Remote Natural Language Command Processing for Client Apps

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional natural language processing systems require updating client applications to recognize new natural language commands, which is inefficient and limits the ability to add new functionality without modifying the client application binary.

Innovation Solution

A client device generates natural language data from user inputs and communicates it to a service provider system for processing, where the system converts and recognizes the commands, generating executable code that is then sent back to the client device to execute blindly, decoupling processing from the client device and allowing updates without modifying the client application.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If natural language processing is embedded in the client application, then the system can recognize and execute natural language commands locally, but the client application must be updated to add new functionality or recognize new commands

Engineering Contradiction:
Improveability to recognize new natural language commandsVSAvoidclient application update requirements
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent extracts the natural language processing functionality from the client application and relocates it to a remote server. The client application now only needs to communicate natural language commands to the server, which handles the complex processing and returns executable code. This extraction eliminates the need to update the client application binary when adding new commands or functionality.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent introduces a remote server as an intermediary between the user's natural language input and the client application execution. The server acts as a mediator that receives natural language commands, processes them through NLP techniques, generates appropriate executable code, and sends it back to the client. This intermediary handles all complexity of language understanding and command generation.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Speed

If natural language processing is performed on the client device, then processing speed may be faster, but memory and processing resources are consumed locally

Engineering Contradiction:
Improvecommand processing speedVSAvoidclient device processing resources
Core Design Contradiction:
SpeedVSUse of energy by moving object

Solution Approach 1:

The patent extracts the computationally intensive natural language processing tasks from the client device and relocates them to a remote server with greater processing power. The client device only performs lightweight operations of capturing input and executing returned code, significantly reducing local resource consumption while maintaining acceptable response times through efficient communication.

Inventive Principle:
Principle #2Taking out (Extraction)

3Ease of operation

If the client application contains built-in natural language recognition, then it can process commands independently, but it requires modification to support new functionality

Engineering Contradiction:
Improveindependent command processingVSAvoidnew functionality addition
Core Design Contradiction:
Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent extracts the natural language recognition and processing capabilities from the client application, leaving the client with only the essential function of capturing user input and executing returned code. This extraction enables the system to add new functionality by simply updating the server-side processing logic, without requiring any modification to the client application binary.

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentUS11163377B2Remote generation of executable code for a client application based on natural language commands captured at a client device
Publication Date: 2021.11.02 ADOBE INC
  • US11163377B2 patent drawing
  • US11163377B2 patent drawing
  • US11163377B2 patent drawing

AI summary

Remote generation of executable code for a client application based on natural language commands captured at a client device are described. A natural language command is received at a client device, and natural language data is generated and communicated to a remote service provider system. The service provider system processes the natural language data using natural language processing techniques to recognize one or more actions of the natural language command, and generates executable code to perform the one or more actions of the natural language command by the client application. The executable code is then communicated back to the client device over a network to cause the client application to blindly execute the executable code to perform the one or more actions of the natural language command.