CN112700282A - Method and device for screening advertisement delivery sites and storage medium - Google Patents

Abstract

The application provides a screening method and device for advertisement delivery sites and a storage medium. The method comprises the following steps: acquiring a first site set, wherein the first site set comprises at least 3 sites to be selected; obtaining a site evaluation value of each site to be selected according to the expected delivery time period and site information corresponding to each site to be selected; obtaining a corresponding relation between the exposure times and the advertisement conversion rate according to the user record information of each station to be selected and the record information of the historical delivery activities; and screening sites meeting the delivery constraint conditions from the first site set according to the site evaluation values of all the sites to be selected, the passenger flow prediction information of the expected delivery time interval and the corresponding relation to form a second site set so as to deliver the advertisements to all the sites in the second site set. By using the method, the advertisement putting value can be effectively improved.

Description

Screening method, device and storage medium for advertisement placement site

technical field

The present application belongs to the field of computers, and in particular relates to a method, device and computer-readable storage medium for screening advertisement placement sites.

Background technique

This section is intended to provide a background or context for the embodiments of the application that are recited in the claims. The descriptions herein are not admitted to be prior art by inclusion in this section.

The higher the quality of offline advertising site selection, the higher the advertising conversion rate and the higher the economic benefits. The existing offline advertisement site selection method uses the positioning function of the mobile terminal to determine the number of active users in each area, thereby forming the distribution information of the number of active users, which is used as the basis for offline advertisement site selection.

For offline advertisements (such as light box advertisements, posters) set up at subway stations or railway stations, etc., due to the large mobility of passengers in subway stations or railway stations, there are great differences in the degree of association between different stations. If the subway station is used as an independent individual to evaluate the entry and exit and then screen the placement sites, the value of advertising promotion is limited.

SUMMARY OF THE INVENTION

In view of the above-mentioned problems in the prior art, the embodiments of the present application provide a method, an apparatus, and a computer-readable storage medium for screening advertisement placement sites. With this method and device, the above problems can be solved.

The following solutions are provided in the embodiments of the present application: a method for screening advertisement placement sites, comprising:

Obtain a first site set, the first site set includes at least 3 candidate sites;

According to the estimated delivery period and the site information corresponding to each candidate site, the site evaluation value of each candidate site is obtained;

According to the user record information of each candidate site and the record information of historical advertising activities, obtain the corresponding relationship between the number of exposures and the conversion rate of advertisements;

According to the site evaluation value of each candidate site, the passenger flow forecast information for the expected delivery period, and the corresponding relationship, select the sites that meet the delivery constraints from the first site set to form a second site set. Each site in the second set of sites serves the advertisement.

In some embodiments, according to the site evaluation value of each candidate site, the passenger flow prediction information for the expected delivery period, and the corresponding relationship, the sites that meet the delivery constraints are selected from the first site set to form the first site set. A collection of two sites, including:

The combined evaluation value of the site combination is determined according to the site evaluation value of each candidate site in the site combination, the passenger flow forecast information for the site combination in the expected delivery period, and the corresponding relationship, wherein the site combination is A combination of at least two candidate sites in the first site set;

A site combination that satisfies the constraint condition is selected from the site combination composed of the candidate sites, and each site in the selected site combination constitutes the second site set.

In some embodiments, the number of exposures is calculated according to the cumulative number of exposures during the advertisement placement period;

The combined evaluation value of the site combination is determined according to the site evaluation value of each candidate site in the site combination, the passenger flow forecast information for the site combination in the expected delivery period, and the corresponding relationship, wherein the site combination is The combination formed by at least two candidate sites in the first site set includes:

The combined evaluation value of the site combination is calculated according to the following formula:

Wherein, Q(m) is the combined evaluation value of the site combination, m is the set formed by each site in the site combination, qi is the site evaluation value of the _i -th site in the site combination, and n is the predicted The upper limit of the cumulative number of exposures during the period when the advertisement is placed in the site combination, N ^* _k is the predicted number of users whose cumulative exposure times are k during the period when the advertisement is placed in the site combination, and r _k is the corresponding relationship where the cumulative number of exposures is the advertisement conversion rate corresponding to k times, and N ^* is the predicted total number of users during the period in which the advertisement is placed on the site combination.

In some embodiments, the number of exposures is calculated according to the number of daily exposures during the advertisement placement period;

The combined evaluation value of the site combination is determined according to the site evaluation value of each candidate site in the site combination, the passenger flow forecast information for the site combination in the expected delivery period, and the corresponding relationship, wherein the site combination is The combination formed by at least two candidate sites in the first site set includes:

Calculate the combined evaluation value of the site combination according to the following formula:

Wherein, Q(m) is the combined evaluation value of the site combination, m is the set formed by each site in the site combination, qi is the site evaluation value of the _i -th site in the site combination, and n is the predicted The upper limit of the number of daily exposures during the period in which the advertisement is placed in the site combination, N ^* _k is the predicted daily average value of the number of users with k daily exposures during the period when the advertisement is placed in the site combination, and r _k is the In the corresponding relationship, the number of daily exposures is the corresponding advertisement conversion rate of k times, and N ^* is the predicted daily average of the total number of users during the period in which the advertisement is combined on the site.

In some embodiments, a site combination that satisfies the constraint condition is selected from the site combination composed of the candidate sites, and each site in the selected site combination constitutes the second site set, including:

From all possible site combinations formed by the candidate sites, select a site combination with the highest combined evaluation value of the site combination that satisfies the constraint condition, and each site in the selected site combination constitutes the second site gather.

In some embodiments, a site combination that satisfies the constraint condition is selected from the site combination composed of the candidate sites, and each site in the selected site combination constitutes the second site set, including:

Select sites from the first site set to join the second site set one by one, until the last site added to the second site set makes the second site set do not meet the constraint condition, stop sending to the second site set. A new site is added to the second site set, and the last site added to the second site set is eliminated.

In some embodiments, sequentially selecting sites from the first site set to join the second site set includes:

For the first time, a site with the highest site evaluation value is selected from the first site set to join the second site set;

Each subsequent selection step includes:

From the unselected sites in the first site set, select a site with the highest degree of association with the site that was previously added to the second site set as the first candidate site, and calculate and add the first candidate site to the second site set. In the case of two site sets, the combined evaluation value of the second site set obtains the first predicted value;

Select a site with the highest site evaluation value from the unselected sites in the first site set as the second candidate site, and calculate the second candidate site when the second candidate site is added to the second site set. the combined evaluation value of the site set to obtain the second predicted value;

If the first predicted value is greater than the second predicted value, add the first candidate site to the second site set; if the first predicted value is smaller than the second predicted value, add the The second candidate site is added to the second site set.

In some embodiments, if the first predicted value is equal to the second predicted value, a site is randomly selected from the first candidate site and the second candidate site to join the second site set.

In some embodiments, the degree of association between the two sites is determined according to the number of users whose either site is an inbound site and the other site is an outbound site.

In some embodiments, the constraint conditions include: the number of sites in the second site set is less than or equal to the upper limit threshold of the number of sites, and/or,

The sum of the delivery costs of the sites in the second site set is less than or equal to the cost upper limit threshold.

In some embodiments, the number of exposures is calculated according to the cumulative number of exposures during the advertisement placement period;

According to the user record information of each candidate site and the record information of historical advertising activities, the corresponding relationship between the number of exposures and the conversion rate of advertisements is obtained, including:

Determine the cumulative exposure times of each user within the set time window according to the user record information of each candidate site and the record information of historical advertising activities;

According to the record information of the historical advertising activities, the proportion of users who have been successfully converted for each accumulated exposure within the set time window is respectively determined as the advertisement conversion rate corresponding to the accumulated exposure.

In some embodiments, the number of exposures is calculated according to the number of daily exposures during the advertisement placement period;

According to the user record information of each candidate site and the record information of historical advertising activities, the corresponding relationship between the number of exposures and the conversion rate of advertisements is obtained, including:

Determine the daily exposure times of each user in each day within the set time window according to the user's inbound and outbound record information and the record information of historical advertising activities;

For each day of the time window, according to the record information of the historical delivery activities, determine the proportion of users who have been successfully converted in the time window with the number of exposures on each day of the day in the time window;

For the number of exposures in any day, the daily average value of the ratio is calculated as the advertisement conversion rate corresponding to the number of daily exposures.

In some embodiments, when the duration of the historical advertising campaign is longer than or equal to the duration of the current advertising campaign, the duration of the set time window is equal to the duration of the current advertising campaign, and the set time window is equal to the duration of the current advertising campaign. The last day of the fixed time window is the last day of the historical campaign; or,

When the duration of the historical delivery activity is less than the duration of the current delivery activity, the starting point of the set time window is the first day of the historical delivery activity, and the end point of the time window is the historical delivery activity. The last day to run the campaign.

In some embodiments, the site evaluation value of each candidate site is obtained according to the estimated delivery period and site information corresponding to each candidate site, including:

For each candidate site, according to the historical data of multiple scoring indicators in the corresponding site information, predict the corresponding indicator prediction value within the estimated delivery period;

For each site to be selected, the site evaluation value corresponding to the site to be selected is calculated according to the index prediction values corresponding to the plurality of scoring indexes.

In some embodiments, the multiple scoring indicators include: the average daily passenger flow of the site, the number of similar merchants around the site, the average daily number of users operating the site, the search preferences of the site users, the age distribution of the site users, the gender distribution of the site users, the site users At least two scoring metrics of transaction preference and site user spending.

In some embodiments, for each candidate site, calculating the site evaluation value corresponding to the candidate site according to the index prediction values corresponding to the multiple scoring indicators, including:

Calculate the normalized index prediction value of each scoring index of each candidate site according to the following formula:

为第i个站点的第j个评分指标的归一化指标预测值，

为第i个站点的第j个评分指标的指标预测值，meas(C^j)为第j个评分指标的指标预测值的平均值，std(C^j)为第j个评分指标的指标预测值的标准差；in,

is the predicted value of the normalized index of the jth scoring index of the ith site,

is the index prediction value of the jth scoring index of the ith site, meas(C ^j ) is the average of the index prediction values of the jth scoring index, and std(C ^j ) is the index prediction value of the jth scoring index the standard deviation of ;

Calculate the site evaluation value of each candidate site according to the following formula:

为第i个站点的第j个评分指标的归一化指标预测值，q_i为第i个站点的站点评价值,a_j为第j个评分指标的归一化指标预测值对应的比例系数。in,

is the predicted value of the normalized index of the jth scoring index of the ith site, q _i is the site evaluation value of the ith site, and a _j is the proportional coefficient corresponding to the predicted value of the normalized index of the jth scoring index .

In some embodiments, the scale coefficients corresponding to the normalized index prediction values of each scoring index are all 1.

In some embodiments, the user is defined in terms of the user of the mobile payment application of the mobile terminal as a dimension.

The following solutions are provided in the embodiments of the present application: a screening device for an advertisement placement site, comprising:

an acquisition module, configured to acquire a first site set, where the first site set includes at least 3 candidate sites;

The site evaluation module is used to obtain the site evaluation value of each candidate site according to the estimated delivery period and the site information corresponding to each candidate site;

The corresponding relationship determination module is used to obtain the corresponding relationship between the number of exposures and the conversion rate of advertisements according to the user record information of each candidate site and the record information of historical advertising activities;

The screening module is used for screening the sites that meet the delivery constraints from the first site set according to the site evaluation value of each candidate site, the passenger flow forecast information for the expected delivery period, and the corresponding relationship, to form a second site. a collection of sites to serve the advertisement to each site in the second collection of sites.

In some embodiments, the screening module is specifically used to:

The combined evaluation value of the site combination is determined according to the site evaluation value of each candidate site in the site combination, the passenger flow forecast information for the site combination in the expected delivery period, and the corresponding relationship, wherein the site combination is A combination of at least two candidate sites in the first site set;

A site combination that satisfies the constraint condition is selected from the site combination composed of the candidate sites, and each site in the selected site combination constitutes the second site set.

In some embodiments, the number of exposures is calculated according to the cumulative number of exposures during the advertisement placement period;

The combined evaluation value of the site combination is determined according to the site evaluation value of each candidate site in the site combination, the passenger flow forecast information for the site combination in the expected delivery period, and the corresponding relationship, wherein the site combination is The combination formed by at least two candidate sites in the first site set includes:

The combined evaluation value of the site combination is calculated according to the following formula:

Wherein, Q(m) is the combined evaluation value of the site combination, m is the set formed by each site in the site combination, qi is the site evaluation value of the _i -th site in the site combination, and n is the predicted The upper limit of the cumulative number of exposures during the period when the advertisement is placed in the site combination, N ^* _k is the predicted number of users whose cumulative exposure times are k during the period when the advertisement is placed in the site combination, and r _k is the corresponding relationship where the cumulative number of exposures is the advertisement conversion rate corresponding to k times, and N ^* is the predicted total number of users during the period in which the advertisement is placed on the site combination.

In some embodiments, the number of exposures is calculated according to the number of daily exposures during the advertisement placement period;

The combined evaluation value of the site combination is determined according to the site evaluation value of each candidate site in the site combination, the passenger flow forecast information for the site combination in the expected delivery period, and the corresponding relationship, wherein the site combination is The combination formed by at least two candidate sites in the first site set includes:

Calculate the combined evaluation value of the site combination according to the following formula:

Wherein, Q(m) is the combined evaluation value of the site combination, m is the set formed by each site in the site combination, qi is the site evaluation value of the _i -th site in the site combination, and n is the predicted The upper limit of the number of daily exposures during the period in which the advertisement is placed in the site combination, N ^* _k is the predicted daily average value of the number of users with k daily exposures during the period when the advertisement is placed in the site combination, and r _k is the In the corresponding relationship, the number of daily exposures is the corresponding advertisement conversion rate of k times, and N ^* is the predicted daily average of the total number of users during the period in which the advertisement is combined on the site.

In some embodiments, a site combination that satisfies the constraint condition is selected from the site combination composed of the candidate sites, and each site in the selected site combination constitutes the second site set, including:

From all possible site combinations formed by the candidate sites, select a site combination with the highest combined evaluation value of the site combination that satisfies the constraint condition, and each site in the selected site combination constitutes the second site gather.

In some embodiments,

A site combination that satisfies the constraint condition is selected from the site combination composed of the candidate sites, and each site in the selected site combination constitutes the second site set, including:

Select sites from the first site set to join the second site set one by one, until the last site added to the second site set makes the second site set do not meet the constraint condition, stop sending to the second site set. A new site is added to the second site set, and the last site added to the second site set is eliminated.

In some embodiments, sequentially selecting sites from the first site set to join the second site set includes:

For the first time, a site with the highest site evaluation value is selected from the first site set to join the second site set;

Each subsequent selection step includes:

From the unselected sites in the first site set, select a site with the highest degree of association with the site that was previously added to the second site set as the first candidate site, and calculate and add the first candidate site to the second site set. In the case of two site sets, the combined evaluation value of the second site set obtains the first predicted value;

Select a site with the highest site evaluation value from the unselected sites in the first site set as the second candidate site, and calculate the second candidate site when the second candidate site is added to the second site set. the combined evaluation value of the site set to obtain the second predicted value;

If the first predicted value is greater than the second predicted value, add the first candidate site to the second site set; if the first predicted value is smaller than the second predicted value, add the The second candidate site is added to the second site set.

In some embodiments, if the first predicted value is equal to the second predicted value, a site is randomly selected from the first candidate site and the second candidate site to join the second site set.

In some embodiments, the degree of association between the two sites is determined according to the number of users whose either site is an inbound site and the other site is an outbound site.

In some embodiments, the constraint conditions include: the number of sites in the second site set is less than or equal to the upper limit threshold of the number of sites, and/or,

The sum of the delivery costs of the sites in the second site set is less than or equal to the cost upper limit threshold.

In some embodiments, the number of exposures is calculated according to the cumulative number of exposures during the advertisement placement period;

According to the user record information of each candidate site and the record information of historical advertising activities, the corresponding relationship between the number of exposures and the conversion rate of advertisements is obtained, including:

Determine the cumulative exposure times of each user within the set time window according to the user record information of each candidate site and the record information of historical advertising activities;

According to the record information of the historical advertising activities, the proportion of users who have been successfully converted for each accumulated exposure within the set time window is respectively determined as the advertisement conversion rate corresponding to the accumulated exposure.

In some embodiments, the number of exposures is calculated according to the number of daily exposures during the advertisement placement period;

According to the user record information of each candidate site and the record information of historical advertising activities, the corresponding relationship between the number of exposures and the conversion rate of advertisements is obtained, including:

Determine the daily exposure times of each user in each day within the set time window according to the user's inbound and outbound record information and the record information of historical advertising activities;

For each day of the time window, according to the record information of the historical delivery activities, determine the proportion of users who have been successfully converted in the time window with the number of exposures on each day of the day in the time window;

For the number of exposures in any day, the daily average value of the ratio is calculated as the advertisement conversion rate corresponding to the number of daily exposures.

In some embodiments, when the duration of the historical advertising campaign is longer than or equal to the duration of the current advertising campaign, the duration of the set time window is equal to the duration of the current advertising campaign, and the set time window is equal to the duration of the current advertising campaign. The last day of the fixed time window is the last day of the historical campaign; or,

When the duration of the historical delivery activity is less than the duration of the current delivery activity, the starting point of the set time window is the first day of the historical delivery activity, and the end point of the time window is the historical delivery activity. The last day to run the campaign.

In some embodiments, the site evaluation value of each candidate site is obtained according to the estimated delivery period and site information corresponding to each candidate site, including:

For each candidate site, according to the historical data of multiple scoring indicators in the corresponding site information, predict the corresponding indicator prediction value within the estimated delivery period;

For each site to be selected, the site evaluation value corresponding to the site to be selected is calculated according to the index prediction values corresponding to the plurality of scoring indexes.

In some embodiments, the multiple scoring indicators include: the average daily passenger flow of the site, the number of similar merchants around the site, the average daily number of users operating the site, the search preferences of the site users, the age distribution of the site users, the gender distribution of the site users, the site users At least two scoring metrics of transaction preference and site user spending.

In some embodiments, for each candidate site, calculating the site evaluation value corresponding to the candidate site according to the index prediction values corresponding to the multiple scoring indicators, including:

Calculate the normalized index prediction value of each scoring index of each candidate site according to the following formula:

为第i个站点的第j个评分指标的归一化指标预测值，

为第i个站点的第j个评分指标的指标预测值，meas(C^j)为第j个评分指标的指标预测值的平均值，std(C^j)为第j个评分指标的指标预测值的标准差；in,

is the predicted value of the normalized index of the jth scoring index of the ith site,

is the index prediction value of the jth scoring index of the ith site, meas(C ^j ) is the average of the index prediction values of the jth scoring index, and std(C ^j ) is the index prediction value of the jth scoring index the standard deviation of ;

Calculate the site evaluation value of each candidate site according to the following formula:

为第i个站点的第j个评分指标的归一化指标预测值，q_i为第i个站点的站点评价值,a_j为第j个评分指标的归一化指标预测值对应的比例系数。in,

is the predicted value of the normalized index of the jth scoring index of the ith site, q _i is the site evaluation value of the ith site, and a _j is the proportional coefficient corresponding to the predicted value of the normalized index of the jth scoring index .

In some embodiments, the scale coefficients corresponding to the normalized index prediction values of each scoring index are all 1.

In some embodiments, the user is defined in terms of the user of the mobile payment application of the mobile terminal as a dimension.

The embodiments of the present application provide the following solutions: an apparatus for determining an advertisement placement site, characterized by comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores data that can be accessed by at least one processor Instructions executed by one processor, the instructions being executed by at least one processor to enable the at least one processor to perform: the aforementioned method.

The embodiments of the present application provide the following solutions: a computer-readable storage medium, characterized in that, the computer-readable storage medium stores a program, and when the program is executed by a processor, the processor is made to execute the program. : the aforementioned method.

The above-mentioned at least one technical solution adopted in the embodiment of the present application can achieve the following beneficial effects: because the site's own placement benefit (ie, site evaluation value) and the associated characteristics between sites are comprehensively considered when screening advertisement placement sites, the overall exposure to The number of users with more times is more, which effectively improves the comprehensive benefit of advertising.

It should be understood that the above description is only an overview of the technical solutions of the present application, so that the technical means of the present application can be more clearly understood and implemented in accordance with the contents of the description. In order to make the above-mentioned and other objects, features and advantages of the present application more apparent and comprehensible, specific embodiments of the present application are illustrated below.

Description of drawings

The advantages and benefits described herein, as well as other advantages and benefits, will become apparent to those of ordinary skill in the art upon reading the following detailed description of the exemplary embodiments. The drawings are for purposes of illustrating exemplary embodiments only and are not to be considered limiting of the application. Also, the same components are denoted by the same reference numerals throughout the drawings. In the attached image:

FIG. 1 is a schematic flowchart of a method for screening advertisement placement sites according to an embodiment of the present application;

2 is a schematic structural diagram of a screening device for an advertisement placement site according to an embodiment of the present application;

FIG. 3 is a schematic structural diagram of a screening apparatus for an advertisement placement site according to another embodiment of the present application.

In the drawings, the same or corresponding reference numerals denote the same or corresponding parts.

Detailed ways

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure will be more thoroughly understood, and will fully convey the scope of the present disclosure to those skilled in the art.

In this application, it should be understood that terms such as "comprising" or "having" are intended to indicate the presence of features, numbers, steps, acts, components, parts or combinations thereof disclosed in this specification and are not intended to exclude a or multiple other features, numbers, steps, acts, components, parts, or combinations thereof may exist.

In addition, it should be noted that the embodiments of the present application and the features of the embodiments may be combined with each other in the case of no conflict. The present application will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

FIG. 1 is a schematic flowchart of a method for screening advertisement placement sites according to an embodiment of the present application. The method is used to select from a first site set (that is, a set consisting of selectable subway stations) for this advertisement. In this process, from a device perspective, the execution body may be one or more computing devices; from a program perspective, the execution body may correspondingly be a program mounted on these computing devices.

The flow in FIG. 1 may include the following steps 100 to 103 .

Step 100: Acquire a first site set, where the first site set includes at least 3 candidate sites.

The subway stations in the first station set are optional subway stations in this advertising campaign. The first station set is denoted as M={a ₁ , a ₂ , ..., a _i , ...}, where a _i represents the subway station numbered i.

Step 101: Obtain a site evaluation value of each candidate site according to the estimated delivery period and site information corresponding to each candidate site.

The site evaluation value is the evaluation value obtained by evaluating the advertising value of a single site.

Step 102 , obtaining the corresponding relationship between the number of exposures and the conversion rate of advertisements according to the user record information of each candidate site and the record information of historical advertising activities.

展示二维码进出地铁站，这里所述说的“用户”可以定义为一个

用户，进而可通过

后台服务器得到用户记录信息。例如某一个“用户”的乘车记录，该“用户”的购物行为，该“用户”是否对

的地铁站站点广告所成功转化等信息。

Display the QR code entering and exiting the subway station. The "user" mentioned here can be defined as a

users, which can then be

The background server obtains the user record information. For example, the ride record of a "user", the shopping behavior of the "user", whether the "user" is right

Information such as the successful conversion of the subway station site advertisement.

后台服务器获得某一用户进出地铁站的记录信息，从另一个APP的后台服务器购物记录信息中得到该APP的一次地铁站线下广告的记录信息，那么可以以身份证号为维度定义一个“用户”。In some embodiments, by

The background server obtains the record information of a user entering and leaving the subway station, and obtains the record information of an offline advertisement of the subway station of the APP from the shopping record information of the background server of another APP, then you can define a "user" with the ID number as the dimension. ".

Based on the above information, it is possible to determine the number of exposures of any "user" in the historical advertising activities, and whether the "user" has been successfully converted, so as to determine the corresponding relationship between the number of exposures and the conversion rate.

Step 103: According to the site evaluation value of each candidate site, the passenger flow prediction information for the expected delivery period, and the corresponding relationship, select the sites that meet the delivery constraints from the first site set to form a second site set. , to serve the advertisement to each site in the second set of sites.

The site evaluation value is an evaluation of the advertising value of a single site.

Passenger flow can be predicted by a number of known methods. Thereby, the number of people corresponding to different exposure times in any combination of sites can be determined.

In addition, in step 103, the corresponding relationship between the number of exposures and the conversion rate of the advertisement is obtained. By combining the above three kinds of information, the overall advertising value of any site combination can be evaluated, so that sites can be better screened.

It is easy to understand that the higher the site evaluation value of the screened sites themselves and the closer the connection between the screened sites, the higher the overall advertising value.

Since the site's own delivery benefits (ie, site evaluation value) and the correlation characteristics between sites are comprehensively considered when screening advertisement delivery sites, the overall number of users with more exposures is larger, which effectively improves the comprehensive benefits of advertising delivery. .

In some embodiments, according to the site evaluation value of each candidate site, the passenger flow prediction information for the expected delivery period, and the corresponding relationship, the sites that meet the delivery constraints are selected from the first site set to form the first site set. A collection of two sites, including:

The combined evaluation value of the site combination is determined according to the site evaluation value of each candidate site in the site combination, the passenger flow forecast information for the site combination in the expected delivery period, and the corresponding relationship, wherein the site combination is A combination of at least two candidate sites in the first site set;

A site combination that satisfies the constraint condition is selected from the site combination composed of the candidate sites, and each site in the selected site combination constitutes the second site set.

That is, the ad placement value of the site combination is evaluated, and the combined evaluation value of the site combination is obtained. According to the combined evaluation values of different site combinations, a site combination with the highest or relatively high combination evaluation value among the site combinations that satisfy the constraint conditions is selected for this advertisement placement.

In some embodiments, the number of exposures is calculated according to the cumulative number of exposures during the advertisement placement period;

The combined evaluation value of the site combination is determined according to the site evaluation value of each candidate site in the site combination, the passenger flow forecast information for the site combination in the expected delivery period, and the corresponding relationship, wherein the site combination is The combination formed by at least two candidate sites in the first site set includes:

The combined evaluation value of the site combination is calculated according to the following formula:

Wherein, Q(m) is the combined evaluation value of the site combination, m is the set formed by each site in the site combination, qi is the site evaluation value of the _i -th site in the site combination, and n is the predicted The upper limit of the cumulative number of exposures during the period when the advertisement is placed in the site combination, N ^* _k is the predicted number of users whose cumulative exposure times are k during the period when the advertisement is placed in the site combination, and r _k is the corresponding relationship where the cumulative number of exposures is the advertisement conversion rate corresponding to k times, and N ^* is the predicted total number of users during the period in which the advertisement is placed on the site combination.

In some embodiments, the number of exposures is calculated according to the number of daily exposures during the advertisement placement period;

The combined evaluation value of the site combination is determined according to the site evaluation value of each candidate site in the site combination, the passenger flow forecast information for the site combination in the expected delivery period, and the corresponding relationship, wherein the site combination is The combination formed by at least two candidate sites in the first site set includes:

Calculate the combined evaluation value of the site combination according to the following formula:

Wherein, Q(m) is the combined evaluation value of the site combination, m is the set formed by each site in the site combination, qi is the site evaluation value of the _i -th site in the site combination, and n is the predicted The upper limit of the number of daily exposures during the period in which the advertisement is placed in the site combination, N ^* _k is the predicted daily average value of the number of users with k daily exposures during the period when the advertisement is placed in the site combination, and r _k is the In the corresponding relationship, the number of daily exposures is the corresponding advertisement conversion rate of k times, and N ^* is the predicted daily average of the total number of users during the period in which the advertisement is combined on the site.

In the above two implementations, for a certain site combination, the site evaluation value of each site itself is considered, and the association between the sites in the site combination is considered, that is, the placement of each site in the site combination is predicted. Advertising, how many users have seen this advertisement once, how many users have seen this advertisement twice, and combined with the conversion rate of different exposure times, can comprehensively evaluate the advertising value of this site combination.

Of course, the calculation method of the combined evaluation value is not limited to this. Following the definitions of the previous two embodiments, the calculation formula of the combined evaluation value is, for example:

Among them, the increased b and c are positive proportional coefficients.

In some embodiments, a site combination that satisfies the constraint condition is selected from the site combination composed of the candidate sites, and each site in the selected site combination constitutes the second site set, including:

From all possible site combinations formed by the candidate sites, select a site combination with the highest combined evaluation value of the site combination that satisfies the constraint condition, and each site in the selected site combination constitutes the second site gather.

That is, an exhaustive method can be used to calculate the combined evaluation value of all possible site combinations, and then select a site combination with the highest combined evaluation value among the site combinations that satisfy the constraints for this advertisement placement.

In some embodiments, a site combination that satisfies the constraint condition is selected from the site combination composed of the candidate sites, and each site in the selected site combination constitutes the second site set, including:

Select sites from the first site set to join the second site set one by one, until the last site added to the second site set makes the second site set do not meet the constraint condition, stop sending to the second site set. A new site is added to the second site set, and the last site added to the second site set is eliminated.

For example, selecting the site where this advertisement is placed according to the aforementioned exhaustive method will have the problems of a large amount of calculation and a long calculation time. Then, according to a certain search strategy, a site combination with a relatively high combination evaluation value that satisfies the constraints can be found.

In some embodiments, sequentially selecting sites from the first site set to join the second site set includes:

For the first time, a site with the highest site evaluation value is selected from the first site set to join the second site set;

Each subsequent selection step includes:

From the unselected sites in the first site set, select a site with the highest degree of association with the site that was previously added to the second site set as the first candidate site, and calculate and add the first candidate site to the second site set. In the case of two site sets, the combined evaluation value of the second site set obtains the first predicted value;

Select a site with the highest site evaluation value from the unselected sites in the first site set as the second candidate site, and calculate the second candidate site when the second candidate site is added to the second site set. the combined evaluation value of the site set to obtain the second predicted value;

If the first predicted value is greater than the second predicted value, add the first candidate site to the second site set; if the first predicted value is smaller than the second predicted value, add the The second candidate site is added to the second site set.

That is, a site with the highest site evaluation value is used as the starting point of the search. Then each time a site is selected, both the site evaluation value of the site itself and the combined evaluation value between the newly added site and the previously added site are considered, so that in the case of a relatively small amount of computation Quickly determine a site combination with a relatively high combination evaluation value that satisfies the constraints.

In some embodiments, if the first predicted value is equal to the second predicted value, a site is randomly selected from the first candidate site and the second candidate site to join the second site set.

In some embodiments, the degree of association between the two sites is determined according to the number of users whose either site is an inbound site and the other site is an outbound site.

In some embodiments, the constraint conditions include: the number of sites in the second site set is less than or equal to the upper limit threshold of the number of sites, and/or,

The sum of the delivery costs of the sites in the second site set is less than or equal to the cost upper limit threshold.

In the above embodiment, the single site with the highest site evaluation value is used as the starting point of the search of the second site set, and one site is added to the second site set for each search.

As a feasible variant, the starting point of the search can also be to calculate the combined evaluation value of any two sites in the first site set, and select a pair of sites with the highest combined evaluation value to join the second site set as the second site. The starting point for collection searches. In the subsequent selection step, each time a site that is most closely associated with the site with the highest evaluation value of the site in the second site set is selected from the first site set to join the second site set.

In some embodiments, the number of exposures is calculated according to the cumulative number of exposures during the advertisement placement period;

According to the user record information of each candidate site and the record information of historical advertising activities, the corresponding relationship between the number of exposures and the conversion rate of advertisements is obtained, including:

Determine the cumulative exposure times of each user within the set time window according to the user record information of each candidate site and the record information of historical advertising activities;

According to the record information of the historical advertising activities, the proportion of users who have been successfully converted for each accumulated exposure within the set time window is respectively determined as the advertisement conversion rate corresponding to the accumulated exposure.

For example, the user record information shows that in a certain week, user A enters and exits station B at subway station A 5 times, and enters and exits station A at subway station B for 5 times; user B enters station A at subway station C and exits station 5 times. 7 exits. The record information of the historical advertising activity shows that the advertising campaign has set up advertisements in subway stations A and B respectively, and the advertising campaign is exactly the previous week. Then, during the duration of the historical campaign, the total number of exposures for User A is 20, and the total number of exposures for User B is 7.

Combining the above two kinds of information, it is further possible to determine how many users with a cumulative exposure count of 1 have been successfully converted, how many users with a cumulative exposure count of 2 have been successfully converted, and so on. Thereby, the corresponding relationship between the cumulative number of exposures and the conversion rate of the advertisement is determined.

In some embodiments, the number of exposures is calculated according to the number of daily exposures during the advertisement placement period;

According to the user record information of each candidate site and the record information of historical advertising activities, the corresponding relationship between the number of exposures and the conversion rate of advertisements is obtained, including:

Determine the daily exposure times of each user in each day within the set time window according to the user's inbound and outbound record information and the record information of historical advertising activities;

For each day of the time window, according to the record information of the historical delivery activities, determine the proportion of users who have been successfully converted in the time window with the number of exposures on each day of the day in the time window;

For the number of exposures in any day, the daily average value of the ratio is calculated as the advertisement conversion rate corresponding to the number of daily exposures.

For example, the user record information shows that on a certain day, user A enters and exits station B at subway station A once, and enters and exits station A at subway station B once; user B enters and exits station at subway station C. once. The record information of the historical delivery activity shows that the delivery activity has set up advertisements in subway stations A and B respectively, and the date of the historical delivery activity covers that day. Then, the number of daily exposures of user A is 4, and the number of daily exposures of user B is 1.

In the above embodiment, the correspondence between the number of daily exposures and the conversion rate of advertisements per day is calculated, and then the average conversion rate of advertisements corresponding to the same number of daily exposures is averaged, and the evaluation value is used as the conversion rate of advertisements corresponding to the number of daily exposures.

In some embodiments, when the duration of the historical advertising campaign is longer than or equal to the duration of the current advertising campaign, the duration of the set time window is equal to the duration of the current advertising campaign, and the set time window is equal to the duration of the current advertising campaign. The last day of the fixed time window is the last day of the historical campaign; or,

When the duration of the historical delivery activity is less than the duration of the current delivery activity, the starting point of the set time window is the first day of the historical delivery activity, and the end point of the time window is the historical delivery activity. The last day to run the campaign.

Whether each user has been successfully converted (for example, becoming a new registered user or purchasing the goods or services promoted by the historical advertising campaign) and the date of the successful conversion can be determined according to the record information of the historical advertising activities. The exposure times of each user can be determined according to the user record information. Combining the above two kinds of information, the corresponding relationship between the number of exposures and the conversion rate of advertisements can be obtained.

Generally, regardless of other factors, the higher the total number of impressions, the higher the ad conversion rate, and the higher the number of daily impressions, the higher the ad conversion rate.

In some embodiments, the site evaluation value of each candidate site is obtained according to the estimated delivery period and site information corresponding to each candidate site, including:

For each candidate site, according to the historical data of multiple scoring indicators in the corresponding site information, predict the corresponding indicator prediction value within the estimated delivery period;

For each site to be selected, the site evaluation value corresponding to the site to be selected is calculated according to the index prediction values corresponding to the plurality of scoring indexes.

In some embodiments, the multiple scoring indicators include: the average daily passenger flow of the site, the number of similar merchants around the site, the average daily number of users operating the site, the search preferences of the site users, the age distribution of the site users, the gender distribution of the site users, the site users At least two scoring metrics of transaction preference and site user spending.

For example, the average daily passenger flow of a site is 10,000 people, and the corresponding indicator forecast value is 10,000. The average daily passenger flow of another site is 20,000 people, and the corresponding indicator forecast value is 20,000.

For another example, the proportion of male passengers at a certain site is 0.6, and the proportion of female passengers is 0.4, and the corresponding indicator prediction value is 0.6 (this campaign is aimed at male users). The proportion of male passengers at another station is 0.55, and the proportion of female passengers is 0.45, corresponding to a predicted value of 0.55.

In some embodiments, for each candidate site, calculating the site evaluation value corresponding to the candidate site according to the index prediction values corresponding to the multiple scoring indicators, including:

Calculate the normalized index prediction value of each scoring index of each candidate site according to the following formula:

为第i个站点的第j个评分指标的归一化指标预测值，

为第i个站点的第j个评分指标的指标预测值，meas(C^j)为第j个评分指标的指标预测值的平均值，sts(C^j)为第j个评分指标的指标预测值的标准差；in,

is the predicted value of the normalized index of the jth scoring index of the ith site,

is the index predicted value of the jth scoring index of the ith site, meas(C ^j ) is the average of the index predicted values of the jth scoring index, and sts(C ^j ) is the index predicted value of the jth scoring index the standard deviation of ;

Calculate the site evaluation value of each candidate site according to the following formula:

为第i个站点的第j个评分指标的归一化指标预测值，q_i为第i个站点的站点评价值,a_j为第j个评分指标的归一化指标预测值对应的比例系数。in,

is the predicted value of the normalized index of the jth scoring index of the ith site, q _i is the site evaluation value of the ith site, and a _j is the proportional coefficient corresponding to the predicted value of the normalized index of the jth scoring index .

In some embodiments, the scale coefficients corresponding to the normalized index prediction values of each scoring index are all 1.

In some embodiments, the user is defined in terms of the user of the mobile payment application of the mobile terminal as a dimension.

Referring to FIG. 2 , the following solutions are provided in the embodiments of the present application: an apparatus for screening advertisement placement sites, including:

Obtaining module 1, for obtaining a first site set, the first site set includes at least 3 candidate sites;

The site evaluation module 2 is used to obtain the site evaluation value of each candidate site according to the estimated delivery period and the site information corresponding to each candidate site;

Correspondence determination module 3, configured to obtain the corresponding relationship between the number of exposures and the conversion rate of advertisements according to the user record information of each candidate site and the record information of historical advertising activities;

The screening module 4 is used for screening the sites that meet the delivery constraints from the first site set according to the site evaluation value of each candidate site, the passenger flow forecast information for the expected delivery period, and the corresponding relationship, forming the first site set. A second set of sites to deliver the advertisement to each site in the second set of sites.

In some embodiments, the screening module 4 is specifically used for:

The combined evaluation value of the site combination is determined according to the site evaluation value of each candidate site in the site combination, the passenger flow forecast information for the site combination in the expected delivery period, and the corresponding relationship, wherein the site combination is A combination of at least two candidate sites in the first site set;

A site combination that satisfies the constraint condition is selected from the site combination composed of the candidate sites, and each site in the selected site combination constitutes the second site set.

In some embodiments, the number of exposures is calculated according to the cumulative number of exposures during the advertisement placement period;

The combined evaluation value of the site combination is determined according to the site evaluation value of each candidate site in the site combination, the passenger flow forecast information for the site combination in the expected delivery period, and the corresponding relationship, wherein the site combination is The combination formed by at least two candidate sites in the first site set includes:

The combined evaluation value of the site combination is calculated according to the following formula:

Wherein, Q(m) is the combined evaluation value of the site combination, m is the set formed by each site in the site combination, qi is the site evaluation value of the _i -th site in the site combination, and n is the predicted The upper limit of the cumulative number of exposures during the period when the advertisement is placed in the site combination, N ^* _k is the predicted number of users whose cumulative exposure times are k during the period when the advertisement is placed in the site combination, and r _k is the corresponding relationship where the cumulative number of exposures is the advertisement conversion rate corresponding to k times, and N ^* is the predicted total number of users during the period in which the advertisement is placed on the site combination.

In some embodiments, the number of exposures is calculated according to the number of daily exposures during the advertisement placement period;

The combined evaluation value of the site combination is determined according to the site evaluation value of each candidate site in the site combination, the passenger flow forecast information for the site combination in the expected delivery period, and the corresponding relationship, wherein the site combination is The combination formed by at least two candidate sites in the first site set includes:

Calculate the combined evaluation value of the site combination according to the following formula:

Wherein, Q(m) is the combined evaluation value of the site combination, m is the set formed by each site in the site combination, qi is the site evaluation value of the _i -th site in the site combination, and n is the predicted The upper limit of the number of daily exposures during the period in which the advertisement is placed in the site combination, N ^* _k is the predicted daily average value of the number of users with k daily exposures during the period when the advertisement is placed in the site combination, and r _k is the In the corresponding relationship, the number of daily exposures is the corresponding advertisement conversion rate of k times, and N ^* is the predicted daily average of the total number of users during the period in which the advertisement is combined on the site.

In some embodiments, a site combination that satisfies the constraint condition is selected from the site combination composed of the candidate sites, and each site in the selected site combination constitutes the second site set, including:

From all possible site combinations formed by the candidate sites, select a site combination with the highest combined evaluation value of the site combination that satisfies the constraint condition, and each site in the selected site combination constitutes the second site gather.

In some embodiments,

A site combination that satisfies the constraint condition is selected from the site combination composed of the candidate sites, and each site in the selected site combination constitutes the second site set, including:

Select sites from the first site set to join the second site set one by one, until the last site added to the second site set makes the second site set do not meet the constraint condition, stop sending to the second site set. A new site is added to the second site set, and the last site added to the second site set is eliminated.

In some embodiments, sequentially selecting sites from the first site set to join the second site set includes:

For the first time, a site with the highest site evaluation value is selected from the first site set to join the second site set;

Each subsequent selection step includes:

From the unselected sites in the first site set, select a site with the highest degree of association with the site that was previously added to the second site set as the first candidate site, and calculate and add the first candidate site to the second site set. In the case of two site sets, the combined evaluation value of the second site set obtains the first predicted value;

Select a site with the highest site evaluation value from the unselected sites in the first site set as the second candidate site, and calculate the second candidate site when the second candidate site is added to the second site set. the combined evaluation value of the site set to obtain the second predicted value;

If the first predicted value is greater than the second predicted value, add the first candidate site to the second site set; if the first predicted value is smaller than the second predicted value, add the The second candidate site is added to the second site set.

In some embodiments, if the first predicted value is equal to the second predicted value, a site is randomly selected from the first candidate site and the second candidate site to join the second site set.

In some embodiments, the degree of association between the two sites is determined according to the number of users whose either site is an inbound site and the other site is an outbound site.

In some embodiments, the constraint conditions include: the number of sites in the second site set is less than or equal to the upper limit threshold of the number of sites, and/or,

The sum of the delivery costs of the sites in the second site set is less than or equal to the cost upper limit threshold.

In some embodiments, the number of exposures is calculated according to the cumulative number of exposures during the advertisement placement period;

According to the user record information of each candidate site and the record information of historical advertising activities, the corresponding relationship between the number of exposures and the conversion rate of advertisements is obtained, including:

Determine the cumulative exposure times of each user within the set time window according to the user record information of each candidate site and the record information of historical advertising activities;

According to the record information of the historical advertising activities, the proportion of users who have been successfully converted for each accumulated exposure within the set time window is respectively determined as the advertisement conversion rate corresponding to the accumulated exposure.

In some embodiments, the number of exposures is calculated according to the number of daily exposures during the advertisement placement period;

According to the user record information of each candidate site and the record information of historical advertising activities, the corresponding relationship between the number of exposures and the conversion rate of advertisements is obtained, including:

Determine the daily exposure times of each user in each day within the set time window according to the user's inbound and outbound record information and the record information of historical advertising activities;

For each day of the time window, according to the record information of the historical delivery activities, determine the proportion of users who have been successfully converted in the time window with the number of exposures on each day of the day in the time window;

For the number of exposures in any day, the daily average value of the ratio is calculated as the advertisement conversion rate corresponding to the number of daily exposures.

For example, calculate the corresponding relationship between the number of daily exposures and the conversion rate of advertisements according to the following formula:

其中，

in,

Among them, N _k,t is the total number of users with exposure times k on day t, n _k,t is the total number of users who have been successfully converted among users with exposure times k on day t, and r _k,t is exposure times on day t is the ad conversion rate of k, T is the number of days in the set time window, and r _k is the average ad conversion rate corresponding to the number of daily exposures k.

In some embodiments, when the duration of the historical advertising campaign is longer than or equal to the duration of the current advertising campaign, the duration of the set time window is equal to the duration of the current advertising campaign, and the set time window is equal to the duration of the current advertising campaign. The last day of the fixed time window is the last day of the historical campaign; or,

When the duration of the historical delivery activity is less than the duration of the current delivery activity, the starting point of the set time window is the first day of the historical delivery activity, and the end point of the time window is the historical delivery activity. The last day to run the campaign.

In some embodiments, the site evaluation value of each candidate site is obtained according to the estimated delivery period and site information corresponding to each candidate site, including:

For each candidate site, according to the historical data of multiple scoring indicators in the corresponding site information, predict the corresponding indicator prediction value within the estimated delivery period;

For each site to be selected, the site evaluation value corresponding to the site to be selected is calculated according to the index prediction values corresponding to the plurality of scoring indexes.

In some embodiments, the multiple scoring indicators include: the average daily passenger flow of the site, the number of similar merchants around the site, the average daily number of users operating the site, the search preferences of the site users, the age distribution of the site users, the gender distribution of the site users, the site users At least two scoring metrics of transaction preference and site user spending.

In some embodiments, for each candidate site, calculating the site evaluation value corresponding to the candidate site according to the index prediction values corresponding to the multiple scoring indicators, including:

Calculate the normalized index prediction value of each scoring index of each candidate site according to the following formula:

为第i个站点的第j个评分指标的归一化指标预测值，

为第i个站点的第j个评分指标的指标预测值，meas(C^j)为第j个评分指标的指标预测值的平均值，std(C^j)为第j个评分指标的指标预测值的标准差；in,

is the predicted value of the normalized index of the jth scoring index of the ith site,

is the index prediction value of the jth scoring index of the ith site, meas(C ^j ) is the average of the index prediction values of the jth scoring index, and std(C ^j ) is the index prediction value of the jth scoring index the standard deviation of ;

Calculate the site evaluation value of each candidate site according to the following formula:

为第i个站点的第j个评分指标的归一化指标预测值，q_i为第i个站点的站点评价值,a_j为第j个评分指标的归一化指标预测值对应的比例系数。in,

is the predicted value of the normalized index of the jth scoring index of the ith site, q _i is the site evaluation value of the ith site, and a _j is the proportional coefficient corresponding to the predicted value of the normalized index of the jth scoring index .

In some embodiments, the scale coefficients corresponding to the normalized index prediction values of each scoring index are all 1.

In some embodiments, the user is defined in terms of the user of the mobile payment application of the mobile terminal as a dimension.

FIG. 3 is an apparatus for determining an advertisement placement site according to an embodiment of the present application, which is used for performing the screening method for an advertisement placement site shown in FIG. 1 , the apparatus includes: at least one processor; and is connected in communication with the at least one processor The memory; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute: the aforementioned method for screening advertisement placement sites.

According to some embodiments of the present application, there is provided a non-volatile computer storage medium having computer-executable instructions stored thereon, the computer-executable instructions being configured to be executed when executed by a processor: the aforementioned advertisement placement site filter method.

Each embodiment in this application is described in a progressive manner, and the same and similar parts between the various embodiments may be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of the apparatus and the computer-readable storage medium, since they are basically similar to the method embodiments, the description thereof is simplified, and reference may be made to the partial descriptions of the method embodiments for related parts.

The screening apparatus and the computer-readable storage medium provided in the embodiments of the present application are in a one-to-one correspondence with the method. Therefore, the apparatus and the computer-readable storage medium also have similar beneficial technical effects to their corresponding methods. The technical effects have been described in detail, therefore, the beneficial technical effects of the apparatus and the computer-readable storage medium will not be repeated here.

It should be apparent to those skilled in the art that the embodiments of the present application may be provided as a method, an apparatus or a computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods (systems), and computer program products according to embodiments of the present application. It will be understood that each flow and/or block in the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Screening means for implementing the functions specified in a flow or flow of a flowchart and/or a block or blocks of a block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions The apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

These computer program instructions can also be loaded on a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process such that The instructions provide steps for implementing the functions specified in the flow or blocks of the flowcharts and/or the block or blocks of the block diagrams.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

Memory may include non-persistent memory in computer readable media, random access memory (RAM) and/or non-volatile memory in the form of, for example, read only memory (ROM) or flash memory (fkash RAM). Memory is an example of a computer-readable medium.

Computer-readable media includes both persistent and non-permanent, removable and non-removable media, and storage of information may be implemented by any method or technology. Information may be computer readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Flash Memory or other memory technology, Compact Disc Read Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, Magnetic tape cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device. Furthermore, although the operations of the methods of the present application are depicted in the figures in a particular order, this does not require or imply that the operations must be performed in the particular order, or that all illustrated operations must be performed to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined to be performed as one step, and/or one step may be decomposed into multiple steps to be performed.

While the spirit and principles of this application have been described with reference to a number of specific embodiments, it should be understood that this application is not limited to the specific embodiments disclosed, nor does the division of aspects imply that features in these aspects cannot be combined for Benefit, this division is only for convenience of presentation. This application is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.

Claims (38)

1. a screening method for an advertisement placement site, characterized in that, comprising: Obtain a first site set, the first site set includes at least 3 candidate sites; According to the estimated delivery period and the site information corresponding to each candidate site, the site evaluation value of each candidate site is obtained; According to the user record information of each candidate site and the record information of historical advertising activities, obtain the corresponding relationship between the number of exposures and the conversion rate of advertisements; According to the site evaluation value of each candidate site, the passenger flow forecast information for the expected delivery period, and the corresponding relationship, select the sites that meet the delivery constraints from the first site set to form a second site set. Each site in the second set of sites serves the advertisement. 2 . The method according to claim 1 , wherein, according to the site evaluation value of each candidate site, the passenger flow forecast information for the expected delivery period, and the corresponding relationship, the first site set is selected from the first site set. 3 . Sites that meet the delivery constraints form a second site set, including: The combined evaluation value of the site combination is determined according to the site evaluation value of each candidate site in the site combination, the passenger flow forecast information for the site combination in the expected delivery period, and the corresponding relationship, wherein the site combination is A combination of at least two candidate sites in the first site set; A site combination that satisfies the constraint condition is selected from the site combination composed of the candidate sites, and each site in the selected site combination constitutes the second site set. 3. The method according to claim 2, wherein the number of exposures is calculated according to the cumulative number of exposures during the advertisement placement period; The combined evaluation value of the site combination is determined according to the site evaluation value of each candidate site in the site combination, the passenger flow forecast information for the site combination in the expected delivery period, and the corresponding relationship, wherein the site combination is The combination formed by at least two candidate sites in the first site set includes: The combined evaluation value of the site combination is calculated according to the following formula:

Wherein, Q(m) is the combined evaluation value of the site combination, m is the set formed by each site in the site combination, qi is the site evaluation value of the _i -th site in the site combination, and n is the predicted The upper limit of the cumulative number of exposures during the period when the advertisement is placed in the site combination, N ^* _k is the predicted number of users whose cumulative exposure times are k during the period when the advertisement is placed in the site combination, and r _k is the corresponding relationship where the cumulative number of exposures is the advertisement conversion rate corresponding to k times, and N ^* is the predicted total number of users during the period in which the advertisement is placed on the site combination. 4. The method according to claim 2, wherein the number of exposures is calculated according to the number of daily exposures during advertisement placement; The combined evaluation value of the site combination is determined according to the site evaluation value of each candidate site in the site combination, the passenger flow forecast information for the site combination in the expected delivery period, and the corresponding relationship, wherein the site combination is The combination formed by at least two candidate sites in the first site set includes: Calculate the combined evaluation value of the site combination according to the following formula:

Wherein, Q(m) is the combined evaluation value of the site combination, m is the set formed by each site in the site combination, qi is the site evaluation value of the _i -th site in the site combination, and n is the predicted The upper limit of the number of daily exposures during the period in which the advertisement is placed in the site combination, N ^* _k is the predicted daily average value of the number of users with k daily exposures during the period when the advertisement is placed in the site combination, and r _k is the In the corresponding relationship, the number of daily exposures is the corresponding advertisement conversion rate of k times, and N ^* is the predicted daily average of the total number of users during the period in which the advertisement is combined on the site. 5. The method according to claim 2, wherein a site combination that satisfies the constraint condition is selected from the site combination composed of the candidate sites, and each site in the selected site combination constitutes the said site combination. A second collection of sites, including: From all possible site combinations formed by the candidate sites, select a site combination with the highest combined evaluation value of the site combination that satisfies the constraint condition, and each site in the selected site combination constitutes the second site gather. 6. The method according to claim 2, wherein a site combination that satisfies the constraint condition is selected from the site combination composed of the candidate sites, and each site in the selected site combination constitutes the said site combination. A second collection of sites, including: Select sites from the first site set to join the second site set one by one, until the last site added to the second site set makes the second site set do not meet the constraint condition, stop sending to the second site set. A new site is added to the second site set, and the last site added to the second site set is eliminated. 7. The method according to claim 6, wherein successively selecting sites from the first site set to join the second site set, comprising: For the first time, a site with the highest site evaluation value is selected from the first site set to join the second site set; Each subsequent selection step includes: From the unselected sites in the first site set, select a site with the highest degree of association with the site that was previously added to the second site set as the first candidate site, and calculate and add the first candidate site to the second site set. In the case of two site sets, the combined evaluation value of the second site set obtains the first predicted value; Select a site with the highest site evaluation value from the unselected sites in the first site set as the second candidate site, and calculate the second candidate site when the second candidate site is added to the second site set. the combined evaluation value of the site set to obtain the second predicted value; If the first predicted value is greater than the second predicted value, add the first candidate site to the second site set; if the first predicted value is smaller than the second predicted value, add the The second candidate site is added to the second site set. 8. The method according to claim 7, wherein, if the first predicted value is equal to the second predicted value, then randomly select one of the first candidate site and the second candidate site A site joins the second set of sites. 9 . The method according to claim 7 , wherein the degree of association between the two sites is determined according to the number of users whose either site is an inbound site and the other site is an outbound site. 10 . 10. The method according to claim 1, wherein the constraint condition comprises: the number of sites in the second site set is less than or equal to the upper limit threshold of the number of sites, and/or, The sum of the delivery costs of the sites in the second site set is less than or equal to the cost upper limit threshold. 11. The method according to claim 1, wherein the number of exposures is calculated according to the cumulative number of exposures during the advertisement placement period; According to the user record information of each candidate site and the record information of historical advertising activities, the corresponding relationship between the number of exposures and the conversion rate of advertisements is obtained, including: Determine the cumulative exposure times of each user within the set time window according to the user record information of each candidate site and the record information of historical advertising activities; According to the record information of the historical advertising activities, the proportion of users who have been successfully converted for each accumulated exposure within the set time window is respectively determined as the advertisement conversion rate corresponding to the accumulated exposure. 12. The method according to claim 1, wherein the number of exposures is calculated according to the number of daily exposures during the advertisement placement period; According to the user record information of each candidate site and the record information of historical advertising activities, the corresponding relationship between the number of exposures and the conversion rate of advertisements is obtained, including: Determine the daily exposure times of each user in each day within the set time window according to the user's inbound and outbound record information and the record information of historical advertising activities; For each day of the time window, according to the record information of the historical delivery activities, determine the proportion of users who have been successfully converted in the time window with the number of exposures on each day of the day in the time window; For the number of exposures in any day, the daily average value of the ratio is calculated as the advertisement conversion rate corresponding to the number of daily exposures. 13. The method according to claim 11 or 12, characterized in that, when the duration of the historical advertising campaign is longer than or equal to the duration of the current advertising campaign, the duration of the set time window is equal to The duration of this advertising campaign, the last day of the set time window is the last day of the historical campaign; or, When the duration of the historical delivery activity is less than the duration of the current delivery activity, the starting point of the set time window is the first day of the historical delivery activity, and the end point of the time window is the historical delivery activity. The last day to run the campaign. 14. The method according to claim 1, wherein the site evaluation value of each candidate site is obtained according to the expected delivery period and the site information corresponding to each candidate site, comprising: For each candidate site, according to the historical data of multiple scoring indicators in the corresponding site information, predict the corresponding indicator prediction value within the estimated delivery period; For each site to be selected, the site evaluation value corresponding to the site to be selected is calculated according to the index prediction values corresponding to the plurality of scoring indexes. 15. The method according to claim 14, wherein the plurality of scoring indicators comprises: the average daily passenger flow of the site, the number of similar merchants around the site, the average daily number of users operating the site, the search preference of the site users, the age of the site users At least two scoring indicators in distribution, site user gender distribution, site user transaction preference, and site user consumption amount. 16. The method according to claim 14, wherein, for each candidate site, calculating the site evaluation value corresponding to the candidate site according to the index prediction value corresponding to the plurality of scoring indicators, comprising: Calculate the normalized index prediction value of each scoring index of each candidate site according to the following formula:

in,

is the predicted value of the normalized index of the jth scoring index of the ith site,

is the index prediction value of the jth scoring index of the ith site, meas(C ^j ) is the average of the index prediction values of the jth scoring index, and std(C ^j ) is the index prediction value of the jth scoring index the standard deviation of ; Calculate the site evaluation value of each candidate site according to the following formula:

in,

is the predicted value of the normalized index of the jth scoring index of the ith site, q _i is the site evaluation value of the ith site, and a _j is the proportional coefficient corresponding to the predicted value of the normalized index of the jth scoring index . 17 . The method according to claim 16 , wherein the scale coefficients corresponding to the normalized index prediction values of each scoring index are all 1. 18 . 18. The method according to claim 1, wherein the user is defined according to the dimension of the user of the mobile payment application of the mobile terminal. 19. A screening device for an advertisement placement site, characterized in that it comprises: an acquisition module, configured to acquire a first site set, where the first site set includes at least 3 candidate sites; The site evaluation module is used to obtain the site evaluation value of each candidate site according to the estimated delivery period and the site information corresponding to each candidate site; The corresponding relationship determination module is used to obtain the corresponding relationship between the number of exposures and the conversion rate of advertisements according to the user record information of each candidate site and the record information of historical advertising activities; The screening module is used for screening the sites that meet the delivery constraints from the first site set according to the site evaluation value of each candidate site, the passenger flow forecast information for the expected delivery period, and the corresponding relationship, to form a second site. a collection of sites to serve the advertisement to each site in the second collection of sites. 20. The screening device according to claim 19, wherein the screening module is specifically used for: The combined evaluation value of the site combination is determined according to the site evaluation value of each candidate site in the site combination, the passenger flow forecast information for the site combination in the expected delivery period, and the corresponding relationship, wherein the site combination is A combination of at least two candidate sites in the first site set; A site combination that satisfies the constraint condition is selected from the site combination composed of the candidate sites, and each site in the selected site combination constitutes the second site set. 21. The screening device of claim 20, wherein The number of exposures is calculated according to the cumulative number of exposures during the advertisement placement period; The combined evaluation value of the site combination is determined according to the site evaluation value of each candidate site in the site combination, the passenger flow forecast information for the site combination in the expected delivery period, and the corresponding relationship, wherein the site combination is The combination formed by at least two candidate sites in the first site set includes: The combined evaluation value of the site combination is calculated according to the following formula:

Wherein, Q(m) is the combined evaluation value of the site combination, m is the set formed by each site in the site combination, qi is the site evaluation value of the _i -th site in the site combination, and n is the predicted The upper limit of the cumulative number of exposures during the period when the advertisement is placed in the site combination, N ^* _k is the predicted number of users whose cumulative exposure times are k during the period when the advertisement is placed in the site combination, and r _k is the corresponding relationship where the cumulative number of exposures is the advertisement conversion rate corresponding to k times, and N ^* is the predicted total number of users during the period in which the advertisement is placed on the site combination. 22. The screening device of claim 20, wherein The number of exposures is calculated according to the number of daily exposures during the advertising period; The combined evaluation value of the site combination is determined according to the site evaluation value of each candidate site in the site combination, the passenger flow forecast information for the site combination in the expected delivery period, and the corresponding relationship, wherein the site combination is The combination formed by at least two candidate sites in the first site set includes: Calculate the combined evaluation value of the site combination according to the following formula:

Wherein, Q(m) is the combined evaluation value of the site combination, m is the set formed by each site in the site combination, qi is the site evaluation value of the _i -th site in the site combination, and n is the predicted The upper limit of the number of daily exposures during the period in which the advertisement is placed in the site combination, N ^* _k is the predicted daily average value of the number of users with k daily exposures during the period when the advertisement is placed in the site combination, and r _k is the In the corresponding relationship, the number of daily exposures is the corresponding advertisement conversion rate of k times, and N ^* is the predicted daily average of the total number of users during the period in which the advertisement is combined on the site. 23. The screening device according to claim 20, wherein a site combination that satisfies the constraint condition is selected from the site combination composed of the candidate sites, and each site in the selected site combination constitutes a The second set of sites described above includes: From all possible site combinations formed by the candidate sites, select a site combination with the highest combined evaluation value of the site combination that satisfies the constraint condition, and each site in the selected site combination constitutes the second site gather. 24. The screening device of claim 20, wherein A site combination that satisfies the constraint condition is selected from the site combination composed of the candidate sites, and each site in the selected site combination constitutes the second site set, including: Select sites from the first site set to join the second site set one by one, until the last site added to the second site set makes the second site set do not meet the constraint condition, stop sending to the second site set. A new site is added to the second site set, and the last site added to the second site set is eliminated. 25. The screening device of claim 24, wherein Selecting sites one by one from the first site set to join the second site set, including: For the first time, a site with the highest site evaluation value is selected from the first site set to join the second site set; Each subsequent selection step includes: From the unselected sites in the first site set, select a site with the highest degree of association with the site that was previously added to the second site set as the first candidate site, and calculate and add the first candidate site to the second site set. In the case of two site sets, the combined evaluation value of the second site set obtains the first predicted value; Select a site with the highest site evaluation value from the unselected sites in the first site set as the second candidate site, and calculate the second candidate site when the second candidate site is added to the second site set. the combined evaluation value of the site set to obtain the second predicted value; If the first predicted value is greater than the second predicted value, add the first candidate site to the second site set; if the first predicted value is smaller than the second predicted value, add the The second candidate site is added to the second site set. 26. The screening device according to claim 25, wherein, if the first predicted value is equal to the second predicted value, then randomly selected from the first candidate site and the second candidate site One site joins the second set of sites. 27. The screening device according to 25, wherein the degree of association between the two sites is determined according to the number of users whose either site is an inbound site and the other site is an outbound site. 28. The screening device according to claim 19, wherein the constraint condition comprises: the number of sites in the second site set is less than or equal to the upper limit threshold of the number of sites, and/or, The sum of the delivery costs of the sites in the second site set is less than or equal to the cost upper limit threshold. 29. The screening device according to claim 19, wherein the number of exposures is calculated according to the cumulative number of exposures during advertisement placement; According to the user record information of each candidate site and the record information of historical advertising activities, the corresponding relationship between the number of exposures and the conversion rate of advertisements is obtained, including: Determine the cumulative exposure times of each user within the set time window according to the user record information of each candidate site and the record information of historical advertising activities; According to the record information of the historical advertising activities, the proportion of users who have been successfully converted for each accumulated exposure within the set time window is respectively determined as the advertisement conversion rate corresponding to the accumulated exposure. 30. The screening device of claim 19, wherein The number of exposures is calculated according to the number of daily exposures during the advertising period; According to the user record information of each candidate site and the record information of historical advertising activities, the corresponding relationship between the number of exposures and the conversion rate of advertisements is obtained, including: Determine the daily exposure times of each user in each day within the set time window according to the user's inbound and outbound record information and the record information of historical advertising activities; For each day of the time window, according to the record information of the historical delivery activities, determine the proportion of users who have been successfully converted in the time window with the number of exposures on each day of the day in the time window; For the number of exposures in any day, the daily average value of the ratio is calculated as the advertisement conversion rate corresponding to the number of daily exposures. 31. The screening device of claim 29 or 30, wherein In the case where the duration of the historical advertising campaign is longer than or equal to the duration of the current advertising campaign, the duration of the set time window is equal to the duration of the current advertising campaign, and the last date of the set time window day is the last day of said historical campaign; or, When the duration of the historical delivery activity is less than the duration of the current delivery activity, the starting point of the set time window is the first day of the historical delivery activity, and the end point of the time window is the historical delivery activity. The last day to run the campaign. 32. The screening device of claim 19, wherein According to the estimated delivery period and the site information corresponding to each candidate site, the site evaluation value of each candidate site is obtained, including: For each candidate site, according to the historical data of multiple scoring indicators in the corresponding site information, predict the corresponding indicator prediction value within the estimated delivery period; For each site to be selected, the site evaluation value corresponding to the site to be selected is calculated according to the index prediction values corresponding to the plurality of scoring indexes. 33. The screening device according to claim 32, wherein the plurality of scoring indicators comprises: the average daily passenger flow of the site, the number of similar merchants around the site, the average daily number of operating users of the site, the search preferences of site users, the number of site users At least two scoring indicators in age distribution, site user gender distribution, site user transaction preference, and site user consumption amount. 34. The screening device of claim 32, wherein For each candidate site, calculate the site evaluation value corresponding to the candidate site according to the index prediction values corresponding to the multiple scoring indicators, including: Calculate the normalized index prediction value of each scoring index of each candidate site according to the following formula:

in,

is the predicted value of the normalized index of the jth scoring index of the ith site,

is the index prediction value of the jth scoring index of the ith site, meas(C ^j ) is the average of the index prediction values of the jth scoring index, and std(C ^j ) is the index prediction value of the jth scoring index the standard deviation of ; Calculate the site evaluation value of each candidate site according to the following formula:

in,

is the predicted value of the normalized index of the jth scoring index of the ith site, q _i is the site evaluation value of the ith site, and a _j is the proportional coefficient corresponding to the predicted value of the normalized index of the jth scoring index . 35 . The screening device according to claim 34 , wherein the proportional coefficients corresponding to the normalized index prediction values of each scoring index are all 1. 36 . 36. The screening apparatus according to claim 19, wherein the user is defined according to the user of the mobile payment application of the mobile terminal as a dimension. 37. An apparatus for screening advertisement placement sites, comprising: at least one processor; and a memory connected in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions Executed by at least one processor to enable the at least one processor to perform: the method of any one of claims 1-18. 38. A computer-readable storage medium, wherein the computer-readable storage medium stores a program, and when the program is executed by a processor, the processor is caused to execute: according to any one of claims 1-18 method described in item.

Images