Free Oracle Cloud Platform Digital Assistant 2021 Specialist Exam 1Z0-1071-21 Exam Practice Test

Forlive-agenttransfer,you wantthebot-user conversation historyto becomeavailableto the humanagentthat theconversation istransferredto. Howdoyoumakethisconversationhistoryavailable?

• Inthe skillsettings,either switch EnableInsights to On orswitch SkillConversation to On,depending on theDigital Assistant version.
• Thisiscontrolled from OracleServiceCloud and hastobe turnedonbysetting acustomproperty.
• Setacustompropertyon the OracleServiceCloudinstancethat's accessedbyOracleDigitalAssistant.
• SettheconvHistorypropertyinthesystem.Agentinitiationcomponent.

What happens if there is a system error and the state does not have an error action?

• The skill transitions to the state that is defined by the defaultTransitions error action. If there isn't one, then it outputs the Unexpected Error Prompt value.
• The skill transitions to the state that is defined by the next action. If there isn't one, then it transition to the defaultTransitions error action.
• The skill transitions to the state that is defined by the next action.. If there isn't one, then it transitions to the next state in the dialog flow.
• The skill outputs the Unexpected Error Prompt value and then transitions to the state that is defined by the defaultTransitions error action. If there isn't one, then it ends the conversation.

You are advised to implement an 80/20 split with training and test utterances. This means that 80% of new utterances harvested from the conversation logs should be used as intent training utterances and 20% for testing.Why is this a good practice?

• Adding 100% of user phrases to the intent would overload the model.
• Batch testing works more efficiently when there is a ratio of one test utterance for every five training utterances.
• By performing an 80/20 split, you are randomizing which data is added to the utterances.
• By keeping 20% for testing, you are able to test the model with data on which it has not been specifically trained.

You have a use case that calls for users to enter a series of complex values.What would you do to ensure that users enter these values correctly with the least effort?

• Create a composite bag entity for the types of values, and then add a regex entity to handle validation.
• Use a system.commonResponse component to aggregate and validate user input.
• Create a webview service which connects the skill to a web app that renders as a form and provides features such as input validation and option buttons.
• Create a dedicated skill for collecting and validating input and pair it with a skill for processing the validated input.

When testing your skill, you notice that two of its intents consistently rank as the top two, resolving within just a few points of each other.Given the unpredictable nature of which intent gets the top score, what would you do to allow the skill user to choose the correct intent?

• Change the Confidence Win Margin so that both intents are offered to the user.
• Change the Confidence Threshold during your testing until the correct intent always wins.
• For each intent, create an entity of phrases that are distinct to each intent, and add the appropriate entity to the corresponding intent.
• Keep adding training data until you get a predictable result every time.
• Change the Explicit Invocation Threshold to zero to ensure that the correct intent is picked up when the user mentions the name of the intent.

Which two features of Oracle Digital Assistant should you use to allow a skill to specifically classify the user message "What's my balance in savings?" and to identify the type of account?

• an entity that defines account types (with values such as "checking" or "savings")
• an intent that is been trained with utterances such as "check balance", "What is my current balance?", and "How much money do I have?"
• an input form rendered by a webview that is hosted within a Digital Assistant
• dialog flows with a system.Text component to read the user input
• a resource bundle populated with phrases such as "check balance", "What is my current balance?", and "How much money do I have?"

Which three statements are true about composite bag entities?

• They define a business domain object as a collection of related system entities and custom entities.
• When you add entities to the composite bag, you can control how they get extracted in related to other entities and when they are prompted for.
• The composite bag will always enforce that every entity has a valid value before allowing the conversation to move on to the next state in the dialog flow.
• You need to create a separate composite bag to handle nonentity types such as strings. Locations, and attachments.
• The composite bag can resolve all entity values using only a single state in the dialog flow.

Youwantyourskilltooutputthesizeofthepizzathatwasordered.. Which FreeMarker operation must you use

• "You ordered a${size[0]} pizza." 3)
• "You ordered a ${size} pizza." 🙂
• "You ordered a ${size.value} pizza.
• "You ordered a ${size.string} pizza."

Youhavea usecasethat calls foruserstoenteraseriesofcomplexvalues. What wouldyoudoto ensurethatusers enterthese values correctly with the least effort?

• Create a compositebagentityfor thetypesofvalues,and then adda regexentity tohandlevalidation.
• Use asystem.commonResponsecomponenttoaggregateand validateuserinput.
• Createa webviewservicewhichconnectsthe skilltoa webappthat renders as a form andprovidesfeatures such asinputvalidation andoptionbuttons.
• Createa dedicated skillforcollecting and validatinginputandpairitwith a skillforprocessingthe validatedinput.

Which statement is FALSE regarding the core function of a digital assistant and how it could respond to user input?

• It is able to automatically route the conversation to another digital assistant if the request can't be handled by the current digital assistant.
• It is able to respond to a user request to exit the current conversation.
• It is able to respond to a help request and return a help message, one that can be specific to one of its skills, or to the digital assistant itself
• It is able to route the conversation to the start state of a skill that's managed by the digital assistant.