Generating search keyword suggestions from recently used application

Abstract

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.

What is claimed is: 
     
         1 . A method for providing search suggestions, the method comprising:
 capturing, by a computer, data from a first application, wherein the data includes data displayed on a screen by the first application, includes data on user behavior in the first application, includes characters a user selected in the first application, includes one or more locations the user clicked in the first application, and includes one or more locations the user's cursor was located in the first application;   segmenting, by the computer, the data from the first application into blocks;   extracting, by the computer, words from the data from the first application using natural language processing;   generating, by the computer, tokens of phrases and words using natural language processing tokenization;   retrieving, by the computer, stored significance data for the first application, wherein the stored significance data is stored on a remote computer, is aggregated from more than one user, includes prior determinations of blocks for the first application, includes significance values for blocks, and includes a number of times a block has resulted in a search by the user;   scoring, by the computer, the blocks based upon the data from the first application and upon the stored significance data;   scoring, by the computer, the tokens based upon the scoring of the blocks and the data from the first application;   detecting, by the computer, a switch action from the first application to a second application, wherein the second application contains a search function;   providing, by the computer, the scored tokens to the search function of the second application;   monitoring, by the computer, one or more search terms entered by the user into the search function of the second application; and   updating, by the computer, the stored significance data based upon the segmentation of the data from the first application into blocks and upon the search terms entered by the user into the search function of the second application.