Nested Decision Tree Framework for Agent Action Ranking

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Determining and ranking recommended actions for enterprise tasks is challenging due to difficulties in communicating context-specific conditions, such as customer focus and historical data, which affects the relevance and efficiency of task completion.

Innovation Solution

Systems and methods that determine and rank recommended actions based on context-specific conditions, including customer attributes, calculated attributes, and business interests, while linking outcomes from executed actions to related actions to avoid redundant information entry.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If multiple recommended actions are generated and ranked for enterprise tasks, then task resolution efficiency is improved, but the complexity of determining and communicating context-specific conditions increases

Engineering Contradiction:

Improvetask resolution efficiencyVSAvoidcomplexity of determining and communicating context-specific conditions

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system segments the complex task of determining recommended actions into distinct components: context attribute identification, condition evaluation, action generation, and ranking. Each component processes specific aspects independently, making the overall system more manageable despite handling multiple context-specific conditions

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary ranking mechanism that mediates between multiple context-specific conditions and the final recommended actions. This intermediary layer evaluates and prioritizes actions based on weighted conditions, simplifying the communication between complex contextual factors and actionable recommendations

Inventive Principle:

Principle #24Intermediary (Mediator)

2Loss of time

If information is communicated between executed recommended actions and related recommended actions, then redundant information entry is reduced, but the complexity of linking outcomes increases

Engineering Contradiction:

Improvetime for redundant information entryVSAvoidcomplexity of linking outcomes

Core Design Contradiction:

Loss of timeVSDevice complexity

Solution Approach 1:

The system merges the information flow between executed actions and related actions by combining outcome data from completed tasks with the context of subsequent recommended actions. This merging allows automatic population of fields in related actions without requiring separate data entry, reducing redundancy while managing complexity through integrated processing

Inventive Principle:

Principle #5Merging (Combining)

Data Source

PatentUS20220230181A1Next best action framework with nested decision trees

Publication Date: 2022.07.21 SERVICENOW INC

AI summary

A system includes one or more client instances of a client hosted by a platform, in which the one or more client instances include an agent portal. The agent portal may receive a request from a customer related to a customer issue, determine a context for the customer issue based on one or more attributes, and determine a subset of actions as recommended actions based on factors to resolve the customer issue. The factors may include the context, historical data associated with the customer, and/or a client interest associated with the client. Moreover, the agent portal may rank the recommended actions as ranked recommended actions, display the ranked recommended actions for selection by the agent, and provide a guidance corresponding to a selected recommended action.