CN113869926A

CN113869926A - Advertisement identification method and device, electronic equipment and storage medium

Info

Publication number: CN113869926A
Application number: CN202010614085.8A
Authority: CN
Inventors: 张焱; 卜建辉; 唐新春
Original assignee: Beijing Dajia Internet Information Technology Co Ltd
Current assignee: Beijing Dajia Internet Information Technology Co Ltd
Priority date: 2020-06-30
Filing date: 2020-06-30
Publication date: 2021-12-31

Abstract

The disclosure relates to an advertisement identification method, an advertisement identification device, electronic equipment and a storage medium, and relates to the technical field of networks. The method and the device can obtain the historical advertisement set, and determine the negative feedback indicated value of each advertisement to be recommended in the advertisement set to be recommended according to the negative feedback indicated value of each historical advertisement in the historical advertisement set and the similarity between each advertisement to be recommended in the advertisement set to be recommended and each historical advertisement in the historical advertisement set. Then, the advertisements to be recommended, of which the negative feedback indication value is greater than the preset threshold value, in the set of advertisements to be recommended can be determined as the advertisements meeting the negative feedback behavior triggering condition of the user. The advertisement identification method and the advertisement identification device can comprehensively identify more advertisements meeting negative feedback behavior triggering conditions of the user, so that the identification accuracy of the advertisements meeting the negative feedback behavior triggering conditions of the user can be improved, the advertisement delivery quality is improved, and the service experience of the user is guaranteed.

Description

Advertisement identification method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of network technologies, and in particular, to an advertisement identification method and apparatus, an electronic device, and a storage medium.

Background

The advertisement delivery platform can be used for delivering advertisements to users, such as: video advertisements, picture advertisements, web page advertisements, and the like. However, the phenomenon that users feel the discomfort of part of advertisements often exists, so that in order to guarantee the long-term development of an advertisement delivery platform, the user-conscious advertisements need to be considered when the advertisements are delivered to the users, and the service experience of the users is guaranteed.

In the prior art, an advertisement delivery platform generally adopts a self-adaptive strategy of advertisement recommendation based on user behaviors to guarantee service experience of a user. For example, before recommending advertisements to a user, the advertisement delivery platform may identify advertisements that are objectionable to the user from the advertisements to be recommended according to negative feedback behavior data of the user on the advertisements, and intervene in the advertisements that are objectionable to the user according to a predetermined rule and a manual review manner, such as: shielding, reducing recommendation times and the like, thereby ensuring the service experience of the user facing the advertisement putting platform.

However, the above conventional advertisement recommendation method has insufficient accuracy in identifying the advertisement which is objectionable to the user, and seriously affects the service experience of the user. For example, if the negative feedback behavior data indicates that the user feels the advertisement of a certain product a, the existing advertisement recommendation method can only identify that the advertisement related to the product a is the advertisement that the user feels, and the user may feel that the advertisement is similar or similar to the product a, so that the method has a great limitation.

Disclosure of Invention

The present disclosure provides an advertisement recognition method, an advertisement recognition apparatus, an electronic device, and a storage medium, which can more accurately recognize an advertisement that a user feels when placing an advertisement.

The technical scheme of the embodiment of the disclosure is as follows:

in a first aspect, an embodiment of the present disclosure provides an advertisement identification method, which may include: acquiring a historical advertisement set, wherein the historical advertisement set comprises at least one historical advertisement indicated by negative feedback behavior data of a user and a negative feedback indication value of the historical advertisement; determining a negative feedback indicated value of each advertisement to be recommended in the advertisement set to be recommended according to the negative feedback indicated value of each historical advertisement in the historical advertisement set and the similarity between each advertisement to be recommended in the advertisement set to be recommended and each historical advertisement in the historical advertisement set; and determining the advertisements to be recommended, of which the negative feedback indicated value is greater than a preset threshold value, in the set of advertisements to be recommended as the advertisements meeting the negative feedback behavior triggering condition of the user.

The negative feedback behavior data is used for indicating that the user has a negative feedback behavior on the advertisement, and the negative feedback behavior on the advertisement by the user indicates that the user feels the advertisement. The negative feedback indication value may indicate a user's dislikeness of the advertisement. The larger the negative feedback indication value is, the higher the degree of the dislike is. Advertisements that satisfy the negative feedback behavior triggering condition of the user are advertisements that the user may feel objectionable.

Optionally, the step of determining the negative feedback indication value of each advertisement in the set of advertisements to be recommended according to the negative feedback indication value of each historical advertisement in the set of historical advertisements and the similarity between each advertisement to be recommended in the set of advertisements to be recommended and each historical advertisement in the set of historical advertisements may include: for each advertisement to be recommended in the set of advertisements to be recommended: determining target similarity according to the similarity between the advertisement to be recommended and each historical advertisement in the historical advertisement set, wherein the target similarity is the maximum similarity, the average similarity or the median similarity; and determining a negative feedback indicated value of the advertisement to be recommended according to the target similarity and the reverse feedback indicated value of each historical advertisement in the historical advertisement set.

In one embodiment, the negative feedback indication values of the historical ads in the historical ad set are the same. The step of determining the negative feedback indication value of the advertisement to be recommended according to the target similarity and the negative feedback indication value of each historical advertisement in the historical advertisement set may include: and obtaining the product of the target similarity and the negative feedback indicating value of any historical advertisement in the historical advertisement set as the negative feedback indicating value of the advertisement to be recommended.

In another embodiment, the step of determining a negative feedback indication value of an advertisement to be recommended according to the target similarity and the negative feedback indication value of each historical advertisement in the historical advertisement set may include: determining a target negative feedback indication value according to the negative feedback indication values of the historical advertisements in the historical advertisement set, wherein the target negative feedback indication value is a maximum negative feedback indication value, an average negative feedback indication value or a neutral negative feedback indication value; and obtaining the product of the target similarity and the target negative feedback indicating value as the negative feedback indicating value of the advertisement to be recommended.

Optionally, before the step of determining the target similarity according to the similarity between the advertisement to be recommended and each historical advertisement in the historical advertisement set, the method may further include: and determining the similarity between the advertisement to be recommended and each historical advertisement in the historical advertisement set.

Optionally, after the step of determining that the advertisement to be recommended with the negative feedback indication value larger than the preset threshold in the set of advertisements to be recommended is an advertisement that meets the negative feedback behavior triggering condition of the user, the method may further include: filtering the advertisements meeting the negative feedback behavior triggering condition of the user in the advertisement set to be recommended; according to a preset ordering rule, ordering the advertisements in the advertisement set to be recommended after the advertisements meeting the negative feedback behavior triggering condition of the user are filtered; and advertising according to the sequencing result.

Optionally, before the step of obtaining the historical advertisement set, the method may further include: negative feedback behavior data of a user in a preset time period is collected, and the negative feedback behavior data is used for indicating that the user has negative feedback behavior on the advertisement; and generating a historical advertisement set according to the negative feedback behavior data.

Optionally, the historical advertisements in the historical advertisement set are all different.

Optionally, the advertisement to be recommended in the advertisement set to be recommended may include any one or more of the following: picture ads, video ads, web ads, email ads, text link ads, and dynamic banner ads.

In a second aspect, an embodiment of the present disclosure provides an advertisement recognition apparatus, which may include: an obtaining module configured to obtain a historical advertisement set; the historical advertisement set comprises at least one historical advertisement indicated by the negative feedback behavior data of the user and a negative feedback indication value of the historical advertisement; the first determining module can be configured to determine a negative feedback indicating value of each advertisement to be recommended in the advertisement set to be recommended according to the negative feedback indicating value of each historical advertisement in the historical advertisement set and the similarity between each advertisement to be recommended in the advertisement set to be recommended and each historical advertisement in the historical advertisement set; the second determination module may be configured to determine that the advertisement to be recommended, in the set of advertisements to be recommended, whose negative feedback indication value is greater than a preset threshold, is an advertisement that satisfies a negative feedback behavior trigger condition of the user.

Optionally, the first determining module may be specifically configured to, for each advertisement to be recommended in the set of advertisements to be recommended: determining target similarity according to the similarity between the advertisement to be recommended and each historical advertisement in the historical advertisement set, wherein the target similarity is the maximum similarity, the average similarity or the median similarity; and determining a negative feedback indicated value of the advertisement to be recommended according to the target similarity and the negative feedback indicated value of each historical advertisement in the historical advertisement set.

In one embodiment, the negative feedback indication values of the historical advertisements in the historical advertisement set are the same; the first determining module is specifically configured to obtain a product of the target similarity and a negative feedback indication value of any historical advertisement in the historical advertisement set as a negative feedback indication value of the advertisement to be recommended.

In another embodiment, the first determining module is specifically configured to determine a target negative feedback indication value according to a negative feedback indication value of each historical advertisement in the historical advertisement set, where the target negative feedback indication value is a maximum negative feedback indication value, an average negative feedback indication value, or a median negative feedback indication value; and obtaining the product of the target similarity and the target negative feedback indicating value as the negative feedback indicating value of the advertisement to be recommended.

Optionally, the apparatus may further include: and the third determination module can be configured to determine the similarity between the advertisement to be recommended and each historical advertisement in the historical advertisement set.

Optionally, the apparatus may further include: the system comprises a filtering module, a sorting module and a putting module; the filtering module can be configured to filter out advertisements in the advertisement set to be recommended, wherein the advertisements meet the negative feedback behavior triggering condition of the user; the sorting module can be configured to sort the advertisements in the advertisement set to be recommended after filtering the advertisements meeting the negative feedback behavior triggering condition of the user according to a preset sorting rule; the placement module may be configured to place advertisements according to the ranking results.

Optionally, the apparatus may further include: the device comprises an acquisition module and a generation module; the acquisition module can be configured to acquire negative feedback behavior data of the user within a preset time period, wherein the negative feedback behavior data is used for indicating that the user has negative feedback behavior on the advertisement; the generation module may be configured to generate a set of historical advertisements based on the negative feedback behavior data.

Optionally, the advertisements to be recommended in the set of advertisements to be recommended include any one or more of the following: picture ads, video ads, web ads, email ads, text link ads, and dynamic banner ads.

In a third aspect, an embodiment of the present disclosure provides an electronic device, including: a processor and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement: acquiring a historical advertisement set, wherein the historical advertisement set comprises at least one historical advertisement indicated by negative feedback behavior data of a user and a negative feedback indication value of the historical advertisement; determining a negative feedback indicated value of each advertisement to be recommended in the advertisement set to be recommended according to the negative feedback indicated value of each historical advertisement in the historical advertisement set and the similarity between each advertisement to be recommended in the advertisement set to be recommended and each historical advertisement in the historical advertisement set; and determining the advertisements to be recommended, of which the negative feedback indicated value is greater than a preset threshold value, in the set of advertisements to be recommended as the advertisements meeting the negative feedback behavior triggering condition of the user.

In a fourth aspect, an embodiment of the present disclosure provides a server, including: a processor and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement: acquiring a historical advertisement set, wherein the historical advertisement set comprises at least one historical advertisement indicated by negative feedback behavior data of a user and a negative feedback indication value of the historical advertisement; determining a negative feedback indicated value of each advertisement to be recommended in the advertisement set to be recommended according to the negative feedback indicated value of each historical advertisement in the historical advertisement set and the similarity between each advertisement to be recommended in the advertisement set to be recommended and each historical advertisement in the historical advertisement set; and determining the advertisements to be recommended, of which the negative feedback indicated value is greater than a preset threshold value, in the set of advertisements to be recommended as the advertisements meeting the negative feedback behavior triggering condition of the user.

In a fifth aspect, embodiments of the present disclosure provide a computer-readable storage medium having instructions stored thereon, where the instructions, when executed by a processor, implement: acquiring a historical advertisement set, wherein the historical advertisement set comprises at least one historical advertisement indicated by negative feedback behavior data of a user and a negative feedback indication value of the historical advertisement; determining a negative feedback indicated value of each advertisement to be recommended in the advertisement set to be recommended according to the negative feedback indicated value of each historical advertisement in the historical advertisement set and the similarity between each advertisement to be recommended in the advertisement set to be recommended and each historical advertisement in the historical advertisement set; and determining the advertisements to be recommended, of which the negative feedback indicated value is greater than a preset threshold value, in the set of advertisements to be recommended as the advertisements meeting the negative feedback behavior triggering condition of the user.

In a sixth aspect, the disclosed embodiments provide a computer program product that, when executed, implements: acquiring a historical advertisement set, wherein the historical advertisement set comprises at least one historical advertisement indicated by negative feedback behavior data of a user and a negative feedback indication value of the historical advertisement; determining a negative feedback indicated value of each advertisement to be recommended in the advertisement set to be recommended according to the negative feedback indicated value of each historical advertisement in the historical advertisement set and the similarity between each advertisement to be recommended in the advertisement set to be recommended and each historical advertisement in the historical advertisement set; and determining the advertisements to be recommended, of which the negative feedback indicated value is greater than a preset threshold value, in the set of advertisements to be recommended as the advertisements meeting the negative feedback behavior triggering condition of the user.

The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:

the disclosed embodiments may obtain a historical advertisement set that includes at least one historical advertisement indicated by negative feedback behavior data of a user, and a negative feedback indication value of the historical advertisement. And determining the negative feedback indicated value of each advertisement to be recommended in the advertisement set to be recommended according to the negative feedback indicated value of each historical advertisement in the historical advertisement set and the similarity between each advertisement to be recommended in the advertisement set to be recommended and each historical advertisement in the historical advertisement set. Then, the advertisements to be recommended, of which the negative feedback indication value is greater than the preset threshold value, in the set of advertisements to be recommended may be determined to be the advertisements that satisfy the negative feedback behavior triggering condition of the user (i.e., the advertisements that are disliked by the user). Therefore, the advertisements to be recommended which meet the triggering condition of the negative feedback behavior of the user in the advertisement set to be recommended can be identified based on the negative feedback indicated value of each advertisement to be recommended. The negative feedback indicated value of each advertisement to be recommended is determined according to the negative feedback indicated value of each historical advertisement in the historical advertisement set and the similarity between the advertisement to be recommended and each historical advertisement in the historical advertisement set, so that when the advertisement to be recommended meeting the negative feedback behavior triggering condition of the user is identified based on the negative feedback indicated value of each advertisement to be recommended, more advertisements meeting the negative feedback behavior triggering condition of the user can be more comprehensively identified, the identification accuracy of the advertisement meeting the negative feedback behavior triggering condition of the user can be improved, the advertisement putting quality is improved, and the service experience of the user is guaranteed.

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

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.

Fig. 1 is a schematic view of an application scenario provided in the embodiment of the present disclosure;

FIG. 2 is a schematic flow chart illustrating an advertisement recognition method according to an embodiment of the present disclosure;

FIG. 3 is another schematic flow chart diagram of an advertisement identification method provided by an embodiment of the present disclosure;

FIG. 4 is a schematic flow chart of an advertisement identification method according to an embodiment of the present disclosure;

FIG. 5 is a schematic flow chart of an advertisement recognition method according to an embodiment of the present disclosure;

fig. 6 is a schematic flow chart of advertisement delivery provided by the embodiment of the present disclosure;

FIG. 7 is a schematic structural diagram of an advertisement recognition device according to an embodiment of the present disclosure;

fig. 8 is another schematic structural diagram of an advertisement recognition device according to an embodiment of the present disclosure;

fig. 9 is a schematic structural diagram of an advertisement recognition device according to an embodiment of the present disclosure;

fig. 10 is a schematic structural diagram of an advertisement recognition device according to an embodiment of the present disclosure;

fig. 11 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.

Detailed Description

In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, and/or components.

First, an application scenario of the embodiment of the present disclosure is explained:

fig. 1 is a schematic view of an application scenario provided by an embodiment of the present disclosure, as shown in fig. 1, the application scenario may include: a server 110 and a user terminal 120, the server 110 may establish a connection with the user terminal 120 through a wired network or a wireless network.

The server 110 may be a data server of an advertisement delivery platform, and may be used to store and process advertisement data. For example, the server 110 may store an advertisement to be recommended, which needs to be recommended to the user by the advertisement delivery platform, and the server 110 may send the advertisement to be recommended to the user terminal 120 through the aforementioned limited network or wireless network, so that the user terminal 120 may display the advertisement to the user to complete delivery of the advertisement.

Optionally, the server 110 may also include or be connected to a database, and the advertisement to be recommended may also be stored in the database, such as: the advertisements to be recommended may form an advertisement set to be recommended and stored in the database, and when the advertisements need to be recommended, the server 110 may call the database to extract the advertisements to be recommended that need to be delivered from the advertisement set to be recommended.

Optionally, the advertisement to be recommended in the advertisement set to be recommended may include any one or more of the following: picture ads, video ads, web ads, email ads, text link ads, and dynamic banner ads. The present disclosure is not limited with respect to the particular type of advertisement to be recommended.

In some embodiments, the server 110 may be a single server or a server cluster composed of a plurality of servers. In some embodiments, the server cluster may also be a distributed cluster. The present disclosure is also not limited to a particular implementation of the server 110.

Optionally, the advertisement delivery platform may be some advertisement service platforms specially used for advertisement delivery, or may also be other service platforms such as a live broadcast platform, a short video platform, a shopping platform, a takeaway platform, a shared service platform, a friend-making platform, and a functional website, which are integrated with an advertisement delivery function, and the specific type of the advertisement delivery platform is not limited in this disclosure.

In addition, in the application scenario, the user terminal 120 may be a personal intelligent device such as a mobile phone and a tablet computer, or may also be a device such as a notebook computer, a desktop computer, a television, and a projector. Taking the user terminal 120 as a mobile phone and the advertisement delivery platform as a live broadcast platform as an example: when a user opens an application program of the live broadcast platform through a mobile phone, the user can watch live broadcast on the live broadcast platform, a server of the live broadcast platform can send advertisements to be recommended to the mobile phone of the user through a network, and the mobile phone can display the advertisements to be recommended sent by the server to the user through an application program interface of the live broadcast platform, so that advertisement putting is achieved. It should be noted that the embodiment of the present disclosure also does not limit the type of the user terminal 120.

It is understood that in the above application scenario, the server 110 may establish a connection with a plurality of identical or different user terminals 120 through a network, so as to implement advertisement delivery to users corresponding to the plurality of user terminals 120. Alternatively, when advertisements are delivered to users corresponding to a plurality of user terminals 120, the advertisements received by the user terminals 120 may be the same or different, and are not limited herein.

Based on the application scenario shown in fig. 1, the embodiment of the present disclosure provides an advertisement identification method, which can identify an advertisement that is objectionable to a user more accurately when an advertisement is delivered.

In some embodiments, the execution subject of the method may be a server in the application scenario shown in fig. 1, for example, the server may identify an advertisement that is objectionable to the user in the set of advertisements to be recommended, so as to reduce the recommendation frequency of the objectionable advertisement to the user or block the objectionable advertisement from the user when the advertisement is delivered to the user.

Or, in other embodiments, the execution subject of the method may also be a user terminal, for example, the user terminal may obtain a set of advertisements to be recommended from a server, and identify advertisements that are objectionable to the user, and may also reduce the number of times of recommending advertisements that are objectionable to the user or block the objectionable advertisements from the user when delivering the advertisements to the user.

In another embodiment, the server and the user terminal may execute partial steps of the method respectively to implement the entire process of the method together.

It should be noted that the present disclosure does not limit the implementation subject of the method.

Fig. 2 is a schematic flowchart of an advertisement identification method according to an embodiment of the present disclosure.

As shown in fig. 2, the advertisement recognition method may include:

s201, acquiring a historical advertisement set.

Wherein the historical advertisement set may include at least one historical advertisement indicated by the negative feedback behavior data of the user and a negative feedback indication value for each historical advertisement. The negative feedback behavior data of the user refers to: some negative feedback behavior of the user on the presence of a certain advertisement. The historical advertisement indicated by the negative feedback behavior data of the user can be understood as the historical advertisement which is disliked by the user. The negative feedback indication value of the historical advertisement may indicate the user's dislike of the historical advertisement, such as: the larger the negative feedback instruction value is, the larger the degree of dislike is.

The historical advertisement set can be obtained by collecting and analyzing negative feedback behavior data of the user. For example, when a user is browsing a web page, the user may click "close" or "block" an advertisement if the user sees an advertisement pushed on the web page. By counting the similar behaviors of the user on the advertisement, the negative feedback behavior data of the user can be obtained, and whether the user feels dislike to the advertisement or not can be obtained by analyzing the negative feedback behavior data of the user. Such as: when the user sees the advertisement A, clicking the 'mask advertisement', the user feels the advertisement A. That is, advertisement a may be included in the historical advertisements indicated by the user negative feedback behavior data.

According to the above manner, the negative feedback behavior data of each user is collected and analyzed, so that the historical advertisement indicated by the negative feedback behavior data of each user can be obtained, or the historical advertisement can be called as the advertisement which is felt by each user, and thus the historical advertisement set corresponding to each user is formed.

Alternatively, the historical advertisement set may be stored in the user terminal or in the server. When stored in the user terminal, the server may obtain a historical advertisement set to the user terminal; when stored in the server, the server may directly retrieve the historical advertisement set.

With this understanding, please refer to FIG. 3 for illustration: fig. 3 is another schematic flow chart of the advertisement identification method according to the embodiment of the present disclosure, in the embodiment of the present disclosure, before the step S201, the advertisement identification method may further include:

s301, negative feedback behavior data of the user in a preset time period are collected.

Wherein negative feedback behavior data may be used to indicate that a user is disliked an advertisement. The preset time period may be a day, a few days, a few hours, etc. in the past, and the present disclosure does not limit the specific duration of the preset time period.

And S302, generating a historical advertisement set according to the negative feedback behavior data.

For example, the negative feedback behavior data may include advertisement identifications of history advertisements that are objectionable to the user, such as: advertisement numbers, advertisement names, etc. According to the advertisement identifications of the historical advertisements in the negative feedback behavior data, the historical advertisements corresponding to the historical advertisement identifications can be determined to generate a historical advertisement set. Or, the negative feedback behavior data may also directly include historical advertisements that are objectionable to the user, so that a historical advertisement set may be generated directly according to the negative feedback behavior data. The present disclosure is not limited to a particular data type of negative feedback behavior data.

After step S201 is performed, step S202 may be performed:

s202, determining the negative feedback indicated value of each advertisement to be recommended in the advertisement set to be recommended according to the negative feedback indicated value of each historical advertisement in the historical advertisement set and the similarity between each advertisement to be recommended in the advertisement set to be recommended and each historical advertisement in the historical advertisement set.

Fig. 4 is a schematic flowchart of an advertisement identification method according to an embodiment of the present disclosure.

Optionally, as shown in fig. 4, the step S202 may include:

for each advertisement to be recommended in the set of advertisements to be recommended:

s401, determining target similarity according to the similarity between the advertisement to be recommended and each historical advertisement in the historical advertisement set.

In one embodiment, the target similarity may be a maximum similarity. For example, when the history advertisement set includes a plurality of (a plurality of) history advertisements indicated by negative feedback behavior data of the user (i.e., the negative feedback behavior data of the user indicates two or more, and are the same in the following embodiments), the similarity between the advertisement to be recommended and each history advertisement in the history advertisement set is also a plurality of, and the maximum similarity may be obtained from the plurality of similarities as the target similarity.

In another embodiment, the target similarity may be an average similarity. Similarly, when the historical advertisement set contains a plurality of historical advertisements indicated by the negative feedback behavior data of the user, an average value of a plurality of similarity degrees corresponding to the advertisements to be recommended may be calculated, and the average similarity degree is obtained as the target similarity degree.

In yet another embodiment, the target similarity may be a median similarity. Similarly, when the historical advertisement set comprises a plurality of historical advertisements indicated by the negative feedback behavior data of the user, the median of the plurality of similarities can be selected from the plurality of similarities corresponding to the advertisements to be recommended, and thus the median similarity is obtained as the target similarity.

In other embodiments, other ways may also be used to determine the target similarity, such as: 70%, 80%, 90%, etc. of the maximum similarity may be determined as the target similarity, or a similarity at a certain position with a size ranked between 60% and 80% may be selected from the multiple similarities as the target similarity, etc., and the method for determining the target similarity is not limited herein by the present disclosure.

It can be understood that when only one historical advertisement indicated by the negative feedback behavior data of the user is included in the historical advertisement set, the target similarity is only the similarity between the advertisement to be recommended and the historical advertisement.

S402, determining a negative feedback indicated value of the advertisement to be recommended according to the target similarity and the negative feedback indicated value of each historical advertisement in the historical advertisement set.

In some embodiments, the negative feedback indicator (or referred to as "counterincibility") is the same for each historical advertisement in the set of historical advertisements. For example, the negative feedback indication values of the historical advertisements in the historical advertisement set may be set to a uniform preset value in advance, such as: if the user feels the advertisement, the negative feedback indication value of the advertisement is a, a is a number greater than 0, and may be any number such as 1, 2, 3, 4, and the like, and the size of a is not limited by the disclosure. Accordingly, if the user is not repugnant to the ad, the negative feedback indicator value for the ad (i.e., ads outside of the historical set of ads) may be 0.

When the negative feedback indicated values of the historical advertisements in the historical advertisement set are the same, the negative feedback indicated value of the advertisement to be recommended can be obtained by calculation according to the target similarity corresponding to the advertisement to be recommended and the negative feedback indicated value of any one historical advertisement in the historical advertisement set. For example, the product of the target similarity corresponding to the advertisement to be recommended and the negative feedback indication value of any one of the historical advertisements in the historical advertisement set (the negative feedback indication value of each historical advertisement is the same) may be calculated, and the product result may be used as the negative feedback indication value of the advertisement to be recommended.

Optionally, according to the technical solution of the present disclosure, a person skilled in the art may also expand the way of calculating the product between the target similarity corresponding to the advertisement to be recommended and the negative feedback indication value of any one historical advertisement in the historical advertisement set as the negative feedback indication value of the advertisement to be recommended to other calculation ways, such as: the negative feedback indication value of the advertisement to be recommended may also be the result of squaring the aforementioned product or performing an evolution, and the like, and the disclosure does not limit the product to the only way.

In other embodiments, the negative feedback indication value of each historical advertisement in the historical advertisement set may be different values or may be partially the same. For example, the user's level of dislike for each historical advertisement may be counted, and a negative feedback indication value may be set for the corresponding historical advertisement, such as: a closed interval with a negative feedback indicating value of 0 to 1 can be set, and when the negative feedback indicating value is 0, the user does not feel the historical advertisement; when the negative feedback indicating value is 1, the user is indicated to be extremely repugnant to the historical advertisement; when the negative feedback indicator value is other values between 0 and 1, such as: 0.5, 0.8, etc., may represent different levels of user dislike of historical advertisements, respectively. Alternatively, the negative feedback indication value of each historical advertisement in the historical advertisement set may be represented in various other ways, such as a closed interval of 1 to 2, a closed interval of 0 to 2, and the like, and the disclosure is not limited thereto.

When the negative feedback indication values of the historical advertisements in the historical advertisement set are different or are partially the same, a target negative feedback indication value can be determined from a plurality of negative feedback indication values, and then the product of the target negative feedback indication value and the target similarity is calculated to be used as the negative feedback indication value of the advertisement to be recommended. The determination of the target negative feedback indication value may refer to the determination manner of the target similarity, such as: the target negative feedback indication value may be a maximum negative feedback indication value, an average negative feedback indication value, a median negative feedback indication value, or the like. Or, the negative feedback indication value of the advertisement with the maximum similarity to the advertisement to be recommended in the historical advertisement set may be used as the target negative feedback indication value. In addition, it should be noted that, the present disclosure also does not limit calculating a product of the target negative feedback indication value and the target similarity, and a mode of using the product as the negative feedback indication value of the advertisement to be recommended is a unique mode, which is not described herein again.

It can be understood that, in actual implementation of the embodiment of the present disclosure, no matter the negative feedback indication values of the historical advertisements in the historical advertisement set are the same, or the negative feedback indication values of the historical advertisements in the historical advertisement set are different, the target negative feedback indication value may be determined by determining the negative feedback indication value, the maximum negative feedback indication value, the average negative feedback indication value, or the median negative feedback indication value of the historical advertisement in the historical advertisement set that has the greatest similarity to the advertisement to be recommended. It should be noted that the present disclosure also does not limit the determination manner of the target negative feedback indication value.

After step S202 is executed, step S203 may be executed:

s203, determining the advertisements to be recommended, of which the negative feedback indicated value is larger than a preset threshold value, in the set of advertisements to be recommended as the advertisements meeting the negative feedback behavior triggering condition of the user.

Wherein, when a certain advertisement meets the negative feedback behavior triggering condition of the user, the following steps are included: when the advertisement is pushed to the user, the user may dislike the advertisement, mask it, etc.

After the negative feedback indication value of each advertisement to be recommended in the set of advertisements to be recommended is determined according to the negative feedback indication value of each historical advertisement in the historical advertisement set and the similarity between each advertisement to be recommended in the set of advertisements to be recommended and each historical advertisement in the historical advertisement set, the advertisement to be recommended with the negative feedback indication value larger than a preset threshold value in the set of advertisements to be recommended can be determined as the advertisement meeting the triggering condition of the negative feedback behavior of the user according to the negative feedback indication value of each advertisement to be recommended in the set of advertisements to be recommended, so that when the advertisement is subsequently put to the user based on the set of advertisements to be recommended, the advertisement meeting the triggering condition of the negative feedback behavior of the user in the set of advertisements to be recommended can be subjected to corresponding intervention processing, such as: masking, reducing the number of recommendations, etc.

Correspondingly, the advertisement to be recommended, in the set of advertisements to be recommended, whose negative feedback indication value is smaller than the preset threshold value, may be regarded as an advertisement that does not satisfy the negative feedback behavior triggering condition of the user (or an advertisement that the user may not feel objectionable). The advertisement to be recommended with the negative feedback indication value equal to the preset threshold value may be an advertisement satisfying the triggering condition of the negative feedback behavior of the user, and may also be an advertisement not satisfying the triggering condition of the negative feedback behavior of the user, which is not limited in the present disclosure.

Optionally, the specific value of the preset threshold may be set according to the actual requirement and the set value range of the negative feedback indication value of each historical advertisement in the historical advertisement set, for example, when the negative feedback indication value of each historical advertisement in the historical advertisement set is 1, the preset threshold may be 0.5, 0.6, 0.7, 0.8, 0.9, and the like, and the disclosure is not limited.

As can be seen from the above, the embodiments of the present disclosure may obtain a historical advertisement set, where the historical advertisement set includes at least one historical advertisement indicated by negative feedback behavior data of a user, and a negative feedback indication value of the historical advertisement. And determining the negative feedback indicated value of each advertisement to be recommended in the advertisement set to be recommended according to the negative feedback indicated value of each historical advertisement in the historical advertisement set and the similarity between each advertisement to be recommended in the advertisement set to be recommended and each historical advertisement in the historical advertisement set. Then, the advertisements to be recommended, of which the negative feedback indication value is greater than the preset threshold value, in the set of advertisements to be recommended may be determined to be the advertisements that satisfy the negative feedback behavior triggering condition of the user (i.e., the advertisements that are disliked by the user). Therefore, the advertisements to be recommended which meet the triggering condition of the negative feedback behavior of the user in the advertisement set to be recommended can be identified based on the negative feedback indicated value of each advertisement to be recommended. The negative feedback indicated value of each advertisement to be recommended is determined according to the negative feedback indicated value of each historical advertisement in the historical advertisement set and the similarity between the advertisement to be recommended and each historical advertisement in the historical advertisement set, so that when the advertisement to be recommended meeting the negative feedback behavior triggering condition of the user is identified based on the negative feedback indicated value of each advertisement to be recommended, more advertisements meeting the negative feedback behavior triggering condition of the user can be more comprehensively identified, the identification accuracy of the advertisement meeting the negative feedback behavior triggering condition of the user can be improved, the advertisement putting quality is improved, and the service experience of the user is guaranteed.

In one embodiment, for each advertisement to be recommended: and directly adopting a similarity algorithm to calculate the similarity between the advertisement to be recommended and each historical advertisement in the historical advertisement set. And then, determining the target similarity according to the calculated similarity between the advertisement to be recommended and each historical advertisement in the historical advertisement set. In this embodiment, the calculation of the similarity between the advertisement to be recommended and each historical advertisement in the historical advertisement set may be real-time online calculation.

In another embodiment, the similarity between any two advertisements to be recommended in the set of advertisements to be recommended and the advertisement to be recommended can be calculated offline in advance. The historical advertisements in the historical advertisement set are obtained according to the negative feedback behavior data of the user, the negative feedback behavior data of the user are generated based on the advertisements delivered to the user by the advertisement delivery platform, and the advertisements delivered to the user by the advertisement delivery platform are all the advertisements to be recommended in the advertisement set to be recommended. Therefore, the similarity between each advertisement to be recommended and each historical advertisement in the historical advertisement set is included in the similarity between any two advertisements to be recommended in the advertisement set to be recommended, which is calculated offline in advance. Correspondingly, the step of determining the similarity between the advertisement to be recommended and each historical advertisement in the historical advertisement set may be: and directly extracting the similarity between the advertisement to be recommended and each historical advertisement in the historical advertisement set from the similarity between any two advertisements to be recommended in the advertisement set to be recommended calculated offline in advance.

Compared with the former embodiment, the similarity between the recommended advertisement and each historical advertisement in the historical advertisement set in the embodiment can be calculated in real time without on-line, the on-line computation amount of the advertisement identification method can be greatly reduced, the consumption time of advertisement identification is shortened, and the timeliness of advertisement delivery is improved.

Optionally, in this embodiment of the present disclosure, when performing the calculation of the similarity, the similarity calculation method adopted may include: distance measurement algorithms (e.g., Euclidean distance, Minkowski distance, Mahalanobis distance, Manhattan distance, etc.), and similarity measurement algorithms (e.g., vector space cosine similarity, Pearson correlation, etc.).

Taking the picture advertisement as an example:

assuming that the advertisement to be recommended is a picture 1, and the advertisement in the historical advertisement set is a picture 2, the picture 1 can be represented as a vector 1, and the picture 2 can be represented as a vector 2, then the cosine distance between the vector 1 and the vector 2 is calculated, and the cosine distance between the vector 1 and the vector 2 is used for representing the similarity between the picture 1 and the picture 2.

It should be noted that, for different types of advertisements, different similarity algorithms may be used for calculation, and the specific type of the similarity algorithm is not limited in the embodiments of the present disclosure.

Optionally, in any embodiment of the present disclosure, the historical advertisements in the historical advertisement set may be different. That is, each historical advertisement in the set of historical advertisements may be non-repeating.

The user may perform two or more times of countering feedback on the same advertisement, and repeated historical advertisements may appear in a historical advertisement set generated according to the negative feedback behavior data of the user. That is, the same historical advertisement may appear multiple times (two or more). When the repeated historical advertisements are too many, more meaningless repeated calculations exist in the calculation process (including real-time calculation or offline calculation) of the similarity, and the repeated historical advertisements in the historical advertisement set are processed to make the historical advertisements in the historical advertisement set different, so that the calculation efficiency of the subsequent similarity can be greatly improved, or the data volume of the offline similarity is reduced, and the timeliness of advertisement delivery is further improved.

In some embodiments, a historical advertisement set may be generated according to negative feedback behavior data of a user, and then repeated historical advertisements in the historical advertisement set may be deleted. In other embodiments, the negative feedback behavior data of the user may be subjected to de-duplication processing first, and then a historical advertisement set is generated, which is not limited in this disclosure.

Taking a preset time period as n days in the past as an example, n is an integer greater than 0:

suppose that the negative feedback behavior data submitted by user k in the past n days contains the advertisement identification of the following historical advertisements (d)₁To d_nAre all advertisement identifications):

{d₁，d₂，d₃，d₄，...，d_n}；

with d₁For example, d₁The corresponding historical advertisement is C₁Then, based on the negative feedback behavior data submitted by user k in the past n days, the generated historical advertisement set may be as follows:

hate_set(k，n)＝{C₁，C₂，C₃，C₄，...，C_n}；

wherein, white_set(k，n)Representing a historical set of ads generated from negative feedback behavior data submitted by user k over the past n days.

Assume the historical advertisement set hate_set(k，n)There are two historical ads that are the same, such as: c₃And C₄If they are the same, C can be deleted₃Or C₄Any of them, pair hate_set(k，n)Performing de-duplication treatment and deleting the hate_set(k，n)Of the repeated historical advertisements.

Fig. 5 is a schematic flowchart of an advertisement identification method according to an embodiment of the present disclosure.

Optionally, as shown in fig. 5, after the step of determining that the advertisement to be recommended with the negative feedback indication value greater than the preset threshold in the set of advertisements to be recommended is an advertisement that meets the negative feedback behavior triggering condition of the user, the method may further include:

s501, filtering out advertisements meeting negative feedback behavior triggering conditions of the user in the advertisement set to be recommended.

S502, according to a preset ordering rule, ordering the advertisements in the advertisement set to be recommended after the advertisements meeting the negative feedback behavior triggering conditions of the user are filtered.

And S503, advertising according to the sequencing result.

For example, for an advertisement set to be recommended after filtering out advertisements that satisfy a negative feedback behavior triggering condition of a user (i.e., user's repugnance), the remaining advertisements to be recommended in the advertisement set to be recommended may be sorted according to a delivery proportion, a frequency, a time period requirement, and the like of the advertisements to be recommended (or may be other priority setting rules), and then advertisement delivery may be performed in sequence according to a sorting result, or a preset number of advertisements to be recommended may be selected for delivery, where the preset number may be 1, 2, 3, or more.

For example, the following steps are carried out:

assume that there is a to-be-recommended set B as follows:

B＝{B₁，B₂，B₃，B₄，B₅，B₆}；

if the advertisements meeting the negative feedback behavior triggering condition of the user in the set B to be recommended are obtained according to the advertisement identification method in the foregoing embodiment of the present disclosure, the following are performed in sequence: b is₃、B₅And B₆And B is₁Is higher than B₂Priority of (A), B₂Is higher than B₄The advertisement placement according to the sorting result may be to recommend the advertisement B₁And (5) delivering to the user.

In order to express the technical solution of the present disclosure more clearly, the following describes an application of the advertisement identification method provided by the embodiment of the present disclosure in advertisement delivery in a specific implementation manner:

in this embodiment, a server of the advertisement delivery platform and the user terminal may establish a connection through a wired network or a wireless network, and a set of advertisements to be recommended may be preset in the server, where the set of advertisements to be recommended includes M advertisements to be recommended. Before executing the advertisement identification method, the server can calculate the similarity between every two advertisements to be recommended in the M advertisements to be recommended offline in advance through a similarity model f. To recommend advertisement c_iAnd c_j(c_iAnd c_jAdvertisements in M advertisements to be recommended) similarity S based on similarity model f_i，jFor example, the following steps are carried out:

S_i，j＝f(c_i，c_j) And S is_i，j＝S_j，i。

In addition, the user terminal can collect negative feedback behavior data of the user in the past n days and send the negative feedback behavior data to the server, wherein the negative feedback behavior data can be used for indicating that the user has negative feedback behavior on the advertisement, namely, the negative feedback behavior is objectionable to the advertisement. The server can generate a historical advertisement set according to the negative feedback behavior data, and the generated historical advertisement set is a subset of the advertisement set to be recommended. Further, the server can also perform de-duplication processing on the historical advertisement set, and delete repeated historical advertisements in the historical advertisement set.

Fig. 6 is a schematic flowchart of advertisement delivery provided by the embodiment of the present disclosure.

As shown in fig. 6, taking the target similarity as the maximum similarity and the negative feedback indication values (i.e., the counterintuitives) of the historical advertisements in the historical advertisement set as 1, the advertisement delivery step may include:

s601, the user terminal sends an advertisement putting request to the server.

For example, when a user opens an application program or a web page of some service platform on a user terminal, or opens some user terminals such as a television or a computer, the user terminal usually sends an advertisement delivery request to a server to obtain an advertisement to be recommended in the server and display the advertisement to the user. The advertisement delivery request may include a user terminal identifier or a user identifier, where the identifier may be a mobile phone number of a user, a device number of a user terminal, or an account number of another user.

S602, the server acquires a historical advertisement set.

S603, the server determines the maximum similarity corresponding to each advertisement to be recommended according to the similarity between each advertisement to be recommended and each historical advertisement in the historical advertisement set.

S604, the server obtains the product of the maximum similarity corresponding to each advertisement to be recommended and 1, and obtains a negative feedback indicated value of each advertisement to be recommended.

That is, user k treats advertisement c as a recommendation_iThe negative feedback indication value h (k, i) of (1) may be as follows:

wherein, state _ set (k, n) represents a historical advertisement set; max represents taking the maximum value; s (i, j) represents an advertisement c to be recommended_iSimilarity to each historical advertisement in the set of historical advertisements.

S605, the server determines the advertisement to be recommended with the negative feedback indicated value larger than or equal to a preset threshold value in the advertisement set to be recommended as the advertisement meeting the negative feedback behavior triggering condition of the user.

S606, the server filters out the advertisements meeting the negative feedback behavior triggering conditions of the user in the advertisement set to be recommended.

S607, according to a preset ordering rule, ordering the advertisements in the advertisement set to be recommended after the advertisements meeting the negative feedback behavior triggering condition of the user are filtered.

And S608, the server determines the target advertisement to be recommended to be delivered according to the sorting result and sends the target advertisement to the user terminal.

And S609, the user terminal displays the target advertisement to be recommended to the user.

As described above, according to the present embodiment, advertisements meeting the triggering condition of the negative feedback behavior of the user can be filtered from the set of advertisements to be recommended, so that advertisements meeting the triggering condition of the negative feedback behavior of the user can be shielded for the user.

The set of advertisements in the set to be recommended (the set of advertisements masked from user k) that satisfy the triggering condition of the negative feedback behavior of user k may be represented as follows:

Shield(k，i)＝I{h(k，i)≥T}，whereT≥0；

wherein Shield (k, i) represents an advertisement set which meets the triggering condition of the negative feedback behavior of the user k in the set to be recommended; i represents an element in Shield (k, I); h (k, i) a negative feedback indication value of each advertisement to be recommended; t represents a preset threshold.

When T is equal to 0, Shield (k, i) is equal to the set of advertisements to be recommended, and represents that all advertisements to be recommended are shielded for the user k; when T belongs to an open interval of 0 to 1, Shield (k, i) is a subset of a set of advertisements to be recommended and represents an advertisement with a negative feedback indication value larger than or equal to T for a user k; when T is equal to 1, Shield (k, i) is also a subset of the set of advertisements to be recommended, but Shield (k, i) is equal to the set of historical advertisements, meaning that only the historical advertisements indicated by the negative feedback behavior data (i.e., the historical advertisements of the set of historical advertisements) are masked from user k.

The beneficial effects of the present embodiment are described in detail in the foregoing embodiments, and are not described herein again.

The above description has introduced the solution provided by the embodiments of the present disclosure mainly from the perspective of the server/user terminal. It will be appreciated that the server/user terminal may comprise one or more hardware structures and/or software modules for implementing the advertisement recognition method described above, and that these implementing hardware structures and/or software modules may constitute an electronic device. Those of skill in the art will readily appreciate that the present disclosure can be implemented in hardware or a combination of hardware and computer software for implementing the exemplary algorithm steps described in connection with the embodiments disclosed herein. Whether a function is performed as hardware or computer software drives hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

Accordingly, the embodiment of the present disclosure also provides an advertisement recognition device, which may be fully integrated in the server/user terminal, or partially integrated in the server or partially integrated in the user terminal.

Fig. 7 is a schematic structural diagram of an advertisement recognition device according to an embodiment of the present disclosure.

As shown in fig. 7, the advertisement recognition apparatus may include: the obtaining module 10 may be configured to obtain a historical advertisement set, where the historical advertisement set includes at least one historical advertisement indicated by the negative feedback behavior data of the user and a negative feedback indication value of the historical advertisement. The first determining module 20 may be configured to determine the negative feedback indication value of each advertisement to be recommended in the set of advertisements to be recommended according to the negative feedback indication value of each historical advertisement in the set of historical advertisements and a similarity between each advertisement to be recommended in the set of advertisements to be recommended and each historical advertisement in the set of historical advertisements. The second determining module 30 may be configured to determine, as an advertisement satisfying a negative feedback behavior triggering condition of the user, an advertisement to be recommended in the set of advertisements to be recommended whose negative feedback indication value is greater than a preset threshold.

Optionally, the first determining module 20 may be specifically configured to, for each advertisement to be recommended in the set of advertisements to be recommended: determining target similarity according to the similarity between the advertisement to be recommended and each historical advertisement in the historical advertisement set, wherein the target similarity is the maximum similarity, the average similarity or the median similarity; and determining a negative feedback indicated value of the advertisement to be recommended according to the target similarity and the negative feedback indicated value of each historical advertisement in the historical advertisement set.

In one embodiment, the negative feedback indication values of the historical ads in the historical ad set are the same. The first determining module 20 is specifically configured to obtain a product between the target similarity and a negative feedback indication value of any historical advertisement in the historical advertisement set as a negative feedback indication value of the advertisement to be recommended.

In another embodiment, the first determining module 20 is specifically configured to determine a target negative feedback indication value according to a negative feedback indication value of each historical advertisement in the historical advertisement set, where the target negative feedback indication value is a maximum negative feedback indication value, an average negative feedback indication value, or a median negative feedback indication value; and obtaining the product of the target similarity and the target negative feedback indicating value as the negative feedback indicating value of the advertisement to be recommended.

Fig. 8 is another schematic structural diagram of an advertisement recognition device according to an embodiment of the present disclosure.

Optionally, as shown in fig. 8, the advertisement recognition apparatus may further include: the third determining module 40 may be configured to determine similarity between the advertisement to be recommended and each historical advertisement in the historical advertisement set.

Fig. 9 is a schematic structural diagram of an advertisement recognition device according to an embodiment of the present disclosure.

Optionally, as shown in fig. 9, the advertisement recognition apparatus may further include: a filtering module 50, a sorting module 60 and a throwing module 70; the filtering module 50 may be configured to filter out advertisements in the set of advertisements to be recommended that satisfy the negative feedback behavior triggering condition of the user; the sorting module 60 may be configured to sort the advertisements in the advertisement set to be recommended after filtering out the advertisements satisfying the negative feedback behavior triggering condition of the user according to a preset sorting rule. Placement module 70 may be configured to place advertisements based on the ranking results.

Fig. 10 is a schematic structural diagram of an advertisement recognition device according to an embodiment of the present disclosure.

Optionally, as shown in fig. 10, the advertisement recognition apparatus may further include: an acquisition module 80 and a generation module 90; the collecting module 80 may be configured to collect negative feedback behavior data of the user in a preset time period, wherein the negative feedback behavior data is used for indicating that the user has negative feedback behavior on the advertisement. The generation module 90 may be configured to generate a set of historical advertisements based on the negative feedback behavior data.

As described above, the embodiments of the present disclosure may perform the division of the functional modules for the server/user terminal according to the above method examples. The integrated module can be realized in a hardware form, and can also be realized in a software functional module form. In addition, it should be further noted that the division of the modules in the embodiments of the present disclosure is schematic, and is only a logic function division, and there may be another division manner in actual implementation. For example, the advertisement recognition device may divide each function module according to each function, or may integrate two or more functions into one processing module.

With regard to the advertisement recognition device in the foregoing embodiment, the specific manner in which each module performs operations and the beneficial effects thereof have been described in detail in the foregoing method embodiment, and are not described herein again.

The embodiment of the disclosure also provides an electronic device, which may be the user terminal such as the mobile phone, the tablet computer, the computer, or the like, or some outdoor advertisement large screen display devices.

As shown in fig. 11, the electronic device may include: a processor 100 and a memory 200 for storing instructions executable by the processor 100; wherein the processor 100 is configured to execute instructions to implement: acquiring a historical advertisement set, wherein the historical advertisement set comprises at least one historical advertisement indicated by negative feedback behavior data of a user and a negative feedback indication value of the historical advertisement; determining a negative feedback indicated value of each advertisement to be recommended in the advertisement set to be recommended according to the negative feedback indicated value of each historical advertisement in the historical advertisement set and the similarity between each advertisement to be recommended in the advertisement set to be recommended and each historical advertisement in the historical advertisement set; and determining the advertisements to be recommended, of which the negative feedback indicated value is greater than a preset threshold value, in the set of advertisements to be recommended as the advertisements meeting the negative feedback behavior triggering condition of the user.

Optionally, an embodiment of the present disclosure further provides a server. The server may include: a processor and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement: acquiring a historical advertisement set, wherein the historical advertisement set comprises at least one historical advertisement indicated by negative feedback behavior data of a user and a negative feedback indication value of the historical advertisement; determining a negative feedback indicated value of each advertisement to be recommended in the advertisement set to be recommended according to the negative feedback indicated value of each historical advertisement in the historical advertisement set and the similarity between each advertisement to be recommended in the advertisement set to be recommended and each historical advertisement in the historical advertisement set; and determining the advertisements to be recommended, of which the negative feedback indicated value is greater than a preset threshold value, in the set of advertisements to be recommended as the advertisements meeting the negative feedback behavior triggering condition of the user.

In an exemplary embodiment, the present disclosure also provides a computer-readable storage medium having stored thereon instructions that, when executed by a processor, implement: acquiring a historical advertisement set, wherein the historical advertisement set comprises at least one historical advertisement indicated by negative feedback behavior data of a user and a negative feedback indication value of the historical advertisement; determining a negative feedback indicated value of each advertisement to be recommended in the advertisement set to be recommended according to the negative feedback indicated value of each historical advertisement in the historical advertisement set and the similarity between each advertisement to be recommended in the advertisement set to be recommended and each historical advertisement in the historical advertisement set; and determining the advertisements to be recommended, of which the negative feedback indicated value is greater than a preset threshold value, in the set of advertisements to be recommended as the advertisements meeting the negative feedback behavior triggering condition of the user.

The computer readable storage medium may be a non-transitory computer readable storage medium, which may be, for example, a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

Optionally, an embodiment of the present disclosure further provides a computer program product, where the computer program product, when executed, implements: acquiring a historical advertisement set, wherein the historical advertisement set comprises at least one historical advertisement indicated by negative feedback behavior data of a user and a negative feedback indication value of the historical advertisement; determining a negative feedback indicated value of each advertisement to be recommended in the advertisement set to be recommended according to the negative feedback indicated value of each historical advertisement in the historical advertisement set and the similarity between each advertisement to be recommended in the advertisement set to be recommended and each historical advertisement in the historical advertisement set; and determining the advertisements to be recommended, of which the negative feedback indicated value is greater than a preset threshold value, in the set of advertisements to be recommended as the advertisements meeting the negative feedback behavior triggering condition of the user.

It is to be understood that, when the electronic device or the server is operated, the instructions stored on the computer-readable storage medium are executed, or the computer program product is executed, other steps of the advertisement identification method described in the foregoing method embodiments of the present disclosure may also be implemented, and are not described in detail herein.

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 application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the 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 will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. An advertisement identification method, the method comprising:

acquiring a historical advertisement set, wherein the historical advertisement set comprises at least one historical advertisement indicated by negative feedback behavior data of a user and a negative feedback indication value of the historical advertisement;

determining a negative feedback indicated value of each advertisement to be recommended in the advertisement set to be recommended according to the negative feedback indicated value of each historical advertisement in the historical advertisement set and the similarity between each advertisement to be recommended in the advertisement set to be recommended and each historical advertisement in the historical advertisement set;

and determining the advertisements to be recommended, of which the negative feedback indicated value is greater than a preset threshold value, in the set of advertisements to be recommended as the advertisements meeting the triggering condition of the negative feedback behavior of the user.

2. The method of claim 1, wherein the determining the negative feedback indication value of each advertisement in the set of advertisements to be recommended according to the negative feedback indication value of each historical advertisement in the set of historical advertisements and a similarity between each advertisement to be recommended in the set of advertisements to be recommended and each historical advertisement in the set of historical advertisements comprises:

for each advertisement to be recommended in the advertisement set to be recommended:

determining target similarity according to the similarity between the advertisement to be recommended and each historical advertisement in the historical advertisement set, wherein the target similarity is maximum similarity, average similarity or median similarity;

and determining a negative feedback indicated value of the advertisement to be recommended according to the target similarity and the negative feedback indicated value of each historical advertisement in the historical advertisement set.

3. The method of claim 2, wherein the negative feedback indication values of the historical ads in the set of historical ads are the same; the determining a negative feedback indication value of the advertisement to be recommended according to the target similarity and the negative feedback indication values of the historical advertisements in the historical advertisement set includes:

and obtaining the product of the target similarity and a negative feedback indicating value of any historical advertisement in the historical advertisement set as the negative feedback indicating value of the advertisement to be recommended.

4. The method of claim 2, wherein the determining a negative feedback indication value of the advertisement to be recommended according to the target similarity and a negative feedback indication value of each historical advertisement in the historical advertisement set comprises:

determining a target negative feedback indication value according to the negative feedback indication values of the historical advertisements in the historical advertisement set, wherein the target negative feedback indication value is a maximum negative feedback indication value, an average negative feedback indication value or a neutral negative feedback indication value;

and obtaining the product of the target similarity and the target negative feedback indicating value as the negative feedback indicating value of the advertisement to be recommended.

5. The method of claim 2, wherein before determining the target similarity according to the similarity between the advertisement to be recommended and each historical advertisement in the historical advertisement set, the method further comprises:

and determining the similarity between the advertisement to be recommended and each historical advertisement in the historical advertisement set.

6. The method of claim 1, wherein after determining that the to-be-recommended advertisement in the set of to-be-recommended advertisements with the negative feedback indication value larger than a preset threshold is an advertisement that satisfies a negative feedback behavior triggering condition of a user, the method further comprises:

filtering the advertisements meeting the negative feedback behavior triggering condition of the user in the advertisement set to be recommended;

according to a preset ordering rule, ordering the advertisements in the advertisement set to be recommended after the advertisements meeting the negative feedback behavior triggering condition of the user are filtered;

and advertising according to the sequencing result.

7. An advertisement recognition apparatus, comprising:

an obtaining module configured to obtain a historical advertisement set, wherein the historical advertisement set comprises at least one historical advertisement indicated by negative feedback behavior data of a user and a negative feedback indication value of the historical advertisement;

the first determination module is configured to determine a negative feedback indication value of each advertisement to be recommended in the advertisement set to be recommended according to the negative feedback indication value of each historical advertisement in the historical advertisement set and the similarity between each advertisement to be recommended in the advertisement set to be recommended and each historical advertisement in the historical advertisement set;

and the second determination module is configured to determine that the advertisements to be recommended, of which the negative feedback indication values are greater than a preset threshold value, in the set of advertisements to be recommended are the advertisements meeting the negative feedback behavior triggering condition of the user.

8. An electronic device, comprising: a processor and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement:

9. A server, comprising: a processor and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement:

10. A computer-readable storage medium having instructions stored thereon, the instructions when executed by a processor implementing: