Method for filtering advertisement and server using the same

Abstract

The present invention relates to an ad filtering method and a detection server utilizing the same. An ad filtering method of a detection server according to one embodiment of the present invention may include: a step of collecting ad content displayed on a target web page within a web server; and a step of detecting ad content to be blocked based on ad text included in the ad content.

Description

Technology Field

[0001] The present invention relates to an ad filtering method capable of filtering out ad content that is vulgar or illegal, ad content that is not suitable for the purpose of the service, etc., among ad content displayed on a web page, and a detection server using the same. Background Technology

[0003] Traditionally, advertisements primarily consisted of using offline billboards or unilaterally delivering advertising content to users via TV or radio; however, with the advancement of network-related technologies, online advertising—which displays advertising content on parts of content pages when accessing a site through a network—has increased.

[0004] Due to the increase in such online advertising, some large network businesses were using a mutually beneficial system in which they displayed advertisements on content pages visible upon accessing their websites, using the fees received from advertisers to provide various services to users visiting the websites for free; this increased traffic to the websites for these services led to enhanced advertising effectiveness.

[0005] However, if advertisements displayed on content pages contain vulgar or illegal content, or content that does not align with the purpose of the service, problems may arise such as users forming a negative image of the website itself.

[0006] To prevent this, rule-based filtering was conventionally performed using the advertiser providing the advertisement or the ad URL address. However, problems exist, such as the difficulty of applying rule-based filtering when meta-information, including advertiser information or ad URL addresses, is intentionally tampered with or obfuscated. Prior art literature

[0008] Republic of Korea Published Patent Application No. 10-2009-0118335 The problem to be solved

[0009] The present invention aims to provide an ad filtering method capable of filtering ad content subject to blocking among ad content displayed on a web page, and a detection server utilizing the same.

[0010] The present invention aims to provide an ad filtering method capable of filtering ad content to be blocked based on text by applying OCR to ad images included in ad content, and a detection server utilizing the same. means of solving the problem

[0012] An ad filtering method of a detection server according to one embodiment of the present invention may include: a step of collecting ad content displayed on a target web page within a web server; and a step of detecting ad content to be blocked based on ad text included in the ad content.

[0013] A detection server according to one embodiment of the present invention may include an ad collection unit that collects ad content displayed on a target web page within a web server; and a blocking target detection unit that detects ad content to be blocked based on ad text included in the ad content.

[0014] In addition, the means for solving the above-mentioned problem do not enumerate all the features of the present invention. Various features of the present invention and the advantages and effects derived therefrom can be understood in more detail by referring to the specific embodiments below. Effects of the invention

[0016] According to an ad filtering method and a detection server utilizing the same according to an embodiment of the present invention, ad content subject to blocking can be identified based on the ad text included in each ad content displayed on a web server. That is, it is possible to determine whether an ad content subject to blocking is an ad content by analyzing the ad content itself, rather than meta-information such as the advertiser or ad URL address of the ad content. Therefore, ad content subject to blocking can be filtered even in cases where meta-information such as advertiser information or ad URL address is intentionally tampered with or obfuscated. Furthermore, it is possible to filter previously unknown advertisers or ad URL addresses in the same manner.

[0017] However, the effects that can be achieved by the ad filtering method according to the embodiments of the present invention and the detection server using the same are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art to which the present invention belongs from the description below. Brief explanation of the drawing

[0019] FIG. 1 is a schematic diagram showing an advertisement filtering system according to one embodiment of the present invention. FIG. 2 is a block diagram showing a detection server according to an embodiment of the present invention. FIG. 3 is a schematic diagram showing the operation of a detection server according to an embodiment of the present invention. FIG. 4 is a diagram showing an exemplary hardware configuration of a computing device in which methods according to various embodiments of the present invention can be implemented. FIG. 5 is a flowchart illustrating an ad filtering method according to one embodiment of the present invention. Specific details for implementing the invention

[0020] Hereinafter, embodiments disclosed in this specification will be described in detail with reference to the attached drawings. Identical or similar components regardless of drawing symbols will be assigned the same reference number, and redundant descriptions thereof will be omitted. The suffixes "module" and "part" for components used in the following description are assigned or used interchangeably solely for the ease of drafting the specification and do not inherently possess distinct meanings or roles. That is, the term "part" used in this invention refers to a hardware component such as software, FPGA, or ASIC, and the "part" performs certain roles. However, the meaning of "part" is not limited to software or hardware. The "part" may be configured to reside in an addressable storage medium or may be configured to run one or more processors. Accordingly, as an example, a 'part' includes components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functionality provided within the components and 'parts' may be combined into a smaller number of components and 'parts' or further separated into additional components and 'parts'.

[0021] In addition, when describing the embodiments disclosed in this specification, if it is determined that a detailed description of related prior art may obscure the essence of the embodiments disclosed in this specification, such detailed description is omitted. Furthermore, the attached drawings are intended only to facilitate understanding of the embodiments disclosed in this specification, and the technical concept disclosed in this specification is not limited by the attached drawings; it should be understood that they include all modifications, equivalents, and substitutions that fall within the spirit and technical scope of the present invention.

[0023] FIG. 1 is a schematic diagram showing an advertisement filtering system according to one embodiment of the present invention.

[0024] Referring to FIG. 1, an ad filtering system according to one embodiment of the present invention may include an ad server (A), a web server (B), and a detection server (100).

[0025] An advertisement filtering system according to an embodiment of the present invention will be described below with reference to FIG. 1.

[0027] An advertising server (A) can provide advertising content, etc. to multiple web servers (W), etc. A web server (W) can display the advertising content received from the advertising server (A) on a designated area within a web page and can receive compensation, such as money, from the advertising server (A) in exchange for displaying the advertising content. Here, the advertising server (A) may store a large amount of advertising content, etc. and can provide the advertising content to each web server (W) according to a pre-set algorithm, etc.

[0028] The ad server (A) may create an ad management page to provide the types and list of ad content provided to the web server (W), and may individually create and provide an ad management page corresponding to each web server (W). The administrator of the web server (W), etc., may access the ad management page to check the ad content displayed on their web server (W) and perform operations such as adding, deleting, or changing the ad content.

[0029] A web server (W) may include multiple web pages, etc., and may provide various types of content or services to multiple user terminals (1), etc. using the web pages, etc. According to an embodiment, the web server (W) may communicate with applications, etc. running on the user terminal (1), and may also provide content, etc. requested by the user through the applications. Specifically, the web server (W) may operate a server-based service that supports applications stored on the user terminal (1), and through this, may distribute content such as webtoons, web novels, digital books, and videos to the user terminal (1). Accordingly, an application installed on the user terminal (1) may automatically or in response to a user's request transmit a request for the provision of content to the web server (W), and may receive the requested content from the web server (W).

[0030] Here, the user terminal (1) can access the web server (W) by running various types of applications and can receive content from the web server (W) using the applications. The user terminal (1) can provide the received content to the user by displaying it visually, aurally, tactilely, etc. Here, the content is implemented as text, images, videos, audio, or a combination thereof, and may be comics, webtoons, web novels, digital books, videos, movies, dramas, etc.

[0031] The user terminal (1) may include a display unit for visually displaying provided content to the user, an input unit for receiving user input, a communication unit for supporting communication with a web server (W), a memory and a processor for storing at least one program.

[0032] The user terminal (1) may be a mobile terminal such as a smartphone or tablet PC, and depending on the embodiment, may also include a fixed device such as a desktop. Specifically, the user terminal (1) may include a mobile phone, a smartphone, a laptop computer, a digital broadcasting terminal, a PDA (personal digital assistants), a PMP (portable multimedia player), a slate PC, a tablet PC, an ultrabook, a wearable device (e.g., a smartwatch, a smart glass, a head-mounted display), etc.

[0033] A user terminal (1) can be connected to the internet, etc., through a network (N), and the network (N) connectable to the user terminal (1) may include wired networks and wireless networks. Specifically, the user terminal (1) may support communication with various networks such as a wired internet network, Wi-Fi (Wireless Fidelity), WiBro (Wireless Broadband Internet), Bluetooth, and a mobile communication network. However, the network according to the present invention is not limited to the networks listed above and may include known wireless data networks, known telephone networks, known wired or wireless television networks, etc.

[0034] The detection server (100) can extract inappropriate advertising content among the advertising content displayed on the web server (W) as advertising content to be blocked, and can provide a blocking list for these to the web server (W). For example, the detection server (100) can detect advertising content regarding goods or services that are not socially acceptable, such as prostitution or drugs, as advertising content to be blocked. Advertising content regarding prostitution, drugs, etc., must be blocked in advance by the advertising server (A), but there may be cases where it is not blocked by the advertising server (A), and in preparation for this, the detection server (100) can perform additional filtering.

[0035] In addition, according to the embodiment, it is possible for an administrator operating the web server (W) to independently set specific advertising content as advertising content subject to blocking. For example, the administrator may set advertising content that does not match the purpose of the service provided by the web server (W), advertising content regarding products or services of competitors, advertising content displayed in a foreign language, etc., as advertising content subject to blocking. In addition, advertising content containing sexually suggestive or inappropriate phrases, etc., may also be individually set as advertising content subject to blocking.

[0036] Conventionally, rule-based filtering was performed by storing metadata, such as advertisers providing the ad content to be blocked or the ad URL addresses of said content, and utilizing this information. However, a problem existed in that it was difficult to apply rule-based filtering when metadata, such as advertiser information or ad URL addresses, was intentionally tampered with or obfuscated. Furthermore, there was also a problem in that rules to filter previously unknown advertisers or ad URL addresses could not be created in advance.

[0037] Meanwhile, according to a detection server (100) according to an embodiment of the present invention, it is possible to determine whether an ad content is subject to blocking based on the ad texts included in each ad content displayed on a web server (W). That is, since it is possible to determine whether an ad content is subject to blocking by analyzing the ad content itself rather than the meta-information of the ad content, it is possible to solve existing problems. In addition, since the ad texts included in the ad content are intended to be displayed to the user and cannot be hidden or altered, detection can be performed more effectively. Hereinafter, a detection server (100) according to an embodiment of the present invention will be described with reference to FIGS. 2 and FIGS. 3.

[0039] Referring to FIG. 2, a detection server (100) according to one embodiment of the present invention may include an advertisement collection unit (110), a blocking target detection unit (120), and a blocking list transmission unit (130). Here, the detection server (100) or each of the components (110 to 130) constituting it may be implemented through a computing device illustrated in FIG. 4.

[0040] The ad collection unit (110) can collect ad content displayed on target web pages within the web server (A). The web server (A) may contain multiple web pages, and multiple ad content may be displayed on each web page. Here, the ad collection unit (110) can collect ad content displayed on pre-set target web pages among the multiple web pages included in the web server (A). The target web pages can be set by an administrator, etc., and according to the embodiment, it is also possible to set all web pages included in the web server (A) as target web pages.

[0041] Referring to FIG. 3, the ad collection unit (110) can crawl (C) the ad management page (P1), extract each ad content displayed on the ad management page (P1), and store the extracted ad content. That is, since each ad displayed on the target web page included in the web server (A) appears on the ad management page (P1), the ad collection unit (110) can crawl after accessing the ad management page (P1). Afterward, each ad content displayed on the ad management page (P1) can be stored in the ad content DB (D1). Here, the ad content may mostly include ad images, and the ad collection unit (110) can extract the ad images included in the ad content. At this time, each ad image may be stored in a separate image database (not shown). The ad collection unit (110) can perform crawling on the target web pages periodically (e.g., every day) according to a pre-set scheduler. In the case where multiple ad servers (A) provide advertisements to a single web server (W), there may be multiple ad management pages (P1) corresponding to each ad server (A). In this case, the ad collection unit (110) can crawl each ad management page (P1) individually and distinguish and store each ad content.

[0042] The blocking target detection unit (120) can detect blocking target advertising content based on the advertising text included in the advertising content. Here, if text is included separately from the advertising image within the advertising content, the text can be stored by including it in the advertising text. However, since text is mostly included within the advertising image included in the advertising content, the blocking target detection unit (120) can extract text from the advertising image.

[0043] That is, as illustrated in FIG. 3, the blocking target detection unit (120) can perform OCR (Optical Character Recognition) on the advertisement image to extract text contained within the advertisement image. The blocking target detection unit (120) can perform OCR directly on each advertisement image extracted from the advertisement receipt unit (110), or perform OCR sequentially on each advertisement image stored in the image database.

[0044] Subsequently, the blocking target detection unit (120) can generate an ad text including text extracted through OCR (O) and text included within the ad content, and input the ad text into a classification model (M) trained based on machine learning. Here, the classification model may be trained to classify the input ad text into a general ad group and a blocking target group. That is, if the classification model classifies the ad text as belonging to a pre-set blocking target group, the blocking target detection unit (120) can store the ad content corresponding to the ad text as the blocking target ad content. In this case, the blocking target ad content can be stored in the blocking list (D2), and the ad content corresponding to the remaining general ad group can be stored in the general ad list (not shown).

[0045] The classification model can be implemented using various neural network models, and the classification model can be pre-trained using a model learning unit (not shown). Specifically, the model learning unit can collect multiple advertising content as learning content from an advertising server (A) or an advertising management page of the advertising server (A). At this time, the model learning unit can exclude learning content that does not contain text from among the collected multiple learning content. That is, since the classification model detects advertising content to be blocked based on text included in the advertising content, the model learning unit can exclude content that does not contain text. For example, after performing OCR on the learning content, if characters are not recognized, it can be excluded from the learning content. In addition, the model learning unit can check whether stop words or duplicate text are included in the learning text extracted from the learning content, and the identified stop words or duplicate text can be excluded from the learning text.

[0046] According to an embodiment, the model learning unit may also add training data by performing text augmentation on the training texts. For example, new training data may be generated by replacing words included in the already generated training text, adding new words, or changing the positions of each word.

[0047] Subsequently, the model training unit can train a classification model based on supervised learning by marking whether each training data corresponds to blocked content. Depending on the embodiment, a clustering model may be applied to the training text, and the model may be trained based on unsupervised learning so that each cluster is distinguished into blocked content and general content.

[0048] Meanwhile, according to an embodiment, it is also possible for the blocking target detection unit (120) to directly learn and generate a classification model instead of the model learning unit (not shown).

[0050] The blocking list transmission unit (130) can generate a blocking list of ad content to be blocked and can provide the generated blocking lists to the dashboard page (P2) of the web server (W). That is, the web server (W) can display the blocking list through the dashboard page (P2), and the administrator of the web server (W) can set the ad content to be blocked on the web server (W) on the ad management page (P1) based on the blocking list displayed on the dashboard page (P2). Here, the dashboard page may include a download function for the blocking list, and when the administrator requests a download, the web server (W) can provide the administrator's terminal device, etc., with metadata information, etc., of the ad content included in the blocking list. Therefore, the administrator can easily refer to the blocking list to set the ad content to be blocked.

[0051] According to an embodiment, it is also possible to implement the web server (W) to configure advertising content based on a blocking list. For example, the web server (W) can configure advertising content included in the blocking list to be blocked by using the API (Application Programming Interface) of the advertising management page (P1) provided by the advertising server (A). At this time, the web server (W) can display the advertising content blocked by the blocking list on the dashboard page (P1) so that the administrator can easily check the currently blocked advertising content.

[0052] Additionally, the block list transmission unit (130) can transmit a message containing a block list of ad content to be blocked to an administrator terminal (not shown). That is, instead of creating a dashboard page (P2) within the web server (W), the block list transmission unit (130) can transmit an email, text message, instant message, etc. containing a block list of ad content to be blocked to the administrator terminal. In this case, the administrator of the web server (W) can set the ad content to be blocked on the ad management page (P1) based on the received block list. Here, the administrator's email address or phone number, etc., may be stored in advance within the web server (W).

[0053] Meanwhile, according to an embodiment, a separate file server (not shown) may be further included to display the advertisement images stored in the detection server (100) on the dashboard page (P2) of the web server (W), and the file server may receive the advertisement images from the detection server (100) and deliver them to the dashboard page (P2).

[0055] FIG. 4 is a block diagram illustrating a computing environment (10) suitable for use in exemplary embodiments. In the illustrated embodiments, each component may have different functions and capabilities in addition to those described below, and may include additional components in addition to those described below.

[0056] The illustrated computing environment (10) includes a computing device (12). In one embodiment, the computing device (12) may be a detection server (100).

[0057] The computing device (12) includes at least one processor (14), a computer-readable storage medium (16), and a communication bus (18). The processor (14) can cause the computing device (12) to operate according to the exemplary embodiment described above. For example, the processor (14) can execute one or more programs stored in the computer-readable storage medium (16). The one or more programs may include one or more computer-executable instructions, and the computer-executable instructions may be configured to cause the computing device (12) to perform operations according to the exemplary embodiment when executed by the processor (14).

[0058] A computer-readable storage medium (16) is configured to store computer-executable instructions or program code, program data and / or other suitable forms of information. A program (20) stored in the computer-readable storage medium (16) includes a set of instructions executable by a processor (14). In one embodiment, the computer-readable storage medium (16) may be memory (volatile memory such as random access memory, non-volatile memory, or a suitable combination thereof), one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, other forms of storage media that are accessed by a computing device (12) and capable of storing desired information, or a suitable combination thereof.

[0059] The communication bus (18) interconnects various other components of the computing device (12), including the processor (14) and the computer-readable storage medium (16).

[0060] The computing device (12) may also include one or more input / output interfaces (22) and one or more network communication interfaces (26) that provide interfaces for one or more input / output devices (24). The input / output interfaces (22) and network communication interfaces (26) are connected to a communication bus (18). The input / output devices (24) may be connected to other components of the computing device (12) through the input / output interfaces (22). An exemplary input / output device (24) may include an input device such as a pointing device (such as a mouse or trackpad), a keyboard, a touch input device (such as a touchpad or touchscreen), a voice or sound input device, various types of sensor devices and / or imaging devices, and / or an output device such as a display device, a printer, a speaker and / or a network card. An exemplary input / output device (24) may be included inside the computing device (12) as a component constituting the computing device (12), or it may be connected to the computing device (12) as a separate device distinct from the computing device (12).

[0062] FIG. 5 is a flowchart illustrating an ad filtering method according to an embodiment of the present invention. Here, each step of the ad filtering method may be performed by a detection server (100) or a computing device (12) mentioned in FIG. 1 and FIG. 9 and in the description related to these figures.

[0063] Referring to FIG. 5, the detection server can collect advertising content displayed on target web pages within the web server (S10). Here, advertisements displayed on the target web pages may appear on the ad management page, and the detection server can crawl the ad management page to extract the advertising content and store the extracted advertising content. Here, the advertising content may include advertising images, and the detection server can extract the advertising images included in the advertising content. The detection server can perform crawling on the target web pages periodically (e.g., daily) according to a preset scheduler.

[0064] Subsequently, the detection server can detect ad content subject to blocking based on the ad text included in the ad content (S20). Here, since text may be included within the ad image, the detection server can perform OCR on the ad image to extract the ad text included in the ad image. Additionally, the extracted ad text can be input into a classification model trained based on machine learning. Here, the classification model may be trained to classify the input ad text into general ad text and text subject to blocking. That is, if the classification model classifies the ad text into a pre-set blocking group, the detection server can store the ad content corresponding to that ad text as ad content subject to blocking. In this case, the ad content subject to blocking can be stored in the blocking list, and the ad content corresponding to the remaining general ad group can be stored in the general ad list.

[0065] The classification model can be implemented using various neural network models, and the detection server can train the classification model in advance. Specifically, multiple advertising contents can be collected as training content from the ad server or the ad management page of the ad server. At this time, the detection server can exclude training content that lacks text, and can also exclude stop words, duplicate text, etc., contained within the extracted training text. Additionally, the detection server can add training data by performing text augmentation on the training texts, such as replacing words, adding words, or changing word positions. Subsequently, the detection server can train the classification model based on supervised learning by marking each training data point to indicate whether it corresponds to blocking content, or train it based on unsupervised learning using clustering models to distinguish between blocking content and general content.

[0066] The detection server can provide a blocking list of ad content to be blocked to the dashboard page of the web server (S30). In this case, the web server can display the blocking list through the dashboard page, and the administrator of the web server can set the ad content to be blocked on the web server on the ad management page based on the blocking list displayed within the dashboard page. Here, the dashboard page may include a download function for the blocking list, and when the administrator requests a download, the web server can provide the administrator's terminal device, etc., with metadata information, etc., of the ad content included in the blocking list. Therefore, the administrator can easily refer to the blocking list to set the ad content to be blocked.

[0067] According to an embodiment, it is also possible to implement the web server to configure advertising content based on a block list. For example, the web server may configure advertising content included in the block list to be blocked by using the API of the ad management page provided by the ad server. In this case, the web server may display the advertising content blocked by the block list on a dashboard page so that an administrator can easily check the currently blocked advertising content.

[0068] Additionally, the detection server can send a message containing a blocking list of ad content to be blocked to the administrator's terminal. That is, instead of creating a dashboard page within the web server, the detection server can send an email, text message, instant message, etc., containing a blocking list of ad content to be blocked to the administrator's terminal. In this case, the web server administrator can configure the ad content to be blocked on the ad management page based on the received blocking list. Here, the administrator's email address or phone number, etc., may be stored in advance within the web server.

[0070] The present invention described above can be implemented as computer-readable code on a medium on which a program is recorded. The computer-readable medium may be one that continuously stores a program executable by a computer, or temporarily stores it for execution or download. Furthermore, the medium may be various recording or storage means in the form of a single or multiple hardware components, and is not limited to a medium directly connected to a computer system but may also exist distributed over a network. Examples of media may include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and media configured to store program instructions, including ROM, RAM, and flash memory. Additionally, other examples of media may include recording or storage media managed by app stores that distribute applications or sites and servers that supply or distribute various other software. Accordingly, the above detailed description should not be interpreted restrictively in all respects but should be considered exemplary. The scope of the present invention shall be determined by a reasonable interpretation of the appended claims, and all modifications within the equivalent scope of the present invention are included within the scope of the present invention.

[0072] The present invention is not limited by the aforementioned embodiments and attached drawings. It will be obvious to those skilled in the art that the components according to the present invention can be substituted, modified, and changed within the scope of the technical concept of the present invention without departing from the spirit of the invention. Explanation of the symbols

[0074] 100: Detection Server 110: Ad Collection Unit 120: Block target detection unit 130: Block list transmission unit

Claims

Claim 1 A method for filtering advertisements in a detection server comprises: a step of collecting advertisement content displayed on a target web page within a web server; a step of detecting advertisement content to be blocked based on advertisement text included in the advertisement content; and a step of providing a blocking list of the advertisement content to be blocked to a dashboard page of the web server, wherein the advertisement text includes text extracted by performing OCR (Optical Character Recognition) on the advertisement content, the collecting step involves crawling an advertisement management page representing advertisements displayed within the target web page to extract an advertisement image included in the advertisement content, and the detecting step involves performing OCR (Optical Character Recognition) on the advertisement image to extract advertisement text included in the advertisement image, and inputting the advertisement text into a classification model trained based on machine learning so that if the advertisement text is classified into a pre-set blocking target group, the advertisement content corresponding to the advertisement text is stored as the advertisement content to be blocked. Claim 2 delete Claim 3 delete Claim 4 delete Claim 5 An ad filtering method for a detection server according to claim 1, wherein the classification model excludes learning content without text among a plurality of collected learning contents, excludes stop words or duplicate text included in the learning text extracted from the learning content, and learns using learning data generated by performing text augmentation on the learning texts. Claim 6 delete Claim 7 An ad filtering method of a detection server according to claim 1, wherein the message including a blocking list of the ad content to be blocked is transmitted to an administrator terminal. Claim 8 A computer program stored on a medium to execute the ad filtering method of a detection server of any one of claims 1, 5, and 7 in combination with hardware. Claim 9 A detection server comprising: an ad collection unit that collects ad content displayed on a target web page within a web server; a block target detection unit that detects ad content to be blocked based on ad text included in the ad content; and a block list transmission unit that generates a block list of ad content to be blocked and provides the block list to a dashboard page of the web server, wherein the ad text includes text extracted by performing OCR (Optical Character Recognition) on the ad content, the ad collection unit crawls an ad management page representing ads displayed on the target web page to extract an ad image included in the ad content, and the block target detection unit performs OCR (Optical Character Recognition) on the ad image to extract the ad text included in the ad image, and inputs the ad text into a classification model trained based on machine learning, and if the ad text is classified into a pre-set block target group, stores the ad content corresponding to the ad text as the ad content to be blocked.

Images