{"id":51176,"date":"2023-01-16T05:46:24","date_gmt":"2023-01-16T05:46:24","guid":{"rendered":"https:\/\/developer.kore.ai\/v10-1\/?p=51176"},"modified":"2023-11-03T06:43:54","modified_gmt":"2023-11-03T06:43:54","slug":"intent-discovery","status":"publish","type":"post","link":"https:\/\/developer.kore.ai\/v10-1\/docs\/bots\/intent-discovery\/","title":{"rendered":"Intent Discovery (Beta)"},"content":{"rendered":"

The new Intent Discovery module helps you auto-extract popular intents from previous user conversations. It reduces the time and effort to build a virtual assistant and leads to the success of your Conversational AI Journey. This is a beta feature and is available only for the English language and Enterprise users.<\/p>\n

You can upload your historical transcripts in CSV format. After the transcripts are uploaded into the bot, the bot uses LLMs to identify the different topics, intents, or conversations between the user and the bot. It intelligently identifies all the intents available. You can review each intent to understand which conversations have resulted in identifying these intents. After the review, you can also see the underline utterances that resulted in identifying an intent. You can either add these intents as new intents for your virtual assistant or pick specific utterances and train them as utterances for your existing dialogs and FAQs. So, it helps both ways \u2013 either create new intents or enhance the training you provide to your virtual assistant.<\/p>\n

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

The Intent Discovery journey consists of the following steps:<\/p>\n

    \n
  1. Create a Project<\/a>: You may have many business use cases to automate. Projects help manage intent discovery for each business use case separately \u2013 a project for a specific use case.<\/li>\n
  2. Upload Transcripts<\/a>: Upload your use case-specific historical transcripts in CSV format. Conversations are extracted from the uploaded transcripts.<\/li>\n
  3. Extract Intents:<\/a> Intents and training data are extracted from the conversations.<\/li>\n
  4. Train the Utterances<\/a>: to create new intents or add them as training data: You can add new intents as dialogs or FAQs or train them for existing dialogs or FAQs.<\/li>\n<\/ol>\n

    Create a Project<\/span><\/h2>\n
      \n
    1. Go to Build <\/b>> Tools <\/b>> Intent Discovery<\/b>.
      \n      \"\"<\/a><\/li>\n
    2. Click the Create Project<\/b> button.<\/li>\n
    3. Enter a name and a brief description of the project. Note that the character limit for Project Name is 256, and Description is 1000.<\/span>\u00a0<\/span>
      \n      \"Intent<\/a><\/li>\n
    4. Click Proceed<\/b>. The new project is created. You see the Intent Discovery page with the header Projects \/ {{New Project\u2019s Name}}<\/strong>.
      \n      \"\"<\/a>
      \n<\/span><\/li>\n<\/ol>\n

      The Intent Discovery landing page lists all the projects with conversational insights for each project, such as the status of the project, number of sessions, intents extracted, and Results in terms of added dialogs, added FAQs, trained dialogs, and trained FAQs. Note that the result will be NA for the projects for which intent extraction is incomplete.<\/span><\/p>\n

      The status of a project can be any of the following, displayed in the Status column:<\/span><\/p>\n