CN120707215A

CN120707215A - Method, device, electronic equipment and readable storage medium for acquiring and pushing advertisement

Info

Publication number: CN120707215A
Application number: CN202410347126.XA
Authority: CN
Inventors: 纪德辉; 马海航; 孙立顺; 孟祥民; 丁健航; 高彬斌; 袁彬; 刘志远; 周亮; 余明星
Original assignee: Beijing Xiaomi Mobile Software Co Ltd
Current assignee: Beijing Xiaomi Mobile Software Co Ltd
Priority date: 2024-03-25
Filing date: 2024-03-25
Publication date: 2025-09-26

Abstract

The disclosure relates to a method, a device, an electronic device and a readable storage medium for acquiring and pushing advertisements. The method for acquiring the advertisements comprises the steps of acquiring an evaluation result of at least one object category, wherein the evaluation result comprises preference information of a user for each object category, generating a target advertisement acquisition request carrying the evaluation result, sending the target advertisement acquisition request to a server, and acquiring a target advertisement set obtained by responding to the target advertisement acquisition request and screening based on the evaluation result by the server. The method and the device can effectively ensure that the privacy data of the user are not revealed, and meanwhile, can accurately push advertisements to the user based on the target advertisement acquisition request, ensure the advertisement recommendation efficiency, and further can effectively solve the technical problem that the advertisement recommendation in the related technology cannot simultaneously ensure the privacy of the user and the advertisement recommendation efficiency.

Description

Method, device, electronic equipment and readable storage medium for acquiring and pushing advertisement

Technical Field

The present disclosure relates to the field of communications technologies, and in particular, to a method, an apparatus, an electronic device, and a readable storage medium for acquiring and pushing advertisements.

Background

With international importance on privacy, various countries are gradually introduced to limit laws and regulations for acquiring behavior information of users, and use and storage requirements of personal data are strictly defined.

In the related art, if the recommendation efficiency of the advertisement system needs to be ensured, behavior information of the user needs to be acquired, so that the privacy of the user cannot be effectively protected, that is, the recommendation efficiency of the advertisement system and the privacy of the user cannot be ensured in the related art.

Therefore, the method for realizing advertisement recommendation in the related art has the technical problem that the privacy of the user and the advertisement recommendation efficiency cannot be ensured at the same time.

Disclosure of Invention

The present disclosure provides methods, apparatuses, electronic devices, and readable storage media for acquiring and pushing advertisements to address deficiencies in the related art.

According to a first aspect of an embodiment of the present disclosure, a method for acquiring an advertisement is provided, the method including:

obtaining an evaluation result of at least one object category, wherein the evaluation result comprises preference information of a user for each object category;

Generating a target advertisement acquisition request carrying the evaluation result, and sending the target advertisement acquisition request to a server;

And acquiring a target advertisement set which is obtained by the server responding to the target advertisement acquisition request and screening based on the evaluation result.

Optionally, the method further comprises:

Acquiring object interaction information of a terminal, wherein the object interaction information comprises interaction information between a user and each object on the terminal;

And determining the evaluation result based on the object interaction information.

Optionally, the determining the evaluation result based on the object interaction information includes:

processing the object interaction information according to a preset period to obtain the evaluation result, and/or,

And under the condition that the object interaction information indicates that at least one target object of the terminal generates preset interaction behavior, processing the object interaction information to obtain the evaluation result.

Optionally, the generating a target advertisement acquisition request carrying the evaluation result includes:

Acquiring an original advertisement acquisition request for requesting acquisition of an advertisement from a server;

And generating the target advertisement acquisition request according to the original advertisement acquisition request, the processing strategy mark corresponding to the terminal and the evaluation result, wherein the processing strategy mark is used for indicating whether the server needs to screen and obtain the target advertisement set based on the evaluation result.

Optionally, the object comprises at least one of:

an application, a good or a service.

According to a second aspect of embodiments of the present disclosure, there is also provided a method of pushing an advertisement, the method including:

Acquiring a target advertisement acquisition request from a terminal, wherein the target advertisement acquisition request carries an evaluation result, and the evaluation result comprises preference information of a user of the terminal for each object class;

Responding to the target advertisement acquisition request, and screening and obtaining a target advertisement set based on the evaluation result;

Pushing the target advertisement set to the terminal.

Optionally, the screening to obtain the target advertisement set based on the evaluation result includes:

sorting all candidate advertisements according to the evaluation result to obtain sorting results corresponding to all candidate advertisements, wherein the candidate advertisements are advertisements for popularizing candidate objects;

screening target advertisements from all candidate advertisements according to the sorting result;

generating the target advertisement set containing all the target advertisements.

Optionally, the ranking all the candidate advertisements according to the evaluation result to obtain ranking results corresponding to all the candidate advertisements includes:

Determining the terminal score corresponding to each candidate advertisement according to the evaluation result and the object category to which each candidate advertisement belongs;

Determining estimated advertising revenue corresponding to each candidate advertisement;

determining a final score corresponding to each candidate advertisement according to the terminal score corresponding to each candidate advertisement and the estimated advertisement income corresponding to each candidate advertisement;

and sorting all the candidate advertisements according to the final scores corresponding to each candidate advertisement to obtain the sorting result.

Optionally, the method further comprises:

Determining a processing strategy mark in the target advertisement acquisition request;

Executing a jump operation for jumping to the step of responding to the target advertisement acquisition request and screening and obtaining a target advertisement result based on the evaluation result under the condition that the value of the processing strategy mark is judged to be a first value;

and stopping executing the subsequent steps when the value of the processing strategy mark is determined to be the second value.

According to a third aspect of the embodiments of the present disclosure, there is also provided an apparatus for acquiring an advertisement, including:

the first acquisition module is used for acquiring an evaluation result of at least one object category, wherein the evaluation result comprises preference information of a user on each object category;

The generation module is used for generating a target advertisement acquisition request carrying the evaluation result and sending the target advertisement acquisition request to a server;

And the second acquisition module is used for acquiring the target advertisement set which is obtained by the server through screening based on the response to the target advertisement acquisition request and the evaluation result.

Optionally, the apparatus further comprises:

the third acquisition module is used for acquiring object interaction information of a terminal, wherein the object interaction information comprises interaction information between a user and each object on the terminal;

And the result determining module is used for determining the evaluation result based on the object interaction information.

Optionally, the result determining module is configured to:

Optionally, the generating module is configured to:

According to a fourth aspect of embodiments of the present disclosure, there is also provided an apparatus for pushing an advertisement, including:

The terminal comprises an acquisition module, a target advertisement acquisition module and a display module, wherein the acquisition module is used for acquiring a target advertisement acquisition request from a terminal, wherein the target advertisement acquisition request carries an evaluation result, and the evaluation result comprises preference information of a user of the terminal on each object class;

The screening module is used for responding to the target advertisement acquisition request and screening and obtaining a target advertisement set based on the evaluation result;

and the pushing module is used for pushing the target advertisement set to the terminal.

Optionally, the screening module includes:

the ranking unit is used for ranking all candidate advertisements according to the evaluation result to obtain ranking results corresponding to all candidate advertisements, wherein the candidate advertisements are advertisements used for popularizing candidate objects;

The screening unit is used for screening target advertisements from all candidate advertisements according to the sorting result;

and the generation unit is used for generating the target advertisement set containing all the target advertisements.

Optionally, the sorting unit is configured to:

Optionally, the device further comprises a judging module, wherein the judging module is used for:

According to a fifth aspect of embodiments of the present disclosure, there is also provided an electronic device, comprising a processor;

a memory for storing processor-executable instructions;

Wherein the processor implements any of the methods described above by executing the executable instructions.

According to a sixth aspect of the disclosed embodiments, there is also provided a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method of any of the embodiments described above.

The technical scheme provided by the embodiment of the disclosure can comprise the following beneficial effects:

According to the method for acquiring the advertisements, provided by the embodiment of the invention, the evaluation result of at least one object category is acquired, wherein the evaluation result comprises preference information of a user for each object category, a target advertisement acquisition request carrying the evaluation result is generated and sent to the server, the target advertisement acquisition request is acquired, the server screens out a target advertisement set based on the evaluation result, the evaluation result can be directly generated on the user side, the target advertisement acquisition request carrying the evaluation result is generated, and therefore the server can determine the target advertisement acquisition request without acquiring privacy data of the user to determine the preference information, so that the privacy data of the user can be effectively ensured not to be revealed, meanwhile, advertisements can be accurately pushed to the user based on the target advertisement acquisition request, the advertisement recommendation efficiency is ensured, and the technical problem that the advertisement recommendation in the related technology cannot be ensured simultaneously for privacy of the user and the advertisement recommendation efficiency is effectively solved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and other drawings may be obtained according to these drawings without inventive effort to a person of ordinary skill in the art.

Fig. 1 is a schematic flow chart diagram illustrating a method of acquiring advertisements according to an embodiment of the present disclosure.

Fig. 2 is a schematic flow diagram illustrating another method of acquiring advertisements according to an embodiment of the present disclosure.

Fig. 3 is a schematic flow chart diagram illustrating another method of acquiring advertisements according to an embodiment of the present disclosure.

Fig. 4 is a schematic flow chart diagram illustrating a method of pushing advertisements, according to an embodiment of the present disclosure.

Fig. 5 is a schematic flow chart diagram illustrating another method of pushing advertisements according to an embodiment of the present disclosure.

Fig. 6 is a schematic flow chart diagram illustrating another method of pushing advertisements according to an embodiment of the present disclosure.

Fig. 7 is a schematic flow chart diagram illustrating one embodiment of retrieving and pushing advertisements in accordance with embodiments of the present disclosure.

Fig. 8 is a schematic block diagram illustrating an apparatus for acquiring advertisements according to an embodiment of the present disclosure.

Fig. 9 is a schematic block diagram of an apparatus for pushing advertisements, shown in accordance with an embodiment of the present disclosure.

Fig. 10 is a schematic structural view of an electronic device shown according to an embodiment of the present disclosure.

Fig. 11 is a schematic block diagram illustrating an apparatus for acquiring advertisements according to an embodiment of the present disclosure.

Detailed Description

The following description of the technical solutions in the embodiments of the present disclosure will be made clearly and completely with reference to the accompanying drawings in the embodiments of the present disclosure, and it is apparent that the described embodiments are only some embodiments of the present disclosure, not all embodiments. Based on the embodiments in this disclosure, all other embodiments that a person of ordinary skill in the art would obtain without making any inventive effort are within the scope of protection of this disclosure.

The terminology used in the embodiments of the disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the embodiments of the disclosure. As used in this disclosure of embodiments and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.

It should be understood that although the terms first, second, third, etc. may be used in embodiments of the present disclosure to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, the first information may also be referred to as second information, and similarly, the second information may also be referred to as first information, without departing from the scope of embodiments of the present disclosure. The term "if" as used herein may be interpreted as "at..once" or "when..once" or "in response to a determination", depending on the context.

For purposes of brevity and ease of understanding, the terms "greater than" or "less than," "above," or "below" are used herein in describing the magnitude relationship. It will be understood by those skilled in the art that the term "greater than" also encompasses the meaning of "greater than or equal to," less than "also encompasses the meaning of" less than or equal to, "and that the term" greater than "encompasses the meaning of" greater than or equal to, "and" less than "also encompasses the meaning of" less than or equal to.

Fig. 1 is a schematic flow chart diagram illustrating a method of acquiring advertisements according to an embodiment of the present disclosure. The method for acquiring the advertisement shown in the embodiment may be executed by a terminal, where the terminal includes, but is not limited to, a mobile phone, a tablet computer, a wearable device, a sensor, an internet of things device, and other communication devices.

As shown in fig. 1, the method for acquiring advertisements may include the steps of:

Step S101, an evaluation result of at least one object category is obtained, wherein the evaluation result comprises preference information of a user for each object category.

Specifically, the evaluation result of at least one object category can be determined through object interaction information recorded when a user uses the terminal, the object category can be a category corresponding to each object, and the object can include, but is not limited to, an application, goods or services, and the like. Where the object is an application, the object categories may include, but are not limited to, game-type applications, educational-type applications, social-type applications, shopping-type applications, entertainment-type applications, and the like. Where the object is a commodity, the object category may include, but is not limited to, household items, food items, digital home appliances, household items, and the like. Where the object is a service, the object categories may include, but are not limited to, cloud computing services, cloud storage services, online promotional services, online live services, and the like.

The evaluation result of the at least one object category may be preference information indicating preferences for respective object categories of the at least one object category, and each object category corresponds to the preference information and may be used to indicate a degree of interest of the user in the preference information.

As shown in fig. 2, as an alternative embodiment, the evaluation result in step S101 may be determined by steps S201 and S202 as follows, including:

in step S201, object interaction information of the terminal is obtained, where the object interaction information includes interaction information between the user and each object on the terminal.

Specifically, the terminal in this embodiment may be one terminal device, or may be all terminal devices associated with one account, or may be a terminal device in the same network environment, or the like, and specifically may define, according to a usage scenario, a device included in the terminal.

The object interaction information of the terminal can be stored in an encrypted database of the terminal as encrypted data, the encrypted database is a database which can be accessed only by a certain authority, and further, the encrypted database can also be a database which can not be accessed by a remote server, so that the security of user privacy data is further improved.

Example 1, the manner in which the object interaction information is obtained may be described by taking the object as an application (i.e., app) as follows:

in this example, the object interaction information can be collected by an end intelligent program on the terminal, the end intelligent program refers to a software program running on the terminal and having a certain intelligent capability, and compared with a cloud intelligent program, the end intelligent program does not need to rely on internet connection and can locally perform data processing and decision making, so that intelligent equipment can perform intelligent decision making and interaction more independently, and better user experience is provided for users.

The terminal intelligent program does not collect advertisement ID (unique ID which can be reset by a user and is provided by Google Play service for advertisement service), only collects record data of an app installation sequence, a user app uninstallation sequence, a user app opening sequence, a user installed app list and the like of a terminal user in real time, and stores the record data in an encrypted database format in the terminal, and further, in order to avoid the change of user preference or the occupation of excessive memory space by the record data, the storage duration of the record data in the encrypted database can be set to be no more than 30 days. In addition, also due to memory usage issues, unnecessary raw data (e.g., data that cannot characterize user preferences, erroneous data, duplicate data, etc.) may be dynamically purged.

Alternatively, the list of object interaction item parameters (contained in the object interaction information) that need to be collected may include, but is not limited to, the following categories:

1. the user uses the behavior sequence of the apps, for example, which type of app is used in different time intervals, and further can determine the app used in each time interval by acquiring the opening and closing behaviors of each app, and in addition, the behavior sequence can be updated in real time.

2. The number of times and duration of the user using the app can be determined by using all time intervals corresponding to the app by the user (the number of times is the number of time intervals used by the app, which can effectively avoid the situation that the user performs short-term exit and reenters and is regarded as new once-used apps), for example, when each natural hour is taken as a time interval (for example, 10:00:00 to 10:59:59, 11:00:00 to 11:59:59, 12:00:00 to 12:59:59, and the like), and the time interval corresponding to the app includes 9:00:00 to 9:59:59 and 18:00:00 to 18:59:59, the app can be determined to correspond to two time intervals, and the duration of the app can be obtained by accumulation based on the single duration of each use of the app.

3. And (3) a behavior sequence of installing the apps by the user, namely determining a time interval corresponding to the installation time of each app.

4. The behavior sequence of the first launch app of the user, i.e. the time interval corresponding to the first launch of each app is determined.

5. And the behavior sequence of unloading the apps by the user, namely determining the time interval corresponding to the unloading moment of each app.

6. A list of apps installed by the user's handset.

7. User handset model, region, language, time, network, etc.

The terminal intelligent program on the terminal is adopted for data collection, so that the user data cannot be sent to the server, the risk of leakage of user privacy data in transmission is avoided, and the characteristic data collection, model reasoning and business logic are all completed on the terminal side, network interaction is not needed, and the user state can be perceived in real time.

The method for acquiring the object interaction information can be illustrated by taking the object as a commodity in the manner that 1. The clicking time of the user clicking the purchase link or the advertisement corresponding to each commodity and 2. The browsing time of the user browsing the purchase information or the advertisement corresponding to each commodity can be stored in the encryption database. And determining the clicking time and the browsing time as interaction information.

Step S202, determining an evaluation result based on the object interaction information.

Specifically, after the object interaction information is determined, an evaluation result can be determined by a method comprising the following steps that 1, target object interaction item parameters for determining the evaluation result can be determined from all object interaction item parameters;

2. And then determining scoring information corresponding to the interaction project parameters of each target object.

3. And integrating the scoring information (such as direct packaging, weighting and the like) to obtain the evaluation result.

For example, the evaluation result includes an object class number (i.e., a number corresponding to an object class one-to-one) of interest to the user and a weight corresponding to the object class, and, illustratively, when the object class is an educational class application and the corresponding weight is 0.2, the scoring information corresponding to the educational class application may be (educational class application, 0.2), and further, the sum of the weights corresponding to all the object classes is 1.

Step S102, generating a target advertisement acquisition request carrying an evaluation result, and sending the target advertisement acquisition request to a server.

Specifically, after the evaluation result is obtained, the evaluation result may be packaged together with an advertisement request (for requesting to obtain an advertisement from a server) to obtain a target advertisement obtaining request carrying the evaluation result, and the evaluation result may be used as a value of one or more fields in the target advertisement obtaining request to obtain the target advertisement obtaining request carrying the evaluation result.

After the targeted advertisement acquisition request is generated, the targeted advertisement acquisition request may be transmitted to the server through remote communication with the server.

Step S103, the acquisition server responds to the target advertisement acquisition request and screens the obtained target advertisement set based on the evaluation result.

Specifically, after receiving the target advertisement obtaining request from the terminal, the server determines that the advertisement required by the terminal needs to be recalled, so that the target advertisement obtaining request can be analyzed according to an analysis mode corresponding to the generation mode of the target advertisement obtaining request, and the evaluation result carried in the target advertisement obtaining request can be obtained.

After the server obtains the evaluation result, the server can recall the advertisement according to the preference information of the user on each object category in the evaluation result to obtain the target advertisement of the object category interested by the user, then obtain the target advertisement set comprising all the target advertisements, and finally send the target advertisement set to the terminal, so that the terminal can obtain the target advertisement set from the server.

According to the method and the device for obtaining the target advertisement, the evaluation result of at least one object category is obtained on the user side, wherein the evaluation result comprises preference information of a user for each object category, a target advertisement obtaining request carrying the evaluation result is generated and sent to the server, the server is obtained to screen a target advertisement set based on the evaluation result, and accordingly the evaluation result can be directly generated on the user side and the target advertisement obtaining request carrying the evaluation result is generated, therefore the server can determine the target advertisement obtaining request without collecting privacy data of the user to determine preference information, privacy data of the user can be effectively guaranteed not to be revealed, meanwhile advertisements can be accurately pushed to the user based on the target advertisement obtaining request, advertisement recommendation efficiency is guaranteed, and further the technical problem that privacy and advertisement recommendation efficiency of the user cannot be guaranteed simultaneously in advertisement recommendation in related technologies can be effectively solved.

As an alternative embodiment, step S202 in the foregoing embodiment is implemented by performing feature calculation on the object interaction information to obtain feature data, and transmitting the feature data into the interest level evaluation model to obtain preference information corresponding to each object category output by the interest level evaluation model.

Specifically, after the object interaction information is determined, feature data for attributes related to user preferences can be obtained by performing feature calculation on the object interaction information, then the feature data is transmitted into an interest evaluation model (for example, tensorflow lite, an open source deep learning framework of a tensorflow model running at a device end) preset by a terminal to perform calculation, preference information (for example, scores corresponding to each object category) which is output by the interest evaluation model and is used for representing the user to each object category is obtained, and after the preference information is obtained, all the preference information can be integrated to obtain an evaluation result.

Further, after the evaluation information is obtained, the evaluation information may be encrypted to obtain an encrypted data file, and stored.

Because users can start, exit, update and other operations on the app on the terminal at any time, the object interaction information may change at any time and the frequency of the change is very high, if the corresponding evaluation result is processed every time the object interaction information changes, the processing amount is very high, and because the computing resources of the terminal are limited, if the computing resources of the terminal are occupied for a long time for advertisement request, the computing resources available for other applications or programs are necessarily reduced, in addition, not every user operation will have a larger influence on the object interaction information, and further, the final advertisement request will not be greatly influenced. In order to overcome the above technical problems, as shown in fig. 3, as an alternative embodiment, the step S202 of determining the evaluation result based on the object interaction information in the foregoing embodiment may be implemented in a related manner of steps S301 and/or S302 as follows:

step S301, processing the object interaction information according to a preset period to obtain an evaluation result.

That is, the latest object interaction information may be processed according to a preset period, and the latest evaluation result may be obtained.

Alternatively, the preset period may be a period preset for obtaining the evaluation result according to the object interaction information processing, for example, 1 hour, 6 hours, 24 hours, etc., and specifically, the duration of the preset period may be selected according to the actual application scenario.

Further, when the object interaction information is processed according to the preset period, whether the object interaction information changes relative to the previous object interaction information can be judged, that is, whether the latest object interaction information changes relative to the previous object interaction information can be judged according to the preset period, when the latest object interaction information changes relative to the previous object interaction information, a corresponding evaluation result is generated based on the latest object interaction information, and when the latest object interaction information does not change relative to the previous object interaction information, the latest redemption high interaction information is not processed, that is, the evaluation result does not need to be generated.

In step S302, the object interaction information is processed to obtain an evaluation result when the object interaction information indicates that at least one target object of the terminal has a preset interaction behavior.

Specifically, the object interaction information may include interaction behavior of each object on the terminal, and the object with the preset interaction behavior is recorded as a target object. The preset interaction behavior may be a preset interaction behavior that needs to be focused on, and may include, but is not limited to, a user installing an application, a user uninstalling an application, a user first logging in an application, and so on. And when determining that the object interaction information indicates at least one target object of the terminal to generate any one of all preset interaction behaviors, processing the object interaction information to obtain an evaluation result.

By the method, the object interaction information does not need to be processed frequently, so that an evaluation result is obtained, and the computing resources of the terminal can be effectively saved.

As an alternative embodiment, the step S102 of generating the target advertisement acquisition request carrying the evaluation result in the foregoing embodiment may be implemented in a related manner, where the original advertisement acquisition request for requesting the server to acquire the advertisement is acquired, and the target advertisement acquisition request is generated according to the original advertisement acquisition request, the processing policy flag corresponding to the terminal, and the evaluation result, where the processing policy flag is used to indicate whether the server needs to filter to obtain the target advertisement set based on the evaluation result.

Specifically, in order to request an advertisement from a server, an original advertisement acquisition request capable of advertisement acquisition is required, the server recalls the advertisements in response to the original advertisement acquisition request, and one or more advertisements among the recalled advertisements are returned to the terminal. In this embodiment, since the evaluation result is required to be sent to the server, and the server is required to perform advertisement screening according to the evaluation result, the original advertisement acquisition request and a processing policy flag for indicating whether the server needs to perform advertisement screening based on the evaluation result are required in addition to the original advertisement acquisition request, while the target advertisement acquisition request is generated, the processing policy flag may be an identification information and is pre-defined with the server, and when the processing policy flag is included, the server needs to screen based on the evaluation result to obtain the target advertisement set.

As shown in fig. 4, according to another aspect of the embodiments of the present disclosure, there is also provided a method of pushing an advertisement, the method including the steps of:

in step S401, a target advertisement acquisition request from a terminal is acquired, where the target advertisement acquisition request carries an evaluation result, and the evaluation result includes preference information of a user of the terminal for each object class.

Step S402, screening and obtaining a target advertisement set based on the evaluation result.

Step S403, pushing the target advertisement set to the terminal.

Specifically, the advertisement pushing method in the embodiment can be applied to a server. The terminal may determine an evaluation result of at least one object class by using object interaction information recorded when the terminal is used by a user, and the object class may be a class corresponding to each object. The terminal may obtain the target advertisement obtaining request carrying the evaluation result by packaging the evaluation result together with the advertisement request (for requesting the server to obtain the advertisement), and may obtain the target advertisement obtaining request carrying the evaluation result by using the evaluation result as a value of one or more fields in the target advertisement obtaining request. After the terminal generates the target advertisement acquisition request, the target advertisement acquisition request can be sent to the server through remote communication with the server.

After receiving the target advertisement obtaining request from the terminal, the server can analyze the target advertisement obtaining request according to an analysis mode corresponding to the generation mode of the target advertisement obtaining request, so that the evaluation result carried in the target advertisement obtaining request can be obtained.

After the server obtains the evaluation result, the server can recall the advertisement according to the preference information of the user on each object category in the evaluation result to obtain the target advertisement of the object category interested by the user, then obtain the target advertisement set comprising all the target advertisements, and finally send the target advertisement set to the terminal.

The method and the device have the advantages that only the target advertisement acquisition request from the terminal is acquired through the server, the generation of the target advertisement acquisition request is realized on the terminal, therefore, the server can determine the target advertisement acquisition request without collecting privacy data of the terminal to determine preference information, privacy data of a user can be effectively guaranteed not to be revealed, meanwhile, advertisements can be accurately pushed to the user based on the target advertisement acquisition request, advertisement recommendation efficiency is guaranteed, and further the technical problem that the method for realizing advertisement recommendation in the related technology cannot guarantee privacy of the user and advertisement recommendation efficiency is effectively solved.

As shown in fig. 5, as an alternative embodiment, step S402 in the foregoing embodiment may be implemented in a manner related to steps S501 to S503 as follows to filter out a target advertisement set based on the evaluation result:

Step S501, sorting all candidate advertisements according to the evaluation result to obtain sorting results corresponding to all candidate advertisements, wherein the candidate advertisements are advertisements for popularizing candidate objects.

Specifically, since the evaluation result includes preference information of the user of the terminal for each object category, all candidate advertisements can be ranked according to the preference information, and a ranking result is obtained.

The candidate advertisements may be advertisements that the advertiser requests to be exposed to, and may be ranked according to the preference degree indicated by the preference information, and the ranking result may be a result of ranking all candidate advertisements in order of preference program from high to low, or a result of ranking all candidate advertisements in order of preference program from low to high.

Step S502, screening target advertisements from all candidate advertisements according to the sorting result.

Specifically, after the ordering result is determined, the target advertisement with high target number before the preference degree can be screened out from all candidate advertisements by determining the target number of advertisements to be pushed to the user.

In step S503, a target advertisement set containing all target advertisements is generated.

Specifically, after screening to obtain all target advertisements, the target advertisement sets can be obtained by packaging all target advertisements.

By the method, the implementation mode capable of rapidly screening the advertisements and selecting the advertisements meeting the evaluation results is provided, so that the finally generated target advertisement set can effectively meet the preference of the user.

As shown in fig. 6, as an alternative embodiment, the ranking of all the candidate advertisements according to the evaluation result in step S501 in the foregoing embodiment may be implemented in a manner related to steps S601 to S604 as follows, to obtain ranking results corresponding to all the candidate advertisements, including:

And step S601, determining the terminal score corresponding to each candidate advertisement according to the evaluation result and the object category to which each candidate advertisement belongs.

Specifically, the evaluation result includes preference information of the user of the terminal for each object class, and each preference information may have a corresponding terminal score, so each object class may have a corresponding terminal score. Alternatively, the terminal score may be a score for characterizing the preference degree indicated by the preference information, and further, the higher the terminal score, the higher the preference degree indicated by the preference information.

Based on this, the terminal score corresponding to each object category may be determined as the terminal score of each candidate advertisement according to the object category of each candidate advertisement.

Step S602, determining estimated advertisement revenue corresponding to each candidate advertisement.

Specifically, the estimated advertisement income of each candidate advertisement can be determined by acquiring the corresponding quotation of each candidate advertisement from the advertisement bidding platform.

Step S603, determining a final score corresponding to each candidate advertisement according to the terminal score corresponding to each candidate advertisement and the estimated advertisement income corresponding to each candidate advertisement.

Specifically, when pushing the advertisement, not only the preference of the user but also the profit of the advertisement need to be considered, so when determining the terminal score corresponding to each candidate advertisement, the terminal score and the estimated advertisement income need to be combined, and optionally, the final score (rankscore) can be determined by adopting the following two formulas:

equation 1, rankscore= peCPM +k sortweight;

equation 2, rankscore= peCPM × sortweight ×k;

wherein peCPM is estimated advertising income, sortweight is terminal scoring, K is adjustable weight adjustment factor, and weight adjustment of terminal scoring and terminal intelligent interest can be performed.

Alternatively, any one of the above formulas may be used to determine the final score, or the results determined by the above formulas 1 and 2 may be used to perform weighted calculation to obtain the final score.

Step S604, sorting all the candidate advertisements according to the final scores corresponding to each candidate advertisement, and obtaining a sorting result.

Specifically, after determining the final score corresponding to each candidate advertisement, all candidate advertisements may be ranked in order according to the score level, so as to obtain a ranking result. For example, the ranking may be performed in a manner that the final score is from high to low, resulting in a ranking result.

After the target advertisement obtaining request from the terminal is obtained in step S401, since it is not necessarily indicated that advertisement screening is required in the target advertisement obtaining request, what step is to be specifically performed later is to be determined according to the processing policy flag, so as an alternative embodiment, between the obtaining of the target advertisement obtaining request from the terminal in step S401 and the screening of the target advertisement set based on the evaluation result in step S402, the method further includes the steps of determining the processing policy flag in the target advertisement obtaining request, executing a jump operation for jumping to the step in response to the target advertisement obtaining request and obtaining the target advertisement result based on the screening of the evaluation result in the case that the value of the processing policy flag is determined to be the first value, and stopping executing the subsequent steps in the case that the value of the processing policy flag is determined to be the second value.

That is, after the target advertisement acquisition request is acquired, the processing policy flag may be determined therefrom, and the value of the processing policy flag may be read and judged as the first value or the second value.

The first value may be a value for indicating that advertisement screening is required according to the evaluation result, and the second value may be a value for indicating that advertisement screening is not required according to the evaluation result, and exemplary, the first value may be 1, and the second value may be 0.

In the case where it is determined that the value of the processing policy flag is the first value, that is, the advertisement needs to be screened according to the evaluation result, the jump operation for jumping to step S402 may be performed, and in the case where it is determined that the value of the processing policy flag is the second value, the subsequent steps S402 and S403 are stopped, and the advertisement screening may be performed by acquiring the privacy data from the terminal conventionally, and the screened advertisement may be pushed to the terminal.

As shown in fig. 7, taking a mobile phone as a terminal and taking an app as an object, an embodiment of acquiring and pushing advertisements by applying the method described in any of the foregoing embodiments is provided:

1. intelligent data processing strategy for mobile phone client

1.1, Data collection stage:

The method comprises the steps that after a user interacts with an app on a mobile phone, the object interaction information is updated, in the scheme, the mobile phone can collect the privacy data through an end intelligent program, the end intelligent program does not collect advertisement IDs (unique IDs (which can be reset by the user) provided by Google Play service aiming at advertisement services), only various object interaction project parameters such as an app list installed on the mobile phone user mobile phone, a behavior sequence of unloading the app by the user, a behavior sequence of starting the app for the first time by the user, a behavior sequence of installing the app by the user and the like are collected in real time, the obtained object interaction information is stored in user equipment in an encrypted database format, and the object interaction information is stored for no more than 30 days. In addition, the client may dynamically purge unnecessary raw data in view of memory issues.

The list of object interaction item parameters (contained in the object interaction information) that need to be collected may include, but is not limited to, the following categories:

(1) The user uses the behavior sequence of the apps, for example, which type of app is used in different time intervals, and further can determine the app used in each time interval by acquiring the opening and closing behaviors of each app, and in addition, the behavior sequence can be updated in real time.

(2) The number of times and duration of the user using the app can be determined by using all time intervals corresponding to the app by the user (the number of times is the number of time intervals used by the app, which can effectively avoid the situation that the user performs short-term exit and reenters and is regarded as new once-used apps), for example, when each natural hour is taken as a time interval (for example, 10:00:00 to 10:59:59, 11:00:00 to 11:59:59, 12:00:00 to 12:59:59, and the like), and the time interval corresponding to the app includes 9:00:00 to 9:59:59 and 18:00:00 to 18:59:59, the app can be determined to correspond to two time intervals, and the duration of the app can be obtained by accumulation based on the single duration of each use of the app.

(3) And (3) a behavior sequence of installing the apps by the user, namely determining a time interval corresponding to the installation time of each app.

(4) The behavior sequence of the first launch app of the user, i.e. the time interval corresponding to the first launch of each app is determined.

(5) And the behavior sequence of unloading the apps by the user, namely determining the time interval corresponding to the unloading moment of each app.

(6) A list of apps installed by the user's handset.

(7) User handset model, region, language, time, network, etc.

The data collection through the terminal has the advantages that firstly, user data cannot be sent to the server, the risk that user privacy data are revealed in transmission is avoided, secondly, feature data collection, model reasoning and business logic are all completed on the terminal side, network interaction is not needed, and user states can be perceived in real time.

1.2, Object interaction information processing and model calculation stage:

After the object interaction information is collected, the object interaction information is subjected to feature calculation to obtain feature data, the feature data can be stored, then the feature data is transmitted to tensorflow lite (namely, an intention understanding engine, namely, the interest evaluation model described in the previous embodiment) to calculate, the interest scores (namely, preference information) of various apps of a user are obtained, the interest scores are stored in an encrypted data file, and when the behavior of the user changes (namely, when the object interaction information changes), the interest scores are updated in real time. The model calculation adopts two modes of timing calculation and instant calculation. The timing calculation means that whether the feature data is updated or not compared with the data used for calculation last time (i.e. a preset period) is detected, if so, the model is triggered to calculate, and the instant calculation means that the tensorflow lite calculation is triggered when the preset interaction behavior (such as user installation application, user uninstallation application, user first login application, etc.) is generated.

1.3, Data transmission stage:

When the mobile phone needs to make an advertisement request, the mobile phone can make an assembly of the advertisement request according to the evaluation result to obtain a target advertisement acquisition request, and then the target advertisement acquisition request is sent to an advertisement bidding platform of a server, so that the real-time evaluation result is sent to the server, and the detailed format of each preference information in the evaluation result can be that app number+app corresponding weight of interest of a user.

2. The server performs an advertisement rearrangement policy:

2.1, after the server recalls the advertisement, the advertisement is rearranged:

When the advertisement request contains a processing strategy mark, an intelligent reordering link of the end is added to an advertisement engine in the advertisement system, the intelligent reordering of the end is an evaluation result uploaded by using a mobile phone, advertisement weight is increased for advertisements interested by a user, after reordering, an advertisement list obtained by ordering is required to be filtered (namely, advertisements which do not meet the requirement are deleted), and cutoff is carried out (namely, advertisements with the required advertisement quantity are selected), so that a target advertisement set interested by the user is finally screened and obtained.

Compared with the traditional advertisement system, the intelligent reordering link is added, the final ordering of the advertisement is directly interfered according to the interest classification of the real-time request, the method has the advantages that the real-time evaluation result of the user can be used, compared with the traditional advertising system with T+1 (T is the current moment and T+1 is the next moment), the real-time rearrangement can be higher in recommendation accuracy for users, and the distribution efficiency of the whole advertising system can be improved.

2.2, Rearrangement formula:

the final score (rankscore) is determined for the rearrangement unit by introducing the following two formulas:

equation 1, rankscore= peCPM +k sortweight;

equation 2, rankscore= peCPM × sortweight ×k;

3. Advertisement return

And packaging the target advertisement set on an advertisement bidding platform to obtain a packaging result (comprising the target advertisement set) meeting the requirements of the mobile phone end, and sending the packaging result to the terminal so as to facilitate the display and embedding of the terminal.

As shown in fig. 8, corresponding to the foregoing embodiment of the method for acquiring an advertisement applied to a terminal, the present disclosure further provides an embodiment of an apparatus for acquiring an advertisement applied to a terminal, including:

a first obtaining module 81, configured to obtain an evaluation result of at least one object class, where the evaluation result includes preference information of a user for each object class;

A generating module 82, configured to generate a target advertisement acquisition request carrying an evaluation result, and send the target advertisement acquisition request to the server;

A second obtaining module 83, configured to obtain a target advertisement set obtained by filtering the server in response to the target advertisement obtaining request based on the evaluation result.

As an alternative embodiment, the apparatus for acquiring advertisements applied to a terminal further includes:

the third acquisition module is used for acquiring object interaction information of the terminal, wherein the object interaction information comprises interaction information between a user and each object on the terminal;

And the result determining module is used for determining an evaluation result based on the object interaction information.

As an alternative embodiment, the third acquisition module is configured to:

Performing feature calculation on the object interaction information to obtain feature data;

and transmitting the characteristic data into an interest evaluation model to obtain preference information which is output by the interest evaluation model and corresponds to each object category.

As an alternative embodiment, the result determination module is configured to:

processing the object interaction information according to a preset period to obtain an evaluation result, and/or,

And under the condition that the object interaction information indicates at least one target object of the terminal to generate preset interaction behavior, processing the object interaction information to obtain an evaluation result.

As an alternative embodiment, the generation module 82 is configured to:

Generating a target advertisement acquisition request according to the original advertisement acquisition request, a processing strategy mark corresponding to the terminal and an evaluation result, wherein the processing strategy mark is used for indicating whether the server needs to screen and obtain a target advertisement set based on the evaluation result.

As an alternative embodiment, the object comprises at least one of:

an application, a good or a service.

As shown in fig. 9, corresponding to the foregoing embodiment of the method for pushing advertisements applied to a server, the present disclosure further provides an embodiment of an apparatus for pushing advertisements, including:

An obtaining module 91, configured to obtain a target advertisement obtaining request from a terminal, where the target advertisement obtaining request carries an evaluation result, and the evaluation result includes preference information of a user of the terminal for each object class;

A screening module 92, configured to respond to the target advertisement acquisition request and screen to obtain a target advertisement set based on the evaluation result;

and the pushing module 93 is used for pushing the target advertisement set to the terminal.

As an alternative embodiment, the screening module 92 includes:

the ranking unit is used for ranking all the candidate advertisements according to the evaluation result to obtain ranking results corresponding to all the candidate advertisements, wherein the candidate advertisements are advertisements used for popularizing candidate objects;

and the generating unit is used for generating a target advertisement set containing all target advertisements.

As an alternative embodiment, the sorting unit is configured to:

And sorting all the candidate advertisements according to the final scores corresponding to each candidate advertisement to obtain a sorting result.

As an alternative embodiment, the method further comprises a judging module configured to:

determining a processing strategy mark in a target advertisement acquisition request;

Executing a jump operation for jumping to the screening module 92 in the case where it is determined that the value of the processing policy flag is the first value;

in the case where it is determined that the value of the processing policy flag is the second value, the execution of the subsequent steps is stopped.

The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the related methods, and will not be described in detail herein.

For the device embodiments, reference is made to the description of the method embodiments for the relevant points, since they essentially correspond to the method embodiments. The apparatus embodiments described above are merely illustrative, wherein the modules illustrated as separate components may or may not be physically separate, and the components shown as modules may or may not be physical, i.e., may be located in one place, or may be distributed over a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the objectives of the disclosed solution. Those of ordinary skill in the art will understand and implement the present invention without undue burden.

The present description also provides an electronic device comprising:

A processor;

a memory for storing processor-executable instructions;

Fig. 10 is a schematic structural diagram of an electronic device provided in an exemplary embodiment. Referring to fig. 10, at the hardware level, the device includes a processor 1002, an internal bus 1004, a network interface 1006, a memory 1008, and a non-volatile memory 1010, although other hardware required by other services is possible. One or more embodiments of the present description may be implemented in a software-based manner, such as by the processor 1002 reading a corresponding computer program from the non-volatile memory 1010 into the memory 1008 and then running. Of course, in addition to software implementation, one or more embodiments of the present disclosure do not exclude other implementation manners, such as a logic device or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but may also be hardware or a logic device.

The apparatus shown in fig. 8 and fig. 9 may be applied to the device shown in fig. 10 to implement the technical solution described above.

The apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. A typical implementation device is a computer, which may be in the form of a personal computer, laptop computer, cellular telephone, camera phone, smart phone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or a combination of any of these devices.

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

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

The present specification also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of a method as described in any of the above.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer 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, read only compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic disk storage, quantum memory, graphene-based storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by the computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

Fig. 11 is a schematic block diagram illustrating an apparatus 1100 for acquiring advertisements, according to an embodiment of the present disclosure. For example, apparatus 1100 may be a mobile phone, computer, digital broadcast terminal, messaging device, game console, tablet device, medical device, exercise device, personal digital assistant, or the like.

Referring to FIG. 11, apparatus 1100 may include one or more of a processing component 1102, a memory 1104, a power component 1106, a multimedia component 1108, an audio component 1110, an input/output (I/O) interface 1112, a sensor component 1114, and a communication component 1116.

The processing component 1102 generally controls overall operation of the apparatus 1100, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 1102 may include one or more processors 1120 to execute instructions to perform all or part of the steps of the methods described above. Further, the processing component 1102 can include one or more modules that facilitate interactions between the processing component 1102 and other components. For example, the processing component 1102 may include a multimedia module to facilitate interaction between the multimedia component 1108 and the processing component 1102.

Memory 1104 is configured to store various types of data to support operations at apparatus 1100. Examples of such data include instructions for any application or method operating on the device 1100, contact data, phonebook data, messages, pictures, videos, and the like. The memory 1104 may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.

The power supply component 1106 provides power to the various components of the device 1100. The power supply component 1106 can include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 1100.

Multimedia component 1108 includes a screen between the device 1100 and the user that provides an output interface. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or slide action, but also the duration and pressure associated with the touch or slide operation. In some embodiments, multimedia component 1108 includes a front camera and/or a rear camera. The front camera and/or the rear camera may receive external multimedia data when the apparatus 1100 is in an operational mode, such as a photographing mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

The audio component 1110 is configured to output and/or input an audio signal. For example, the audio component 1110 includes a Microphone (MIC) configured to receive external audio signals when the device 1100 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 1104 or transmitted via the communication component 1116. In some embodiments, the audio component 1110 further comprises a speaker for outputting audio signals.

The I/O interface 1112 provides an interface between the processing component 1102 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, a home button, a volume button, an activate button, and a lock button.

The sensor assembly 1114 includes one or more sensors for providing status assessment of various aspects of the apparatus 1100. For example, the sensor assembly 1114 may detect the on/off state of the device 1100, the relative positioning of the components, such as the display and keypad of the device 1100, the sensor assembly 1114 may also detect a change in position of the device 1100 or a component of the device 1100, the presence or absence of user contact with the device 1100, the orientation or acceleration/deceleration of the device 1100, and a change in temperature of the device 1100. The sensor assembly 1114 may include a proximity sensor configured to detect the presence of nearby objects in the absence of any physical contact. The sensor assembly 1114 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 1114 may also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 1116 is configured to facilitate communication between the apparatus 1100 and other devices in a wired or wireless manner. The device 1100 may access a wireless network based on a communication standard, such as WiFi,2G or 3G,4G LTE, 5G NR, or a combination thereof. In one exemplary embodiment, the communication component 1116 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication component 1116 further includes a Near Field Communication (NFC) module to facilitate short range communication. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the apparatus 1100 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic elements for executing the methods described in any one of the embodiments above.

In an exemplary embodiment, a non-transitory computer-readable storage medium is also provided, such as a memory 1104 including instructions executable by the processor 1120 of the apparatus 1100 to perform the above-described method. For example, the non-transitory computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any adaptations, uses, or adaptations of the disclosure following the general principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method of capturing advertisements, the method comprising:

2. The method of acquiring advertisements of claim 1, wherein the method further comprises:

3. The method of claim 2, wherein the determining the evaluation result based on the object interaction information comprises:

4. The method of claim 1, wherein generating a targeted advertisement acquisition request carrying the evaluation result comprises:

and generating the target advertisement acquisition request according to the original advertisement acquisition request, a processing strategy mark corresponding to the terminal and the evaluation result, wherein the processing strategy mark is used for indicating whether the server needs to screen and obtain the target advertisement set based on the evaluation result.

5. The method of claim 1, wherein the object comprises at least one of:

an application, a good or a service.

6. A method of pushing advertisements, the method comprising:

Pushing the target advertisement set to the terminal.

7. The method for pushing advertisements according to claim 6, wherein the screening to obtain the target advertisement set based on the evaluation result comprises:

8. The method for pushing advertisements according to claim 7, wherein the ranking all candidate advertisements according to the evaluation result to obtain ranking results corresponding to all candidate advertisements comprises:

9. The method of pushing advertisements of claim 6, wherein the method further comprises:

10. An apparatus for capturing advertisements, comprising:

And the second acquisition module is used for acquiring the target advertisement set which is obtained by the server in response to the target advertisement acquisition request and screening based on the evaluation result.

11. The apparatus for capturing advertisements of claim 10, further comprising:

12. The apparatus for capturing advertisements of claim 11, wherein the result determination module is configured to:

13. The apparatus for capturing advertisements of claim 10, wherein the generation module is configured to:

14. An apparatus for pushing advertisements, comprising:

15. The apparatus for pushing advertisements of claim 14, wherein the screening module comprises:

16. The apparatus for pushing advertisements according to claim 15, wherein the ranking unit is configured to:

17. The apparatus for pushing advertisements of claim 14, further comprising a determination module configured to:

18. An electronic device, comprising:

A processor;

a memory for storing processor-executable instructions;

wherein the processor is configured to implement the method of any one of claims 1 to 9.

19. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the steps of the method of any of claims 1 to 9.