Method and system for assessing relevant properties of work contexts for use by information services

摘要

An information retrieval system for automatically retrieving information related to the context of an active task being manipulated by a user. The system observes the operation of the active task and user interactions, and utilizes predetermined criteria to generate context representation of the active task that are relevant to the context of the active task. The information retrieval system then processes the context representation to generate queries or search terms for conducting an information search. The information retrieval system determines the relevance of a word to the context by utilizing an adaptive weighting system. The information retrieval system assigns varying weights to different attributes of a word and calculates an accumulated weight of the word by accumulating all weights assigned to the word. The attributes may include word size, style, location of the word, etc. The system then ranks the importance of words based on their respective accumulated weight, and chooses words that rank within a predetermined number from the top to form search terms to conduct an information search using various data sources.

主权项

1. A method for obtaining representative text items from a plurality of text items in computer tasks, the method comprising:
receiving first information indicative of a first computer task, the first information including a first plurality of text items; determining a genre associated with the first computer task; determining first representative location information of the genre based on a first frequency of occurrence of identical text associated with the first representative location information in the genre; for each of the first plurality of text items, assigning a first weight with a first magnitude, the first magnitude being determined based on the genre and the first representative location information; ranking the first plurality of text items based on the first weight assigned to each of the first plurality of text items to produce a first plurality of ranked text items; generating and storing first representative text items based on the first plurality of ranked text items; wherein the first computer task is a task other than entering search terms for the purpose of retrieving information; receiving second information indicative of a second computer task, the second computer task being different than the first computer task, the second information including a second plurality of text items, wherein the second plurality of text items is different than the first plurality of text items; determining second representative location information of the genre based on a second frequency of occurrence of identical text associated with the second representative location information; for each of the second plurality of text items, assigning a second weight with a second magnitude that is determined based on the genre and the second representative location information, the second magnitude being different than the first magnitude; ranking the second plurality of text items based on the second weight assigned to each of the second plurality of text items to produce a second plurality of ranked text items; and generating and storing second representative text items based on the second plurality of ranked text items; wherein the second computer task is a task other than entering search terms for the purpose of retrieving information.