Precise pushing method and system based on big data
By establishing a classification database and using facial recognition login and collaborative filtering recommendation algorithms, the problem of minors accessing violent or pornographic content in Internet big data has been solved, and precise push based on gender, age and education level has been achieved, improving the accuracy and security of content push.
Patent Information
- Application Number
- CN202510501563.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-21
- Publication Date
- 2025-09-05
AI Technical Summary
Existing Internet and big data analysis technologies make it difficult to accurately push knowledge, especially when considering factors such as user gender, age and education level, and cannot effectively prevent minors from accessing violent or pornographic content.
By establishing a classified database, collecting and analyzing user information, using facial recognition login, combining collaborative filtering recommendation algorithms and distributed processing, using users' historical behavior data for precise push, setting access rights for minors, and calculating user similarity through cosine similarity, accurate content matching can be achieved.
It enables precise content push based on factors such as user gender, age, and education level, preventing minors from accessing inappropriate content and improving the accuracy and security of push.
Smart Images
Figure CN120596733A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of accurate push of big data, and in particular to a method and system for accurate push based on big data. Background Art
[0002] With the advent of the cloud era, big data has attracted increasing attention. The analyst team believes that big data is generally used to describe large amounts of unstructured and semi-structured data, which can be used for market and user group analysis.
[0003] The development of the existing Internet and big data analysis technology has provided new channels and methods for the promotion of knowledge. How to use the Internet to accurately push popular science knowledge has become one of the research and development directions of technical personnel in this field. Summary of the Invention
[0004] To solve the above technical problems, the present invention provides a method and system for accurate push notification based on big data, which specifically includes the following steps:
[0005] Step 1: Establishment of the database, including categories such as entertainment stars, social environment, humanities and history, military development, and food;
[0006] Step 2: User information collection: collect and analyze the user's browsing content on the day through the sub-database, and then compare the browsing content with the database to push content;
[0007] Step 3: User self-selection: Users can choose the content to browse based on the selected modules, and can choose the modules they like to browse or remove the modules they don’t like;
[0008] Step 4: Data information collection, by collecting and processing the user's daily information, and collecting and analyzing the browsing information of the day, month, and year, the pushed content is obtained in a more detailed manner.
[0009] Preferably, the user information includes the user's gender, age and education level. In terms of age content, especially for minors, access denial processing authority is set for minors requesting access to violent and pornographic content.
[0010] Preferably, the user information includes the user's gender, age and education level. In terms of age content, especially for minors, access denial processing authority is set for minors requesting access to violent and pornographic content.
[0011] Preferably, the database login is provided with a face recognition module, and login is performed through face recognition, thereby preventing the database from pushing wrong content when different groups of people log in, which does not meet the browsing needs of the current user.
[0012] Preferably, the user information collection includes the time users spend browsing content of different categories, and the time users spend browsing content is classified from most to least.
[0013] Preferably, the database includes an incremental module, which is used to expand the database content, thereby being able to update the database in real time.
[0014] Preferably, the underlying logic of the database adopts distributed processing and parallel programming, and the distributed processing is implemented through cloud computing, and the recommendation system of the database mostly adopts a collaborative filtering recommendation algorithm.
[0015] Preferably, the collaborative filtering recommendation algorithm specifically uses cosine similarity to convert the ratings of user u and user v into vector models u and v in n-dimensional space, and calculate the similarity between the two users based on the two space vectors, that is, the cosine value of the two space vectors. The specific formula is as follows:
[0016] sim(u,v)=cos(u,v)=u*v / ||u||.||v||
[0017] Preferably: the core dimension recommendation module of the recommendation system mainly reads the user's historical behavior data through the background processing module cluster, calculates the similarity of grouped users based on the user's historical records and the user's collaborative filtering algorithm, and passes the calculation results to the central processing module, which displays the results on the user's browsing interface.
[0018] Technical effects and advantages of the present invention:
[0019] The present invention establishes different classification contents through a database, collects and analyzes users' daily browsing information, and matches the browsing contents that users like to read according to their gender, education level and age stage, so as to achieve accurate push processing. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] Figure 1 This is a main diagram of a precise push method based on big data and a system structure provided by the present invention;
[0021] Figure 2 This is a structural rear view of a precise push method and system based on big data provided by the present invention; DETAILED DESCRIPTION
[0022] The present invention will be described in further detail below with reference to the accompanying drawings and specific embodiments. The embodiments of the present invention are provided for purposes of illustration and description and are not intended to be exhaustive or to limit the invention to the disclosed forms. Many modifications and variations will be apparent to those skilled in the art. The embodiments are chosen and described to better illustrate the principles of the invention and its practical application, and to enable those skilled in the art to understand the invention and design various embodiments with various modifications suitable for specific applications.
[0023] See also Figures 1-2 In this embodiment, a method and system for accurate push notification based on big data are provided, which specifically include the following steps:
[0024] Step 1: Establishment of the database, including categories such as entertainment stars, social environment, humanities and history, military development, and food;
[0025] Step 2: User information collection: collect and analyze the user's browsing content on the day through the sub-database, and then compare the browsing content with the database to push content;
[0026] Step 3: User self-selection. Users can choose the browsing content based on the selected module, and independently select the module content they like to browse or remove the modules they don’t like;
[0027] Step 4: Data information collection, by collecting and processing the user's daily information, and collecting and analyzing the browsing information of the day, month, and year, the pushed content is obtained in a more detailed manner.
[0028] The user information includes the user's gender, age and education level. In terms of age content, especially for minors, access denial processing permissions are set for minors requesting access to violent and pornographic content.
[0029] The user information includes the user's gender, age and education level. In terms of age content, especially for minors, access denial processing permissions are set for minors requesting access to violent and pornographic content.
[0030] The database login is provided with a face recognition module, and login is performed through face recognition, thereby preventing the database from pushing wrong content when different groups of people log in, which does not meet the browsing content required by the current user.
[0031] The user information collection includes the time users spend browsing content of different categories, and the time users spend browsing content is classified from most to least.
[0032] The database includes an incremental module, which is used to expand the database content, so that the database can be updated in real time.
[0033] The underlying logic of the database adopts distributed processing and parallel programming, and the distributed processing is achieved through cloud computing, while the recommendation system of the database mostly adopts collaborative filtering recommendation algorithm.
[0034] The collaborative filtering recommendation algorithm specifically uses cosine similarity to convert the ratings of user u and user v into vector models u and v in n-dimensional space. The similarity between the two users is calculated based on the two space vectors, which is the cosine value of the two space vectors. The specific formula is as follows:
[0035] sim(u,v)=cos(u,v)=u*v / ||u||.||v||
[0036] The core dimension of the recommendation system is the recommendation module. The recommendation module mainly reads the user's historical behavior data through the background processing module cluster, calculates the similarity of grouped users based on the user's historical records and the user's collaborative filtering algorithm, and passes the calculation results to the central processing module. The central processing module displays the results on the user's browsing interface.
[0037] Obviously, the embodiments described are only some 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 and related fields without making creative efforts should fall within the scope of protection of the present invention. Structures, devices, and operating methods not specifically described and explained in the present invention shall be implemented in accordance with conventional means in the field unless otherwise specified or limited.
Claims
1. A precise push method and system based on big data, characterized in that: The specific steps include: Step 1: Establishment of the database, including categories such as entertainment stars, social environment, humanities and history, military development, and food; Step 2: User information collection: collect and analyze the user's browsing content on the day through the sub-database, and then compare the browsing content with the database to push content; Step 3: User self-selection. Users can choose the browsing content based on the selected module, and independently select the module content they like to browse or remove the modules they don’t like; Step 4: Data information collection, by collecting and processing the user's daily information, and collecting and analyzing the browsing information of the day, month, and year, the pushed content is obtained in a more detailed manner.
2. According to claim 1, a method and system for accurate push notification based on big data is characterized in that ,The database contains a positioning module that pushes local ,featured content based on the country and content in which the user is ,located, so that the user can browse the information he needs without ,doing independent search processing.
3. The method and system for accurate push based on big data according to claim 1, characterized in that: The user information includes the user's gender, age and education level. In terms of age content, especially for minors, access denial processing permissions are set for minors requesting access to violent and pornographic content.
4. The method and system for accurate push based on big data according to claim 3, characterized in that: The database login is provided with a face recognition module, and login is performed through face recognition, thereby preventing the database from pushing wrong content when different groups of people log in, which does not meet the browsing content required by the current user.
5. The method and system for accurate push based on big data according to claim 1, characterized in that: The user information collection includes the time users spend browsing content of different categories, and the time users spend browsing content is classified from most to least.
6. The method and system for accurate push based on big data according to claim 1, characterized in that: The database includes an incremental module, which is used to expand the database content, so that the database can be updated in real time.
7. The method and system for accurate push based on big data according to claim 1, characterized in that: The underlying logic of the database adopts distributed processing and parallel programming, and the distributed processing is achieved through cloud computing, while the recommendation system of the database mostly adopts collaborative filtering recommendation algorithm.
8. The method and system for accurate push notification based on big data according to claim 1, characterized in that: The collaborative filtering recommendation algorithm specifically uses cosine similarity to convert the ratings of user u and user v into vector models u and v in n-dimensional space. The similarity between the two users is calculated based on the two space vectors, which is the cosine value of the two space vectors. The specific formula is as follows: sim(u,v)=cos(u,v)=u*v / ||u||.||v|| 9. The method and system for accurate push based on big data according to claim 1, characterized in that: The core dimension of the recommendation system is the recommendation module. The recommendation module mainly reads the user's historical behavior data through the background processing module cluster, calculates the similarity of grouped users based on the user's historical records and the user's collaborative filtering algorithm, and passes the calculation results to the central processing module. The central processing module displays the results on the user's browsing interface.