An advertisement delivery method, a smart terminal and a computer readable storage medium

Abstract

The application discloses an advertisement putting method, an intelligent terminal and a computer readable storage medium, and the method comprises the following steps: obtaining a video comment corresponding to a target video, and determining a target comment in the video comment; performing attribute extraction on the target comment to obtain attribute information corresponding to the target comment; determining a target advertisement corresponding to the target comment in a preset advertisement database according to the attribute information; and loading the target advertisement to an advertisement area corresponding to the target video when the target video is played. The application can accurately put advertisements and improve the utilization rate of advertisement resources.

Description

Technical Field

[0001] This invention relates to the field of advertising delivery, and more particularly to an advertising delivery method, a smart terminal, and a computer-readable storage medium. Background Technology

[0002] With the development of the internet, the number of users of smartphones and other smart terminals is increasing, and the online audio-visual business is also developing rapidly, with the number of users exceeding 900 million. In the context of mobile internet, it is common for creators to independently create and publish videos, and for users to watch these videos. Statistics show that the average daily app usage time per internet user is as high as 6.7 hours. Therefore, videos created by creators have occupied a significant portion of many internet users' time. Among these, short video apps have surpassed comprehensive video apps in average daily usage time, becoming the leading application in the online audio-visual field. They are also continuously penetrating into diverse areas such as e-commerce, live streaming, and education, deepening their influence and driving changes in the online audio-visual industry landscape.

[0003] However, while internet users spend a lot of time watching videos, and many videos created by individuals or small groups garner significant attention and comments, it's difficult for these videos to directly access advertising channels. Many short videos often go unsold by advertisers. On the other hand, mainstream media advertising has a smaller audience, resulting in poor advertising effectiveness. Therefore, the resources attracted by videos created by individuals or small groups often cannot be converted into advertising revenue. Thus, the current advertising placement mechanism needs further improvement. Summary of the Invention

[0004] The main objective of this invention is to provide an advertising delivery method, a smart terminal, and a computer-readable storage medium, aiming to solve the problem of inaccurate advertising delivery in the prior art.

[0005] To achieve the above objectives, the present invention provides an advertising delivery method, which includes the following steps:

[0006] Obtain the video comments corresponding to the target video, and determine the target comments among the video comments;

[0007] Attribute extraction is performed on the target comment to obtain the attribute information corresponding to the target comment;

[0008] Based on the attribute information, determine the target advertisement in the preset advertising database that corresponds to the target comment;

[0009] When the target video is played, the target advertisement is loaded into the advertisement area corresponding to the target video.

[0010] Optionally, the advertising delivery method further includes, before obtaining the video comments corresponding to the target video and determining the target comments among the video comments:

[0011] Get the number of participants for each video file;

[0012] The target video in the video file is determined based on the preset participation threshold and the participation quantity.

[0013] Optionally, in the aforementioned advertising delivery method, the step of obtaining video comments corresponding to the target video and determining the target comments within the video comments specifically includes:

[0014] Obtain the video comments corresponding to the target video;

[0015] The target comment in the video comments is determined based on the number of likes and / or replies corresponding to each video comment.

[0016] Optionally, in the aforementioned advertising delivery method, the attribute information includes a first attribute and / or a second attribute; the step of extracting attributes from the target comment to obtain the attribute information corresponding to the target comment specifically includes:

[0017] When the target review includes a text review, the product attribute corresponding to the text review is identified to obtain the first attribute corresponding to the text review;

[0018] When the target review includes an image review, the product attribute corresponding to the image review is identified to obtain the second attribute corresponding to the target review.

[0019] Optionally, in the aforementioned advertising delivery method, the attribute information further includes a third attribute; the step of extracting attributes from the target comment to obtain the attribute information corresponding to the target comment further includes:

[0020] When the image comment also includes text, text recognition is performed on the image comment to obtain the text information corresponding to the image comment;

[0021] Identify the product attributes corresponding to the text information to obtain the third attribute corresponding to the text information.

[0022] Optionally, in the aforementioned advertising delivery method, the step of determining the target advertisement corresponding to the target comment in a preset advertising database based on the attribute information specifically includes:

[0023] Based on the attribute values ​​of each advertisement in the advertisement database and the attribute information, calculate the similarity value between each advertisement and the target comment;

[0024] The target advertisement in the advertisement data is determined based on the similarity value and the evaluation value corresponding to each advertisement data.

[0025] Optionally, in the aforementioned advertising delivery method, determining the target advertisement in the advertising data based on the similarity value and the evaluation value corresponding to each of the advertising data specifically includes:

[0026] Candidate ads in the advertising data are determined based on a preset similarity threshold.

[0027] The target advertisement among the candidate advertisements is determined based on the historical click-through rate of each candidate advertisement.

[0028] Optionally, the advertising delivery method, after loading the target advertisement into the advertisement area corresponding to the target video when the target video is played, further includes:

[0029] Listen for click events corresponding to the target advertisement;

[0030] The historical click-through rate of the target advertisement is updated based on the click event and the click time corresponding to the click event.

[0031] In addition, to achieve the above objectives, the present invention also provides a smart terminal, wherein the smart terminal includes: a memory, a processor, and an advertising delivery program stored in the memory and executable on the processor, wherein when the advertising delivery program is executed by the processor, it implements the steps of the advertising delivery method as described above.

[0032] In addition, to achieve the above objectives, the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores an advertising delivery program, which, when executed by a processor, implements the steps of the advertising delivery method as described above.

[0033] Research has revealed that internet users now enjoy reading comments while watching videos, fostering greater interaction with creators. Therefore, tailoring ads to comment attributes is more effective at attracting viewers. This invention automatically embeds ads based on video comment attributes, allowing users to encounter video-related ads while browsing comments, effectively utilizing user resources attracted by the video. The process involves first acquiring the target video (the video to be advertised), then selecting high-performing comments from the target video (e.g., those with many likes, shares, or secondary comments) as target comments. Attribute extraction is then performed on these target comments to obtain their attribute information. Finally, based on this attribute information, the target ad is determined and delivered during video playback. Attached Figure Description

[0034] Figure 1 This is a flowchart of a preferred embodiment of the advertising delivery method of the present invention;

[0035] Figure 2 This is a flowchart of the advertising placement method of the present invention for extracting product attributes;

[0036] Figure 3 This is a flowchart of the advertising placement method of the present invention for determining the target advertisement;

[0037] Figure 4 This is a schematic diagram of the operating environment of a preferred embodiment of the smart terminal of the present invention. Detailed Implementation

[0038] This invention provides an advertising delivery method, a computer-readable storage medium, and a terminal device. To make the objectives, technical solutions, and effects of this invention clearer and more explicit, the invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only for explaining the invention and are not intended to limit the invention.

[0039] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this specification means the presence of the stated 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, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein can include wireless connections or wireless coupling. The term “and / or” as used herein includes all or any units and all combinations of one or more associated listed items.

[0040] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0041] The inventors discovered through research that with the rise of short videos and other videos created by individuals or small groups, especially short videos, current advertising methods are not effectively utilizing resources. To address this problem, in this embodiment of the invention, the method includes: acquiring video comments corresponding to a target video and identifying target comments within those video comments; extracting attributes from the target comments to obtain attribute information corresponding to the target comments; determining a target advertisement in a preset advertising database that corresponds to the target comment based on the attribute information; and loading the target advertisement into the advertising area corresponding to the target video when the target video is played.

[0042] Step S100: Obtain the video comments corresponding to the target video, and determine the target comments in the video comments.

[0043] Specifically, the first step is to acquire the target video. The target video refers to the video to be used for ad placement. It can be any video to be played, or a video that meets certain conditions, such as reaching a certain number of views, comments, or shares. In this embodiment, the target video refers to a video file whose corresponding parameter count is greater than or equal to a preset participation threshold. The parameter count refers to the metrics of user participation in the video file, generally including one or more of the number of shares, views, and comments, or a value obtained by applying a certain algorithm to the number of shares, views, and comments. The algorithm can be a weighted sum of different parameters. The participation threshold is a threshold corresponding to the participation count, used to evaluate whether the user participation in the video file meets the standard for ad placement. If the participation count is greater than or equal to the parameter count threshold, the video file is determined to be the target video.

[0044] After obtaining the target video, all video comments corresponding to the target video are retrieved, and then the target comment is determined. The target comment is the comment with the highest popularity among all video comments. In this embodiment, the number of likes and / or replies corresponding to a video comment is used as an indicator of the video comment's popularity. For example, if the number of likes for a certain video comment is the maximum value among all video comments corresponding to this video file, then that video comment is selected as the target comment. Alternatively, a popularity value can be calculated based on the number of likes and replies, and then the video comment with the highest popularity value is selected as the target comment.

[0045] Step S200: Extract attributes from the target comment to obtain the attribute information corresponding to the target comment.

[0046] Specifically, the target comment is then subjected to attribute extraction to obtain the attribute information corresponding to the target comment. In this embodiment, the attribute information refers to the attributes of goods and / or services that are strongly related to the target comment. For example, if the target video is a video about cats, and there are many video comments about the target video, and one video comment with the most likes mentions "lucky cat," then the extracted attribute information is "lucky cat" as the attribute information corresponding to this target comment.

[0047] Furthermore, with the development of technology, the types of comments have become increasingly diversified. Previously, comments were limited to text, but now they also include image-based comments. For more information, please refer to... Figure 2 In this embodiment, when obtaining the target comment, the process of attribute identification based on the form of the target comment is as follows:

[0048] Step S210: When the target review includes a text review, identify the product attribute corresponding to the text review to obtain the first attribute corresponding to the text review;

[0049] Step S210: When the target review includes an image review, identify the product attribute corresponding to the image review to obtain the second attribute corresponding to the target review.

[0050] Specifically, when the target review includes a text review, the product and / or service corresponding to the text review is identified to obtain a first attribute, which is the attribute value obtained through the text review. The identification of the product and / or service corresponding to the text review can be performed in various ways. In the first implementation of this embodiment, the identification method is through keyword identification. For example, if the target review of the aforementioned cat video contains the keyword "lucky cat," then "lucky cat" is used as the first attribute of the target review.

[0051] In the second implementation of this embodiment, a classification method is used to identify product attributes. A large number of training reviews are pre-acquired, and then these training reviews are divided into multiple groups using a clustering algorithm. Each group corresponds to a clustering label. The clustering method can be supervised, semi-supervised, or unsupervised; this embodiment is not limited to any particular method, and any clustering algorithm can be selected based on its clustering effect. Then, based on the obtained clustering results, the clustering label corresponding to the text review to be identified is determined, and the corresponding clustering label is used as the first attribute of that text review.

[0052] In the third implementation of this embodiment, a deep learning-based neural network is used to identify the first attribute. An initial model is pre-set, and a large amount of comment data is acquired as training samples and labeled with attributes. The training samples are then input into the initial model, which classifies each training sample to obtain training values. Then, based on the loss function in the initial model, the loss value between the training samples and the labeled attributes is calculated. After obtaining the loss value, it is fed back into the initial model, and the parameters of the model are adjusted until the initial model converges, resulting in an attribute recognition model. After obtaining the target comment, the target comment is input into the attribute recognition model, which identifies the product attributes to obtain the first attribute.

[0053] When the target review includes an image review, the product attributes of the image review are identified to obtain the second attribute. For image reviews, this essentially involves image processing. While the second attribute cannot be obtained from image reviews using keywords, product attributes can still be identified through clustering algorithms and deep learning-based models. The process is similar to that based on text and will not be elaborated further.

[0054] In addition to the methods mentioned above, image features can also serve as an attribute of a product or service. For example, if the image review is a character illustration from a game, the features of the character illustration can be extracted, and then these features can be compared with the corresponding images of products or services in the database. This comparison can be achieved using perceptual hashing algorithms. Perceptual hashing is a general term for a class of hashing algorithms that generate a "fingerprint" string for each image. By comparing the fingerprint information of different images, the similarity between the images can be determined. The corresponding product or service can be found through the "fingerprints" of different images; therefore, in this process, the image's "fingerprint" is the secondary attribute of the image review. Perceptual hashing algorithms include mean hashing (aHash), perceptual hashing (pHash), and dHash (difference hashing). aHash is faster but less accurate; pHash, on the other hand, is more accurate but slower; dHash combines both, being both accurate and fast.

[0055] Furthermore, many images not only contain image content but also text content. For example, an image might contain a cartoon image of a lucky cat and also the words "lucky cat." To accommodate both the image and text information contained within the image, this embodiment also includes a third attribute based on the text recognition of the image comment. First, text recognition is performed on the image comment to extract the corresponding text information. Text recognition methods can employ OCR (Optical Character Recognition), CRNN (Convolutional Recurrent Neural Network), etc. Through these text recognition technologies, the text information of the image comment can be extracted.

[0056] Then, using a method similar to that described above for identifying product attributes in text reviews, the text information is analyzed to identify its product attributes, thereby obtaining the corresponding third attribute. Since the process is quite similar, it will not be elaborated upon here.

[0057] Step S300: Based on the attribute information, determine the target advertisement in the preset advertising database that corresponds to the target comment.

[0058] Specifically, an advertising database containing a large amount of advertising data is pre-set. This advertising data can include various forms such as text-based advertising slogans, animated advertising videos, and graphic advertising images. Each piece of advertising data is pre-processed to obtain its corresponding attribute values. To facilitate the identification of target advertisements, in this embodiment, the type of the attribute values ​​corresponding to the advertising data corresponds to the type of attribute information mentioned above. For example, the first attribute of a text comment is a keyword, and the second attribute of an image comment is a clustering label obtained after clustering the image comment. Therefore, the attribute values ​​corresponding to each piece of advertising data include the keyword and clustering label corresponding to that advertising data. Image comments obtain labeled attributes based on a deep learning-trained model; therefore, the attribute values ​​corresponding to each piece of advertising data are one or more of the labeled attributes used when training the model. Figure 3 As shown, the target advertisement is then determined based on the attribute information. This process may include:

[0059] Step S310: Calculate the similarity value between each piece of advertising data and the target comment based on the attribute values ​​of each piece of advertising data in the advertising database and the attribute information;

[0060] Step S320: Determine the target advertisement in the advertisement data based on the similarity value and the evaluation value corresponding to each advertisement data.

[0061] After obtaining the attribute information, the similarity value between each piece of advertising data and the target comment is calculated based on the attribute values ​​of each piece of advertising data in the advertising database and the attribute information. The calculation method for the similarity value is also determined according to the type of attribute value or attribute information. For example, if the type of attribute information and attribute value is keywords, the similarity calculation method is a text-based similarity algorithm; if the attribute information and attribute value are clustering tags, the similarity calculation method is a clustering tag-based similarity calculation method.

[0062] After obtaining the similarity value, the target advertisement in the advertising data is determined based on the similarity value and the evaluation value corresponding to each piece of advertising data. The evaluation value refers to an indicator of the effectiveness of the advertising data. The evaluation value can be the historical click-through rate (CTR) of the advertising data, i.e., how many users clicked on this advertising data after it was placed as the target advertisement. It can also include the advertisement conversion rate, i.e., the probability that a user clicked on this advertising data and made a purchase when it was placed as the target advertisement. The method of selecting target advertisements based on similarity value and evaluation value can be to evaluate them in parallel or to evaluate one indicator first and then the other. For example, first, based on the similarity value, advertising data with similarity values ​​exceeding a similarity threshold are selected as candidate advertisements. Then, based on the historical CTR of each advertising data, the candidate advertisement with the highest historical CTR is selected as the target advertisement.

[0063] Step S400: When the target video is played, the target advertisement is loaded into the advertisement area corresponding to the target video.

[0064] Specifically, after identifying the target advertisement, when the target video is played, the target advertisement is placed in the corresponding advertisement area of ​​the target video. In this embodiment, the advertisement area is a broad term, encompassing not only common ad frames but also pre-video ad slots, such as banner ads, text link ads, and interstitial ads (pop-up ads). Furthermore, when placed as an ad frame, the ad frame's position can preferably be at the top or bottom of the page. Taking banner ads as an example, they are image files created in formats such as GIF, JPG, and Flash, positioned on a webpage primarily to display advertising content. They can also be made interactive using languages ​​like Java, and their expressiveness enhanced using plugins like Shockwave.

[0065] Furthermore, after the ad is placed in the ad area, the system can also monitor the target ad for click events, that is, monitor whether the target ad is clicked and record the click time corresponding to the click event. Based on the click time and the occurrence of the click event, the historical click-through rate of the target ad can be updated.

[0066] Furthermore, such as Figure 4 Based on the above-mentioned advertising delivery method, the present invention also provides a smart terminal, which includes a processor 10, a memory 20 and a display 30. Figure 4 Only some components of the smart terminal are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0067] In some embodiments, the memory 20 may be an internal storage unit of the smart terminal, such as a hard drive or memory. In other embodiments, the memory 20 may be an external storage device of the smart terminal, such as a plug-in hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the smart terminal. Further, the memory 20 may include both internal and external storage units of the smart terminal. The memory 20 is used to store application software and various types of data installed on the smart terminal, such as the program code installed on the smart terminal. The memory 20 can also be used to temporarily store data that has been output or will be output. In one embodiment, the memory 20 stores an advertising delivery program 40, which can be executed by the processor 10 to implement the advertising delivery method of this application.

[0068] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor, or other data processing chip, used to run program code stored in the memory 20 or process data, such as executing the advertising delivery method.

[0069] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. The display 30 is used to display information on the smart terminal and to display a visual user interface. The components 10-30 of the smart terminal communicate with each other via a system bus.

[0070] In one embodiment, when the processor 10 executes the advertising delivery program 40 in the memory 20, the following steps are performed:

[0071] Obtain the video comments corresponding to the target video, and determine the target comments among the video comments;

[0072] Attribute extraction is performed on the target comment to obtain the attribute information corresponding to the target comment;

[0073] Based on the attribute information, determine the target advertisement in the preset advertising database that corresponds to the target comment;

[0074] When the target video is played, the target advertisement is loaded into the advertisement area corresponding to the target video.

[0075] Before obtaining the video comments corresponding to the target video and determining the target comment among the video comments, the process further includes:

[0076] Get the number of participants for each video file;

[0077] The target video in the video file is determined based on the preset participation threshold and the participation quantity.

[0078] Specifically, obtaining the video comments corresponding to the target video and determining the target comments within those video comments includes:

[0079] Obtain the video comments corresponding to the target video;

[0080] The target comment in the video comments is determined based on the number of likes and / or replies corresponding to each video comment.

[0081] The attribute information includes a first attribute and / or a second attribute; the step of extracting attributes from the target comment to obtain the attribute information corresponding to the target comment specifically includes:

[0082] When the target review includes a text review, the product attribute corresponding to the text review is identified to obtain the first attribute corresponding to the text review;

[0083] When the target review includes an image review, the product attribute corresponding to the image review is identified to obtain the second attribute corresponding to the target review.

[0084] The attribute information further includes a third attribute; the step of extracting attributes from the target comment to obtain the attribute information corresponding to the target comment also includes:

[0085] When the image comment also includes text, text recognition is performed on the image comment to obtain the text information corresponding to the image comment;

[0086] Identify the product attributes corresponding to the text information to obtain the third attribute corresponding to the text information.

[0087] Specifically, determining the target advertisement corresponding to the target comment in a preset advertising database based on the attribute information includes:

[0088] Based on the attribute values ​​of each advertisement in the advertisement database and the attribute information, calculate the similarity value between each advertisement and the target comment;

[0089] The target advertisement in the advertisement data is determined based on the similarity value and the evaluation value corresponding to each advertisement data.

[0090] Specifically, determining the target advertisement in the advertising data based on the similarity value and the evaluation value corresponding to each piece of advertising data includes:

[0091] Candidate ads in the advertising data are determined based on a preset similarity threshold.

[0092] The target advertisement among the candidate advertisements is determined based on the historical click-through rate of each candidate advertisement.

[0093] Wherein, after loading the target advertisement into the advertisement area corresponding to the target video when the target video is played, it further includes:

[0094] Listen for click events corresponding to the target advertisement;

[0095] The historical click-through rate of the target advertisement is updated based on the click event and the click time corresponding to the click event.

[0096] This invention also provides a computer-readable storage medium storing an advertising delivery program. When executed by a processor, the advertising delivery program implements the steps of the advertising delivery method described above. The method includes: acquiring video comments corresponding to a target video and identifying target comments within the video comments; extracting attributes from the target comments to obtain attribute information corresponding to the target comments; determining a target advertisement corresponding to the target comment in a preset advertising database based on the attribute information; and loading the target advertisement into the advertising area corresponding to the target video when the target video is played. This invention enables precise advertising delivery and improves the utilization rate of advertising resources.

[0097] Of course, those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.). The program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The computer-readable storage medium can be a memory, magnetic disk, optical disk, etc.

[0098] It should be understood that the application of the present invention is not limited to the examples above. Those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

Claims

1. An advertising placement method, characterized in that, The advertising delivery method includes: Obtain the video comments corresponding to the target video, and determine the target comments among the video comments; Attribute extraction is performed on the target comment to obtain the attribute information corresponding to the target comment; Based on the attribute information, determine the target advertisement in the preset advertising database that corresponds to the target comment; When the target video is played, the target advertisement is loaded into the advertisement area corresponding to the target video; Before obtaining the video comments corresponding to the target video and determining the target comment among the video comments, the method further includes: Get the number of participants for each video file; The target video in the video file is determined based on the preset participation threshold and the participation number. The attribute information includes a first attribute and / or a second attribute; the step of extracting attributes from the target comment to obtain the attribute information corresponding to the target comment specifically includes: When the target review includes a text review, the product attribute corresponding to the text review is identified to obtain the first attribute corresponding to the text review; When the target review includes an image review, the product attribute corresponding to the image review is identified to obtain the second attribute corresponding to the target review; The attribute information also includes a third attribute; The step of extracting attributes from the target comment to obtain the attribute information corresponding to the target comment also includes: When the image comment also includes text, text recognition is performed on the image comment to obtain the text information corresponding to the image comment; Identify the product attributes corresponding to the text information to obtain the third attribute corresponding to the text information.

2. The advertising placement method according to claim 1, characterized in that, The step of obtaining the video comments corresponding to the target video and determining the target comments in the video comments specifically includes: Obtain the video comments corresponding to the target video; The target comment in the video comments is determined based on the number of likes and / or replies corresponding to each video comment.

3. The advertising placement method according to claim 1, characterized in that, The step of determining the target advertisement corresponding to the target comment in a preset advertising database based on the attribute information specifically includes: Based on the attribute values ​​of each advertisement in the advertisement database and the attribute information, calculate the similarity value between each advertisement and the target comment; The target advertisement in the advertisement data is determined based on the similarity value and the evaluation value corresponding to each advertisement data.

4. The advertising placement method according to claim 3, characterized in that, The step of determining the target advertisement in the advertising data based on the similarity value and the evaluation value corresponding to each of the advertising data specifically includes: Candidate ads in the advertising data are determined based on a preset similarity threshold. The target advertisement among the candidate advertisements is determined based on the historical click-through rate of each candidate advertisement.

5. The advertising placement method according to claim 4, characterized in that, After loading the target advertisement into the advertisement area corresponding to the target video when the target video is played, the method further includes: Listen for click events corresponding to the target advertisement; The historical click-through rate of the target advertisement is updated based on the click event and the click time corresponding to the click event.

6. A smart terminal, characterized in that, The smart terminal includes: a memory, a processor, and an advertising delivery program stored in the memory and executable on the processor. The advertising delivery program is executed by the processor in real time. The steps of the advertising delivery method as described in any one of claims 1-5 are now described.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores an advertising delivery program, which, when executed by a processor, implements the steps of the advertising delivery method as described in any one of claims 1-5.

Images