Risk Relationship Workflow Customization Using Incremental Cloud Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing user interface workflows for risk relationship customer information collection are not optimized for individual users, leading to inefficiencies and suboptimal interactions, particularly in digital environments.
Innovation Solution
A system utilizing a back-end application computer server that processes user parameters, third-party data, and cloud data through a machine learning algorithm to dynamically customize user interface workflows, enabling real-time adjustments and optimizations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a generic user interface workflow is used for all customers, then the system complexity is reduced and ease of operation is improved, but the adaptability to individual user needs deteriorates
Solution Approach 1:
The system dynamically adjusts the user interface workflow based on real-time analysis of user parameters, third-party data, and cloud data. The machine learning algorithm continuously optimizes the workflow sequence, questions asked, and interaction flow to match individual user characteristics and needs, transforming a static generic workflow into a dynamic adaptive one.
Solution Approach 2:
The system performs self-customization by automatically analyzing user parameters and accessing third-party data to generate personalized workflows without requiring manual configuration. The machine learning algorithm autonomously determines the optimal workflow sequence based on the analyzed data, enabling the system to serve itself in the customization process.
2Adaptability or versatility
If manual customization of user interface workflows is performed, then the adaptability to individual users is improved, but the productivity and time required for customization deteriorates
Solution Approach 1:
The patent replaces manual mechanical customization processes with an automated machine learning system. The algorithm processes user parameters, accesses third-party data, and generates optimized workflows automatically, eliminating the need for manual intervention in the customization process and dramatically improving speed while maintaining or enhancing accuracy.
Solution Approach 2:
The system changes the parameters of the workflow dynamically based on analyzed user data. The machine learning algorithm adjusts the sequence of questions, interaction flow, and workflow steps according to the specific user parameters and third-party data, enabling precise customization at scale without manual effort.
3Measurement precision
If more data about users is collected to improve customization, then the adaptability and accuracy of workflow customization is improved, but the loss of time for data collection and processing deteriorates
Solution Approach 1:
The system performs preliminary data collection and analysis by accessing third-party data sources and retrieving relevant information before the workflow customization is needed. This pre-processing of data allows the machine learning algorithm to generate accurate customizations more quickly, reducing the overall time required while maintaining high measurement precision.
Solution Approach 2:
The patent introduces third-party data sources as intermediaries that provide pre-processed user information. Instead of collecting all necessary data directly from users, the system uses these intermediary data sources to supplement and enhance user parameter collection, reducing the time required for data gathering while improving the accuracy of customization.
Data Source
AI summary
A computer server receives, from a remote user device, information about a new potential risk relationship customer (including at least one new user parameter). Based on the new user parameter, the computer server accesses third-party data and utilizes a stored procedure to read data about the new potential risk relationship customer from an internal table of cloud data. The data read from the internal table is processed to dynamically evolve a schema and create an incremental view of cloud data. The computer server uses the incremental view to read and output a current batch of cloud data. A user interface workflow is then customized via a machine learning algorithm that processes the information about the new potential risk relationship customer, the third-party data, and the current batch of cloud data. A user information data store can then be updated based on information collected via user interface displays.