{"id":40361,"date":"2022-04-08T18:17:44","date_gmt":"2022-04-08T17:17:44","guid":{"rendered":"https:\/\/developer.kore.ai\/v10-1\/?p=40361"},"modified":"2024-02-12T08:24:53","modified_gmt":"2024-02-12T08:24:53","slug":"performance-dashboard","status":"publish","type":"post","link":"https:\/\/developer.kore.ai\/v10-1\/docs\/bots\/analyzing-your-bot\/performance-dashboard\/","title":{"rendered":"Performance Dashboard"},"content":{"rendered":"
<\/div>\r\n\t
\r\n\t\t
\r\n\t\t\t

After you publish a Virtual Assistant (VA), you can monitor its performance using the Performance dashboard. The dashboard provides insights into metrics such as the number of intents identified, tasks completed successfully, and any service or script failures that occur during interactions. You can use these insights to identify areas where your virtual assistant needs improvement. For example, if you see that many intents are not identified, you can train the virtual assistant for those unidentified intents.<\/p>\n

To view the Performance Dashboard, click the Analyze<\/b> tab on the top menu and then click Performance Dashboard<\/b> in the left navigation. Select appropriate filters on the dashboard and click Apply<\/b>.
\n\"Performance<\/a><\/p>\n

Note<\/b>: Performance dashboard is available only post 9.2 release, i.e. post April 09, 2022.<\/div>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n<\/div><\/div><\/div><\/div><\/div><\/section>
<\/div>\r\n\t
\r\n\t\t
\r\n\t\t\t

Performance Dashboard Metrics<\/span><\/h2>\n

The Performance Dashboard provides insights to understand the virtual assistant\u2019s NLP performance and integration metrics. The Performance Dashboard is categorized into four categories to identify how a virtual assistant performs. These categories are mentioned below:<\/p>\n

Intent Identification Rate<\/span><\/h3>\n

This section of the dashboard provides the information of the number of intents that were classified and unclassified. An intent refers to the goal the customer has in mind when typing in a question or comment. While entity refers to the modifier the customer uses to describe an issue, intent is \u201cWhat they really mean\u201d<\/i>. To know more about intents refer here<\/a><\/p>\n

Below are the widgets that are used to provide insights:<\/p>\n\n\n\n\n\n\n\n
Metric<\/b><\/td>\nDescription<\/b><\/td>\n<\/tr>\n
Intent Identification Rate<\/span><\/td>\nA scorecard which displays the percentage and the number of intents that were identified in a duration. It also displays the percentage increase or decrease in identifying intents from the last selected period.<\/span><\/td>\n<\/tr>\n
Intent Identification Trend<\/span><\/td>\nA line chart that displays the total number of intents that were classified by the virtual assistant versus the total number of intents that were unclassified by the virtual assistant over a period of time.<\/span><\/td>\n<\/tr>\n
Popular Intents<\/span><\/td>\nDisplays a table with data insights on the number of times the virtual assistant identified the given intent from the user utterances in active and closed conversations.<\/span><\/p>\n

The following fields are displayed:<\/p>\n

    \n
  • Intent Name<\/b>: Name of the identified intent.<\/li>\n
  • Utterance Group<\/b>: The cluster name where similar utterances are grouped to which the identified intent is mapped.<\/li>\n
  • Count<\/b>: The count of identified utterances.<\/li>\n<\/ul>\n

    Note<\/b>: Clicking an intent name row displays a drill-down view of the relevant utterances, channel, user ID, Date & Time, and chat history.<\/td>\n<\/tr>\n

Popular Unidentified Utterances<\/span><\/td>\nA table that displays the number of utterances that did not identify an intent. The utterances are grouped by their similarity.\u00a0<\/span><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

Goal Completion Rate<\/span><\/h3>\n

The goal completion metrics provide insights as to how many tasks were completed in a period of time by a virtual assistant. This metrics shows all types of tasks which includes the completed tasks, abandoned tasks, incomplete tasks and failed tasks.<\/span><\/p>\n

Listed below are the widgets that could help in providing information about these details:<\/span><\/p>\n\n\n\n\n\n\n\n
Metric<\/b><\/td>\nDescription<\/b><\/td>\n<\/tr>\n
Goal Completion Rate<\/span><\/td>\nA scorecard which displays the percentage and the number of task executions that were successfully completed in a duration. It also displays the percentage increase or decrease in completing tasks from the last selected period.<\/span><\/td>\n<\/tr>\n
Goal Completion Trend<\/span><\/td>\nA line chart that plots the successful and failed task executions over a period of time.<\/span><\/td>\n<\/tr>\n
Task Performance<\/span><\/td>\nA table that provides insights of the number of successful and failed task executions per task for a selected duration.<\/span><\/td>\n<\/tr>\n
Failure Point Analysis<\/span><\/td>\nA table that displays the number of times a task has failed at various nodes.<\/span><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

API Execution Rate<\/span><\/span><\/h3>\n

This section of the dashboard provides the information of the number of APIs that were successfully executed and failed. While configuring a dialog task often there are needs to use a Service node that is used to make REST or SOAP requests to a third party web-services. To know more about service nodes refer <\/span>here<\/span><\/a>.<\/span><\/p>\n

Below are the widgets that are used to provide information about API performance:<\/span><\/p>\n\n\n\n\n\n\n
Metric<\/b><\/td>\nDescription<\/b><\/td>\n<\/tr>\n
API Performance Rate<\/span><\/td>\nA scorecard which displays the percentage and the number of service calls that were executed successfully. It also displays the percentage increase or decrease of APIs that were executed successfully from the last selected period.<\/span><\/td>\n<\/tr>\n
Service Execution Trend<\/span><\/td>\nA line chart that plots the trend of successful and failed service execution over a period of time.<\/span><\/td>\n<\/tr>\n
Service Performance<\/span><\/td>\nA table that displays the number of times a service node is executed, their status, and the average response time of executing the API.<\/span><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

Script Execution Rate<\/span><\/span><\/h3>\n

This section of the dashboard provides the information on the number of scripts that were successfully executed and also failed. A <\/span>Script <\/b>allows you to write JavaScript code in a dialog task. To know more about script nodes please refer <\/span>here<\/span><\/a>.<\/span><\/p>\n

Below are the widgets that are used to provide information about Script performance.<\/span><\/p>\n\n\n\n\n\n\n
Metric<\/b><\/td>\nDescription<\/b><\/td>\n<\/tr>\n
Script Performance Rate<\/strong><\/td>\nA scorecard which displays the percentage and the number of scripts that were executed successfully. It also displays the percentage increase or decrease of Scripts that were executed successfully from the last selected period.<\/span><\/td>\n<\/tr>\n
Script Execution Trend<\/strong><\/td>\nA line chart that plots the trend of successful and failed script execution over a period of time.<\/span><\/td>\n<\/tr>\n
Script Performance<\/strong><\/td>\nA table that displays the number of times a script node is executed, their status, and the average response time executing the script.<\/span><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

Script Performance<\/span><\/h3>\n

The following information on the Service Node execution is displayed in the Script Performance widget:<\/span><\/p>\n\n\n\n\n\n\n\n\n
Metric<\/b><\/td>\nDescription<\/b><\/td>\n<\/tr>\n
Task Name<\/b><\/span><\/td>\nThe name of the task executed for the preprocessor, service node, or postprocessor scripts.<\/span><\/td>\n<\/tr>\n
Node Name<\/b><\/span><\/td>\nThe name of the preprocessor, service script, and postprocessor nodes.<\/span><\/td>\n<\/tr>\n
Status<\/b><\/span><\/td>\nThe script execution status, Success<\/i> or Failed<\/i>.<\/span><\/td>\n<\/tr>\n
Count<\/b><\/span><\/td>\nThe task execution count.<\/span><\/td>\n<\/tr>\n
Avg. Response Time<\/b><\/span><\/td>\nThe average response time of the script or service in the total number of runs. For a Service Node, the Platform tracks and displays the Avg. Response Time separately for the execution of the Preprocessor script<\/b>, service script<\/b>, and Postprocessor script <\/b>nodes.<\/span><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

\"\"<\/a><\/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

Filter Criteria<\/span><\/h2>\n

The Performance Analytics Dashboard data can be viewed based on specific filter criteria that can be selected. Learn more<\/a>.<\/p>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n

<\/div><\/div><\/div><\/div><\/div><\/div><\/section>\n","protected":false},"excerpt":{"rendered":"After you publish a Virtual Assistant (VA), you can monitor its performance using the Performance dashboard. The dashboard provides insights into metrics such as the number of intents identified, tasks completed successfully, and any service or script failures that occur during interactions. You can use these insights to identify areas where your virtual assistant needs...","protected":false},"author":17,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[45],"tags":[],"class_list":["post-40361","post","type-post","status-publish","format-standard","hentry","category-analyzing-your-bot"],"_links":{"self":[{"href":"https:\/\/developer.kore.ai\/v10-1\/wp-json\/wp\/v2\/posts\/40361","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/developer.kore.ai\/v10-1\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/developer.kore.ai\/v10-1\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/developer.kore.ai\/v10-1\/wp-json\/wp\/v2\/users\/17"}],"replies":[{"embeddable":true,"href":"https:\/\/developer.kore.ai\/v10-1\/wp-json\/wp\/v2\/comments?post=40361"}],"version-history":[{"count":28,"href":"https:\/\/developer.kore.ai\/v10-1\/wp-json\/wp\/v2\/posts\/40361\/revisions"}],"predecessor-version":[{"id":61143,"href":"https:\/\/developer.kore.ai\/v10-1\/wp-json\/wp\/v2\/posts\/40361\/revisions\/61143"}],"wp:attachment":[{"href":"https:\/\/developer.kore.ai\/v10-1\/wp-json\/wp\/v2\/media?parent=40361"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/developer.kore.ai\/v10-1\/wp-json\/wp\/v2\/categories?post=40361"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/developer.kore.ai\/v10-1\/wp-json\/wp\/v2\/tags?post=40361"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}