CN115456691A

CN115456691A - Recommendation method and device for offline advertisement space, electronic equipment and storage medium

Info

Publication number: CN115456691A
Application number: CN202211194290.9A
Authority: CN
Inventors: 郭磊; 陈晓倩; 吴士婷
Original assignee: Beijing Century TAL Education Technology Co Ltd
Current assignee: Beijing Century TAL Education Technology Co Ltd
Priority date: 2022-09-28
Filing date: 2022-09-28
Publication date: 2022-12-09

Abstract

The disclosure provides a recommendation method, a recommendation device, an electronic device and a storage medium for offline advertisement space, wherein the method comprises the following steps: acquiring an advertisement putting request input by a user, wherein the advertisement putting request comprises an advertisement type of an advertisement to be put and a target type of a POI (point of interest) for putting the advertisement to be put; acquiring user portrait data and behavior track data of a plurality of online users; according to the user portrait data, acquiring advertisement preference degrees of a plurality of online users to advertisement types by using an advertisement preference pre-estimation model; clustering the behavior track data based on a clustering algorithm to obtain frequent site labels of a plurality of online users; determining the advertisement preference degrees of candidate geographic grids containing the permanent location positions according to the advertisement preference degrees of a plurality of online users and the permanent location positions of the permanent location labels; and determining offline advertisement positions according to the advertisement preference degrees of the candidate geographic grids. The scheme realizes the mapping between the online users and the offline physical space, and solves the problem that the offline advertisement delivery scene lacks effective audience data.

Description

Recommendation method and device for offline advertisement space, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of advertisement space recommendation technologies, and in particular, to a method and an apparatus for recommending an offline advertisement space, an electronic device, and a storage medium.

Background

In the application scenario of advertisement placement, offline advertisement placement is an important ring. The quality of the advertisement putting effect is highly dependent on the quality of the data information of the collectable audiences, and compared with the online advertisement putting scene, the online advertisement putting scene is lack of sufficient data information of effective audiences, so that the recommendation accuracy of the offline advertisement position is not high.

Disclosure of Invention

In order to solve the technical problems or at least partially solve the technical problems, embodiments of the present disclosure provide a method and an apparatus for recommending an offline advertisement slot, an electronic device, and a storage medium.

According to an aspect of the present disclosure, there is provided a method for recommending offline advertising spots, including:

acquiring an advertisement putting request input by a user, wherein the advertisement putting request comprises an advertisement type of an advertisement to be put and a target type of a POI (point of interest) for putting the advertisement to be put;

acquiring user portrait data and behavior track data of a plurality of online users;

according to the user portrait data, utilizing a pre-trained advertisement preference estimation model to obtain advertisement preference degrees of the online users to the advertisement types;

clustering the behavior track data based on a preset clustering algorithm to obtain the constant station labels of the multiple online users;

determining the advertisement preference degrees of candidate geographic grids containing the common station position according to the advertisement preference degrees of the online users and the common station position corresponding to the common station label;

determining a target geographic grid according to the advertisement preference of the candidate geographic grid;

determining a target POI of the target type contained in the target geographic grid as the offline advertising spot.

According to another aspect of the present disclosure, there is provided a push device for an offline advertising spot, including:

the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring an advertisement putting request input by a user, and the advertisement putting request comprises an advertisement type of an advertisement to be put and a target type of a POI (point of interest) for putting the advertisement to be put;

the second acquisition module is used for acquiring user portrait data and behavior track data of a plurality of online users;

the third acquisition module is used for acquiring the advertisement preference degrees of the online users to the advertisement types by utilizing a pre-trained advertisement preference estimation model according to the user portrait data;

the clustering module is used for clustering the behavior track data based on a preset clustering algorithm so as to obtain the permanent station labels of the online users;

the first determining module is used for determining the advertisement preference of the candidate geographic grid containing the common station position according to the advertisement preference of the online users and the common station position corresponding to the common station label;

the second determining module is used for determining a target geographic grid according to the advertisement preference of the candidate geographic grid;

a third determining module for determining the target POI of the target type contained in the target geographic grid as the offline advertising spot.

According to another aspect of the present disclosure, there is provided an electronic device including:

a processor; and

a memory for storing a program, wherein the program is stored in the memory,

wherein the program comprises instructions which, when executed by the processor, cause the processor to perform the method of recommending offline ad spots according to the aforementioned aspect.

According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of recommending an offline ad spot according to the foregoing one aspect.

According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program, wherein the computer program when executed by a processor implements the method of recommending offline advertising spots of the preceding aspect.

According to one or more technical schemes provided in the embodiments of the present disclosure, an advertisement placement request input by a user is obtained, where the advertisement placement request includes an advertisement type of an advertisement to be placed and a target type of a POI to be placed, user portrait data and behavior track data of a plurality of online users are obtained, then, according to the user portrait data, an advertisement preference prediction model trained in advance is used to obtain advertisement preferences of the plurality of online users with respect to the advertisement type, and the behavior track data is clustered based on a preset clustering algorithm to obtain a common premises tag of the plurality of online users, and further, according to the advertisement preferences of the plurality of online users and a common premises location corresponding to the common premises tag, an advertisement preference of a candidate geographic grid including the common premises location is determined, and further, according to the advertisement preference of the candidate geographic grid, a target geographic grid is determined, and a target POI of the target type included in the target geographic grid is determined as an offline advertisement position. By adopting the scheme, the advertisement preference of the users in the offline scene is estimated by utilizing the user image data of the online users, the regular site labels of the online users are mined by utilizing the behavior track data of the online users, the geographic grids of the offline physical space are determined according to the regular site positions, the advertisement preference of the geographic grids is determined according to the advertisement preference of the online users, so that the target POI of the target type is determined as the recommended offline advertisement space, the mapping between the online users and the offline physical space is realized, the problem that the offline advertisement delivery scene lacks effective audience data is solved, and the accuracy of the offline advertisement space recommendation can be improved.

Drawings

Further details, features and advantages of the disclosure are disclosed in the following description of exemplary embodiments, taken in conjunction with the accompanying drawings, in which:

FIG. 1 shows a flow diagram of a method of recommending offline ad slots, according to an example embodiment of the present disclosure;

FIG. 2 shows a flow diagram of a method of recommending offline ad slots, according to another example embodiment of the present disclosure;

FIG. 3 shows a schematic block diagram of a recommendation device for offline ad slots, according to an example embodiment of the present disclosure;

FIG. 4 illustrates a block diagram of an exemplary electronic device that can be used to implement embodiments of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.

It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order, and/or performed in parallel. Moreover, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.

The term "include" and variations thereof as used herein are open-ended, i.e., "including but not limited to". The term "based on" is "based, at least in part, on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the following description. It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.

It is noted that references to "a" or "an" in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will appreciate that references to "one or more" are intended to be exemplary and not limiting unless the context clearly indicates otherwise.

The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.

Before explaining embodiments of the present disclosure, terms to which the present disclosure may relate are explained as follows:

geographic grid: a unified, simple geographic space divides and positions the reference system, according to unifying the rule, carry on the continuous segmentation according to certain longitude and latitude or ground distance ground area, and control the uncertainty of space in certain range, form the regular polygon, every polygon is called the grid cell, thus form hierarchical, hierarchical multilevel grid system, realize the discretization of the ground space, and give the unified code;

POI: a Point of Interest (Point of Interest) of a geographic space, such as a cell, a school, a mall, an office building, etc.;

CTR: click Through Rate (Click-Through-Rate), which is a commonly used term for internet advertisement, refers to the Click arrival Rate of a web advertisement (picture advertisement/text advertisement/keyword advertisement/ranking advertisement/video advertisement, etc.), i.e. the actual number of clicks of the advertisement (strictly speaking, the number of hits to a target page) is divided by the advertisement exposure (Show content).

The following describes a recommendation method, apparatus, electronic device, and storage medium for offline advertisement slots provided by the present disclosure with reference to the accompanying drawings.

In an advertisement putting scene, accurate touch of advertisement putting is one of core technologies. The quality of the advertisement delivery reaching effect is highly dependent on the quality of the data information of the collectable audiences, however, the offline advertisement delivery scene often lacks enough data information of effective audiences, so that the advertisement delivery accuracy is low.

In order to solve the problems, the method comprises the steps of obtaining an advertisement putting request input by a user, wherein the advertisement putting request comprises an advertisement type to be put with an advertisement and a target type of a POI to be put with the advertisement, obtaining user portrait data and behavior track data of a plurality of online users, obtaining advertisement preference degrees of the online users on the advertisement type according to the user portrait data and a pre-trained advertisement preference estimation model, clustering the behavior track data based on a preset clustering algorithm to obtain a plurality of online users' ordinary site tags, determining advertisement preference degrees of candidate geographic grids containing the ordinary site positions according to the advertisement preference degrees of the online users and the ordinary site positions corresponding to the ordinary site tags, determining a target geographic grid according to the advertisement preference degrees of the candidate geographic grids, and determining a target POI of the target type contained in the target geographic grid as the offline advertisement position. By adopting the scheme, the advertisement preference of the users in the offline scene is estimated by utilizing the user image data of the online users, the regular site labels of the online users are mined by utilizing the behavior track data of the online users, the geographic grids of the offline physical space are determined according to the regular site positions, the advertisement preference of the geographic grids is determined according to the advertisement preference of the online users, so that the target POI of the target type is determined as the recommended offline advertisement space, the mapping between the online users and the offline physical space is realized, the problem that the offline advertisement delivery scene lacks effective audience data is solved, and the accuracy of the offline advertisement space recommendation can be improved. The scheme disclosed by the invention can quickly and conveniently map the online data, flow, marketing resources and the real physical space, and realize accurate marketing position selection of any spatial position of the offline advertisement.

Fig. 1 is a flowchart illustrating a method for recommending an offline advertisement spot according to an exemplary embodiment of the present disclosure, which may be performed by an offline advertisement spot recommending apparatus provided in the present disclosure, where the apparatus may be implemented by software and/or hardware, and may be generally integrated in an electronic device, where the electronic device includes a mobile phone, a tablet computer, a server, and the like, and an application having functions of online and offline advertisement delivery and advertisement spot recommendation may be installed in the electronic device.

As shown in fig. 1, the method for recommending offline advertising spots may include the following steps:

step 101, obtaining an advertisement putting request input by a user, wherein the advertisement putting request comprises an advertisement type of an advertisement to be put and a target type of a POI for putting the advertisement to be put.

The advertisement type to be advertised may be one of a plurality of preset advertisement types, which may include, but are not limited to, education, beauty cosmetics, clothing, shoes, food, and the like. The target type is one of a plurality of POI types, which may include, for example and without limitation, a cell, an office building, a school, a mall, an attraction, and so on. Assuming that a user wishes to place an advertisement in a cell, the target type of POI used for advertisement placement may be determined to be a cell.

In the disclosed embodiment, the user refers to an advertiser having an advertisement placement requirement.

Illustratively, a user may input his or her own advertisement placement needs, such as the type of advertisement to be placed, where to show the advertisement, the number of ad spots desired to be obtained, and the like, through an advertisement placement platform provided in the electronic device. The advertisement putting platform can generate and acquire an advertisement putting request input by a user according to an advertisement putting demand input by the user, wherein the target type of the POI to be put with the advertisement can be determined according to the information of where the advertisement is shown input by the user, for example, the place where the advertisement is shown input by the user is a school, and the target type contained in the advertisement putting request is a school. The advertisement delivery platform may be, for example, an application program supporting an Online-large-Offline (Online-mobile-Offline) mode, and supports both Online advertisement slot recommendation and advertisement delivery and Offline advertisement slot recommendation and advertisement delivery.

Step 102, user portrait data and behavior track data of a plurality of online users are obtained.

The online education platform can adopt an OMO mode, and can be used for providing online education services for users, wherein online users can indicate advertisement audiences in online advertisement delivery scenes, for example, if the users want to deliver newly released courses online, registered users on the online education platform can be obtained as online users; user representation data may include, but is not limited to, the user's gender, age, occupation, personal preferences, and the like; the behavior trace data may be obtained from GPS data of the online user, for example, a registered user of the online education platform may authorize the platform to obtain GPS data of an electronic device used by the registered user, and the online education platform may obtain the behavior trace data of the registered user by analyzing the GPS data.

In the embodiment of the present disclosure, the user portrait data of the online user and the behavior trace data of the online user are obtained when the authorization of the online user is obtained.

Illustratively, the application installed in the electronic device and configured to execute the recommendation method for offline advertising slots disclosed by the present disclosure has the characteristics of an OMO service, accumulates a certain amount of online user data of related service fields over time and using by a user, and when offline advertising slots are recommended, user portrait data and behavior trajectory data of a plurality of online users can be obtained from the accumulated online user data so as to carve data information of audiences in an offline advertising scene.

And 103, acquiring the advertisement preference degrees of the online users to the advertisement types by utilizing a pre-trained advertisement preference estimation model according to the user portrait data.

The advertisement preference estimation model can be obtained by pre-training, and can collect data such as user data in an online advertisement putting scene and click conditions of exposed advertisements by a user, and a training sample is constructed to train to obtain the advertisement preference estimation model.

In an optional embodiment of the disclosure, when an advertisement preference estimation model is obtained through training, an advertisement delivery record of delivering advertisements to a sample user in an online advertisement delivery scene and user portrait data of the sample user can be obtained; analyzing the advertisement putting records to obtain historical put advertisements of different advertisement types and operation data of the sample user on the historical put advertisements, wherein the operation data comprises clicks or non-clicks; marking the historical advertisement according to the operation data of the sample user on the historical advertisement, and generating a sample advertisement; constructing an incidence relation between the user portrait data of the sample user and the sample advertisements of different advertisement types, and generating a training sample set; and training an initial network model based on the training sample set to obtain the advertisement preference estimation model.

The sample user can be an audience for online advertisement delivery accumulated in an application program with OMO characteristics, and the sample user can select to click the advertisement or not click the advertisement according to the interest.

In the embodiment of the disclosure, the advertisement delivery records of the advertisements delivered to the sample users and the user image data corresponding to each sample user can be obtained from the historical data accumulated in the online advertisement delivery scene, the advertisement delivery records corresponding to the sample users are analyzed to obtain the historical delivered advertisements of different advertisement types in the advertisement records, whether the sample users click on the historical delivered advertisements is obtained, and then the historical delivered advertisements are labeled according to whether the sample users click on the historical delivered advertisements, so that the sample advertisements are generated.

For example, when the historically delivered advertisements are labeled, different categories may be represented by using preset identifiers, for example, a identifier "1" represents that a sample user clicks an advertisement, and a identifier "0" represents that the sample user does not click an advertisement, when the sample advertisement is generated, the identifier "0" or "1" may be labeled to the historically delivered advertisements according to whether the sample user clicks the historically delivered advertisements, and the labeled advertisements are the sample advertisements.

For example, if it is determined from the advertisement delivery record corresponding to the sample user a that the user performed a click operation on a certain historically delivered advertisement of the education category, the historically delivered advertisement may be labeled with a label "1" to obtain a sample advertisement.

In the embodiment of the disclosure, for the generated sample advertisement, an association relationship between the user portrait data of the sample user and the sample advertisements of different advertisement types can be constructed to obtain a training sample set.

Continuing with the above example, after a sample advertisement is generated, an association relationship between the user portrait data of the sample user a and the sample advertisement of the education class may be constructed to obtain a training sample. Therefore, after the incidence relation between each sample user and the corresponding sample advertisement is established, the training sample set is obtained.

Furthermore, the initial network model can be trained by utilizing the constructed training sample set so as to obtain a trained advertisement preference estimation model.

The initial network model may be a Boosting model, including but not limited to any one of AdaBoost (adaptive Boosting model), GBDT (Gradient Boosting Decision Tree), XGBoost (eXtreme Gradient Boosting Tree), lightGBM (Light Gradient Boosting Machine), and castboost.

In the embodiment of the disclosure, when the initial network model is trained by using the training sample set, user portrait data of a sample user can be input into the initial network model as feature data, a label of a sample advertisement is used as an expected value, iterative training is performed by continuously updating parameters of the network model until a loss function value obtained by calculation according to a prediction result and the expected value of the network model is smaller than a preset value, and the training is finished to obtain a trained advertisement preference estimation model. Therefore, modeling of the advertisement preference of the online user is achieved, and the advertisement preference degree of different user portrait data to a certain advertisement type can be predicted by using the advertisement preference estimation model. Wherein, the higher the advertisement preference degree is, the greater the probability that the user clicks the advertisement when the user is delivered with the type of advertisement.

In the embodiment of the disclosure, after user portrait data corresponding to a plurality of online users is obtained, the user portrait data can be input into a trained advertisement preference estimation model, and the advertisement preference estimation model outputs the advertisement preference degree of each online user for different advertisement types, so that the advertisement preference degree of each online user for the advertisement type in the advertisement putting request is obtained from the output result of the advertisement preference estimation model.

And 104, clustering the behavior track data based on a preset clustering algorithm to obtain the permanent station labels of the online users.

The Clustering algorithm may be preset, and the Clustering algorithm may be, but is not limited to, a DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm, a coacervation hierarchical Clustering algorithm, and the like.

In the embodiment of the disclosure, for the obtained behavior trajectory data of the online users, the behavior trajectory data may be clustered based on a preset clustering algorithm to obtain the permanent station tags of a plurality of online users.

For example, the permanent station tag may be determined according to the geographical location information corresponding to the center of the cluster obtained by clustering, for example, a place name (such as a street name, a county name, and the like) to which the geographical location information corresponding to the center belongs may be used as the permanent station tag, and online users belonging to one cluster have the same permanent station tag.

And 105, determining the advertisement preference of the candidate geographic grid containing the ordinary station position according to the advertisement preference of the online users and the ordinary station position corresponding to the ordinary station label.

The corresponding permanent station position of the permanent station label can be determined by inquiring the corresponding relation between different place names and position information in the map data, and the permanent station position can be represented by longitude and latitude.

In the embodiment of the present disclosure, after determining the advertisement preference of each online user for the advertisement type and the permanent site tag corresponding to each online user, the geographic grid including the permanent site position may be determined as a candidate geographic grid according to the inclusion relationship between the permanent site position and the geographic grid, and the candidate geographic grid is associated with the online user according to the permanent site tag corresponding to each online user, that is, it is determined that the online user whose permanent site position is matched with the permanent site position included in the candidate geographic grid is located, for example, the permanent site tag corresponding to the online user B is C, the permanent site position included in the candidate geographic grid a corresponds to C, and then the online user B is associated with the candidate geographic grid a, and the online user B is a user residing in the candidate geographic grid. Thereby, spatial aggregation of different users is achieved. Further, for each candidate geographic grid, the advertisement preference of the candidate geographic grid may be determined according to the advertisement preferences of all online users associated with the candidate geographic grid.

Illustratively, in determining the advertisement preference for each candidate geographic grid, for one candidate geographic grid, the greatest advertisement preference may be selected as the advertisement preference for that candidate geographic grid from the advertisement preferences of all online users associated with that candidate geographic grid.

And 106, determining the target geographic grid according to the advertisement preference of the candidate geographic grid.

In the embodiment of the disclosure, after the advertisement preference of each candidate geographic grid is determined, the target geographic grid can be determined from the candidate geographic grids according to the advertisement preference of each candidate geographic grid.

For example, after the advertisement preference of each candidate geographic grid is determined, the candidate geographic grids may be sorted in an order from a large advertisement preference to a small advertisement preference, and a preset number of candidate geographic grids sorted in the front may be obtained as the target geographic grid. The preset number can be preset according to actual requirements, or the preset number can be determined according to the advertisement space budget amount in the advertisement delivery request input by the user, and when the user does not input the advertisement space budget amount, the preset default value is used as the preset number.

For example, after the advertisement preference of each candidate geographic grid is determined, a preference mean value is calculated according to the advertisement preferences of all candidate geographic grids, and the candidate geographic grid with the advertisement preference greater than the preference mean value in the candidate geographic grids is determined as the target geographic grid.

Step 107, determining the target POI of the target type contained in the target geographic grid as the offline advertising space.

In the embodiment of the disclosure, after the target geographic grid is determined, the target POI of the target type can be obtained from the target geographic grid, the obtained target POI is determined as an offline advertisement space, and the determined offline advertisement is recommended to the user.

For example, when recommending a determined offline advertisement slot to the user, information such as the name of the target POI, the geographical location of the target POI may be displayed.

The method for recommending the offline advertisement space comprises the steps of obtaining an advertisement putting request input by a user, wherein the advertisement putting request comprises an advertisement type of an advertisement to be put and a target type of a POI (point of interest) of the advertisement to be put, obtaining user portrait data and behavior track data of a plurality of online users, obtaining advertisement preference degrees of the online users to the advertisement type according to the user portrait data by utilizing a pre-trained advertisement preference estimation model, clustering the behavior track data based on a preset clustering algorithm to obtain a common station label of the online users, determining the advertisement preference degree of a candidate geographic grid containing the common station position according to the advertisement preference degrees of the online users and the common station position corresponding to the common station label, determining a target geographic grid according to the advertisement preference degree of the candidate geographic grid, and determining a target POI (point of interest) of the target type contained in the target geographic grid as the offline advertisement space. By adopting the scheme, the advertisement preference of the users in the offline scene is estimated by utilizing the user image data of the online users, the regular site labels of the online users are mined by utilizing the behavior track data of the online users, the geographic grids of the offline physical space are determined according to the regular site positions, the advertisement preference of the geographic grids is determined according to the advertisement preference of the online users, so that the target POI of the target type is determined as the recommended offline advertisement space, the mapping between the online users and the offline physical space is realized, the problem that the offline advertisement delivery scene lacks effective audience data is solved, and the accuracy of the offline advertisement space recommendation can be improved.

In an optional implementation manner of the present disclosure, when determining the advertisement preference of the candidate geographic grid including the permanent location position according to the advertisement preference of the plurality of online users and the permanent location position corresponding to the permanent location tag, the candidate geographic grid including the permanent location position may be determined from the plurality of geographic grids according to the permanent location position corresponding to the permanent location tag; and then, accumulating the advertisement preference degrees of the online users contained in the candidate geographic grids aiming at each candidate geographic grid to obtain the advertisement preference degree of each candidate geographic grid.

For example, the plurality of geographic grids may be a plurality of grid cells obtained by dividing the real geographic region based on a preset geospatial point indexing algorithm.

For example, the plurality of geographic grid cells may be obtained by filtering, according to a preset filtering policy, a plurality of grid cells obtained by dividing the real geographic area based on a preset geospatial point indexing algorithm.

In the embodiment of the present disclosure, after determining the advertisement preference of each online user for the advertisement type and the regular-site tag corresponding to each online user, a candidate geographic grid including the regular-site location may be determined from the multiple geographic grids according to the regular-site location corresponding to the regular-site tag, and then all online users included in each candidate geographic grid are determined according to the correspondence between the regular-site location included in the candidate geographic grid and the regular-site tag corresponding to the online user, and then the advertisement preferences of all online users included in the same candidate geographic grid are accumulated for each candidate geographic grid, so as to obtain the advertisement preference of each candidate geographic grid, thereby obtaining the advertisement preference of each candidate geographic grid.

For example, assuming that a candidate geographic grid includes 30 online users, and the advertisement preference degrees of the 30 online users are all 0.4, the advertisement preference degree of the candidate geographic grid is 30 × 0.4=12.

In the embodiment of the disclosure, the candidate geographic grids including the permanent location position are determined from the multiple geographic grids according to the permanent location position corresponding to the permanent location label, and then the advertisement preference degrees of the online users included in the candidate geographic grids are accumulated aiming at each candidate geographic grid to obtain the advertisement preference degree of each candidate geographic grid.

In an alternative embodiment of the present disclosure, the plurality of geographic grids described in the foregoing example may be determined by the implementation shown in fig. 2. Fig. 2 is a flowchart illustrating a recommendation method for an offline advertising spot according to another exemplary embodiment of the present disclosure, and as shown in fig. 2, the recommendation method for an offline advertising spot may further include the following steps based on the foregoing embodiments:

step 201, acquiring a plurality of grid cells with preset sizes and containing the POI of the target type.

The preset size may be a side length, a radius, or the like of the grid unit, or an area of the grid unit, which is not limited in this disclosure.

Exemplarily, assuming that the preset size is a side length, the position of a target type POI in a delivery area (such as one or more cities) desired by a user may be obtained, and a square area with the side length being the preset size is divided around the POI as a grid unit by taking the position of the target type POI as a center and the preset size as the side length, where multiple POI are obtained as multiple grid units.

For example, assuming that the preset size is an area, the position of a target type POI in a delivery area desired by a user may be obtained, and an area with the preset size is divided around the target type POI as a grid unit, where the plurality of POIs are multiple grid units.

In an optional embodiment of the present disclosure, when a plurality of grid cells are obtained, a geospatial region may be further divided into a plurality of grid regions based on a geospatial point indexing algorithm, and the grid regions are associated with POIs located in the grid regions thereof; screening out candidate grid areas containing POI of the target type from the plurality of grid areas; if the size of the candidate grid area is smaller than or equal to the preset size, determining the candidate grid area as a grid unit; if the size of the candidate grid area is larger than the preset size, the candidate grid area is segmented to obtain a plurality of sub-grids; for each sub-grid, judging whether the size of the sub-grid is larger than a preset size, and if the size of the sub-grid is not larger than the preset size and contains the POI of the target type, determining the sub-grid as the grid unit; if the size of the sub-grid is larger than the preset size, the candidate sub-grid containing the POI of the target type is continuously segmented until a grid unit which is not larger than the preset size and contains the POI of the target type is obtained.

The geospatial point indexing algorithm may be, but is not limited to, a Genhash algorithm, a Google S2 algorithm, etc.; the geospatial region may be a national geospatial region or a desired region designated by a user (advertiser) to which advertising is desired, and is not limited by the present disclosure.

Illustratively, a set of hierarchy geographic grid ID system can be maintained for a geographic spatial region through the Google S2 algorithm, including multiple grid regions and corresponding IDs, and a POI (including POI name, type, location information, etc.) disclosed by a map is acquired by calling an interface, so as to associate the POI with the ID of the grid region to which the POI belongs.

It can be understood that some grids in the multiple grid regions partitioned based on the geospatial point indexing algorithm may not contain POIs of the target type, and therefore in the embodiment of the present disclosure, the grid regions may be filtered, and only the grid region containing POIs of the target type in the grid region is reserved as a candidate grid region, thereby implementing primary screening of the grid region.

Next, for the screened candidate mesh region, it may be determined whether the size of the candidate mesh region satisfies (is not greater than) a preset size. For example, assuming that the preset size is a side length, it may be compared whether the maximum side length of the candidate grid region is less than or equal to a preset side length threshold, if so, it is considered that the side length of the candidate grid region is not greater than the preset side length threshold, otherwise, it is considered that the side length of the candidate grid region is greater than the preset side length threshold, where the preset side length threshold may be preset according to actual needs. For another example, assuming that the preset size is an area, whether the area of the candidate grid region is larger than a preset area threshold may be compared, if so, the area of the candidate grid region is larger than the preset area threshold, otherwise, the area of the candidate grid region is considered to be not larger than the preset area threshold, wherein the preset area threshold may be preset according to actual needs.

In the embodiment of the disclosure, if the size of the candidate grid area is smaller than or equal to the preset size, the candidate grid area is determined as a grid unit; if the size of the candidate grid region is larger than the preset size, the candidate grid region may be segmented to obtain a plurality of sub-grids, for example, the candidate grid region may be quartered to obtain four sub-grids. For each sub-grid obtained by segmentation, whether the size of the sub-grid is larger than a preset size or not can be judged, and the judgment mode is similar to the mode of judging whether the size of the candidate grid area is larger than the preset size or not. If the size of the sub-grid is smaller than or equal to the preset size and the sub-grid contains the POI of the target type, determining the sub-grid as a grid unit; if the sub-grid does not contain POI of the target type, filtering out the sub-grid; and if the sub-grid contains the POI of the target type, but the size of the sub-grid is larger than the preset size, continuously segmenting the sub-grid to obtain a plurality of smaller sub-grids, and repeating the process until a grid unit which is not larger than the preset size and contains the POI of the target type is obtained.

In an optional embodiment of the present disclosure, for any candidate mesh region including the POI of the target type that is screened out, the area of the candidate mesh region may be compared with a preset area threshold, and if the area of the candidate mesh region is less than or equal to the preset area threshold, the candidate mesh region is determined as a mesh unit; and if the area of the candidate grid region is larger than a preset area threshold value, segmenting the candidate grid region to obtain a plurality of sub-grids. Then, discarding the sub-grids which do not contain the POI of the target type in the plurality of sub-grids, comparing the area of the sub-grids containing the POI of the target type with a preset area threshold value, and if the area of a first sub-grid in the plurality of sub-grids is not larger than the preset area threshold value and contains the POI of the target type, determining the first sub-grid as a grid unit, wherein the first sub-grid is any one of the plurality of sub-grids; and if the area of a second sub-grid in the plurality of sub-grids is larger than the preset area threshold and contains the POI of the target type, continuously segmenting the second sub-grid to obtain a plurality of smaller sub-grids, and repeating the process until a grid unit with the area not larger than the preset area threshold and containing the POI of the target type is obtained, wherein the second sub-grid is any one of the plurality of sub-grids except the first sub-grid.

That is to say, in a plurality of sub-grids obtained by segmenting the candidate grid region, for a first sub-grid which has an area not greater than a preset area threshold and contains the POI of the target type, directly determining the first sub-grid as a grid unit; and for the second sub-grid which is larger than the preset area threshold and contains the POI of the target type, continuously dividing the second sub-grid into a plurality of smaller sub-grids, and repeating the process until a grid unit which is smaller than the preset area threshold and contains the POI of the target type is obtained.

In the embodiment of the disclosure, the association relationship between the grid region and the POIs is established, and the grid cells with preset sizes and containing the POIs of the target types are screened by scanning in the geographic space region, so that point location resources and flow are mainly decoupled, and grid searching can be accelerated by grid division.

Step 202, determining the score of each grid cell according to the number of POIs of each POI type contained in each grid cell.

In an optional embodiment of the present disclosure, for each grid cell, the POI types included in the grid cell and the number of POIs of each POI type may be counted, and a value obtained by accumulating the numbers of POIs of different POI types is used as a score of the grid cell. For example, if one grid cell includes 2 schools and 1 shopping malls, the total number of POIs included (2 +1= 3) is used as the score of the grid cell.

In an optional embodiment of the present disclosure, for each grid cell, the number of POIs of each POI type contained in the grid cell may be obtained; and then, determining the score of each grid unit according to preset scores corresponding to different POI types and the number of POIs of each POI type contained in the grid unit. For example, the preset scores corresponding to different POI types are: 1 point of school, 0.8 point of house, 0.6 point of office building and 0.5 point of market, and if one grid unit comprises 2 schools and 1 market, the corresponding score of the grid unit is as follows: 1 + 2+0.5 +1= 2.5 min.

Step 203, determining the plurality of geographic grids from the plurality of grid cells according to the score of each grid cell.

In the embodiment of the present disclosure, after the score corresponding to each grid cell is determined, a plurality of geographic grids may be determined from the plurality of grid cells according to the score corresponding to each grid cell.

In an optional embodiment of the present disclosure, a preset numerical value may be preset as the number of geographic grids to be acquired, and after the score of each grid unit is determined, grid units with preset numerical values may be selected from the grid units as the determined multiple geographic grids according to the order of the scores from high to low, that is, the grid unit with the preset numerical value with the highest score is selected as the geographic grid.

In an optional implementation manner of the present disclosure, the advertisement placement request input by the user may include a budget advertisement bit number, where the budget advertisement bit number is a number of advertisement bits that the user desires to recommend. Therefore, in the embodiment of the present disclosure, when determining a plurality of geographic grids from a plurality of grid units, the number of candidate advertisement spots may be determined according to the budget advertisement spot number and a preset multiple; and then, the grid cells are sorted according to the order of the scores from high to low, the total number of POI of the target type contained in each grid cell is sequentially accumulated from the first sorted grid cell until the total number reaches the candidate advertisement position number, and the currently accumulated target grid cell is determined as the geographic grids.

The preset multiple can be preset according to actual requirements, for example, the preset multiple can be set to be 6 times, 10 times and the like.

For example, assuming that the budget ad spot input by the user is 20 and the preset multiple is 5, the candidate ad spot is determined to be 100, i.e., the number of POIs of the target type included in the multiple geographic grids should be not less than 100. In the embodiment of the present disclosure, after the score of each grid cell is determined, the grid cells are ranked in order from high to low, and starting from the first grid cell ranked, the total number of POIs of the target type contained in the grid cell and the grid cells after the grid cell are sequentially accumulated, and when the total number reaches 100, the currently accumulated target grid cell is determined as a plurality of geographic grids, that is, the grid cell containing the POI of the 100 th target type and the grid cells before the POI are determined as a plurality of geographic grids. For example, assuming that the number of POIs of the target type included in the first grid cell after the ranking is added, when the total number of POIs of the target type reaches 100 when the POI is added to the 35 th grid cell after the ranking, the 35 grid cells from 1 st to 35 th in the ranking are determined as the geographic grid. Therefore, the grid cells which have higher scores and contain POI of the target type can be determined to be a plurality of geographic grids, and the finally recommended advertisement space can be ensured to meet the quantity requirement of the user.

In addition, in an alternative embodiment of the present disclosure, if the total number of POIs of the target type included in all grid cells is accumulated to be still less than the number of candidate advertisement slots, all grid cells are determined to be the geographic grid.

According to the method for recommending the offline advertising space, the multiple grid units which are preset in size and contain the POI of the target type are obtained, the score of each grid unit is determined according to the number of the POI of each POI type contained in each grid unit, and then the multiple geographic grids are determined from the multiple grid units according to the score of each grid unit, so that the purpose that each grid unit is scored is achieved, the geographic grids are screened from the grid units according to the scores and used for being subsequently associated with the ordinary station labels of the online users, the number of the geographic grids which need to be compared with the ordinary station positions can be reduced, and therefore the comparison speed and the comparison efficiency are improved.

By adopting the scheme disclosed by the invention, the online data, flow, marketing resources and the like can be quickly and conveniently associated and mapped with the offline real physical space, and accurate marketing position selection of any spatial position of the offline advertisement is realized.

The exemplary embodiment of the present disclosure also provides a recommendation device for offline advertising spots. Fig. 3 shows a schematic block diagram of a recommendation apparatus for an offline advertising spot according to an exemplary embodiment of the present disclosure, and as shown in fig. 3, the recommendation apparatus 30 for an offline advertising spot includes: a first obtaining module 310, a second obtaining module 320, a third obtaining module 330, a clustering module 340, a first determining module 350, a second determining module 360, and a third determining module 370.

The first obtaining module 310 is configured to obtain an advertisement delivery request input by a user, where the advertisement delivery request includes an advertisement type of an advertisement to be delivered and a target type of a POI delivering the advertisement to be delivered;

a second obtaining module 320, configured to obtain user portrait data and behavior trajectory data of multiple online users;

a third obtaining module 330, configured to obtain advertisement preference degrees of the online users for the advertisement types according to the user portrait data by using a pre-trained advertisement preference estimation model;

the clustering module 340 is configured to cluster the behavior trajectory data based on a preset clustering algorithm to obtain frequent house tags of the multiple online users;

a first determining module 350, configured to determine, according to the advertisement preference degrees of the multiple online users and the permanent location position corresponding to the permanent location tag, an advertisement preference degree of a candidate geographic grid including the permanent location position;

a second determining module 360, configured to determine a target geographic grid according to the advertisement preference of the candidate geographic grid;

a third determining module 370 for determining the target POI of the target type contained in the target geographic grid as the offline advertising spot.

Optionally, the first determining module 350 is further configured to:

determining a candidate geographical grid containing the common station position from a plurality of geographical grids according to the common station position corresponding to the common station label;

and accumulating the advertisement preference degrees of the online users contained in the candidate geographic grids aiming at each candidate geographic grid to obtain the advertisement preference degree of each candidate geographic grid.

Optionally, the apparatus 30 for recommending offline advertisement spots further includes:

the fourth acquisition module is used for acquiring a plurality of grid units which are preset in size and contain the POI of the target type;

a fourth determining module, configured to determine a score of each grid cell according to the number of POIs of each POI type included in each grid cell;

a fifth determining module for determining the plurality of geographic grids from the plurality of grid cells based on the score of each of the grid cells.

Optionally, the fourth obtaining module is further configured to:

dividing a geospatial area into a plurality of grid areas based on a geospatial point index algorithm, wherein the grid areas are associated with POIs positioned in the grid areas;

screening candidate grid areas containing POI of the target type from the plurality of grid areas;

under the condition that the area of the candidate grid region is larger than a preset size area threshold, segmenting the candidate grid region to obtain a plurality of sub-grids;

determining a first sub-grid of the plurality of sub-grids as the grid unit if the area of the first sub-grid is not larger than the preset area threshold and contains the POI of the target type, wherein the first sub-grid is any one of the plurality of sub-grids;

and under the condition that the area of a second sub-grid in the plurality of sub-grids is larger than the preset area threshold and contains the POI of the target type, continuously dividing the second sub-grid until a grid unit which is not larger than the preset area threshold and contains the POI of the target type is obtained, wherein the second sub-grid is any one of the plurality of sub-grids except the first sub-grid.

Optionally, the fourth determining module is further configured to:

aiming at each grid cell, acquiring the number of POI of each POI type contained in the grid cell;

and determining the score of each grid cell according to preset scores corresponding to different POI types and the number of POIs of each POI type contained in the grid cell.

Optionally, the advertisement delivery request further includes a budget advertisement bit number; the fifth determining module is further configured to:

determining the number of candidate advertisement positions according to the budget advertisement positions and a preset multiple;

and sequencing the grid cells according to the sequence of scores from high to low, sequentially accumulating the total number of POI of the target type contained in each grid cell from the first-sequenced grid cell until the total number reaches the number of the candidate advertisement positions, and determining the currently accumulated target grid cell as the multiple geographic grids.

Optionally, the apparatus 30 for recommending offline advertisement spots further includes: a training module; the training module is configured to:

acquiring an advertisement delivery record of delivering advertisements to sample users in an online advertisement delivery scene and user portrait data of the sample users;

analyzing the advertisement putting records to obtain historical put advertisements of different advertisement types and operation data of the sample user on the historical put advertisements, wherein the operation data comprises clicks or non-clicks;

marking the historical advertisement according to the operation data of the sample user on the historical advertisement, and generating a sample advertisement;

constructing an incidence relation between the user portrait data of the sample user and the sample advertisements of different advertisement types, and generating a training sample set;

and training an initial network model based on the training sample set to obtain the advertisement preference estimation model.

The recommendation device for the offline advertisement space provided by the embodiment of the disclosure can execute any recommendation method for the offline advertisement space applicable to the electronic equipment provided by the embodiment of the disclosure, and has corresponding functional modules and beneficial effects of the execution method. Reference may be made to the description of any method embodiment of the disclosure that may not be described in detail in the embodiments of the apparatus of the disclosure.

An exemplary embodiment of the present disclosure also provides an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor. The memory stores a computer program executable by the at least one processor, the computer program when executed by the at least one processor is for causing the electronic device to perform a method of recommending offline advertising spots according to an embodiment of the present disclosure.

The exemplary embodiments of the present disclosure also provide a non-transitory computer readable storage medium storing a computer program, wherein the computer program, when executed by a processor of a computer, is adapted to cause the computer to perform a recommendation method of an offline ad spot according to an embodiment of the present disclosure.

The disclosed exemplary embodiments also provide a computer program product comprising a computer program, wherein the computer program, when executed by a processor of a computer, is adapted to cause the computer to perform a method of recommending offline ad slots according to an embodiment of the present disclosure.

Referring to fig. 4, a block diagram of a structure of an electronic device 1100, which may be a server or a client of the present disclosure, which is an example of a hardware device that may be applied to aspects of the present disclosure, will now be described. Electronic device is intended to represent various forms of digital electronic computer devices, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 4, the electronic device 1100 includes a computing unit 1101, which can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 1102 or a computer program loaded from a storage unit 1108 into a Random Access Memory (RAM) 1103. In the RAM 1103, various programs and data necessary for the operation of the device 1100 may also be stored. The calculation unit 1101, the ROM 1102, and the RAM 1103 are connected to each other by a bus 1104. An input/output (I/O) interface 1105 is also connected to bus 1104.

A number of components in electronic device 1100 connect to I/O interface 1105, including: an input unit 1106, an output unit 1107, a storage unit 1108, and a communication unit 1109. The input unit 1106 may be any type of device capable of inputting information to the electronic device 1100, and the input unit 1106 may receive input numeric or character information and generate key signal inputs related to user settings and/or function controls of the electronic device. Output unit 1107 may be any type of device capable of presenting information and may include, but is not limited to, a display, speakers, a video/audio output terminal, a vibrator, and/or a printer. Storage unit 1108 may include, but is not limited to, a magnetic or optical disk. The communication unit 1109 allows the electronic device 1100 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers and/or chipsets, such as bluetooth (TM) devices, wiFi devices, wiMax devices, cellular communication devices, and/or the like.

The computing unit 1101 can be a variety of general purpose and/or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 1101 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and the like. The calculation unit 1101 performs the respective methods and processes described above. For example, in some embodiments, the recommendation method for offline ad slots may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 1108. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 1100 via the ROM 1102 and/or the communication unit 1109. In some embodiments, the computing unit 1101 may be configured to perform the recommendation method for the offline ad spot by any other suitable means (e.g., by means of firmware).

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

As used in this disclosure, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

Claims

1. A method for recommending offline advertising spots, wherein the method comprises:

clustering the behavior track data based on a preset clustering algorithm to obtain frequent site labels of the multiple online users;

2. The method for recommending an offline advertisement slot according to claim 1, wherein the determining the advertisement preference of the candidate geographic grid including the regular site location according to the advertisement preference of the online users and the regular site location corresponding to the regular site tag comprises:

3. The method for recommending an offline ad spot according to claim 2, wherein said method further comprises:

acquiring a plurality of grid units with preset sizes and containing POI of the target type;

determining the score of each grid cell according to the number of POIs of each POI type contained in each grid cell;

determining the plurality of geographic grids from the plurality of grid cells based on the score for each of the grid cells.

4. The method for recommending offline advertising spots as recited in claim 3, wherein said obtaining a plurality of grid cells of a preset size and containing POIs of said target type comprises:

under the condition that the area of the candidate grid region is larger than a preset area threshold value, segmenting the candidate grid region to obtain a plurality of sub-grids;

and under the condition that the area of a second sub-grid in the sub-grids is larger than the preset area threshold and contains the POI of the target type, continuously dividing the second sub-grid until a grid unit which is not larger than the preset area threshold and contains the POI of the target type is obtained, wherein the second sub-grid is any sub-grid except the first sub-grid in the sub-grids.

5. The method for recommending offline advertising spots as recited in claim 3, wherein said determining the score of each of said grid cells according to the number of POIs of each POI type contained in each of said grid cells comprises:

6. The method for recommending offline ad spots of claim 3, wherein said ad placement request further comprises a budget ad spot number;

and wherein said determining a plurality of geographic grids from said plurality of grid cells based on the score of each of said grid cells comprises:

7. The method for recommending offline ad slots as recited in any one of claims 1-6, wherein said advertisement preference estimation model is trained by:

8. An apparatus for recommending offline advertising spots, wherein the apparatus comprises:

the system comprises a first acquisition module, a first display module and a first display module, wherein the first acquisition module is used for acquiring an advertisement putting request input by a user, and the advertisement putting request comprises an advertisement type of an advertisement to be put and a target type of a POI (point of interest) for putting the advertisement to be put;

the first determining module is used for determining the advertisement preference of the candidate geographic grid containing the ordinary station position according to the advertisement preference of the online users and the ordinary station position corresponding to the ordinary station label;

the second determining module is used for determining the target geographic grid according to the advertisement preference of the candidate geographic grid;

9. An electronic device, comprising:

a processor; and

a memory for storing a program, wherein the program is stored in the memory,

wherein the program comprises instructions which, when executed by the processor, cause the processor to perform the method of recommending offline ad slots of any of claims 1-7.

10. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of recommending an offline ad spot according to any one of claims 1-7.