Information Push System Using Page View Metrics

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for pushing advertisements over the internet often neglect user experience, particularly when dealing with new advertisements from companies lacking historical push data, leading to random and unconsidered content delivery.

Innovation Solution

An information push method that acquires page view numbers and recommendation degrees for information over a predetermined period, adjusts these metrics, and selects content based on specific thresholds and weights to determine and deliver information that meets user preferences.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If random selection is used for new advertisements without historical data, then new advertisements can be pushed to users, but user experience deteriorates due to lack of consideration for user preferences

Engineering Contradiction:

Improveability to push new advertisementsVSAvoiduser experience quality

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system performs preliminary actions by collecting and analyzing user behavior data (clicks, views,停留 time) before pushing new advertisements. This preliminary data collection and analysis enables the system to establish user preference profiles in advance, so when new advertisements need to be pushed, the system can immediately match them with appropriate users based on pre-analyzed preferences rather than random selection.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms by continuously monitoring user interactions with pushed advertisements (click-through rates, view duration, skip behavior) and using this feedback to refine user preference models. This feedback loop ensures that even for new advertisements without historical data, the system can leverage real-time user response feedback to improve matching accuracy and maintain user experience quality.

Inventive Principle:

Principle #23Feedback

2Reliability

If historical push information is used to determine advertisements, then user preferences can be considered, but new advertisements from companies without historical data cannot be effectively pushed

Engineering Contradiction:

Improveuser preference matchingVSAvoidability to push new advertisements

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The system merges multiple data sources and methodologies: it combines historical push information with real-time user behavior data, integrates explicit user feedback with implicit behavioral signals, and merges content-based filtering with collaborative filtering techniques. This merging enables the system to maintain reliable user preference matching while simultaneously accommodating new advertisements without historical data by leveraging other available signal sources.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The system introduces intermediary elements such as user preference profiles, content feature vectors, and matching algorithms that act as mediators between historical data and new advertisements. These intermediaries enable the system to bridge the gap by translating new advertisement content into comparable feature representations that can be matched against user profiles, even when no direct historical interaction data exists for the new advertisements.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Reliability

If multiple data sources and methodologies are integrated, then comprehensive user preference analysis is achieved, but system complexity increases

Engineering Contradiction:

Improveuser preference analysis accuracyVSAvoidsystem architecture complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system segments its architecture into distinct functional modules: data collection modules (behavior tracking, feedback gathering), data processing modules (preprocessing, feature extraction), analysis modules (preference modeling, pattern recognition), and execution modules (advertisement selection, pushing). This segmentation allows each module to handle specific tasks independently, making the overall complex system more manageable, maintainable, and scalable while achieving comprehensive user preference analysis through coordinated module interactions.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS10686903B2Information push method and electronic device

Publication Date: 2020.06.16 BEIJING KINGSOFT INTERNET SECURITY SOFTWARE CO LTD

AI summary

Disclosed is an information push method and an electronic device. The method includes: acquiring a page view number of each piece of information in a predetermined information list for a predetermined period of time before a current time; selecting information from the predetermined information list according to the page view number, wherein the selected information is information not meeting a predetermined information displaying condition; acquiring an information recommendation degree of the selected information; determining information to be pushed from the selected information according to the information recommendation degree; and pushing the information to be pushed.