Predictive Model for Database Field Value Recommendations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for filling out forms on computer systems require manual effort and are inefficient in capturing information, especially when dealing with unstructured data like conversational records, which can lead to lengthy processing times and inaccuracies in case management.
Innovation Solution
A predictive model is trained using historical data to predict field values in forms based on confidence levels, utilizing conversational data from sources like emails, chat messages, and web feeds, converting textual data into numerical representations using encoder models and summarization/classification models to automate field value recommendations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual methods are used to fill out forms and capture information, then accuracy can be maintained through human review, but productivity is reduced due to lengthy processing times and manual workload
Solution Approach 1:
The system performs preliminary analysis of conversational data and pre-populates form fields with predicted values before the user needs to complete the form. The predictive model is trained in advance on historical data, and during case management, it automatically generates recommendations that are ready for user review, eliminating the need for manual data extraction and entry during the time-critical case resolution process
Solution Approach 2:
The system enables self-service by allowing the predictive model to automatically analyze conversational data and populate form fields without requiring manual human intervention for each data entry task. The model serves itself by continuously learning from historical data and improving its predictions, reducing the need for human reviewers while maintaining high accuracy through confidence score thresholds
2Productivity
If automated predictive models are used to generate field values, then productivity increases and processing time decreases, but reliability may be reduced due to potential prediction inaccuracies
Solution Approach 1:
The system implements feedback mechanisms where user corrections of predicted values are fed back into the training data, allowing the model to continuously learn from mistakes and improve accuracy. The confidence score system provides feedback to users about the reliability of predictions, enabling them to make informed decisions about whether to accept or review predicted values
Solution Approach 2:
The system dynamically adjusts the confidence threshold parameter based on the specific field being predicted and the current state of the model's performance. For critical fields with higher stakes, the system requires higher confidence thresholds, while for less critical fields, lower thresholds are acceptable. This parameter adjustment balances productivity and reliability on a per-field basis
3Measurement precision
If complex machine learning models are implemented to process conversational data, then measurement precision of field values improves, but device complexity increases
Solution Approach 1:
The system segments the complex task of form population into separate predictive models for each field or group of related fields. Each model is trained on specific historical data relevant to its target field, making the overall system more manageable. The segmentation also allows different confidence thresholds and validation rules to be applied to different field types, reducing the complexity of error handling
Data Source
AI summary
Computing systems, database systems, and related methods are provided for recommending values for fields of database objects and dynamically updating a recommended value for a field of a database record in response to updated auxiliary data associated with the database record. One method involves obtaining associated conversational data, segmenting the conversational data, converting each respective segment of conversational data into a numerical representation, generating a combined numerical representation of the conversational data based on the sequence of numerical representations using an aggregation model, generating the recommended value based on the combined numerical representation of the conversational data using a prediction model associated with the field, and autopopulating the field of the case database object with the recommended value.