Robot Reply

Parameter Description

• Node Name: name of a node.
• Description: details of a node.
• Reply Way: The options are Static voice, TTS, Video, Multimedia, Card, Voice and text, Variable voice, and WhatsApp Interactive Messages.
  NOTE:

  Currently, variable voices do not support recording in IVR flows.

  • Static voice: The voice file on the voice file server is played directly. This type is used in scenarios where the context is unchanged. Make sure that the voice file exists on the UAP file server.
  • TTS: The configured text is provided for the TTS for conversion and playback. Variables can be added to the reply text, and the TTS dynamically plays a voice based on the return values of the variables.
  • Video: name of a video file on the file server.
  • Multimedia: The configured multimedia information is provided for the corresponding player through a channel gateway. This option is displayed only in the integration environment.
  • Card: The configured card information is provided for a channel gateway for playback. This option is displayed only in the integration environment.
  • Voice and text: Voice files and texts are combined and then played.
  • WhatsApp Interactive Messages support interaction between robots and WhatsApp.
  • Variable voice: Set Language, Type, and Reply Variable to dynamically play a UAP voice package.
    1. Language: Multiple languages are available.
    2. Type: Select a voice playback type. The options are Phone number, Number, time(hh:mm:ss), Date(yyyymmdd), and Price.
• Reply Source: source of the voice content to be played. The options are Reply Template, Reply Variable, and Reply Resource.
• Reply Template: This parameter is displayed when Reply Source is set to Reply Template. Select a content template configured on the Configuration Center > Chatbot Management > Flow Configuration > Resource > Resource Template page.
  1. If Reply Way is set to Multimedia and Reply Template is set to Plain Text, the corresponding parameter values are displayed. To set the plain text content, choose Configuration Center > Resource Management > Multimedia Library > Plain Text.
  2. If Reply Way is set to WhatsApp Interactive Messages, only the WhatsApp interactive message template configured under Resource > Resource Template can be used as the reply template. To set the template content, choose Configuration Center > Resource Management > Multimedia Library > Card Template > WhatsApp Interactive Messages. Then, the parameter values to be set are displayed on the right.
  3. The parameter values in the reply template must be enclosed in quotation marks, as shown in the following figure.
     Figure 1 Variable value
     
• Reply Variable: This parameter is displayed when Reply Source is set to Reply Variable. Select a reply variable.
  1. If Reply Way is set to Voice and text, set this parameter in {Recording file URL}~${Text}$~{Recording file URL}~${Text}$ format, for example, /xxx/xx1.wav~$abc$~/xxx/xx2.wav. In the format, {Text} cannot contain variables. The value can contain a maximum of five voice and text records.
  2. When Reply Way is set to Static voice, set this parameter in the {Voice file URL} format, for example, /xxx/xx1.wav.
• Reply Resource: This parameter is displayed when Reply Source is set to Reply Resource. Select a resource configured on the Configuration Center > Resource Management > Audio and Video or Configuration Center > Resource Management > Multimedia Library page.
• Reply Mode: This parameter is mandatory. The options are as follows:
  • Playback only: Only the voice or video is played, and customer input does not need to be received. Generally, this option is selected for static voice playback.
  • Interruption recognition: The customer needs to answer by voice. Generally, this option is selected for replying to text.
  • Interruption by key presses: The keys pressed by the customer need to be obtained. If Reply Mode of the Robot Reply diagram element is set to Interruption by key presses and the key interaction result needs to be obtained, the Robot Reply diagram element cannot be directly connected to the Call Ending diagram element, and the Key Recognition and Semantic Recognition diagram elements cannot be directly connected before the Call Ending diagram element.
  • Recognition and key presses: Both voice and key information can be received. The information received first is used for matching.
  • Recognition after playback: The system starts to identify the voice or video only after the voice or video is played. If a customer speaks during the playback, the system does not receive the voice.
  • Recognition and key presses after playback: The system starts to identify the voice or video and collect digits only after the voice or video is played. If a customer speaks or presses a key during the playback, no information can be received. If a customer speaks or presses a key after the playback, the information that is received first is used for matching.
  • No interruption after digit collection: Keys can be pressed when the voice or video is played, but the playback is not interrupted.
  • Custom Variable Value: whether voice playback can be interrupted. If voice playback can be interrupted, set Minimum Voice Playing Duration.

    String true -- Voice playback can be interrupted during recognition, and the minimum voice playback duration can be passed.

    String false -- Recognition is performed after voice playback.

• Timeout Interval: timeout period, in seconds. If this parameter is not set, the default value 15 is used. If the duration exceeds the value of this parameter, the system determines that timeout occurs. The value range of this parameter varies with vendors. Currently, the maximum value is 180.
  • If Reply Mode is set to Recognition after playback, the duration starts from the time when the TTS voice playback ends to the time when the recognition stops.
  • If Reply Mode is set to Interruption by key presses or Interruption recognition, the duration starts from the time when the voice playback ends. For example, if a customer does not speak after the TTS voice playback ends, the robot goes to the next diagram element when the timeout period ends.
  • If Reply Mode is set to Playback only, the timeout period does not take effect.
  NOTE:

  Pay attention to the setting of the timeout period in the following scenarios: long TTS voice playback, many keys (such as an ID card) to be pressed by a customer, and many opinions to be said by a customer. When Reply Mode is set to Interruption by key presses or Interruption recognition, if the timeout period is short, the recognition may start before the voice playback ends, or the recognition may end before the customer completes key pressing. If the timeout period is long, there may be a long-time silence after the customer completes key pressing, and a timeout notification is displayed after a long time.

  Robot Message Reply Timeout Processing

  • waitFlag: session identifier. If the value of timeout is less than the remaining timeout period of the current session, the value of waitFlag is true. Otherwise, the value is false.
  • waitTimeout: message timeout period.
  • waitBeginTime: When the value of waitFlag is true, the value of waitBeginTime is set to the current time.
  • When the value of waitFlag is true, reply timeout is processed. When the value of waitFlag is false, the original message processing logic is used.
  • Processing logic: After a message times out, the CC-Messaging triggers the timeout flow and pushes the robot response to the customer.
• Extended Parameter: Enter data required by the IVR, for example, the provider information. The value is sent back to the IVR using the vendor parameter of the dialog interface. This interface is available only to the Robot Reply diagram element in historical flows. If an old flow uses this parameter, you are advised to enter the value of this parameter in the ASR Extended Parameter text box.
• Number of Collected Digits: maximum number of collected digits in the IVR system. This parameter is displayed when Reply Mode is set to Interruption by key presses, Recognition and key presses, or No interruption after digit collection.
• Digit collection timeout: Timeout interval for pressing a key. For example, if this parameter is set to 2 seconds, the flow proceeds when the key pressing interval exceeds 2 seconds, even though the number of collected digits does not reach the specified value.
• Cancel Key: whether to use the star key (*) as the cancel key during IVR digit collection. This parameter is displayed when Reply Mode is set to Interruption by key presses, Recognition and key presses, or No interruption after digit collection.
• Confirm Key: whether to use the pound key (#) as the confirm key during IVR digit collection. This parameter is displayed when Reply Mode is set to Interruption by key presses, Recognition and key presses, or No interruption after digit collection.
• TTS Advanced Settings: Enable or disable this function. By default, this function is disabled.
• Voice: The options are Male, Female, and Custom Sound Effect. The default value is Female. This parameter is configurable when TTS Advanced Settings is enabled.
• Voice Speed: The options are Slow, Medium, Fast, and Custom Speed. The default value is Slow. This parameter is configurable when TTS Advanced Settings is enabled.
• Default Values for Extended TTS Parameters.: Enable or disable this function. By default, this function is disabled.
• TTS Extended Parameter: Enter the data required by the TTS business on the IVR side, for example, the vendor information. The value is sent back to the IVR using the ttsMRCPVendor parameter of the dialog interface.

  Extended parameter of the TTS server. Set this parameter based on the requirements of the TTS server vendor. The values of speed, pitch, volume, and voice_name can be GLOBAL and FLOW variables of the character type or any character string. If the value of a variable is not within the standard range, the default value is used.

  The default values and format requirements are as follows:

  speed=GLOBAL.ttsSpeed;pitch=GLOBAL.ttspitch;volume=GLOBAL.ttsVolume;voice_name=GLOBAL.voiceName;
  1. The value of speed ranges from –500 to 500. The default value is 0.
  2. The value of pitch ranges from –500 to 500. The default value is 0.
  3. The value of volume ranges from 0 to 100. The default value is 50.
  4. The default value of voicename is cn_kefuman_common.
     NOTE:

     • To use the TTS function, you need to contact the system administrator to sign in to the AICC, choose Configuration Center > Chatbot Management > Flow Management > System > TTS/ASR, and configure a TTS server for your tenant space.
     • To set the default values of extended parameters of the TTS server, contact the tenant administrator to sign in to the AICC and choose Configuration Center > Chatbot Management > Flow Configuration > Resource > Variable > Built-in Variable.
• ASR Advanced Settings: Enable or disable this function. By default, this function is disabled.
• Recognition Type: The option is Common. The default value is Common. This parameter is configurable when ASR Advanced Settings is enabled.
• Subscriber Silence Timeout Interval: The default value is 100, in seconds. The value ranges from 0 to 32000. This parameter is configurable when ASR Advanced Settings is enabled.
• Recognition Timeout Interval: The default value is 200, in seconds. The value ranges from 0 to 600. This parameter is configurable when ASR Advanced Settings is enabled.
• Subscriber Pause Timeout Interval: The default value is 500, in milliseconds. The value ranges from 300 to 2000. This parameter is configurable when ASR Advanced Settings is enabled.
• ASR Extended Parameter: Enter the data required by the ASR business on the IVR side, for example, the vendor information. The value is returned to the IVR system using the vendor parameter of the dialog interface.