{"id":22586,"date":"2019-10-03T07:42:23","date_gmt":"2019-10-03T06:42:23","guid":{"rendered":"https:\/\/developer.kore.ai\/v10-1\/?p=22586"},"modified":"2023-04-19T09:33:44","modified_gmt":"2023-04-19T08:33:44","slug":"knowledge-ontology","status":"publish","type":"post","link":"https:\/\/developer.kore.ai\/v10-1\/docs\/bots\/bot-builder-tool\/knowledge-task\/knowledge-ontology\/","title":{"rendered":"Knowledge Graph"},"content":{"rendered":"
<\/div>\r\n\t
\r\n\t\t
\r\n\t\t\t

A component of Kore.ai\u2019s XO Platform, the Knowledge Graph (KG), helps you turn static FAQ text into an intelligent, personalized conversational experience. It goes beyond the usual practice of capturing FAQs as flat question-answer pairs, allowing you to either build an ontology structure or leverage Kore.ai\u2019s LLM to simplify knowledge organization, maintenance, and training.<\/p>\n

Why a Knowledge Graph?<\/span><\/h2>\n

People express a query in multiple ways, so identifying all the options is complex. The XO Platform Knowledge Graph simplifies this process by either building an ontology structure or using an LLM model that does not require such an ontology.<\/p>\n

Knowledge Graph Types<\/span><\/h2>\n

There are two types of Knowledge Graphs:<\/p>\n

    \n
  1. The Ontology Knowledge Graph<\/b> lets you create an ontological structure of key domain terms and associate them with context-specific questions and their alternatives, synonyms, and Machine-Learning-enabled Traits.<\/li>\n
  2. The Few-Shot Knowledge Graph<\/b> leverages a Large Language Model (LLM) to simplify knowledge organization. Using this model, you are not required to build an ontology. All you need to do is add all FAQs to the root node\/term. This significantly reduces the complexity of building and maintaining an ontology structure.<\/li>\n<\/ol>\n

    Choosing Your Knowledge Graph Type<\/span><\/h2>\n

    Starting with v10.1.0 of the XO Platform, the Few-Shot Model is the default for all new Knowledge Graphs created under NLP V3 and in English.<\/p>\n

    If you have built your Ontology-based graph before this release, you can migrate to the new model anytime. You must upgrade to NLP V3 to use the Few-Shot Model. You can return to the Ontology model if you change your mind later.<\/p>\n

    You can select your desired Knowledge Graph Type by going to Build > Natural Language > Thresholds and Configurations > Knowledge Graph<\/b>.<\/p>\n

    \"\"<\/a><\/p>\n

    Changing Knowledge Graph Types is captured in the Change Logs, which you can access by going to Deploy > Change Logs<\/b>.<\/p>\n\n\n\n
    \n

    Important Note:<\/strong> Before changing your Knowledge Graph Type, we recommend backing up your existing knowledge graph by either creating a new bot version or by exporting a copy of your knowledge graph as a JSON or CSV.<\/em><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

    <\/br><\/p>\n

    Please continue reading to learn more about each type of knowledge graph. See Knowledge Graph Terminology<\/a> for in-depth information about Knowledge Graph features and components.<\/p>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n

    <\/div>\r\n\t
    \r\n\t\t
    \r\n\t\t\t

    The Ontology Knowledge Graph<\/span><\/h2>\n

    This type lets you organize FAQs using Default, Mandatory, and Organizer Terms\/Nodes, tags, synonyms, context, traits, and more.<\/p>\n

    Whenever someone asks your VA a question, the terms (node names) in the Knowledge Graph are checked and matched with keywords from the utterance. We call this process path qualification. Tags and synonyms are also checked, and based on the score they receive, questions are shortlisted as likely matches or intents. These shortlisted questions are then compared with the actual utterance to identify the response, which can be either a simple response or the execution of a dialog task.<\/p>\n

    You can also add completely different alternative questions to the FAQ and provide tags, synonyms, and terms appropriately such that any untrained question can also be matched. The performance and intelligence of the Knowledge Graph depend on the way you train it with the appropriate terms, tags, synonyms, etc.<\/p>\n

    Enable the Ontology Knowledge Graph<\/span><\/h3>\n

    To enable this Knowledge Graph type, go to Build > Natural Language > Thresholds and Configurations > Knowledge Graph<\/b>, and select Ontology Model<\/b> as the Knowledge Graph Type.<\/p>\n

    Before enabling the Ontology Knowledge Graph model, please consider the following:<\/p>\n

      \n
    1. You must build a Graph Ontology structure so the engine can qualify paths and compare them with query input. Each relevant term\/node is considered while identifying the appropriate FAQ, so you must regularly maintain the node structure to facilitate optimum performance.<\/li>\n
    2. The model supports three types of terms<\/a>: Default, Mandatory,<\/em> and Organizer<\/em>.<\/li>\n
    3. The Ontology Model also supports other features such as Traits, Patterns, Path Synonyms, KG Synonyms, Bot Synonyms, Preconditions, and more. Please see the Comparison Table below for a detailed list of supported features. Also, see Knowledge Graph Training<\/a> for configuration details.<\/li>\n<\/ol>\n

      How It Works<\/span><\/h3>\n

      The Ontology Knowledge Graph engine uses a two-step approach while extracting a response. It combines a search-driven intent detection process with rule-based filtering. The settings for path coverage (percentage of terms needed) and term usage (mandatory or optional) in the user utterance help in the initial filtering of the FAQ intents. Tokenization and the n-gram-based cosine scoring model help fulfill the final search criteria.<\/p>\n

      When a new utterance reaches the Ontology Knowledge Graph:<\/p>\n