cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 

Guides

Learn more about specific Flow features
Filter
Filter by Labels
Select any of the labels below to filter results.
Filters applied...
flow overview
Sorted by:
Entity annotation helps to extract useful data from the user inputs. Information is captured based on specific entity types such as time, location, currencies, other user details, etc. You can include these entities in the training examples or intents. The messaging bot detects these entity types, extracts the values, and triggers the user action/ information to complete the flow. MARK ENTITIES  automatically annotates all the entities in the selected intents, instead of the user selecting individual entities for each training example. Mark entities implement the list of existing entities that are visible in the Entity Type tab.   In the training example, only the words that match with the keywords and the synonyms of the entities are annotated. This reduces the user’s time and effort to annotate several entity keywords and synonyms manually and improves intent prediction accuracy.  As you can translate the entities in other regional languages, this auto-triggers the Mark Entities, the existing entities are annotated in the selected languages. By default, this also archives all the marked entities that are translated into different languages. You use this to mark the entities for the selected languages to create a  diversified conversational experience. For more information on Entity Annotation, see Data Extraction . 
View full article
by Khoros Staff Khoros Staff Feb 5, 2022
Labels (2)
0
295
Topic Matching helps to predict and then classify untrained data for further topic classification. These classifications are based on topic labeling, sentiments analysis, profanity detection, and spam detection.  Topic classification organizes unstructured data as similar to the Intent classification and does not require training data. In Khoros Flow, topic matching is initiated when Intent Classification fails to match with the user utterance. Some of the typical use cases for topic matching are: Listening bots (Agent Assist) Conditional fallback routing to human agents Flow matching (in addition to intents) With Topic Matching you can find any topic regardless of being implemented in a flow as a trigger or condition unless the Topic matching option is disabled.  Enable Topic Matching When the Enable topic matching is disabled the classification system can simply skip topic classification.  Note: The Enable topic matching option is disabled, by default, for existing projects and should be turned on for new projects (languages).  In a Flow, click Configuration. Click Languages. Select the Enable topic matching option. You can also translate topics for the selected Language . Like with Intent, topics can be disabled individually. When a topic is disabled, its statements, subjects, etc are no longer used in classification. Disabling the topic matching will result in the following: The topic overview screen to be hidden The topic trigger will not be shown The topic match rule for conditions will not be visible Manage Topics  Like with intents, topics can be managed within a separate view named Topics. You can not remove a topic when it is included in a Flow or condition.  With this release, Topics can be grouped like flows and entities. Each topic should have a logical name and statements when newly created. The statement should have a rule that defaults to the This message is about . The Subject of the rule will have the same value as used for the name of the topic. A topic can have multiple different statements, each statement can have multiple rules.  If all rules of a statement match, the topic is matched with a higher Confidence score that defines the accuracy of the topic matched. With Natural Language Processing (NLP), the topic matching will have its confidence level slider. The default value should be 90%. The range is between 1 and 99%. Add Topics Like with intent recognition, you can match flows based on topic classification.  In a Flow, drag and drop the Topic trigger. Enter a logical topic name.  Click Topics in the left panel.  Click + to add a topic.  Select either This message is about , Sentiments or Custom from the Hypothesis drop-down list.  Enter the Subject .  Select the Confidence level for the topic.   Click Save . Add Conditions  A Topic can also be used to match conditions. A perfect example is the use of topic matching when combined with an Unknown . You can add flow level conditions to match the topics. You can choose Topic as a rule for conditions.  Add Translations  You can also translate topics for the selected language.   If Topic match is enabled for one language, it should be enabled for any other language as well. In other words, you cannot enable it for some specific languages.  In a Flow, click Configuration. Click Languages. Click + to add more languages. Click Translate to automatically translate the topics. Select the translation language and region.  Click Next.  Click Start Translation.  The topics will be displayed in a new language tab.
View full article
by Khoros Staff Khoros Staff Mar 28, 2022
Labels (2)
0
326
Logs provide additional information to review, debug and troubleshoot bot conversations. It provides a self-service platform for the users to proactively analyze the cause of communication interruption if any. Previously, these conversations could only be accessed from the Khoros Care Agent View dashboard or Flow Chat view. With the new Flow Logs, you can view project interactions from the Logs window.  Enabling Flow Logs Flow users with the Logs permissions only can access the Logs feature. To add the Logs permission to a member: Click Profile From the drop-down option, click Members . Select your profile from the member list. Click Logs in the Update roles for window. Click Save Interaction overview The overview of all interactions shows the following info for each interaction: STATE: Whether an interaction is still open, resolved or has a runtime error CREATED AT:   Date when conversation initiated  UPDATED AT:  Date when conversation last activity was updated CHANNEL: Social channel or community on which the conversation was initiated THREAD ID: Conversation thread ID number CONV. ID:  Conversation ID number INTERACTION ID:  Khoros interaction ID number (if applicable) It is also possible to filter the list of interactions by the following:  Name of customer Thread ID or identifier of the customer Care conversation ID You can view the details of the conversation by clicking on any interaction. At a time, you can view 20 interactions in the tab, if you have more interactions you can scroll to use the pagination option to view older interactions.  The interaction overview does not automatically show any new interactions. Use the REFRESH button to update new interactions. Interaction details For each interaction, you can see detailed information about the activities taking place within each interaction. Activities are sorted by date (last updated first).  Actions are grouped by each trigger that has invoked the actions. For example, when a customer has sent some text that got matched by a flow, it returns a message, you can clearly see these grouped together.  You can also sort the activities by the time when they were created using the SORTED BY TIME filter option. The time is by default listed as UTC time. Use the timezone option at the bottom to view the activities in a local timezone.  With extremely long interactions, there is also an option to scroll to a specific time using the JUMP TO option.  For each individual trigger, action or event, you can view additional details by selecting them. Each event might show different contextual information. For example, a matched Flow by intent will also show the intents that got matched. The interaction details do not automatically show any new activities. Use the REFRESH button to update new activities.
View full article
by Khoros Staff Khoros Staff Aug 12, 2022
Labels (2)
0
133
This article explains definitions for all the Flow metrics captured in Flow Analytics. Flow Metrics  Flow analytics captures events that take place during user interaction with a chatbot. With each reported event, you can find an agent_id and thread_id . The agent_id relates to the Flow project and the thread_id relates to the interaction with a customer. When considering the Flow event metrics like interaction, handover or resolve, you might see small variants in the reported numbers; this is expected when you compare a metric for a specific period. Sometimes a user interaction can span a longer period than you are currently looking at, ensure that you are considering the correct timeframe.  Flow Analytics Dimensions Analytic events are separated into two dimensions: Thread and Brain events.  Thread events The following events are tagged with the thread events dimension when there is an interaction: Event Definition MESSAGE_IN Flow receives a message Note: This can be either from a customer, a moderator, or an agent (use the originator_role to distinguish). MESSAGE_OUT A reply is sent back by the automation LANGUAGE A language is detected (present in the language field) COUNTRY A country is detected (present in the language field) EVENT_OPENING An opening event is triggered (only supported by certain channels) EVENT_BROADCAST A broadcast is triggered PROJECT A new Flow project has been created ORGANISATION A new Flow organisation is created INTERACTION_NEW When a new interaction is created INTERACTION_UPDATED An existing interaction is updated RESOLVED_BY_BOT An interaction is resolved by the automation RESOLVED_BY_AGENT An interaction has been resolved by an agent TAKEOVER A takeover/handover is applied to an existing interaction TAG_ADD A tag is applied to a user TAG_REMOVE A tag is removed from a user USER_NEW A new user is registered Specific for voice: Event Definition VOICE_CALL_DISCONNECT A call is disconnected VOICE_CALL_HANDOVER A handover is applied for a call VOICE_CALL_CONFERENCE_END A call ends VOICE_CALL_AGENT_JOIN An agent joins a call VOICE_CALL_HOLD_ON A call is put on hold  VOICE_CALL_HOLD_OFF A call is put back from hold VOICE_CALL_AGENT_MUTE_ON An agent puts the call on mute VOICE_CALL_AGENT_MUTE_OFF An agent puts the call off mute Fields Field Description __time Date in a UTC format agent_id Flow project ID channel_id Connected channel or source ID channel_name Type of channel country Two-letter identifier of the region For example: us event_name Type of event  For example: MESSAGE_IN, TAKEOVER, USER_NEW, TAG_ADD language Two-letter language code  For example: en originator_role The originator’s role for the event For example: SYSTEM, EXTERNAL, MODERATOR, etc. tag_name Name of the tag that is applied tag_value Value of the tag that is applied thread_id Conversational thread between the bot and the customer resolution Reason of resolution attachment_event_name Event name that is triggered timestamp UNIX timestamp event_value Related Payload  campaign_id Broadcasted campaign care_conversation_id Care Conversation ID interaction_id Unique id for every interaction Brain events The following events are with the brain events dimension when there is an interaction: Event Definition FLOW_TRIGGERED A specific flow is triggered UNKNOWN_TRIGGERED An unknown message is received SENTIMENT AI estimated sentiment Note: You can find the Sentiment value in the Sentiment field. TAG_CREATED Old form of tags for thread params.  Note: You can find usage of it inside of text replies in the Advanced section in the right sidebar. Fields Field Description __time Date in a UTC format agent_id Flow project ID brain_name AI model flowai for single language model or flowaiv2 for multilingual model channel_id Connected channel or source ID channel_name Type of channel event_name Name of the event that is triggered flow_id Flow ID that is triggered  Note: This can change between versions flow_immutable_id Unique Flow ID that is triggered flow_name Name of the Flow that is triggered intent_id Intent ID that is matched  Note: This can change between versions intent_immutable_id Unique intent ID that is matched intent_label Name of the intent that is matched language Two-letter language code query The text utterance step_id Unique step ID that is matched step_name Name of the step that is matched step_type Type of the step that is matched  For example EVENT, INTENT, ANYTHING, NOTHING, etc.  thread_id Conversational thread between the bot and the customer accuracy AI confidence matched with an intent threshold Confidence threshold used for matching the intent timestamp UNIX timestamp
View full article
by Khoros Staff Khoros Staff Aug 29, 2022
0
153