Sequential Answer Reports for Analytics Reasoning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional digital analytics systems are limited to generating a single answer to user inputs, failing to provide explanations of the logical path to the answer, which hides insights into the reasoning behind the generated responses.

Innovation Solution

A system that generates sequential supporting answer reports, processing user inputs through a machine learning model to create a visual representation of the analytics data, displaying a sequence of reports that illustrate the progression from initial supporting answers to the final answer, providing a clear explanation of the relationship between each supporting answer and the final answer.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If conventional digital analytics systems generate a single answer using machine learning models, then the answer generation speed is fast, but the explanation of the logical path and reasoning process is lost

Engineering Contradiction:
Improveloss of reasoning process informationVSAvoidsystem complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The system segments the answer generation process into multiple intermediate steps, each producing a supporting answer that contributes to the final answer. This segmentation allows the reasoning process to be broken down into visible, explainable components while maintaining the overall efficiency of the machine learning model.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary actions by generating supporting answers before arriving at the final answer. These supporting answers serve as intermediate reasoning steps that explain the logical path, allowing users to understand the derivation process without sacrificing the speed of the final answer generation.

Inventive Principle:
Principle #10Preliminary action

2Ease of operation

If conventional systems provide only a final answer, then the system operation is simple, but user understanding of the reasoning process is limited

Engineering Contradiction:
Improvesystem operation simplicityVSAvoidloss of logical path information
Core Design Contradiction:
Ease of operationVSLoss of information

Solution Approach 1:

The system introduces supporting answers as intermediary elements between the user's question and the final answer. These intermediaries provide a bridge that explains the reasoning process in human-understandable terms while maintaining the simplicity of the overall system operation.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system adds a temporal dimension to the answer presentation by showing a sequence of supporting answers that lead to the final answer. This dimensional expansion transforms a single static answer into a dynamic progression of reasoning steps, enhancing user understanding without complicating the core system operation.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

3Loss of information

If sequential supporting answer reports are generated to explain the logical path, then user understanding of reasoning improves, but the system complexity increases

Engineering Contradiction:
Improveinformation about reasoning processVSAvoidsystem complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The machine learning model is designed to serve multiple functions: it generates both the final answer and the supporting answers that explain the reasoning process. This multi-functionality allows the system to provide comprehensive information about the reasoning process without requiring separate complex systems for explanation generation.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system generates its own explanatory supporting answers automatically through the machine learning model, without requiring external tools or manual intervention. This self-service capability allows the system to provide detailed reasoning information while maintaining manageable system complexity.

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS11797161B2Systems for generating sequential supporting answer reports
Publication Date: 2023.10.24 ADOBE INC
  • US11797161B2 patent drawing
  • US11797161B2 patent drawing
  • US11797161B2 patent drawing

AI summary

In implementations of systems for generating sequential supporting answer reports, a computing device implements a report system to receive a user input defining a question with respect to a visual representation of analytics data rendered in a user interface. The report system determines a final answer to the question by processing a semantic representation of the question using a machine learning model. A sequence of reports is generated and the sequence defines an order of progression from a first supporting answer to the final answer. Each report of the sequence of reports includes a visual representation of a supporting answer to the question. The report system displays a dashboard in the user interface including a first report of the sequence of reports, the first report depicting a visual representation of the first supporting answer to the question.