AI Concept Resolution

Entity Resolution

Datasets can contain multiple records that refer to the same real-world thing even if they may use different names or pseudonyms. They may contain multiple different entities which happen to have the same name. You need to know which is which.

By including entity resolution in your data solution, it is possible to answer questions like: Which John Smith is my customer? Are these two news articles talking about the same real-world event?

Concept Resolution

Besides allowing you to identify and disambiguate entities within a dataset, concept resolution also matches concepts such as topics, events, diseases, or other concepts found in your data.

Concept resolution allows you to group similar concepts together for easier analysis. Some examples include:

Matching events so you don't have to read 20 headlines before realising they are talking about the same thing.
Matching mentions of a product so you can keep track of updates and .

Key Advantages

Improved data quality: By accurately matching and merging data, concept resolution improves the overall quality of your data assets.
Enhanced data analysis: Uncover valuable insights and make better decisions by improving your data's accuracy and integrating external or unstructured data sources.
Increased efficiency: Automatically identify and merge duplicate entities or concepts, reducing the need for manual data cleansing and reconciliation.