Intelligent advertisement putting optimization device based on accurate prediction of user behaviors
Through the intelligent advertising delivery optimization device, user behavior data analysis and prediction models are used to achieve accurate advertising delivery, solving the problems of low accuracy and high cost in traditional advertising delivery methods, and improving the effectiveness and return on investment.
Patent Information
- Application Number
- CN202510294891.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-13
- Publication Date
- 2025-06-27
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional advertising delivery methods have problems such as low accuracy, poor results and high costs, which leads to waste of advertising resources and difficulty in improving the return on advertisers' investment.
Design an intelligent advertising delivery optimization device based on accurate prediction of user behavior, including a data collection terminal, a data processing server, an advertising delivery control unit, an effect monitoring and feedback module and a user interface terminal. By collecting and analyzing user behavior data in real time, building user portraits and prediction models, formulating personalized advertising delivery strategies, and monitoring delivery effects in real time.
It has achieved accurate target audiences, optimized advertising display format and frequency, reduced interference to user browsing experience, improved the accuracy and effectiveness of advertising delivery, reduced advertising costs, and increased the return on investment of advertisers.
Smart Images
Figure CN120219009A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of advertising placement, and particularly to an intelligent advertising placement optimization device based on accurate prediction of user behavior. Background Art
[0002] Advertising, as the name implies, is to make something known to the general public. In terms of its meaning, advertising has broad and narrow senses. Economic advertising refers to advertising for profit, usually commercial advertising. It is a means to promote goods or services by paying to spread product or service information to consumers or users through advertising media. Product advertising is such economic advertising.
[0003] With the rapid development of the Internet, advertising placement has become an important means for enterprises to promote products and services. However, traditional advertising placement methods have many problems, such as low accuracy, poor effect, high cost, etc. These problems lead to waste of advertising resources and it is difficult to improve the return on investment (ROI) of advertisers.
[0004] In the field of social media advertising, although social media platforms provide rich user data and refined targeting functions, advertisers still need to more effectively utilize big data technology to analyze user behavior, optimize advertising placement strategies, and improve advertising effects. Summary of the Invention
[0005] To achieve the above object, the present invention proposes an intelligent advertising placement optimization device based on accurate prediction of user behavior, including a data collection terminal, a data processing server, an advertising placement control unit, an effect monitoring and feedback module, and a user interface terminal. The data collection terminal is used to collect user browsing, clicking, and search behavior data in real time;
[0006] The data processing server is used to clean, analyze, and process a large amount of collected data, and construct user portraits and prediction models. The data processing server includes a data storage, a data cleaning and preprocessing, and a data processing and analysis module;
[0007] The advertising placement control unit formulates an advertising placement strategy according to the output result of the prediction model;
[0008] The effect monitoring and feedback module is used to monitor the effect data of advertising placement in real time, and the user interface terminal provides an operation interface for advertisers.
[0009] In one example, the data collection terminal collects user behavior data, user attribute data, and device information. The user behavior data collection collects all types of user behavior data comprehensively, the user attribute data collection obtains static attribute information of users, and the device information involves the types of devices used by users.
[0010] In one example, the data cleaning and preprocessing of the data processing server include removing duplicate, incorrect or incomplete data records, and performing formatting and standardization processing. The data formatting and standardization uniformly convert data from different sources and in different formats into a standard format.
[0011] In one example, the data storage is equipped with high-capacity and high-performance storage devices and adopts a distributed storage architecture.
[0012] In one example, the user behavior analysis uses machine learning algorithms to divide users with similar behavior characteristics into the same group, and constructs a detailed user portrait for each group. The user interest prediction modeling is based on the historical behavior data and attribute data of users, and uses prediction algorithms such as regression models, classification models, and deep learning models to construct a user interest prediction model.
[0013] In one example, the advertisement delivery control unit includes an advertisement delivery decision module and programmatic advertisement delivery and bidding. The advertisement delivery decision module of the advertisement delivery control unit selects advertisement materials that match the user's interests and delivery goals based on the advertisement materials and delivery goals provided by the advertiser, combined with the user's behavior data and interest prediction results.
[0014] In one example, the programmatic advertisement delivery and bidding of the advertisement delivery control unit participate in the bidding for advertisement positions in real time according to the advertiser's budget and the estimated effect of the advertisement.
[0015] In one example, the effect monitoring and feedback module includes effect data collection and effect evaluation and analysis. The effect data collection collects various effect data in real time after the advertisement is delivered.
[0016] In one example, the effect evaluation and analysis of the effect monitoring and feedback module uses data analysis methods and evaluation models to comprehensively evaluate and deeply analyze the effect of advertisement delivery based on the collected effect data, and compare different delivery strategies, advertisement materials, delivery time periods, target audiences, etc.
[0017] An intelligent advertisement delivery optimization device based on accurate prediction of user behavior proposed by the present invention can bring the following beneficial effects:
[0018] 1. By deeply mining the user behavior data, attribute data, and device information, the present device can construct an extremely detailed and accurate user portrait, which covers multi-dimensional characteristics such as interests and hobbies, active time periods, consumption preferences, purchasing power, etc., enabling advertisement delivery to accurately target the target audience.
[0019] 2. The present invention optimizes the display form and frequency of advertisements by intelligently analyzing factors such as the user's device type and network status, reducing the interference with the user's browsing experience.
[0020] 3. Based on accurate user portraits and behavior predictions, the advertisement placement control unit of the present invention can formulate personalized advertisement placement strategies for each user group or even individual users. Every link, from the selection of advertisement materials to the determination of placement time, frequency, and location, fully considers the personalized needs and preferences of users. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] The drawings described herein are used to provide a further understanding of the present invention and form a part of the present invention. The illustrative embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:
[0022] Figure 1 Schematic diagram of the module structure of the intelligent advertisement placement optimization device based on accurate prediction of user behavior; DETAILED DESCRIPTION OF THE EMBODIMENTS
[0023] In order to more clearly illustrate the overall concept of the present invention, the following will be described in detail by way of examples in conjunction with the drawings of the specification.
[0024] In the description of the present invention, it should be understood that the orientation or positional relationships indicated by the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "axial", "radial", "circumferential", etc. are based on the orientation or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the present invention.
[0025] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, "a plurality" means two or more unless otherwise specifically defined.
[0026] In the present invention, unless otherwise clearly specified or limited, the terms "mounted", "connected", "coupled", "fixed", etc. shall be construed in a broad sense. For example, it may be a fixed connection, a detachable connection, or integrated; it may be a mechanical connection, an electrical connection, or a communication connection; it may be directly connected, or indirectly connected through an intermediate medium, and it may be the internal communication of two components or the interaction relationship between two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0027] In the present invention, unless otherwise clearly specified or limited, the first feature being "on" or "under" the second feature may be that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. In the description of this specification, the description referring to terms such as "one solution", "some solutions", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the solution or example are included in at least one solution or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same solution or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more solutions or examples.
[0028] As Figure 1 shown, the present invention provides an intelligent advertising placement optimization device based on accurate prediction of user behavior, including a data collection terminal, a data processing server, an advertising placement control unit, an effect monitoring and feedback module, and a user interface terminal.
[0029] The data collection terminal includes the front-end codes of websites and applications, mobile device SDKs, etc. By embedding specially designed front-end codes in the target websites and application programs, it can capture interactive data such as users' browsing behaviors, click actions, search queries, etc. For example, it records the duration of users browsing different product pages on an e-commerce platform, the number of times they click on product detail pages, search keywords and their search frequencies, etc., providing basic data for subsequent analysis of users' interests and purchase intentions.
[0030] The front-end codes of websites and applications are used to collect users' browsing, clicking, searching and other behavior data in real time, as well as users' device information, network status, etc. The data collection terminal includes a data collection module, and the data collection module conducts user behavior data collection, user attribute data collection, and device information collection.
[0031] The Mobile Device SDK is developed and integrated for the mobile application environment to collect specific data of mobile device users. This not only covers the behavioral data of users within mobile applications, such as article reading preferences in news and information apps, video viewing durations in short video apps, etc., but also includes device information and network status. Device information involves the types of devices used by users (such as mobile phones, tablets, etc.), device brands and models, operating system versions, etc., and the network status includes parameters such as network types (Wi-Fi, 4G, 5G, etc.) and network speeds. This information helps to understand the advertising acceptance habits and preferences of users under different device and network conditions, providing a reference basis for precise advertising placement.
[0032] User behavioral data collection comprehensively collects various types of behavioral data of users. In addition to the above browsing, clicking, and searching behaviors, it also extends to users' purchase records (including purchase time, purchase commodity categories, purchase frequencies, purchase amounts, etc.), behaviors of adding items to the shopping cart but not completing the purchase (which can analyze users' purchase intentions and potential obstacles), and participation in interactive activities (such as comments, likes, shares, etc.). Taking an e-commerce platform as an example, by recording the behavioral path of a user's multiple views of a certain mouse product, adding it to the shopping cart and then canceling the purchase, and finally completing the purchase during a promotional event, it is possible to deeply understand the user's interest intensity, price sensitivity, and purchase decision-making process for this product.
[0033] User attribute data collection obtains users' static attribute information, such as age, gender, geographical location (accurate to cities, districts, etc.), occupation, educational background, etc. These attribute data provide a basic framework for building user portraits, enabling advertising placement to conduct preliminary market segmentation and target positioning based on demographic characteristics. For example, when placing advertisements for mice with a sense of design, portability, and powerful functions to young, highly educated female workplace user groups, it is more likely to attract their attention and purchase interest.
[0034] The data processing server, as the core processing unit of the device, undertakes the tasks of storing, cleaning, analyzing, and processing massive amounts of data, and is the key support for achieving precise advertising placement. Its main functions and modules include data storage, data cleaning and preprocessing, data processing and analysis modules, user behavior analysis, and user interest prediction modeling;
[0035] Data storage is equipped with large-capacity and high-performance storage devices, which can safely and stably store various types of data collected from data acquisition terminals. Adopting a distributed storage architecture ensures the efficient reading and writing and rapid retrieval of data, meeting the requirements of large-scale data processing.
[0036] Data cleaning and preprocessing: Clean and preprocess the collected raw data, remove duplicate, incorrect or incomplete data records, and ensure the quality and reliability of the data. The specific operations are as follows:
[0037] Duplicate data handling: Identify and delete duplicate records in the data. For example, when the same user views the same product page multiple times in a short period, resulting in multiple identical browsing records in the data, only retain one valid record to avoid interfering with the analysis results.
[0038] Incorrect data handling: Detect and correct incorrect information in the data. For issues such as spelling mistakes and inconsistent formats in user address information, automatically correct the incorrect data by comparing with an authoritative address database to ensure the accuracy of user attribute information.
[0039] Incomplete data handling: Supplement or delete incomplete data records. For data with some missing key information (such as user age, purchase amount, etc.), select appropriate filling methods (such as mean filling, median filling, etc.) or directly delete according to business rules and data characteristics to ensure the integrity and consistency of the data.
[0040] Data formatting and standardization: Uniformly convert data from different sources and in different formats into a standard format for subsequent analysis and processing. For example, uniformly convert date and time data into the format of "YYYY-MM-DD HH:MM:SS", and perform normalization processing on numerical data to make the data in the same dimension, improving the data processing efficiency and model training effect.
[0041] Data processing and analysis module: Use advanced data analysis techniques and machine learning algorithms to deeply mine and analyze the cleaned data, extract valuable information, and build user portraits and prediction models.
[0042] User behavior analysis: Through machine learning algorithms such as clustering algorithms and association rule mining algorithms, identify and analyze the user's browsing, clicking, purchasing and other behavior patterns. Divide users with similar behavior characteristics into the same group, and build detailed user portraits for each group, including multi-dimensional characteristics such as hobbies, active time periods, consumption preferences, and purchasing power. For example, by analyzing the user's high-frequency search and purchase behavior for specific product categories, mark them as enthusiasts of this category; according to the user's activity level at different time periods, divide user groups in different active time periods such as morning and evening to provide accurate target audience positioning for precise delivery.
[0043] User interest prediction modeling is based on the user's historical behavior data and attribute data, and uses advanced prediction algorithms such as regression models, classification models, and deep learning models to construct a user interest prediction model. By inputting feature data such as the user's browsing history, purchase records, search keywords, and user attributes, the potential interest level of the user in different product categories or content types is output. For example, using a deep neural network model, through the learning and training of a large amount of user behavior data, the interest probability of users in new mouse products is accurately predicted, providing a scientific basis for the selection and placement of advertising materials.
[0044] The advertising placement control unit is the execution core for achieving precise advertising placement. According to the output results of the prediction model provided by the data processing server, it formulates and executes advertising placement strategies. Its main functions and modules include the advertising placement decision-making module and programmatic advertising placement and bidding:
[0045] The advertising placement decision-making module intelligently selects advertising materials that highly match the user's interests and placement goals based on the advertising materials provided by the advertiser, placement goals (such as brand promotion, product sales, etc.), and the user's behavior data and interest prediction results. For example, for user groups with office needs and an interest in high-end mouse products, priority is given to pushing mouse advertisements with high performance and ergonomic designs; for young users who pursue fashion and individuality, mouse advertisements with unique appearance designs and intelligent functions are placed. At the same time, factors such as the user's device type, network speed, and active time period are comprehensively considered to formulate personalized advertising placement strategies and determine key parameters such as the advertising placement time, frequency, and location. For example, during the period when the user uses a mobile phone and the network speed is fast, high-definition video advertisements are pushed to attract the user's attention; when the user browses news and information applications, native advertisements that match the news content style are inserted to improve the integration degree and user experience of the advertisements.
[0046] In programmatic advertising placement and bidding, during the process of programmatic advertising placement, according to the advertiser's budget and the estimated effect of the advertisement, it participates in the bidding for advertising positions in real time. Machine learning algorithms are used to analyze and predict real-time bidding data, and the advertising bid is automatically adjusted to control the advertising cost while ensuring the advertising placement effect, achieving the maximum cost performance of advertising placement. For example, by analyzing historical bidding data and real-time market conditions, the competition degree and price trend of different time periods and advertising positions are predicted, and the bidding strategy is intelligently adjusted. The bid is appropriately increased during peak competition periods to ensure advertisement exposure, and the bid is reduced during less competitive periods to save costs. At the same time, based on the actual click-through rate, conversion rate and other effect data of the advertisement, the bidding model is dynamically optimized to improve the accuracy and success rate of bidding.
[0047] The Effect Monitoring and Feedback Module is responsible for monitoring the effect data of the advertisement placement in real time and feeding the data back to the data processing server for the optimization and adjustment of the model, forming a closed-loop optimization mechanism for the advertisement placement. Its main functions and modules include effect data collection and effect evaluation and analysis:
[0048] Effect data collection: It collects various types of effect data after the advertisement placement in real time, such as key indicators like click-through rate (CTR), conversion rate (CVR), impressions, cost per click (CPC), cost per acquisition (CPA), etc. These data intuitively reflect the effect of the advertisement placement and the feedback of users, providing a quantitative basis for subsequent effect evaluation and optimization. For example, by monitoring the click-through rate of the advertisement, the initial interest level of users in the advertisement content can be understood; by analyzing the conversion rate, the actual influence of the advertisement on users' purchase behavior can be evaluated; by counting the impression and cost data, the efficiency and cost-effectiveness of the advertisement placement can be calculated.
[0049] Effect evaluation and analysis: According to the collected effect data, data analysis methods and evaluation models are used to comprehensively evaluate and deeply analyze the effect of the advertisement placement. Methods such as A / B testing are adopted to compare different placement strategies, advertisement materials, placement time periods, target audiences, etc.
[0050] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for the relevant parts, reference can be made to the partial description of the method embodiment.
[0051] The above description is only for the embodiments of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the scope of the claims of the present invention.
Claims
1. An intelligent advertising delivery optimization device based on accurate prediction of user behavior, comprising a data acquisition terminal, a data processing server, an advertising delivery control unit, an effect monitoring and feedback module and a user interface terminal, characterized in that: The data collection terminal is used to collect users' browsing, clicking and searching behavior data in real time; The data processing server is used to clean, analyze and process the large amount of collected data, build user portraits and prediction models, and includes data storage, data cleaning and preprocessing, and data processing and analysis modules; The advertising delivery control unit formulates an advertising delivery strategy based on the output results of the prediction model; The effect monitoring and feedback module is used to monitor the effect data of advertising in real time, and the user interface terminal provides an operation interface for advertisers.
2. According to claim 1, the intelligent advertising delivery optimization device based on accurate prediction of user behavior is characterized by: The data collection terminal collects user behavior data, user attribute data and device information. The user behavior data collection collects all kinds of user behavior data in an all-round way. The user attribute data collection obtains the user's static attribute information. The device information involves the type of device used by the user.
3. According to claim 1, the intelligent advertising delivery optimization device based on accurate prediction of user behavior is characterized by: The data cleaning and preprocessing of the data processing server includes removing duplicate, erroneous or incomplete data records, and performing formatting and standardization. Data formatting and standardization convert data from different sources and in different formats into a standard format.
4. According to claim 1, the intelligent advertising delivery optimization device based on accurate prediction of user behavior is characterized by: The data storage is equipped with large-capacity, high-performance storage devices and adopts a distributed storage architecture.
5. According to claim 1, the intelligent advertising delivery optimization device based on accurate prediction of user behavior is characterized by: The user behavior analysis divides users with similar behavior characteristics into the same group through machine learning algorithms, and builds a detailed user portrait for each group. The user interest prediction model is based on the user's historical behavior data and attribute data, and adopts the prediction algorithms of regression models, classification models, and deep learning models to build a user interest prediction model.
6. The intelligent advertising delivery optimization device based on accurate prediction of user behavior according to claim 1, characterized in that: The advertising delivery control unit includes an advertising delivery decision module and programmatic advertising delivery and bidding. The advertising delivery decision module of the advertising delivery control unit screens out advertising materials that match user interests and delivery targets based on the advertising materials and delivery targets provided by the advertiser, combined with the user's behavior data and interest prediction results.
7. The intelligent advertising delivery optimization device based on accurate prediction of user behavior according to claim 6, characterized in that: The programmatic advertising delivery and bidding of the advertising delivery control unit participates in the bidding for advertising positions in real time according to the advertiser's budget and the estimated effect of the advertisement.
8. The intelligent advertising delivery optimization device based on accurate prediction of user behavior according to claim 1, characterized in that: The effect monitoring and feedback module includes effect data collection and effect evaluation and analysis. The effect data collection collects various effect data after the advertisement is released in real time.
9. The intelligent advertising delivery optimization device based on accurate prediction of user behavior according to claim 8, characterized in that: The effect evaluation and analysis of the effect monitoring and feedback module uses data analysis methods and evaluation models based on the collected effect data to conduct a comprehensive evaluation and in-depth analysis of the effect of advertising, and compare different delivery strategies, advertising materials, delivery time periods, target audiences and other conditions.