Strojové učení potřebuje pro dosažení kvalitních výsledků data, velké množství dat. Proto vyvíjíme vlastní univerzální crawlery, prostřednictvím kterých potřebný obsah získáváme.
Máme prakticky vyřešené záležitosti typu omezování počtu přístupů prostřednictvím captcha kódů, měnící se struktury webů, či praktické problémy typu identifikace správných informací v textu. Například při stahování recenzí je často stejné zboží na jednotlivých eshopech označováno odlišně a pro agregaci dat je třeba identifikovat, že se jedná o tentýž výrobek.
-
Database Creation and Text Analysis in Services
event_note 10.01.2019 person admin2Our EQS software, based on the text analysis in services (e.g. “I am looking for a nursery in Brno which takes children as young as 1 year old”), will present the user with appropriate suppliers. To correctly pair the data, the search algorithm requires a sufficient amount of data for learning. We have approached this […]
-
Suitable representatives for a set of reviews
event_note 08.01.2019 person admin2As we mentioned in the previous post, our team is working on a project to help you make decisions about buying different products and services. We try to help users create an objective view of the specific items they want to buy by analyzing published reviews of other users. Currently, we’ve downloaded enough reports and product articles […]
-
We have downloaded over half a million user reviews
event_note 05.01.2019 person adminWe will inform you about the milestones we have achieved in analyzing text reviews. Let’s take a look at our research. Motivation Our team is currently working on a project to help make decisions about buying different products. A huge amount of opinions and reviews of individual products can be found on the Internet. These […]
-
Text analysis in field of business mediation
event_note 04.01.2019 person Ivan KvisPublic and private customers increase online spend every year. As new generations of buyers mature there are more and more demands for goods and services available online for suppliers. In Czech market there are approximately 20 portals that mediate demands with proper suppliers. Customers are promised to find qualified, relevant suppliers that have proper experience […]
-
The Reviews section launch!
event_note 03.01.2019 person Ivan KvisIn the introductory article of the Reviews section, we present the Multicriterial Text Analysis Software (MTA) project, which deals with the removal of information asymmetries in news and reviews. The MTA team of scientists from CYRRUS ADVISORY, a.s. and Mendel University in Brno uses machine learning methods to analyze text in the field of current […]