Local Classification Server

If you have large amounts of data that needs to be classified you may want your own local classification server software. This will improve performance by cutting the cost of having to send data over Internet to our web api. Another advantage is that you have full control over the server. Maybe run your entire database and tag entries with their
  • sentiment and mood?
  • category?
  • filter out spam?
With your own server license you can still create your own classifiers and be able to run large amounts of data through them - locally on your computer.

Licensing & Pricing

Evaluation
Indie
Professional
Enterprise
Price
Free
€99/year
€1999/year
€5999/year
Installation
For evaluation
1 computer
1 computer
4 computers
Support
No guarantee
Getting started
Getting started
Getting started + 1 month
Upgrades
No guarantee
Yes, minor (1.xx)
Yes, minor (1.xx)
Yes, minor (1.xx)
Attribution required
Yes
Yes
No
No
Download/Buy

Evaluation license

We are providing a server for evaluation purposes that can be run locally, making sure that it fullfills users needs. The evaluation server is not allowed in producation environments and is solely for testing. It needs to be restarted for every 5000 requests. See full evaluation license (pdf).
Download the latest version.

Indie license

For single developers and smaller companies (<€100.000 in revenue per year) we offer a 1 year time limited indie license. Once you have purchased the license you will receive an e-mail with a signed license file, this may take up to 24 hours. Attribution to uClassify is required where used or where derivate work is used (reports, articles, web sites etc). See full indie license (pdf).

Professional license

Once you have purchased the license you will receive an e-mail with a signed license file, this may take up to 24 hours. See full professional license (pdf).

Enterprise license

Please contact us for an invoice. See full enterprise license (pdf).

Other license?

We will add more licenses when we get requests, so if you are looking for something that is not listed contact us and I am sure we can figure something out! We are flexible!

Server Specification

  • Runs as a Windows service
  • Communicates with XML over sockets
  • Multi purpose
  • Highly accurate
  • Low on memory
  • Very fast
  • Parallel request handling
  • Robust
  • Transactional behavior
  • Probabilities [0-1] in the result
Have a look in the manual to find out how it's installed and communicated with.

Architecture

The classification server runs as a Microsoft Windows service driven by XML calls over sockets (which makes it easy to integrate with other Operating Systems). Responses are also returned in XML. The API is very similar to that of our free web API.

Flexibility

The classifier has no limitations in terms of what it can classify, it can be used for spam classification, sentiment, web page categorizing etc. There is no limit of how many classes a classifier can have. Classifiers are thread safe (Readers/Writers lock) so classes and new training data can be added dynamically.

Low on resources

The server is designed to handle huge amounts of data without compromising the accuracy. It's able to keep many huge classifiers in memory simultaneously and respond quickly to classifications.

To give you an idea of how fast it's we recently ran a test on a modern PC, batching blog posts (average 2.4kb) through 5 large classifiers. The throughput was +100 posts/second (including the communication). That is 360000 posts/hour! On one core.

Also, it handles multiple requests in parallel, this is very nice if you have multiple cores!

Stability

We spent a lot of time to get it really robust, making sure that it won't crash or misbehave under any circumstances. Even though the host machine runs out of memory (and has no page file) it will survive, giving proper error messages.

It uses transactional behavior to ensure that classifiers are not left in an undefined state if a write operation unexpectedly fails. For example if the server runs out of memory while training a class, the training is reverted and an error message is returned.

About the classifier

The core is a Naive Bayesian classifier with a couple of steps that improves the classification further. The result of classifications are probabilities [0-1] of a document belonging to each class. Many other models can only answer Yes or No - not to what degree. This is very useful if you want to set a threshold for classifications. E.g. all classifications over 90% is considered spam. Using this model also makes it very scalable in terms of CPU time for classification/training.

Contact us

Feel free to contact us and ask any questions!