Parallel Computing Categorization for Real-Time Emergency Call Text
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing emergency call categorization systems rely on subjective human judgment, leading to inefficiencies, misclassification, and resource allocation issues, and face challenges with scalability, integration, advanced algorithms, and data security.
Innovation Solution
A computer-implemented method using parallel computing and machine learning models for real-time categorization, including sentiment analysis and classification, to objectively assess call severity and allocate resources efficiently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If human judgment is used for emergency call categorization, then subjectivity and flexibility are maintained, but efficiency and accuracy deteriorate
Solution Approach 1:
The patent replaces the mechanical human judgment system with an automated machine learning-based categorization system. The ML model processes call data and assigns categories automatically, eliminating the need for human dispatchers to manually assess each call's severity level, thereby significantly improving categorization efficiency and consistency.
Solution Approach 2:
The system enables self-service categorization where the machine learning model independently performs the categorization task without human intervention. The model uses trained algorithms to automatically analyze call characteristics and assign appropriate severity categories, allowing the system to serve itself rather than requiring human operators for each categorization decision.
2Measurement precision
If manual categorization is used, then flexibility in assessment is maintained, but measurement precision and reliability deteriorate
Solution Approach 1:
The patent substitutes manual assessment mechanisms with an automated machine learning model that provides precise and consistent categorization. The ML model processes call data through complex algorithms trained on historical patterns, achieving high measurement precision in severity assessment while the system architecture remains manageable through modular design.
Solution Approach 2:
The system incorporates feedback mechanisms where the machine learning model continuously learns from categorized call data and adjusts its algorithms to improve accuracy over time. This feedback loop enables the system to refine its categorization precision by analyzing past performance and adapting to evolving emergency call patterns.
3Speed
If real-time processing is implemented, then response time is improved, but computational resources and complexity increase
Solution Approach 1:
The patent applies preliminary action by pre-training the machine learning model on extensive historical emergency call data before actual use. This pre-training phase allows the model to quickly and accurately categorize new incoming calls in real-time without requiring complex computational resources during the actual categorization process, as the heavy lifting is done during the training phase.
Solution Approach 2:
The system segments the categorization process into distinct phases: data collection, model training, and real-time inference. By separating these phases, the patent enables real-time processing during the inference phase while managing computational complexity through the pre-computed training models, allowing fast response times without proportionally increasing operational computational complexity.
Data Source
AI summary
A computer-implemented method comprising: obtaining real-time text data relating to a matter, the text data comprising a plurality of portions of information; performing a categorisation process, wherein the categorisation process is configured to run a plurality of threads in parallel, wherein each thread of the plurality of threads acts on one portion of information at a time, wherein each thread performs the following steps: (i) obtaining a sentiment score based on the portion of information using a Sentiment Analysis machine learning, ML, model; (ii) assigning a category to the matter based on the sentiment score using a classification ML model trained on historical data; and (iii) updating a live category based on the category assigned to the matter; and finally, outputting the live category to a user in real-time.