Cross-Application Search Suggestion Engine Using Contextual Token Scoring

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current search methods require users to manually enter search terms across different applications, which is inefficient and often results in irrelevant search suggestions, as existing search suggestions do not relate to the user's current application usage.

Innovation Solution

A method and system that capture data from a user's current application, segment it into blocks, extract words using natural language processing, score tokens based on user behavior and significance, and provide these scored tokens as search suggestions to a search function in a destination application, eliminating the need for manual input and improving relevance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If users manually enter search terms in a different program, then search functionality is achieved, but time efficiency deteriorates and user convenience worsens

Engineering Contradiction:

Improvesearch efficiencyVSAvoidtime spent on manual search input

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by capturing and processing data from the source application in advance, generating search suggestions before the user actually needs to search. This includes segmenting the display into blocks, extracting words, generating tokens, and scoring them based on user behavior patterns, so that when the user switches to the destination application, ready-to-use suggestions are immediately available.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system introduces an intermediary component that acts as a bridge between the source application and the destination application. This intermediary captures data from the source application, processes it through NLP tokenization and scoring mechanisms, and automatically provides processed search suggestions to the destination application's search function, eliminating the need for direct manual user intervention.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If users manually copy and paste search terms between applications, then search accuracy is maintained, but operational complexity increases

Engineering Contradiction:

Improvesearch term accuracyVSAvoidease of search process

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The system enables self-service by automatically performing the search term extraction and suggestion generation without requiring user intervention. The source application's display data is automatically captured, segmented into blocks, processed through NLP tokenization, and scored based on user behavior patterns, with suggestions automatically provided to the destination application's search function.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system replaces the mechanical manual process of copying and pasting search terms with an automated computational system. Instead of users manually selecting, copying, and pasting text between applications, the system uses automated data capture, NLP processing, and intelligent suggestion generation to accomplish the same goal more efficiently and accurately.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Adaptability or versatility

If existing search suggestions are provided without context, then search function is available, but suggestion relevance deteriorates

Engineering Contradiction:

Improvesearch suggestion availabilityVSAvoidcontextual relevance of suggestions

Core Design Contradiction:

Adaptability or versatilityVSLoss of information

Solution Approach 1:

The system applies local quality by providing different search suggestions based on the specific context of each source application and user behavior. Instead of generic search suggestions, the system segments the source application display into specific blocks, extracts words relevant to each block, generates tokens, and scores them based on user interaction patterns with that particular application, ensuring contextually relevant suggestions for each situation.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system implements feedback mechanisms by monitoring user behavior patterns within the source application and using this information to refine and score search suggestions. The system captures how users interact with the source application, processes this behavioral data through the tokenization and scoring system, and uses the feedback to provide more accurate and relevant search suggestions in the destination application.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS10585923B2Generating search keyword suggestions from recently used application

Publication Date: 2020.03.10 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

A computer provides search suggestions by capturing data from a first application, wherein the data includes data displayed on a screen by the first application. The computer segments the data from the first application into blocks. The computer extracts words from the data from the first application. The computer generates tokens of phrases and words using natural language processing tokenization. The computer scores the blocks based upon the data from the first application. The computer scores the tokens based upon the scoring of the blocks and the data from the first application. The computer detects a switch action from the first application to a second application, wherein the second application contains a search function. The computer provides the scored tokens to the search function of the second application.