Hybrid NLP Gateway with Embedded Engine and Cloud Supplement

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Cloud-only natural language processing systems face connectivity issues when used to control gateway devices, while stand-alone implementations lack centralized upgrades and usage data collection.

Innovation Solution

A hybrid system that embeds a natural language processing engine in a gateway device, supplemented by a cloud service for processing unrecognized commands and extending capabilities without requiring firmware updates on the device, allowing for centralized upgrades and data collection.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a cloud-only natural language processing system is implemented, then centralized upgrades and usage data collection are enabled, but network connectivity is required which may be disrupted by configuration operations

Engineering Contradiction:

Improvecentralized upgrades and data collectionVSAvoidnetwork connectivity

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The natural language processing system is segmented into two parts: a cloud-based service for centralized management and updates, and a local embedded engine for autonomous operation. This segmentation allows the system to maintain centralized upgrade capabilities through the cloud portion while ensuring reliability through the local portion that can operate independently when network connectivity is unavailable.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The embedded natural language processing engine acts as an intermediary between the cloud service and the gateway device. It receives commands from the gateway, attempts local processing, and only communicates with the cloud service when necessary (for unrecognized commands or updates). This intermediary role allows the system to function with reduced dependency on continuous network connectivity while still enabling centralized upgrades.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If a stand-alone natural language processing system is implemented, then network connectivity is not required, but centralized upgrades and usage data collection are not possible

Engineering Contradiction:

Improveindependent operationVSAvoidcentralized upgrades and data collection

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The system merges the advantages of both cloud-based and stand-alone implementations by combining a local embedded natural language processing engine with a cloud service. The local engine provides independent operation without network connectivity, while the cloud service component enables centralized upgrades and usage data collection. The two components work together to achieve both reliability and adaptability.

Inventive Principle:

Principle #5Merging (Combining)

3Speed

If the embedded artificial intelligence engine processes all user commands locally, then response time is reduced, but command recognition accuracy decreases for complex or unrecognized commands

Engineering Contradiction:

Improveresponse timeVSAvoidcommand recognition accuracy

Core Design Contradiction:

SpeedVSMeasurement precision

Solution Approach 1:

The embedded artificial intelligence engine performs preliminary processing of user commands locally, attempting to recognize and execute common commands without network delay. When the local engine encounters unrecognized or complex commands, it then communicates with the cloud service for enhanced processing. This preliminary local action maintains fast response times for common commands while achieving high accuracy for complex commands through cloud assistance.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

Instead of attempting to process all command recognition locally (which would require excessive local computing resources), the system uses partial local processing for common commands and supplements with cloud-based processing for unrecognized commands. This partial action approach achieves high recognition accuracy without requiring the embedded engine to handle every possible command scenario alone.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentEP3158713B1Cloud service supplementing embedded natural language processing engine

Publication Date: 2021.05.26 INTERDIGITAL CE PATENT HOLDINGS SAS

Figure 1
Figure 2
Figure 3

AI summary

A system and method are provided. The system includes a gateway portion (201), embedded in a gateway device, having an embedded artificial intelligence engine (220) for processing commands using natural language processing. The system further includes a supplemental cloud server portion (202) having a supplemental artificial intelligence engine (280) for processing, using the natural language processing, the commands unable to be processed by the embedded artificial intelligence engine. The gateway portion (201) further includes a configuration and status interface (230) for performing at least one of diagnostic operations, configuration operations, and status operations, on the gateway device responsive to instructions from any of the embedded artificial intelligence engine and the supplemental artificial intelligence engine.