ML Expansion Recommendations for Natural Language Data Access

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Natural language data applications face inefficiencies in interpreting user requests due to ambiguity, leading to time-consuming and repetitive interrogation processes when accessing diverse data sources with different domain-specific languages.

Innovation Solution

A method utilizing machine learning algorithms to generate expansion recommendations, associating queries with hierarchical components and recommendation models, reducing the need for user disambiguation and improving the accuracy and efficiency of natural language processing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If natural language data applications use traditional interrogation processes to disambiguate user requests, then they can obtain precise information about user intent, but the process becomes time-consuming and repetitive

Engineering Contradiction:

Improveaccuracy of user intent interpretationVSAvoidtime required for disambiguation

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by proactively generating expansion recommendations based on hierarchical components before the user can provide additional disambiguation information. The ML model predicts what data or filters the user likely wants to expand based on the initial query and contextual hierarchy, preparing recommendations in advance that align with user intent without requiring time-consuming back-and-forth interrogation.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system serves itself by using the ML recommendation model to automatically interpret and expand upon user queries without requiring manual clarification. The hierarchical component structure enables the system to self-determine the most relevant expansions based on the query context, data source hierarchy, and predicted user intent, reducing reliance on traditional user-led disambiguation processes.

Inventive Principle:

Principle #25Self-service

2Reliability

If natural language data applications request detailed disambiguating information from users, then they can accurately retrieve the intended data, but user effort and complexity increase

Engineering Contradiction:

Improveaccuracy of data retrievalVSAvoiduser effort required

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The ML recommendation model acts as an intermediary between the user's natural language query and the data retrieval system. Instead of requiring users to directly specify all disambiguation details, the model translates the query into hierarchical expansion recommendations that bridge the gap between ambiguous user intent and precise data retrieval requirements, maintaining accuracy while reducing user effort.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system performs self-service by automatically interpreting the natural language query and generating appropriate expansion recommendations based on the hierarchical data structure. The system determines what additional information or filters are needed without requiring users to manually provide detailed disambiguation, thereby maintaining reliable data retrieval while significantly reducing operational complexity for users.

Inventive Principle:

Principle #25Self-service

3Stability of the object's composition

If natural language applications repeat disambiguation processes for similar queries, then they maintain consistency in information gathering, but efficiency decreases

Engineering Contradiction:

Improveconsistency of information gatheringVSAvoidprocessing efficiency

Core Design Contradiction:

Stability of the object's compositionVSProductivity

Solution Approach 1:

The system implements feedback by analyzing user responses to expansion recommendations and using this information to refine future recommendations. The ML model learns from user interactions and adjusts its prediction of user intent based on patterns observed in how users respond to expansion suggestions, maintaining consistency in information gathering while improving efficiency through adaptive learning rather than repeating the same disambiguation processes.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system performs preliminary actions by pre-generating expansion recommendations based on hierarchical components before users submit follow-up queries. This preliminary structuring of potential expansions based on the data hierarchy allows the system to maintain consistent information gathering approaches while avoiding repetitive disambiguation by having recommendations ready in advance based on query patterns and user behavior.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11170016B2Navigating hierarchical components based on an expansion recommendation machine learning model

Publication Date: 2021.11.09 CISCO TECHNOLOGY INC

AI summary

A natural language (NL) application implements functionality that enables users to more effectively access various data storage systems based on NL requests. The operations of the NL application are guided by, at least in part, on one or more templates and/or machine-learning models. Advantageously, the templates and/or machine-learning models provide a flexible framework that may be readily tailored to reduce the amount of time and user effort associated with processing NL requests and to increase the overall accuracy of NL application implementations.