is located for the advertisement delivery metric according to multiple attention intervals divided by the numerical range of the metric quantity, and the metric quantity of the advertisement includes: According to multiple first attention intervals divided by the numerical range of the metric quantity counted from the first set, and the metric quantity of the advertisement in the first set, determining the first attention interval where the advertisement in the first set is located for the advertisement delivery metric; According to multiple second attention intervals divided by the numerical range of the metric quantity counted from the second set, and the metric quantity of the advertisement in the second set, determining the second attention interval where the advertisement in the second set is located for the advertisement delivery metric.

3. The method according to claim 2, characterized in that, The method further includes: When receiving an evaluation request for a target advertisement, determining the target advertisement industry and target advertisement position where the target advertisement is located; Determining a target first set that matches the target advertisement industry, and a target second set that matches the target advertisement position; For the advertisement delivery metric, adding the first attention interval where the target advertisement is located in the target first set within the preset time range to the response to the evaluation request; For the advertisement delivery metric, adding the second attention interval where the target advertisement is located in the target second set within the preset time range to the response to the evaluation request.

4. The method according to claim 1, wherein One of the attention intervals corresponds to a ranking percentage range; the determining the attention interval where the advertisement is located according to the ratio of the number of advertisements whose metric quantity is less than that of the advertisement to the total number of advertisements includes: Determining the attention interval corresponding to the ranking percentage range where the ratio is located as the attention interval where the advertisement is located.

5. The method according to claim 1, characterized in that Different attention intervals are set with different attention labels. The determining the attention interval where the advertisement in the preset set is located for the advertisement delivery metric includes: Determining the attention interval where the advertisement is located within the preset time range and the corresponding attention label.

6. The method according to claim 1, wherein The method further includes: Within the preset time range, sort each advertisement in the attention interval where the advertisement is located according to the metric quantity to obtain a sorting result.

7. The method according to any one of claims 1 to 6, characterized in that The advertisement placement metrics include one or more of: revenue per thousand impressions, estimated click-through rate, estimated conversion rate.

8. An advertisement evaluation device, characterized in that, The device includes: An acquisition module, configured to acquire advertisements in a preset set and at least one advertisement placement metric; A statistics module, configured to, for each preset time period, count the metric quantity of the advertisements in the preset set for the advertisement placement metric; A division module, configured to determine the attention interval where the advertisement in the preset set is located for the advertisement placement metric according to a plurality of attention intervals divided by the numerical range of the metric quantity and the metric quantity of the advertisement; The determining the attention interval where the advertisement in the preset set is located for the advertisement placement metric includes: acquiring the total number of advertisements in the preset set and the number of advertisements in the preset set whose metric quantity is less than that of the advertisement; determining the attention interval where the advertisement is located according to the ratio of the number of advertisements in the preset set whose metric quantity is less than that of the advertisement to the total number of advertisements.

9. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the advertisement evaluation method according to any one of claims 1 to 7 is implemented.

Images