Genesys Voicebots (CE41) for Genesys Cloud
What's the challenge?
When your customers call in to self-service or need an agent, they want to get off the phone as soon as possible. Traditional IVRs confuse, frustrate and are simply unfriendly to use. This causes frustration and leads to longer agent interactions.
What's the solution?
Deliver a great experience and increase your operational efficiency by using the ease of use of a voice bot that leverages natural language processing.
- 1 What's the challenge?
- 2 What's the solution?
- 3 Use Case Overview
- 4 Use Case Definition
- 5 User Interface & Reporting
- 6 Customer-facing Considerations
- 7 Related Documentation
Use Case Overview
Story and Business Context
Natural Language Understanding (NLU) allows customers to speak in their natural language without having to repeat specific keywords that may or may not align with the customer's intent. With the evolving functionality of artificial intelligence tools such as Alexa, Siri, and the like, customer begin to see these types of interactions as the norm. Contact centers are a natural progression into this world of virtual assistants.
When a customer can speak naturally, the company can better understand the intent of a customer and then more quickly route the call to a highly skilled agent. Voicebot integration within Genesys Cloud enables customers to utilize NLU within inbound synchronous customer interaction flows.
Voicebots can alleviate strain on contact center employees while improving the customer experience and controlling costs. Voicebots are always on and available, and can be handed over to an agent at any time needed. While Voicebots can also be used by employees and for business optimization purposes, the remainder of this document refers to omnichannel bots in the context of customer engagement. The primary benefits of bots are to increase self-service success, deflect interactions from the contact center, and improve the customer experience. Benefits typically include:
Use Case Benefits*
The following benefits are based on benchmark information captured from Genesys customers and may vary based on industry, lines of business or Genesys product line:
|Use Case Benefits||Explanation|
|Improved Customer Experience||Reduce the time required to address the customer request, handle off-hour contacts, offer immediate options, and improve outcomes.|
|Improved First Contact Resolution||Use NLU to improve the identification of customer intent to serve the customer best. Tailor the customer experience to the individual based on who they are, why they could be interacting, and the status of the contact center.|
|Reduced IT Operational Costs||Reuse of existing assets and the option to use less expensive speech alternatives.|
|Reduced Volume of Interactions||Increase self-service interactions to reduce agent-assisted interactions for repetitive or common requests.|
Genesys supports a “design once, deploy anywhere” concept for bots to enable organizations to provide a seamless customer experience across voice and digital channels. This use case, however, focuses on deploying a bot on voice.
During a call, the customer uses NLU to either easily get to an appropriate agent or obtain the information and assistance they need without engaging an agent.
The voicebot supports or orchestrates the following capabilities:
- Use NLU to derive intents and slots.
- Stream the customer response to the voicebot for processing. The voicebot recognizes the intent, understands its meaning, and captures key information into slots. These slots are then passed back to Genesys Cloud Architect for further processing.
- Delegate to an agent to connect the customer to a live person with the full context of the interaction.
Simple bot orchestration enables customers to use the best bot for the job. For example, Google Dialogflow has the highest alphanumeric recognition rates. Also:
- Genesys Cloud Architect makes it easy to integrate to new bot providers, switching between bot providers or using multiple bot providers within a single interaction.
- A-B testing with Genesys Cloud Architect helps determine which bot is most effective for a particular business use case.
- Graceful escalation to a live agent at the right time.
Use Case Definition
When a customer calls Genesys Cloud, a Voicebot can be initiated. The system asks the customer an open question, such as "How may I help?".
After the customer responds, the Voicebot attempts to interpret the intent of the request and then decides the next step. For example, if the customer replies, "I want to check the status of my flight," then the Voicebot prompts the user for a flight number to fill the required slot for the intent. Once, the intent is detected and all the slots are filled the call returns to the Genesys IVR for fulfillment. For example, a back-end web-service call on the flight number can be used to return the flight status which is then played back to the caller.
If the Voicebot cannot establish or understand the customer's intent, the system routes the call to an agent.
After the Voicebot task ends, the Genesys IVR asks if the customer needs any additional help. The customer can ask another question, request to speak to an adviser, or indicate that no further assistance is needed. If the customer needs no further assistance, the call ends.
If the customer chooses to speak or chat with an agent but faces a long wait-time to reach an agent, or the request.
Business Flow Description
- An inbound call interaction starts.
- The customer receives a standard welcome message from the system.
- The system asks an open-ended question. For example “How may I help you?” to determine intent and capture the customer's response. One intent is always "I want to speak to an agent." (BL1)
- The customer response routes to the voicebot. The voicebot converses with the customer to determine intent. The voicebot prompts the customer, as needed, to determine intent and collect all required slots. If intent is recognized and slots are returned, the conversation moves to the correct point in the flow. Otherwise, after a configured number of retries, return a failure message. (BL2, BL1, BL3)
- If the flow steers to fulfillment for the intent, then the system uses the slot information returned from the voicebot to complete fulfillment for the intent.
- After the task ends, the system asks if the customer needs further assistance. The voicebot can be called on again. The greeting for the second and subsequent invocations can be customized.
- If the customer replies that they require no further assistance, the system presents a good-bye message and ends the call.
Business and Distribution Logic
BL1: Agent Handoff: The customer asks to connect to an available agent. At that point, the voicebot disconnects and the customer context data appears in the agent desktop.
BL2: Retries: In the voicebot management interface, configure the number of retries for self-service tasks and questions. Configure the dialog to, upon maximum retries, present a message, or hand-off to an agent. Or through IVR configuration, offer a callback if the agent is busy or the request is outside business hours through IVR configuration.
BL3: Response Type: Configure the interaction flows to accept natural language responses and closed responses such as account number, date of birth, and yes or no questions. This process means that customers can backtrack to a different point in the dialogue when required. For example, if a customer is midway through getting flight information and says, “actually just tell me where your nearest ticket counter is,” then voicebot informs the customer of the location of the nearest counter.
Parameters influencing voicebot behavior
This use case is supported across industry verticals. The basic features of voicebot business logic, such as personalization, are parameterized. Example parameters include:
- Intents: The goal of the interaction. For example, a "switch flight" intent returned by the NLU indicates that the customer should receive a payment business process.
- Slots. More pieces of key information returned by the NLU. These pieces can accelerate the conversation by prepopulating answers to subsequent questions.
- Based on user choice, such as "I want to speak to an adviser."
- Based on default handling, such as retries, timeouts, and global commands.
- Based on application logic, such as the customer owes money and application decides to transfer.
There are three possible ways for the flow to end with a transfer to ACD after a voicebot:
- The caller requests live Agent assistance.
- The voicebot failure path steered the call to ACD.
- The path for a particular intent steered the call to ACD.
User Interface & Reporting
There is no applicable content for this section.
There is no applicable content for this section.
Administrators and contact center managers use flow outcomes to gather data about self-service success. This information helps determine how well Architect flows service the customer interaction and includes:
- The total number of interactions that start a self-service operation.
- The number and percentage of interactions that fail the self-service operation.
- The number and percentage of interactions that successfully complete the self-service operation.
- The length of time successful interactions spend in the self-service operation.
All required, alternate, and optional use cases are listed here, as well as any exceptions.
|All of the following required:||At least one of the following required:||Optional||Exceptions|
- The customer's response is streamed to the voicebot for processing. The voicebot recognizes the intent, understands its meaning, and captures key information into slots. These slots are then passed back to Genesys Cloud Architect for further use.
Third-Party Voice Bots
- Third-party voicebot is enabled via the Integrations Registry and informational through AppFoundry.
- Customers use their own third-party voicebot accounts for Integration Services.
- Third-party voice bots are not PCI-compliant and cannot be used in secure flows.
- Region and Language limitations are detailed in the Amazon Documentation.
- Lex integration is not HIPAA-compliant.
- Dialogflow Language support is detailed in the Google Documentation.
- Dialogflow integration is not HIPAA-compliant.
- Voicebot configuration and settings are quoted as part of a Professional Services engagement to capture requirements and business logic.
- Version V 1.0.1 last updated February 23, 2021