AI Resource Initialization for User Conversion

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Traditional campaigns for new user account initialization rely on standardized parameters, leading to inefficient and costly account initialization processes due to a lack of customization based on user and device attributes, resulting in low conversion rates and few long-term beneficial users.

Innovation Solution

A system that captures user and device attribute data to generate customized resource initialization data using machine learning techniques, including neural networks for user classification and resource optimization, to tailor offers and improve account initialization rates.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If standardized initialization parameters are used for all users, then the system complexity is reduced and ease of manufacture is improved, but the conversion rate of users initializing accounts decreases and productivity is worsened

Engineering Contradiction:

Improveease of generating initialization dataVSAvoidconversion rate of account initialization

Core Design Contradiction:

Ease of manufactureVSProductivity

Solution Approach 1:

The patent segments users into different categories based on their attributes, device characteristics, and behavior patterns. Instead of applying a single standardized initialization approach to all users, the system divides the user base into segments and applies customized initialization parameters to each segment, thereby improving conversion rates while maintaining manageable system complexity through automated classification.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent implements local quality by tailoring the initialization data to match specific user characteristics and device attributes. Rather than using uniform parameters globally, the system adjusts initialization parameters locally for each user or user segment based on their particular needs, device capabilities, and predicted behavior patterns, thus optimizing conversion rates without requiring complete customization for every individual user.

Inventive Principle:

Principle #3Local quality

2Productivity

If customized resource initialization data is generated for particular users using machine learning, then the conversion rate of users initializing accounts is improved, but the device complexity and computational resources required increase

Engineering Contradiction:

Improveconversion rate of account initializationVSAvoidcomplexity of processing and generating customized data

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent applies preliminary action by pre-training machine learning models offline using historical user data before deployment. The models are prepared in advance with learned patterns and relationships, so that during actual operation, the system can generate customized initialization data quickly by applying the pre-trained models to new user inputs, rather than performing complex training computations in real-time.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary layer of machine learning models that mediate between raw user input data and the final customized initialization parameters. These models serve as intermediaries that have already processed and extracted relevant patterns from historical data, allowing the system to generate personalized recommendations without directly implementing complex analytical logic in the main application flow.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Measurement precision

If user attribute, device function, and navigation data are captured and processed, then the accuracy of user classification and resource optimization is improved, but the quantity of data to be processed and stored increases

Engineering Contradiction:

Improveaccuracy of user classificationVSAvoidquantity of user and device data

Core Design Contradiction:

Measurement precisionVSQuantity of substance

Solution Approach 1:

The patent applies the extraction principle by selectively extracting only the most relevant features and attributes from the collected user data, device data, and navigation data. Rather than processing and storing all raw data, the system identifies and extracts key features that are most predictive of user behavior and account initialization likelihood, thereby maintaining high classification accuracy while reducing the volume of data that needs to be stored and processed.

Inventive Principle:

Principle #2Taking out (Extraction)

Data Source

PatentUS11991182B2Optimizing resource utilization

Publication Date: 2024.05.21 TRUIST BANK

AI summary

Disclosed are systems d methods for optimizing resource utilization by generating resource initialization data that is customized to particular users. The initialization data is customized and optimized based on user evaluation data that includes information about user attributes, functions, and user computing devices. The systems and methods utilize artificial intelligence (“AI”) systems to process data received from user devices, such as Internet navigation data, device configuration data, and user account data associated with users that have been authenticated. The AI systems process the user evaluation data to classify users by determining the probabilities that the users match predefined classifications. For users that meet predefined classifications, the AI systems determine probabilities that users will accept customized resource initialization parameters. The user acceptance probabilities are used to determine optimized resource initialization data and to generate graphical user interfaces that display optimized resource initialization data on a user computing device.