The Knowledge Intelligence engine scans and analyses any articles, questions, videos, PDFs, Word documents (DOCX) and PowerPoint presentations (PPTX) created or added to Fuse. The knowledge Intelligence engine then extracts important information such key phrases, and entities such as organisations, dates, people, and locations. By gaining a deeper understanding of the content, Fuse is able to present you with the most relevant content possible when searching.
Fuse’s Knowledge Intelligence engine recognises keywords and phrases that exist inside an item of content. For example, an item of content might contain the phrase 'electric vehicle'. Even though this phrase contains two very distinct words, Fuse is able to recognise that they are being used jointly, as well as understands the context in which the phrase is being used. These key phrases are added as additional metadata to the original content item. This means if you search for 'Articles about electric vehicles', any available articles containing metadata for the phrase ‘electric vehicle’ will rank higher than other articles containing the separate words 'electric' and/or 'vehicle'.
Fuse is able to process the text within the content and extract entities. An entity is a piece of information that is present somewhere in the content body that matches predefined categories, such as a person, date, company or file type, which Fuse can transform into a tag. These tags are then used to help users find this content quickly in searches.
For example, a Word document might contain the following sentence: 'John Smith's company, ACME Corp, successfully designed and produced their first electric car in 2020'. Fuse might scan this sentence within the Word document and add the following tags to make it easier to find:
- 2020 (DateTime)
- John Smith (Person)
- ACME Corp (Organisation)
Fuse's Knowledge Intelligence engine recognises the following entities:
|Person||The name of a person. For example, John Smith.|
|PersonType||A person's job or role. For example, Admin.|
|Location||Landmarks, structures, geographical features, and geopolitical entities. This might be a city, town or region. For example, London.|
|Organisation||Companies, political organisations, music groups, sports clubs, government, and public organisations. For example, ACME Ltd.|
|Event||Cultural events, public holidays and sporting events.|
|Product||This might be a product that a company produces, such as software or computing products.|
|Address||The street address of a physical location, such as a house or office building. For example, 123 Carlton Avenue.|
|Phone number||A phone number.|
An email address. For example, firstname.lastname@example.org.
By default, we have toggled off the ability for our search engine to return users based on email addresses. This means that when you search using an email address, matching content is returned if that email address features in the body of the content, but any matching users with that email address are not.If you'd like to have this toggled back on, please contact your Customer Success Consultant (CSC).
|IPAddress||A network IP address.|
|URL||A web address. For example, www.bbc.co.uk.|
|DateTime||Dates and times. This includes calendar dates, date and time ranges, times of day, durations, and set and repeated times.|
|Quantity||This can be units of measurement and amounts. This includes percentages, ages, currency, temperatures, and dimensions.|