|Home||Products & Services||Customers||Support||About Us||News & Events||Contact Us|
Frequently Asked Questions
What is InfoTame?
InfoTame is an ultra fast analytics engine based on superior software algorithms originally designed to filter the global database of a national intelligence service. Our software can help organizations suffering from information overload to extract hidden patterns, vital clues and significant facts from millions of documents in seconds.
Who created InfoTame?
InfoTame’s underlying technology was originally created for the KGB in the former Soviet Union as a highly efficient (and scalable) way to analyze vast amounts of textual information. Facing a tidal wave of global data, intelligence services are always seeking ever more efficient processing systems to replace the human operators who manually perform watch list scans. Such technology has, therefore, been in use for some years – although it has only recently become commercially available via InfoTame.
What does InfoTame do?
In one sentence: «InfoTame gives you answers to questions that you do not know how to ask.»
InfoTame enables you to extract useful and significant information from millions of text documents (emails, PDF documents, MS Word, web pages) in seconds.
Unlike key word searching, InfoTame can extract information based on its «significance». This is a completely different approach from software that finds words or concepts based on «frequency» or «relevancy».
The real value is that InfoTame gives you answers to questions you may not know how to ask. In addition to guiding you to «known unknowns» (like a search engine), InfoTame also allows you to drill down to «unknown unknowns» buried deep within mountains of documents. In other words, InfoTame helps you to locate both explicit and implicit information.
Conventional wisdom says that you cannot search for something if you don’t know what you are looking for. Now, with InfoTame, you can. InfoTame provides a unique capability that is not offered by any other software product.
How does it work?
InfoTame is a unique approach to extracting significant facts from large amounts of text using mathematics (rather than text-based linguistics).
The software has been designed using techniques from statistical physics, and uses 15 statistical significance parameters. In general terms, the software measures the distance in the 15 –dimensional significance space between the query and each word in the entire database of documents. We call this technique «Statistical Spectral Content Analysis».
Or to put it another way: InfoTame is to text what Excel® is to numbers. InfoTame applies statistical analysis to text like Excel applies statistics to numbers. As a result, InfoTame, within seconds, extracts meaning from millions of documents containing hundreds of millions of words, just like Excel makes sense of millions of numbers in large spreadsheets.
Why should I buy InfoTame?
The benefits of using InfoTame include:
Why should I believe you?
Don’t take our word for it. Contact us for a free demonstration.
An addition, here is what litigation experts have to say in support of our statements:
«Every litigator involved in Electronic Evidence Discovery should be using leading software solutions like those provided by InfoTame to achieve rapid insights into mountains of data.»
Browning E. Marean
«ITee Legal is a revolutionary product that changes the way lawyers approach discovery… ITee Legal may shorten the discovery process from months to days and reduces the overall expenses significantly.»
Who are InfoTame’s competitors?
We are currently unaware of any other commercial product which uses purely mathematical techniques derived from statistical physics to analyze text documents.
There are other text-mining products designed on rule-based taxonomies, expert rules and linguistics. However, they suffer from several disadvantages. First, such approaches will fail to spot important documents unless they contain pertinent phrases. InfoTame, on the other hand, is objective because it is based on mathematical principles which are free from inherent biases. So, for example, InfoTame can handle synonyms, misspellings, multi-spellings, aliases and coded information (e.g. «the thing», a837, project pepper etc.).
Second, semantic analysis methods are very slow and expensive – while neural networks are not scalable.
In fact, our technology complements existing content management tools used for unstructured data, case management tools and traditional search engines – adding a powerful layer of analytics which helps your organization extract the maximum information hidden in the mountains of text stored by these more common products.
So InfoTame is unique?
Yes. There is no other product that currently offers you all the following features:
How much does InfoTame cost?
The cost of a single-user or multi-user licence depends on the number and format of your documents which must be loaded into the InfoTame analytics engine.
We offer a variety of pricing options and flexible terms. Please contact us for further details.
How long does it take to set up InfoTame and get it running?
A typical installation will usually take one to four weeks, depending on the volume of data.
How easy is the software to use?
Unlike other software packages, InfoTame does not require you to learn additional complexity or force you to change your working style. InfoTame has developed an intuitive user interface, which masks enormous complexity behind the scenes.
Can I evaluate InfoTame on a trial basis?
Yes. Please contact us for further details.
How is InfoTame different from a search engine?
Unlike search engines, which simply return documents, InfoTame analyzes the documents. ITee returns an Information Portrait™, which distils the essence of millions of documents onto a single page, automatically guiding users to discover not only what they seek, but what they don"t know exists (and therefore cannot enter in the query line of any search engine). InfoTame enables users to uncover and understand hidden relationships between people, events, places, companies within minutes, from millions of documents, before they read a single page.
Is InfoTame scalable?
ITee is highly scalable. It works with thousands of documents and with many millions of documents. In fact, the more documents, the higher the Information Portrait quality. The algorithms used in ITee are highly efficient and runtime increases only slightly as the database size increases by an order of magnitude. InfoTame"s architecture is scalable to accommodate even the largest databases. ITee can be implemented on multiple servers to handle large-scale implementations as well as large flows of real-time feeds.
How is database access security addressed in InfoTame?
User set-up procedure allows the administrator to specify access to all or some of the available databases on a user by user basis.
Can InfoTame"s database be updated automatically?
Yes, update processes are automated. ITee is designed for dynamically changing environments.
How does InfoTame filter out miscellaneous and irrelevant information?
InfoTame is based on Statistical Spectral Content Analytics. It generates the statistical spectrum for the entire database and compares it with the spectrum of the search results. The spectrum for words like «a», «the», «of», etc., will be similar for both data sets. These words will therefore be eliminated as insignificant, without a single filter or a predefined set of «stop words».
Does InfoTame work with multiple languages?
InfoTame is based on mathematics and can work with any language, including 16-Bit character sets. Since ITee translates every word into a mathematical representation, mixed language queries are possible.
How do you know that the Information Portrait contains the most relevant terms?
InfoTame is based on Statistical Spectral Content Analytics, a mathematical algorithm which is objective and does not rely on an expert system or some preset linguistic rules (chosen by humans with biases).
Can InfoTame analyze a subset of documents based, for example, on their source?
InfoTame has an advanced query language option, which can perform complex queries. Not only can specific sources be selected, but many other parameters can be selected to shape the query as the user may desire.
Next-Generation Intelligent Search Engine
© 2001-09 INFOTAME® CORPORATION. ALL RIGHTS RESERVED