Driving powerful search with knowledge graphs
Search should be about getting people to complete their mission. Search has evolved just as consumers have in their quest for ease of use. As technology has evolved, so has the search to help people achieve more and more complex tasks. Today consumer expectations are such that search is not limited to just text but also in more advanced formats such as voice, AR/VR, or chatbots.
Evolution of search
Roadmap of search maturity:
- Basic keyword search allows quick access to large amounts of data.
- Full-text search
- Faceted search
- Asset-oriented or action-oriented search
- Knowledge graph-based search
Basic keyword search
A keyword search as the name suggests looks for words anywhere in the record. Keywords may also substitute for a title or author search when you have an incomplete title or author information.
In the case of keyword searches and metadata searches, an organization must assign specific information to each artefact that will be used to locate information for a particular use. Many of today’s vendors have been creating scanners and other programs that will scan through a document and simultaneously assign keywords or try to classify artefacts according to a user defined metadata structure (metamodel).
Full-text searches scan documents from top to down, finding the words or parts of words that match the user’s selection. This type of search returns and recognizes textual artefacts comprising the selected terms and ranks them by the level of appropriateness according to the word frequency or how the words are combined in the relevant context.
Also known as faceted navigation or faceted browsing, is a technique used by eCommerce organizations to help their users analyze, organize, and filter large sets of product offerings based on filters such as size, color, price, and brand. Faceted search based on taxonomies will enable users to filter irrelevant search results to improve findability quickly.
Ideal situations for such search are the instances which vary by breadth vs depth of information. E-commerce that’s why presents the best use case for faceted search. However, this has limitations, as the search results don’t change based on user behavior.
The focus here is on the user – what does the user want to do or what do they want to find? In other words, how can search results be used for measuring the success of an intended action?
Action-oriented search shouldn’t be just a link to a vast data dump in a document. If the user must find one’s way through the actual information he needs, an action-oriented search isn’t successful.
Knowledge Graph-based search
A knowledge graph connects various information assets to people and people to other objects and defines the relationship between them. Over the period, based on the search experience, the search results improve. Also, a knowledge graph improves search by capturing the meaning of the search terms. That’s why Knowledge graph-based search is also called ‘semantic search’. They rely upon defined relationships between various objects to narrow down possible search results. These objects can be varied types of data sources.
A knowledge graph combined with the power of metadata and taxonomies powers semantic search, and the search results improve over time based upon the user feedback – which can be collected in various forms such as a thumbs-up/down, question at the end of the information and rating.
Fig: Knowledge graphs can connect data and content across RWS and 3rd party applications, providing deep visual feedback on knowledge relationships.
Building successful search
In other words, search has evolved from mere keywords to a conversation. We expect search to be an exchange and not a one-way interaction. The goal remains to make information more easily accessible and useful.
3 Key considerations for a successful search:
- Search is about things and not strings: what action are you enabling via that action or activity? When searching for an expert: a search is done to understand their expertise, contact them, where they are located, and where they work with or are associated with. So, an ideal search for finding an expert should only return a few links but all the relevant information to complete a user’s journey.
- Knowledge graph: a map of information across an organization and how it relates to each other.
Benefits of knowledge graphs:
- Understanding context: How things relate to each other.
- Natural language search: Store information on how people think, making search natural and easier
- Structure and unstructured information: integrating various forms of content allows searching multiple formats simultaneously.
- Aggregation: from multiple repositories in various formats
- AI and ML can be either rule-based or statistical. A good search shouldn’t be either or it can be both since both have the right use and time.
How Tridion can help with building powerful search experiences
If you want your organization to give its customers a better search experience – more like Google or Amazon— you need to build in semantics. This is equally applicable if your focus is on helping your employees to find what they need.
Tridion has built-in semantic AI. Semantic AI is a SaaS-based offering available for the various components of Tridion: Tridion Sites for Web Content Management, Tridion Docs for Structured Content Management, and Dynamic Experience Delivery for search and headless content publishing. It can be used both with on-premises and cloud-based deployments of Tridion.
A new module of Tridion, ‘Taxonomy Space’, allows companies to manage their underlying knowledge models based on open standards such as SKOS and EuroVoc.
There are multiple ways semantic AI will benefit organizations, and it can be used in many different use cases, such as:
- Self-service experience optimization
- Enterprise search-enabled workplaces
- Digital experience enhancements
- Recommender systems
- Conversational interfaces
To learn more about Tridion’s semantic AI capabilities, click here.
Additionally, you can also register for our webinar to be held in collaboration with CIDM on Using Structured authoring to publish videos at scale on 10th May 2023. Click here to register your spot.
RWS is the global leader in content management and translation technology and services. 90 of the top 100 global companies work with RWS.
Tridion, our composable Knowledge Management Platform (KMP) enables you to link together your various knowledge repositories and consolidate information management and semantic search for better employee and customer experiences.
Tridion provides easy web-based structured authoring & reviewing, streamlined end-to-end component content management, semantic AI and auto tagging, versioning, translation management and traditional as well as headless content publishing.
As a true collaborative environment with a familiar Microsoft Word-style interface, all subject matter experts (SMEs) in your organization can contribute their knowledge without technical or XML skills, while staff and customers can find the information they need.
Tridion supports global enterprise use cases including single sourcing, product documentation, learning and training, rules and regulations, policies and procedures, supported by efficient translations with delivery to multiple end points such as documents, PDFs, knowledge portals, Intranet, customer facing websites, apps, chatbots, and IoT devices, all governed by the required workflows and approvals.