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

Abstract

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.

Description

FIELD OF THE DISCLOSURE [0001] The present disclosure generally relates to automatic method and system for forming queries to retrieve information, and more specifically, to method and system to automatically generate keywords, phrases and other entities representing the content and / or context of an active task being manipulated by a user and to retrieve information based on the representation. The representation of work context may be used to support a variety of information services. BACKGROUND OF THE DISCLOSURE [0002] Information retrieval systems, such as databases or search engines, allow users to retrieve information related to a specific subject by using one or more keywords that may be related to the specific subject. For example, a legal search service called Lexis® provided by the LexisNexis Group is widely used in the legal field to search for cases, journal articles, treaties, as well as other publications that are related to a specific topic or issue. Another informatio...

AI Technical Summary

Benefits of technology

[0023] In another aspect, the information retrieval system determines the relevance of a word, phrase, symbol, other entities, etc. to the context of an active task being manipulated by the user by utilizing an adaptive weighting system. The information retrieval system assigns varying weight to different attributes of a word or text, and calculates an accumulated weight of the word or text by accumulating all weights assigned to the word or text. The attributes may include word size, style, location of the word, etc. A text appearing in a normal style may have its weight incremented by a tunable parameter p1, and a text occurring as emphasized form may have its weight incremented by a tunable parameter p2, wherein p1 and p2 are different weights. The system may assign a heavier weight to a text that appears in a specific portion of the document, in an active window visible to the user, or in a portion selected by the user. The system may increase the weight of a word or text highlighted by the user. The system may also increase the weight of a word or text that is displayed in an emphasized form, such as bold, italic, larger fonts, and the like.

Problems solved by technology

This type of information retrieval system poses problems to users because the users need to be familiar with the proper format for inputting queries into such systems.

Although these tools provide basic assistance on query formation during information search and retrieval, such tools cannot function effectively in more realistic work environments in which the content of the query of question plays a paramount role.

These scenarios illustrate various problems associated with conventional information retrieval systems.

The first problem is that conventional information retrieval systems do not consider relevance of active goals in searching for information.

Typically, these goals are not fully expressed by users in forming their queries when using conventional information retrieval systems.

The second problem is that conventional information retrieval systems are subject to word-sense ambiguity.

The third problem is that conventional information retrieval systems fail to consider audience appropriateness when searching and retrieving information based on keywords or queries provided by the user.

Moreover, when using conventional information retrieval systems, users often are unable to provide sufficient information in their queries.

Needless to say, a two-word query most likely does not contain enough information to discern the active goals of the user, or even the appropriate senses of the words in the query.

Images