Advertisement recognition method, device, electronic device and storage medium

Abstract

The present disclosure relates to an advertisement identification method, device, electronic device and storage medium, and relates to the field of network technology. The present disclosure can obtain a historical advertisement set, and determine the 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. Then, it can be determined that the advertisement to be recommended in the advertisement set to be recommended whose negative feedback indication value is greater than a preset threshold is an advertisement that meets the user's negative feedback behavior trigger condition. It is able to more comprehensively identify more advertisements that meet the user's negative feedback behavior trigger condition, thereby improving the recognition accuracy of advertisements that meet the user's negative feedback behavior trigger condition, improving the quality of advertisement delivery, and ensuring the user's service experience.

Description

Technical Field

[0001] The present disclosure relates to the field of network technology, and in particular to an advertisement recognition method, device, electronic device and storage medium. Background Art

[0002] Advertising platforms can be used to deliver advertisements to users, such as video ads, image ads, web page ads, etc. However, there is often a phenomenon that users dislike some advertisements. Therefore, in order to ensure the long-term development of advertising delivery platforms, when delivering advertisements to users, it is necessary to consider the advertisements that users dislike and ensure the user's service experience.

[0003] In the prior art, advertising delivery platforms usually adopt an adaptive strategy for advertising recommendation based on user behavior to ensure the user's service experience. For example, before recommending advertisements to users, the advertising delivery platform can identify the advertisements that users dislike from the advertisements to be recommended based on the user's negative feedback behavior data on the advertisements, and intervene in the advertisements that users dislike according to established rules and manual review, such as blocking, reducing the number of recommendations, etc., so as to ensure the service experience of the advertising delivery platform for users.

[0004] However, the above existing advertising recommendation methods are not accurate enough in identifying advertisements that users dislike, which seriously affects the user's service experience. For example, if the negative feedback behavior data indicates that the user dislikes the advertisement of a certain product A, the existing advertising recommendation method can only identify the advertisement about product A as the advertisement that the user dislikes, while the user may actually be more disgusted with other advertisements that are close or similar to product A, which has great limitations. Summary of the invention

[0005] The present disclosure provides an advertisement recognition method, device, electronic device and storage medium, which can more accurately identify advertisements that users dislike when placing advertisements.

[0006] The technical solution of the embodiment of the present disclosure is as follows:

[0007] In a first aspect, an embodiment of the present disclosure provides an advertisement identification method, which may include: obtaining a historical advertisement set, the historical advertisement set including at least one historical advertisement indicated by a user's negative feedback behavior data, and a negative feedback indication value of the historical advertisement; determining the negative feedback indication value of each to-be-recommended advertisement in the to-be-recommended advertisement set according to the negative feedback indication value of each historical advertisement in the historical advertisement set and the similarity between each to-be-recommended advertisement in the to-be-recommended advertisement set and each historical advertisement in the historical advertisement set; determining that the to-be-recommended advertisement in the to-be-recommended advertisement set whose negative feedback indication value is greater than a preset threshold is an advertisement that meets the user's negative feedback behavior trigger condition.

[0008] Among them, the negative feedback behavior data is used to indicate that the user has negative feedback behavior on the advertisement. The user's negative feedback behavior on the advertisement indicates that the user dislikes the advertisement. The negative feedback indicator value can indicate the user's dislike for the advertisement. The larger the negative feedback indicator value, the higher the dislike. Advertisements that meet the user's negative feedback behavior trigger condition are advertisements that the user may dislike.

[0009] Optionally, the above-mentioned step of determining the negative feedback indication value of each advertisement in the to-be-recommended advertisement set according to the negative feedback indication value of each historical advertisement in the historical advertisement set and the similarity between each to-be-recommended advertisement in the to-be-recommended advertisement set and each historical advertisement in the historical advertisement set may include: for each to-be-recommended advertisement in the to-be-recommended advertisement set: determining a target similarity according to the similarity between the to-be-recommended advertisement and each historical advertisement in the historical advertisement set, the target similarity being the maximum similarity, the average similarity or the median similarity; determining the negative feedback indication value of the to-be-recommended advertisement according to the target similarity and the negative feedback indication value of each historical advertisement in the historical advertisement set.

[0010] In one implementation, the negative feedback indicator values ​​of each historical advertisement in the historical advertisement set are all the same. The step of determining the negative feedback indicator value of the advertisement to be recommended based on the target similarity and the negative feedback indicator value of each historical advertisement in the historical advertisement set may include: obtaining the product of the target similarity and the negative feedback indicator value of any historical advertisement in the historical advertisement set as the negative feedback indicator value of the advertisement to be recommended.

[0011] In another embodiment, the step of determining the negative feedback indication value of the advertisement to be recommended based on 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 based on the negative feedback indication value of each historical advertisement in the historical advertisement set, the target negative feedback indication value being the maximum negative feedback indication value, the average negative feedback indication value or the median negative feedback indication value; and obtaining the product of the target similarity and the target negative feedback indication value as the negative feedback indication value of the advertisement to be recommended.

[0012] Optionally, before the step of determining the target similarity according to the similarities between the advertisement to be recommended and each historical advertisement in the historical advertisement set, the method may further include: determining the similarities between the advertisement to be recommended and each historical advertisement in the historical advertisement set.

[0013] Optionally, after the above step of determining that the advertisements to be recommended whose negative feedback indication values ​​in the advertisement set to be recommended are greater than a preset threshold value are advertisements that meet the user's negative feedback behavior trigger conditions, the method may further include: filtering out the advertisements in the advertisement set to be recommended that meet the user's negative feedback behavior trigger conditions; sorting the advertisements in the advertisement set to be recommended after filtering out the advertisements that meet the user's negative feedback behavior trigger conditions according to preset sorting rules; and delivering the advertisements according to the sorting results.

[0014] Optionally, before the above step of obtaining a historical advertisement set, the method may further include: collecting negative feedback behavior data of the user within a preset time period, the negative feedback behavior data being used to indicate that the user has negative feedback behavior on the advertisement; and generating a historical advertisement set based on the negative feedback behavior data.

[0015] Optionally, the historical advertisements in the above historical advertisement set are all different.

[0016] Optionally, the advertisements to be recommended in the above-mentioned set of advertisements to be recommended may include any one or more of the following: picture advertisements, video advertisements, web page advertisements, email advertisements, text link advertisements, and dynamic banner advertisements.

[0017] In a second aspect, an embodiment of the present disclosure provides an advertisement identification device, which may include: an acquisition module, which may be configured to acquire a historical advertisement set; the historical advertisement set includes at least one historical advertisement indicated by the user's negative feedback behavior data, and a negative feedback indication value of the historical advertisement; a first determination module, which may be configured to determine the negative feedback indication value of each to-be-recommended advertisement in the to-be-recommended advertisement set based on the negative feedback indication value of each historical advertisement in the historical advertisement set and the similarity between each to-be-recommended advertisement in the to-be-recommended advertisement set and each historical advertisement in the historical advertisement set; and a second determination module, which may be configured to determine that the to-be-recommended advertisement in the to-be-recommended advertisement set whose negative feedback indication value is greater than a preset threshold is an advertisement that meets the user's negative feedback behavior trigger condition.

[0018] Optionally, the first determination module can be specifically configured to, for each advertisement to be recommended in the set of advertisements to be recommended: determine a target similarity based on the similarity between the advertisement to be recommended and each historical advertisement in the set of historical advertisements, where the target similarity is a maximum similarity, an average similarity or a median similarity; and determine a negative feedback indication value of the advertisement to be recommended based on the target similarity and the negative feedback indication value of each historical advertisement in the set of historical advertisements.

[0019] In one implementation, the negative feedback indication value of each historical advertisement in the historical advertisement set is the same; the first determination module is specifically configured to obtain the product of the target similarity and the negative feedback indication value of any historical advertisement in the historical advertisement set as the negative feedback indication value of the advertisement to be recommended.

[0020] In another embodiment, the first determination module is specifically configured to determine a target negative feedback indication value based on the negative feedback indication values ​​of each historical advertisement in the historical advertisement set, where the target negative feedback indication value is the maximum negative feedback indication value, the average negative feedback indication value or the median negative feedback indication value; and obtain the product of the target similarity and the target negative feedback indication value as the negative feedback indication value of the advertisement to be recommended.

[0021] Optionally, the device may further include: a third determination module, which may be configured to determine the similarity between the advertisement to be recommended and each historical advertisement in the historical advertisement set.

[0022] Optionally, the device may also include: a filtering module, a sorting module and a delivery module; the filtering module can be configured to filter out advertisements in the set of advertisements to be recommended that meet the user's negative feedback behavior trigger conditions; the sorting module can be configured to sort the advertisements in the set of advertisements to be recommended after filtering out the advertisements that meet the user's negative feedback behavior trigger conditions according to preset sorting rules; the delivery module can be configured to deliver advertisements according to the sorting results.

[0023] Optionally, the device may also include: a collection module and a generation module; the collection module may be configured to collect negative feedback behavior data of the user within a preset time period, the negative feedback behavior data being used to indicate that the user has negative feedback behavior on the advertisement; the generation module may be configured to generate a historical advertisement collection based on the negative feedback behavior data.

[0024] Optionally, the historical advertisements in the above historical advertisement set are all different.

[0025] Optionally, the advertisements to be recommended in the above-mentioned set of advertisements to be recommended include any one or more of the following: picture advertisements, video advertisements, web page advertisements, email advertisements, text link advertisements, and dynamic banner advertisements.

[0026] In a third aspect, an embodiment of the present disclosure provides an electronic device, comprising: a processor and a memory for storing processor executable instructions; wherein the processor is configured to execute instructions to achieve: obtaining a historical advertisement set, the historical advertisement set including at least one historical advertisement indicated by the user's negative feedback behavior data, and a negative feedback indication value of the historical advertisement; determining the negative feedback indication value of each to-be-recommended advertisement in the to-be-recommended advertisement set according to the negative feedback indication value of each historical advertisement in the historical advertisement set and the similarity between each to-be-recommended advertisement in the to-be-recommended advertisement set and each historical advertisement in the historical advertisement set; determining that the to-be-recommended advertisement in the to-be-recommended advertisement set whose negative feedback indication value is greater than a preset threshold is an advertisement that meets the user's negative feedback behavior trigger condition.

[0027] In a fourth aspect, an embodiment of the present disclosure provides a server, comprising: a processor and a memory for storing processor executable instructions; wherein the processor is configured to execute instructions to achieve: obtaining a historical advertisement set, the historical advertisement set including at least one historical advertisement indicated by the user's negative feedback behavior data, and a negative feedback indication value of the historical advertisement; determining the negative feedback indication value of each to-be-recommended advertisement in the to-be-recommended advertisement set according to the negative feedback indication value of each historical advertisement in the historical advertisement set and the similarity between each to-be-recommended advertisement in the to-be-recommended advertisement set and each historical advertisement in the historical advertisement set; determining that the to-be-recommended advertisement in the to-be-recommended advertisement set whose negative feedback indication value is greater than a preset threshold is an advertisement that meets the user's negative feedback behavior trigger condition.

[0028] In a fifth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having instructions stored thereon, which, when executed by a processor, implement the following: obtaining a historical advertisement set, the historical advertisement set including at least one historical advertisement indicated by the user's negative feedback behavior data, and a negative feedback indication value of the historical advertisement; determining the negative feedback indication value of each to-be-recommended advertisement in the to-be-recommended advertisement set according to the negative feedback indication value of each historical advertisement in the historical advertisement set and the similarity between each to-be-recommended advertisement in the to-be-recommended advertisement set and each historical advertisement in the historical advertisement set; determining that the to-be-recommended advertisement in the to-be-recommended advertisement set whose negative feedback indication value is greater than a preset threshold is an advertisement that meets the user's negative feedback behavior trigger condition.

[0029] In a sixth aspect, an embodiment of the present disclosure provides a computer program product, which, when executed, implements: obtaining a historical advertisement set, the historical advertisement set including at least one historical advertisement indicated by the user's negative feedback behavior data, and a negative feedback indication value of the historical advertisement; determining the negative feedback indication value of each to-be-recommended advertisement in the to-be-recommended advertisement set based on the negative feedback indication value of each historical advertisement in the historical advertisement set and the similarity between each to-be-recommended advertisement in the to-be-recommended advertisement set and each historical advertisement in the historical advertisement set; determining that the to-be-recommended advertisement in the to-be-recommended advertisement set whose negative feedback indication value is greater than a preset threshold is an advertisement that meets the user's negative feedback behavior trigger condition.

[0030] The technical solution provided by the embodiments of the present disclosure brings at least the following beneficial effects:

[0031] The disclosed embodiment can obtain a historical advertisement set, which includes at least one historical advertisement indicated by the user's negative feedback behavior data, and a negative feedback indication value of the historical advertisement. 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, the negative feedback indication value of each advertisement to be recommended in the advertisement set to be recommended can be determined. Then, it can be determined that the advertisement to be recommended in the advertisement set to be recommended whose negative feedback indication value is greater than a preset threshold is an advertisement that meets the user's negative feedback behavior trigger condition (that is, an advertisement that the user dislikes). Thereby, it is possible to identify the advertisement to be recommended in the advertisement set to be recommended that meets the user's negative feedback behavior trigger condition based on the negative feedback indication value of each advertisement to be recommended. The negative feedback indication value of each advertisement to be recommended is determined based on the negative feedback indication value of each historical advertisement in the historical advertisement set, as well as the similarity between the advertisement to be recommended and each historical advertisement in the historical advertisement set. This allows for more comprehensive identification of more advertisements that meet the user's negative feedback behavior trigger conditions when identifying advertisements to be recommended that meet the user's negative feedback behavior trigger conditions based on the negative feedback indication value of each advertisement to be recommended, thereby improving the accuracy of identifying advertisements that meet the user's negative feedback behavior trigger conditions, improving the quality of advertising delivery, and ensuring the user's service experience.

[0032] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.

[0034] Figure 1A schematic diagram of an application scenario provided by an embodiment of the present disclosure;

[0035] Figure 2 A flowchart of an advertisement identification method provided by an embodiment of the present disclosure;

[0036] Figure 3 Another schematic diagram of a flow chart of an advertisement identification method provided by an embodiment of the present disclosure;

[0037] Figure 4 Another flowchart of the advertisement identification method provided by the embodiment of the present disclosure;

[0038] Figure 5 Another flowchart of the advertisement identification method provided by the embodiment of the present disclosure;

[0039] Figure 6 A schematic diagram of the process of advertisement delivery provided by the embodiment of the present disclosure;

[0040] Figure 7 A schematic diagram of the structure of an advertisement recognition device provided in an embodiment of the present disclosure;

[0041] Figure 8 Another structural schematic diagram of the advertisement identification device provided by the embodiment of the present disclosure;

[0042] Fig. 9 Another structural diagram of an advertisement identification device provided by an embodiment of the present disclosure;

[0043] Fig.10 Another structural diagram of an advertisement identification device provided by an embodiment of the present disclosure;

[0044] Fig.11 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0045] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.

[0046] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0047] It should also be understood that the term “comprising” indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements and / or components.

[0048] First, the application scenarios of the embodiments of the present disclosure are described:

[0049] Figure 1 A schematic diagram of an application scenario provided by an embodiment of the present disclosure, such as Figure 1 As shown, 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 via a wired network or a wireless network.

[0050] The server 110 may be a data server of the advertising delivery platform, and may be used to store and process advertising data. For example, the server 110 may store advertisements to be recommended to users by the advertising delivery platform, and the server 110 may send the advertisements to be recommended to the user terminal 120 through the aforementioned wired network or wireless network, so that the user terminal 120 may display the advertisements to the user, thereby completing the delivery of the advertisements.

[0051] Optionally, the server 110 may also include a database or be connected to a database, and the advertisements to be recommended may also be stored in the database. For example, the advertisements to be recommended may constitute a set of advertisements to be recommended and stored in the database. When an advertisement needs to be recommended, the server 110 may call the database and extract the advertisements to be recommended from the set of advertisements to be recommended.

[0052] Optionally, the advertisements to be recommended in the above-mentioned advertisement set to be recommended may include any one or more of the following: picture advertisements, video advertisements, web page advertisements, email advertisements, text link advertisements, and dynamic banner advertisements. The present disclosure does not limit the specific types of advertisements to be recommended.

[0053] In some embodiments, the server 110 may be a single server, or a server cluster composed of multiple servers. In some implementations, the server cluster may also be a distributed cluster. The present disclosure does not limit the specific implementation of the server 110.

[0054] Optionally, the advertising delivery platform may be some advertising service platforms specifically used for advertising delivery, or it may be other service platforms such as live broadcast platforms, short video platforms, shopping platforms, food delivery platforms, sharing service platforms, dating platforms, functional websites, etc. that are integrated with advertising delivery functions. The present disclosure does not limit the specific types of advertising delivery platforms.

[0055] In addition, in the above application scenarios, the user terminal 120 can be a personal smart device such as a mobile phone or a tablet computer, or can also be a laptop computer, a desktop computer, a television, a projector, or other devices. Take the case where the user terminal 120 is a mobile phone and the advertising delivery platform is a live broadcast platform as an example: when the user opens the application of the live broadcast platform through the mobile phone, he can watch the live broadcast on the live broadcast platform. The server of the live broadcast platform can send the recommended advertisements to the user's mobile phone through the network, and the mobile phone can display the recommended advertisements sent by the server to the user through the application interface of the live broadcast platform to realize advertising delivery. It should be noted that the disclosed embodiment also does not limit the type of user terminal 120.

[0056] It can be understood that in the above application scenario, the server 110 can establish a connection with multiple identical or different user terminals 120 through a network to implement advertisement delivery to users corresponding to the multiple user terminals 120. Optionally, when delivering advertisements to users corresponding to multiple user terminals 120, the advertisements received by each user terminal 120 can be the same or different, which is not limited here.

[0057] Based on the above Figure 1 In the application scenario shown, the embodiment of the present disclosure provides an advertisement identification method, which can more accurately identify advertisements that users dislike when delivering advertisements.

[0058] In some implementation modes, the execution subject of the method may be the aforementioned Figure 1 The server in the application scenario shown, for example, can identify advertisements that are disliked by users in the set of advertisements to be recommended, so as to reduce the number of recommendations of the advertisements that are disliked by users when delivering advertisements to users, or block the disliked advertisements from users.

[0059] Alternatively, in other implementations, the executor 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 disliked by the user. Similarly, when serving advertisements to the user, the number of recommendations for advertisements that are disliked by the user may be reduced, or the disliked advertisements may be blocked from the user.

[0060] Alternatively, in other implementations, the server and the user terminal may respectively execute partial steps of the method to jointly implement the complete process of the method.

[0061] It should be noted that the present disclosure does not limit the execution subject of the method.

[0062] Figure 2 A flowchart of an advertisement identification method provided in an embodiment of the present disclosure.

[0063] like Figure 2 As shown, the advertisement identification method may include:

[0064] S201. Obtain a historical advertisement collection.

[0065] The historical advertisement set may include at least one historical advertisement indicated by the user's negative feedback behavior data, and the negative feedback indicator value of each historical advertisement. The user's negative feedback behavior data refers to some negative feedback behaviors of the user on a certain advertisement. The historical advertisements indicated by the user's negative feedback behavior data can be understood as historical advertisements that the user dislikes. The negative feedback indicator value of the historical advertisement can indicate the user's dislike for the historical advertisement, such as: the larger the negative feedback indicator value, the greater the dislike.

[0066] The above historical advertisement collection can be obtained by collecting and analyzing the user's negative feedback behavior data. For example, when a user is browsing a web page, if he sees an advertisement pushed on the web page, the user can click "Close Ads", "Block Ads", etc. By counting similar behaviors of users towards advertisements, the user's negative feedback behavior data can be obtained, and by analyzing the user's negative feedback behavior data, it can be known whether the user is disgusted with the advertisement. For example: when the user sees Ad A, he clicks "Block Ads", which means that the user is disgusted with Ad A. That is, the historical advertisements indicated by the user's negative feedback behavior data can include Ad A.

[0067] By collecting and analyzing the negative feedback behavior data of each user in the above manner, we can obtain the historical advertisements indicated by the negative feedback behavior data of each user, or the advertisements that each user dislikes, thereby forming a historical advertisement set corresponding to each user.

[0068] Optionally, the historical advertisement set may be stored in a user terminal or in a server. When stored in the user terminal, the server may obtain the historical advertisement set from the user terminal; when stored in the server, the server may directly obtain the historical advertisement set.

[0069] Based on this understanding, please refer to Figure 3 As shown: Figure 3 This is another flowchart of the advertisement identification method provided by the embodiment of the present disclosure. In the embodiment of the present disclosure, before the above step S201, the advertisement identification method may further include:

[0070] S301. Collect negative feedback behavior data of users within a preset time period.

[0071] Among them, negative feedback behavior data can be used to indicate that the user dislikes the advertisement. The preset time period can be a certain day, a certain few days, a certain few hours, etc. in the past, and the present disclosure does not limit the specific length of the preset time period.

[0072] S302: Generate a historical advertisement set based on the negative feedback behavior data.

[0073] For example, the negative feedback behavior data may include advertisement identifiers of historical advertisements that users have reported as being offensive, such as advertisement numbers, advertisement names, etc. Based on the advertisement identifiers of historical advertisements in the negative feedback behavior data, the historical advertisements corresponding to each historical advertisement identifier may be determined to generate a historical advertisement set. Alternatively, the negative feedback behavior data may also directly include historical advertisements that users are offensive to generate a historical advertisement set directly based on the negative feedback behavior data. The present disclosure does not limit the specific data type of the negative feedback behavior data.

[0074] After executing step S201, step S202 may be executed:

[0075] S202: Determine the negative feedback indicator value of each advertisement to be recommended in the set of advertisements to be recommended according to the negative feedback indicator 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.

[0076] Figure 4 Another flowchart of the advertisement identification method provided by the embodiment of the present disclosure is provided.

[0077] Alternatively, if Figure 4 As shown, the above step S202 may include:

[0078] For each ad to be recommended in the ad set to be recommended:

[0079] S401: Determine a target similarity based on the similarities between the advertisement to be recommended and each historical advertisement in the historical advertisement set.

[0080] In one embodiment, the target similarity may be the maximum similarity. For example, when the historical advertisement set contains multiple (multiple refers to two or more than two, the same in the following embodiments) historical advertisements indicated by the user's negative feedback behavior data (i.e., the user dislikes), the similarities between the advertisement to be recommended and each historical advertisement in the historical advertisement set are also multiple, and the maximum similarity can be obtained from the multiple similarities as the target similarity.

[0081] In another embodiment, the target similarity may also be an average similarity. Similarly, when the historical advertisement set includes multiple historical advertisements indicated by the user's negative feedback behavior data, the average of multiple similarities corresponding to the advertisements to be recommended may be calculated to obtain the average similarity as the target similarity.

[0082] In another embodiment, the target similarity may also be a median similarity. Similarly, when the historical advertisement set includes multiple historical advertisements indicated by the user's negative feedback behavior data, the median of multiple similarities may be selected from multiple similarities corresponding to the advertisement to be recommended, thereby obtaining the median similarity as the target similarity.

[0083] In other implementations, other methods may 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 position between 60% and 80% may be selected from multiple similarities as the target similarity, etc. The present disclosure does not limit the method for determining the target similarity.

[0084] It can be understood that when the historical advertisement set contains only one historical advertisement indicated by the user's negative feedback behavior data, the target similarity is unique, that is, the similarity between the advertisement to be recommended and the historical advertisement.

[0085] S402: Determine the negative feedback indicator value of the advertisement to be recommended according to the target similarity and the negative feedback indicator value of each historical advertisement in the historical advertisement set.

[0086] In some embodiments, the negative feedback indicator value (or referred to as the degree of disgust) of each historical advertisement in the historical advertisement set is the same. For example, the negative feedback indicator value of each historical advertisement in the historical advertisement set can be set to a unified preset value in advance, such as: if the user is disgusted with the advertisement, the negative feedback indicator value of the advertisement is a, a is a number greater than 0, and can be any number such as 1, 2, 3, 4, etc., and the present disclosure does not limit the size of a. Correspondingly, if the user is not disgusted with the advertisement, the negative feedback indicator value of the advertisement (i.e., the advertisement outside the historical advertisement set) can be 0.

[0087] When the negative feedback indicator values ​​of the historical advertisements in the historical advertisement set are all the same, the negative feedback indicator value of the advertisement to be recommended can be calculated based on the target similarity corresponding to the advertisement to be recommended and the negative feedback indicator value of any 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 indicator value of any historical advertisement in the historical advertisement set (the negative feedback indicator value of each historical advertisement is the same) can be calculated, and the product result is used as the negative feedback indicator value of the advertisement to be recommended.

[0088] Optionally, those skilled in the art may also expand the method of calculating the product between the target similarity corresponding to the advertisement to be recommended and the negative feedback indication value of any historical advertisement in the historical advertisement set as the negative feedback indication value of the advertisement to be recommended to other calculation methods according to the technical solution of the present disclosure, such as: the negative feedback indication value of the advertisement to be recommended may also be the result of squaring the aforementioned product or taking the square root thereof, etc. The present disclosure does not limit the product to be the only method.

[0089] In some other embodiments, the negative feedback indicator value of each historical advertisement in the historical advertisement set may also be different values, or may be partially the same. For example, the user's aversion to each historical advertisement may be counted, and a negative feedback indicator value may be set for the corresponding historical advertisement, such as: the negative feedback indicator value may be set to a closed interval of 0 to 1, when the negative feedback indicator value is 0, it indicates that the user is not averse to the historical advertisement; when the negative feedback indicator value is 1, it indicates that the user is extremely averse to the historical advertisement; when the negative feedback indicator value is other values ​​between 0 and 1, such as 0.5, 0.8, etc., it may respectively indicate different degrees of aversion of the user to the historical advertisement. Alternatively, the negative feedback indicator value of each historical advertisement in the historical advertisement set may be indicated by a closed interval of 1 to 2, a closed interval of 0 to 2, or other various different methods, which are not limited by the present disclosure.

[0090] When the negative feedback indicator values ​​of each historical advertisement in the historical advertisement set are different or partially the same, a target negative feedback indicator value can be first determined from multiple negative feedback indicator values, and then the product of the target negative feedback indicator value and the aforementioned target similarity is calculated as the negative feedback indicator value of the advertisement to be recommended. Among them, the determination of the target negative feedback indicator value can refer to the determination method of the aforementioned target similarity, such as: the target negative feedback indicator value can be the maximum negative feedback indicator value, the average negative feedback indicator value, the median negative feedback indicator value, etc. Alternatively, the negative feedback indicator value of the advertisement with the greatest similarity to the advertisement to be recommended in the historical advertisement set can be used as the target negative feedback indicator value. In addition, it should be noted that the present disclosure does not limit the method of calculating the product of the target negative feedback indicator value and the target similarity as the negative feedback indicator value of the advertisement to be recommended as the only method, which will not be repeated here.

[0091] It is understandable that, in actual implementation of the embodiments of the present disclosure, regardless of whether the negative feedback indicator values ​​of each historical advertisement in the historical advertisement set are the same or the negative feedback indicator values ​​of each historical advertisement in the historical advertisement set are different, the target negative feedback indicator value can be determined by determining the negative feedback indicator value, the maximum negative feedback indicator value, the average negative feedback indicator value, or the median negative feedback indicator 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 method for determining the target negative feedback indicator value.

[0092] After executing step S202, step S203 may be executed:

[0093] S203: Determine that the advertisements to be recommended whose negative feedback indication values ​​in the set of advertisements to be recommended are advertisements that meet the negative feedback behavior triggering condition of the user.

[0094] Among them, a certain advertisement meets the user's negative feedback behavior triggering condition means that when the advertisement is pushed to the user, the user may be disgusted with the advertisement and block it.

[0095] After determining the negative feedback indication value of each advertisement to be recommended in the advertisement set to be recommended based on 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, the advertisement to be recommended having a negative feedback indication value greater than a preset threshold in the advertisement set to be recommended can be determined as an advertisement that meets the user's negative feedback behavior trigger condition, so that when subsequently delivering advertisements to the user based on the advertisement set to be recommended, corresponding intervention processing can be performed on the advertisements in the advertisement set to be recommended that meet the user's negative feedback behavior trigger condition, such as: blocking processing, reducing the number of recommendations, etc.

[0096] Accordingly, the advertisements to be recommended whose negative feedback indicator value in the set of advertisements to be recommended is less than the preset threshold value can be considered as advertisements that do not meet the user's negative feedback behavior triggering condition (or advertisements that the user may not dislike). The advertisements to be recommended whose negative feedback indicator value is equal to the preset threshold value can be advertisements that meet the user's negative feedback behavior triggering condition, or advertisements that do not meet the user's negative feedback behavior triggering condition, and the present disclosure does not limit this.

[0097] Optionally, the specific numerical value of the preset threshold can be set according to actual needs and the value range of the negative feedback indication value of each historical advertisement in the set 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 can be 0.5, 0.6, 0.7, 0.8, 0.9, etc., and the present disclosure is not limited to this.

[0098] As can be seen from the above, the disclosed embodiment can obtain a historical advertisement set, and the historical advertisement set includes at least one historical advertisement indicated by the user's negative feedback behavior data, and a negative feedback indication value of the historical advertisement. According to the negative feedback indication value of each historical advertisement in the historical advertisement set, and the similarity between each to-be-recommended advertisement in the to-be-recommended advertisement set and each historical advertisement in the historical advertisement set, the negative feedback indication value of each to-be-recommended advertisement in the to-be-recommended advertisement set can be determined. Then, it can be determined that the to-be-recommended advertisement in the to-be-recommended advertisement set whose negative feedback indication value is greater than a preset threshold is an advertisement that meets the user's negative feedback behavior trigger condition (that is, an advertisement that the user dislikes). Thereby, it is possible to identify the to-be-recommended advertisements in the to-be-recommended advertisement set that meet the user's negative feedback behavior trigger condition based on the negative feedback indication value of each to-be-recommended advertisement. The negative feedback indication value of each advertisement to be recommended is determined based on the negative feedback indication value of each historical advertisement in the historical advertisement set, as well as the similarity between the advertisement to be recommended and each historical advertisement in the historical advertisement set. This allows for more comprehensive identification of more advertisements that meet the user's negative feedback behavior trigger conditions when identifying advertisements to be recommended that meet the user's negative feedback behavior trigger conditions based on the negative feedback indication value of each advertisement to be recommended, thereby improving the accuracy of identifying advertisements that meet the user's negative feedback behavior trigger conditions, improving the quality of advertising delivery, and ensuring the user's service experience.

[0099] Optionally, before the step of determining the target similarity according to the similarities between the advertisement to be recommended and each historical advertisement in the historical advertisement set, the method may further include: determining the similarities between the advertisement to be recommended and each historical advertisement in the historical advertisement set.

[0100] In one implementation, for each advertisement to be recommended, a similarity algorithm may be directly used to calculate the similarity between the advertisement to be recommended and each historical advertisement in the historical advertisement set. Then, the target similarity is determined based on the calculated similarity between the advertisement to be recommended and each historical advertisement in the historical advertisement set. In this implementation, the calculation of the similarity between the advertisement to be recommended and each historical advertisement in the historical advertisement set may be a real-time online calculation.

[0101] In another implementation, the similarity between any two advertisements to be recommended in the set of advertisements to be recommended may be calculated offline in advance. Since the historical advertisements in the set of historical advertisements are obtained based on the user's negative feedback behavior data, and the user's negative feedback behavior data is generated based on the advertisements delivered to the user by the advertising delivery platform, the advertisements delivered to the user by the advertising delivery platform are all advertisements to be recommended in the set of advertisements to be recommended. Therefore, the similarity between each advertisement to be recommended and each historical advertisement in the set of historical advertisements is included in the similarity between any two advertisements to be recommended in the set of advertisements to be recommended that has been calculated offline in advance. Accordingly, the above step of determining the similarity between the advertisement to be recommended and each historical advertisement in the set of historical advertisements may be: directly extracting the similarity between the advertisement to be recommended and each historical advertisement in the set of historical advertisements from the similarity between any two advertisements to be recommended in the set of advertisements to be recommended that has been calculated offline in advance.

[0102] Compared with the previous implementation, the similarity between the recommended advertisements and the historical advertisements in the historical advertisement set in this implementation does not need to be calculated online in real time, which can greatly reduce the online computing amount of the advertisement identification method, shorten the time consumed for advertisement identification, and improve the timeliness of advertisement delivery.

[0103] Optionally, in the embodiment of the present disclosure, when calculating the similarity, the similarity algorithm adopted may include: distance measurement algorithm (such as: Euclidean distance, Minkowski distance, Mahalanobis distance, Manhattan distance, etc.), similarity measurement algorithm (such as: vector space cosine similarity, Pearson correlation, etc.).

[0104] Take image ads as an example:

[0105] Assume that the advertisement to be recommended is picture 1, and the advertisement in the historical advertisement set is picture 2. Picture 1 can be represented as vector 1, and picture 2 can be represented as vector 2. Then, the cosine distance between vector 1 and vector 2 is calculated, and the cosine distance between vector 1 and vector 2 is used to represent the similarity between picture 1 and picture 2.

[0106] It should be noted that different similarity algorithms may be used to calculate different types of advertisements, and the embodiments of the present disclosure do not limit the specific type of the similarity algorithm.

[0107] Optionally, in any embodiment of the present disclosure, the historical advertisements in the historical advertisement set may all be different, that is, each historical advertisement in the historical advertisement set may be non-repetitive.

[0108] A user may give negative feedback to the same advertisement twice or more. In the historical advertisement set generated based on the user's negative feedback behavior data, repeated historical advertisements may appear. That is, the same historical advertisement may appear multiple times (twice or more). When there are too many repeated historical advertisements, there will be more meaningless repeated calculations in the above similarity calculation process (including real-time calculation or offline calculation). By processing the repeated historical advertisements in the historical advertisement set, the historical advertisements in the historical advertisement set are made different, which can greatly improve the efficiency of subsequent similarity calculations, or reduce the amount of offline similarity data, further improving the timeliness of advertising delivery.

[0109] In some implementations, a historical advertisement set may be generated based on the user's negative feedback behavior data, and then duplicate historical advertisements in the historical advertisement set may be deleted. In other implementations, the user's negative feedback behavior data may be deduplicated first, and then a historical advertisement set may be generated, which is not limited in the present disclosure.

[0110] Take the preset time period as the past n days as an example, where n is an integer greater than 0:

[0111] Assume that the negative feedback behavior data submitted by user k in the past n days includes the following historical advertisement identifications (d1 to d n All are advertising logos):

[0112] {d1, d2, d3, d4, ..., d n};

[0113] Taking d1 as an example, the historical advertisement corresponding to d1 is C1. Based on the negative feedback behavior data submitted by user k in the past n days, the generated historical advertisement set can be as follows:

[0114] hate set(k，n) ={C1,C2,C3,C4,...,C n};

[0115] Among them, hate set(k，n) Represents the historical advertisement set generated based on the negative feedback behavior data submitted by user k in the past n days.

[0116] Assume that the above historical advertising collection is hate set(k，n) If there are two identical historical ads, such as C3 and C4, you can delete either C3 or C4. set(k，n) Perform deduplication and delete hate set(k，n) Repeated historical advertisements.

[0117] Figure 5Another flowchart of the advertisement identification method provided by the embodiment of the present disclosure is provided.

[0118] Alternatively, if Figure 5 As shown, after the above step of determining that the advertisements to be recommended whose negative feedback indication value is greater than the preset threshold in the set of advertisements to be recommended are advertisements that meet the user's negative feedback behavior triggering condition, the method may further include:

[0119] S501: Filter out advertisements that meet the user's negative feedback behavior triggering condition from the set of advertisements to be recommended.

[0120] S502: Sort the advertisements in the set of advertisements to be recommended after filtering out advertisements that meet the user's negative feedback behavior triggering condition according to a preset sorting rule.

[0121] S503: Place advertisements according to the ranking results.

[0122] Among them, the preset sorting rules can be advertising delivery rules. For example, for the set of advertisements to be recommended after filtering out advertisements that meet the user's negative feedback behavior trigger conditions (i.e., user dislike), the remaining advertisements to be recommended in the set can be sorted according to the delivery proportion, frequency, time period requirements, etc. of the advertisements to be recommended (or other priority setting rules). Then, the advertisements can be delivered in sequence according to the sorting results, or a preset number of advertisements to be recommended can be selected for delivery, and the preset number can be 1, 2, 3 or more.

[0123] For example:

[0124] Assume that there is a set B to be recommended as follows:

[0125] B={B1, ​​B2, B3, B4, B5, B6};

[0126] If according to the advertisement identification method described in the aforementioned embodiment of the present disclosure, the advertisements in the to-be-recommended set B that meet the user's negative feedback behavior trigger condition are B3, B5 and B6, respectively, and the priority of B1 is greater than the priority of B2, and the priority of B2 is greater than the priority of B4, then the advertisement delivery according to the sorting result can be to deliver the to-be-recommended advertisement B1 to the user.

[0127] In order to more clearly express the technical solution of the present disclosure, the application of the advertisement recognition method provided by the embodiment of the present disclosure in advertisement delivery is described below with a specific implementation method:

[0128] In this embodiment, the server of the advertising delivery platform and the user terminal can establish a connection through a wired network or a wireless network, and a set of advertisements to be recommended can be preset in the server, and the set of advertisements to be recommended includes M advertisements to be recommended. Before executing the advertisement identification method, the server can pre-calculate the similarity between each two advertisements to be recommended in the M advertisements to be recommended offline through a similarity model f. i With c j (c i With c j are all advertisements among the M advertisements to be recommended) based on the similarity S of the similarity model f i，j For example:

[0129] S i，j =f(c i , c j ), and S i，j =S j，i .

[0130] In addition, the user terminal can collect the user's negative feedback behavior data in the past n days and send it to the server, wherein the negative feedback behavior data can be used to indicate that the user has negative feedback behavior on the advertisement, that is, is disgusted with the advertisement. The server can generate a historical advertisement set based on the negative feedback behavior data, and the generated historical advertisement set is a subset of the above-mentioned advertisement set to be recommended. Furthermore, the server can also perform deduplication processing on the historical advertisement set and delete duplicate historical advertisements in the historical advertisement set.

[0131] Figure 6 A schematic diagram of the advertisement delivery process provided by an embodiment of the present disclosure.

[0132] like Figure 6 As shown, taking the target similarity as the maximum similarity and the negative feedback indicator value (i.e., the degree of disgust) of each historical advertisement in the historical advertisement set as 1 as an example, the steps of advertisement delivery may include:

[0133] S601: The user terminal sends an advertisement delivery request to the server.

[0134] For example, when a user opens an application or web page of a certain service platform on a user terminal, or opens a certain user terminal such as a TV or computer, the user terminal usually sends an advertisement delivery request to the server to obtain the recommended advertisements from the server and display them to the user. The advertisement delivery request may include a user terminal identifier or a user identifier, which may be a user's mobile phone number, a device number of the user terminal, or other user accounts.

[0135] S602: The server obtains a historical advertisement set.

[0136] 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.

[0137] S604: The server obtains the product of the maximum similarity corresponding to each advertisement to be recommended and 1, and obtains a negative feedback indication value of each advertisement to be recommended.

[0138] That is, user k treats the recommended ad c i The negative feedback indicator value h(k, i) can be as follows:

[0139]

[0140] Where hate_set(k, n) represents the historical advertisement set; max represents the maximum value; S(i, j) represents the advertisement to be recommended c i The similarity with each historical advertisement in the historical advertisement set.

[0141] S605: The server determines the advertisements to be recommended whose negative feedback indication values ​​in the set of advertisements to be recommended are greater than or equal to a preset threshold as advertisements that meet the negative feedback behavior triggering condition of the user.

[0142] S606: The server filters out advertisements that meet the user's negative feedback behavior triggering condition from the set of advertisements to be recommended.

[0143] S607: Sort the advertisements in the set of advertisements to be recommended after filtering out the advertisements that meet the user's negative feedback behavior triggering condition according to a preset sorting rule.

[0144] S608: The server determines the target advertisement to be recommended based on the ranking result and sends it to the user terminal.

[0145] S609: The user terminal displays the target advertisement to be recommended to the user.

[0146] As described above, through this implementation, advertisements that meet the user's negative feedback behavior triggering condition can be filtered out from the set of advertisements to be recommended, thereby shielding the user from advertisements that meet the user's negative feedback behavior triggering condition.

[0147] The set of advertisements in the set to be recommended that meet the negative feedback behavior triggering condition of user k (the set of advertisements blocked from user k) can be expressed as follows:

[0148] Shield(k,i)=I{h(k,i)≥T}, whereT≥0;

[0149] Among them, Shield(k, i) represents the set of advertisements in the to-be-recommended set that meet the negative feedback behavior triggering conditions of user k; I represents the elements in Shield(k, i); h(k, i) is the negative feedback indication value of each to-be-recommended advertisement; and T represents the preset threshold.

[0150] When T is equal to 0, Shield(k, i) is equal to the set of advertisements to be recommended, indicating that all advertisements to be recommended are blocked for user k; when T belongs to the open interval of 0 to 1, Shield(k, i) is a subset of the set of advertisements to be recommended, indicating that advertisements with negative feedback indication values ​​greater than or equal to T are blocked for 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, indicating that only historical advertisements indicated by negative feedback behavior data (i.e., historical advertisements in the set of historical advertisements) are blocked for user k.

[0151] The beneficial effects of this embodiment have been described in detail in the above embodiments and will not be repeated here.

[0152] The above description mainly introduces the solution provided by the embodiment of the present disclosure from the perspective of the server / user terminal. It is understandable that the server / user terminal may include one or more hardware structures and / or software modules for implementing the aforementioned advertising identification method, and these execution hardware structures and / or software modules may constitute an electronic device. Those skilled in the art should easily realize that, in combination with the algorithm steps of each example described in the embodiments disclosed herein, the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present disclosure.

[0153] Based on this, the embodiment of the present disclosure also provides an advertisement identification device, which can be fully integrated into the server / user terminal, or partially integrated into the server and partially integrated into the user terminal.

[0154] Figure 7 A schematic diagram of the structure of an advertisement recognition device provided in an embodiment of the present disclosure.

[0155] like Figure 7As shown, the advertisement identification device may include: an acquisition module 10, which may be configured to acquire a historical advertisement set, the historical advertisement set including at least one historical advertisement indicated by the user's negative feedback behavior data, and a negative feedback indication value of the historical advertisement. A first determination module 20, which may be configured to determine the 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. A second determination module 30, which may be configured to determine that the advertisement to be recommended in the advertisement set to be recommended whose negative feedback indication value is greater than a preset threshold is an advertisement that meets the user's negative feedback behavior trigger condition.

[0156] Optionally, the first determination module 20 can be specifically configured to, for each advertisement to be recommended in the set of advertisements to be recommended: determine a target similarity based on the similarity between the advertisement to be recommended and each historical advertisement in the set of historical advertisements, where the target similarity is a maximum similarity, an average similarity or a median similarity; and determine a negative feedback indication value of the advertisement to be recommended based on the target similarity and the negative feedback indication value of each historical advertisement in the set of historical advertisements.

[0157] In one embodiment, the negative feedback indicator values ​​of each historical advertisement in the historical advertisement set are the same. The first determination module 20 is specifically configured to obtain the product of the target similarity and the negative feedback indicator value of any historical advertisement in the historical advertisement set as the negative feedback indicator value of the advertisement to be recommended.

[0158] In another embodiment, the first determination module 20 is specifically configured to determine a target negative feedback indication value based on the negative feedback indication values ​​of each historical advertisement in the historical advertisement set, where the target negative feedback indication value is the maximum negative feedback indication value, the average negative feedback indication value or the median negative feedback indication value; and obtain the product of the target similarity and the target negative feedback indication value as the negative feedback indication value of the advertisement to be recommended.

[0159] Figure 8 Another structural schematic diagram of the advertisement identification device provided in an embodiment of the present disclosure.

[0160] Optionally, see Figure 8 As shown, the advertisement identification device may further include: a third determination module 40, which may be configured to determine the similarity between the advertisement to be recommended and each historical advertisement in the historical advertisement set.

[0161] Fig. 9 This is another structural schematic diagram of the advertisement identification device provided in an embodiment of the present disclosure.

[0162] Alternatively, if Fig. 9As shown, the advertisement identification device may further include: a filtering module 50, a sorting module 60 and a delivery module 70; the filtering module 50 may be configured to filter out advertisements that meet the user's negative feedback behavior triggering condition in the to-be-recommended advertisement set; the sorting module 60 may be configured to sort the advertisements in the to-be-recommended advertisement set after filtering out the advertisements that meet the user's negative feedback behavior triggering condition according to a preset sorting rule. The delivery module 70 may be configured to deliver advertisements according to the sorting result.

[0163] Fig.10 This is another structural schematic diagram of the advertisement identification device provided in an embodiment of the present disclosure.

[0164] Alternatively, if Fig.10 As shown, the advertisement identification device may further include: a collection module 80 and a generation module 90; the collection module 80 may be configured to collect negative feedback behavior data of the user within a preset time period, and the negative feedback behavior data is used to indicate that the user has negative feedback behavior on the advertisement. The generation module 90 may be configured to generate a historical advertisement set according to the negative feedback behavior data.

[0165] As described above, the embodiments of the present disclosure can divide the server / user terminal into functional modules according to the above method examples. Among them, the above integrated modules can be implemented in the form of hardware or in the form of software functional modules. In addition, it should be noted that the division of modules in the embodiments of the present disclosure is schematic and is only a logical functional division. There may be other division methods in actual implementation. For example, the advertising recognition device can divide each functional module corresponding to each function, or integrate two or more functions into one processing module.

[0166] Regarding the advertisement identification device in the above embodiment, the specific manner in which each module performs operations and the beneficial effects possessed have been described in detail in the above method embodiment and will not be repeated here.

[0167] The disclosed embodiment also provides an electronic device, which may be a user terminal such as the aforementioned mobile phone, tablet computer, computer, etc., or may be some large-screen display devices for outdoor advertising.

[0168] Fig.11 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure.

[0169] like Fig.11As shown, the electronic device may include: a processor 100 and a memory 200 for storing executable instructions of the processor 100; wherein the processor 100 is configured to execute instructions to achieve: obtaining a historical advertisement set, the historical advertisement set including at least one historical advertisement indicated by the user's negative feedback behavior data, and a negative feedback indication value of the historical advertisement; determining the negative feedback indication value of each to-be-recommended advertisement in the to-be-recommended advertisement set according to the negative feedback indication value of each historical advertisement in the historical advertisement set and the similarity between each to-be-recommended advertisement in the to-be-recommended advertisement set and each historical advertisement in the historical advertisement set; determining that the to-be-recommended advertisement in the to-be-recommended advertisement set whose negative feedback indication value is greater than a preset threshold is an advertisement that meets the user's negative feedback behavior trigger condition.

[0170] Optionally, the embodiment of the present disclosure further provides a server. The server may include: a processor and a memory for storing instructions executable by the processor; wherein the processor is configured to execute instructions to implement: obtaining a historical advertisement set, the historical advertisement set including at least one historical advertisement indicated by the user's negative feedback behavior data, and a negative feedback indication value of the historical advertisement; determining the 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; determining that the advertisement to be recommended in the advertisement set to be recommended whose negative feedback indication value is greater than a preset threshold is an advertisement that meets the negative feedback behavior trigger condition of the user.

[0171] In an exemplary embodiment, the present disclosure further provides a computer-readable storage medium having instructions stored thereon, which, when executed by a processor, implement the following steps: obtaining a historical advertisement set, the historical advertisement set including at least one historical advertisement indicated by the user's negative feedback behavior data, and a negative feedback indication value of the historical advertisement; determining the negative feedback indication value of each to-be-recommended advertisement in the to-be-recommended advertisement set according to the negative feedback indication value of each historical advertisement in the historical advertisement set and the similarity between each to-be-recommended advertisement in the to-be-recommended advertisement set and each historical advertisement in the historical advertisement set; determining that the to-be-recommended advertisement in the to-be-recommended advertisement set whose negative feedback indication value is greater than a preset threshold is an advertisement that meets the user's negative feedback behavior trigger condition.

[0172] The computer-readable storage medium may be a non-transitory computer-readable storage medium, for example, the non-transitory computer-readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0173] Optionally, the embodiments of the present disclosure further provide a computer program product, which, when executed, implements: obtaining a historical advertisement set, the historical advertisement set including at least one historical advertisement indicated by the user's negative feedback behavior data, and a negative feedback indication value of the historical advertisement; determining the negative feedback indication value of each to-be-recommended advertisement in the to-be-recommended advertisement set based on the negative feedback indication value of each historical advertisement in the historical advertisement set and the similarity between each to-be-recommended advertisement in the to-be-recommended advertisement set and each historical advertisement in the historical advertisement set; determining that the to-be-recommended advertisement in the to-be-recommended advertisement set whose negative feedback indication value is greater than a preset threshold is an advertisement that meets the user's negative feedback behavior trigger condition.

[0174] It is easy to understand that when the above-mentioned electronic device or server is running, when the instructions stored on the above-mentioned computer-readable storage medium are executed, or when the computer program product is executed, the other steps of the advertisement identification method described in the aforementioned method embodiment of the present disclosure can also be implemented, which will not be repeated here one by one.

[0175] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0176] It should be understood that the present disclosure is not limited to the exact structures that have been 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 recognition method, characterized in that: The method comprises: Acquire a historical advertisement set, the historical advertisement set including 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; For each advertisement to be recommended in the set of advertisements to be recommended, determining a target similarity according to similarities between the advertisement to be recommended and each historical advertisement in the set of historical advertisements; 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, including: when the negative feedback indication values ​​of each historical advertisement in the historical advertisement set are the same, obtaining the product of the target similarity and the negative feedback indication value of any historical advertisement in the historical advertisement set as the negative feedback indication value of the advertisement to be recommended; It is determined that the advertisements to be recommended in the set of advertisements to be recommended and whose negative feedback indication values ​​are greater than a preset threshold are advertisements that meet the negative feedback behavior triggering condition of the user.

2. The method according to claim 1, characterized in that The target similarity is a maximum similarity, an average similarity or a median similarity.

3. The method according to claim 2, characterized in that The 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 includes: Determining a target negative feedback indication value according to the negative feedback indication value of each historical advertisement 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 median negative feedback indication value; The product of the target similarity and the target negative feedback indicator value is obtained as the negative feedback indicator value of the advertisement to be recommended.

4. The method according to claim 2, characterized in that: Before determining the target similarity according to the similarities between the advertisement to be recommended and each historical advertisement in the historical advertisement set, the method further includes: Determine the similarity between the advertisement to be recommended and each historical advertisement in the historical advertisement set.

5. The method according to claim 1, characterized in that: After determining that the advertisements to be recommended whose negative feedback indication values ​​in the set of advertisements to be recommended are greater than a preset threshold are advertisements that meet the user's negative feedback behavior triggering condition, the method further includes: Filtering out advertisements that meet the user's negative feedback behavior triggering condition from the set of advertisements to be recommended; Sorting the advertisements in the set of advertisements to be recommended after filtering out the advertisements that meet the user's negative feedback behavior triggering condition according to a preset sorting rule; Advertisements are delivered based on the ranking results.

6. The method according to claim 1, characterized in that Before acquiring the historical advertisement set, the method further includes: Collecting negative feedback behavior data of users within a preset time period, wherein the negative feedback behavior data is used to indicate that the user has negative feedback behavior on the advertisement; The historical advertisement set is generated according to the negative feedback behavior data.

7. The method according to claim 6, characterized in that The historical advertisements in the historical advertisement set are all different.

8. The method according to any one of claims 1 to 7, characterized in that: The advertisements to be recommended in the set of advertisements to be recommended include any one or more of the following: picture advertisements, video advertisements, web page advertisements, email advertisements, text link advertisements, and dynamic banner advertisements.

9. An advertisement recognition device, characterized in that: The device comprises: An acquisition module is configured to acquire a historical advertisement set, wherein the historical advertisement set includes at least one historical advertisement indicated by the user's negative feedback behavior data and a negative feedback indication value of the historical advertisement; The first determination module is configured to determine, for each advertisement to be recommended in the advertisement set to be recommended, a target similarity according to the similarity between the advertisement to be recommended and each historical advertisement in the historical advertisement set; determine 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, including: when the negative feedback indication values ​​of each historical advertisement in the historical advertisement set are the same, obtain the product of the target similarity and the negative feedback indication value of any historical advertisement in the historical advertisement set as the negative feedback indication value of the advertisement to be recommended; The second determination module is configured to determine that the advertisements to be recommended whose negative feedback indication values ​​in the set of advertisements to be recommended are greater than a preset threshold value are advertisements that meet the negative feedback behavior triggering condition of the user.

10. The device according to claim 9, characterized in that The target similarity is a maximum similarity, an average similarity or a median similarity.

11. The device according to claim 10, characterized in that The first determination module is specifically configured to determine a target negative feedback indication value according to the negative feedback indication value of each historical advertisement 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 median negative feedback indication value; The product of the target similarity and the target negative feedback indicator value is obtained as the negative feedback indicator value of the advertisement to be recommended.

12. The device according to claim 10, characterized in that The device further includes: a third determining module configured to determine the similarity between the advertisement to be recommended and each historical advertisement in the historical advertisement set.

13. The device according to claim 9, characterized in that The device also includes: a filtering module, a sorting module and a delivery module; The filtering module is configured to filter out advertisements that meet the user's negative feedback behavior triggering condition in the set of advertisements to be recommended; The sorting module is configured to sort the advertisements in the set of advertisements to be recommended after filtering out advertisements that meet the user's negative feedback behavior triggering condition according to a preset sorting rule; The delivery module is configured to deliver advertisements according to the ranking results.

14. The device according to claim 9, characterized in that The device also includes: a collection module and a generation module; The collection module is configured to collect negative feedback behavior data of users within a preset time period, wherein the negative feedback behavior data is used to indicate that the user has negative feedback behavior on the advertisement; The generating module is configured to generate the historical advertisement set according to the negative feedback behavior data.

15. The device according to claim 14, characterized in that The historical advertisements in the historical advertisement set are all different.

16. The device according to any one of claims 9 to 15, characterized in that: The advertisements to be recommended in the set of advertisements to be recommended include any one or more of the following: picture advertisements, video advertisements, web page advertisements, email advertisements, text link advertisements, and dynamic banner advertisements.

17. An electronic device, characterized in that: include: A processor and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the advertisement identification method according to any one of claims 1-8.

18. A server, characterized in that: include: A processor and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the advertisement identification method according to any one of claims 1-8.

19. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the advertisement identification method according to any one of claims 1 to 8 is implemented.

Images