Advertisement promotion method and system based on user portrait

Abstract

The invention relates to the field of advertisement promotion, in particular to an advertisement promotion method and system based on a user portrait. The method comprises the following steps: acquiring real-time behavior information of a user before advertisement promotion, and determining a presentation form demand of the user for the advertisement according to the real-time behavior information; obtaining user information, and determining dynamic demand information according to the presentation form demand and the user information; and determining to present customized promotion information according to the dynamic demand information and the presentation form demand, and performing advertisement promotion according to the presented customized promotion information. According to the method, the user behavior data is acquired in real time, the demand of the user for the advertisement presentation form is accurately captured, and the dynamic demand information is generated in combination with the personal information of the user. According to the method, high personalization of the content and form of the advertisement is ensured, and the correlation and attraction of the advertisement are improved to the greatest extent, so that the user participation degree and the conversion rate are improved, the advertisement promotion effect is optimized, the interference of the advertisement to the user is reduced, and the accuracy and timeliness of advertisement putting are enhanced.

Description

Technical Field

[0001] The present application relates to the field of advertising promotion, and in particular to an advertising promotion method and system based on user portraits. Background Art

[0002] With the rapid development of Internet technology, the forms of advertising promotion and push have become more diverse. When promoting advertising to users, the system obtains and analyzes the user's behavioral interest in advertising, and accurately promotes advertising to users based on the analysis results, thereby meeting the user's actual demand for advertising.

[0003] However, due to the inaccurate positioning of the system on the specific needs of users, there is a large deviation between the advertisements pushed by the system and the actual needs of users for the pushed advertisements, thereby affecting the user experience and the conversion rate of the advertising promotion. Summary of the invention

[0004] The present application provides an advertising promotion method and system based on user portrait to solve the above problems.

[0005] In a first aspect, the present application provides an advertising promotion method based on user portraits, the method comprising: Acquire real-time behavior information of users before advertisement promotion, and determine the user's demand for advertisement presentation form based on the real-time behavior information; Acquire user information, and determine dynamic demand information based on the real-time behavior information and the user information; According to the dynamic demand information and the presentation format requirement, it is determined to present customized promotion information, and advertising promotion is performed according to the presented customized promotion information.

[0006] Through this solution, by obtaining user behavior information in real time and understanding the user's current interests and needs, the user's needs for the presentation form of the advertisement are predicted, ensuring that the form of the advertisement content is highly matched with the user's immediate needs. Combined with user information, dynamic demand information is generated to further accurately define the user's expectations for the advertisement content in the current environment. Based on dynamic demand information and the user's presentation form requirements, the advertisement content and promotion strategy are precisely adjusted to ensure that the advertisement is not only highly consistent with the user's interests, but also maximizes the user's interaction or purchase intention. Real-time optimization and precise push of advertisement content are achieved, which improves the relevance of advertisements and user engagement, thereby improving the conversion rate and advertising effect of advertisements.

[0007] Optionally, determining the user's demand for advertisement presentation form according to the real-time behavior information includes: Determine, based on the real-time behavior information, the user's dwell time, click count, number of comments on different types of content before the advertisement is promoted, and the maximum dwell time, click count, and comment count of the user on the different types of content; Determining the comprehensive attention intensity of the user to the different types of content according to the stay time, the number of clicks, the number of comments, the maximum stay time, the maximum number of clicks, and the maximum number of comments of the user on the different types of content; Obtaining content type information, and determining the number of content types and the proportion of content forms according to the content type information; Acquire presentation form information of the different types of content, acquire presentation form information of the different types of content, and determine the number of presentation forms according to the presentation form information; Determine a presentation form index according to the number of content types, the proportion of content forms, the comprehensive attention intensity and the number of presentation forms; Acquire a form index level, match the form index level with the presentation form index, and determine the presentation form requirement.

[0008] Through this solution, the user's dwell time, clicks and comments on different types of content before advertising promotion are analyzed through real-time behavioral information, and the user's interest preferences are obtained from these data. By calculating the maximum dwell time, clicks and comments of each type of content, the comprehensive attention intensity of users to different types of content is further measured. This step helps to more accurately identify the user's interest points and participation. By obtaining content type information, the number and form proportion of each type of content are determined to provide basic data for advertising matching. The final presentation form requirements are determined by comprehensively considering the dwell time, clicks, comments, number of content types, form proportion, and number of presentation forms. This process can customize the advertising display method according to user behavior, improve the personalization, accuracy and interactivity of advertising, and thus enhance the attractiveness and conversion effect of advertising to users.

[0009] Optionally, the comprehensive attention intensity is determined according to the maximum dwell time, the maximum number of clicks, the maximum number of comments, the dwell time, the number of clicks and the number of comments, and is calculated according to the following formula: ; in, represents the comprehensive attention strength, Indicates the preset time weight, represents the residence time, represents the maximum value of the residence time, represents the preset nonlinear time weight, Indicates the preset click weight. represents the number of clicks, Indicates the maximum number of clicks. Indicates the preset comment count weight, Indicates the number of comments. Indicates the maximum number of comments. Represents the preset nonlinear comment count weight.

[0010] Through this solution, the user's attention level in different dimensions is reflected according to the maximum dwell time, the maximum number of clicks and the maximum number of comments, as well as the real-time dwell time, clicks and comments, combined with the preset time weight, preset click weight and preset comment weight. The preset nonlinear time weight and the preset nonlinear comment weight are used to optimize the impact of nonlinear data and enhance the model's adaptability to the complexity of user behavior. In the formula, after the dwell time, clicks, comments and other behavioral data are standardized, the comprehensive attention intensity is calculated by comprehensive weighted calculation to ensure the organic combination of multi-dimensional data. This step can not only accurately reflect the user's preference for content, but also provide a reliable basis for the subsequent advertising presentation requirements, thereby improving the relevance of advertising recommendations and user experience.

[0011] Optionally, the presentation form requirement is determined according to the number of content types, the proportion of the content forms, the comprehensive attention intensity and the number of presentation forms, and is calculated according to the following formula: ; in, Indicates The presentation index of the form, Indicates the number of content types. Indicates the user's The comprehensive attention intensity of each presentation form, Indicates The content in The proportion of each form.

[0012] Through this solution, the presentation form index of each form is calculated using a formula by combining the number of content types, the proportion of content forms, the comprehensive attention intensity and the number of presentation forms. This step takes into account the impact of different content types, the user's attention intensity to each form, and the proportion of content in each presentation form, thereby forming a refined presentation index. By obtaining the form index level and matching it with the corresponding presentation form index, the needs of each presentation form can be effectively quantified and ranked. In this way, not only can the preferences of each user be accurately reflected, but also the advertising presentation form can be dynamically adjusted according to changes in user interests, the content push strategy can be optimized, the user experience and advertising delivery effect can be improved, and ultimately the content can be efficiently matched with user needs.

[0013] Optionally, the user information includes the user's historical browsing information, and before obtaining the user's real-time behavior information before the advertisement promotion, the method further includes: Determine a set of historical commodity types browsed by the user according to the historical browsing information; Acquire current advertisement information, and determine the type of product promoted in the current advertisement based on the current advertisement information; Matching the historical commodity type set with the commodity type to determine whether the commodity type is within the historical commodity type set; If the product type is within the historical product type set, it is determined to push the current advertisement to the user.

[0014] Through this solution, the historical product type set browsed by the user is determined based on the user's historical browsing information. This step can extract the user's long-term interest preferences and form a preliminary user portrait. By obtaining the current advertising information and analyzing the product types promoted by the advertisement, a data basis is provided for the subsequent matching process. The historical product type set is matched with the advertising product type to determine whether the current advertisement meets the user's historical preferences. If the match is successful, it means that the user may have potential interest in the product type, and thus the current advertisement is pushed to the user. This process effectively avoids the possibility of pushing irrelevant advertisements to users, improves the relevance and click-through rate of advertisements, and can also dynamically optimize advertising strategies based on real-time user behavior and historical data, ultimately achieving precision promotion.

[0015] Optionally, the user information includes a real-time physical location of the user, and determining the dynamic demand information according to the real-time behavior information and the user information includes: Determining, based on the real-time behavior information, the type of advertisement of the user at the real-time physical location; According to the real-time physical location, determining whether the user has triggered an advertisement attention demand of the advertisement type at the real-time physical location; If the user triggers the advertisement attention demand at the real-time physical location, determining the user's demand for presentation type of browsing content according to the real-time behavior information; Obtaining authorization information of the user after triggering the advertisement attention demand, and predicting the real-time click position of the advertisement details in the advertisement page when the user is at the real-time physical location according to the authorization information; The presentation type requirement and the real-time click position are incorporated into the dynamic requirement information.

[0016] Through this solution, the user's presentation type requirements for browsing content are identified based on real-time behavioral information to ensure that the advertising content matches the user's interests. The real-time physical location is used to determine whether the user has triggered the advertising attention demand of the advertising type, which provides a basis for the precise delivery of advertisements. If the user triggers the advertising attention demand, the behavioral information is further analyzed to determine the user's specific presentation type requirements for browsing content. By obtaining the user's authorization information, the real-time click position of the user on the advertising details in the advertising page is predicted, so as to preset the best position and form of advertising display. The presentation type requirements and real-time click positions are combined to form dynamic demand information, so as to realize dynamic adjustment of advertising display content and timing. Through these steps, advertisements can not only accurately match user needs, but also improve user experience and enhance the conversion rate of advertising effects.

[0017] Optionally, the user information includes information of a user's mobile device, and predicting, based on the authorization information, a real-time click position of the advertisement details in the advertisement page when the user is at the real-time physical location includes: Determining whether the user allows obtaining the user's mobile device information according to the authorization information; If the user allows obtaining the mobile device information, obtaining the mobile device information; Determine, based on the mobile device information, the height and swing amplitude of the mobile device when the user is at the real-time physical location; Determining a range of movement of the center of gravity of the mobile device according to the height and the swing amplitude; Determining a convenient operation range of the user at the real-time physical location according to the center of gravity movement range; The real-time click position of the advertisement details in the advertisement page when the user is at the real-time physical location is predicted according to the convenient operation range.

[0018] Through this solution, based on the user authorization information, it is determined whether the user allows the acquisition of their mobile device information. This step ensures compliance with the privacy protection principle. If the user agrees, the information of their mobile device is obtained, and the height and swing amplitude of the device are analyzed based on the information, which can reflect the user's current interaction status. For example, changes in the height and swing amplitude of the device may indicate whether the user is using the device or is in an active state. Further, based on the height and swing amplitude, the range of movement of the center of gravity of the device is calculated, thereby inferring the possible operating range of the user. Through this convenient operating range, the most likely area of ​​the ad details on the ad page to be clicked is predicted when the user is at the real-time physical location. This solution accurately locates the user's behavior patterns and interaction intentions, thereby optimizing ad display and improving user experience and advertising effectiveness.

[0019] Optionally, the presentation type requirement includes a video duration range corresponding to the video type, and determining to present customized promotion information according to the dynamic requirement information and the presentation form requirement includes: Determine the user's browsing needs for browsing content before the advertisement is promoted according to the presentation form requirements, and judge whether the browsing needs are within the presentation type requirements; If the browsing requirement is within the presentation type requirement, then obtaining the advertisement information of the advertisement to be promoted; Determine the duration of each presentation form of the advertisement to be promoted according to the advertisement information; Matching the presentation duration with the video duration range to obtain the advertisement presentation type corresponding to the presentation duration within the video duration range; Determining, based on the real-time click location, how long the payment details of the advertisement to be promoted are displayed when the user is at the real-time physical location; The advertisement display type and the display duration are incorporated into the presentation of customized promotion information.

[0020] Through this solution, the type of advertising presentation suitable for the video duration is determined according to the presentation form requirements, and the user's browsing needs are predicted in combination with the user's interests and behaviors. If the user's browsing needs meet the presentation type requirements, the advertising information of the advertisement to be promoted is further obtained, and the duration of each presentation form in the advertisement is calculated. The duration of the advertisement presentation form is matched with the video duration range to ensure that the advertisement content is displayed within the appropriate duration. Through real-time click location data, the display duration of the user's payment details on the advertisement page is predicted, providing a more accurate adjustment basis for advertisement presentation. The advertisement presentation type and display duration are included in the presentation of customized promotional information to ensure that the advertisement can accurately adapt to user needs and improve the conversion rate of advertising effects and user experience.

[0021] Optionally, determining, based on the real-time click position, a display duration of payment details of the to-be-promoted advertisement when the user is at the real-time physical location includes: Determining the location of payment details in the advertisement to be promoted when the user is at the real-time physical location according to the real-time click location; Obtaining user behavior information at the real-time physical location, and determining a display time node for the payment details location based on the behavior information; The display duration of the payment details of the advertisement to be promoted when the user is at the real-time physical location is determined according to the payment details location and the display time node.

[0022] Through this solution, the location of the payment details in the promotional ad in the real-time physical location of the user is determined based on the real-time click location, so as to accurately lock the key content that needs to be displayed in the ad. Obtain the user's behavior information at this location, analyze its interaction mode, and determine its attention node on the payment details based on the user's behavior trajectory. This process ensures that the timing of ad display is highly consistent with user interests. Combined with the payment details location and display time node, determine the display duration of the ad payment details to ensure that the ad is presented to the user in the most appropriate time period. Through these three steps of precise matching and adjustment, the solution optimizes the ad display duration to avoid excessive interruptions, while increasing the user's attention to the payment details, thereby improving the effectiveness and conversion rate of the ad.

[0023] In a second aspect, the present application provides an advertising promotion system based on user portraits, the system comprising: A format requirement determination module is used to obtain real-time behavior information of users before advertising promotion, and determine the user's requirements for the presentation format of the advertisement based on the real-time behavior information; A demand information determination module, used to obtain user information and determine dynamic demand information according to the real-time behavior information and the user information; The promotion information determination module is used to determine the presentation of customized promotion information according to the dynamic demand information and the presentation form requirement, and to perform advertising promotion according to the presentation of customized promotion information. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0025] Figure 1A schematic diagram of an application scenario provided for an embodiment of the present application; Figure 2 A flowchart of an advertising promotion method based on user portrait provided in one embodiment of the present application; Figure 3 A schematic diagram of the structure of an advertising promotion system based on user portraits provided in one embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0027] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0028] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0029] Since the system does not accurately identify the specific needs of users, there is a large deviation between the advertisements pushed by the system and the actual needs of users for the pushed advertisements, which affects the user experience and the conversion rate of advertising promotion.

[0030] Based on this, the present application provides an advertising promotion method and system based on user portraits, which obtains user behavior information in real time, understands the user's current interests and needs, and thus predicts the user's needs for the presentation form of the advertisement, ensuring that the form of the advertisement content is highly matched with the user's immediate needs. Combined with user information, dynamic demand information is generated to further accurately define the user's expectations for the advertisement content in the current environment. Based on dynamic demand information and the user's presentation form requirements, the advertisement content and promotion strategy are precisely adjusted to ensure that the advertisement is not only highly consistent with the user's interests, but also maximizes the user's interaction or purchase intention. Real-time optimization and precise push of advertisement content are achieved, which improves the relevance of advertisements and user engagement, thereby improving the conversion rate and advertising effect of advertisements.

[0031] Figure 1A schematic diagram of an application scenario provided for the present application. When conducting advertising promotion based on user portraits, the method provided by the present application is applied to determine the user's presentation form requirements by obtaining and analyzing the user's real-time behavior information; obtain user information, and determine dynamic demand information based on the presentation form requirements and user information; and determine customized promotion information for the advertisement presentation based on the dynamic demand information and presentation form requirements.

[0032] Specifically, the method provided in the present application is applied to any server, and the server interacts with the advertising promotion system, which can be a system for managing and controlling the promotion of advertisements. The server obtains and analyzes the real-time behavior information and user information of users in the advertising promotion system before the advertising promotion, thereby determining the customized promotion information for the advertisement, and sends the customized promotion information to the advertising promotion system, and the advertising promotion system promotes the advertisement according to the customized promotion information. By obtaining the real-time behavior information of users, their requirements for the presentation form of advertisements can be accurately identified; combined with user information, dynamic demand information can be constructed to achieve personalized demand insights; based on the dynamic and presentation form requirements, customized promotion information can be customized to implement efficient and accurate advertising promotion, thereby improving advertising effectiveness and user satisfaction.

[0033] For specific implementation methods, please refer to the following embodiments.

[0034] Figure 2 This is a flowchart of a user portrait-based advertising promotion method provided in an embodiment of the present application. The method of this embodiment can be applied to the server in the above scenario. Figure 2 As shown, the method includes: S201. Obtain the real-time behavior information of the user before the advertisement is promoted, and determine the user's demand for the presentation form of the advertisement based on the real-time behavior information.

[0035] Real-time behavior information may be information generated by a user's operation on the browsed content before an advertisement is pushed to the user.

[0036] The presentation form requirement may be a user's demand for an advertisement presentation form determined based on the user's real-time behavior information.

[0037] Specifically, the same user's demand for the presentation of different types of browsing content changes in real time. In addition, different users' demand for the presentation of the same type of browsing content will also change. Therefore, the real-time behavior information of the user before the advertising promotion is obtained from the advertising promotion system. The number of forwarding and likes of the browsing content by the user is extracted from the real-time behavior information. The browsing content corresponding to the number of forwarding and likes is obtained from the advertising promotion system, and the browsing content corresponding to the number of forwarding and likes is analyzed using video content analysis technology to obtain the video features of the browsing content corresponding to the number of forwarding and likes, and the video features of the browsing content corresponding to the number of forwarding and likes are determined as the presentation form requirements.

[0038] S202: Obtain user information, and determine dynamic demand information based on real-time behavior information and user information.

[0039] User information may be information about the user when the user browses content or advertisements.

[0040] The dynamic demand information may be information corresponding to the user's dynamically changing demands on the presentation format of the content when browsing the content and the user's own browsing demands on the content.

[0041] Specifically, due to user factors and the user's demand for the presentation form of the browsed content, the user's demand for the presentation form of the browsed content and the browsing content will change dynamically. Therefore, the user information is obtained from the advertising promotion system. The user's age and education level are extracted from the user information. The user's age, education level, forwarding times and like times are analyzed using user behavior analysis technology to obtain the user's first presentation form demand for the browsed content, and the presentation form demand is adjusted according to the first presentation form demand to obtain the adjusted form demand. The adjusted form demand is determined as dynamic demand information.

[0042] S203: Determine to present customized promotion information according to dynamic demand information and presentation format requirements, and perform advertising promotion according to the presented customized promotion information.

[0043] Presenting customized promotion information may be information related to the advertising promotion determined according to the user's own needs during the advertising promotion.

[0044] Specifically, the dynamic demand information and presentation form requirements for browsing content generated by the user's own factors will affect the user's actual needs to a certain extent. Therefore, the user's presentation time period and presentation duration for the content before the advertisement is promoted are extracted from the dynamic demand information. The user's word count requirements for browsing content before the advertisement is promoted are extracted from the presentation form requirements. The advertisements corresponding to the presentation time period, presentation duration and word count requirements determined in the above steps are obtained from the advertising promotion system, and the advertisements corresponding to the presentation time period, presentation duration and word count requirements determined in the above steps are determined as waiting promotion advertisements, and the waiting promotion advertisements are included in the presentation of customized promotion information.

[0045] Through this solution, by obtaining user behavior information in real time and understanding the user's current interests and needs, the user's needs for the presentation form of the advertisement are predicted, ensuring that the form of the advertisement content is highly matched with the user's immediate needs. Combined with user information, dynamic demand information is generated to further accurately define the user's expectations for the advertisement content in the current environment. Based on dynamic demand information and the user's presentation form requirements, the advertisement content and promotion strategy are precisely adjusted to ensure that the advertisement is not only highly consistent with the user's interests, but also maximizes the user's interaction or purchase intention. Real-time optimization and precise push of advertisement content are achieved, which improves the relevance of advertisements and user engagement, thereby improving the conversion rate and advertising effect of advertisements.

[0046] In some embodiments, based on real-time behavior information, determine the user's dwell time, click count, comment count, maximum dwell time, click count, and comment count for different types of content before the advertisement is promoted; determine the user's comprehensive attention intensity for different types of content based on dwell time, click count, comment count, maximum dwell time, click count, and comment count for different types of content; obtain content type information, and determine the number of content types and the proportion of content forms based on the content type information; obtain presentation form information for different types of content, and determine the number of presentation forms based on the presentation form information. Determine the presentation form index based on the number of content types, the proportion of content forms, the comprehensive attention intensity, and the number of presentation forms; obtain the form index level, match the form index level with the presentation form index, and determine the presentation form requirement.

[0047] The rendition information includes the number of renditions.

[0048] The comprehensive attention strength may be a numerical value that measures the user's interest in the content being browsed before advertising is promoted.

[0049] The presentation form information may be information corresponding to the presentation form of each type of content.

[0050] The maximum dwell time may be the maximum dwell time generated when the user browses different types of content before the advertisement is promoted.

[0051] The maximum number of clicks may be the maximum number of clicks generated when users browse different types of content before the advertisement is promoted.

[0052] The maximum number of comments may be the maximum number of comments generated by users when browsing different types of content before the advertisement is promoted.

[0053] The content type information may be information corresponding to each type of content browsed by the user before advertising is promoted to the user.

[0054] The number of content types may be the number corresponding to each type of content browsed by the user before advertising is promoted to the user.

[0055] The content form ratio may be the duration of a certain form of presentation in the content browsed by the user before advertising is promoted to the user, or the duration ratio of the content in the entire content, or the content ratio.

[0056] The number of presentation forms may be the number corresponding to the presentation forms of the content browsed by the user before the advertisement is promoted to the user.

[0057] The format index level may be a level corresponding to the degree of user demand for the presentation format of content before advertising is provided to the user.

[0058] The presentation form index may be a numerical value indicating the strength of a user's demand for the presentation form of the content being browsed before advertising is promoted to the user.

[0059] Specifically, there are differences between different operation behaviors of users on the browsed content, and different operation behaviors reflect the user's demand for the presentation form of the browsed content to different degrees. Therefore, the number of presentation forms is extracted from the presentation form demand. The maximum dwell time, maximum number of clicks, maximum number of comments when the user pays attention to the browsed content before the advertising promotion, as well as the dwell time, clicks and comments of the user on each browsed content are extracted from the real-time behavior information. The dwell time, clicks, and comments of the user on different types of content before the advertising promotion, the maximum dwell time, maximum number of clicks, and maximum number of comments of the user on different types of content are analyzed using a mathematical analysis method to obtain the comprehensive attention intensity of the user on different types of content. The content type information is obtained from the advertising promotion system, and the content quantity and content form proportion are extracted from the content type information. Different types of content are obtained from the advertising promotion system, and different types of content are analyzed using video content analysis technology to obtain video features of different types of content, and the video features of different types of content are determined as presentation form information. The number of presentation forms is extracted from the presentation form information. The number of content types, the proportion of content forms, the comprehensive attention intensity and the number of presentation forms are analyzed using mathematical analysis methods to determine the presentation form index. Before determining the presentation form requirements, all possible form index levels, the presentation forms corresponding to the form index levels and their corresponding presentation form indexes are pre-set to obtain a form index level. The presentation form index is matched with the form index level to obtain the presentation form corresponding to the presentation form index, and the presentation form corresponding to the presentation form index is determined as the presentation form requirement.

[0060] Through this solution, the user's dwell time, clicks and comments on different types of content before advertising promotion are analyzed through real-time behavioral information, and the user's interest preferences are obtained from these data. By calculating the maximum dwell time, clicks and comments of each type of content, the comprehensive attention intensity of users to different types of content is further measured. This step helps to more accurately identify the user's interest points and participation. By obtaining content type information, the number and form proportion of each type of content are determined to provide basic data for advertising matching. The final presentation form requirements are determined by comprehensively considering the dwell time, clicks, comments, number of content types, form proportion, and number of presentation forms. This process can customize the advertising display method according to user behavior, improve the personalization, accuracy and interactivity of advertising, and thus enhance the attractiveness and conversion effect of advertising to users.

[0061] In some embodiments, the comprehensive attention intensity is determined according to the maximum dwell time, the maximum number of clicks, the maximum number of comments, the dwell time, the number of clicks, and the number of comments, calculated according to formula (1): (1) in, represents the comprehensive attention strength, Indicates the preset time weight, represents the residence time, represents the maximum value of the residence time, represents the preset nonlinear time weight, Indicates the preset click weight. represents the number of clicks, Indicates the maximum number of clicks. Indicates the preset comment count weight, Indicates the number of comments. Indicates the maximum number of comments. Represents the preset nonlinear comment count weight.

[0062] The preset time weight may be a value indicating the influence of the dwell time of the user while browsing the content on the calculation result of the comprehensive attention strength when calculating the comprehensive attention strength.

[0063] The preset nonlinear time weight may be a value indicating whether to enhance or weaken the nonlinear contribution of the dwell time to the calculation result of the comprehensive attention strength when calculating the comprehensive attention strength.

[0064] The preset click count weight may be a value indicating the influence of the click count of the user when browsing the content on the calculation result of the comprehensive attention strength when calculating the comprehensive attention strength.

[0065] The preset comment count weight may be a value indicating the influence of the number of comments made by the user when browsing the content on the calculation result of the comprehensive attention strength when calculating the comprehensive attention strength.

[0066] The preset non-linear comment count weight may be a value indicating whether to enhance or weaken the non-linear contribution of the comment count to the calculation result of the comprehensive attention strength when calculating the comprehensive attention strength.

[0067] Specifically, there are many specific operations of users on browsing content, and the degree of attention of users on browsing content reflected by these operations is different. Therefore, the maximum historical stay time, the maximum historical click count, the maximum historical comment count, and the historical stay time, historical click count, and historical comment count of each browsing content of the user are obtained from the advertising promotion system, and the maximum historical stay time, the maximum historical click count, the maximum historical comment count, and the historical stay time, historical click count, and historical comment count of each browsing content of the user obtained in the above steps are calculated to obtain the preset time weight, the preset nonlinear time weight, the preset click count weight, the preset comment count weight, and the preset nonlinear comment count weight. In the process of calculating the preset time weight, the preset nonlinear time weight, the preset click count weight, the preset comment count weight, and the preset nonlinear comment count weight, the linear regression analysis method, the regression tree analysis method, the random forest analysis method, and the neural network regression analysis method can be used for calculation. The mathematical analysis method is used to analyze the maximum dwell time, the maximum number of clicks, the maximum number of comments, the dwell time, the number of clicks, the number of comments, the preset time weight, the preset nonlinear time weight, the preset click weight, the preset comment weight and the preset nonlinear comment weight, and the comprehensive attention intensity is determined by calculation according to formula (1).

[0068] In formula (1), The user's residence time is standardized to the interval ([0,1]) to eliminate the impact of the absolute value difference of the residence time between different contents. Used to simulate the diminishing marginal returns, that is, when the user stays longer, the additional growth in attention intensity gradually decreases. For example, the growth from 10 seconds to 20 seconds may be more significant than that from 200 seconds to 210 seconds. Shorter stays are sufficient to reflect interest, while extremely long stays may reflect factors such as distraction. (a>1): The importance of content with high stay time is amplified. (a<1): Reduce the weight of high stay time, suitable for fast-consumption content. Determine the relative importance of dwell time in the overall attention intensity. If the content type is more dependent on users' in-depth browsing (such as long videos or articles), Should be set higher.

[0069] The click counts are normalized to ([0,1]) to ensure that the click counts of different content are comparable. Indicates the importance of click behavior in comprehensive attention. The number of clicks usually represents the user's initial interest in the content. Its importance may not be as high as the dwell time and number of comments, but it is also one of the core indicators for measuring the intensity of user attention. The number of comments is normalized to ([0,1]) to ensure that the number of comments for different content is comparable. Used to simulate the amplification or suppression effect of comment behavior: ( >1): Emphasize the weight of highly commented content and highlight the deep value of user interaction. ( <1): Weaken the influence of highly commented content, so that low-comment content can also reflect a certain level of attention. The number of comments is usually a direct manifestation of user engagement, and is suitable for strong interactive scenarios such as forums and social media. Therefore, the power transformation can flexibly adjust the weight of this indicator. Determine the relative contribution of the number of comments to the overall attention strength.

[0070] Through this solution, the user's attention level in different dimensions is reflected according to the maximum dwell time, the maximum number of clicks and the maximum number of comments, as well as the real-time dwell time, clicks and comments, combined with the preset time weight, preset click weight and preset comment weight. The preset nonlinear time weight and the preset nonlinear comment weight are used to optimize the impact of nonlinear data and enhance the model's adaptability to the complexity of user behavior. In the formula, after the dwell time, clicks, comments and other behavioral data are standardized, the comprehensive attention intensity is calculated by comprehensive weighted calculation to ensure the organic combination of multi-dimensional data. This step can not only accurately reflect the user's preference for content, but also provide a reliable basis for the subsequent advertising presentation requirements, thereby improving the relevance of advertising recommendations and user experience.

[0071] In some embodiments, based on the number of content types, the proportion of content forms, the comprehensive attention intensity and the number of presentation forms, the presentation form requirement is determined according to formula (2): (2) in, Indicates The presentation index of the form, Indicates the number of content types. Indicates the user's The comprehensive attention intensity of each presentation form, Indicates The content in The proportion of each form;

[0072] Specifically, the content browsed by users is not only of the same type, but of multiple types, and when users browse different types of content, they have different demands for the presentation of different types of content. For example, when users browse technology-related content, they prefer explanations and introductions to technology content, and when users browse food-related content, they prefer the experience of food. In addition, different users may have different demands for the presentation of the same type of content. For example, when the content type browsed by different users is a certain model of mobile phone, some users prefer to browse the introduction to the device parameters of this model of mobile phone, some users prefer to browse the introduction to the appearance of this model of mobile phone, and some users prefer to browse the introduction to the applicable groups of this model of mobile phone.

[0073] Therefore, we use mathematical analysis methods to analyze the comprehensive attention intensity, the number of content types, the proportion of content forms, and the number of presentation forms, and calculate the presentation form index according to formula (2). In formula (2), It reflects the comprehensive score of the presentation format in meeting user needs and advertising effectiveness. It can be understood as the user's i The interest level of a content type is derived from a combination of multiple factors (such as historical browsing behavior, click-through rate, etc.). It means the i i The content type in the jth j The weight or proportion of a presentation form. For example, in a video ad, if a certain content form occupies a larger duration or a more prominent position in the video, the proportion will be larger. It is a weighted summation process of all content types (N in total). The contribution of each content type to the final presentation index is determined by its attention intensity. and the proportion in this presentation format is determined by the product of .

[0074] Through this solution, the presentation form index of each form is calculated using a formula by combining the number of content types, the proportion of content forms, the comprehensive attention intensity and the number of presentation forms. This step takes into account the impact of different content types, the user's attention intensity to each form, and the proportion of content in each presentation form, thereby forming a refined presentation index. By obtaining the form index level and matching it with the corresponding presentation form index, the needs of each presentation form can be effectively quantified and ranked. In this way, not only can the preferences of each user be accurately reflected, but also the advertising presentation form can be dynamically adjusted according to changes in user interests, the content push strategy can be optimized, the user experience and advertising delivery effect can be improved, and ultimately the content can be efficiently matched with user needs.

[0075] In some embodiments, based on historical browsing information, a set of historical product types browsed by the user is determined; current advertising information is obtained, and based on the current advertising information, the type of product promoted in the current advertisement is determined; the historical product type set is matched with the product type to determine whether the product type is in the historical product type set; if the product type is in the historical product type set, it is determined that the current advertisement is pushed to the user.

[0076] User information includes the user's browsing history.

[0077] The historical browsing information may be information about the content browsed by the user before the advertisement is promoted to the user.

[0078] The current advertisement information may be information of related advertisements determined when performing advertisement promotion to the user.

[0079] The historical product type set may be a set corresponding to product types browsed by the user before advertising promotion is performed on the user.

[0080] The product type may be the type of product displayed in the relevant advertisement when the advertisement is promoted to the user.

[0081] Specifically, the user's demand for goods is diverse and changing. When promoting advertisements to users, there may be situations where the corresponding goods in the promoted advertisements do not meet the user's actual demand for goods. Therefore, the user's browsing information of historical content before the advertisement is promoted is extracted from the user information. All goods and their types browsed by the user before the advertisement are extracted from the historical browsing information, and all goods and their types browsed by the user before the advertisement are determined as a historical product type set. The current advertisement information is obtained from the advertisement promotion system, and the product type of the product promoted in the current advertisement is extracted from the current advertisement information. The historical product type set is matched with the product type to determine whether the product type is in the historical product type set. If the product type is in the historical product type set, it is determined that the user has a potential purchase intention and purchase demand for the product in the current advertisement, and at this time, it is determined to push the current advertisement to the user.

[0082] Through this solution, the historical product type set browsed by the user is determined based on the user's historical browsing information. This step can extract the user's long-term interest preferences and form a preliminary user portrait. By obtaining the current advertising information and analyzing the product types promoted by the advertisement, a data basis is provided for the subsequent matching process. The historical product type set is matched with the advertising product type to determine whether the current advertisement meets the user's historical preferences. If the match is successful, it means that the user may have potential interest in the product type, and thus the current advertisement is pushed to the user. This process effectively avoids the possibility of pushing irrelevant advertisements to users, improves the relevance and click-through rate of advertisements, and can also dynamically optimize advertising strategies based on real-time user behavior and historical data, ultimately achieving precision promotion.

[0083] In some embodiments, the advertisement type of the user at the real-time physical location is determined based on the real-time behavior information; based on the real-time physical location, it is determined whether the user has triggered an advertisement attention demand of the advertisement type at the real-time physical location; if the user has triggered an advertisement attention demand at the real-time physical location, then based on the real-time behavior information, the user's presentation type demand for the browsed content is determined; the user's authorization information is obtained after the advertisement attention demand is triggered, and based on the authorization information, the real-time click position of the advertisement details in the advertisement page when the user is at the real-time physical location is predicted; and the presentation type demand and the real-time click position are incorporated into the dynamic demand information.

[0084] User information includes the user's real-time physical location.

[0085] The real-time physical location may be the actual physical location of the user after it is determined that the advertisement is being promoted to the user.

[0086] The advertisement type may be a type corresponding to when the user browses the content at the real-time physical location after determining to promote the advertisement to the user.

[0087] The advertisement attention demand may be a demand of the user for paying attention to the promoted advertisement after it is determined to promote the advertisement to the user.

[0088] The presentation type requirement may be a requirement corresponding to the type of advertisement presentation at the user's real-time physical location after determining to promote the advertisement to the user.

[0089] The authorization information may be information that the user authorizes the advertising promotion system to obtain user-related privacy information.

[0090] The real-time click position may be the position corresponding to when the user clicks on the advertisement page when the user browses the advertisement content using a mobile device at the real-time physical location.

[0091] Specifically, the user's location and the environment corresponding to the user's location may affect or change the user's demand for browsing content or advertisement presentation type, thereby causing the promoted advertisement to fail to meet the user's actual needs.

[0092] Therefore, the real-time physical location of the user is extracted from the user information. The browsing time of the user on several browsing contents at the real-time physical location is extracted from the real-time behavior information. Before determining the advertisement type, an advertisement type and its corresponding browsing time level are preset to obtain a set of preset time level types. The browsing time level can be high, medium and low. The browsing time obtained in the above steps is matched with the preset time level type set to obtain a matching result. According to the matching result, the advertisement type corresponding to the browsing time and the high and medium levels in the preset level type set is determined as the advertisement type. Based on the real-time physical location, the click details information of the user at the real-time physical location is obtained from the advertising promotion system, and the click type and click object of the user at the real-time physical location are extracted from the click details information. Based on the click object, the click type is matched with the advertisement type to determine whether the click type is consistent with the advertisement type. If they are consistent, it is determined that the user has triggered the advertisement attention demand at the real-time physical location.

[0093] The bounce rate of the user when browsing the content at the real-time physical location is extracted from the real-time behavior information. Before determining the presentation type requirement, a bounce rate level and its corresponding presentation requirement type are preset to obtain a preset type set. The bounce rate level can be high, medium and low. The bounce rate is matched with the preset type set to obtain the presentation requirement type corresponding to the high-level bounce rate level and the medium-level bounce rate level corresponding to the bounce rate obtained in the above steps, and the presentation requirement type corresponding to the high-level and medium-level corresponding to the bounce rate is determined as the presentation type requirement. The authorization information of the user after the advertisement attention demand is triggered is obtained from the advertising promotion system. Based on the authorization information, the real-time click position of the advertisement details in the advertisement page when the user is at the real-time physical location is predicted. The presentation type requirement and the real-time click position are included in the dynamic demand information.

[0094] Through this solution, the user's presentation type requirements for browsing content are identified based on real-time behavioral information to ensure that the advertising content matches the user's interests. The real-time physical location is used to determine whether the user has triggered the advertising attention demand of the advertising type, which provides a basis for the precise delivery of advertisements. If the user triggers the advertising attention demand, the behavioral information is further analyzed to determine the user's specific presentation type requirements for browsing content. By obtaining the user's authorization information, the real-time click position of the user on the advertising details in the advertising page is predicted, so as to preset the best position and form of advertising display. The presentation type requirements and real-time click positions are combined to form dynamic demand information, so as to realize dynamic adjustment of advertising display content and timing. Through these steps, advertisements can not only accurately match user needs, but also improve user experience and enhance the conversion rate of advertising effects.

[0095] In some embodiments, based on the authorization information, determine whether the user allows the acquisition of the user's mobile device information; if the user allows the acquisition of the mobile device information, then the mobile device information is acquired; based on the mobile device information, determine the height and swing amplitude of the mobile device when the user is in the real-time physical location; based on the height and swing amplitude, determine the movement range of the center of gravity of the mobile device; based on the movement range of the center of gravity, determine the convenient operation range of the user when the user is in the real-time physical location; based on the convenient operation range, predict the real-time click position of the advertisement details in the advertisement page when the user is in the real-time physical location.

[0096] User information includes user's mobile device information.

[0097] The mobile device information may be information about the device when the user uses the device to browse content at the real-time physical location.

[0098] The convenient operation range may be a range that facilitates the user to perform browsing and clicking operations on the content page when the user uses a mobile device to browse the content at a real-time physical location.

[0099] The center of gravity movement range may be a range formed by the movement of the center of gravity of the mobile device due to the change in the position of the mobile device when the user uses the mobile device at the real-time physical location.

[0100] Specifically, the user's activities at the real-time physical location or the environment in which the user is located will affect or change the user's attention to and browsing of the advertisement page and other related operations, thereby causing a change in the user's actual demand for the browsed content.

[0101] Therefore, the authorization information obtained in the above steps is sent to the user, asking the user whether he agrees that the advertising promotion system obtains the user's mobile device information. If the user agrees that the advertising promotion system obtains his mobile device information, the mobile device information is obtained from the advertising promotion system, and the height and swing amplitude of the mobile device when the user uses the mobile device at the real-time physical location are extracted from the mobile device information. The height and swing amplitude are analyzed using machine learning and data processing technology to obtain the center of gravity movement range of the mobile device. The display range of the mobile device is extracted from the mobile device information, and the display range of the mobile device is used as the reference range. The display range opposite to the center of gravity movement range is determined as the convenient operation range, the convenient operation range is determined as the real-time click position, and the real-time click position is included in the dynamic demand information.

[0102] Through this solution, based on the user authorization information, it is determined whether the user allows the acquisition of their mobile device information. This step ensures compliance with the privacy protection principle. If the user agrees, the information of their mobile device is obtained, and the height and swing amplitude of the device are analyzed based on the information, which can reflect the user's current interaction status. For example, changes in the height and swing amplitude of the device may indicate whether the user is using the device or is in an active state. Further, based on the height and swing amplitude, the range of movement of the center of gravity of the device is calculated, thereby inferring the possible operation range of the user. Through this convenient operation range, the most likely area of ​​the ad details on the ad page to be clicked is predicted when the user is at the real-time physical location. This solution accurately locates the user's behavior patterns and interaction intentions, thereby optimizing ad display and improving user experience and advertising effectiveness.

[0103] In some embodiments, based on the presentation form requirements, the user's browsing needs for browsing content before the advertisement is promoted are determined to determine whether the browsing needs are within the presentation type requirements; if the browsing needs are within the presentation type requirements, the advertising information of the advertisement to be promoted is obtained; based on the advertising information, the presentation duration of each presentation form in the advertisement to be promoted is determined; the presentation duration is matched with the video duration range to obtain the advertisement presentation type corresponding to the presentation duration within the video duration range; based on the real-time click position, the display duration of the payment details of the advertisement to be promoted when the user is at the real-time physical location is determined; the advertisement presentation type and display duration are incorporated into the presentation of customized promotion information.

[0104] The presentation type requirement includes the video duration range corresponding to the video type.

[0105] The browsing demand may be the user's demand for the type of content to be browsed before advertising is promoted to the user.

[0106] The presentation duration may be the display duration of each presentation type in the advertisement to be promoted when promoting advertisements to users.

[0107] The video duration range may be a range corresponding to the user's requirements for the duration of the promoted advertisement when promoting advertisements to the user.

[0108] The advertisement presentation type may be a type corresponding to the user's demand for a specific presentation form of the advertisement within the duration of the video when the advertisement is promoted to the user.

[0109] The display duration may be the length of time that the payment details location is displayed on the advertisement page when the user browses the advertisement at a real-time physical location.

[0110] Specifically, due to the mismatch between the user's browsing needs for browsing content before the advertising promotion and the demand for the presentation type of the advertisement to be promoted, the advertisement to be promoted does not correspond to the actual needs of the user, which in turn affects the accuracy and conversion rate of the advertising promotion.

[0111] Therefore, the user's browsing needs for browsing content before the advertisement is promoted are extracted from the presentation form requirements, the browsing needs are matched with the presentation type requirements, and it is determined whether the browsing needs are within the presentation type requirements. If the browsing needs are within the presentation type requirements, the advertisement information of the advertisement to be promoted is obtained from the advertisement promotion system. The presentation duration of each presentation form in the advertisement to be promoted is extracted from the advertisement information, the video range duration is obtained from the presentation type requirements, the video range duration is matched with the presentation duration, and the advertisement presentation type corresponding to the presentation duration within the video duration range is obtained. According to the real-time click position, the display duration of the payment details of the advertisement to be promoted when the user is at the real-time physical location is determined. The advertisement presentation type and display duration obtained in the above steps are included in the presentation of customized promotion information.

[0112] Through this solution, the type of advertising presentation that is suitable for the video duration is determined based on the presentation format requirements, and the user's browsing needs are predicted based on their interests and behaviors. If the user's browsing needs meet the presentation type requirements, the advertising information of the advertisement to be promoted is further obtained, and the duration of each presentation form in the advertisement is calculated. The duration of the advertisement presentation form is matched with the video duration range to ensure that the advertisement content is displayed within the appropriate duration. Through real-time click location data, the display duration of the user's payment details on the advertisement page is predicted, providing a more accurate basis for adjustment of the advertisement presentation. The advertisement presentation type and display duration are included in the presentation of customized promotional information to ensure that the advertisement can accurately adapt to user needs and improve the conversion rate of advertising effects and user experience.

[0113] In some embodiments, the location of the payment details in the advertisement to be promoted is determined based on the real-time click location when the user is at the real-time physical location; the behavior information of the user at the real-time physical location is obtained, and the display time node of the payment details location is determined based on the behavior information; based on the payment details location and the display time node, the display duration of the payment details for the advertisement to be promoted when the user is at the real-time physical location is determined.

[0114] The payment details location may be the location of the relevant details of the payment for the product on the advertisement page after the advertisement is promoted to the user.

[0115] Behavioral information may be information generated by the user's operation on the advertisement page at the user's real-time physical location.

[0116] The display time node may be the moment when the payment details location is displayed on the advertisement page when the user browses the advertisement at the real-time physical location.

[0117] Specifically, the relevant operations performed by the user on the advertisement at the real-time physical location will affect or change the display time of the payment details in the advertisement page, thereby affecting the user's willingness to purchase the corresponding product in the advertisement and the conversion rate of the advertising promotion. Therefore, the real-time click location is determined as the payment details location in the advertisement to be promoted when the user is at the real-time physical location. The user's behavior information at the real-time physical location is obtained from the advertising promotion system, and the user's browsing time period for the advertisement is extracted from the behavior information. According to the browsing time period, the display time node of the payment details location is determined. Taking the display time node as the time starting point, the moment corresponding to the display time node and the time length corresponding to the browsing time period are added to obtain the display time of the payment details of the advertisement to be promoted when the user is at the real-time physical location, and the display time is included in the presentation of customized promotion information.

[0118] Through this solution, the location of the payment details in the promotional ad in the real-time physical location of the user is determined based on the real-time click location, so as to accurately lock the key content that needs to be displayed in the ad. Obtain the user's behavior information at this location, analyze its interaction mode, and determine its attention node on the payment details based on the user's behavior trajectory. This process ensures that the timing of ad display is highly consistent with user interests. Combined with the payment details location and display time node, determine the display duration of the ad payment details to ensure that the ad is presented to the user in the most appropriate time period. Through these three steps of precise matching and adjustment, the solution optimizes the ad display duration to avoid excessive interruptions, while increasing the user's attention to the payment details, thereby improving the effectiveness and conversion rate of the ad.

[0119] Figure 3 A schematic diagram of a user portrait-based advertising promotion system provided in an embodiment of the present application is shown in FIG. Figure 3As shown, the user portrait-based advertising promotion system 300 of this embodiment includes: a format requirement determination module 301 , a requirement information determination module 302 and a promotion information determination module 303 .

[0120] The form requirement determination module 301 is used to obtain the real-time behavior information of the user before the advertisement is promoted, and determine the user's requirements for the presentation form of the advertisement according to the real-time behavior information; The demand information determination module 302 is used to obtain user information and determine dynamic demand information according to the real-time behavior information and the user information; The promotion information determination module 303 is used to determine the presentation of customized promotion information according to the dynamic demand information and the presentation form requirement, and perform advertising promotion according to the presentation of customized promotion information.

[0121] Optionally, the form requirement determination module 301 is specifically used to: Determine, based on the real-time behavior information, the user's dwell time, click count, number of comments on different types of content before the advertisement is promoted, and the maximum dwell time, click count, and comment count of the user on the different types of content; Determining the comprehensive attention intensity of the user to the different types of content according to the stay time, the number of clicks, the number of comments, the maximum stay time, the maximum number of clicks, and the maximum number of comments of the user on the different types of content; Obtaining content type information, and determining the number of content types and the proportion of content forms according to the content type information; Acquire presentation form information of the different types of content, acquire presentation form information of the different types of content, and determine the number of presentation forms according to the presentation form information; Determine a presentation form index according to the number of content types, the proportion of content forms, the comprehensive attention intensity and the number of presentation forms; Acquire a form index level, match the form index level with the presentation form index, and determine the presentation form requirement.

[0122] Optionally, the form requirement determination module 301 is specifically used to: The comprehensive attention intensity is determined based on the maximum stay time, the maximum number of clicks, the maximum number of comments, the stay time, the number of clicks and the number of comments, and is calculated according to the following formula: ; in, Indicates the comprehensive attention intensity, Indicates the preset time weight, Indicates the dwell time, represents the maximum residence time, represents the preset nonlinear time weight, Indicates the preset click weight. Indicates the number of clicks, Indicates the maximum number of clicks. Indicates the preset comment count weight, Indicates the number of comments. Indicates the maximum number of comments. Represents the preset nonlinear comment count weight.

[0123] Optionally, the form requirement determination module 301 is specifically used to: The presentation form requirement is determined based on the number of content types, the proportion of the content forms, the comprehensive attention intensity and the number of presentation forms, and is calculated according to the following formula:

[0124] ; in, Indicates The presentation index of the form, Indicates the number of content types. Indicates the user's The comprehensive attention intensity of each presentation form, Indicates The content in The proportion of each form.

[0125] Optionally, the user portrait-based advertising promotion system 300 further includes a push confirmation module 304, which is specifically used to: Determine a set of historical commodity types browsed by the user according to the historical browsing information; Acquire current advertisement information, and determine the type of product promoted in the current advertisement based on the current advertisement information; Matching the historical commodity type set with the commodity type to determine whether the commodity type is within the historical commodity type set; If the product type is within the historical product type set, it is determined to push the current advertisement to the user.

[0126] Optionally, the demand information determination module 302 is specifically configured to: Determining, based on the real-time behavior information, the type of advertisement of the user at the real-time physical location; According to the real-time physical location, determining whether the user has triggered an advertisement attention demand of the advertisement type at the real-time physical location; If the user triggers the advertisement attention demand at the real-time physical location, determining the user's demand for presentation type of browsing content according to the real-time behavior information; Obtaining authorization information of the user after triggering the advertisement attention demand, and predicting the real-time click position of the advertisement details in the advertisement page when the user is at the real-time physical location according to the authorization information; The presentation type requirement and the real-time click position are incorporated into the dynamic requirement information.

[0127] Optionally, the demand information determination module 302 is specifically configured to: Determining whether the user allows obtaining the user's mobile device information according to the authorization information; If the user allows obtaining the mobile device information, obtaining the mobile device information; Determine, based on the mobile device information, the height and swing amplitude of the mobile device when the user is at the real-time physical location; Determining a range of movement of the center of gravity of the mobile device according to the height and the swing amplitude; Determining a convenient operation range of the user at the real-time physical location according to the center of gravity movement range; The real-time click position of the advertisement details in the advertisement page when the user is at the real-time physical location is predicted according to the convenient operation range.

[0128] Optionally, the promotion information determination module 303 is specifically used to: Determine the user's browsing needs for browsing content before the advertisement is promoted according to the presentation form requirements, and judge whether the browsing needs are within the presentation type requirements; If the browsing requirement is within the presentation type requirement, then obtaining the advertisement information of the advertisement to be promoted; Determine the duration of each presentation form of the advertisement to be promoted according to the advertisement information; Matching the presentation duration with the video duration range to obtain the advertisement presentation type corresponding to the presentation duration within the video duration range; Determining, based on the real-time click location, how long the payment details of the advertisement to be promoted are displayed when the user is at the real-time physical location; The advertisement display type and the display duration are incorporated into the presentation of customized promotion information.

[0129] Optionally, the promotion information determination module 303 is specifically used to: Determining the location of payment details in the advertisement to be promoted when the user is at the real-time physical location according to the real-time click location; Obtaining user behavior information at the real-time physical location, and determining a display time node for the payment details location based on the behavior information; The display duration of the payment details of the advertisement to be promoted when the user is at the real-time physical location is determined according to the payment details location and the display time node.

[0130] The system of this embodiment can be used to execute the method of any of the above embodiments. The implementation principles and technical effects are similar and will not be described in detail here.

Claims

1. An advertising promotion method based on user portrait, characterized in that: include: Acquire real-time behavior information of users before advertisement promotion, and determine the user's demand for advertisement presentation form based on the real-time behavior information; Acquire user information, and determine dynamic demand information based on the real-time behavior information and the user information; According to the dynamic demand information and the presentation format requirement, it is determined to present customized promotion information, and advertising promotion is performed according to the presented customized promotion information.

2. The method according to claim 1, characterized in that Determining the user's demand for the presentation form of the advertisement according to the real-time behavior information includes: Determine, based on the real-time behavior information, the user's dwell time, click count, number of comments on different types of content before the advertisement is promoted, and the maximum dwell time, click count, and comment count of the user on the different types of content; Determining the comprehensive attention intensity of the user to the different types of content according to the stay time, the number of clicks, the number of comments, the maximum stay time, the maximum number of clicks, and the maximum number of comments of the user on the different types of content; Obtaining content type information, and determining the number of content types and the proportion of content forms according to the content type information; Acquire presentation form information of the different types of content, and determine the number of presentation forms according to the presentation form information; Determine a presentation form index according to the number of content types, the proportion of content forms, the comprehensive attention intensity and the number of presentation forms; Acquire a form index level, match the form index level with the presentation form index, and determine the presentation form requirement.

3. The method according to claim 2, characterized in that The comprehensive attention intensity is determined according to the maximum stay time, the maximum number of clicks, the maximum number of comments, the stay time, the number of clicks and the number of comments, and is calculated according to the following formula: ； in, represents the comprehensive attention strength, Indicates the preset time weight, represents the residence time, represents the maximum value of the residence time, represents the preset nonlinear time weight, Indicates the preset click weight. represents the number of clicks, Indicates the maximum number of clicks. Indicates the preset comment count weight, Indicates the number of comments. Indicates the maximum number of comments. Represents the preset nonlinear comment count weight.

4. The method according to claim 3, characterized in that: The presentation form requirement is determined based on the number of content types, the proportion of content forms, the comprehensive attention intensity and the number of presentation forms, and is calculated according to the following formula: ； in, Indicates The presentation index of the form, Indicates the number of content types. Indicates the user's The comprehensive attention intensity of each presentation form, Indicates The content in The proportion of each form.

5. The method according to claim 1, characterized in that The user information includes the user's historical browsing information. Before obtaining the user's real-time behavior information before the advertisement promotion, the method further includes: Determine a set of historical commodity types browsed by the user according to the historical browsing information; Acquire current advertisement information, and determine the type of product promoted in the current advertisement based on the current advertisement information; Matching the historical commodity type set with the commodity type to determine whether the commodity type is within the historical commodity type set; If the product type is within the historical product type set, it is determined to push the current advertisement to the user.

6. The method according to claim 1, characterized in that The user information includes the real-time physical location of the user, and determining the dynamic demand information according to the real-time behavior information and the user information includes: Determining, based on the real-time behavior information, the type of advertisement of the user at the real-time physical location; According to the real-time physical location, determining whether the user has triggered an advertisement attention demand of the advertisement type at the real-time physical location; If the user triggers the advertisement attention demand at the real-time physical location, determining the user's demand for presentation type of browsing content according to the real-time behavior information; Obtaining authorization information of the user after triggering the advertisement attention demand, and predicting the real-time click position of the advertisement details in the advertisement page when the user is at the real-time physical location according to the authorization information; The presentation type requirement and the real-time click position are incorporated into the dynamic requirement information.

7. The method according to claim 6, characterized in that The user information includes information of a user's mobile device, and the predicting, based on the authorization information, a real-time click position of the advertisement details in the advertisement page when the user is at the real-time physical location includes: Determining whether the user allows obtaining the user's mobile device information according to the authorization information; If the user allows obtaining the mobile device information, obtaining the mobile device information; Determine, based on the mobile device information, the height and swing amplitude of the mobile device when the user is at the real-time physical location; Determining a range of movement of the center of gravity of the mobile device according to the height and the swing amplitude; Determining a convenient operation range of the user at the real-time physical location according to the center of gravity movement range; The real-time click position of the advertisement details in the advertisement page when the user is at the real-time physical location is predicted according to the convenient operation range.

8. The method according to claim 7, characterized in that The presentation type requirement includes a video duration range corresponding to the video type, and the determining of presenting customized promotion information according to the dynamic requirement information and the presentation form requirement includes: Determine the user's browsing needs for browsing content before the advertisement is promoted according to the presentation form requirements, and judge whether the browsing needs are within the presentation type requirements; If the browsing requirement is within the presentation type requirement, then obtaining the advertisement information of the advertisement to be promoted; Determine the duration of each presentation form of the advertisement to be promoted according to the advertisement information; Matching the presentation duration with the video duration range to obtain the advertisement presentation type corresponding to the presentation duration within the video duration range; Determining, based on the real-time click location, how long the payment details of the advertisement to be promoted are displayed when the user is at the real-time physical location; The advertisement display type and the display duration are incorporated into the presentation of customized promotion information.

9. The method according to claim 8, characterized in that The step of determining, based on the real-time click position, the display duration of the payment details of the to-be-promoted advertisement when the user is at the real-time physical location comprises: Determining the location of payment details in the advertisement to be promoted when the user is at the real-time physical location according to the real-time click location; Obtaining user behavior information at the real-time physical location, and determining a display time node for the payment details location based on the behavior information; The display duration of the payment details of the advertisement to be promoted when the user is at the real-time physical location is determined according to the payment details location and the display time node.

10. An advertising promotion system based on user portrait, characterized in that: include: A format requirement determination module is used to obtain real-time behavior information of users before advertising promotion, and determine the user's requirements for the presentation format of the advertisement based on the real-time behavior information; A demand information determination module, used to obtain user information and determine dynamic demand information according to the real-time behavior information and the user information; The promotion information determination module is used to determine the presentation of customized promotion information according to the dynamic demand information and the presentation form requirement, and to perform advertising promotion according to the presentation of customized promotion information.

Images