Online advertisement putting system and method based on big data analysis

Through big data analysis and Internet of Things technology, real-time collection of user environment data, user portraits, and development of advertising strategies has been solved, and the problem of insufficient accuracy and timeliness of advertising delivery in the existing technology has been achieved, achieving more efficient advertising delivery results.

CN118941340AInactive Publication Date: 2024-11-12GUANGZHOU ANSAI COMPUTER TECHNOLOGY CO LTD

Patent Information

Application Number
CN202411225478.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-03
Publication Date
2024-11-12
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing online advertising delivery system cannot perceive the user's environmental changes in real time, and cannot make flexibly adjust according to factors such as time, location and weather, resulting in the inaccurate and timely advertising delivery, and the inability to comprehensively and accurately grasp the actual needs of users.

Method used

Adopt an online advertising delivery system based on big data analysis, combines IoT technology to collect users' weather, geographical location and time data in real time, build user portraits through data analysis modules, formulate advertising delivery strategies, and support multiple delivery channels for real-time monitoring. and evaluate advertising performance and adjust delivery strategies.

Benefits of technology

It improves the accuracy and timeliness of advertising delivery, realizes personalized and precise advertising push, and enhances user experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118941340A_ABST
    Figure CN118941340A_ABST
Patent Text Reader

Abstract

The invention discloses an online advertisement putting system and method based on big data analysis, and relates to the technical field of online advertisement putting, and the system comprises a data collection module which is used for collecting the traditional data of a user and obtaining the data of the environment where the user is located through an Internet of Things device. Traditional data of a user is collected through the data collection module, environment data, including weather conditions, geographical location information and accurate time, of the user can also be obtained, hobbies and interests and actual requirements of the user are comprehensively known, and the data analysis module analyzes the environment data such as weather, geographical location and time, so that the user experience is improved. The requirements and behavior modes of the user in different environments are accurately mastered, the advertisement content is adjusted according to the requirement change of the user, the pertinence and attraction of the advertisement are improved, the environment where the user is located is sensed in real time, the advertisement putting strategy is adjusted according to the environment, the individuation and precision of advertisement putting are achieved, and the user experience is improved. And the accuracy and timeliness of advertisement putting are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of online advertising delivery, and in particular to an online advertising delivery system and method based on big data analysis. Background Art

[0002] In today's digital age, online advertising has become an important means for companies to promote their products and services. Online advertising is a term in the advertising field, which mainly refers to the form of advertising in which advertising agencies can obtain commissions (agency fees) from the media. This form of advertising not only covers the four traditional media - television, newspapers, magazines, and radio, but also includes new media such as outdoor advertising and Internet advertising. Online advertising can transcend geographical restrictions and cover Internet users around the world. Compared with traditional media advertising, the production and publishing costs of online advertising are lower. Online advertising can provide rich interactive experiences, such as clicks, comments, sharing, etc. The online advertising delivery system, as an important tool in the field of modern marketing, provides advertisers with a comprehensive platform to achieve accurate advertising delivery, effect monitoring and optimized management.

[0003] However, the existing online advertising delivery system has many problems and is difficult to meet the needs of advertisers and users. The existing advertising delivery system mainly relies on the analysis of users' browsing history, search history and other data. Although this method can understand users' interests and hobbies to a certain extent, the data source is single and lacks the perception of users' real-time environment. Advertising delivery often cannot adapt to users' changes in time, cannot be flexibly adjusted according to different time, location and weather factors, and cannot fully and accurately grasp users' actual needs. Therefore, it is necessary to propose an online advertising delivery system and method based on big data analysis to solve the problems in the existing technology. Summary of the invention

[0004] The purpose of the present invention is to make up for the shortcomings of the existing technology and provide an online advertising delivery system and method based on big data analysis. It can combine the Internet of Things technology to perceive the user's environment in real time, including weather, geographic location, and time data, and adjust the advertising delivery strategy accordingly to improve the accuracy, timeliness and user experience of advertising delivery.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: an online advertising delivery system based on big data analysis, the system comprising: Data collection module, used to collect traditional user data and obtain user's environmental data through IoT devices, including weather conditions, geographic location information and time data; The data analysis module analyzes the collected data, builds user portraits, and formulates advertising strategies based on environmental data; Advertisement delivery module, which accurately pushes advertisements to target users according to the advertisement delivery strategy and supports multiple delivery channels; The effect evaluation module monitors and evaluates the advertising effect in real time and adjusts the advertising strategy based on feedback information.

[0006] Furthermore, the specific execution steps of the data acquisition module to collect the user's traditional data include: Connect data with users' commonly used browsers and various applications, and obtain users' web browsing history through authorization; Cooperate with search engines to obtain information about search keywords, search time and search frequency with user authorization; Cooperate with the online systems of e-commerce platforms and offline physical stores to collect users’ purchase records.

[0007] Furthermore, the specific execution steps of the data acquisition module to obtain the user's environment data include: Determine the user's geographic location coordinates through the positioning function of the user's device; Send the geographic location coordinates to the meteorological data service provider, and the service provider queries the real-time weather conditions of the area based on the coordinates; For smartphones, the built-in GPS and Beidou positioning systems are used to obtain the user's geographic location coordinates at regular intervals; Process the acquired geographic location information and convert it into easy-to-understand address information. At the same time, determine the type of place where the user is located based on the geographic location information; When the user device interacts with the system, the system time of the device is automatically read; The acquired time information is recorded, including year, month, day, hour, minute, and second. At the same time, the current time period is determined based on the time information, including morning, noon, evening, weekdays, weekends, and holidays. Finally, the weather conditions, geographic location information and time data obtained above are transmitted back to the data acquisition module for storage and subsequent analysis.

[0008] Furthermore, the specific execution steps of the data analysis module include: Check whether there are obvious outliers in the collected data, clean up invalid links and duplicate records in browsing history and search records, identify and remove noise in the data, and convert data from different sources into a unified format; Analyze the collected data and build user portraits; Conduct detailed analysis of environmental data; Comprehensively analyze user portraits and environmental data to formulate advertising strategies.

[0009] Furthermore, in the specific execution steps of the data analysis module, the steps of analyzing the collected data and constructing the user portrait are as follows: Perform text analysis on browsing history and search records, extract keywords, calculate the weight of each keyword, and In the documentation The word frequency in , the calculation formula is: ,in is the keyword In the documentation The number of times it appears in It is a document The total number of times all words appear in ; Inverse Document Frequency The calculation formula is: ,in is the total number of documents, Contains keywords The number of documents; Keywords Weight for: , determine the user’s interest area based on the keyword weight; Calculate the user's purchase frequency and consumption amount distribution, understand the user's consumption habits, analyze the product types, brands and price information in the purchase behavior data, determine the user's consumption preferences, and define the total price of the goods purchased by the user as , the quantity of goods purchased is The average commodity price is , Consumption Capacity Index It is expressed as: ,in and It is the weight coefficient, which is adjusted according to the actual situation and defines the user's The number of purchases within is , purchase frequency index It is expressed as: ; Combine interests and hobbies with consumption habits to determine the user's needs and preferences, and define the weight of interests and hobbies as The consumption capacity index is , the purchase frequency index is , comprehensive index of demand preference It is expressed as: ,in , , is the weight coefficient, which is adjusted according to the actual situation; Divide users into groups with different demand preferences and deliver targeted advertising.

[0010] Furthermore, in the specific execution steps of the data analysis module, the steps of specifically analyzing the environmental data are as follows: Define the influence coefficient of different weather types on user behavior, and define the influence coefficient of sunny days on outdoor activities as , the influence coefficient of rainy days on indoor activities is ; It is detected that the user is in a sunny area. For users who have searched for sports equipment and travel destinations, their interest in outdoor activity related ads is It is expressed as: ,in The probability of the user's historical behavior tending towards outdoor activities; It is detected that it is raining in the user's area, and the user is interested in rain gear and indoor activity ads It is expressed as: ,in The probability of the user's historical behavior tending towards indoor activities; Set demand weights for different geographical locations and define the shopping demand weights for commercial centers as , the catering demand weight is , the travel demand weight of the transportation hub is ; Interest in shopping ads when users are in a commercial center It is expressed as: ,in The probability of the user's historical behavior towards shopping; Interest in catering advertisements It is expressed as: ,in The probability of the user's historical behavior preference for food and beverage; Users’ interest in travel-related ads when they are at a transportation hub It is expressed as: ,in The probability of the user's historical behavior towards travel; Define the impact factors of different time periods on various types of advertisements, and define the impact factor of breakfast food advertisements in the morning as , the impact factors of noon and evening on restaurant advertising are ; In the morning, users’ interest in breakfast food ads It is expressed as: ,in The probability of the user's historical behavior preference for breakfast food; Users’ interest in restaurant ads during lunch and dinner It is expressed as: ,in is the probability of the user's historical behavior toward a restaurant.

[0011] Furthermore, in the specific execution steps of the data analysis module, the steps of comprehensively analyzing user portraits and environmental data and formulating advertising delivery strategies are as follows: Combine the user's interests, hobbies, consumption habits, and demand preferences with the analysis results of environmental data to determine the type of advertisements that the user is most likely to be interested in in a specific environment; Choose the most appropriate advertising channel based on user habits and preferences; Adjust the content and form of advertisements based on user portraits and environmental data to make them more attractive and targeted.

[0012] An online advertising delivery method based on big data analysis, the method comprising: Collect user's environment data and traditional data in real time through IoT devices; Clean and pre-process the collected data, build user portraits, and formulate advertising strategies based on environmental data; Select appropriate channels based on delivery strategies to accurately push ads to target users, and monitor feedback information in real time; Monitor and evaluate advertising effectiveness in real time, adjust advertising strategies and optimize user portraits based on feedback information.

[0013] Furthermore, when collecting the user's environmental data, it includes cooperating with a meteorological data service provider to obtain weather information, using a mobile phone positioning service to obtain a geographic location, and obtaining time data from the user's device system clock.

[0014] Compared with the prior art, the online advertising delivery system and method based on big data analysis have the following beneficial effects: The present invention utilizes the data acquisition module to collect traditional data of users, and can also obtain the environmental data of users, including weather conditions, geographical location information and accurate time, so as to fully understand the interests and actual needs of users. The data analysis module accurately grasps the needs and behavior patterns of users in different environments by analyzing environmental data such as weather, geographical location and time, adjusts the advertising content according to changes in user needs, and improves the pertinence and attractiveness of advertisements. By real-time perception of the user's environment and adjusting the advertising delivery strategy accordingly, the personalized and precise advertising delivery is achieved, thereby improving the accuracy and timeliness of advertising delivery.

[0015] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 It is a structural diagram of an online advertising delivery system based on big data analysis; Figure 2 The present invention is a flowchart of an online advertising method based on big data analysis. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Embodiment 1

[0019] An online advertising delivery system based on big data analysis, the system comprises: a data collection module, a data analysis module, an advertising delivery module and an effect evaluation module.

[0020] The data collection module is used to collect the user's traditional data and obtain the user's environmental data through IoT devices, including weather conditions, geographic location information and time data.

[0021] The specific steps are: connect data with the browsers and various applications commonly used by users, obtain the user's web browsing history through authorization, cooperate with search engines to obtain their search keywords, search time and search frequency information with the user's authorization, and cooperate with the online systems of e-commerce platforms and offline physical stores to collect users' purchase records.

[0022] The user's geographic location coordinates are determined through the positioning function of the user's device. The accuracy of the geographic location can be ensured by using the GPS positioning system of the smartphone or IP address positioning. The geographic location coordinates are sent to the meteorological data service provider, and the service provider queries the real-time weather conditions of the area based on the coordinates, including temperature, humidity, precipitation probability, weather type (such as sunny, cloudy, rainy, etc.).

[0023] For smart phones, the built-in GPS and Beidou positioning systems are used to obtain the user's geographic location coordinates at regular intervals (such as 5 minutes). At the same time, the positioning accuracy and stability are improved by combining Wi-Fi positioning, base station positioning and other technologies. For other IoT devices, such as smart watches and smart home devices, if they have positioning functions, their location information can also be obtained through the corresponding communication protocols and associated with the user's main device to more comprehensively determine the user's location.

[0024] The acquired geographic location information is processed and converted into easy-to-understand address information, such as city, district, street, etc. At the same time, the type of place where the user is located is determined based on the geographic location information, such as commercial center, residential area, park, transportation hub, etc.; when the user device interacts with the system for data, the system time of the device is automatically read. This time is usually very accurate and will be continuously updated with the automatic synchronization function of the device; the acquired time information is recorded, including year, month, day, hour, minute, and second. At the same time, the current time period is determined based on the time information, including morning, noon, evening, weekdays, weekends, and holidays; finally, the weather conditions, geographic location information, and time data acquired above are transmitted back to the data acquisition module for storage and subsequent analysis.

[0025] Finally, combined with other data for comprehensive analysis, users' behaviors and needs may be different during specific time periods (such as holidays) and under specific weather conditions, thus providing a more accurate basis for the formulation of advertising strategies. Through the above detailed execution steps, the data collection module can comprehensively and accurately collect users' traditional data and environmental data, providing strong support for subsequent data analysis and advertising. The data analysis module is the core of the entire advertising delivery system. It conducts in-depth analysis of the collected data, builds user portraits, and formulates advertising delivery strategies based on environmental data.

[0026] The specific steps of the data analysis module are: check whether there are obvious outliers in the collected data, such as unreasonable geographic location coordinates, extreme time values ​​or weather data that is inconsistent with common sense, clean up invalid links and duplicate records in browsing history and search records, identify noise in the data and remove it, and convert data from different sources into a unified format.

[0027] Then analyze the collected data, build user portraits, perform text analysis on browsing history and search records, extract keywords, calculate the weight of each keyword, and In the document (here it can be seen as a collection of the user's browsing history or search records) The word frequency in , the calculation formula is: ,in is the keyword In the documentation The number of times it appears in It is a document The total number of times all words appear in ; Inverse Document Frequency The calculation formula is: ,in is the total number of documents, Contains keywords The number of documents; Keywords Weight for: , ,Determine the user's interest area based on the weight of the keyword.

[0028] Then calculate the user's purchase frequency and consumption amount distribution, understand the user's consumption habits, analyze the product types, brands and price information in the purchase behavior data, determine the user's consumption preferences, and define the total price of the goods purchased by the user as , the quantity of goods purchased is The average commodity price is , Consumption Capacity Index It is expressed as: ,in and It is the weight coefficient, which is adjusted according to the actual situation and defines the user's The number of purchases within is , purchase frequency index It is expressed as: ; Next, we combine interests and hobbies with consumption habits to determine the user's needs and preferences, and define the weight of interests and hobbies as The consumption capacity index is , the purchase frequency index is , comprehensive index of demand preference It is expressed as: ,in , , It is the weight coefficient, which is adjusted according to the actual situation; users are divided into different demand preference groups and targeted advertising is delivered.

[0029] Then, we conduct a specific analysis of the environmental data and define the influence coefficients of different weather types on user behavior. We define the influence coefficient of sunny days on outdoor activities as , the influence coefficient of rainy days on indoor activities is ; It is detected that the user is in a sunny area. For users who have searched for sports equipment and travel destinations, their interest in outdoor activity related ads is It is expressed as: ,in The probability of the user's historical behavior being inclined towards outdoor activities. It is detected that the user is in a rainy area, and the user's interest in rain gear and indoor activity advertisements It is expressed as: ,in is the probability of the user's historical behavior tending towards indoor activities.

[0030] Set demand weights for different geographical locations and define the shopping demand weights for commercial centers as , the catering demand weight is , the travel demand weight of the transportation hub is ; Interest in shopping ads when users are in a commercial center It is expressed as: ,in The probability of the user's historical behavior towards shopping and the interest in catering advertisements It is expressed as: ,in The probability of the user's historical behavior preference for food and beverage; Users’ interest in travel-related ads when they are at a transportation hub It is expressed as: ,in is the probability of the user's historical behavior towards travel.

[0031] Define the impact factors of different time periods on various types of advertisements, and define the impact factor of breakfast food advertisements in the morning as ; In the morning, users’ interest in breakfast food ads It is expressed as: ,in The probability of the user's historical behavior preference for breakfast food; Users’ interest in restaurant ads during lunch and dinner It is expressed as: ,in The probability of the user's historical behavior toward a restaurant; Comprehensively analyze user portraits and environmental data to formulate advertising strategies, combine user interests, consumption habits, and demand preferences with the analysis results of environmental data, and determine the types of ads that users are most likely to be interested in in a specific environment. For example, if the user's interests are sports and fitness, and the current weather is sunny, the location is near a park, and it is morning, then ads for sports drinks, energy bars, and other foods suitable for consumption before and after exercise can be pushed to the user; Choose the most appropriate advertising channel based on user habits and preferences. For example, for users who frequently use social media, you can place ads on their frequently used social platforms. For users who like online shopping, you can display ads on e-commerce platforms. Based on user portraits and environmental data, adjust the content and form of ads to make them more attractive and targeted. For example, when pushing umbrella ads to users on rainy days, you can use warm and practical advertising copy and show the waterproof performance and fashionable design of umbrellas. According to the advertising delivery strategy, the ads can be accurately pushed to target users, and multiple delivery channels can be supported. Finally, the advertising delivery effect is monitored and evaluated in real time, and the delivery strategy is adjusted based on feedback information.

[0032] The system uses the data acquisition module to collect traditional user data and can also obtain the user's environmental data, including weather conditions, geographic location information and exact time, to fully understand the user's interests and actual needs. The data analysis module analyzes environmental data such as weather, geographic location and time to accurately grasp the user's needs and behavior patterns in different environments, adjust advertising content according to changes in user needs, and improve the pertinence and attractiveness of advertising.

[0033] Embodiment 2 An online advertising delivery method based on big data analysis, the steps of the dynamic monitoring area adjustment module are as follows: First, use browser plug-ins and application programming interfaces (APIs) to collect users' browsing history, including the addresses of visited web pages, dwell time, visit frequency and other information. Cooperate with search engines to obtain users' search records, including search keywords, search time, search frequency, etc. Connect with the online systems of e-commerce platforms and offline physical stores to collect users' purchasing behavior data, such as the types of goods purchased, brands, prices, purchase time, etc.

[0034] Cooperate with meteorological data service providers to obtain local weather conditions through the user's geographic location information, including temperature, humidity, precipitation probability, weather type, etc., and utilize the positioning functions of the user's device, such as GPS, IP address positioning, etc., to obtain the user's geographic location information, including longitude and latitude coordinates, city, district, street, etc., and directly obtain the accurate time from the system clock of the user's device, including year, month, day, hour, minute, second and other information.

[0035] Perform text analysis on browsing history and search records, extract keywords, use the term frequency-inverse document frequency (TF-IDF) algorithm to calculate the weight of each keyword, and determine the user's interest area based on the keyword weight. For example, if the user frequently searches for keywords such as "sports equipment" and "fitness courses", the user's interests and hobbies can be marked as "sports and fitness". Analyze the product types, brands, prices and other information in the purchase behavior data to determine the user's consumption preferences, calculate the user's purchase frequency and consumption amount distribution, and understand the user's consumption habits. For example, if the user often buys high-end brand electronic products, it can be judged that the user has a high consumption capacity and preference for technology products. Combine interests and consumption habits to determine the user's demand preferences. Through algorithms such as cluster analysis, divide users into different demand preference groups for targeted advertising, define the impact coefficient of different weather types on user behavior, set demand weights for different geographical locations and venue types, and set the impact factors of different time periods on various types of advertisements.

[0036] Comprehensively analyze user portraits and environmental data to determine the types of ads that users are most likely to be interested in in a specific environment. For example, if the user's hobby is sports and fitness, and the current weather is sunny, the location is near a park, and it is morning, then you can push ads for sports drinks, energy bars, and other items suitable for consumption before and after exercise to the user. Choose the most appropriate advertising channel based on the user's usage habits and preferences. For example, for users who frequently use social media, you can put ads on their frequently used social platforms. For users who like online shopping, you can display ads on e-commerce platforms. Optimize the content and form of ads to make them more attractive and targeted. For example, when pushing umbrella ads to users on rainy days, you can use warm and practical advertising copy and showcase the umbrella's waterproof performance and fashionable design.

[0037] Analyze user usage habits, combine user browsing history and application usage records, determine the devices and software that users frequently use, as well as the frequency and time distribution of usage on different channels, consider the adaptability of different advertising types to each delivery channel, and the user group characteristics of each channel, ensure that the target audience of advertising matches the user group of the channel, and select the most appropriate advertising channel based on the analysis results of user usage habits and channel adaptability, taking into account the costs and benefits of advertising.

[0038] Customize ads based on user portraits. Utilize the user portraits built using the data analysis module to understand the user's interests, hobbies, consumption habits, and demand preferences, personalize the ad content, and adjust the ad content and format based on the analysis results of environmental data by the data analysis module to make it more suitable for the user's environment. Select appropriate ad formats, such as picture ads, video ads, information flow ads, pop-up ads, etc., based on different delivery channels and user needs.

[0039] Connect with the delivery channels. According to the selected advertising delivery channels, connect with the corresponding platforms or service providers, provide necessary advertising materials and data, and convert and optimize the formats according to the requirements of the channels. During the advertising delivery process, monitor the number of advertisements displayed, click-through rate, conversion rate and other indicators in real time to understand the effectiveness of the advertising delivery. According to the real-time monitoring data and user feedback information, continuously optimize the advertising delivery strategy, adjust the advertising delivery channel combination, advertising content and format, release time, etc.

[0040] Monitor advertising data in real time, connect data with the advertising delivery module and various delivery channels, obtain data such as the number of advertisements displayed, clicked, and converted in real time, collect user evaluations and feedback on advertisements through online surveys, user comments, social media monitoring, etc., integrate data from different channels, and ensure data accuracy and completeness.

[0041] Based on the collected data, calculate the value of each evaluation indicator, compare the current advertising effect with historical data, analyze the improvement effect of the advertising strategy, and at the same time, compare with the advertising effect of the same industry to understand the competitiveness of this system in the market. Use data analysis technology to conduct in-depth mining of user behavior data, analyze the user's behavior path before and after clicking on the advertisement, understand the user's decision-making process, and analyze the differences in responses of different user groups to advertisements to provide a basis for precise delivery.

[0042] The results of data analysis and evaluation are organized into a report, including the values ​​of various evaluation indicators, comparative analysis results, user feedback summaries, etc., and fed back to relevant departments. The evaluation report is promptly fed back to the advertising delivery module, data analysis module and other relevant departments to provide a basis for optimizing the advertising delivery strategy. According to the results of the effect evaluation, the advertising delivery strategy is continuously optimized, and the advertising creativity, delivery channel combination, advertising content and format are adjusted to improve the effectiveness of advertising and user experience. At the same time, the effect evaluation indicators are regularly adjusted and improved to adapt to market changes and changes in user needs.

[0043] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the same elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. An online advertising delivery system based on big data analysis, characterized in that: The system includes: Data collection module, used to collect traditional user data and obtain user's environmental data through IoT devices, including weather conditions, geographic location information and time data; The data analysis module analyzes the collected data, builds user portraits, and formulates advertising strategies based on environmental data; Advertisement delivery module, which accurately pushes advertisements to target users according to the advertisement delivery strategy and supports multiple delivery channels; The effect evaluation module monitors and evaluates the advertising effect in real time and adjusts the advertising strategy based on feedback information.

2. The online advertising delivery system based on big data analysis according to claim 1, characterized in that: The specific execution steps of the data acquisition module to collect the user's traditional data include: Connect data with users' commonly used browsers and various applications, and obtain users' web browsing history through authorization; Cooperate with search engines to obtain information about search keywords, search time and search frequency with user authorization; Cooperate with the online systems of e-commerce platforms and offline physical stores to collect users’ purchase records.

3. The online advertising delivery system based on big data analysis according to claim 1, characterized in that: The specific execution steps of the data acquisition module to obtain the user's environmental data include: Determine the user's geographic location coordinates through the positioning function of the user's device; Send the geographic location coordinates to the meteorological data service provider, and the service provider queries the real-time weather conditions of the area based on the coordinates; For smartphones, the built-in GPS and Beidou positioning systems are used to obtain the user's geographic location coordinates at regular intervals; Process the acquired geographic location information and convert it into easy-to-understand address information. At the same time, determine the type of place where the user is located based on the geographic location information; When the user device interacts with the system, the system time of the device is automatically read; The acquired time information is recorded, including year, month, day, hour, minute, and second. At the same time, the current time period is determined based on the time information, including morning, noon, evening, weekdays, weekends, and holidays. Finally, the weather conditions, geographic location information and time data obtained above are transmitted back to the data acquisition module for storage and subsequent analysis.

4. The online advertising delivery system based on big data analysis according to claim 1, characterized in that: The specific execution steps of the data analysis module include: Check whether there are obvious outliers in the collected data, clean up invalid links and duplicate records in browsing history and search records, identify and remove noise in the data, and convert data from different sources into a unified format; Analyze the collected data and build user portraits; Conduct detailed analysis of environmental data; Comprehensively analyze user portraits and environmental data to formulate advertising strategies.

5. The online advertising delivery system based on big data analysis according to claim 4 is characterized in that: In the specific execution steps of the data analysis module, the steps of analyzing the collected data and constructing the user portrait are as follows: Perform text analysis on browsing history and search records, extract keywords, calculate the weight of each keyword, and In the documentation The word frequency in , the calculation formula is: ,in is the keyword In the documentation The number of times it appears in It is a document The total number of times all words appear in ; Inverse Document Frequency The calculation formula is: ,in is the total number of documents, Contains keywords The number of documents; Keywords Weight for: , determine the user’s interest area based on the keyword weight; Calculate the user's purchase frequency and consumption amount distribution, understand the user's consumption habits, analyze the product types, brands and price information in the purchase behavior data, determine the user's consumption preferences, and define the total price of the goods purchased by the user as , the quantity of goods purchased is The average commodity price is , Consumption Capacity Index It is expressed as: ,in and It is the weight coefficient, which is adjusted according to the actual situation and defines the user's The number of purchases within is , purchase frequency index It is expressed as: ; Combine interests and hobbies with consumption habits to determine the user's needs and preferences, and define the weight of interests and hobbies as The consumption capacity index is , the purchase frequency index is , comprehensive index of demand preference It is expressed as: ,in , , is the weight coefficient, which is adjusted according to the actual situation; Divide users into groups with different demand preferences and deliver targeted advertising.

6. The online advertising delivery system based on big data analysis according to claim 4, characterized in that: In the specific execution steps of the data analysis module, the steps of specifically analyzing the environmental data are as follows: Define the influence coefficient of different weather types on user behavior, and define the influence coefficient of sunny days on outdoor activities as , the influence coefficient of rainy days on indoor activities is ; It is detected that the user is in a sunny area. For users who have searched for sports equipment and travel destinations, their interest in outdoor activity related ads is It is expressed as: ,in The probability of the user's historical behavior tending towards outdoor activities; It is detected that it is raining in the user's area, and the user is interested in rain gear and indoor activity ads It is expressed as: ,in The probability of the user's historical behavior tending towards indoor activities; Set demand weights for different geographical locations and define the shopping demand weights for commercial centers as , the catering demand weight is , the travel demand weight of the transportation hub is ; Interest in shopping ads when users are in a commercial center It is expressed as: ,in The probability of the user's historical behavior towards shopping; Interest in catering advertisements It is expressed as: ,in The probability of the user's historical behavior preference for food and beverage; Users’ interest in travel-related ads when they are at a transportation hub It is expressed as: ,in The probability of the user's historical behavior towards travel; Define the impact factors of different time periods on various types of advertisements, and define the impact factor of breakfast food advertisements in the morning as , the impact factors of noon and evening on restaurant advertising are ; In the morning, users’ interest in breakfast food ads It is expressed as: ,in The probability of the user's historical behavior preference for breakfast food; Users’ interest in restaurant ads during lunch and dinner It is expressed as: ,in is the probability of the user's historical behavior toward a restaurant.

7. The online advertising delivery system based on big data analysis according to claim 4, characterized in that: In the specific execution steps of the data analysis module, the steps of comprehensively analyzing user portraits and environmental data and formulating advertising delivery strategies are as follows: Combine the user's interests, hobbies, consumption habits, and demand preferences with the analysis results of environmental data to determine the type of advertisements that the user is most likely to be interested in in a specific environment; Choose the most appropriate advertising channel based on user habits and preferences; Adjust the content and form of advertisements based on user portraits and environmental data to make them more attractive and targeted.

8. An online advertising method based on big data analysis, characterized in that: The method includes: Collect user's environment data and traditional data in real time through IoT devices; Clean and pre-process the collected data, build user portraits, and formulate advertising strategies based on environmental data; Select appropriate channels based on delivery strategies to accurately push ads to target users, and monitor feedback information in real time; Monitor and evaluate advertising effectiveness in real time, adjust advertising strategies and optimize user portraits based on feedback information.

9. The online advertising delivery method based on big data analysis according to claim 8, characterized in that: When collecting environmental data about the user, it includes cooperating with meteorological data service providers to obtain weather information, using mobile phone positioning services to obtain geographic location, and obtaining time data from the system clock of the user's device.

Citation Information

Patent Citations

  • Big data analysis system for advertising

    CN117593053A

  • Advertisement putting method and system based on user big data analysis

    CN117808535A

  • Advertisement promotion platform and promotion method based on big data analysis

    CN118134554A

  • Accurate advertisement putting method and system based on Internet big data

    CN118229362A

  • System for analyzing advertising on online video platforms for digital marketing through machine learning, in order to reach a broad audience.

    DE202022102520U1

Cited By

  • Advertisement generation marketing method based on user behavior driving

    CN119722190A

  • Advertisement putting strategy optimization method and system based on AI learning

    CN120258913A

  • Marketing method and device based on user behavior analysis, equipment and medium

    CN120952924A