Can a KM system anticipate a user’s information needs? How useful would it be to have perpetual, proactive presentation in real-time of potentially relevant documents, data and messages in the context of a given project and in the context of a given application?
Here are some notes on what has been called “just-in-time information retrieval” and “implicit query.”
One of the features of Vannevar Bush’s Memex, the PKM device proposed in the article “As We May Think” (1945) was a concept called “associative indexing, the basic idea of which is a provision whereby any item may be caused at will to select immediately and automatically another.”
The real heart of the matter of selection, however, goes deeper than a lag in the adoption of mechanisms by libraries, or a lack of development of devices for their use. Our ineptitude in getting at the record is largely caused by the artificiality of systems of indexing. When data of any sort are placed in storage, they are filed alphabetically or numerically, and information is found (when it is) by tracing it down from subclass to subclass. It can be in only one place, unless duplicates are used; one has to have rules as to which path will locate it, and the rules are cumbersome. Having found one item, moreover, one has to emerge from the system and re-enter on a new path.
The human mind does not work that way. It operates by association. With one item in its grasp, it snaps instantly to the next that is suggested by the association of thoughts, in accordance with some intricate web of trails carried by the cells of the brain. It has other characteristics, of course; trails that are not frequently followed are prone to fade, items are not fully permanent, memory is transitory. Yet the speed of action, the intricacy of trails, the detail of mental pictures, is awe-inspiring beyond all else in nature.
Man cannot hope fully to duplicate this mental process artificially, but he certainly ought to be able to learn from it. In minor ways he may even improve, for his records have relative permanency. The first idea, however, to be drawn from the analogy concerns selection. Selection by association, rather than indexing, may yet be mechanized. One cannot hope thus to equal the speed and flexibility with which the mind follows an associative trail, but it should be possible to beat the mind decisively in regard to the permanence and clarity of the items resurrected from storage.
Search technology has actually made a lot of progress toward achieving this mechanization in the 59 years since then. In fact, knowledge workers can use their modern Memex equivalents to extend their searches to our collective organizational and planetary memories, not just their own.
Future attempts at Associative Linking
MIT Technology Review (July/August 2004) picked up on the imminent release of "Dashboard," developed as an open-source project by Nat Friedman.
These days, finding information on the Web can be easier than finding it on your computer’s hard drive. But Nat Friedman, a software engineer and open-source-programming guru in
Friedman's Dashboard site, which includes interesting screenshots, describes the project thusly:
The goal of the dashboard is to automatically show a user useful files and other objects as he goes about his day. While you read email, browse the web, write a document, or talk to your friends on IM, the dashboard does its best to proactively find objects that are relevant to your current activity, and to display them in a friendly way, saving you from digging around through your stuff like a disorganized filing clerk.
For example, if a friend IMs you and says "I can't wait for our camping trip this weekend!" the dashboard will show things like your recent emails about the camping trip, your camping bookmarks, and any files or notes you've got on your hard drive about camping.
Friedman also points to a CNET story about similar functionality under development at Microsoft for the future "Longhorn" version of Windows. Microsoft call this ideas "implicit query." As explained in "Microsoft aims for search on its own terms,"[1]
Implicit Query, an experimental application that was put together a few weeks ago, for example, retrieves links, music files, e-mails and other materials that relate to applications running in the foreground, according to the company.
"We analyze whatever text you are working on and then pull out words that are important and query on those automatically," said Susan Dumais, a senior researcher in the Adaptive Systems and Interactive Group at Microsoft Research. "The idea is to retrieve a bunch of things without you explicitly searching for them."
Microsoft is also looking at integrating these tools directly into operating systems and applications. "I don't want to stop everything I am doing. Bring the search results to me," Dumais said. "People spent a lot of time essentially acting as a file clerk."
Previous attempts at Associative Linking
PKM fans may remember Kenjin, the short-lived personal version of Autonomy's Active Knowledge technology that would present links to internal and external sources for material based on the content of the currently open application window on a user's desktop. As described in Time magazine:
Once installed on your PC Kenjin, which means "wise man" in Japanese and operates as a window at the bottom of your screen, watches and understands what you do and automatically suggests links to related websites and other files on your hard drive. Kenjin not only analyzes the documents on your screen, but also extracts concepts from the text and determines which ideas are the most important. The software then identifies similar concepts and ideas in other sources. So rather than having to stop what you're doing to roam the Net in search of more information, Kenjin (which can be downloaded free of charge at www.kenjin.com) analyzes what you need and brings the information to you.
For example, let's say I'm writing an article about Leonardo--the inventor, painter, poet and practitioner of mirror writing, not the boyish movie star. As I work on my PC, Kenjin is out scanning the Web for relevant links, e-mails and documents about Da Vinci, which then automatically appear on my screen ranked in order of relevance. Because Kenjin understands what I'm working on rather than simply identifying an ambiguous keyword, it sends lots of stuff about Da Vinci and nothing at all about DiCaprio. All I have to do is write. Over time, Kenjin gradually learns about the subjects that interest me and uses this knowledge to further refine and personalize the information it offers.[2]
Kenjin was sort of a free sample to promote Active Knowledge. Autonomy dropped Kenjin some time ago. By now, Autonomy doesn’t seem to use the label “Active Knowledge” any more either, though the concept of proactive search and delivery is still integral to its offerings. It’s hard to tell what’s going on because, against all reason, Autonomy has no search function on it’s website!
It should be noted that there are already a host of desktop PKM applications that can execute searches on hundreds of types of document and data on local drives, such as Enfish, X-1, and many others. Though not as automated or integrated, some of these tools executed very sophisticated queries.
Susan Dumais
A Google search on “Implicit Query” brings up a number of hits, many of them related to Susan Dumais, a Senior Researcher in the Adaptive Systems & Interaction Group at Microsoft Research. (She has also worked with W. P. Jones and H. Bruce at the
In a 1999 IEEE presentation, she contrasts explicit and implicit query this way:
Explicit queries:
--Search is a separate, discrete task
--Results not well integrated into larger task context
Implicit queries:
--Search as part of normal information flow
--Ongoing query formulation based on user activities
--Non-intrusive results display
[1] "Microsoft aims for search on its own terms" by Michael Kanellos CNET News Nov. 24, 2003.
[2] “Smart Stuff: Two new technologies to ease information overload” By James Geary, Time Europe Mar. 31, 2000. See also “Search the Web Without Searching: Kenjin analyzes your documents and finds what you need on the Web, with surprising accuracy.” by Chris Yurko. PC World February 11, 2000.
Recent Comments