Cognitive Automation Platform for Unauthorized Event Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Large enterprises face challenges in verifying the authenticity of numerous requests for products or services, especially when received electronically, due to the difficulty in determining user sincerity and authenticity.
Innovation Solution
Implementing cognitive automation techniques to analyze requests for potential unauthorized activity by using models that analyze keywords, typing patterns, tone, and historical data, and generate additional authentication information requests to confirm the legitimacy of the requests.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional manual verification methods are used to determine user authenticity, then the process is simple and straightforward, but the accuracy and efficiency of detecting unauthorized requests deteriorate due to the large volume of electronic requests
Solution Approach 1:
The patent replaces manual verification mechanisms with cognitive automation systems that use machine learning models to analyze request patterns, user behavior, and authentication data. This substitution enables automated processing of large volumes of requests while maintaining or improving detection accuracy through advanced pattern recognition capabilities that exceed human analytical capacity.
Solution Approach 2:
The patent introduces cognitive automation models as intermediary systems between request submission and verification outcomes. These models act as mediators that process requests through multiple analysis layers including pattern recognition, behavioral assessment, and risk evaluation, thereby improving detection accuracy without requiring proportional increases in manual review capacity.
2Measurement precision
If cognitive automation models analyze multiple data points including keywords, typing patterns, and historical behavior, then the accuracy of unauthorized event detection improves, but the complexity of the detection system increases
Solution Approach 1:
The patent segments the detection system into distinct modular components: keyword analysis modules, typing pattern recognition modules, historical behavior analysis modules, and synthesis modules. Each component processes specific data types independently and contributes to the overall assessment, allowing the system to handle multiple data dimensions while maintaining manageable complexity through modular architecture.
Solution Approach 2:
The cognitive automation models are designed as multi-functional systems that simultaneously perform pattern recognition, behavioral analysis, risk assessment, and decision support across diverse request types and authentication scenarios. This universal approach allows a single system architecture to handle varied verification needs without requiring separate specialized systems for each function.
3Measurement precision
If additional authentication information is requested to verify request legitimacy, then the accuracy of authorization determination improves, but the time required for processing requests increases
Solution Approach 1:
The patent implements preliminary analysis of request patterns, user behavior, and authentication data before formal verification proceedings. The cognitive automation models pre-assess risk levels and identify high-confidence requests that can be approved quickly, while only flagging uncertain cases for additional authentication steps. This preliminary sorting reduces the need for time-consuming additional verification on low-risk requests.
Solution Approach 2:
The system applies additional authentication requirements selectively rather than universally. Cognitive automation models evaluate each request individually and impose additional verification steps only when the risk assessment indicates necessity. This partial application of excessive verification measures maintains security for high-risk requests while minimizing processing delays for low-risk requests that don't require extensive validation.
Data Source
AI summary
Systems for using cognitive automation techniques to detect unauthorized events are provided. In some examples, a request for a product or service (e.g., event processing) may be received. The request may be received electronically, via a telephone communication, in person, or the like. The request may be analyzed (e.g., using a cognitive automation model) to determine whether it is potentially unauthorized. If so, one or more requests for additional information may be generated or identified. For instance, requests for authentication information, responses to questions or a series of questions, or the like, may be generated. In some examples, the additional information requested may be identified using the cognitive automation model. Responses to the request for additional information may be analyzed (e.g., using the cognitive automation model) to determine whether the request for the product or service is unauthorized. If so, processing the request may be prevented.