Alphabetical list view of relevant generic Search, Bot-platform and SearchAssist platform specific terms:
Analytics
The analytics feature of the SearchAssist application provides real-time, interactive, and smart insights about the Search Assistant’s performance. Refer Performance Insights.
Business Rules
Business Rules feature allows you to define and apply those rules to personalize and fine-tune the search results based on contexts. Rules can also be used for merchandising and promotions. Refer Adding Business Rules.
Channel
A channel enables you to configure destinations for your Search Assistant to communicate with one or more channels. Refer Adding Channels.
Entity Extraction
Entity Extraction in virtual-assistants’ context refers to extracting the required information to accomplish the task via named entities or categories. The SearchAssist platform uses NLP techniques to find and track named entities from the source field. Refer Extracting Entities.
Experiments
Experiments are ways to test combinations of multiple index and search configuration variants and pick the best one that fulfills business needs. SearchAssist allows you to create and run experiments with two or more variants, analyze to continuously improve search relevance and user experience. Refer Adding Experiments
Facets
Facets allow users to define their own views by applying a unique set of filters, thus refining their search results by selecting relevant and multiple filters in parallel based on the field values. Refer Creating Facets.
Fields
Fields are key areas identified from the data sources that can be used in creating the search index schema for easy retrieval. For example, question and answer for an FAQ source, heading, and body for Files or Web content, etc. Refer Configuring Fields.
Field Mapping
Field Mapping is a stage in the Indexing Pipeline used to perform the customization mapping to the target field.
Indexing
Indexing is the technique by which search engines process information to give quick responses to users’ queries. SearchAssist’s search algorithm applies the inverted index process and by default, indexes all the data.
Index Configuration
Index Configuration allows you to configure the fields relevant to your business use cases so that the Search Assistant can handle documents and fields better, and customize the data and results accordingly. The index configuration involves the following processes:
- Define Fields as the properties from the data sources that you would want to be included or excluded from the index
- Define Traits to help identify specific entities or attributes that can be extracted from the users’ input
- Configure Indexing Pipeline Stages to transform the source content into optimized documents using the Workbench
- Train the Search Assistant to build the index based on the configurations especially after each update
Refer Managing Indices.
Indexing Pipeline
An Indexing Pipeline transforms the content into a document suitable for indexing. It consists of a series of configurable indexing pipeline stages. Each stage performs a set of different transformational operations on the data before passing the resulting content to the next stage in the pipeline.
Keyword Extraction
Keyword Extraction is a technique to automatically detect important words from the text stored in a field. Refer Extracting Keywords.
Kore.ai’s Virtual Assistant or bot
A virtual assistant application built on the Kore.ai bot-platform or Kore.ai’s Experience optimization platform.
Results Ranking
Results Ranking is an interactive and visual way to tune results. SearchAssist allows you to preview and customize the search results as per the business needs.Refer Tuning Results Ranking.
Result Templates
In SearchAssist, Result Templates decide the individual query results format in a search interface. In other terms, these templates allow you to decide how to display different types of items in a result list. Refer Designing Results Views.
Search Experience
Search experience can be customized and the way in which the results should be displayed to the search user can be configured so that the search users always see the results in a more meaningful way. Refer Designing Search Experience.
Search Interface
The Search Interface is a graphical user interface used by the search users to pose their queries.
Search Assistant
A Search Assistant is an application created using SearchAssist Platform to add and manage content, store index, configure and test various configurations, fine-tune relevance, define and apply business rules and deliver personalized search experience.
Semantic Analysis
Semantic analysis is the technique to understand the logical meaning and interpretation of words, signs, and sentence structure. Refer Applying Semantic Meanings.
Search Configuration
Search Configuration allows you to tune the results that are displayed to the user for specific queries. This helps in improving the user experience by allowing them to view the most relevant and useful results as per business requirements.
Sources
Sources hold the inputs for your Search Assistant. From sources ingest static content from files, databases. You can also map dynamic content from websites or the dynamic action prompts from the actively linked enterprise Virtual Assistants. Refer Managing Content Sources.
Synonyms ensure that the Search Assistant identifies your user queries more effectively by adding synonyms for keywords used in search queries.
Traits
Traits are specific associated attributes, or characteristics the users exhibit or express in their conversations. Traits have unique utterances that can lead to identifying intent. Extract traits from documents and user queries that help to increase the relevance score. Refer Configuring Traits
Workbench
Workbench combines the key aspects of the data indexing configuration process and transforms source content into transformed objects for indexing. It’s bundled with a Simulator that provides an interactive preview of how stage rules affect a document before it’s indexed. Refer Managing Indexing Pipeline.
Weights
Each field defined in the index configuration can be assigned a weight that plays an important role in ranking the results, these can be used to fine-tune the search relevance. Refer Assigning Weights.